[Pcre-svn] [1066] code/trunk: Allow non-ASCII in group names…

Páxina inicial
Borrar esta mensaxe
Autor: Subversion repository
Data:  
Para: pcre-svn
Asunto: [Pcre-svn] [1066] code/trunk: Allow non-ASCII in group names when UTF is set; revise group naming terminology
Revision: 1066
          http://www.exim.org/viewvc/pcre2?view=rev&revision=1066
Author:   ph10
Date:     2019-02-06 18:11:36 +0000 (Wed, 06 Feb 2019)
Log Message:
-----------
Allow non-ASCII in group names when UTF is set; revise group naming terminology 
in documentation to use "capture group", as Perl does.


Modified Paths:
--------------
    code/trunk/ChangeLog
    code/trunk/doc/html/pcre2_substring_nametable_scan.html
    code/trunk/doc/html/pcre2api.html
    code/trunk/doc/html/pcre2callout.html
    code/trunk/doc/html/pcre2compat.html
    code/trunk/doc/html/pcre2limits.html
    code/trunk/doc/html/pcre2pattern.html
    code/trunk/doc/html/pcre2perform.html
    code/trunk/doc/html/pcre2syntax.html
    code/trunk/doc/html/pcre2test.html
    code/trunk/doc/html/pcre2unicode.html
    code/trunk/doc/pcre2.txt
    code/trunk/doc/pcre2_substring_nametable_scan.3
    code/trunk/doc/pcre2api.3
    code/trunk/doc/pcre2callout.3
    code/trunk/doc/pcre2compat.3
    code/trunk/doc/pcre2limits.3
    code/trunk/doc/pcre2pattern.3
    code/trunk/doc/pcre2perform.3
    code/trunk/doc/pcre2syntax.3
    code/trunk/doc/pcre2test.1
    code/trunk/doc/pcre2test.txt
    code/trunk/doc/pcre2unicode.3
    code/trunk/src/pcre2_compile.c
    code/trunk/src/pcre2_error.c
    code/trunk/src/pcre2test.c
    code/trunk/testdata/testinput10
    code/trunk/testdata/testinput4
    code/trunk/testdata/testinput5
    code/trunk/testdata/testoutput10
    code/trunk/testdata/testoutput11-16
    code/trunk/testdata/testoutput11-32
    code/trunk/testdata/testoutput12-16
    code/trunk/testdata/testoutput12-32
    code/trunk/testdata/testoutput15
    code/trunk/testdata/testoutput16
    code/trunk/testdata/testoutput17
    code/trunk/testdata/testoutput2
    code/trunk/testdata/testoutput20
    code/trunk/testdata/testoutput21
    code/trunk/testdata/testoutput22-16
    code/trunk/testdata/testoutput22-32
    code/trunk/testdata/testoutput22-8
    code/trunk/testdata/testoutput3
    code/trunk/testdata/testoutput3A
    code/trunk/testdata/testoutput3B
    code/trunk/testdata/testoutput4
    code/trunk/testdata/testoutput5
    code/trunk/testdata/testoutput6
    code/trunk/testdata/testoutput7
    code/trunk/testdata/testoutput8-16-2
    code/trunk/testdata/testoutput8-16-3
    code/trunk/testdata/testoutput8-16-4
    code/trunk/testdata/testoutput8-32-2
    code/trunk/testdata/testoutput8-32-3
    code/trunk/testdata/testoutput8-32-4
    code/trunk/testdata/testoutput8-8-2
    code/trunk/testdata/testoutput8-8-3
    code/trunk/testdata/testoutput8-8-4
    code/trunk/testdata/testoutput9


Modified: code/trunk/ChangeLog
===================================================================
--- code/trunk/ChangeLog    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/ChangeLog    2019-02-06 18:11:36 UTC (rev 1066)
@@ -121,7 +121,10 @@
 tests such as (?(VERSION>=0)...) when the version test was true. Incorrect 
 processing or a crash could result.


+30. When PCRE2_UTF is set, allow non-ASCII letters and decimal digits in group
+names, as Perl does.

+
Version 10.32 10-September-2018
-------------------------------


Modified: code/trunk/doc/html/pcre2_substring_nametable_scan.html
===================================================================
--- code/trunk/doc/html/pcre2_substring_nametable_scan.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2_substring_nametable_scan.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -27,8 +27,8 @@
 </b><br>
 <P>
 This convenience function finds, for a compiled pattern, the first and last
-entries for a given name in the table that translates capturing parenthesis
-names into numbers.
+entries for a given name in the table that translates capture group names into
+numbers.
 <pre>
   <i>code</i>    Compiled regular expression
   <i>name</i>    Name whose entries required


Modified: code/trunk/doc/html/pcre2api.html
===================================================================
--- code/trunk/doc/html/pcre2api.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2api.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -49,7 +49,7 @@
 <li><a name="TOC34" href="#SEC34">EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS</a>
 <li><a name="TOC35" href="#SEC35">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a>
 <li><a name="TOC36" href="#SEC36">CREATING A NEW STRING WITH SUBSTITUTIONS</a>
-<li><a name="TOC37" href="#SEC37">DUPLICATE SUBPATTERN NAMES</a>
+<li><a name="TOC37" href="#SEC37">DUPLICATE CAPTURE GROUP NAMES</a>
 <li><a name="TOC38" href="#SEC38">FINDING ALL POSSIBLE MATCHES AT ONE POSITION</a>
 <li><a name="TOC39" href="#SEC39">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a>
 <li><a name="TOC40" href="#SEC40">SEE ALSO</a>
@@ -1490,10 +1490,10 @@
 <pre>
   PCRE2_DUPNAMES
 </pre>
-If this bit is set, names used to identify capturing subpatterns need not be
-unique. This can be helpful for certain types of pattern when it is known that
-only one instance of the named subpattern can ever be matched. There are more
-details of named subpatterns below; see also the
+If this bit is set, names used to identify capture groups need not be unique.
+This can be helpful for certain types of pattern when it is known that only one
+instance of the named group can ever be matched. There are more details of
+named capture groups below; see also the
 <a href="pcre2pattern.html"><b>pcre2pattern</b></a>
 documentation.
 <pre>
@@ -1526,11 +1526,11 @@
 If this bit is set, most white space characters in the pattern are totally
 ignored except when escaped or inside a character class. However, white space
 is not allowed within sequences such as (?&#62; that introduce various
-parenthesized subpatterns, nor within numerical quantifiers such as {1,3}.
-Ignorable white space is permitted between an item and a following quantifier
-and between a quantifier and a following + that indicates possessiveness.
-PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be changed within
-a pattern by a (?x) option setting.
+parenthesized groups, nor within numerical quantifiers such as {1,3}. Ignorable
+white space is permitted between an item and a following quantifier and between
+a quantifier and a following + that indicates possessiveness. PCRE2_EXTENDED is
+equivalent to Perl's /x option, and it can be changed within a pattern by a
+(?x) option setting.
 </P>
 <P>
 When PCRE2 is compiled without Unicode support, PCRE2_EXTENDED recognizes as
@@ -1606,7 +1606,7 @@
 <pre>
   PCRE2_MATCH_UNSET_BACKREF
 </pre>
-If this option is set, a backreference to an unset subpattern group matches an
+If this option is set, a backreference to an unset capture group matches an
 empty string (by default this causes the current matching alternative to fail).
 A pattern such as (\1)(a) succeeds when this option is set (assuming it can
 find an "a" in the subject), whereas it fails by default, for Perl
@@ -1668,7 +1668,7 @@
 the pattern. Any opening parenthesis that is not followed by ? behaves as if it
 were followed by ?: but named parentheses can still be used for capturing (and
 they acquire numbers in the usual way). This is the same as Perl's /n option.
-Note that, when this option is set, references to capturing groups
+Note that, when this option is set, references to capture groups
 (backreferences or recursion/subroutine calls) may only refer to named groups,
 though the reference can be by name or by number.
 <pre>
@@ -1687,7 +1687,7 @@
 If this option is set, it disables an optimization that is applied when .* is
 the first significant item in a top-level branch of a pattern, and all the
 other branches also start with .* or with \A or \G or ^. The optimization is
-automatically disabled for .* if it is inside an atomic group or a capturing
+automatically disabled for .* if it is inside an atomic group or a capture
 group that is the subject of a backreference, or if the pattern contains
 (*PRUNE) or (*SKIP). When the optimization is not disabled, such a pattern is
 automatically anchored if PCRE2_DOTALL is set for all the .* items and
@@ -2066,7 +2066,7 @@
 following are true:
 <pre>
   .* is not in an atomic group
-  .* is not in a capturing group that is the subject of a backreference
+  .* is not in a capture group that is the subject of a backreference
   PCRE2_DOTALL is in force for .*
   Neither (*PRUNE) nor (*SKIP) appears in the pattern
   PCRE2_NO_DOTSTAR_ANCHOR is not set
@@ -2077,12 +2077,12 @@
   PCRE2_INFO_BACKREFMAX
 </pre>
 Return the number of the highest backreference in the pattern. The third
-argument should point to an <b>uint32_t</b> variable. Named subpatterns acquire
-numbers as well as names, and these count towards the highest backreference.
-Backreferences such as \4 or \g{12} match the captured characters of the
-given group, but in addition, the check that a capturing group is set in a
-conditional subpattern such as (?(3)a|b) is also a backreference. Zero is
-returned if there are no backreferences.
+argument should point to an <b>uint32_t</b> variable. Named capture groups
+acquire numbers as well as names, and these count towards the highest
+backreference. Backreferences such as \4 or \g{12} match the captured
+characters of the given group, but in addition, the check that a capture
+group is set in a conditional group such as (?(3)a|b) is also a backreference.
+Zero is returned if there are no backreferences.
 <pre>
   PCRE2_INFO_BSR
 </pre>
@@ -2093,9 +2093,9 @@
 <pre>
   PCRE2_INFO_CAPTURECOUNT
 </pre>
-Return the highest capturing subpattern number in the pattern. In patterns
-where (?| is not used, this is also the total number of capturing subpatterns.
-The third argument should point to an <b>uint32_t</b> variable.
+Return the highest capture group number in the pattern. In patterns where (?|
+is not used, this is also the total number of capture groups. The third
+argument should point to an <b>uint32_t</b> variable.
 <pre>
   PCRE2_INFO_DEPTHLIMIT
 </pre>
@@ -2143,7 +2143,7 @@
 backtracking positions when the pattern is processed by <b>pcre2_match()</b>
 without the use of JIT. The third argument should point to a <b>size_t</b>
 variable. The frame size depends on the number of capturing parentheses in the
-pattern. Each additional capturing group adds two PCRE2_SIZE variables.
+pattern. Each additional capture group adds two PCRE2_SIZE variables.
 <pre>
   PCRE2_INFO_HASBACKSLASHC
 </pre>
@@ -2267,9 +2267,9 @@
 terminated.
 </P>
 <P>
-The names are in alphabetical order. If (?| is used to create multiple groups
-with the same number, as described in the
-<a href="pcre2pattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
+The names are in alphabetical order. If (?| is used to create multiple capture
+groups with the same number, as described in the
+<a href="pcre2pattern.html#dupgroupnumber">section on duplicate group numbers</a>
 in the
 <a href="pcre2pattern.html"><b>pcre2pattern</b></a>
 page, the groups may be given the same name, but there is only one entry in the
@@ -2276,11 +2276,11 @@
 table. Different names for groups of the same number are not permitted.
 </P>
 <P>
-Duplicate names for subpatterns with different numbers are permitted, but only
-if PCRE2_DUPNAMES is set. They appear in the table in the order in which they
-were found in the pattern. In the absence of (?| this is the order of
+Duplicate names for capture groups with different numbers are permitted, but
+only if PCRE2_DUPNAMES is set. They appear in the table in the order in which
+they were found in the pattern. In the absence of (?| this is the order of
 increasing number; when (?| is used this is not necessarily the case because
-later subpatterns may have lower numbers.
+later capture groups may have lower numbers.
 </P>
 <P>
 As a simple example of the name/number table, consider the following pattern
@@ -2289,9 +2289,9 @@
 <pre>
   (?&#60;date&#62; (?&#60;year&#62;(\d\d)?\d\d) - (?&#60;month&#62;\d\d) - (?&#60;day&#62;\d\d) )
 </pre>
-There are four named subpatterns, so the table has four entries, and each entry
-in the table is eight bytes long. The table is as follows, with non-printing
-bytes shows in hexadecimal, and undefined bytes shown as ??:
+There are four named capture groups, so the table has four entries, and each
+entry in the table is eight bytes long. The table is as follows, with
+non-printing bytes shows in hexadecimal, and undefined bytes shown as ??:
 <pre>
   00 01 d  a  t  e  00 ??
   00 05 d  a  y  00 ?? ??
@@ -2298,7 +2298,7 @@
   00 04 m  o  n  t  h  00
   00 02 y  e  a  r  00 ??
 </pre>
-When writing code to extract data from named subpatterns using the
+When writing code to extract data from named capture groups using the
 name-to-number map, remember that the length of the entries is likely to be
 different for each compiled pattern.
 <pre>
@@ -2741,12 +2741,12 @@
 In general, a pattern matches a certain portion of the subject, and in
 addition, further substrings from the subject may be picked out by
 parenthesized parts of the pattern. Following the usage in Jeffrey Friedl's
-book, this is called "capturing" in what follows, and the phrase "capturing
-subpattern" or "capturing group" is used for a fragment of a pattern that picks
-out a substring. PCRE2 supports several other kinds of parenthesized subpattern
-that do not cause substrings to be captured. The <b>pcre2_pattern_info()</b>
-function can be used to find out how many capturing subpatterns there are in a
-compiled pattern.
+book, this is called "capturing" in what follows, and the phrase "capture
+group" (Perl terminology) is used for a fragment of a pattern that picks out a
+substring. PCRE2 supports several other kinds of parenthesized group that do
+not cause substrings to be captured. The <b>pcre2_pattern_info()</b> function
+can be used to find out how many capture groups there are in a compiled
+pattern.
 </P>
 <P>
 You can use auxiliary functions for accessing captured substrings
@@ -2795,9 +2795,8 @@
 end offset values for the match are 2 and 0.
 </P>
 <P>
-If a capturing subpattern group is matched repeatedly within a single match
-operation, it is the last portion of the subject that it matched that is
-returned.
+If a capture group is matched repeatedly within a single match operation, it is
+the last portion of the subject that it matched that is returned.
 </P>
 <P>
 If the ovector is too small to hold all the captured substring offsets, as much
@@ -2806,21 +2805,20 @@
 data block whose ovector is of minimum length (that is, one pair).
 </P>
 <P>
-It is possible for capturing subpattern number <i>n+1</i> to match some part of
-the subject when subpattern <i>n</i> has not been used at all. For example, if
-the string "abc" is matched against the pattern (a|(z))(bc) the return from the
-function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
-happens, both values in the offset pairs corresponding to unused subpatterns
-are set to PCRE2_UNSET.
+It is possible for capture group number <i>n+1</i> to match some part of the
+subject when group <i>n</i> has not been used at all. For example, if the string
+"abc" is matched against the pattern (a|(z))(bc) the return from the function
+is 4, and groups 1 and 3 are matched, but 2 is not. When this happens, both
+values in the offset pairs corresponding to unused groups are set to
+PCRE2_UNSET.
 </P>
 <P>
-Offset values that correspond to unused subpatterns at the end of the
-expression are also set to PCRE2_UNSET. For example, if the string "abc" is
-matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched.
-The return from the function is 2, because the highest used capturing
-subpattern number is 1. The offsets for for the second and third capturing
-subpatterns (assuming the vector is large enough, of course) are set to
-PCRE2_UNSET.
+Offset values that correspond to unused groups at the end of the expression are
+also set to PCRE2_UNSET. For example, if the string "abc" is matched against
+the pattern (abc)(x(yz)?)? groups 2 and 3 are not matched. The return from the
+function is 2, because the highest used capture group number is 1. The offsets
+for for the second and third capture groupss (assuming the vector is large
+enough, of course) are set to PCRE2_UNSET.
 </P>
 <P>
 Elements in the ovector that do not correspond to capturing parentheses in the
@@ -2993,11 +2991,11 @@
 </pre>
 This error is returned when <b>pcre2_match()</b> detects a recursion loop within
 the pattern. Specifically, it means that either the whole pattern or a
-subpattern has been called recursively for the second time at the same position
-in the subject string. Some simple patterns that might do this are detected and
-faulted at compile time, but more complicated cases, in particular mutual
-recursions between two different subpatterns, cannot be detected until matching
-is attempted.
+capture group has been called recursively for the second time at the same
+position in the subject string. Some simple patterns that might do this are
+detected and faulted at compile time, but more complicated cases, in particular
+mutual recursions between two different groups, cannot be detected until
+matching is attempted.
 <a name="geterrormessage"></a></P>
 <br><a name="SEC32" href="#TOC1">OBTAINING A TEXTUAL ERROR MESSAGE</a><br>
 <P>
@@ -3074,7 +3072,7 @@
 into a supplied buffer, whereas <b>pcre2_substring_get_bynumber()</b> copies it
 into new memory, obtained using the same memory allocation function that was
 used for the match data block. The first two arguments of these functions are a
-pointer to the match data block and a capturing group number.
+pointer to the match data block and a capture group number.
 </P>
 <P>
 The final arguments of <b>pcre2_substring_copy_bynumber()</b> are a pointer to
@@ -3150,9 +3148,9 @@
 </P>
 <P>
 If this function encounters a substring that is unset, which can happen when
-capturing subpattern number <i>n+1</i> matches some part of the subject, but
-subpattern <i>n</i> has not been used at all, it returns an empty string. This
-can be distinguished from a genuine zero-length substring by inspecting the
+capture group number <i>n+1</i> matches some part of the subject, but group
+<i>n</i> has not been used at all, it returns an empty string. This can be
+distinguished from a genuine zero-length substring by inspecting the
 appropriate offset in the ovector, which contain PCRE2_UNSET for unset
 substrings, or by calling <b>pcre2_substring_length_bynumber()</b>.
 <a name="extractbyname"></a></P>
@@ -3182,14 +3180,14 @@
 <pre>
   (a+)b(?&#60;xxx&#62;\d+)...
 </pre>
-the number of the subpattern called "xxx" is 2. If the name is known to be
+the number of the capture group called "xxx" is 2. If the name is known to be
 unique (PCRE2_DUPNAMES was not set), you can find the number from the name by
 calling <b>pcre2_substring_number_from_name()</b>. The first argument is the
 compiled pattern, and the second is the name. The yield of the function is the
-subpattern number, PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that
-name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of
-that name. Given the number, you can extract the substring directly from the
-ovector, or use one of the "bynumber" functions described above.
+group number, PCRE2_ERROR_NOSUBSTRING if there is no group with that name, or
+PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one group with that name.
+Given the number, you can extract the substring directly from the ovector, or
+use one of the "bynumber" functions described above.
 </P>
 <P>
 For convenience, there are also "byname" functions that correspond to the
@@ -3196,7 +3194,7 @@
 "bynumber" functions, the only difference being that the second argument is a
 name instead of a number. If PCRE2_DUPNAMES is set and there are duplicate
 names, these functions scan all the groups with the given name, and return the
-first named string that is set.
+captured substring from the first named group that is set.
 </P>
 <P>
 If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is
@@ -3207,13 +3205,13 @@
 </P>
 <P>
 <b>Warning:</b> If the pattern uses the (?| feature to set up multiple
-subpatterns with the same number, as described in the
-<a href="pcre2pattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
+capture groups with the same number, as described in the
+<a href="pcre2pattern.html#dupgroupnumber">section on duplicate group numbers</a>
 in the
 <a href="pcre2pattern.html"><b>pcre2pattern</b></a>
-page, you cannot use names to distinguish the different subpatterns, because
+page, you cannot use names to distinguish the different capture groups, because
 names are not included in the compiled code. The matching process uses only
-numbers. For this reason, the use of different names for subpatterns of the
+numbers. For this reason, the use of different names for groups with the
 same number causes an error at compile time.
 <a name="substitutions"></a></P>
 <br><a name="SEC36" href="#TOC1">CREATING A NEW STRING WITH SUBSTITUTIONS</a><br>
@@ -3276,7 +3274,7 @@
 In the replacement string, which is interpreted as a UTF string in UTF mode,
 and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK option is set, a
 dollar character is an escape character that can specify the insertion of
-characters from capturing groups or names from (*MARK) or other control verbs
+characters from capture groups or names from (*MARK) or other control verbs
 in the pattern. The following forms are always recognized:
 <pre>
   $$                  insert a dollar character
@@ -3345,13 +3343,13 @@
 using PCRE2_SUBSTITUTE_OVERFLOW_LENGTH.
 </P>
 <P>
-PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capturing groups that do
+PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capture groups that do
 not appear in the pattern to be treated as unset groups. This option should be
 used with care, because it means that a typo in a group name or number no
 longer causes the PCRE2_ERROR_NOSUBSTRING error.
 </P>
 <P>
-PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capturing groups (including unknown
+PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capture groups (including unknown
 groups when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) to be treated as empty
 strings when inserted as described above. If this option is not set, an attempt
 to insert an unset group causes the PCRE2_ERROR_UNSET error. This option does
@@ -3379,7 +3377,7 @@
 \u and \l force the next character (if it is a letter) to upper or lower
 case, respectively, and then the state automatically reverts to no case
 forcing. Case forcing applies to all inserted  characters, including those from
-captured groups and letters within \Q...\E quoted sequences.
+capture groups and letters within \Q...\E quoted sequences.
 </P>
 <P>
 Note that case forcing sequences such as \U...\E do not nest. For example,
@@ -3388,7 +3386,8 @@
 </P>
 <P>
 The second effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more
-flexibility to group substitution. The syntax is similar to that used by Bash:
+flexibility to capture group substitution. The syntax is similar to that used
+by Bash:
 <pre>
   ${&#60;n&#62;:-&#60;string&#62;}
   ${&#60;n&#62;:+&#60;string1&#62;:&#60;string2&#62;}
@@ -3518,20 +3517,21 @@
 output and the call to <b>pcre2_substitute()</b> exits, returning the number of
 matches so far.
 </P>
-<br><a name="SEC37" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br>
+<br><a name="SEC37" href="#TOC1">DUPLICATE CAPTURE GROUP NAMES</a><br>
 <P>
 <b>int pcre2_substring_nametable_scan(const pcre2_code *<i>code</i>,</b>
 <b>  PCRE2_SPTR <i>name</i>, PCRE2_SPTR *<i>first</i>, PCRE2_SPTR *<i>last</i>);</b>
 </P>
 <P>
-When a pattern is compiled with the PCRE2_DUPNAMES option, names for
-subpatterns are not required to be unique. Duplicate names are always allowed
-for subpatterns with the same number, created by using the (?| feature. Indeed,
-if such subpatterns are named, they are required to use the same names.
+When a pattern is compiled with the PCRE2_DUPNAMES option, names for capture
+groups are not required to be unique. Duplicate names are always allowed for
+groups with the same number, created by using the (?| feature. Indeed, if such
+groups are named, they are required to use the same names.
 </P>
 <P>
-Normally, patterns with duplicate names are such that in any one match, only
-one of the named subpatterns participates. An example is shown in the
+Normally, patterns that use duplicate names are such that in any one match,
+only one of each set of identically-named groups participates. An example is
+shown in the
 <a href="pcre2pattern.html"><b>pcre2pattern</b></a>
 documentation.
 </P>
@@ -3703,9 +3703,8 @@
 On success, the yield of the function is a number greater than zero, which is
 the number of matched substrings. The offsets of the substrings are returned in
 the ovector, and can be extracted by number in the same way as for
-<b>pcre2_match()</b>, but the numbers bear no relation to any capturing groups
-that may exist in the pattern, because DFA matching does not support group
-capture.
+<b>pcre2_match()</b>, but the numbers bear no relation to any capture groups
+that may exist in the pattern, because DFA matching does not support capturing.
 </P>
 <P>
 Calls to the convenience functions that extract substrings by name
@@ -3747,7 +3746,7 @@
 </pre>
 This return is given if <b>pcre2_dfa_match()</b> encounters a condition item
 that uses a backreference for the condition, or a test for recursion in a
-specific group. These are not supported.
+specific capture group. These are not supported.
 <pre>
   PCRE2_ERROR_DFA_WSSIZE
 </pre>
@@ -3756,9 +3755,9 @@
 <pre>
   PCRE2_ERROR_DFA_RECURSE
 </pre>
-When a recursive subpattern is processed, the matching function calls itself
-recursively, using private memory for the ovector and <i>workspace</i>. This
-error is given if the internal ovector is not large enough. This should be
+When a recursion or subroutine call is processed, the matching function calls
+itself recursively, using private memory for the ovector and <i>workspace</i>.
+This error is given if the internal ovector is not large enough. This should be
 extremely rare, as a vector of size 1000 is used.
 <pre>
   PCRE2_ERROR_DFA_BADRESTART
@@ -3785,7 +3784,7 @@
 </P>
 <br><a name="SEC42" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 04 January 2019
+Last updated: 04 February 2019
 <br>
 Copyright &copy; 1997-2019 University of Cambridge.
 <br>


Modified: code/trunk/doc/html/pcre2callout.html
===================================================================
--- code/trunk/doc/html/pcre2callout.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2callout.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -151,7 +151,7 @@
 </P>
 <P>
 This optimization is disabled, however, if .* is in an atomic group or if there
-is a backreference to the capturing group in which it appears. It is also
+is a backreference to the capture group in which it appears. It is also
 disabled if the pattern contains (*PRUNE) or (*SKIP). However, the presence of
 callouts does not affect it.
 </P>
@@ -354,8 +354,8 @@
 alternation bar or a closing parenthesis, the length is one, unless a closing
 parenthesis is followed by a quantifier, in which case its length is included.
 (This changed in release 10.23. In earlier releases, before an opening
-parenthesis the length was that of the entire subpattern, and before an
-alternation bar or a closing parenthesis the length was zero.)
+parenthesis the length was that of the entire group, and before an alternation
+bar or a closing parenthesis the length was zero.)
 </P>
 <P>
 The <i>pattern_position</i> and <i>next_item_length</i> fields are intended to
@@ -471,9 +471,9 @@
 </P>
 <br><a name="SEC8" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 17 September 2018
+Last updated: 03 February 2019
 <br>
-Copyright &copy; 1997-2018 University of Cambridge.
+Copyright &copy; 1997-2019 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE2 index page</a>.


Modified: code/trunk/doc/html/pcre2compat.html
===================================================================
--- code/trunk/doc/html/pcre2compat.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2compat.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -36,10 +36,9 @@
 for example, \b* (but not \b{3}), but these do not seem to have any use.
 </P>
 <P>
-3. Capturing subpatterns that occur inside negative lookaround assertions are
-counted, but their entries in the offsets vector are set only when a negative
-assertion is a condition that has a matching branch (that is, the condition is
-false).
+3. Capture groups that occur inside negative lookaround assertions are counted,
+but their entries in the offsets vector are set only when a negative assertion
+is a condition that has a matching branch (that is, the condition is false).
 </P>
 <P>
 4. The following Perl escape sequences are not supported: \F, \l, \L, \u,
@@ -94,13 +93,13 @@
 into subroutine calls is now supported, as in Perl.
 </P>
 <P>
-9. If any of the backtracking control verbs are used in a subpattern that is
-called as a subroutine (whether or not recursively), their effect is confined
-to that subpattern; it does not extend to the surrounding pattern. This is not
-always the case in Perl. In particular, if (*THEN) is present in a group that
-is called as a subroutine, its action is limited to that group, even if the
-group does not contain any | characters. Note that such subpatterns are
-processed as anchored at the point where they are tested.
+9. If any of the backtracking control verbs are used in a group that is called
+as a subroutine (whether or not recursively), their effect is confined to that
+group; it does not extend to the surrounding pattern. This is not always the
+case in Perl. In particular, if (*THEN) is present in a group that is called as
+a subroutine, its action is limited to that group, even if the group does not
+contain any | characters. Note that such groups are processed as anchored
+at the point where they are tested.
 </P>
 <P>
 10. If a pattern contains more than one backtracking control verb, the first
@@ -120,22 +119,21 @@
 "b".
 </P>
 <P>
-13. PCRE2's handling of duplicate subpattern numbers and duplicate subpattern
-names is not as general as Perl's. This is a consequence of the fact the PCRE2
-works internally just with numbers, using an external table to translate
-between numbers and names. In particular, a pattern such as (?|(?&#60;a&#62;A)|(?&#60;b&#62;B),
-where the two capturing parentheses have the same number but different names,
-is not supported, and causes an error at compile time. If it were allowed, it
-would not be possible to distinguish which parentheses matched, because both
-names map to capturing subpattern number 1. To avoid this confusing situation,
-an error is given at compile time.
+13. PCRE2's handling of duplicate capture group numbers and names is not as
+general as Perl's. This is a consequence of the fact the PCRE2 works internally
+just with numbers, using an external table to translate between numbers and
+names. In particular, a pattern such as (?|(?&#60;a&#62;A)|(?&#60;b&#62;B), where the two
+capture groups have the same number but different names, is not supported, and
+causes an error at compile time. If it were allowed, it would not be possible
+to distinguish which group matched, because both names map to capture group
+number 1. To avoid this confusing situation, an error is given at compile time.
 </P>
 <P>
 14. Perl used to recognize comments in some places that PCRE2 does not, for
-example, between the ( and ? at the start of a subpattern. If the /x modifier
-is set, Perl allowed white space between ( and ? though the latest Perls give
-an error (for a while it was just deprecated). There may still be some cases
-where Perl behaves differently.
+example, between the ( and ? at the start of a group. If the /x modifier is
+set, Perl allowed white space between ( and ? though the latest Perls give an
+error (for a while it was just deprecated). There may still be some cases where
+Perl behaves differently.
 </P>
 <P>
 15. Perl, when in warning mode, gives warnings for character classes such as
@@ -235,9 +233,9 @@
 REVISION
 </b><br>
 <P>
-Last updated: 28 July 2018
+Last updated: 03 February 2019
 <br>
-Copyright &copy; 1997-2018 University of Cambridge.
+Copyright &copy; 1997-2019 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE2 index page</a>.


Modified: code/trunk/doc/html/pcre2limits.html
===================================================================
--- code/trunk/doc/html/pcre2limits.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2limits.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -50,17 +50,17 @@
 The maximum length of a lookbehind assertion is 65535 characters.
 </P>
 <P>
-There is no limit to the number of parenthesized subpatterns, but there can be
-no more than 65535 capturing subpatterns. There is, however, a limit to the
-depth of nesting of parenthesized subpatterns of all kinds. This is imposed in
-order to limit the amount of system stack used at compile time. The default
-limit can be specified when PCRE2 is built; if not, the default is set to 250.
-An application can change this limit by calling pcre2_set_parens_nest_limit()
-to set the limit in a compile context.
+There is no limit to the number of parenthesized groups, but there can be no
+more than 65535 capture groups, and there is a limit to the depth of nesting of
+parenthesized subpatterns of all kinds. This is imposed in order to limit the
+amount of system stack used at compile time. The default limit can be specified
+when PCRE2 is built; if not, the default is set to 250. An application can
+change this limit by calling pcre2_set_parens_nest_limit() to set the limit in
+a compile context.
 </P>
 <P>
-The maximum length of name for a named subpattern is 32 code units, and the
-maximum number of named subpatterns is 10000.
+The maximum length of name for a named capture group is 32 code units, and the
+maximum number of such groups is 10000.
 </P>
 <P>
 The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb
@@ -86,9 +86,9 @@
 REVISION
 </b><br>
 <P>
-Last updated: 30 March 2017
+Last updated: 02 February 2019
 <br>
-Copyright &copy; 1997-2017 University of Cambridge.
+Copyright &copy; 1997-2019 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE2 index page</a>.


Modified: code/trunk/doc/html/pcre2pattern.html
===================================================================
--- code/trunk/doc/html/pcre2pattern.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2pattern.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -26,18 +26,18 @@
 <li><a name="TOC11" href="#SEC11">COMPATIBILITY FEATURE FOR WORD BOUNDARIES</a>
 <li><a name="TOC12" href="#SEC12">VERTICAL BAR</a>
 <li><a name="TOC13" href="#SEC13">INTERNAL OPTION SETTING</a>
-<li><a name="TOC14" href="#SEC14">SUBPATTERNS</a>
-<li><a name="TOC15" href="#SEC15">DUPLICATE SUBPATTERN NUMBERS</a>
-<li><a name="TOC16" href="#SEC16">NAMED SUBPATTERNS</a>
+<li><a name="TOC14" href="#SEC14">GROUPS</a>
+<li><a name="TOC15" href="#SEC15">DUPLICATE GROUP NUMBERS</a>
+<li><a name="TOC16" href="#SEC16">NAMED CAPTURE GROUPS</a>
 <li><a name="TOC17" href="#SEC17">REPETITION</a>
 <li><a name="TOC18" href="#SEC18">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a>
 <li><a name="TOC19" href="#SEC19">BACKREFERENCES</a>
 <li><a name="TOC20" href="#SEC20">ASSERTIONS</a>
 <li><a name="TOC21" href="#SEC21">SCRIPT RUNS</a>
-<li><a name="TOC22" href="#SEC22">CONDITIONAL SUBPATTERNS</a>
+<li><a name="TOC22" href="#SEC22">CONDITIONAL GROUPS</a>
 <li><a name="TOC23" href="#SEC23">COMMENTS</a>
 <li><a name="TOC24" href="#SEC24">RECURSIVE PATTERNS</a>
-<li><a name="TOC25" href="#SEC25">SUBPATTERNS AS SUBROUTINES</a>
+<li><a name="TOC25" href="#SEC25">GROUPS AS SUBROUTINES</a>
 <li><a name="TOC26" href="#SEC26">ONIGURUMA SUBROUTINE SYNTAX</a>
 <li><a name="TOC27" href="#SEC27">CALLOUTS</a>
 <li><a name="TOC28" href="#SEC28">BACKTRACKING CONTROL</a>
@@ -63,13 +63,13 @@
 PCRE2's regular expressions is intended as reference material.
 </P>
 <P>
-This document discusses the patterns that are supported by PCRE2 when its main
-matching function, <b>pcre2_match()</b>, is used. PCRE2 also has an alternative
-matching function, <b>pcre2_dfa_match()</b>, which matches using a different
-algorithm that is not Perl-compatible. Some of the features discussed below are
-not available when DFA matching is used. The advantages and disadvantages of
-the alternative function, and how it differs from the normal function, are
-discussed in the
+This document discusses the regular expression patterns that are supported by
+PCRE2 when its main matching function, <b>pcre2_match()</b>, is used. PCRE2 also
+has an alternative matching function, <b>pcre2_dfa_match()</b>, which matches
+using a different algorithm that is not Perl-compatible. Some of the features
+discussed below are not available when DFA matching is used. The advantages and
+disadvantages of the alternative function, and how it differs from the normal
+function, are discussed in the
 <a href="pcre2matching.html"><b>pcre2matching</b></a>
 page.
 </P>
@@ -183,8 +183,8 @@
 </P>
 <P>
 These facilities are provided to catch runaway matches that are provoked by
-patterns with huge matching trees (a typical example is a pattern with nested
-unlimited repeats applied to a long string that does not match). When one of
+patterns with huge matching trees. A common example is a pattern with nested
+unlimited repeats applied to a long string that does not match. When one of
 these limits is reached, <b>pcre2_match()</b> gives an error return. The limits
 can also be set by items at the start of the pattern of the form
 <pre>
@@ -290,10 +290,10 @@
 independently of case.
 </P>
 <P>
-The power of regular expressions comes from the ability to include alternatives
-and repetitions in the pattern. These are encoded in the pattern by the use of
-<i>metacharacters</i>, which do not stand for themselves but instead are
-interpreted in some special way.
+The power of regular expressions comes from the ability to include wild cards,
+character classes, alternatives, and repetitions in the pattern. These are
+encoded in the pattern by the use of <i>metacharacters</i>, which do not stand
+for themselves but instead are interpreted in some special way.
 </P>
 <P>
 There are two different sets of metacharacters: those that are recognized
@@ -307,14 +307,11 @@
   .      match any character except newline (by default)
   [      start character class definition
   |      start of alternative branch
-  (      start subpattern
-  )      end subpattern
-  ?      extends the meaning of (
-         also 0 or 1 quantifier
-         also quantifier minimizer
+  (      start group or control verb
+  )      end group or control verb
   *      0 or more quantifier
-  +      1 or more quantifier
-         also "possessive quantifier"
+  +      1 or more quantifier; also "possessive quantifier"
+  ?      0 or 1 quantifier; also quantifier minimizer
   {      start min/max quantifier
 </pre>
 Part of a pattern that is in square brackets is called a "character class". In
@@ -323,7 +320,7 @@
   \      general escape character
   ^      negate the class, but only if the first character
   -      indicates character range
-  [      POSIX character class (only if followed by POSIX syntax)
+  [      POSIX character class (if followed by POSIX syntax)
   ]      terminates the character class
 </pre>
 The following sections describe the use of each of the metacharacters.
@@ -331,7 +328,7 @@
 <br><a name="SEC5" href="#TOC1">BACKSLASH</a><br>
 <P>
 The backslash character has several uses. Firstly, if it is followed by a
-character that is not a number or a letter, it takes away any special meaning
+character that is not a digit or a letter, it takes away any special meaning
 that character may have. This use of backslash as an escape character applies
 both inside and outside character classes.
 </P>
@@ -343,7 +340,7 @@
 In particular, if you want to match a backslash, you write \\.
 </P>
 <P>
-In a UTF mode, only ASCII numbers and letters have any special meaning after a
+In a UTF mode, only ASCII digits and letters have any special meaning after a
 backslash. All other characters (in particular, those whose code points are
 greater than 127) are treated as literals.
 </P>
@@ -355,13 +352,13 @@
 of the pattern.
 </P>
 <P>
-If you want to remove the special meaning from a sequence of characters, you
-can do so by putting them between \Q and \E. This is different from Perl in
-that $ and @ are handled as literals in \Q...\E sequences in PCRE2, whereas
-in Perl, $ and @ cause variable interpolation. Also, Perl does "double-quotish
-backslash interpolation" on any backslashes between \Q and \E which, its
-documentation says, "may lead to confusing results". PCRE2 treats a backslash
-between \Q and \E just like any other character. Note the following examples:
+If you want to treat all characters in a sequence as literals, you can do so by
+putting them between \Q and \E. This is different from Perl in that $ and @
+are handled as literals in \Q...\E sequences in PCRE2, whereas in Perl, $ and
+@ cause variable interpolation. Also, Perl does "double-quotish backslash
+interpolation" on any backslashes between \Q and \E which, its documentation
+says, "may lead to confusing results". PCRE2 treats a backslash between \Q and
+\E just like any other character. Note the following examples:
 <pre>
   Pattern            PCRE2 matches   Perl matches


@@ -386,8 +383,8 @@
 in patterns in a visible manner. There is no restriction on the appearance of
 non-printing characters in a pattern, but when a pattern is being prepared by
 text editing, it is often easier to use one of the following escape sequences
-than the binary character it represents. In an ASCII or Unicode environment,
-these escapes are as follows:
+instead of the binary character it represents. In an ASCII or Unicode
+environment, these escapes are as follows:
 <pre>
   \a          alarm, that is, the BEL character (hex 07)
   \cx         "control-x", where x is any printable ASCII character
@@ -475,12 +472,12 @@
 <P>
 Outside a character class, PCRE2 reads the digit and any following digits as a
 decimal number. If the number is less than 10, begins with the digit 8 or 9, or
-if there are at least that many previous capturing left parentheses in the
-expression, the entire sequence is taken as a <i>backreference</i>. A
-description of how this works is given
+if there are at least that many previous capture groups in the expression, the
+entire sequence is taken as a <i>backreference</i>. A description of how this
+works is given
 <a href="#backreferences">later,</a>
 following the discussion of
-<a href="#subpattern">parenthesized subpatterns.</a>
+<a href="#group">parenthesized groups.</a>
 Otherwise, up to three octal digits are read to form a character code.
 </P>
 <P>
@@ -490,7 +487,7 @@
 for themselves. For example, outside a character class:
 <pre>
   \040   is another way of writing an ASCII space
-  \40    is the same, provided there are fewer than 40 previous capturing subpatterns
+  \40    is the same, provided there are fewer than 40 previous capture groups
   \7     is always a backreference
   \11    might be a backreference, or another way of writing a tab
   \011   is always a tab
@@ -515,7 +512,9 @@
 described only when it is followed by two hexadecimal digits. Otherwise, it
 matches a literal "x" character. In this mode, support for code points greater
 than 256 is provided by \u, which must be followed by four hexadecimal digits;
-otherwise it matches a literal "u" character.
+otherwise it matches a literal "u" character. This syntax makes PCRE2 behave 
+like ECMAscript (aka JavaScript). Code points greater than 0xFFFF are not
+supported.
 </P>
 <P>
 Characters whose value is less than 256 can be defined by either of the two
@@ -574,7 +573,7 @@
 can be coded as \g{name}. Backreferences are discussed
 <a href="#backreferences">later,</a>
 following the discussion of
-<a href="#subpattern">parenthesized subpatterns.</a>
+<a href="#group">parenthesized groups.</a>
 </P>
 <br><b>
 Absolute and relative subroutine calls
@@ -582,11 +581,11 @@
 <P>
 For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or
 a number enclosed either in angle brackets or single quotes, is an alternative
-syntax for referencing a subpattern as a "subroutine". Details are discussed
+syntax for referencing a capture group as a subroutine. Details are discussed
 <a href="#onigurumasubroutines">later.</a>
 Note that \g{...} (Perl syntax) and \g&#60;...&#62; (Oniguruma syntax) are <i>not</i>
 synonymous. The former is a backreference; the latter is a
-<a href="#subpatternsassubroutines">subroutine</a>
+<a href="#groupsassubroutines">subroutine</a>
 call.
 <a name="genericchartypes"></a></P>
 <br><b>
@@ -753,21 +752,22 @@
 </b><br>
 <P>
 When PCRE2 is built with Unicode support (the default), three additional escape
-sequences that match characters with specific properties are available. In
-8-bit non-UTF-8 mode, these sequences are of course limited to testing
-characters whose code points are less than 256, but they do work in this mode.
-In 32-bit non-UTF mode, code points greater than 0x10ffff (the Unicode limit)
-may be encountered. These are all treated as being in the Unknown script and
-with an unassigned type. The extra escape sequences are:
+sequences that match characters with specific properties are available. They
+can be used in any mode, though in 8-bit and 16-bit non-UTF modes these
+sequences are of course limited to testing characters whose code points are
+less than U+0100 and U+10000, respectively. In 32-bit non-UTF mode, code points
+greater than 0x10ffff (the Unicode limit) may be encountered. These are all
+treated as being in the Unknown script and with an unassigned type. The extra
+escape sequences are:
 <pre>
   \p{<i>xx</i>}   a character with the <i>xx</i> property
   \P{<i>xx</i>}   a character without the <i>xx</i> property
   \X       a Unicode extended grapheme cluster
 </pre>
-The property names represented by <i>xx</i> above are limited to the Unicode
-script names, the general category properties, "Any", which matches any
-character (including newline), and some special PCRE2 properties (described
-in the
+The property names represented by <i>xx</i> above are case-sensitive. There is
+support for Unicode script names, Unicode general category properties, "Any",
+which matches any character (including newline), and some special PCRE2
+properties (described in the
 <a href="#extraprops">next section).</a>
 Other Perl properties such as "InMusicalSymbols" are not supported by PCRE2.
 Note that \P{Any} does not match any characters, so always causes a match
@@ -1003,12 +1003,14 @@
 a modifier or "other".
 </P>
 <P>
-The Cs (Surrogate) property applies only to characters in the range U+D800 to
-U+DFFF. Such characters are not valid in Unicode strings and so
-cannot be tested by PCRE2, unless UTF validity checking has been turned off
-(see the discussion of PCRE2_NO_UTF_CHECK in the
+The Cs (Surrogate) property applies only to characters whose code points are in
+the range U+D800 to U+DFFF. These characters are no different to any other
+character when PCRE2 is not in UTF mode (using the 16-bit or 32-bit library).
+However, they are not valid in Unicode strings and so cannot be tested by PCRE2
+in UTF mode, unless UTF validity checking has been turned off (see the
+discussion of PCRE2_NO_UTF_CHECK in the
 <a href="pcre2api.html"><b>pcre2api</b></a>
-page). Perl does not support the Cs property.
+page).
 </P>
 <P>
 The long synonyms for property names that Perl supports (such as \p{Letter})
@@ -1138,7 +1140,7 @@
 However, in this case, the part of the subject before the real match does not
 have to be of fixed length, as lookbehind assertions do. The use of \K does
 not interfere with the setting of
-<a href="#subpattern">captured substrings.</a>
+<a href="#group">captured substrings.</a>
 For example, when the pattern
 <pre>
   (foo)\Kbar
@@ -1166,7 +1168,7 @@
 The final use of backslash is for certain simple assertions. An assertion
 specifies a condition that has to be met at a particular point in a match,
 without consuming any characters from the subject string. The use of
-subpatterns for more complicated assertions is described
+groups for more complicated assertions is described
 <a href="#bigassertions">below.</a>
 The backslashed assertions are:
 <pre>
@@ -1186,12 +1188,12 @@
 A word boundary is a position in the subject string where the current character
 and the previous character do not both match \w or \W (i.e. one matches
 \w and the other matches \W), or the start or end of the string if the
-first or last character matches \w, respectively. In a UTF mode, the meanings
-of \w and \W can be changed by setting the PCRE2_UCP option. When this is
-done, it also affects \b and \B. Neither PCRE2 nor Perl has a separate "start
-of word" or "end of word" metasequence. However, whatever follows \b normally
-determines which it is. For example, the fragment \ba matches "a" at the start
-of a word.
+first or last character matches \w, respectively. When PCRE2 is built with 
+Unicode support, the meanings of \w and \W can be changed by setting the
+PCRE2_UCP option. When this is done, it also affects \b and \B. Neither PCRE2
+nor Perl has a separate "start of word" or "end of word" metasequence. However,
+whatever follows \b normally determines which it is. For example, the fragment
+\ba matches "a" at the start of a word.
 </P>
 <P>
 The \A, \Z, and \z assertions differ from the traditional circumflex and
@@ -1386,7 +1388,7 @@
 </pre>
 In this example, a group that starts with (?| resets the capturing parentheses
 numbers in each alternative (see
-<a href="#dupsubpatternnumber">"Duplicate Subpattern Numbers"</a>
+<a href="#dupgroupnumber">"Duplicate Group Numbers"</a>
 below). The assertions at the start of each branch check the next UTF-8
 character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The
 character's individual bytes are then captured by the appropriate number of
@@ -1632,10 +1634,10 @@
 matches either "gilbert" or "sullivan". Any number of alternatives may appear,
 and an empty alternative is permitted (matching the empty string). The matching
 process tries each alternative in turn, from left to right, and the first one
-that succeeds is used. If the alternatives are within a subpattern
-<a href="#subpattern">(defined below),</a>
+that succeeds is used. If the alternatives are within a group
+<a href="#group">(defined below),</a>
 "succeeds" means matching the rest of the main pattern as well as the
-alternative in the subpattern.
+alternative in the group.
 </P>
 <br><a name="SEC13" href="#TOC1">INTERNAL OPTION SETTING</a><br>
 <P>
@@ -1678,9 +1680,9 @@
 </P>
 <P>
 When one of these option changes occurs at top level (that is, not inside
-subpattern parentheses), the change applies to the remainder of the pattern
-that follows. An option change within a subpattern (see below for a description
-of subpatterns) affects only that part of the subpattern that follows it, so
+group parentheses), the change applies to the remainder of the pattern
+that follows. An option change within a group (see below for a description
+of groups) affects only that part of the group that follows it, so
 <pre>
   (a(?i)b)c
 </pre>
@@ -1687,7 +1689,7 @@
 matches abc and aBc and no other strings (assuming PCRE2_CASELESS is not used).
 By this means, options can be made to have different settings in different
 parts of the pattern. Any changes made in one alternative do carry on
-into subsequent branches within the same subpattern. For example,
+into subsequent branches within the same group. For example,
 <pre>
   (a(?i)b|c)
 </pre>
@@ -1698,7 +1700,7 @@
 </P>
 <P>
 As a convenient shorthand, if any option settings are required at the start of
-a non-capturing subpattern (see the next section), the option letters may
+a non-capturing group (see the next section), the option letters may
 appear between the "?" and the ":". Thus the two patterns
 <pre>
   (?i:saturday|sunday)
@@ -1707,10 +1709,11 @@
 match exactly the same set of strings.
 </P>
 <P>
-<b>Note:</b> There are other PCRE2-specific options that can be set by the
-application when the compiling function is called. The pattern can contain
-special leading sequences such as (*CRLF) to override what the application has
-set or what has been defaulted. Details are given in the section entitled
+<b>Note:</b> There are other PCRE2-specific options, applying to the whole
+pattern, which can be set by the application when the compiling function is
+called. In addition, the pattern can contain special leading sequences such as
+(*CRLF) to override what the application has set or what has been defaulted.
+Details are given in the section entitled
 <a href="#newlineseq">"Newline sequences"</a>
 above. There are also the (*UTF) and (*UCP) leading sequences that can be used
 to set UTF and Unicode property modes; they are equivalent to setting the
@@ -1717,11 +1720,11 @@
 PCRE2_UTF and PCRE2_UCP options, respectively. However, the application can set
 the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP options, which lock out the use of the
 (*UTF) and (*UCP) sequences.
-<a name="subpattern"></a></P>
-<br><a name="SEC14" href="#TOC1">SUBPATTERNS</a><br>
+<a name="group"></a></P>
+<br><a name="SEC14" href="#TOC1">GROUPS</a><br>
 <P>
-Subpatterns are delimited by parentheses (round brackets), which can be nested.
-Turning part of a pattern into a subpattern does two things:
+Groups are delimited by parentheses (round brackets), which can be nested.
+Turning part of a pattern into a group does two things:
 <br>
 <br>
 1. It localizes a set of alternatives. For example, the pattern
@@ -1732,16 +1735,16 @@
 match "cataract", "erpillar" or an empty string.
 <br>
 <br>
-2. It sets up the subpattern as a capturing subpattern. This means that, when
-the whole pattern matches, the portion of the subject string that matched the
-subpattern is passed back to the caller, separately from the portion that
-matched the whole pattern. (This applies only to the traditional matching
-function; the DFA matching function does not support capturing.)
+2. It creates a "capture group". This means that, when the whole pattern
+matches, the portion of the subject string that matched the group is passed
+back to the caller, separately from the portion that matched the whole pattern.
+(This applies only to the traditional matching function; the DFA matching
+function does not support capturing.)
 </P>
 <P>
 Opening parentheses are counted from left to right (starting from 1) to obtain
-numbers for the capturing subpatterns. For example, if the string "the red
-king" is matched against the pattern
+numbers for capture groups. For example, if the string "the red king" is
+matched against the pattern
 <pre>
   the ((red|white) (king|queen))
 </pre>
@@ -1750,36 +1753,35 @@
 </P>
 <P>
 The fact that plain parentheses fulfil two functions is not always helpful.
-There are often times when a grouping subpattern is required without a
-capturing requirement. If an opening parenthesis is followed by a question mark
-and a colon, the subpattern does not do any capturing, and is not counted when
-computing the number of any subsequent capturing subpatterns. For example, if
-the string "the white queen" is matched against the pattern
+There are often times when grouping is required without capturing. If an
+opening parenthesis is followed by a question mark and a colon, the group
+does not do any capturing, and is not counted when computing the number of any
+subsequent capture groups. For example, if the string "the white queen"
+is matched against the pattern
 <pre>
   the ((?:red|white) (king|queen))
 </pre>
 the captured substrings are "white queen" and "queen", and are numbered 1 and
-2. The maximum number of capturing subpatterns is 65535.
+2. The maximum number of capture groups is 65535.
 </P>
 <P>
 As a convenient shorthand, if any option settings are required at the start of
-a non-capturing subpattern, the option letters may appear between the "?" and
-the ":". Thus the two patterns
+a non-capturing group, the option letters may appear between the "?" and the
+":". Thus the two patterns
 <pre>
   (?i:saturday|sunday)
   (?:(?i)saturday|sunday)
 </pre>
 match exactly the same set of strings. Because alternative branches are tried
-from left to right, and options are not reset until the end of the subpattern
-is reached, an option setting in one branch does affect subsequent branches, so
+from left to right, and options are not reset until the end of the group is
+reached, an option setting in one branch does affect subsequent branches, so
 the above patterns match "SUNDAY" as well as "Saturday".
-<a name="dupsubpatternnumber"></a></P>
-<br><a name="SEC15" href="#TOC1">DUPLICATE SUBPATTERN NUMBERS</a><br>
+<a name="dupgroupnumber"></a></P>
+<br><a name="SEC15" href="#TOC1">DUPLICATE GROUP NUMBERS</a><br>
 <P>
-Perl 5.10 introduced a feature whereby each alternative in a subpattern uses
-the same numbers for its capturing parentheses. Such a subpattern starts with
-(?| and is itself a non-capturing subpattern. For example, consider this
-pattern:
+Perl 5.10 introduced a feature whereby each alternative in a group uses the
+same numbers for its capturing parentheses. Such a group starts with (?| and is
+itself a non-capturing group. For example, consider this pattern:
 <pre>
   (?|(Sat)ur|(Sun))day
 </pre>
@@ -1789,7 +1791,7 @@
 is useful when you want to capture part, but not all, of one of a number of
 alternatives. Inside a (?| group, parentheses are numbered as usual, but the
 number is reset at the start of each branch. The numbers of any capturing
-parentheses that follow the subpattern start after the highest number used in
+parentheses that follow the whole group start after the highest number used in
 any branch. The following example is taken from the Perl documentation. The
 numbers underneath show in which buffer the captured content will be stored.
 <pre>
@@ -1797,13 +1799,12 @@
   / ( a )  (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x
   # 1            2         2  3        2     3     4
 </pre>
-A backreference to a numbered subpattern uses the most recent value that is
-set for that number by any subpattern. The following pattern matches "abcabc"
-or "defdef":
+A backreference to a capture group uses the most recent value that is set for
+the group. The following pattern matches "abcabc" or "defdef":
 <pre>
   /(?|(abc)|(def))\1/
 </pre>
-In contrast, a subroutine call to a numbered subpattern always refers to the
+In contrast, a subroutine call to a capture group always refers to the
 first one in the pattern with the given number. The following pattern matches
 "abcabc" or "defabc":
 <pre>
@@ -1815,29 +1816,35 @@
 <P>
 If a
 <a href="#conditions">condition test</a>
-for a subpattern's having matched refers to a non-unique number, the test is
-true if any of the subpatterns of that number have matched.
+for a group's having matched refers to a non-unique number, the test is
+true if any group with that number has matched.
 </P>
 <P>
 An alternative approach to using this "branch reset" feature is to use
-duplicate named subpatterns, as described in the next section.
+duplicate named groups, as described in the next section.
 </P>
-<br><a name="SEC16" href="#TOC1">NAMED SUBPATTERNS</a><br>
+<br><a name="SEC16" href="#TOC1">NAMED CAPTURE GROUPS</a><br>
 <P>
-Identifying capturing parentheses by number is simple, but it can be very hard
-to keep track of the numbers in complicated patterns. Furthermore, if an
-expression is modified, the numbers may change. To help with this difficulty,
-PCRE2 supports the naming of capturing subpatterns. This feature was not added
-to Perl until release 5.10. Python had the feature earlier, and PCRE1
-introduced it at release 4.0, using the Python syntax. PCRE2 supports both the
-Perl and the Python syntax.
+Identifying capture groups by number is simple, but it can be very hard to keep
+track of the numbers in complicated patterns. Furthermore, if an expression is
+modified, the numbers may change. To help with this difficulty, PCRE2 supports
+the naming of capture groups. This feature was not added to Perl until release
+5.10. Python had the feature earlier, and PCRE1 introduced it at release 4.0,
+using the Python syntax. PCRE2 supports both the Perl and the Python syntax.
 </P>
 <P>
-In PCRE2, a capturing subpattern can be named in one of three ways:
-(?&#60;name&#62;...) or (?'name'...) as in Perl, or (?P&#60;name&#62;...) as in Python. Names
-consist of up to 32 alphanumeric characters and underscores, but must start
-with a non-digit. References to capturing parentheses from other parts of the
-pattern, such as
+In PCRE2, a capture group can be named in one of three ways: (?&#60;name&#62;...) or
+(?'name'...) as in Perl, or (?P&#60;name&#62;...) as in Python. Names may be up to 32
+code units long. When PCRE2_UTF is not set, they may contain only ASCII
+alphanumeric characters and underscores, but must start with a non-digit. When
+PCRE2_UTF is set, the syntax of group names is extended to allow any Unicode
+letter or Unicode decimal digit. In other words, group names must match one of
+these patterns:
+<pre>
+  ^[_A-Za-z][_A-Za-z0-9]*\z   when PCRE2_UTF is not set
+  ^[_\p{L}][_\p{L}\p{Nd}]*\z  when PCRE2_UTF is set
+</pre>
+References to capture groups from other parts of the pattern, such as
 <a href="#backreferences">backreferences,</a>
 <a href="#recursion">recursion,</a>
 and
@@ -1845,8 +1852,8 @@
 can all be made by name as well as by number.
 </P>
 <P>
-Named capturing parentheses are allocated numbers as well as names, exactly as
-if the names were not present. In both PCRE2 and Perl, capturing subpatterns
+Named capture groups are allocated numbers as well as names, exactly as
+if the names were not present. In both PCRE2 and Perl, capture groups
 are primarily identified by numbers; any names are just aliases for these
 numbers. The PCRE2 API provides function calls for extracting the complete
 name-to-number translation table from a compiled pattern, as well as
@@ -1853,10 +1860,10 @@
 convenience functions for extracting captured substrings by name.
 </P>
 <P>
-<b>Warning:</b> When more than one subpattern has the same number, as described
-in the previous section, a name given to one of them applies to all of them.
-Perl allows identically numbered subpatterns to have different names. Consider
-this pattern, where there are two capturing subpatterns, both numbered 1:
+<b>Warning:</b> When more than one capture group has the same number, as
+described in the previous section, a name given to one of them applies to all
+of them. Perl allows identically numbered groups to have different names.
+Consider this pattern, where there are two capture groups, both numbered 1:
 <pre>
   (?|(?&#60;AA&#62;aa)|(?&#60;BB&#62;bb))
 </pre>
@@ -1871,21 +1878,21 @@
 <pre>
   (?|(?&#60;AA&#62;aa)|(bb))
 </pre>
-Although the second subpattern number 1 is not explicitly named, the name AA is
-still an alias for subpattern 1. Whether the pattern matches "aa" or "bb", a
+Although the second group number 1 is not explicitly named, the name AA is
+still an alias for any group 1. Whether the pattern matches "aa" or "bb", a
 reference by name to group AA yields the matched string.
 </P>
 <P>
 By default, a name must be unique within a pattern, except that duplicate names
-are permitted for subpatterns with the same number, for example:
+are permitted for groups with the same number, for example:
 <pre>
   (?|(?&#60;AA&#62;aa)|(?&#60;AA&#62;bb))
 </pre>
 The duplicate name constraint can be disabled by setting the PCRE2_DUPNAMES
 option at compile time, or by the use of (?J) within the pattern. Duplicate
-names can be useful for patterns where only one instance of the named
-parentheses can match. Suppose you want to match the name of a weekday, either
-as a 3-letter abbreviation or as the full name, and in both cases you want to
+names can be useful for patterns where only one instance of the named capture
+group can match. Suppose you want to match the name of a weekday, either as a
+3-letter abbreviation or as the full name, and in both cases you want to
 extract the abbreviation. This pattern (ignoring the line breaks) does the job:
 <pre>
   (?&#60;DN&#62;Mon|Fri|Sun)(?:day)?|
@@ -1894,19 +1901,19 @@
   (?&#60;DN&#62;Thu)(?:rsday)?|
   (?&#60;DN&#62;Sat)(?:urday)?
 </pre>
-There are five capturing substrings, but only one is ever set after a match.
-The convenience functions for extracting the data by name returns the substring
-for the first (and in this example, the only) subpattern of that name that
-matched. This saves searching to find which numbered subpattern it was. (An
-alternative way of solving this problem is to use a "branch reset" subpattern,
-as described in the previous section.)
+There are five capture groups, but only one is ever set after a match. The
+convenience functions for extracting the data by name returns the substring for
+the first (and in this example, the only) group of that name that matched. This
+saves searching to find which numbered group it was. (An alternative way of
+solving this problem is to use a "branch reset" group, as described in the
+previous section.)
 </P>
 <P>
-If you make a backreference to a non-unique named subpattern from elsewhere in
-the pattern, the subpatterns to which the name refers are checked in the order
-in which they appear in the overall pattern. The first one that is set is used
-for the reference. For example, this pattern matches both "foofoo" and
-"barbar" but not "foobar" or "barfoo":
+If you make a backreference to a non-unique named group from elsewhere in the
+pattern, the groups to which the name refers are checked in the order in which
+they appear in the overall pattern. The first one that is set is used for the
+reference. For example, this pattern matches both "foofoo" and "barbar" but not
+"foobar" or "barfoo":
 <pre>
   (?:(?&#60;n&#62;foo)|(?&#60;n&#62;bar))\k&#60;n&#62;


@@ -1913,7 +1920,7 @@
 </PRE>
 </P>
 <P>
-If you make a subroutine call to a non-unique named subpattern, the one that
+If you make a subroutine call to a non-unique named group, the one that
 corresponds to the first occurrence of the name is used. In the absence of
 duplicate numbers this is the one with the lowest number.
 </P>
@@ -1921,11 +1928,11 @@
 If you use a named reference in a condition
 test (see the
 <a href="#conditions">section about conditions</a>
-below), either to check whether a subpattern has matched, or to check for
-recursion, all subpatterns with the same name are tested. If the condition is
-true for any one of them, the overall condition is true. This is the same
-behaviour as testing by number. For further details of the interfaces for
-handling named subpatterns, see the
+below), either to check whether a capture group has matched, or to check for
+recursion, all groups with the same name are tested. If the condition is true
+for any one of them, the overall condition is true. This is the same behaviour
+as testing by number. For further details of the interfaces for handling named
+capture groups, see the
 <a href="pcre2api.html"><b>pcre2api</b></a>
 documentation.
 </P>
@@ -1937,18 +1944,18 @@
   a literal data character
   the dot metacharacter
   the \C escape sequence
+  the \R escape sequence
   the \X escape sequence
-  the \R escape sequence
   an escape such as \d or \pL that matches a single character
   a character class
   a backreference
-  a parenthesized subpattern (including most assertions)
-  a subroutine call to a subpattern (recursive or otherwise)
+  a parenthesized group (including most assertions)
+  a subroutine call (recursive or otherwise)
 </pre>
 The general repetition quantifier specifies a minimum and maximum number of
 permitted matches, by giving the two numbers in curly brackets (braces),
 separated by a comma. The numbers must be less than 65536, and the first must
-be less than or equal to the second. For example:
+be less than or equal to the second. For example,
 <pre>
   z{2,4}
 </pre>
@@ -1978,12 +1985,12 @@
 <P>
 The quantifier {0} is permitted, causing the expression to behave as if the
 previous item and the quantifier were not present. This may be useful for
-subpatterns that are referenced as
-<a href="#subpatternsassubroutines">subroutines</a>
+capture groups that are referenced as
+<a href="#groupsassubroutines">subroutines</a>
 from elsewhere in the pattern (but see also the section entitled
-<a href="#subdefine">"Defining subpatterns for use by reference only"</a>
-below). Items other than subpatterns that have a {0} quantifier are omitted
-from the compiled pattern.
+<a href="#subdefine">"Defining capture groups for use by reference only"</a>
+below). Except for parenthesized groups, items that have a {0} quantifier are
+omitted from the compiled pattern.
 </P>
 <P>
 For convenience, the three most common quantifiers have single-character
@@ -1993,23 +2000,23 @@
   +    is equivalent to {1,}
   ?    is equivalent to {0,1}
 </pre>
-It is possible to construct infinite loops by following a subpattern that can
-match no characters with a quantifier that has no upper limit, for example:
+It is possible to construct infinite loops by following a group that can match
+no characters with a quantifier that has no upper limit, for example:
 <pre>
   (a?)*
 </pre>
 Earlier versions of Perl and PCRE1 used to give an error at compile time for
 such patterns. However, because there are cases where this can be useful, such
-patterns are now accepted, but if any repetition of the subpattern does in fact
+patterns are now accepted, but if any repetition of the group does in fact
 match no characters, the loop is forcibly broken.
 </P>
 <P>
-By default, the quantifiers are "greedy", that is, they match as much as
-possible (up to the maximum number of permitted times), without causing the
-rest of the pattern to fail. The classic example of where this gives problems
-is in trying to match comments in C programs. These appear between /* and */
-and within the comment, individual * and / characters may appear. An attempt to
-match C comments by applying the pattern
+By default, quantifiers are "greedy", that is, they match as much as possible
+(up to the maximum number of permitted times), without causing the rest of the
+pattern to fail. The classic example of where this gives problems is in trying
+to match comments in C programs. These appear between /* and */ and within the
+comment, individual * and / characters may appear. An attempt to match C
+comments by applying the pattern
 <pre>
   /\*.*\*/
 </pre>
@@ -2018,11 +2025,9 @@
   /* first comment */  not comment  /* second comment */
 </pre>
 fails, because it matches the entire string owing to the greediness of the .*
-item.
-</P>
-<P>
-If a quantifier is followed by a question mark, it ceases to be greedy, and
-instead matches the minimum number of times possible, so the pattern
+item. However, if a quantifier is followed by a question mark, it ceases to be
+greedy, and instead matches the minimum number of times possible, so the
+pattern
 <pre>
   /\*.*?\*/
 </pre>
@@ -2043,7 +2048,7 @@
 default behaviour.
 </P>
 <P>
-When a parenthesized subpattern is quantified with a minimum repeat count that
+When a parenthesized group is quantified with a minimum repeat count that
 is greater than 1 or with a limited maximum, more memory is required for the
 compiled pattern, in proportion to the size of the minimum or maximum.
 </P>
@@ -2083,15 +2088,14 @@
 PCRE2_NO_DOTSTAR_ANCHOR, to do so explicitly.
 </P>
 <P>
-When a capturing subpattern is repeated, the value captured is the substring
-that matched the final iteration. For example, after
+When a capture group is repeated, the value captured is the substring that
+matched the final iteration. For example, after
 <pre>
   (tweedle[dume]{3}\s*)+
 </pre>
 has matched "tweedledum tweedledee" the value of the captured substring is
-"tweedledee". However, if there are nested capturing subpatterns, the
-corresponding captured values may have been set in previous iterations. For
-example, after
+"tweedledee". However, if there are nested capture groups, the corresponding
+captured values may have been set in previous iterations. For example, after
 <pre>
   (a|(b))+
 </pre>
@@ -2115,7 +2119,7 @@
 action of the matcher is to try again with only 5 digits matching the \d+
 item, and then with 4, and so on, before ultimately failing. "Atomic grouping"
 (a term taken from Jeffrey Friedl's book) provides the means for specifying
-that once a subpattern has matched, it is not to be re-evaluated in this way.
+that once a group has matched, it is not to be re-evaluated in this way.
 </P>
 <P>
 If we use atomic grouping for the previous example, the matcher gives up
@@ -2129,26 +2133,26 @@
 <pre>
   (*atomic:\d+)foo
 </pre>
-This kind of parenthesis "locks up" the  part of the pattern it contains once
-it has matched, and a failure further into the pattern is prevented from
-backtracking into it. Backtracking past it to previous items, however, works as
-normal.
+This kind of parenthesized group "locks up" the  part of the pattern it
+contains once it has matched, and a failure further into the pattern is
+prevented from backtracking into it. Backtracking past it to previous items,
+however, works as normal.
 </P>
 <P>
-An alternative description is that a subpattern of this type matches exactly
-the string of characters that an identical standalone pattern would match, if
+An alternative description is that a group of this type matches exactly the
+string of characters that an identical standalone pattern would match, if
 anchored at the current point in the subject string.
 </P>
 <P>
-Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as
-the above example can be thought of as a maximizing repeat that must swallow
-everything it can. So, while both \d+ and \d+? are prepared to adjust the
-number of digits they match in order to make the rest of the pattern match,
-(?&#62;\d+) can only match an entire sequence of digits.
+Atomic groups are not capture groups. Simple cases such as the above example
+can be thought of as a maximizing repeat that must swallow everything it can.
+So, while both \d+ and \d+? are prepared to adjust the number of digits they
+match in order to make the rest of the pattern match, (?&#62;\d+) can only match
+an entire sequence of digits.
 </P>
 <P>
 Atomic groups in general can of course contain arbitrarily complicated
-subpatterns, and can be nested. However, when the subpattern for an atomic
+expressions, and can be nested. However, when the contents of an atomic
 group is just a single repeated item, as in the example above, a simpler
 notation, called a "possessive quantifier" can be used. This consists of an
 additional + character following a quantifier. Using this notation, the
@@ -2171,8 +2175,8 @@
 The possessive quantifier syntax is an extension to the Perl 5.8 syntax.
 Jeffrey Friedl originated the idea (and the name) in the first edition of his
 book. Mike McCloskey liked it, so implemented it when he built Sun's Java
-package, and PCRE1 copied it from there. It ultimately found its way into Perl
-at release 5.10.
+package, and PCRE1 copied it from there. It found its way into Perl at release
+5.10.
 </P>
 <P>
 PCRE2 has an optimization that automatically "possessifies" certain simple
@@ -2182,10 +2186,9 @@
 the pattern with (*NO_AUTO_POSSESS).
 </P>
 <P>
-When a pattern contains an unlimited repeat inside a subpattern that can itself
-be repeated an unlimited number of times, the use of an atomic group is the
-only way to avoid some failing matches taking a very long time indeed. The
-pattern
+When a pattern contains an unlimited repeat inside a group that can itself be
+repeated an unlimited number of times, the use of an atomic group is the only
+way to avoid some failing matches taking a very long time indeed. The pattern
 <pre>
   (\D+|&#60;\d+&#62;)*[!?]
 </pre>
@@ -2211,28 +2214,27 @@
 <br><a name="SEC19" href="#TOC1">BACKREFERENCES</a><br>
 <P>
 Outside a character class, a backslash followed by a digit greater than 0 (and
-possibly further digits) is a backreference to a capturing subpattern earlier
-(that is, to its left) in the pattern, provided there have been that many
-previous capturing left parentheses.
+possibly further digits) is a backreference to a capture group earlier (that
+is, to its left) in the pattern, provided there have been that many previous
+capture groups.
 </P>
 <P>
 However, if the decimal number following the backslash is less than 8, it is
-always taken as a backreference, and causes an error only if there are not
-that many capturing left parentheses in the entire pattern. In other words, the
-parentheses that are referenced need not be to the left of the reference for
-numbers less than 8. A "forward backreference" of this type can make sense
-when a repetition is involved and the subpattern to the right has participated
-in an earlier iteration.
+always taken as a backreference, and causes an error only if there are not that
+many capture groups in the entire pattern. In other words, the group that is
+referenced need not be to the left of the reference for numbers less than 8. A
+"forward backreference" of this type can make sense when a repetition is
+involved and the group to the right has participated in an earlier iteration.
 </P>
 <P>
-It is not possible to have a numerical "forward backreference" to a subpattern
-whose number is 8 or more using this syntax because a sequence such as \50 is
+It is not possible to have a numerical "forward backreference" to a group whose
+number is 8 or more using this syntax because a sequence such as \50 is
 interpreted as a character defined in octal. See the subsection entitled
 "Non-printing characters"
 <a href="#digitsafterbackslash">above</a>
-for further details of the handling of digits following a backslash. There is
-no such problem when named parentheses are used. A backreference to any
-subpattern is possible using named parentheses (see below).
+for further details of the handling of digits following a backslash. Other
+forms of backreferencing do not suffer from this restriction. In particular,
+there is no problem when named capture groups are used (see below).
 </P>
 <P>
 Another way of avoiding the ambiguity inherent in the use of digits following a
@@ -2250,22 +2252,22 @@
 <pre>
   (abc(def)ghi)\g{-1}
 </pre>
-The sequence \g{-1} is a reference to the most recently started capturing
-subpattern before \g, that is, is it equivalent to \2 in this example.
-Similarly, \g{-2} would be equivalent to \1. The use of relative references
-can be helpful in long patterns, and also in patterns that are created by
-joining together fragments that contain references within themselves.
+The sequence \g{-1} is a reference to the most recently started capture group
+before \g, that is, is it equivalent to \2 in this example. Similarly,
+\g{-2} would be equivalent to \1. The use of relative references can be
+helpful in long patterns, and also in patterns that are created by joining
+together fragments that contain references within themselves.
 </P>
 <P>
-The sequence \g{+1} is a reference to the next capturing subpattern. This kind
-of forward reference can be useful it patterns that repeat. Perl does not
-support the use of + in this way.
+The sequence \g{+1} is a reference to the next capture group. This kind of
+forward reference can be useful in patterns that repeat. Perl does not support
+the use of + in this way.
 </P>
 <P>
-A backreference matches whatever actually matched the capturing subpattern in
-the current subject string, rather than anything matching the subpattern
-itself (see
-<a href="#subpatternsassubroutines">"Subpatterns as subroutines"</a>
+A backreference matches whatever actually most recently matched the capture
+group in the current subject string, rather than anything at all that matches
+the group (see
+<a href="#groupsassubroutines">"Groups as subroutines"</a>
 below for a way of doing that). So the pattern
 <pre>
   (sens|respons)e and \1ibility
@@ -2277,15 +2279,15 @@
   ((?i)rah)\s+\1
 </pre>
 matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original
-capturing subpattern is matched caselessly.
+capture group is matched caselessly.
 </P>
 <P>
-There are several different ways of writing backreferences to named
-subpatterns. The .NET syntax \k{name} and the Perl syntax \k&#60;name&#62; or
-\k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified
+There are several different ways of writing backreferences to named capture
+groups. The .NET syntax \k{name} and the Perl syntax \k&#60;name&#62; or \k'name'
+are supported, as is the Python syntax (?P=name). Perl 5.10's unified
 backreference syntax, in which \g can be used for both numeric and named
-references, is also supported. We could rewrite the above example in any of
-the following ways:
+references, is also supported. We could rewrite the above example in any of the
+following ways:
 <pre>
   (?&#60;p1&#62;(?i)rah)\s+\k&#60;p1&#62;
   (?'p1'(?i)rah)\s+\k{p1}
@@ -2292,13 +2294,13 @@
   (?P&#60;p1&#62;(?i)rah)\s+(?P=p1)
   (?&#60;p1&#62;(?i)rah)\s+\g{p1}
 </pre>
-A subpattern that is referenced by name may appear in the pattern before or
+A capture group that is referenced by name may appear in the pattern before or
 after the reference.
 </P>
 <P>
-There may be more than one backreference to the same subpattern. If a
-subpattern has not actually been used in a particular match, any backreferences
-to it always fail by default. For example, the pattern
+There may be more than one backreference to the same group. If a group has not
+actually been used in a particular match, backreferences to it always fail by
+default. For example, the pattern
 <pre>
   (a|(bc))\2
 </pre>
@@ -2307,12 +2309,11 @@
 unset value matches an empty string.
 </P>
 <P>
-Because there may be many capturing parentheses in a pattern, all digits
-following a backslash are taken as part of a potential backreference number.
-If the pattern continues with a digit character, some delimiter must be used to
-terminate the backreference. If the PCRE2_EXTENDED or PCRE2_EXTENDED_MORE
-option is set, this can be white space. Otherwise, the \g{ syntax or an empty
-comment (see
+Because there may be many capture groups in a pattern, all digits following a
+backslash are taken as part of a potential backreference number. If the pattern
+continues with a digit character, some delimiter must be used to terminate the
+backreference. If the PCRE2_EXTENDED or PCRE2_EXTENDED_MORE option is set, this
+can be white space. Otherwise, the \g{} syntax or an empty comment (see
 <a href="#comments">"Comments"</a>
 below) can be used.
 </P>
@@ -2320,19 +2321,18 @@
 Recursive backreferences
 </b><br>
 <P>
-A backreference that occurs inside the parentheses to which it refers fails
-when the subpattern is first used, so, for example, (a\1) never matches.
-However, such references can be useful inside repeated subpatterns. For
-example, the pattern
+A backreference that occurs inside the group to which it refers fails when the
+group is first used, so, for example, (a\1) never matches. However, such
+references can be useful inside repeated groups. For example, the pattern
 <pre>
   (a|b\1)+
 </pre>
 matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of
-the subpattern, the backreference matches the character string corresponding
-to the previous iteration. In order for this to work, the pattern must be such
-that the first iteration does not need to match the backreference. This can be
-done using alternation, as in the example above, or by a quantifier with a
-minimum of zero.
+the group, the backreference matches the character string corresponding to the
+previous iteration. In order for this to work, the pattern must be such that
+the first iteration does not need to match the backreference. This can be done
+using alternation, as in the example above, or by a quantifier with a minimum
+of zero.
 </P>
 <P>
 Backreferences of this type cause the group that they reference to be treated
@@ -2349,27 +2349,27 @@
 <a href="#smallassertions">above.</a>
 </P>
 <P>
-More complicated assertions are coded as subpatterns. There are two kinds:
-those that look ahead of the current position in the subject string, and those
-that look behind it, and in each case an assertion may be positive (must match
-for the assertion to be true) or negative (must not match for the assertion to
-be true). An assertion subpattern is matched in the normal way, and if it is
-true, matching continues after it, but with the matching position in the
-subject string is was it was before the assertion was processed.
+More complicated assertions are coded as parenthesized groups. There are two
+kinds: those that look ahead of the current position in the subject string, and
+those that look behind it, and in each case an assertion may be positive (must
+match for the assertion to be true) or negative (must not match for the
+assertion to be true). An assertion group is matched in the normal way,
+and if it is true, matching continues after it, but with the matching position
+in the subject string is was it was before the assertion was processed.
 </P>
 <P>
 A lookaround assertion may also appear as the condition in a
-<a href="#conditions">conditional subpattern</a>
+<a href="#conditions">conditional group</a>
 (see below). In this case, the result of matching the assertion determines
 which branch of the condition is followed.
 </P>
 <P>
-Assertion subpatterns are not capturing subpatterns. If an assertion contains
-capturing subpatterns within it, these are counted for the purposes of
-numbering the capturing subpatterns in the whole pattern. Within each branch of
-an assertion, locally captured substrings may be referenced in the usual way.
-For example, a sequence such as (.)\g{-1} can be used to check that two
-adjacent characters are the same.
+Assertion groups are not capture groups. If an assertion contains capture
+groups within it, these are counted for the purposes of numbering the capture
+groups in the whole pattern. Within each branch of an assertion, locally
+captured substrings may be referenced in the usual way. For example, a sequence
+such as (.)\g{-1} can be used to check that two adjacent characters are the
+same.
 </P>
 <P>
 When a branch within an assertion fails to match, any substrings that were
@@ -2384,7 +2384,7 @@
 branch are retained, and matching continues with the next pattern item after
 the assertion. For a negative assertion, a matching branch means that the
 assertion is not true. If such an assertion is being used as a condition in a
-<a href="#conditions">conditional subpattern</a>
+<a href="#conditions">conditional group</a>
 (see below), captured substrings are retained, because matching continues with
 the "no" branch of the condition. For other failing negative assertions,
 control passes to the previous backtracking point, thus discarding any captured
@@ -2391,17 +2391,17 @@
 strings within the assertion.
 </P>
 <P>
-For compatibility with Perl, most assertion subpatterns may be repeated; though
-it makes no sense to assert the same thing several times, the side effect of
-capturing parentheses may occasionally be useful. However, an assertion that
-forms the condition for a conditional subpattern may not be quantified. In
-practice, for other assertions, there only three cases:
+For compatibility with Perl, most assertion groups may be repeated; though it
+makes no sense to assert the same thing several times, the side effect of
+capturing may occasionally be useful. However, an assertion that forms the
+condition for a conditional group may not be quantified. In practice, for
+other assertions, there only three cases:
 <br>
 <br>
 (1) If the quantifier is {0}, the assertion is never obeyed during matching.
-However, it may contain internal capturing parenthesized groups that are called
-from elsewhere via the
-<a href="#subpatternsassubroutines">subroutine mechanism.</a>
+However, it may contain internal capture groups that are called from elsewhere
+via the
+<a href="#groupsassubroutines">subroutine mechanism.</a>
 <br>
 <br>
 (2) If quantifier is {0,n} where n is greater than zero, it is treated as if it
@@ -2427,9 +2427,9 @@
   (*positive_lookbehind: or (*plb: is the same as (?&#60;=
   (*negative_lookbehind: or (*nlb: is the same as (?&#60;!
 </pre>
-For example, (*pla:foo) is the same assertion as (?=foo). However, in the
-following sections, the various assertions are described using the original
-symbolic forms.
+For example, (*pla:foo) is the same assertion as (?=foo). In the following
+sections, the various assertions are described using the original symbolic
+forms.
 </P>
 <br><b>
 Lookahead assertions
@@ -2513,9 +2513,9 @@
 permitted in lookbehinds.
 </P>
 <P>
-<a href="#subpatternsassubroutines">"Subroutine"</a>
+<a href="#groupsassubroutines">"Subroutine"</a>
 calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long
-as the subpattern matches a fixed-length string. However,
+as the called capture group matches a fixed-length string. However,
 <a href="#recursion">recursion,</a>
 that is, a "subroutine" call into a group that is already active,
 is not supported.
@@ -2524,10 +2524,10 @@
 Perl does not support backreferences in lookbehinds. PCRE2 does support them,
 but only if certain conditions are met. The PCRE2_MATCH_UNSET_BACKREF option
 must not be set, there must be no use of (?| in the pattern (it creates
-duplicate subpattern numbers), and if the backreference is by name, the name
-must be unique. Of course, the referenced subpattern must itself be of fixed
-length. The following pattern matches words containing at least two characters
-that begin and end with the same character:
+duplicate group numbers), and if the backreference is by name, the name
+must be unique. Of course, the referenced group must itself match a fixed
+length substring. The following pattern matches words containing at least two
+characters that begin and end with the same character:
 <pre>
    \b(\w)\w++(?&#60;=\1)
 </PRE>
@@ -2653,15 +2653,15 @@
 <P>
 <b>Warning:</b> The (*ACCEPT) control verb
 <a href="#acceptverb">(see below)</a>
-should not be used within a script run subpattern, because it causes an
-immediate exit from the subpattern, bypassing the script run checking.
+should not be used within a script run group, because it causes an immediate
+exit from the group, bypassing the script run checking.
 <a name="conditions"></a></P>
-<br><a name="SEC22" href="#TOC1">CONDITIONAL SUBPATTERNS</a><br>
+<br><a name="SEC22" href="#TOC1">CONDITIONAL GROUPS</a><br>
 <P>
-It is possible to cause the matching process to obey a subpattern
-conditionally or to choose between two alternative subpatterns, depending on
-the result of an assertion, or whether a specific capturing subpattern has
-already been matched. The two possible forms of conditional subpattern are:
+It is possible to cause the matching process to obey a pattern fragment
+conditionally or to choose between two alternative fragments, depending on
+the result of an assertion, or whether a specific capture group has
+already been matched. The two possible forms of conditional group are:
 <pre>
   (?(condition)yes-pattern)
   (?(condition)yes-pattern|no-pattern)
@@ -2669,11 +2669,10 @@
 If the condition is satisfied, the yes-pattern is used; otherwise the
 no-pattern (if present) is used. An absent no-pattern is equivalent to an empty
 string (it always matches). If there are more than two alternatives in the
-subpattern, a compile-time error occurs. Each of the two alternatives may
-itself contain nested subpatterns of any form, including conditional
-subpatterns; the restriction to two alternatives applies only at the level of
-the condition. This pattern fragment is an example where the alternatives are
-complex:
+group, a compile-time error occurs. Each of the two alternatives may itself
+contain nested groups of any form, including conditional groups; the
+restriction to two alternatives applies only at the level of the condition
+itself. This pattern fragment is an example where the alternatives are complex:
 <pre>
   (?(1) (A|B|C) | (D | (?(2)E|F) | E) )


@@ -2680,25 +2679,24 @@
 </PRE>
 </P>
 <P>
-There are five kinds of condition: references to subpatterns, references to
+There are five kinds of condition: references to capture groups, references to
 recursion, two pseudo-conditions called DEFINE and VERSION, and assertions.
 </P>
 <br><b>
-Checking for a used subpattern by number
+Checking for a used capture group by number
 </b><br>
 <P>
 If the text between the parentheses consists of a sequence of digits, the
-condition is true if a capturing subpattern of that number has previously
-matched. If there is more than one capturing subpattern with the same number
-(see the earlier
-<a href="#recursion">section about duplicate subpattern numbers),</a>
+condition is true if a capture group of that number has previously matched. If
+there is more than one capture group with the same number (see the earlier
+<a href="#recursion">section about duplicate group numbers),</a>
 the condition is true if any of them have matched. An alternative notation is
-to precede the digits with a plus or minus sign. In this case, the subpattern
-number is relative rather than absolute. The most recently opened parentheses
-can be referenced by (?(-1), the next most recent by (?(-2), and so on. Inside
-loops it can also make sense to refer to subsequent groups. The next
-parentheses to be opened can be referenced as (?(+1), and so on. (The value
-zero in any of these forms is not used; it provokes a compile-time error.)
+to precede the digits with a plus or minus sign. In this case, the group number
+is relative rather than absolute. The most recently opened capture group can be
+referenced by (?(-1), the next most recent by (?(-2), and so on. Inside loops
+it can also make sense to refer to subsequent groups. The next capture group
+can be referenced as (?(+1), and so on. (The value zero in any of these forms
+is not used; it provokes a compile-time error.)
 </P>
 <P>
 Consider the following pattern, which contains non-significant white space to
@@ -2710,12 +2708,12 @@
 The first part matches an optional opening parenthesis, and if that
 character is present, sets it as the first captured substring. The second part
 matches one or more characters that are not parentheses. The third part is a
-conditional subpattern that tests whether or not the first set of parentheses
-matched. If they did, that is, if subject started with an opening parenthesis,
+conditional group that tests whether or not the first capture group
+matched. If it did, that is, if subject started with an opening parenthesis,
 the condition is true, and so the yes-pattern is executed and a closing
 parenthesis is required. Otherwise, since no-pattern is not present, the
-subpattern matches nothing. In other words, this pattern matches a sequence of
-non-parentheses, optionally enclosed in parentheses.
+conditional group matches nothing. In other words, this pattern matches a
+sequence of non-parentheses, optionally enclosed in parentheses.
 </P>
 <P>
 If you were embedding this pattern in a larger one, you could use a relative
@@ -2726,22 +2724,20 @@
 This makes the fragment independent of the parentheses in the larger pattern.
 </P>
 <br><b>
-Checking for a used subpattern by name
+Checking for a used capture group by name
 </b><br>
 <P>
 Perl uses the syntax (?(&#60;name&#62;)...) or (?('name')...) to test for a used
-subpattern by name. For compatibility with earlier versions of PCRE1, which had
-this facility before Perl, the syntax (?(name)...) is also recognized. Note,
-however, that undelimited names consisting of the letter R followed by digits
-are ambiguous (see the following section).
-</P>
-<P>
-Rewriting the above example to use a named subpattern gives this:
+capture group by name. For compatibility with earlier versions of PCRE1, which
+had this facility before Perl, the syntax (?(name)...) is also recognized.
+Note, however, that undelimited names consisting of the letter R followed by
+digits are ambiguous (see the following section). Rewriting the above example
+to use a named group gives this:
 <pre>
   (?&#60;OPEN&#62; \( )?    [^()]+    (?(&#60;OPEN&#62;) \) )
 </pre>
 If the name used in a condition of this kind is a duplicate, the test is
-applied to all subpatterns of the same name, and is true if any one of them has
+applied to all groups of the same name, and is true if any one of them has
 matched.
 </P>
 <br><b>
@@ -2753,20 +2749,20 @@
 sections entitled
 <a href="#recursion">"Recursive patterns"</a>
 and
-<a href="#subpatternsassubroutines">"Subpatterns as subroutines"</a>
-below for details of recursion and subpattern calls.
+<a href="#groupsassubroutines">"Groups as subroutines"</a>
+below for details of recursion and subroutine calls.
 </P>
 <P>
-If a condition is the string (R), and there is no subpattern with the name R,
-the condition is true if matching is currently in a recursion or subroutine
-call to the whole pattern or any subpattern. If digits follow the letter R, and
-there is no subpattern with that name, the condition is true if the most recent
-call is into a subpattern with the given number, which must exist somewhere in
-the overall pattern. This is a contrived example that is equivalent to a+b:
+If a condition is the string (R), and there is no capture group with the name
+R, the condition is true if matching is currently in a recursion or subroutine
+call to the whole pattern or any capture group. If digits follow the letter R,
+and there is no group with that name, the condition is true if the most recent
+call is into a group with the given number, which must exist somewhere in the
+overall pattern. This is a contrived example that is equivalent to a+b:
 <pre>
   ((?(R1)a+|(?1)b))
 </pre>
-However, in both cases, if there is a subpattern with a matching name, the
+However, in both cases, if there is a capture group with a matching name, the
 condition tests for its being set, as described in the section above, instead
 of testing for recursion. For example, creating a group with the name R1 by
 adding (?&#60;R1&#62;) to the above pattern completely changes its meaning.
@@ -2776,13 +2772,13 @@
 <pre>
   (?(R&name)...)
 </pre>
-the condition is true if the most recent recursion is into a subpattern of that
-name (which must exist within the pattern).
+the condition is true if the most recent recursion is into a group of that name
+(which must exist within the pattern).
 </P>
 <P>
 This condition does not check the entire recursion stack. It tests only the
 current level. If the name used in a condition of this kind is a duplicate, the
-test is applied to all subpatterns of the same name, and is true if any one of
+test is applied to all groups of the same name, and is true if any one of
 them is the most recent recursion.
 </P>
 <P>
@@ -2789,15 +2785,15 @@
 At "top level", all these recursion test conditions are false.
 <a name="subdefine"></a></P>
 <br><b>
-Defining subpatterns for use by reference only
+Defining capture groups for use by reference only
 </b><br>
 <P>
 If the condition is the string (DEFINE), the condition is always false, even if
 there is a group with the name DEFINE. In this case, there may be only one
-alternative in the subpattern. It is always skipped if control reaches this
-point in the pattern; the idea of DEFINE is that it can be used to define
-subroutines that can be referenced from elsewhere. (The use of
-<a href="#subpatternsassubroutines">subroutines</a>
+alternative in the rest of the conditional group. It is always skipped if
+control reaches this point in the pattern; the idea of DEFINE is that it can be
+used to define subroutines that can be referenced from elsewhere. (The use of
+<a href="#groupsassubroutines">subroutines</a>
 is described below.) For example, a pattern to match an IPv4 address such as
 "192.168.23.245" could be written like this (ignore white space and line
 breaks):
@@ -2834,10 +2830,10 @@
 Assertion conditions
 </b><br>
 <P>
-If the condition is not in any of the above formats, it must be an assertion.
-This may be a positive or negative lookahead or lookbehind assertion. Consider
-this pattern, again containing non-significant white space, and with the two
-alternatives on the second line:
+If the condition is not in any of the above formats, it must be a parenthesized
+assertion. This may be a positive or negative lookahead or lookbehind
+assertion. Consider this pattern, again containing non-significant white space,
+and with the two alternatives on the second line:
 <pre>
   (?(?=[^a-z]*[a-z])
   \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} )
@@ -2850,11 +2846,11 @@
 dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits.
 </P>
 <P>
-When an assertion that is a condition contains capturing subpatterns, any
+When an assertion that is a condition contains capture groups, any
 capturing that occurs in a matching branch is retained afterwards, for both
 positive and negative assertions, because matching always continues after the
 assertion, whether it succeeds or fails. (Compare non-conditional assertions,
-when captures are retained only for positive assertions that succeed.)
+for which captures are retained only for positive assertions that succeed.)
 <a name="comments"></a></P>
 <br><a name="SEC23" href="#TOC1">COMMENTS</a><br>
 <P>
@@ -2861,7 +2857,7 @@
 There are two ways of including comments in patterns that are processed by
 PCRE2. In both cases, the start of the comment must not be in a character
 class, nor in the middle of any other sequence of related characters such as
-(?: or a subpattern name or number. The characters that make up a comment play
+(?: or a group name or number. The characters that make up a comment play
 no part in the pattern matching.
 </P>
 <P>
@@ -2908,14 +2904,14 @@
 <P>
 Obviously, PCRE2 cannot support the interpolation of Perl code. Instead, it
 supports special syntax for recursion of the entire pattern, and also for
-individual subpattern recursion. After its introduction in PCRE1 and Python,
+individual capture group recursion. After its introduction in PCRE1 and Python,
 this kind of recursion was subsequently introduced into Perl at release 5.10.
 </P>
 <P>
 A special item that consists of (? followed by a number greater than zero and a
-closing parenthesis is a recursive subroutine call of the subpattern of the
-given number, provided that it occurs inside that subpattern. (If not, it is a
-<a href="#subpatternsassubroutines">non-recursive subroutine</a>
+closing parenthesis is a recursive subroutine call of the capture group of the
+given number, provided that it occurs inside that group. (If not, it is a
+<a href="#groupsassubroutines">non-recursive subroutine</a>
 call, which is described in the next section.) The special item (?R) or (?0) is
 a recursive call of the entire regular expression.
 </P>
@@ -2949,13 +2945,13 @@
 </P>
 <P>
 Be aware however, that if
-<a href="#dupsubpatternnumber">duplicate subpattern numbers</a>
-are in use, relative references refer to the earliest subpattern with the
+<a href="#dupgroupnumber">duplicate capture group numbers</a>
+are in use, relative references refer to the earliest group with the
 appropriate number. Consider, for example:
 <pre>
   (?|(a)|(b)) (c) (?-2)
 </pre>
-The first two capturing groups (a) and (b) are both numbered 1, and group (c)
+The first two capture groups (a) and (b) are both numbered 1, and group (c)
 is number 2. When the reference (?-2) is encountered, the second most recently
 opened parentheses has the number 1, but it is the first such group (the (a)
 group) to which the recursion refers. This would be the same if an absolute
@@ -2963,10 +2959,10 @@
 shorthand for computing a group number.
 </P>
 <P>
-It is also possible to refer to subsequently opened parentheses, by writing
+It is also possible to refer to subsequent capture groups, by writing
 references such as (?+2). However, these cannot be recursive because the
 reference is not inside the parentheses that are referenced. They are always
-<a href="#subpatternsassubroutines">non-recursive subroutine</a>
+<a href="#groupsassubroutines">non-recursive subroutine</a>
 calls, as described in the next section.
 </P>
 <P>
@@ -2976,7 +2972,7 @@
 <pre>
   (?&#60;pn&#62; \( ( [^()]++ | (?&pn) )* \) )
 </pre>
-If there is more than one subpattern with the same name, the earliest one is
+If there is more than one group with the same name, the earliest one is
 used.
 </P>
 <P>
@@ -3002,9 +2998,9 @@
   (ab(cd)ef)
 </pre>
 the value for the inner capturing parentheses (numbered 2) is "ef", which is
-the last value taken on at the top level. If a capturing subpattern is not
-matched at the top level, its final captured value is unset, even if it was
-(temporarily) set at a deeper level during the matching process.
+the last value taken on at the top level. If a capture group is not matched at
+the top level, its final captured value is unset, even if it was (temporarily)
+set at a deeper level during the matching process.
 </P>
 <P>
 Do not confuse the (?R) item with the condition (R), which tests for recursion.
@@ -3014,9 +3010,9 @@
 <pre>
   &#60; (?: (?(R) \d++  | [^&#60;&#62;]*+) | (?R)) * &#62;
 </pre>
-In this pattern, (?(R) is the start of a conditional subpattern, with two
-different alternatives for the recursive and non-recursive cases. The (?R) item
-is the actual recursive call.
+In this pattern, (?(R) is the start of a conditional group, with two different
+alternatives for the recursive and non-recursive cases. The (?R) item is the
+actual recursive call.
 <a name="recursiondifference"></a></P>
 <br><b>
 Differences in recursion processing between PCRE2 and Perl
@@ -3026,7 +3022,7 @@
 </P>
 <P>
 Before release 10.30, recursion processing in PCRE2 differed from Perl in that
-a recursive subpattern call was always treated as an atomic group. That is,
+a recursive subroutine call was always treated as an atomic group. That is,
 once it had matched some of the subject string, it was never re-entered, even
 if it contained untried alternatives and there was a subsequent matching
 failure. (Historical note: PCRE implemented recursion before Perl did.)
@@ -3062,7 +3058,7 @@
 <P>
 Another way in which PCRE2 and Perl used to differ in their recursion
 processing is in the handling of captured values. Formerly in Perl, when a
-subpattern was called recursively or as a subpattern (see the next section), it
+group was called recursively or as a subroutine (see the next section), it
 had no access to any values that were captured outside the recursion, whereas
 in PCRE2 these values can be referenced. Consider this pattern:
 <pre>
@@ -3073,16 +3069,15 @@
 alternative matches "a" and then recurses. In the recursion, \1 does now match
 "b" and so the whole match succeeds. This match used to fail in Perl, but in
 later versions (I tried 5.024) it now works.
-<a name="subpatternsassubroutines"></a></P>
-<br><a name="SEC25" href="#TOC1">SUBPATTERNS AS SUBROUTINES</a><br>
+<a name="groupsassubroutines"></a></P>
+<br><a name="SEC25" href="#TOC1">GROUPS AS SUBROUTINES</a><br>
 <P>
-If the syntax for a recursive subpattern call (either by number or by
-name) is used outside the parentheses to which it refers, it operates a bit
-like a subroutine in a programming language. More accurately, PCRE2 treats the
-referenced subpattern as an independent subpattern which it tries to match at
-the current matching position. The called subpattern may be defined before or
-after the reference. A numbered reference can be absolute or relative, as in
-these examples:
+If the syntax for a recursive group call (either by number or by name) is used
+outside the parentheses to which it refers, it operates a bit like a subroutine
+in a programming language. More accurately, PCRE2 treats the referenced group
+as an independent subpattern which it tries to match at the current matching
+position. The called group may be defined before or after the reference. A
+numbered reference can be absolute or relative, as in these examples:
 <pre>
   (...(absolute)...)...(?2)...
   (...(relative)...)...(?-1)...
@@ -3107,7 +3102,7 @@
 call revert to their previous values afterwards.
 </P>
 <P>
-Processing options such as case-independence are fixed when a subpattern is
+Processing options such as case-independence are fixed when a group is
 defined, so if it is used as a subroutine, such options cannot be changed for
 different calls. For example, consider this pattern:
 <pre>
@@ -3114,12 +3109,12 @@
   (abc)(?i:(?-1))
 </pre>
 It matches "abcabc". It does not match "abcABC" because the change of
-processing option does not affect the called subpattern.
+processing option does not affect the called group.
 </P>
 <P>
 The behaviour of
 <a href="#backtrackcontrol">backtracking control verbs</a>
-in subpatterns when called as subroutines is described in the section entitled
+in groups when called as subroutines is described in the section entitled
 <a href="#btsub">"Backtracking verbs in subroutines"</a>
 below.
 <a name="onigurumasubroutines"></a></P>
@@ -3127,8 +3122,8 @@
 <P>
 For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or
 a number enclosed either in angle brackets or single quotes, is an alternative
-syntax for referencing a subpattern as a subroutine, possibly recursively. Here
-are two of the examples used above, rewritten using this syntax:
+syntax for calling a group as a subroutine, possibly recursively. Here are two
+of the examples used above, rewritten using this syntax:
 <pre>
   (?&#60;pn&#62; \( ( (?&#62;[^()]+) | \g&#60;pn&#62; )* \) )
   (sens|respons)e and \g'1'ibility
@@ -3265,7 +3260,7 @@
 <a href="#btrepeat">repeated groups,</a>
 <a href="#btassert">assertions,</a>
 and in
-<a href="#btsub">subpatterns called as subroutines</a>
+<a href="#btsub">capture groups called as subroutines</a>
 (whether or not recursively) is documented below.
 <a name="nooptimize"></a></P>
 <br><b>
@@ -3299,8 +3294,8 @@
    (*ACCEPT) or (*ACCEPT:NAME)
 </pre>
 This verb causes the match to end successfully, skipping the remainder of the
-pattern. However, when it is inside a subpattern that is called as a
-subroutine, only that subpattern is ended successfully. Matching then continues
+pattern. However, when it is inside a capture group that is called as a
+subroutine, only that group is ended successfully. Matching then continues
 at the outer level. If (*ACCEPT) in triggered in a positive assertion, the
 assertion succeeds; in a negative assertion, the assertion fails.
 </P>
@@ -3314,9 +3309,8 @@
 the outer parentheses.
 </P>
 <P>
-<b>Warning:</b> (*ACCEPT) should not be used within a script run subpattern,
-because it causes an immediate exit from the subpattern, bypassing the script
-run checking.
+<b>Warning:</b> (*ACCEPT) should not be used within a script run group, because
+it causes an immediate exit from the group, bypassing the script run checking.
 <pre>
   (*FAIL) or (*FAIL:NAME)
 </pre>
@@ -3563,31 +3557,29 @@
 ignoring those set by other backtracking verbs.
 </P>
 <P>
-A subpattern that does not contain a | character is just a part of the
-enclosing alternative; it is not a nested alternation with only one
-alternative. The effect of (*THEN) extends beyond such a subpattern to the
-enclosing alternative. Consider this pattern, where A, B, etc. are complex
-pattern fragments that do not contain any | characters at this level:
+A group that does not contain a | character is just a part of the enclosing
+alternative; it is not a nested alternation with only one alternative. The
+effect of (*THEN) extends beyond such a group to the enclosing alternative.
+Consider this pattern, where A, B, etc. are complex pattern fragments that do
+not contain any | characters at this level:
 <pre>
   A (B(*THEN)C) | D
 </pre>
 If A and B are matched, but there is a failure in C, matching does not
 backtrack into A; instead it moves to the next alternative, that is, D.
-However, if the subpattern containing (*THEN) is given an alternative, it
+However, if the group containing (*THEN) is given an alternative, it
 behaves differently:
 <pre>
   A (B(*THEN)C | (*FAIL)) | D
 </pre>
-The effect of (*THEN) is now confined to the inner subpattern. After a failure
-in C, matching moves to (*FAIL), which causes the whole subpattern to fail
-because there are no more alternatives to try. In this case, matching does now
-backtrack into A.
+The effect of (*THEN) is now confined to the inner group. After a failure in C,
+matching moves to (*FAIL), which causes the whole group to fail because there
+are no more alternatives to try. In this case, matching does backtrack into A.
 </P>
 <P>
-Note that a conditional subpattern is not considered as having two
-alternatives, because only one is ever used. In other words, the | character in
-a conditional subpattern has a different meaning. Ignoring white space,
-consider:
+Note that a conditional group is not considered as having two alternatives,
+because only one is ever used. In other words, the | character in a conditional
+group has a different meaning. Ignoring white space, consider:
 <pre>
   ^.*? (?(?=a) a | b(*THEN)c )
 </pre>
@@ -3595,7 +3587,7 @@
 it initially matches zero characters. The condition (?=a) then fails, the
 character "b" is matched, but "c" is not. At this point, matching does not
 backtrack to .*? as might perhaps be expected from the presence of the |
-character. The conditional subpattern is part of the single alternative that
+character. The conditional group is part of the single alternative that
 comprises the whole pattern, and so the match fails. (If there was a backtrack
 into .*?, allowing it to match "b", the match would succeed.)
 </P>
@@ -3651,7 +3643,7 @@
 (*FAIL) in any assertion has its normal effect: it forces an immediate
 backtrack. The behaviour of the other backtracking verbs depends on whether or
 not the assertion is standalone or acting as the condition in a conditional
-subpattern.
+group.
 </P>
 <P>
 (*ACCEPT) in a standalone positive assertion causes the assertion to succeed
@@ -3690,29 +3682,28 @@
 Backtracking verbs in subroutines
 </b><br>
 <P>
-These behaviours occur whether or not the subpattern is called recursively.
+These behaviours occur whether or not the group is called recursively.
 </P>
 <P>
-(*ACCEPT) in a subpattern called as a subroutine causes the subroutine match to
+(*ACCEPT) in a group called as a subroutine causes the subroutine match to
 succeed without any further processing. Matching then continues after the
 subroutine call. Perl documents this behaviour. Perl's treatment of the other
 verbs in subroutines is different in some cases.
 </P>
 <P>
-(*FAIL) in a subpattern called as a subroutine has its normal effect: it forces
+(*FAIL) in a group called as a subroutine has its normal effect: it forces
 an immediate backtrack.
 </P>
 <P>
 (*COMMIT), (*SKIP), and (*PRUNE) cause the subroutine match to fail when
-triggered by being backtracked to in a subpattern called as a subroutine. There
-is then a backtrack at the outer level.
+triggered by being backtracked to in a group called as a subroutine. There is
+then a backtrack at the outer level.
 </P>
 <P>
 (*THEN), when triggered, skips to the next alternative in the innermost
-enclosing group within the subpattern that has alternatives (its normal
-behaviour). However, if there is no such group within the subroutine
-subpattern, the subroutine match fails and there is a backtrack at the outer
-level.
+enclosing group that has alternatives (its normal behaviour). However, if there
+is no such group within the subroutine's group, the subroutine match fails and
+there is a backtrack at the outer level.
 </P>
 <br><a name="SEC29" href="#TOC1">SEE ALSO</a><br>
 <P>
@@ -3730,9 +3721,9 @@
 </P>
 <br><a name="SEC31" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 27 November 2018
+Last updated: 04 February 2019
 <br>
-Copyright &copy; 1997-2018 University of Cambridge.
+Copyright &copy; 1997-2019 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE2 index page</a>.


Modified: code/trunk/doc/html/pcre2perform.html
===================================================================
--- code/trunk/doc/html/pcre2perform.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2perform.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -31,9 +31,9 @@
 Patterns are compiled by PCRE2 into a reasonably efficient interpretive code,
 so that most simple patterns do not use much memory for storing the compiled
 version. However, there is one case where the memory usage of a compiled
-pattern can be unexpectedly large. If a parenthesized subpattern has a
-quantifier with a minimum greater than 1 and/or a limited maximum, the whole
-subpattern is repeated in the compiled code. For example, the pattern
+pattern can be unexpectedly large. If a parenthesized group has a quantifier
+with a minimum greater than 1 and/or a limited maximum, the whole group is
+repeated in the compiled code. For example, the pattern
 <pre>
   (abc|def){2,4}
 </pre>
@@ -252,9 +252,9 @@
 </P>
 <br><a name="SEC6" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 25 April 2018
+Last updated: 03 February 2019
 <br>
-Copyright &copy; 1997-2018 University of Cambridge.
+Copyright &copy; 1997-2019 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE2 index page</a>.


Modified: code/trunk/doc/html/pcre2syntax.html
===================================================================
--- code/trunk/doc/html/pcre2syntax.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2syntax.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -424,20 +424,23 @@
 <br><a name="SEC13" href="#TOC1">CAPTURING</a><br>
 <P>
 <pre>
-  (...)           capturing group
-  (?&#60;name&#62;...)    named capturing group (Perl)
-  (?'name'...)    named capturing group (Perl)
-  (?P&#60;name&#62;...)   named capturing group (Python)
-  (?:...)         non-capturing group
-  (?|...)         non-capturing group; reset group numbers for
-                   capturing groups in each alternative
-</PRE>
+  (...)           capture group
+  (?&#60;name&#62;...)    named capture group (Perl)
+  (?'name'...)    named capture group (Perl)
+  (?P&#60;name&#62;...)   named capture group (Python)
+  (?:...)         non-capture group
+  (?|...)         non-capture group; reset group numbers for
+                   capture groups in each alternative
+</pre>
+In non-UTF modes, names may contain underscores and ASCII letters and digits;
+in UTF modes, any Unicode letters and Unicode decimal digits are permitted. In
+both cases, a name must not start with a digit.
 </P>
 <br><a name="SEC14" href="#TOC1">ATOMIC GROUPS</a><br>
 <P>
 <pre>
-  (?&#62;...)         atomic, non-capturing group
-  (*atomic:...)   atomic, non-capturing group
+  (?&#62;...)         atomic non-capture group
+  (*atomic:...)   atomic non-capture group
 </PRE>
 </P>
 <br><a name="SEC15" href="#TOC1">COMMENT</a><br>
@@ -465,7 +468,7 @@
 Unsetting x or xx unsets both. Several options may be set at once, and a
 mixture of setting and unsetting such as (?i-x) is allowed, but there may be
 only one hyphen. Setting (but no unsetting) is allowed after (?^ for example
-(?^in). An option setting may appear at the start of a non-capturing group, for
+(?^in). An option setting may appear at the start of a non-capture group, for
 example (?i:...).
 </P>
 <P>
@@ -565,19 +568,19 @@
 <P>
 <pre>
   (?R)            recurse whole pattern
-  (?n)            call subpattern by absolute number
-  (?+n)           call subpattern by relative number
-  (?-n)           call subpattern by relative number
-  (?&name)        call subpattern by name (Perl)
-  (?P&#62;name)       call subpattern by name (Python)
-  \g&#60;name&#62;        call subpattern by name (Oniguruma)
-  \g'name'        call subpattern by name (Oniguruma)
-  \g&#60;n&#62;           call subpattern by absolute number (Oniguruma)
-  \g'n'           call subpattern by absolute number (Oniguruma)
-  \g&#60;+n&#62;          call subpattern by relative number (PCRE2 extension)
-  \g'+n'          call subpattern by relative number (PCRE2 extension)
-  \g&#60;-n&#62;          call subpattern by relative number (PCRE2 extension)
-  \g'-n'          call subpattern by relative number (PCRE2 extension)
+  (?n)            call subroutine by absolute number
+  (?+n)           call subroutine by relative number
+  (?-n)           call subroutine by relative number
+  (?&name)        call subroutine by name (Perl)
+  (?P&#62;name)       call subroutine by name (Python)
+  \g&#60;name&#62;        call subroutine by name (Oniguruma)
+  \g'name'        call subroutine by name (Oniguruma)
+  \g&#60;n&#62;           call subroutine by absolute number (Oniguruma)
+  \g'n'           call subroutine by absolute number (Oniguruma)
+  \g&#60;+n&#62;          call subroutine by relative number (PCRE2 extension)
+  \g'+n'          call subroutine by relative number (PCRE2 extension)
+  \g&#60;-n&#62;          call subroutine by relative number (PCRE2 extension)
+  \g'-n'          call subroutine by relative number (PCRE2 extension)
 </PRE>
 </P>
 <br><a name="SEC23" href="#TOC1">CONDITIONAL PATTERNS</a><br>
@@ -595,7 +598,7 @@
   (?(R)               overall recursion condition
   (?(Rn)              specific numbered group recursion condition
   (?(R&name)          specific named group recursion condition
-  (?(DEFINE)          define subpattern for reference
+  (?(DEFINE)          define groups for reference
   (?(VERSION[&#62;]=n.m)  test PCRE2 version
   (?(assert)          assertion condition
 </pre>
@@ -657,9 +660,9 @@
 </P>
 <br><a name="SEC28" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 10 October 2018
+Last updated: 03 February 2019
 <br>
-Copyright &copy; 1997-2018 University of Cambridge.
+Copyright &copy; 1997-2019 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE2 index page</a>.


Modified: code/trunk/doc/html/pcre2test.html
===================================================================
--- code/trunk/doc/html/pcre2test.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2test.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -716,7 +716,7 @@
 some typical examples:
 <pre>
     re&#62; /(?i)(^a|^b)/m,info
-  Capturing subpattern count = 1
+  Capture group count = 1
   Compile options: multiline
   Overall options: caseless multiline
   First code unit at start or follows newline
@@ -723,7 +723,7 @@
   Subject length lower bound = 1


     re&#62; /(?i)abc/info
-  Capturing subpattern count = 0
+  Capture group count = 0
   Compile options: &#60;none&#62;
   Overall options: caseless
   First code unit = 'a' (caseless)
@@ -1353,8 +1353,8 @@
 <P>
 The <b>copy</b> and <b>get</b> modifiers can be used to test the
 <b>pcre2_substring_copy_xxx()</b> and <b>pcre2_substring_get_xxx()</b> functions.
-They can be given more than once, and each can specify a group name or number,
-for example:
+They can be given more than once, and each can specify a capture group name or
+number, for example:
 <pre>
    abcd\=copy=1,copy=3,get=G1
 </pre>
@@ -2075,9 +2075,9 @@
 </P>
 <br><a name="SEC21" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 12 November 2018
+Last updated: 03 February 2019
 <br>
-Copyright &copy; 1997-2018 University of Cambridge.
+Copyright &copy; 1997-2019 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE2 index page</a>.


Modified: code/trunk/doc/html/pcre2unicode.html
===================================================================
--- code/trunk/doc/html/pcre2unicode.html    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/html/pcre2unicode.html    2019-02-06 18:11:36 UTC (rev 1066)
@@ -38,10 +38,11 @@
 </b><br>
 <P>
 When PCRE2 is built with Unicode support, the escape sequences \p{..},
-\P{..}, and \X can be used. The Unicode properties that can be tested are
-limited to the general category properties such as Lu for an upper case letter
-or Nd for a decimal number, the Unicode script names such as Arabic or Han, and
-the derived properties Any and L&. Full lists are given in the
+\P{..}, and \X can be used. This is not dependent on the PCRE2_UTF setting.
+The Unicode properties that can be tested are limited to the general category
+properties such as Lu for an upper case letter or Nd for a decimal number, the
+Unicode script names such as Arabic or Han, and the derived properties Any and
+L&. Full lists are given in the
 <a href="pcre2pattern.html"><b>pcre2pattern</b></a>
 and
 <a href="pcre2syntax.html"><b>pcre2syntax</b></a>
@@ -73,11 +74,17 @@
 single code unit.
 </P>
 <P>
+In UTF modes, capture group names are not restricted to ASCII, and may contain
+any Unicode letters and decimal digits, as well as underscore.
+</P>
+<P>
 The escape sequence \C can be used to match a single code unit in a UTF mode,
 but its use can lead to some strange effects because it breaks up multi-unit
 characters (see the description of \C in the
 <a href="pcre2pattern.html"><b>pcre2pattern</b></a>
-documentation).
+documentation). For this reason, there is a build-time option that disables 
+support for \C completely. There is also a less draconian compile-time option
+for locking out the use of \C when a pattern is compiled.
 </P>
 <P>
 The use of \C is not supported by the alternative matching function
@@ -410,9 +417,9 @@
 REVISION
 </b><br>
 <P>
-Last updated: 12 October 2018
+Last updated: 03 February 2019
 <br>
-Copyright &copy; 1997-2018 University of Cambridge.
+Copyright &copy; 1997-2019 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE2 index page</a>.


Modified: code/trunk/doc/pcre2.txt
===================================================================
--- code/trunk/doc/pcre2.txt    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2.txt    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1475,11 +1475,11 @@


          PCRE2_DUPNAMES


-       If  this  bit is set, names used to identify capturing subpatterns need
-       not be unique. This can be helpful for certain types of pattern when it
-       is  known  that  only  one instance of the named subpattern can ever be
-       matched. There are more details of named subpatterns  below;  see  also
-       the pcre2pattern documentation.
+       If  this  bit is set, names used to identify capture groups need not be
+       unique.  This can be helpful for certain types of pattern  when  it  is
+       known  that  only  one instance of the named group can ever be matched.
+       There are more details of named capture  groups  below;  see  also  the
+       pcre2pattern documentation.


          PCRE2_ENDANCHORED


@@ -1510,12 +1510,12 @@
        If this bit is set, most white space  characters  in  the  pattern  are
        totally  ignored  except when escaped or inside a character class. How-
        ever, white space is not allowed within  sequences  such  as  (?>  that
-       introduce various parenthesized subpatterns, nor within numerical quan-
-       tifiers such as {1,3}.  Ignorable white space is permitted  between  an
-       item  and a following quantifier and between a quantifier and a follow-
-       ing + that indicates possessiveness.  PCRE2_EXTENDED is  equivalent  to
-       Perl's  /x  option,  and  it  can be changed within a pattern by a (?x)
-       option setting.
+       introduce  various  parenthesized  groups, nor within numerical quanti-
+       fiers such as {1,3}. Ignorable white space is permitted between an item
+       and  a  following quantifier and between a quantifier and a following +
+       that indicates possessiveness. PCRE2_EXTENDED is equivalent  to  Perl's
+       /x option, and it can be changed within a pattern by a (?x) option set-
+       ting.


        When PCRE2 is compiled without Unicode support,  PCRE2_EXTENDED  recog-
        nizes  as  white space only those characters with code points less than
@@ -1588,7 +1588,7 @@


          PCRE2_MATCH_UNSET_BACKREF


-       If  this  option  is  set, a backreference to an unset subpattern group
+       If  this  option  is  set,  a  backreference  to an unset capture group
        matches an empty string (by default this causes  the  current  matching
        alternative  to  fail).   A  pattern such as (\1)(a) succeeds when this
        option is set (assuming it can find an "a" in the subject), whereas  it
@@ -1654,7 +1654,7 @@
        ? behaves as if it were followed by ?: but named parentheses can  still
        be used for capturing (and they acquire numbers in the usual way). This
        is the same as Perl's /n option.  Note that, when this option  is  set,
-       references  to capturing groups (backreferences or recursion/subroutine
+       references  to  capture  groups (backreferences or recursion/subroutine
        calls) may only refer to named groups, though the reference can  be  by
        name or by number.


@@ -1674,9 +1674,9 @@
        .* is the first significant item in a top-level branch  of  a  pattern,
        and  all  the  other branches also start with .* or with \A or \G or ^.
        The optimization is automatically disabled for .* if it  is  inside  an
-       atomic  group  or a capturing group that is the subject of a backrefer-
-       ence, or if the pattern contains (*PRUNE) or (*SKIP).  When  the  opti-
-       mization  is  not disabled, such a pattern is automatically anchored if
+       atomic group or a capture group that is the subject of a backreference,
+       or if the pattern contains (*PRUNE) or (*SKIP). When  the  optimization
+       is   not   disabled,  such  a  pattern  is  automatically  anchored  if
        PCRE2_DOTALL is set for all the .* items and PCRE2_MULTILINE is not set
        for  any  ^ items. Otherwise, the fact that any match must start either
        at the start of the subject or following a newline is remembered.  Like
@@ -2038,7 +2038,7 @@
        all the following are true:


          .* is not in an atomic group
-         .* is not in a capturing group that is the subject
+         .* is not in a capture group that is the subject
               of a backreference
          PCRE2_DOTALL is in force for .*
          Neither (*PRUNE) nor (*SKIP) appears in the pattern
@@ -2050,12 +2050,12 @@
          PCRE2_INFO_BACKREFMAX


        Return the number of the highest  backreference  in  the  pattern.  The
-       third  argument should point to an uint32_t variable. Named subpatterns
-       acquire numbers as well as names, and these count towards  the  highest
-       backreference.   Backreferences such as \4 or \g{12} match the captured
-       characters of the given group, but in addition, the check that  a  cap-
-       turing  group  is  set in a conditional subpattern such as (?(3)a|b) is
-       also a backreference. Zero is returned if there are no backreferences.
+       third  argument  should  point  to  an uint32_t variable. Named capture
+       groups acquire numbers as well as names, and these  count  towards  the
+       highest  backreference.  Backreferences  such as \4 or \g{12} match the
+       captured characters of the given group, but in addition, the check that
+       a capture group is set in a conditional group such as (?(3)a|b) is also
+       a backreference.  Zero is returned if there are no backreferences.


          PCRE2_INFO_BSR


@@ -2066,9 +2066,9 @@

          PCRE2_INFO_CAPTURECOUNT


-       Return  the highest capturing subpattern number in the pattern. In pat-
-       terns where (?| is not used, this is also the total number of capturing
-       subpatterns.  The third argument should point to an uint32_t variable.
+       Return  the  highest  capture  group number in the pattern. In patterns
+       where (?| is not used, this is also the total number of capture groups.
+       The third argument should point to an uint32_t variable.


          PCRE2_INFO_DEPTHLIMIT


@@ -2118,8 +2118,8 @@
        backtracking positions when the pattern is processed  by  pcre2_match()
        without  the  use  of  JIT. The third argument should point to a size_t
        variable. The frame size depends on the number of capturing parentheses
-       in  the  pattern.  Each  additional capturing group adds two PCRE2_SIZE
-       variables.
+       in the pattern. Each additional capture group adds two PCRE2_SIZE vari-
+       ables.


          PCRE2_INFO_HASBACKSLASHC


@@ -2245,26 +2245,27 @@
        The rest of the entry is the corresponding name, zero terminated.


        The  names are in alphabetical order. If (?| is used to create multiple
-       groups with the same number, as described in the section  on  duplicate
-       subpattern  numbers  in  the pcre2pattern page, the groups may be given
-       the same name, but there is only one  entry  in  the  table.  Different
-       names for groups of the same number are not permitted.
+       capture groups with the same number, as described  in  the  section  on
+       duplicate  group  numbers  in  the pcre2pattern page, the groups may be
+       given the same name, but there is only one entry in the table.  Differ-
+       ent names for groups of the same number are not permitted.


-       Duplicate  names  for subpatterns with different numbers are permitted,
-       but only if PCRE2_DUPNAMES is set. They appear  in  the  table  in  the
+       Duplicate  names  for capture groups with different numbers are permit-
+       ted, but only if PCRE2_DUPNAMES is set. They appear in the table in the
        order  in  which  they were found in the pattern. In the absence of (?|
        this is the order of increasing number; when (?| is used  this  is  not
-       necessarily the case because later subpatterns may have lower numbers.
+       necessarily  the  case because later capture groups may have lower num-
+       bers.


-       As  a  simple  example of the name/number table, consider the following
-       pattern after compilation by the 8-bit library  (assume  PCRE2_EXTENDED
+       As a simple example of the name/number table,  consider  the  following
+       pattern  after  compilation by the 8-bit library (assume PCRE2_EXTENDED
        is set, so white space - including newlines - is ignored):


          (?<date> (?<year>(\d\d)?\d\d) -
          (?<month>\d\d) - (?<day>\d\d) )


-       There  are  four  named subpatterns, so the table has four entries, and
-       each entry in the table is eight bytes long. The table is  as  follows,
+       There are four named capture groups, so the table has four entries, and
+       each  entry  in the table is eight bytes long. The table is as follows,
        with non-printing bytes shows in hexadecimal, and undefined bytes shown
        as ??:


@@ -2273,8 +2274,8 @@
          00 04 m  o  n  t  h  00
          00 02 y  e  a  r  00 ??


-       When writing code to extract data  from  named  subpatterns  using  the
-       name-to-number  map,  remember that the length of the entries is likely
+       When  writing  code to extract data from named capture groups using the
+       name-to-number map, remember that the length of the entries  is  likely
        to be different for each compiled pattern.


          PCRE2_INFO_NEWLINE
@@ -2293,14 +2294,14 @@


          PCRE2_INFO_SIZE


-       Return  the  size  of  the  compiled  pattern  in  bytes (for all three
-       libraries). The third argument should point to a size_t variable.  This
-       value  includes  the  size  of the general data block that precedes the
-       code units of the compiled pattern itself. The value that is used  when
-       pcre2_compile()  is  getting memory in which to place the compiled pat-
-       tern may be slightly larger than the value  returned  by  this  option,
-       because  there are cases where the code that calculates the size has to
-       over-estimate. Processing a pattern with  the  JIT  compiler  does  not
+       Return the size of  the  compiled  pattern  in  bytes  (for  all  three
+       libraries).  The third argument should point to a size_t variable. This
+       value includes the size of the general data  block  that  precedes  the
+       code  units of the compiled pattern itself. The value that is used when
+       pcre2_compile() is getting memory in which to place the  compiled  pat-
+       tern  may  be  slightly  larger than the value returned by this option,
+       because there are cases where the code that calculates the size has  to
+       over-estimate.  Processing  a  pattern  with  the JIT compiler does not
        alter the value returned by this option.



@@ -2311,30 +2312,30 @@
          void *user_data);


        A script language that supports the use of string arguments in callouts
-       might like to scan all the callouts in a  pattern  before  running  the
+       might  like  to  scan  all the callouts in a pattern before running the
        match. This can be done by calling pcre2_callout_enumerate(). The first
-       argument is a pointer to a compiled pattern, the  second  points  to  a
-       callback  function,  and the third is arbitrary user data. The callback
-       function is called for every callout in the pattern  in  the  order  in
+       argument  is  a  pointer  to a compiled pattern, the second points to a
+       callback function, and the third is arbitrary user data.  The  callback
+       function  is  called  for  every callout in the pattern in the order in
        which they appear. Its first argument is a pointer to a callout enumer-
-       ation block, and its second argument is the user_data  value  that  was
-       passed  to  pcre2_callout_enumerate(). The contents of the callout enu-
-       meration block are described in the pcre2callout  documentation,  which
+       ation  block,  and  its second argument is the user_data value that was
+       passed to pcre2_callout_enumerate(). The contents of the  callout  enu-
+       meration  block  are described in the pcre2callout documentation, which
        also gives further details about callouts.



SERIALIZATION AND PRECOMPILING

-       It  is  possible  to  save  compiled patterns on disc or elsewhere, and
-       reload them later, subject to a number of  restrictions.  The  host  on
-       which  the  patterns  are  reloaded must be running the same version of
+       It is possible to save compiled patterns  on  disc  or  elsewhere,  and
+       reload  them  later,  subject  to a number of restrictions. The host on
+       which the patterns are reloaded must be running  the  same  version  of
        PCRE2, with the same code unit width, and must also have the same endi-
-       anness,  pointer  width,  and PCRE2_SIZE type. Before compiled patterns
-       can be saved, they must be converted to a "serialized" form,  which  in
-       the  case of PCRE2 is really just a bytecode dump.  The functions whose
-       names begin with pcre2_serialize_ are used for converting to  and  from
-       the  serialized form. They are described in the pcre2serialize documen-
-       tation. Note that PCRE2 serialization does not  convert  compiled  pat-
+       anness, pointer width, and PCRE2_SIZE type.  Before  compiled  patterns
+       can  be  saved, they must be converted to a "serialized" form, which in
+       the case of PCRE2 is really just a bytecode dump.  The functions  whose
+       names  begin  with pcre2_serialize_ are used for converting to and from
+       the serialized form. They are described in the pcre2serialize  documen-
+       tation.  Note  that  PCRE2 serialization does not convert compiled pat-
        terns to an abstract format like Java or .NET serialization.



@@ -2348,60 +2349,60 @@

        void pcre2_match_data_free(pcre2_match_data *match_data);


-       Information  about  a  successful  or unsuccessful match is placed in a
-       match data block, which is an opaque  structure  that  is  accessed  by
-       function  calls.  In particular, the match data block contains a vector
-       of offsets into the subject string that define the matched part of  the
-       subject  and  any  substrings  that were captured. This is known as the
+       Information about a successful or unsuccessful match  is  placed  in  a
+       match  data  block,  which  is  an opaque structure that is accessed by
+       function calls. In particular, the match data block contains  a  vector
+       of  offsets into the subject string that define the matched part of the
+       subject and any substrings that were captured. This  is  known  as  the
        ovector.


-       Before calling pcre2_match(), pcre2_dfa_match(),  or  pcre2_jit_match()
+       Before  calling  pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match()
        you must create a match data block by calling one of the creation func-
-       tions above. For pcre2_match_data_create(), the first argument  is  the
-       number  of  pairs  of  offsets  in  the ovector. One pair of offsets is
+       tions  above.  For pcre2_match_data_create(), the first argument is the
+       number of pairs of offsets in the  ovector.  One  pair  of  offsets  is
        required to identify the string that matched the whole pattern, with an
-       additional  pair for each captured substring. For example, a value of 4
-       creates enough space to record the matched portion of the subject  plus
-       three  captured  substrings. A minimum of at least 1 pair is imposed by
+       additional pair for each captured substring. For example, a value of  4
+       creates  enough space to record the matched portion of the subject plus
+       three captured substrings. A minimum of at least 1 pair is  imposed  by
        pcre2_match_data_create(), so it is always possible to return the over-
        all matched string.


        The second argument of pcre2_match_data_create() is a pointer to a gen-
-       eral context, which can specify custom memory management for  obtaining
+       eral  context, which can specify custom memory management for obtaining
        the memory for the match data block. If you are not using custom memory
        management, pass NULL, which causes malloc() to be used.


-       For pcre2_match_data_create_from_pattern(), the  first  argument  is  a
+       For  pcre2_match_data_create_from_pattern(),  the  first  argument is a
        pointer to a compiled pattern. The ovector is created to be exactly the
        right size to hold all the substrings a pattern might capture. The sec-
-       ond  argument is again a pointer to a general context, but in this case
+       ond argument is again a pointer to a general context, but in this  case
        if NULL is passed, the memory is obtained using the same allocator that
        was used for the compiled pattern (custom or default).


-       A  match  data block can be used many times, with the same or different
-       compiled patterns. You can extract information from a match data  block
+       A match data block can be used many times, with the same  or  different
+       compiled  patterns. You can extract information from a match data block
        after  a  match  operation  has  finished,  using  functions  that  are
-       described in the sections on  matched  strings  and  other  match  data
+       described  in  the  sections  on  matched  strings and other match data
        below.


-       When  a  call  of  pcre2_match()  fails, valid data is available in the
-       match   block   only   when   the   error    is    PCRE2_ERROR_NOMATCH,
-       PCRE2_ERROR_PARTIAL,  or  one  of  the  error  codes for an invalid UTF
+       When a call of pcre2_match() fails, valid  data  is  available  in  the
+       match    block    only   when   the   error   is   PCRE2_ERROR_NOMATCH,
+       PCRE2_ERROR_PARTIAL, or one of the  error  codes  for  an  invalid  UTF
        string. Exactly what is available depends on the error, and is detailed
        below.


-       When  one of the matching functions is called, pointers to the compiled
-       pattern and the subject string are set in the match data block so  that
-       they  can  be referenced by the extraction functions after a successful
+       When one of the matching functions is called, pointers to the  compiled
+       pattern  and the subject string are set in the match data block so that
+       they can be referenced by the extraction functions after  a  successful
        match. After running a match, you must not free a compiled pattern or a
-       subject  string until after all operations on the match data block (for
-       that match) have taken place,  unless,  in  the  case  of  the  subject
-       string,  you  have used the PCRE2_COPY_MATCHED_SUBJECT option, which is
-       described in the  section  entitled  "Option  bits  for  pcre2_match()"
+       subject string until after all operations on the match data block  (for
+       that  match)  have  taken  place,  unless,  in  the case of the subject
+       string, you have used the PCRE2_COPY_MATCHED_SUBJECT option,  which  is
+       described  in  the  section  entitled  "Option  bits for pcre2_match()"
        below.


-       When  a match data block itself is no longer needed, it should be freed
-       by calling pcre2_match_data_free(). If this function is called  with  a
+       When a match data block itself is no longer needed, it should be  freed
+       by  calling  pcre2_match_data_free(). If this function is called with a
        NULL argument, it returns immediately, without doing anything.



@@ -2412,15 +2413,15 @@
          uint32_t options, pcre2_match_data *match_data,
          pcre2_match_context *mcontext);


-       The  function pcre2_match() is called to match a subject string against
-       a compiled pattern, which is passed in the code argument. You can  call
+       The function pcre2_match() is called to match a subject string  against
+       a  compiled pattern, which is passed in the code argument. You can call
        pcre2_match() with the same code argument as many times as you like, in
-       order to find multiple matches in the subject string or to  match  dif-
+       order  to  find multiple matches in the subject string or to match dif-
        ferent subject strings with the same pattern.


-       This  function  is  the  main  matching facility of the library, and it
-       operates in a Perl-like manner. For specialist use  there  is  also  an
-       alternative  matching function, which is described below in the section
+       This function is the main matching facility  of  the  library,  and  it
+       operates  in  a  Perl-like  manner. For specialist use there is also an
+       alternative matching function, which is described below in the  section
        about the pcre2_dfa_match() function.


        Here is an example of a simple call to pcre2_match():
@@ -2435,7 +2436,7 @@
            md,             /* the match data block */
            NULL);          /* a match context; NULL means use defaults */


-       If the subject string is zero-terminated, the length can  be  given  as
+       If  the  subject  string is zero-terminated, the length can be given as
        PCRE2_ZERO_TERMINATED. A match context must be provided if certain less
        common matching parameters are to be changed. For details, see the sec-
        tion on the match context above.
@@ -2442,110 +2443,110 @@


    The string to be matched by pcre2_match()


-       The  subject string is passed to pcre2_match() as a pointer in subject,
-       a length in length, and a starting offset in  startoffset.  The  length
-       and  offset  are  in  code units, not characters.  That is, they are in
-       bytes for the 8-bit library, 16-bit code units for the 16-bit  library,
-       and  32-bit  code units for the 32-bit library, whether or not UTF pro-
+       The subject string is passed to pcre2_match() as a pointer in  subject,
+       a  length  in  length, and a starting offset in startoffset. The length
+       and offset are in code units, not characters.  That  is,  they  are  in
+       bytes  for the 8-bit library, 16-bit code units for the 16-bit library,
+       and 32-bit code units for the 32-bit library, whether or not  UTF  pro-
        cessing is enabled.


        If startoffset is greater than the length of the subject, pcre2_match()
-       returns  PCRE2_ERROR_BADOFFSET.  When  the starting offset is zero, the
-       search for a match starts at the beginning of the subject, and this  is
+       returns PCRE2_ERROR_BADOFFSET. When the starting offset  is  zero,  the
+       search  for a match starts at the beginning of the subject, and this is
        by far the most common case. In UTF-8 or UTF-16 mode, the starting off-
-       set must point to the start of a character, or to the end of  the  sub-
-       ject  (in  UTF-32 mode, one code unit equals one character, so all off-
-       sets are valid). Like the  pattern  string,  the  subject  may  contain
+       set  must  point to the start of a character, or to the end of the sub-
+       ject (in UTF-32 mode, one code unit equals one character, so  all  off-
+       sets  are  valid).  Like  the  pattern  string, the subject may contain
        binary zeros.


-       A  non-zero  starting offset is useful when searching for another match
-       in the same subject by calling pcre2_match()  again  after  a  previous
-       success.   Setting  startoffset  differs  from passing over a shortened
-       string and setting PCRE2_NOTBOL in the case of a  pattern  that  begins
+       A non-zero starting offset is useful when searching for  another  match
+       in  the  same  subject  by calling pcre2_match() again after a previous
+       success.  Setting startoffset differs from  passing  over  a  shortened
+       string  and  setting  PCRE2_NOTBOL in the case of a pattern that begins
        with any kind of lookbehind. For example, consider the pattern


          \Biss\B


-       which  finds  occurrences  of "iss" in the middle of words. (\B matches
-       only if the current position in the subject is not  a  word  boundary.)
+       which finds occurrences of "iss" in the middle of  words.  (\B  matches
+       only  if  the  current position in the subject is not a word boundary.)
        When applied to the string "Mississipi" the first call to pcre2_match()
-       finds the first occurrence. If pcre2_match() is called again with  just
-       the  remainder  of  the  subject,  namely  "issipi", it does not match,
+       finds  the first occurrence. If pcre2_match() is called again with just
+       the remainder of the subject,  namely  "issipi",  it  does  not  match,
        because \B is always false at the start of the subject, which is deemed
-       to  be  a word boundary. However, if pcre2_match() is passed the entire
+       to be a word boundary. However, if pcre2_match() is passed  the  entire
        string again, but with startoffset set to 4, it finds the second occur-
-       rence  of "iss" because it is able to look behind the starting point to
+       rence of "iss" because it is able to look behind the starting point  to
        discover that it is preceded by a letter.


-       Finding all the matches in a subject is tricky  when  the  pattern  can
+       Finding  all  the  matches  in a subject is tricky when the pattern can
        match an empty string. It is possible to emulate Perl's /g behaviour by
-       first  trying  the  match  again  at  the   same   offset,   with   the
-       PCRE2_NOTEMPTY_ATSTART  and  PCRE2_ANCHORED  options,  and then if that
-       fails, advancing the starting  offset  and  trying  an  ordinary  match
-       again.  There  is  some  code  that  demonstrates how to do this in the
-       pcre2demo sample program. In the most general case, you have  to  check
-       to  see  if the newline convention recognizes CRLF as a newline, and if
-       so, and the current character is CR followed by LF, advance the  start-
+       first   trying   the   match   again  at  the  same  offset,  with  the
+       PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED options,  and  then  if  that
+       fails,  advancing  the  starting  offset  and  trying an ordinary match
+       again. There is some code that demonstrates  how  to  do  this  in  the
+       pcre2demo  sample  program. In the most general case, you have to check
+       to see if the newline convention recognizes CRLF as a newline,  and  if
+       so,  and the current character is CR followed by LF, advance the start-
        ing offset by two characters instead of one.


        If a non-zero starting offset is passed when the pattern is anchored, a
        single attempt to match at the given offset is made. This can only suc-
-       ceed  if  the  pattern does not require the match to be at the start of
-       the subject. In other words, the anchoring must be the result  of  set-
-       ting  the PCRE2_ANCHORED option or the use of .* with PCRE2_DOTALL, not
+       ceed if the pattern does not require the match to be at  the  start  of
+       the  subject.  In other words, the anchoring must be the result of set-
+       ting the PCRE2_ANCHORED option or the use of .* with PCRE2_DOTALL,  not
        by starting the pattern with ^ or \A.


    Option bits for pcre2_match()


        The unused bits of the options argument for pcre2_match() must be zero.
-       The    only    bits    that    may    be    set   are   PCRE2_ANCHORED,
-       PCRE2_COPY_MATCHED_SUBJECT,      PCRE2_ENDANCHORED,       PCRE2_NOTBOL,
-       PCRE2_NOTEOL,   PCRE2_NOTEMPTY,  PCRE2_NOTEMPTY_ATSTART,  PCRE2_NO_JIT,
-       PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and  PCRE2_PARTIAL_SOFT.  Their
+       The   only   bits    that    may    be    set    are    PCRE2_ANCHORED,
+       PCRE2_COPY_MATCHED_SUBJECT,       PCRE2_ENDANCHORED,      PCRE2_NOTBOL,
+       PCRE2_NOTEOL,  PCRE2_NOTEMPTY,  PCRE2_NOTEMPTY_ATSTART,   PCRE2_NO_JIT,
+       PCRE2_NO_UTF_CHECK,  PCRE2_PARTIAL_HARD,  and PCRE2_PARTIAL_SOFT. Their
        action is described below.


-       Setting  PCRE2_ANCHORED  or PCRE2_ENDANCHORED at match time is not sup-
-       ported by the just-in-time (JIT) compiler. If it is set,  JIT  matching
-       is  disabled  and  the interpretive code in pcre2_match() is run. Apart
-       from PCRE2_NO_JIT (obviously), the remaining options are supported  for
+       Setting PCRE2_ANCHORED or PCRE2_ENDANCHORED at match time is  not  sup-
+       ported  by  the just-in-time (JIT) compiler. If it is set, JIT matching
+       is disabled and the interpretive code in pcre2_match()  is  run.  Apart
+       from  PCRE2_NO_JIT (obviously), the remaining options are supported for
        JIT matching.


          PCRE2_ANCHORED


        The PCRE2_ANCHORED option limits pcre2_match() to matching at the first
-       matching position. If a pattern was compiled  with  PCRE2_ANCHORED,  or
-       turned  out to be anchored by virtue of its contents, it cannot be made
-       unachored at matching time. Note that setting the option at match  time
+       matching  position.  If  a pattern was compiled with PCRE2_ANCHORED, or
+       turned out to be anchored by virtue of its contents, it cannot be  made
+       unachored  at matching time. Note that setting the option at match time
        disables JIT matching.


          PCRE2_COPY_MATCHED_SUBJECT


-       By  default,  a  pointer to the subject is remembered in the match data
-       block so that, after a successful match, it can be  referenced  by  the
-       substring  extraction  functions.  This means that the subject's memory
-       must not be freed until all such  operations  are  complete.  For  some
-       applications  where  the  lifetime of the subject string is not guaran-
-       teed, it may be necessary to make a copy of the subject string, but  it
+       By default, a pointer to the subject is remembered in  the  match  data
+       block  so  that,  after a successful match, it can be referenced by the
+       substring extraction functions. This means that  the  subject's  memory
+       must  not  be  freed  until  all such operations are complete. For some
+       applications where the lifetime of the subject string  is  not  guaran-
+       teed,  it may be necessary to make a copy of the subject string, but it
        is wasteful to do this unless the match is successful. After a success-
-       ful match, if PCRE2_COPY_MATCHED_SUBJECT is set, the subject is  copied
-       and  the  new  pointer is remembered in the match data block instead of
-       the original subject pointer. The memory allocator that  was  used  for
-       the  match  block  itself is used. The copy is automatically freed when
-       pcre2_match_data_free() is called to free the match data block.  It  is
+       ful  match, if PCRE2_COPY_MATCHED_SUBJECT is set, the subject is copied
+       and the new pointer is remembered in the match data  block  instead  of
+       the  original  subject  pointer. The memory allocator that was used for
+       the match block itself is used. The copy is  automatically  freed  when
+       pcre2_match_data_free()  is  called to free the match data block. It is
        also automatically freed if the match data block is re-used for another
        match operation.


          PCRE2_ENDANCHORED


-       If the PCRE2_ENDANCHORED option is set, any string  that  pcre2_match()
-       matches  must be right at the end of the subject string. Note that set-
+       If  the  PCRE2_ENDANCHORED option is set, any string that pcre2_match()
+       matches must be right at the end of the subject string. Note that  set-
        ting the option at match time disables JIT matching.


          PCRE2_NOTBOL


        This option specifies that first character of the subject string is not
-       the  beginning  of  a  line, so the circumflex metacharacter should not
-       match before it. Setting this without  having  set  PCRE2_MULTILINE  at
+       the beginning of a line, so the  circumflex  metacharacter  should  not
+       match  before  it.  Setting  this without having set PCRE2_MULTILINE at
        compile time causes circumflex never to match. This option affects only
        the behaviour of the circumflex metacharacter. It does not affect \A.


@@ -2552,9 +2553,9 @@
          PCRE2_NOTEOL


        This option specifies that the end of the subject string is not the end
-       of  a line, so the dollar metacharacter should not match it nor (except
-       in multiline mode) a newline immediately before it. Setting this  with-
-       out  having  set PCRE2_MULTILINE at compile time causes dollar never to
+       of a line, so the dollar metacharacter should not match it nor  (except
+       in  multiline mode) a newline immediately before it. Setting this with-
+       out having set PCRE2_MULTILINE at compile time causes dollar  never  to
        match. This option affects only the behaviour of the dollar metacharac-
        ter. It does not affect \Z or \z.


@@ -2561,79 +2562,79 @@
          PCRE2_NOTEMPTY


        An empty string is not considered to be a valid match if this option is
-       set. If there are alternatives in the pattern, they are tried.  If  all
-       the  alternatives  match  the empty string, the entire match fails. For
+       set.  If  there are alternatives in the pattern, they are tried. If all
+       the alternatives match the empty string, the entire  match  fails.  For
        example, if the pattern


          a?b?


-       is applied to a string not beginning with "a" or  "b",  it  matches  an
+       is  applied  to  a  string not beginning with "a" or "b", it matches an
        empty string at the start of the subject. With PCRE2_NOTEMPTY set, this
-       match is not valid, so pcre2_match() searches further into  the  string
+       match  is  not valid, so pcre2_match() searches further into the string
        for occurrences of "a" or "b".


          PCRE2_NOTEMPTY_ATSTART


-       This  is  like PCRE2_NOTEMPTY, except that it locks out an empty string
+       This is like PCRE2_NOTEMPTY, except that it locks out an  empty  string
        match only at the first matching position, that is, at the start of the
-       subject  plus  the  starting offset. An empty string match later in the
-       subject is permitted.  If the pattern is anchored,  such  a  match  can
+       subject plus the starting offset. An empty string match  later  in  the
+       subject  is  permitted.   If  the pattern is anchored, such a match can
        occur only if the pattern contains \K.


          PCRE2_NO_JIT


-       By   default,   if   a  pattern  has  been  successfully  processed  by
-       pcre2_jit_compile(), JIT is automatically used  when  pcre2_match()  is
-       called  with  options  that JIT supports. Setting PCRE2_NO_JIT disables
+       By  default,  if  a  pattern  has  been   successfully   processed   by
+       pcre2_jit_compile(),  JIT  is  automatically used when pcre2_match() is
+       called with options that JIT supports.  Setting  PCRE2_NO_JIT  disables
        the use of JIT; it forces matching to be done by the interpreter.


          PCRE2_NO_UTF_CHECK


        When PCRE2_UTF is set at compile time, the validity of the subject as a
-       UTF  string  is  checked  by default when pcre2_match() is subsequently
-       called.  If a non-zero starting offset is given, the check  is  applied
-       only  to that part of the subject that could be inspected during match-
-       ing, and there is a check that the starting offset points to the  first
-       code  unit of a character or to the end of the subject. If there are no
-       lookbehind assertions in the pattern, the check starts at the  starting
-       offset.  Otherwise,  it  starts at the length of the longest lookbehind
+       UTF string is checked by default  when  pcre2_match()  is  subsequently
+       called.   If  a non-zero starting offset is given, the check is applied
+       only to that part of the subject that could be inspected during  match-
+       ing,  and there is a check that the starting offset points to the first
+       code unit of a character or to the end of the subject. If there are  no
+       lookbehind  assertions in the pattern, the check starts at the starting
+       offset. Otherwise, it starts at the length of  the  longest  lookbehind
        before the starting offset, or at the start of the subject if there are
-       not  that  many  characters  before  the starting offset. Note that the
+       not that many characters before the  starting  offset.  Note  that  the
        sequences \b and \B are one-character lookbehinds.


        The check is carried out before any other processing takes place, and a
-       negative  error  code is returned if the check fails. There are several
-       UTF error codes for each code unit width,  corresponding  to  different
-       problems  with  the code unit sequence. There are discussions about the
-       validity of UTF-8 strings, UTF-16 strings, and UTF-32  strings  in  the
+       negative error code is returned if the check fails. There  are  several
+       UTF  error  codes  for each code unit width, corresponding to different
+       problems with the code unit sequence. There are discussions  about  the
+       validity  of  UTF-8  strings, UTF-16 strings, and UTF-32 strings in the
        pcre2unicode page.


-       If  you  know  that  your  subject is valid, and you want to skip these
-       checks for performance reasons,  you  can  set  the  PCRE2_NO_UTF_CHECK
-       option  when  calling  pcre2_match(). You might want to do this for the
+       If you know that your subject is valid, and  you  want  to  skip  these
+       checks  for  performance  reasons,  you  can set the PCRE2_NO_UTF_CHECK
+       option when calling pcre2_match(). You might want to do  this  for  the
        second and subsequent calls to pcre2_match() if you are making repeated
        calls to find other matches in the same subject string.


-       Warning:  When  PCRE2_NO_UTF_CHECK  is  set,  the  effect of passing an
-       invalid string as a subject, or an invalid  value  of  startoffset,  is
+       Warning: When PCRE2_NO_UTF_CHECK is  set,  the  effect  of  passing  an
+       invalid  string  as  a  subject, or an invalid value of startoffset, is
        undefined.  Your program may crash or loop indefinitely.


          PCRE2_PARTIAL_HARD
          PCRE2_PARTIAL_SOFT


-       These  options  turn  on  the partial matching feature. A partial match
-       occurs if the end of the subject string is  reached  successfully,  but
-       there  are not enough subject characters to complete the match. If this
-       happens when PCRE2_PARTIAL_SOFT (but not  PCRE2_PARTIAL_HARD)  is  set,
-       matching  continues  by  testing any remaining alternatives. Only if no
-       complete match can be found is PCRE2_ERROR_PARTIAL returned instead  of
-       PCRE2_ERROR_NOMATCH.  In other words, PCRE2_PARTIAL_SOFT specifies that
-       the caller is prepared to handle a partial match, but only if  no  com-
+       These options turn on the partial matching  feature.  A  partial  match
+       occurs  if  the  end of the subject string is reached successfully, but
+       there are not enough subject characters to complete the match. If  this
+       happens  when  PCRE2_PARTIAL_SOFT  (but not PCRE2_PARTIAL_HARD) is set,
+       matching continues by testing any remaining alternatives.  Only  if  no
+       complete  match can be found is PCRE2_ERROR_PARTIAL returned instead of
+       PCRE2_ERROR_NOMATCH. In other words, PCRE2_PARTIAL_SOFT specifies  that
+       the  caller  is prepared to handle a partial match, but only if no com-
        plete match can be found.


-       If  PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this
-       case, if a partial match is found,  pcre2_match()  immediately  returns
-       PCRE2_ERROR_PARTIAL,  without  considering  any  other alternatives. In
+       If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In  this
+       case,  if  a  partial match is found, pcre2_match() immediately returns
+       PCRE2_ERROR_PARTIAL, without considering  any  other  alternatives.  In
        other words, when PCRE2_PARTIAL_HARD is set, a partial match is consid-
        ered to be more important that an alternative complete match.


@@ -2643,38 +2644,38 @@

NEWLINE HANDLING WHEN MATCHING

-       When PCRE2 is built, a default newline convention is set; this is  usu-
-       ally  the standard convention for the operating system. The default can
-       be overridden in a compile context by calling  pcre2_set_newline().  It
-       can  also be overridden by starting a pattern string with, for example,
-       (*CRLF), as described in the section  on  newline  conventions  in  the
-       pcre2pattern  page. During matching, the newline choice affects the be-
-       haviour of the dot, circumflex, and dollar metacharacters. It may  also
-       alter  the  way  the  match starting position is advanced after a match
+       When  PCRE2 is built, a default newline convention is set; this is usu-
+       ally the standard convention for the operating system. The default  can
+       be  overridden  in a compile context by calling pcre2_set_newline(). It
+       can also be overridden by starting a pattern string with, for  example,
+       (*CRLF),  as  described  in  the  section on newline conventions in the
+       pcre2pattern page. During matching, the newline choice affects the  be-
+       haviour  of the dot, circumflex, and dollar metacharacters. It may also
+       alter the way the match starting position is  advanced  after  a  match
        failure for an unanchored pattern.


        When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is
-       set  as  the  newline convention, and a match attempt for an unanchored
+       set as the newline convention, and a match attempt  for  an  unanchored
        pattern fails when the current starting position is at a CRLF sequence,
-       and  the  pattern contains no explicit matches for CR or LF characters,
-       the match position is advanced by two characters  instead  of  one,  in
+       and the pattern contains no explicit matches for CR or  LF  characters,
+       the  match  position  is  advanced by two characters instead of one, in
        other words, to after the CRLF.


        The above rule is a compromise that makes the most common cases work as
-       expected. For example, if the pattern  is  .+A  (and  the  PCRE2_DOTALL
+       expected.  For  example,  if  the  pattern is .+A (and the PCRE2_DOTALL
        option is not set), it does not match the string "\r\nA" because, after
-       failing at the start, it skips both the CR and the LF before  retrying.
-       However,  the  pattern  [\r\n]A does match that string, because it con-
+       failing  at the start, it skips both the CR and the LF before retrying.
+       However, the pattern [\r\n]A does match that string,  because  it  con-
        tains an explicit CR or LF reference, and so advances only by one char-
        acter after the first failure.


        An explicit match for CR of LF is either a literal appearance of one of
-       those characters in the pattern, or one of the \r or \n  or  equivalent
+       those  characters  in the pattern, or one of the \r or \n or equivalent
        octal or hexadecimal escape sequences. Implicit matches such as [^X] do
-       not count, nor does \s, even though it includes CR and LF in the  char-
+       not  count, nor does \s, even though it includes CR and LF in the char-
        acters that it matches.


-       Notwithstanding  the above, anomalous effects may still occur when CRLF
+       Notwithstanding the above, anomalous effects may still occur when  CRLF
        is a valid newline sequence and explicit \r or \n escapes appear in the
        pattern.


@@ -2685,82 +2686,82 @@

        PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *match_data);


-       In  general, a pattern matches a certain portion of the subject, and in
-       addition, further substrings from the subject  may  be  picked  out  by
-       parenthesized  parts  of  the  pattern.  Following the usage in Jeffrey
-       Friedl's book, this is called "capturing"  in  what  follows,  and  the
-       phrase  "capturing subpattern" or "capturing group" is used for a frag-
-       ment of a pattern that picks out a substring.  PCRE2  supports  several
-       other kinds of parenthesized subpattern that do not cause substrings to
-       be captured. The pcre2_pattern_info() function can be used to find  out
-       how many capturing subpatterns there are in a compiled pattern.
+       In general, a pattern matches a certain portion of the subject, and  in
+       addition,  further  substrings  from  the  subject may be picked out by
+       parenthesized parts of the pattern.  Following  the  usage  in  Jeffrey
+       Friedl's  book,  this  is  called  "capturing" in what follows, and the
+       phrase "capture group" (Perl terminology) is used for a fragment  of  a
+       pattern  that picks out a substring. PCRE2 supports several other kinds
+       of parenthesized group that do not cause substrings to be captured. The
+       pcre2_pattern_info()  function can be used to find out how many capture
+       groups there are in a compiled pattern.


-       You  can  use  auxiliary functions for accessing captured substrings by
+       You can use auxiliary functions for accessing  captured  substrings  by
        number or by name, as described in sections below.


        Alternatively, you can make direct use of the vector of PCRE2_SIZE val-
-       ues,  called  the  ovector,  which  contains  the  offsets  of captured
-       strings.  It  is  part  of  the  match  data   block.    The   function
-       pcre2_get_ovector_pointer()  returns  the  address  of the ovector, and
+       ues, called  the  ovector,  which  contains  the  offsets  of  captured
+       strings.   It   is   part  of  the  match  data  block.   The  function
+       pcre2_get_ovector_pointer() returns the address  of  the  ovector,  and
        pcre2_get_ovector_count() returns the number of pairs of values it con-
        tains.


        Within the ovector, the first in each pair of values is set to the off-
        set of the first code unit of a substring, and the second is set to the
-       offset  of the first code unit after the end of a substring. These val-
-       ues are always code unit offsets, not character offsets. That is,  they
-       are  byte  offsets  in  the 8-bit library, 16-bit offsets in the 16-bit
+       offset of the first code unit after the end of a substring. These  val-
+       ues  are always code unit offsets, not character offsets. That is, they
+       are byte offsets in the 8-bit library, 16-bit  offsets  in  the  16-bit
        library, and 32-bit offsets in the 32-bit library.


-       After a partial match  (error  return  PCRE2_ERROR_PARTIAL),  only  the
-       first  pair  of  offsets  (that is, ovector[0] and ovector[1]) are set.
-       They identify the part of the subject that was partially  matched.  See
+       After  a  partial  match  (error  return PCRE2_ERROR_PARTIAL), only the
+       first pair of offsets (that is, ovector[0]  and  ovector[1])  are  set.
+       They  identify  the part of the subject that was partially matched. See
        the pcre2partial documentation for details of partial matching.


-       After  a  fully  successful match, the first pair of offsets identifies
-       the portion of the subject string that was matched by the  entire  pat-
-       tern.  The  next  pair is used for the first captured substring, and so
-       on. The value returned by pcre2_match() is one more  than  the  highest
-       numbered  pair  that  has been set. For example, if two substrings have
-       been captured, the returned value is 3. If there are no  captured  sub-
+       After a fully successful match, the first pair  of  offsets  identifies
+       the  portion  of the subject string that was matched by the entire pat-
+       tern. The next pair is used for the first captured  substring,  and  so
+       on.  The  value  returned by pcre2_match() is one more than the highest
+       numbered pair that has been set. For example, if  two  substrings  have
+       been  captured,  the returned value is 3. If there are no captured sub-
        strings, the return value from a successful match is 1, indicating that
        just the first pair of offsets has been set.


-       If a pattern uses the \K escape sequence within a  positive  assertion,
+       If  a  pattern uses the \K escape sequence within a positive assertion,
        the reported start of a successful match can be greater than the end of
-       the match.  For example, if the pattern  (?=ab\K)  is  matched  against
+       the  match.   For  example,  if the pattern (?=ab\K) is matched against
        "ab", the start and end offset values for the match are 2 and 0.


-       If  a  capturing subpattern group is matched repeatedly within a single
-       match operation, it is the last portion of the subject that it  matched
-       that is returned.
+       If a capture group is matched repeatedly within a single  match  opera-
+       tion,  it  is  the  last portion of the subject that it matched that is
+       returned.


        If the ovector is too small to hold all the captured substring offsets,
-       as much as possible is filled in, and the function returns a  value  of
-       zero.  If captured substrings are not of interest, pcre2_match() may be
+       as  much  as possible is filled in, and the function returns a value of
+       zero. If captured substrings are not of interest, pcre2_match() may  be
        called with a match data block whose ovector is of minimum length (that
        is, one pair).


-       It  is  possible for capturing subpattern number n+1 to match some part
-       of the subject when subpattern n has not been used at all. For example,
-       if  the  string  "abc"  is  matched against the pattern (a|(z))(bc) the
-       return from the function is 4, and subpatterns 1 and 3 are matched, but
-       2  is  not.  When  this happens, both values in the offset pairs corre-
-       sponding to unused subpatterns are set to PCRE2_UNSET.
+       It is possible for capture group number n+1 to match some part  of  the
+       subject  when  group  n  has  not been used at all. For example, if the
+       string "abc" is matched against the pattern (a|(z))(bc) the return from
+       the  function  is 4, and groups 1 and 3 are matched, but 2 is not. When
+       this happens, both values in the offset pairs corresponding  to  unused
+       groups are set to PCRE2_UNSET.


-       Offset values that correspond to unused subpatterns at the end  of  the
-       expression  are  also  set  to  PCRE2_UNSET. For example, if the string
-       "abc" is matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3
-       are  not matched.  The return from the function is 2, because the high-
-       est used capturing subpattern number is 1. The offsets for for the sec-
-       ond  and  third  capturing  subpatterns  (assuming  the vector is large
-       enough, of course) are set to PCRE2_UNSET.
+       Offset  values  that  correspond  to  unused  groups  at the end of the
+       expression are also set to PCRE2_UNSET.  For  example,  if  the  string
+       "abc"  is matched against the pattern (abc)(x(yz)?)? groups 2 and 3 are
+       not matched. The return from the function is  2,  because  the  highest
+       used  capture  group  number  is  1. The offsets for for the second and
+       third capture groupss (assuming the vector is large enough, of  course)
+       are set to PCRE2_UNSET.


        Elements in the ovector that do not correspond to capturing parentheses
        in the pattern are never changed. That is, if a pattern contains n cap-
        turing parentheses, no more than ovector[0] to ovector[2n+1] are set by
-       pcre2_match().  The  other  elements retain whatever values they previ-
-       ously had. After a failed match attempt, the contents  of  the  ovector
+       pcre2_match(). The other elements retain whatever  values  they  previ-
+       ously  had.  After  a failed match attempt, the contents of the ovector
        are unchanged.



@@ -2770,55 +2771,55 @@

        PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data);


-       As  well as the offsets in the ovector, other information about a match
-       is retained in the match data block and can be retrieved by  the  above
-       functions  in  appropriate  circumstances.  If they are called at other
+       As well as the offsets in the ovector, other information about a  match
+       is  retained  in the match data block and can be retrieved by the above
+       functions in appropriate circumstances. If they  are  called  at  other
        times, the result is undefined.


-       After a successful match, a partial match (PCRE2_ERROR_PARTIAL),  or  a
-       failure  to  match (PCRE2_ERROR_NOMATCH), a mark name may be available.
-       The function pcre2_get_mark() can be called to access this name,  which
-       can  be  specified  in  the  pattern by any of the backtracking control
+       After  a  successful match, a partial match (PCRE2_ERROR_PARTIAL), or a
+       failure to match (PCRE2_ERROR_NOMATCH), a mark name may  be  available.
+       The  function pcre2_get_mark() can be called to access this name, which
+       can be specified in the pattern by  any  of  the  backtracking  control
        verbs, not just (*MARK). The same function applies to all the verbs. It
        returns a pointer to the zero-terminated name, which is within the com-
        piled pattern. If no name is available, NULL is returned. The length of
-       the  name  (excluding  the terminating zero) is stored in the code unit
-       that precedes the name. You should use this length instead  of  relying
+       the name (excluding the terminating zero) is stored in  the  code  unit
+       that  precedes  the name. You should use this length instead of relying
        on the terminating zero if the name might contain a binary zero.


-       After  a  successful  match, the name that is returned is the last mark
+       After a successful match, the name that is returned is  the  last  mark
        name encountered on the matching path through the pattern. Instances of
-       backtracking  verbs  without  names do not count. Thus, for example, if
+       backtracking verbs without names do not count. Thus,  for  example,  if
        the matching path contains (*MARK:A)(*PRUNE), the name "A" is returned.
-       After  a  "no  match"  or a partial match, the last encountered name is
+       After a "no match" or a partial match, the  last  encountered  name  is
        returned. For example, consider this pattern:


          ^(*MARK:A)((*MARK:B)a|b)c


-       When it matches "bc", the returned name is A. The B mark is  "seen"  in
-       the  first  branch of the group, but it is not on the matching path. On
-       the other hand, when this pattern fails to  match  "bx",  the  returned
+       When  it  matches "bc", the returned name is A. The B mark is "seen" in
+       the first branch of the group, but it is not on the matching  path.  On
+       the  other  hand,  when  this pattern fails to match "bx", the returned
        name is B.


-       Warning:  By  default, certain start-of-match optimizations are used to
-       give a fast "no match" result in some situations. For example,  if  the
-       anchoring  is removed from the pattern above, there is an initial check
-       for the presence of "c" in the  subject  before  running  the  matching
+       Warning: By default, certain start-of-match optimizations are  used  to
+       give  a  fast "no match" result in some situations. For example, if the
+       anchoring is removed from the pattern above, there is an initial  check
+       for  the  presence  of  "c"  in the subject before running the matching
        engine. This check fails for "bx", causing a match failure without see-
        ing any marks. You can disable the start-of-match optimizations by set-
-       ting  the  PCRE2_NO_START_OPTIMIZE  option  for  pcre2_compile()  or by
+       ting the  PCRE2_NO_START_OPTIMIZE  option  for  pcre2_compile()  or  by
        starting the pattern with (*NO_START_OPT).


-       After a successful match, a partial match, or one of  the  invalid  UTF
-       errors  (for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar() can
+       After  a  successful  match, a partial match, or one of the invalid UTF
+       errors (for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar()  can
        be called. After a successful or partial match it returns the code unit
-       offset  of  the character at which the match started. For a non-partial
-       match, this can be different to the value of ovector[0] if the  pattern
-       contains  the  \K escape sequence. After a partial match, however, this
-       value is always the same as ovector[0] because \K does not  affect  the
+       offset of the character at which the match started. For  a  non-partial
+       match,  this can be different to the value of ovector[0] if the pattern
+       contains the \K escape sequence. After a partial match,  however,  this
+       value  is  always the same as ovector[0] because \K does not affect the
        result of a partial match.


-       After  a UTF check failure, pcre2_get_startchar() can be used to obtain
+       After a UTF check failure, pcre2_get_startchar() can be used to  obtain
        the code unit offset of the invalid UTF character. Details are given in
        the pcre2unicode page.


@@ -2825,14 +2826,14 @@

ERROR RETURNS FROM pcre2_match()

-       If  pcre2_match() fails, it returns a negative number. This can be con-
-       verted to a text string by calling the pcre2_get_error_message()  func-
-       tion  (see  "Obtaining a textual error message" below).  Negative error
-       codes are also returned by other functions,  and  are  documented  with
-       them.  The codes are given names in the header file. If UTF checking is
+       If pcre2_match() fails, it returns a negative number. This can be  con-
+       verted  to a text string by calling the pcre2_get_error_message() func-
+       tion (see "Obtaining a textual error message" below).   Negative  error
+       codes  are  also  returned  by other functions, and are documented with
+       them. The codes are given names in the header file. If UTF checking  is
        in force and an invalid UTF subject string is detected, one of a number
-       of  UTF-specific negative error codes is returned. Details are given in
-       the pcre2unicode page. The following are the other errors that  may  be
+       of UTF-specific negative error codes is returned. Details are given  in
+       the  pcre2unicode  page. The following are the other errors that may be
        returned by pcre2_match():


          PCRE2_ERROR_NOMATCH
@@ -2841,20 +2842,20 @@


          PCRE2_ERROR_PARTIAL


-       The  subject  string did not match, but it did match partially. See the
+       The subject string did not match, but it did match partially.  See  the
        pcre2partial documentation for details of partial matching.


          PCRE2_ERROR_BADMAGIC


        PCRE2 stores a 4-byte "magic number" at the start of the compiled code,
-       to  catch  the case when it is passed a junk pointer. This is the error
+       to catch the case when it is passed a junk pointer. This is  the  error
        that is returned when the magic number is not present.


          PCRE2_ERROR_BADMODE


-       This error is given when a compiled pattern is passed to a function  in
-       a  library  of a different code unit width, for example, a pattern com-
-       piled by the 8-bit library is passed to  a  16-bit  or  32-bit  library
+       This  error is given when a compiled pattern is passed to a function in
+       a library of a different code unit width, for example, a  pattern  com-
+       piled  by  the  8-bit  library  is passed to a 16-bit or 32-bit library
        function.


          PCRE2_ERROR_BADOFFSET
@@ -2868,15 +2869,15 @@
          PCRE2_ERROR_BADUTFOFFSET


        The UTF code unit sequence that was passed as a subject was checked and
-       found to be valid (the PCRE2_NO_UTF_CHECK option was not set), but  the
-       value  of startoffset did not point to the beginning of a UTF character
+       found  to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the
+       value of startoffset did not point to the beginning of a UTF  character
        or the end of the subject.


          PCRE2_ERROR_CALLOUT


-       This error is never generated by pcre2_match() itself. It  is  provided
-       for  use  by  callout  functions  that  want  to cause pcre2_match() or
-       pcre2_callout_enumerate() to return a distinctive error code.  See  the
+       This  error  is never generated by pcre2_match() itself. It is provided
+       for use by callout  functions  that  want  to  cause  pcre2_match()  or
+       pcre2_callout_enumerate()  to  return a distinctive error code. See the
        pcre2callout documentation for details.


          PCRE2_ERROR_DEPTHLIMIT
@@ -2889,14 +2890,14 @@


          PCRE2_ERROR_INTERNAL


-       An  unexpected  internal error has occurred. This error could be caused
+       An unexpected internal error has occurred. This error could  be  caused
        by a bug in PCRE2 or by overwriting of the compiled pattern.


          PCRE2_ERROR_JIT_STACKLIMIT


-       This error is returned when a pattern  that  was  successfully  studied
-       using  JIT  is being matched, but the memory available for the just-in-
-       time processing stack is not large enough. See the pcre2jit  documenta-
+       This  error  is  returned  when a pattern that was successfully studied
+       using JIT is being matched, but the memory available for  the  just-in-
+       time  processing stack is not large enough. See the pcre2jit documenta-
        tion for more details.


          PCRE2_ERROR_MATCHLIMIT
@@ -2905,11 +2906,11 @@


          PCRE2_ERROR_NOMEMORY


-       If  a  pattern contains many nested backtracking points, heap memory is
-       used to remember them. This error is given when the  memory  allocation
-       function  (default  or  custom)  fails.  Note  that  a different error,
-       PCRE2_ERROR_HEAPLIMIT, is given if the amount of memory needed  exceeds
-       the    heap   limit.   PCRE2_ERROR_NOMEMORY   is   also   returned   if
+       If a pattern contains many nested backtracking points, heap  memory  is
+       used  to  remember them. This error is given when the memory allocation
+       function (default or  custom)  fails.  Note  that  a  different  error,
+       PCRE2_ERROR_HEAPLIMIT,  is given if the amount of memory needed exceeds
+       the   heap   limit.   PCRE2_ERROR_NOMEMORY   is   also   returned    if
        PCRE2_COPY_MATCHED_SUBJECT is set and memory allocation fails.


          PCRE2_ERROR_NULL
@@ -2918,13 +2919,13 @@


          PCRE2_ERROR_RECURSELOOP


-       This error is returned when  pcre2_match()  detects  a  recursion  loop
-       within  the  pattern. Specifically, it means that either the whole pat-
-       tern or a subpattern has been called recursively for the second time at
-       the  same  position  in  the  subject string. Some simple patterns that
-       might do this are detected and faulted at compile time, but  more  com-
-       plicated  cases,  in particular mutual recursions between two different
-       subpatterns, cannot be detected until matching is attempted.
+       This  error  is  returned  when  pcre2_match() detects a recursion loop
+       within the pattern. Specifically, it means that either the  whole  pat-
+       tern or a capture group has been called recursively for the second time
+       at the same position in the subject string. Some simple  patterns  that
+       might  do  this are detected and faulted at compile time, but more com-
+       plicated cases, in particular mutual recursions between  two  different
+       groups, cannot be detected until matching is attempted.



 OBTAINING A TEXTUAL ERROR MESSAGE
@@ -2932,20 +2933,20 @@
        int pcre2_get_error_message(int errorcode, PCRE2_UCHAR *buffer,
          PCRE2_SIZE bufflen);


-       A text message for an error code  from  any  PCRE2  function  (compile,
-       match,  or  auxiliary)  can be obtained by calling pcre2_get_error_mes-
-       sage(). The code is passed as the first argument,  with  the  remaining
-       two  arguments  specifying  a  code  unit buffer and its length in code
-       units, into which the text message is placed. The message  is  returned
-       in  code  units  of the appropriate width for the library that is being
+       A  text  message  for  an  error code from any PCRE2 function (compile,
+       match, or auxiliary) can be obtained  by  calling  pcre2_get_error_mes-
+       sage().  The  code  is passed as the first argument, with the remaining
+       two arguments specifying a code unit buffer  and  its  length  in  code
+       units,  into  which the text message is placed. The message is returned
+       in code units of the appropriate width for the library  that  is  being
        used.


-       The returned message is terminated with a trailing zero, and the  func-
-       tion  returns  the  number  of  code units used, excluding the trailing
+       The  returned message is terminated with a trailing zero, and the func-
+       tion returns the number of code  units  used,  excluding  the  trailing
        zero.  If  the  error  number  is  unknown,  the  negative  error  code
-       PCRE2_ERROR_BADDATA  is  returned. If the buffer is too small, the mes-
-       sage is truncated (but still with a trailing zero),  and  the  negative
-       error  code PCRE2_ERROR_NOMEMORY is returned.  None of the messages are
+       PCRE2_ERROR_BADDATA is returned. If the buffer is too small,  the  mes-
+       sage  is  truncated  (but still with a trailing zero), and the negative
+       error code PCRE2_ERROR_NOMEMORY is returned.  None of the messages  are
        very long; a buffer size of 120 code units is ample.



@@ -2964,40 +2965,40 @@

        void pcre2_substring_free(PCRE2_UCHAR *buffer);


-       Captured substrings can be accessed directly by using  the  ovector  as
+       Captured  substrings  can  be accessed directly by using the ovector as
        described above.  For convenience, auxiliary functions are provided for
-       extracting  captured  substrings  as  new,  separate,   zero-terminated
+       extracting   captured  substrings  as  new,  separate,  zero-terminated
        strings. A substring that contains a binary zero is correctly extracted
-       and has a further zero added on the end, but  the  result  is  not,  of
+       and  has  a  further  zero  added on the end, but the result is not, of
        course, a C string.


        The functions in this section identify substrings by number. The number
        zero refers to the entire matched substring, with higher numbers refer-
-       ring  to  substrings  captured by parenthesized groups. After a partial
-       match, only substring zero is available.  An  attempt  to  extract  any
-       other  substring  gives the error PCRE2_ERROR_PARTIAL. The next section
+       ring to substrings captured by parenthesized groups.  After  a  partial
+       match,  only  substring  zero  is  available. An attempt to extract any
+       other substring gives the error PCRE2_ERROR_PARTIAL. The  next  section
        describes similar functions for extracting captured substrings by name.


-       If a pattern uses the \K escape sequence within a  positive  assertion,
+       If  a  pattern uses the \K escape sequence within a positive assertion,
        the reported start of a successful match can be greater than the end of
-       the match.  For example, if the pattern  (?=ab\K)  is  matched  against
-       "ab",  the  start  and  end offset values for the match are 2 and 0. In
-       this situation, calling these functions with a  zero  substring  number
+       the  match.   For  example,  if the pattern (?=ab\K) is matched against
+       "ab", the start and end offset values for the match are  2  and  0.  In
+       this  situation,  calling  these functions with a zero substring number
        extracts a zero-length empty string.


-       You  can  find the length in code units of a captured substring without
-       extracting it by calling pcre2_substring_length_bynumber().  The  first
-       argument  is a pointer to the match data block, the second is the group
-       number, and the third is a pointer to a variable into which the  length
-       is  placed.  If  you just want to know whether or not the substring has
+       You can find the length in code units of a captured  substring  without
+       extracting  it  by calling pcre2_substring_length_bynumber(). The first
+       argument is a pointer to the match data block, the second is the  group
+       number,  and the third is a pointer to a variable into which the length
+       is placed. If you just want to know whether or not  the  substring  has
        been captured, you can pass the third argument as NULL.


-       The pcre2_substring_copy_bynumber() function  copies  a  captured  sub-
-       string  into  a supplied buffer, whereas pcre2_substring_get_bynumber()
-       copies it into new memory, obtained using the  same  memory  allocation
-       function  that  was  used for the match data block. The first two argu-
-       ments of these functions are a pointer to the match data  block  and  a
-       capturing group number.
+       The  pcre2_substring_copy_bynumber()  function  copies  a captured sub-
+       string into a supplied buffer,  whereas  pcre2_substring_get_bynumber()
+       copies  it  into  new memory, obtained using the same memory allocation
+       function that was used for the match data block. The  first  two  argu-
+       ments  of  these  functions are a pointer to the match data block and a
+       capture group number.


        The final arguments of pcre2_substring_copy_bynumber() are a pointer to
        the buffer and a pointer to a variable that contains its length in code
@@ -3005,25 +3006,25 @@
        for the extracted substring, excluding the terminating zero.


        For pcre2_substring_get_bynumber() the third and fourth arguments point
-       to  variables that are updated with a pointer to the new memory and the
-       number of code units that comprise the substring, again  excluding  the
-       terminating  zero.  When  the substring is no longer needed, the memory
+       to variables that are updated with a pointer to the new memory and  the
+       number  of  code units that comprise the substring, again excluding the
+       terminating zero. When the substring is no longer  needed,  the  memory
        should be freed by calling pcre2_substring_free().


-       The return value from all these functions is zero  for  success,  or  a
-       negative  error  code.  If  the pattern match failed, the match failure
-       code is returned.  If a substring number  greater  than  zero  is  used
-       after  a partial match, PCRE2_ERROR_PARTIAL is returned. Other possible
+       The  return  value  from  all these functions is zero for success, or a
+       negative error code. If the pattern match  failed,  the  match  failure
+       code  is  returned.   If  a  substring number greater than zero is used
+       after a partial match, PCRE2_ERROR_PARTIAL is returned. Other  possible
        error codes are:


          PCRE2_ERROR_NOMEMORY


-       The buffer was too small for  pcre2_substring_copy_bynumber(),  or  the
+       The  buffer  was  too small for pcre2_substring_copy_bynumber(), or the
        attempt to get memory failed for pcre2_substring_get_bynumber().


          PCRE2_ERROR_NOSUBSTRING


-       There  is  no  substring  with that number in the pattern, that is, the
+       There is no substring with that number in the  pattern,  that  is,  the
        number is greater than the number of capturing parentheses.


          PCRE2_ERROR_UNAVAILABLE
@@ -3034,8 +3035,8 @@


          PCRE2_ERROR_UNSET


-       The substring did not participate in the match.  For  example,  if  the
-       pattern  is  (abc)|(def) and the subject is "def", and the ovector con-
+       The  substring  did  not  participate in the match. For example, if the
+       pattern is (abc)|(def) and the subject is "def", and the  ovector  con-
        tains at least two capturing slots, substring number 1 is unset.



@@ -3046,33 +3047,32 @@

        void pcre2_substring_list_free(PCRE2_SPTR *list);


-       The pcre2_substring_list_get() function  extracts  all  available  sub-
-       strings  and  builds  a  list of pointers to them. It also (optionally)
-       builds a second list that  contains  their  lengths  (in  code  units),
+       The  pcre2_substring_list_get()  function  extracts  all available sub-
+       strings and builds a list of pointers to  them.  It  also  (optionally)
+       builds  a  second  list  that  contains  their lengths (in code units),
        excluding a terminating zero that is added to each of them. All this is
        done in a single block of memory that is obtained using the same memory
        allocation function that was used to get the match data block.


-       This  function  must be called only after a successful match. If called
+       This function must be called only after a successful match.  If  called
        after a partial match, the error code PCRE2_ERROR_PARTIAL is returned.


-       The address of the memory block is returned via listptr, which is  also
+       The  address of the memory block is returned via listptr, which is also
        the start of the list of string pointers. The end of the list is marked
-       by a NULL pointer. The address of the list of lengths is  returned  via
-       lengthsptr.  If your strings do not contain binary zeros and you do not
+       by  a  NULL pointer. The address of the list of lengths is returned via
+       lengthsptr. If your strings do not contain binary zeros and you do  not
        therefore need the lengths, you may supply NULL as the lengthsptr argu-
-       ment  to  disable  the  creation of a list of lengths. The yield of the
-       function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the  mem-
-       ory  block could not be obtained. When the list is no longer needed, it
+       ment to disable the creation of a list of lengths.  The  yield  of  the
+       function  is zero if all went well, or PCRE2_ERROR_NOMEMORY if the mem-
+       ory block could not be obtained. When the list is no longer needed,  it
        should be freed by calling pcre2_substring_list_free().


        If this function encounters a substring that is unset, which can happen
-       when  capturing subpattern number n+1 matches some part of the subject,
-       but subpattern n has not been used at all, it returns an empty  string.
-       This  can  be  distinguished  from  a  genuine zero-length substring by
-       inspecting  the  appropriate  offset  in  the  ovector,  which  contain
-       PCRE2_UNSET   for   unset   substrings,   or   by   calling  pcre2_sub-
-       string_length_bynumber().
+       when capture group number n+1 matches some part  of  the  subject,  but
+       group  n has not been used at all, it returns an empty string. This can
+       be distinguished from a genuine zero-length substring by inspecting the
+       appropriate  offset in the ovector, which contain PCRE2_UNSET for unset
+       substrings, or by calling pcre2_substring_length_bynumber().



EXTRACTING CAPTURED SUBSTRINGS BY NAME
@@ -3096,34 +3096,35 @@

          (a+)b(?<xxx>\d+)...


-       the number of the subpattern called "xxx" is 2. If the name is known to
-       be unique (PCRE2_DUPNAMES was not set), you can find  the  number  from
+       the number of the capture group called "xxx" is 2. If the name is known
+       to be unique (PCRE2_DUPNAMES was not set), you can find the number from
        the name by calling pcre2_substring_number_from_name(). The first argu-
        ment is the compiled pattern, and the second is the name. The yield  of
-       the function is the subpattern number, PCRE2_ERROR_NOSUBSTRING if there
-       is no subpattern of  that  name,  or  PCRE2_ERROR_NOUNIQUESUBSTRING  if
-       there  is  more than one subpattern of that name. Given the number, you
-       can extract the substring directly from the ovector, or use one of  the
-       "bynumber" functions described above.
+       the  function  is the group number, PCRE2_ERROR_NOSUBSTRING if there is
+       no group with that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if  there  is
+       more  than one group with that name.  Given the number, you can extract
+       the substring directly from the ovector, or use one of  the  "bynumber"
+       functions described above.


        For  convenience,  there are also "byname" functions that correspond to
        the "bynumber" functions, the only difference  being  that  the  second
        argument  is  a  name instead of a number. If PCRE2_DUPNAMES is set and
        there are duplicate names, these functions scan all the groups with the
-       given name, and return the first named string that is set.
+       given  name,  and  return  the  captured substring from the first named
+       group that is set.


-       If  there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is
-       returned. If all groups with the name have  numbers  that  are  greater
-       than  the  number  of  slots in the ovector, PCRE2_ERROR_UNAVAILABLE is
-       returned. If there is at least one group with a slot  in  the  ovector,
+       If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING  is
+       returned.  If  all  groups  with the name have numbers that are greater
+       than the number of slots in  the  ovector,  PCRE2_ERROR_UNAVAILABLE  is
+       returned.  If  there  is at least one group with a slot in the ovector,
        but no group is found to be set, PCRE2_ERROR_UNSET is returned.


-       Warning: If the pattern uses the (?| feature to set up multiple subpat-
-       terns with the same number, as described in the  section  on  duplicate
-       subpattern  numbers  in  the pcre2pattern page, you cannot use names to
-       distinguish the different subpatterns, because names are  not  included
-       in  the compiled code. The matching process uses only numbers. For this
-       reason, the use of different names for subpatterns of the  same  number
+       Warning: If the pattern uses the (?| feature to set up multiple capture
+       groups  with  the same number, as described in the section on duplicate
+       group numbers in the pcre2pattern page, you cannot use names to distin-
+       guish  the  different capture groups, because names are not included in
+       the compiled code. The matching process uses  only  numbers.  For  this
+       reason,  the  use  of  different  names for groups with the same number
        causes an error at compile time.



@@ -3136,54 +3137,54 @@
          PCRE2_SIZE rlength, PCRE2_UCHAR *outputbuffer,
          PCRE2_SIZE *outlengthptr);


-       This  function calls pcre2_match() and then makes a copy of the subject
-       string in outputbuffer, replacing one or more parts that  were  matched
+       This function calls pcre2_match() and then makes a copy of the  subject
+       string  in  outputbuffer, replacing one or more parts that were matched
        with the replacement string, whose length is supplied in rlength.  This
-       can be given as PCRE2_ZERO_TERMINATED  for  a  zero-terminated  string.
-       The  default is to perform just one replacement, but there is an option
-       that requests multiple replacements (see PCRE2_SUBSTITUTE_GLOBAL  below
+       can  be  given  as  PCRE2_ZERO_TERMINATED for a zero-terminated string.
+       The default is to perform just one replacement, but there is an  option
+       that  requests multiple replacements (see PCRE2_SUBSTITUTE_GLOBAL below
        for details).


-       Matches  in  which  a  \K item in a lookahead in the pattern causes the
-       match to end before it starts are not supported, and give  rise  to  an
+       Matches in which a \K item in a lookahead in  the  pattern  causes  the
+       match  to  end  before it starts are not supported, and give rise to an
        error return. For global replacements, matches in which \K in a lookbe-
-       hind causes the match to start earlier than the point that was  reached
+       hind  causes the match to start earlier than the point that was reached
        in the previous iteration are also not supported.


-       The  first  seven  arguments  of pcre2_substitute() are the same as for
+       The first seven arguments of pcre2_substitute() are  the  same  as  for
        pcre2_match(), except that the partial matching options are not permit-
-       ted,  and  match_data may be passed as NULL, in which case a match data
-       block is obtained and freed within this function, using memory  manage-
-       ment  functions from the match context, if provided, or else those that
+       ted, and match_data may be passed as NULL, in which case a  match  data
+       block  is obtained and freed within this function, using memory manage-
+       ment functions from the match context, if provided, or else those  that
        were used to allocate memory for the compiled code.


-       If an external match_data block is provided,  its  contents  afterwards
-       are  those  set by the final call to pcre2_match(). For global changes,
-       this will have ended in a matching error. The contents of  the  ovector
+       If  an  external  match_data block is provided, its contents afterwards
+       are those set by the final call to pcre2_match(). For  global  changes,
+       this  will  have ended in a matching error. The contents of the ovector
        within the match data block may or may not have been changed.


-       The  outlengthptr  argument  must point to a variable that contains the
-       length, in code units, of the output buffer. If the  function  is  suc-
-       cessful,  the value is updated to contain the length of the new string,
+       The outlengthptr argument must point to a variable  that  contains  the
+       length,  in  code  units, of the output buffer. If the function is suc-
+       cessful, the value is updated to contain the length of the new  string,
        excluding the trailing zero that is automatically added.


-       If the function is not  successful,  the  value  set  via  outlengthptr
-       depends  on  the  type  of  error. For syntax errors in the replacement
-       string, the value is the offset in the  replacement  string  where  the
-       error  was  detected.  For  other  errors,  the value is PCRE2_UNSET by
-       default. This includes the case of the output buffer being  too  small,
-       unless  PCRE2_SUBSTITUTE_OVERFLOW_LENGTH  is  set (see below), in which
-       case the value is the minimum length needed, including  space  for  the
-       trailing  zero.  Note  that  in  order  to compute the required length,
-       pcre2_substitute() has  to  simulate  all  the  matching  and  copying,
+       If  the  function  is  not  successful,  the value set via outlengthptr
+       depends on the type of error. For  syntax  errors  in  the  replacement
+       string,  the  value  is  the offset in the replacement string where the
+       error was detected. For other  errors,  the  value  is  PCRE2_UNSET  by
+       default.  This  includes the case of the output buffer being too small,
+       unless PCRE2_SUBSTITUTE_OVERFLOW_LENGTH is set (see  below),  in  which
+       case  the  value  is the minimum length needed, including space for the
+       trailing zero. Note that in  order  to  compute  the  required  length,
+       pcre2_substitute()  has  to  simulate  all  the  matching  and copying,
        instead of giving an error return as soon as the buffer overflows. Note
        also that the length is in code units, not bytes.


-       In the replacement string, which is interpreted as a UTF string in  UTF
-       mode,  and  is  checked  for UTF validity unless the PCRE2_NO_UTF_CHECK
+       In  the replacement string, which is interpreted as a UTF string in UTF
+       mode, and is checked for UTF  validity  unless  the  PCRE2_NO_UTF_CHECK
        option is set, a dollar character is an escape character that can spec-
-       ify  the  insertion  of  characters from capturing groups or names from
-       (*MARK) or other control verbs in the pattern. The following forms  are
+       ify the insertion of characters  from  capture  groups  or  names  from
+       (*MARK)  or other control verbs in the pattern. The following forms are
        always recognized:


          $$                  insert a dollar character
@@ -3190,18 +3191,18 @@
          $<n> or ${<n>}      insert the contents of group <n>
          $*MARK or ${*MARK}  insert a control verb name


-       Either  a  group  number  or  a  group name can be given for <n>. Curly
-       brackets are required only if the following character would  be  inter-
+       Either a group number or a group name  can  be  given  for  <n>.  Curly
+       brackets  are  required only if the following character would be inter-
        preted as part of the number or name. The number may be zero to include
-       the entire matched string.   For  example,  if  the  pattern  a(b)c  is
-       matched  with "=abc=" and the replacement string "+$1$0$1+", the result
+       the  entire  matched  string.   For  example,  if  the pattern a(b)c is
+       matched with "=abc=" and the replacement string "+$1$0$1+", the  result
        is "=+babcb+=".


-       $*MARK inserts the name from the last encountered backtracking  control
-       verb  on the matching path that has a name. (*MARK) must always include
-       a name, but the other verbs need not.  For  example,  in  the  case  of
+       $*MARK  inserts the name from the last encountered backtracking control
+       verb on the matching path that has a name. (*MARK) must always  include
+       a  name,  but  the  other  verbs  need not. For example, in the case of
        (*MARK:A)(*PRUNE) the name inserted is "A", but for (*MARK:A)(*PRUNE:B)
-       the relevant name is "B". This facility can be used to  perform  simple
+       the  relevant  name is "B". This facility can be used to perform simple
        simultaneous substitutions, as this pcre2test example shows:


          /(*MARK:pear)apple|(*MARK:orange)lemon/g,replace=${*MARK}
@@ -3208,19 +3209,19 @@
              apple lemon
           2: pear orange


-       As  well as the usual options for pcre2_match(), a number of additional
+       As well as the usual options for pcre2_match(), a number of  additional
        options can be set in the options argument of pcre2_substitute().


        PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject
-       string,  replacing every matching substring. If this option is not set,
-       only the first matching substring is replaced. The search  for  matches
-       takes  place in the original subject string (that is, previous replace-
-       ments do not affect it).  Iteration is  implemented  by  advancing  the
-       startoffset  value  for  each search, which is always passed the entire
+       string, replacing every matching substring. If this option is not  set,
+       only  the  first matching substring is replaced. The search for matches
+       takes place in the original subject string (that is, previous  replace-
+       ments  do  not  affect  it).  Iteration is implemented by advancing the
+       startoffset value for each search, which is always  passed  the  entire
        subject string. If an offset limit is set in the match context, search-
        ing stops when that limit is reached.


-       You  can  restrict  the effect of a global substitution to a portion of
+       You can restrict the effect of a global substitution to  a  portion  of
        the subject string by setting either or both of startoffset and an off-
        set limit. Here is a pcre2test example:


@@ -3228,36 +3229,35 @@
          ABC ABC ABC ABC\=offset=3,offset_limit=12
           2: ABC A!C A!C ABC


-       When  continuing  with  global substitutions after matching a substring
+       When continuing with global substitutions after  matching  a  substring
        with zero length, an attempt to find a non-empty match at the same off-
        set is performed.  If this is not successful, the offset is advanced by
        one character except when CRLF is a valid newline sequence and the next
-       two  characters are CR, LF. In this case, the offset is advanced by two
+       two characters are CR, LF. In this case, the offset is advanced by  two
        characters.


-       PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when  the  output
+       PCRE2_SUBSTITUTE_OVERFLOW_LENGTH  changes  what happens when the output
        buffer is too small. The default action is to return PCRE2_ERROR_NOMEM-
-       ORY immediately. If this option  is  set,  however,  pcre2_substitute()
+       ORY  immediately.  If  this  option is set, however, pcre2_substitute()
        continues to go through the motions of matching and substituting (with-
-       out, of course, writing anything) in order to compute the size of  buf-
-       fer  that  is  needed.  This  value is passed back via the outlengthptr
-       variable,   with   the   result   of   the   function    still    being
+       out,  of course, writing anything) in order to compute the size of buf-
+       fer that is needed. This value is  passed  back  via  the  outlengthptr
+       variable,    with    the   result   of   the   function   still   being
        PCRE2_ERROR_NOMEMORY.


-       Passing  a  buffer  size  of zero is a permitted way of finding out how
-       much memory is needed for given substitution. However, this  does  mean
+       Passing a buffer size of zero is a permitted way  of  finding  out  how
+       much  memory  is needed for given substitution. However, this does mean
        that the entire operation is carried out twice. Depending on the appli-
-       cation, it may be more efficient to allocate a large  buffer  and  free
-       the   excess   afterwards,   instead  of  using  PCRE2_SUBSTITUTE_OVER-
+       cation,  it  may  be more efficient to allocate a large buffer and free
+       the  excess  afterwards,  instead   of   using   PCRE2_SUBSTITUTE_OVER-
        FLOW_LENGTH.


-       PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references  to  capturing  groups
-       that  do  not appear in the pattern to be treated as unset groups. This
-       option should be used with care, because it means  that  a  typo  in  a
-       group  name  or  number  no  longer  causes the PCRE2_ERROR_NOSUBSTRING
-       error.
+       PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capture groups that
+       do not appear in the pattern to be treated as unset groups. This option
+       should  be used with care, because it means that a typo in a group name
+       or number no longer causes the PCRE2_ERROR_NOSUBSTRING error.


-       PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capturing  groups  (including
+       PCRE2_SUBSTITUTE_UNSET_EMPTY causes  unset  capture  groups  (including
        unknown  groups  when  PCRE2_SUBSTITUTE_UNKNOWN_UNSET  is  set)  to  be
        treated as empty strings when inserted  as  described  above.  If  this
        option  is  not  set,  an  attempt  to insert an unset group causes the
@@ -3283,7 +3283,7 @@
        no  case  forcing. The sequences \u and \l force the next character (if
        it is a letter) to upper or lower  case,  respectively,  and  then  the
        state automatically reverts to no case forcing. Case forcing applies to
-       all inserted  characters, including those from captured groups and let-
+       all inserted  characters, including those from capture groups and  let-
        ters within \Q...\E quoted sequences.


        Note that case forcing sequences such as \U...\E do not nest. For exam-
@@ -3291,8 +3291,8 @@
        \E has no effect.


        The  second  effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more
-       flexibility to group substitution. The syntax is similar to  that  used
-       by Bash:
+       flexibility to capture group substitution. The  syntax  is  similar  to
+       that used by Bash:


          ${<n>:-<string>}
          ${<n>:+<string1>:<string2>}
@@ -3411,20 +3411,20 @@
        ing the number of matches so far.



-DUPLICATE SUBPATTERN NAMES
+DUPLICATE CAPTURE GROUP NAMES

        int pcre2_substring_nametable_scan(const pcre2_code *code,
          PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last);


        When a pattern is compiled with the PCRE2_DUPNAMES  option,  names  for
-       subpatterns  are  not required to be unique. Duplicate names are always
-       allowed for subpatterns with the same number, created by using the  (?|
-       feature.  Indeed,  if  such subpatterns are named, they are required to
-       use the same names.
+       capture  groups  are  not  required  to  be unique. Duplicate names are
+       always allowed for groups with the same number, created  by  using  the
+       (?| feature. Indeed, if such groups are named, they are required to use
+       the same names.


-       Normally, patterns with duplicate names are such that in any one match,
-       only  one of the named subpatterns participates. An example is shown in
-       the pcre2pattern documentation.
+       Normally, patterns that use duplicate names are such that  in  any  one
+       match,  only  one of each set of identically-named groups participates.
+       An example is shown in the pcre2pattern documentation.


        When  duplicates   are   present,   pcre2_substring_copy_byname()   and
        pcre2_substring_get_byname()  return  the first substring corresponding
@@ -3583,8 +3583,8 @@
        which is the number of matched substrings.  The  offsets  of  the  sub-
        strings  are returned in the ovector, and can be extracted by number in
        the same way as for pcre2_match(), but the numbers bear no relation  to
-       any  capturing groups that may exist in the pattern, because DFA match-
-       ing does not support group capture.
+       any  capture groups that may exist in the pattern, because DFA matching
+       does not support capturing.


        Calls to the convenience functions  that  extract  substrings  by  name
        return  the  error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used
@@ -3621,7 +3621,7 @@


        This  return  is given if pcre2_dfa_match() encounters a condition item
        that uses a backreference for the condition, or a test for recursion in
-       a specific group. These are not supported.
+       a specific capture group. These are not supported.


          PCRE2_ERROR_DFA_WSSIZE


@@ -3630,22 +3630,23 @@

          PCRE2_ERROR_DFA_RECURSE


-       When a recursive subpattern is processed, the matching  function  calls
-       itself recursively, using private memory for the ovector and workspace.
-       This error is given if the internal ovector is not large  enough.  This
-       should be extremely rare, as a vector of size 1000 is used.
+       When a recursion or subroutine call is processed, the matching function
+       calls  itself  recursively,  using  private  memory for the ovector and
+       workspace.  This error is given if the internal ovector  is  not  large
+       enough.  This  should  be  extremely  rare, as a vector of size 1000 is
+       used.


          PCRE2_ERROR_DFA_BADRESTART


-       When  pcre2_dfa_match()  is  called  with the PCRE2_DFA_RESTART option,
-       some plausibility checks are made on the  contents  of  the  workspace,
-       which  should  contain data about the previous partial match. If any of
+       When pcre2_dfa_match() is called  with  the  PCRE2_DFA_RESTART  option,
+       some  plausibility  checks  are  made on the contents of the workspace,
+       which should contain data about the previous partial match. If  any  of
        these checks fail, this error is given.



SEE ALSO

-       pcre2build(3),   pcre2callout(3),    pcre2demo(3),    pcre2matching(3),
+       pcre2build(3),    pcre2callout(3),    pcre2demo(3),   pcre2matching(3),
        pcre2partial(3), pcre2posix(3), pcre2sample(3), pcre2unicode(3).



@@ -3658,7 +3659,7 @@

REVISION

-       Last updated: 04 January 2019
+       Last updated: 04 February 2019
        Copyright (c) 1997-2019 University of Cambridge.
 ------------------------------------------------------------------------------


@@ -4362,7 +4363,7 @@
        all branches are anchorable.


        This  optimization is disabled, however, if .* is in an atomic group or
-       if there is a backreference to the capturing group in which it appears.
+       if there is a backreference to the capture group in which  it  appears.
        It  is  also disabled if the pattern contains (*PRUNE) or (*SKIP). How-
        ever, the presence of callouts does not affect it.


@@ -4546,8 +4547,8 @@
        the length is one, unless a closing parenthesis is followed by a  quan-
        tifier, in which case its length is included.  (This changed in release
        10.23. In earlier releases, before an opening  parenthesis  the  length
-       was  that  of the entire subpattern, and before an alternation bar or a
-       closing parenthesis the length was zero.)
+       was  that of the entire group, and before an alternation bar or a clos-
+       ing parenthesis the length was zero.)


        The pattern_position and next_item_length fields are intended  to  help
        in  distinguishing between different automatic callouts, which all have
@@ -4659,8 +4660,8 @@


REVISION

-       Last updated: 17 September 2018
-       Copyright (c) 1997-2018 University of Cambridge.
+       Last updated: 03 February 2019
+       Copyright (c) 1997-2019 University of Cambridge.
 ------------------------------------------------------------------------------



@@ -4689,10 +4690,10 @@
        repeat quantifiers on other  assertions,  for  example,  \b*  (but  not
        \b{3}), but these do not seem to have any use.


-       3.  Capturing  subpatterns that occur inside negative lookaround asser-
-       tions are counted, but their entries in the offsets vector are set only
-       when  a  negative  assertion  is a condition that has a matching branch
-       (that is, the condition is false).
+       3.  Capture groups that occur inside negative lookaround assertions are
+       counted, but their entries in the offsets vector are set  only  when  a
+       negative  assertion is a condition that has a matching branch (that is,
+       the condition is false).


        4. The following Perl escape sequences are not supported: \F,  \l,  \L,
        \u, \U, and \N when followed by a character name. \N on its own, match-
@@ -4744,14 +4745,14 @@
        groups up to PCRE2 release 10.23, but from release 10.30 this  changed,
        and backtracking into subroutine calls is now supported, as in Perl.


-       9.  If  any  of the backtracking control verbs are used in a subpattern
-       that is called as a subroutine  (whether  or  not  recursively),  their
-       effect  is  confined to that subpattern; it does not extend to the sur-
-       rounding pattern. This is not always the case in Perl.  In  particular,
-       if  (*THEN)  is  present in a group that is called as a subroutine, its
-       action is limited to that group, even if the group does not contain any
-       |  characters.  Note that such subpatterns are processed as anchored at
-       the point where they are tested.
+       9. If any of the backtracking control verbs are used in a group that is
+       called as a subroutine (whether or not recursively),  their  effect  is
+       confined  to that group; it does not extend to the surrounding pattern.
+       This is not always the case in  Perl.  In  particular,  if  (*THEN)  is
+       present  in  a group that is called as a subroutine, its action is lim-
+       ited to that group, even if the group does not contain  any  |  charac-
+       ters.  Note  that  such  groups  are processed as anchored at the point
+       where they are tested.


        10. If a pattern contains more than one backtracking control verb,  the
        first  one  that  is backtracked onto acts. For example, in the pattern
@@ -4767,91 +4768,90 @@
        matching  "aba"  against  the  pattern  /^(a(b)?)+$/  in Perl leaves $2
        unset, but in PCRE2 it is set to "b".


-       13. PCRE2's handling of duplicate subpattern numbers and duplicate sub-
-       pattern names is not as general as Perl's. This is a consequence of the
-       fact the PCRE2 works internally just with numbers,  using  an  external
-       table  to translate between numbers and names. In particular, a pattern
-       such as (?|(?<a>A)|(?<b>B), where the two  capturing  parentheses  have
-       the  same  number  but different names, is not supported, and causes an
-       error at compile time. If it were allowed, it would not be possible  to
-       distinguish  which  parentheses matched, because both names map to cap-
-       turing subpattern number 1. To avoid this confusing situation, an error
-       is given at compile time.
+       13. PCRE2's handling of duplicate capture group numbers  and  names  is
+       not  as  general as Perl's. This is a consequence of the fact the PCRE2
+       works internally just with numbers, using an external table  to  trans-
+       late  between  numbers  and  names.  In  particular,  a pattern such as
+       (?|(?<a>A)|(?<b>B), where the two capture groups have the  same  number
+       but  different  names, is not supported, and causes an error at compile
+       time. If it were allowed, it would not be possible to distinguish which
+       group  matched,  because  both  names map to capture group number 1. To
+       avoid this confusing situation, an error is given at compile time.


        14. Perl used to recognize comments in some places that PCRE2 does not,
-       for example, between the ( and ? at the start of a subpattern.  If  the
-       /x modifier is set, Perl allowed white space between ( and ? though the
-       latest Perls give an error (for a while it was just deprecated).  There
+       for  example,  between  the  ( and ? at the start of a group. If the /x
+       modifier is set, Perl allowed white space between ( and  ?  though  the
+       latest  Perls give an error (for a while it was just deprecated). There
        may still be some cases where Perl behaves differently.


-       15.  Perl,  when  in warning mode, gives warnings for character classes
-       such as [A-\d] or [a-[:digit:]]. It then treats the hyphens  as  liter-
+       15. Perl, when in warning mode, gives warnings  for  character  classes
+       such  as  [A-\d] or [a-[:digit:]]. It then treats the hyphens as liter-
        als. PCRE2 has no warning features, so it gives an error in these cases
        because they are almost certainly user mistakes.


-       16. In PCRE2, the upper/lower case character properties Lu and  Ll  are
-       not  affected when case-independent matching is specified. For example,
+       16.  In  PCRE2, the upper/lower case character properties Lu and Ll are
+       not affected when case-independent matching is specified. For  example,
        \p{Lu} always matches an upper case letter. I think Perl has changed in
-       this  respect; in the release at the time of writing (5.24), \p{Lu} and
+       this respect; in the release at the time of writing (5.24), \p{Lu}  and
        \p{Ll} match all letters, regardless of case, when case independence is
        specified.


-       17.  PCRE2  provides  some  extensions  to  the Perl regular expression
-       facilities.  Perl 5.10 includes new features that are  not  in  earlier
-       versions  of  Perl,  some  of which (such as named parentheses) were in
+       17. PCRE2 provides some  extensions  to  the  Perl  regular  expression
+       facilities.   Perl  5.10  includes new features that are not in earlier
+       versions of Perl, some of which (such as  named  parentheses)  were  in
        PCRE2 for some time before. This list is with respect to Perl 5.26:


-       (a) Although lookbehind assertions in PCRE2  must  match  fixed  length
-       strings,  each alternative branch of a lookbehind assertion can match a
-       different length of string. Perl requires them all  to  have  the  same
+       (a)  Although  lookbehind  assertions  in PCRE2 must match fixed length
+       strings, each alternative branch of a lookbehind assertion can match  a
+       different  length  of  string.  Perl requires them all to have the same
        length.


        (b) From PCRE2 10.23, backreferences to groups of fixed length are sup-
-       ported in lookbehinds, provided that there is no possibility of  refer-
-       encing  a  non-unique  number or name. Perl does not support backrefer-
+       ported  in lookbehinds, provided that there is no possibility of refer-
+       encing a non-unique number or name. Perl does  not  support  backrefer-
        ences in lookbehinds.


-       (c) If PCRE2_DOLLAR_ENDONLY is set and PCRE2_MULTILINE is not set,  the
+       (c)  If PCRE2_DOLLAR_ENDONLY is set and PCRE2_MULTILINE is not set, the
        $ meta-character matches only at the very end of the string.


-       (d)  A  backslash  followed  by  a  letter  with  no special meaning is
+       (d) A backslash followed  by  a  letter  with  no  special  meaning  is
        faulted. (Perl can be made to issue a warning.)


-       (e) If PCRE2_UNGREEDY is set, the greediness of the repetition  quanti-
+       (e)  If PCRE2_UNGREEDY is set, the greediness of the repetition quanti-
        fiers is inverted, that is, by default they are not greedy, but if fol-
        lowed by a question mark they are.


-       (f) PCRE2_ANCHORED can be used at matching time to force a  pattern  to
+       (f)  PCRE2_ANCHORED  can be used at matching time to force a pattern to
        be tried only at the first matching position in the subject string.


-       (g)     The     PCRE2_NOTBOL,    PCRE2_NOTEOL,    PCRE2_NOTEMPTY    and
+       (g)    The    PCRE2_NOTBOL,    PCRE2_NOTEOL,     PCRE2_NOTEMPTY     and
        PCRE2_NOTEMPTY_ATSTART options have no Perl equivalents.


-       (h) The \R escape sequence can be restricted to match only CR,  LF,  or
+       (h)  The  \R escape sequence can be restricted to match only CR, LF, or
        CRLF by the PCRE2_BSR_ANYCRLF option.


-       (i)  The  callout  facility is PCRE2-specific. Perl supports codeblocks
+       (i) The callout facility is PCRE2-specific.  Perl  supports  codeblocks
        and variable interpolation, but not general hooks on every match.


        (j) The partial matching facility is PCRE2-specific.


-       (k) The alternative matching function (pcre2_dfa_match() matches  in  a
+       (k)  The  alternative matching function (pcre2_dfa_match() matches in a
        different way and is not Perl-compatible.


-       (l)  PCRE2 recognizes some special sequences such as (*CR) or (*NO_JIT)
-       at the start of a pattern that  set  overall  options  that  cannot  be
+       (l) PCRE2 recognizes some special sequences such as (*CR) or  (*NO_JIT)
+       at  the  start  of  a  pattern  that set overall options that cannot be
        changed within the pattern.


-       18.  The  Perl  /a modifier restricts /d numbers to pure ascii, and the
-       /aa modifier restricts /i  case-insensitive  matching  to  pure  ascii,
-       ignoring  Unicode  rules.  This  separation  cannot be represented with
+       18. The Perl /a modifier restricts /d numbers to pure  ascii,  and  the
+       /aa  modifier  restricts  /i  case-insensitive  matching to pure ascii,
+       ignoring Unicode rules. This  separation  cannot  be  represented  with
        PCRE2_UCP.


        19. Perl has different limits than PCRE2. See the pcre2limit documenta-
        tion for details. Perl went with 5.10 from recursion to iteration keep-
        ing the intermediate matches on the heap, which is ~10% slower but does
-       not  fall into any stack-overflow limit. PCRE2 made a similar change at
-       release 10.30, and also has many build-time and  run-time  customizable
+       not fall into any stack-overflow limit. PCRE2 made a similar change  at
+       release  10.30,  and also has many build-time and run-time customizable
        limits.



@@ -4864,8 +4864,8 @@

REVISION

-       Last updated: 28 July 2018
-       Copyright (c) 1997-2018 University of Cambridge.
+       Last updated: 03 February 2019
+       Copyright (c) 1997-2019 University of Cambridge.
 ------------------------------------------------------------------------------



@@ -5306,23 +5306,22 @@

        The maximum length of a lookbehind assertion is 65535 characters.


-       There is no limit to the number of parenthesized subpatterns, but there
-       can be no more than 65535 capturing subpatterns. There is,  however,  a
-       limit  to  the  depth  of  nesting  of parenthesized subpatterns of all
-       kinds. This is imposed in order to limit the  amount  of  system  stack
-       used  at compile time. The default limit can be specified when PCRE2 is
-       built; if not, the default is set to 250.  An  application  can  change
-       this limit by calling pcre2_set_parens_nest_limit() to set the limit in
-       a compile context.
+       There  is no limit to the number of parenthesized groups, but there can
+       be no more than 65535 capture groups, and there is a limit to the depth
+       of  nesting  of parenthesized subpatterns of all kinds. This is imposed
+       in order to limit the amount of system stack used at compile time.  The
+       default limit can be specified when PCRE2 is built; if not, the default
+       is set to  250.  An  application  can  change  this  limit  by  calling
+       pcre2_set_parens_nest_limit() to set the limit in a compile context.


-       The maximum length of name for a named subpattern is 32 code units, and
-       the maximum number of named subpatterns is 10000.
+       The  maximum length of name for a named capture group is 32 code units,
+       and the maximum number of such groups is 10000.


-       The  maximum  length  of  a  name  in  a (*MARK), (*PRUNE), (*SKIP), or
-       (*THEN) verb is 255 code units for the 8-bit  library  and  65535  code
+       The maximum length of a  name  in  a  (*MARK),  (*PRUNE),  (*SKIP),  or
+       (*THEN)  verb  is  255  code units for the 8-bit library and 65535 code
        units for the 16-bit and 32-bit libraries.


-       The  maximum  length  of  a string argument to a callout is the largest
+       The maximum length of a string argument to a  callout  is  the  largest
        number a 32-bit unsigned integer can hold.



@@ -5335,8 +5334,8 @@

REVISION

-       Last updated: 30 March 2017
-       Copyright (c) 1997-2017 University of Cambridge.
+       Last updated: 02 February 2019
+       Copyright (c) 1997-2019 University of Cambridge.
 ------------------------------------------------------------------------------



@@ -6025,22 +6024,23 @@
        great  detail.  This  description  of  PCRE2's  regular  expressions is
        intended as reference material.


-       This document discusses the patterns that are supported by  PCRE2  when
-       its  main  matching function, pcre2_match(), is used. PCRE2 also has an
-       alternative matching function, pcre2_dfa_match(), which matches using a
-       different  algorithm  that is not Perl-compatible. Some of the features
-       discussed below are not available when DFA matching is used. The advan-
-       tages and disadvantages of the alternative function, and how it differs
-       from the normal function, are discussed in the pcre2matching page.
+       This document discusses the regular expression patterns that  are  sup-
+       ported  by  PCRE2  when  its  main matching function, pcre2_match(), is
+       used.   PCRE2   also   has   an    alternative    matching    function,
+       pcre2_dfa_match(),  which  matches  using a different algorithm that is
+       not Perl-compatible. Some of  the  features  discussed  below  are  not
+       available  when  DFA matching is used. The advantages and disadvantages
+       of the alternative function, and how it differs from the  normal  func-
+       tion, are discussed in the pcre2matching page.



SPECIAL START-OF-PATTERN ITEMS

-       A number of options that can be passed to pcre2_compile() can  also  be
+       A  number  of options that can be passed to pcre2_compile() can also be
        set by special items at the start of a pattern. These are not Perl-com-
-       patible, but are provided to make these options accessible  to  pattern
-       writers  who are not able to change the program that processes the pat-
-       tern. Any number of these items  may  appear,  but  they  must  all  be
+       patible,  but  are provided to make these options accessible to pattern
+       writers who are not able to change the program that processes the  pat-
+       tern.  Any  number  of  these  items  may  appear, but they must all be
        together right at the start of the pattern string, and the letters must
        be in upper case.


@@ -6048,31 +6048,31 @@

        In the 8-bit and 16-bit PCRE2 libraries, characters may be coded either
        as single code units, or as multiple UTF-8 or UTF-16 code units. UTF-32
-       can be specified for the 32-bit library, in which  case  it  constrains
-       the  character  values  to  valid  Unicode  code points. To process UTF
-       strings, PCRE2 must be built to include Unicode support (which  is  the
-       default).  When  using  UTF  strings you must either call the compiling
-       function with the PCRE2_UTF option, or the pattern must start with  the
-       special  sequence  (*UTF),  which is equivalent to setting the relevant
+       can  be  specified  for the 32-bit library, in which case it constrains
+       the character values to valid  Unicode  code  points.  To  process  UTF
+       strings,  PCRE2  must be built to include Unicode support (which is the
+       default). When using UTF strings you must  either  call  the  compiling
+       function  with the PCRE2_UTF option, or the pattern must start with the
+       special sequence (*UTF), which is equivalent to  setting  the  relevant
        option. How setting a UTF mode affects pattern matching is mentioned in
-       several  places  below.  There  is  also  a  summary of features in the
+       several places below. There is  also  a  summary  of  features  in  the
        pcre2unicode page.


        Some applications that allow their users to supply patterns may wish to
-       restrict   them   to   non-UTF   data  for  security  reasons.  If  the
-       PCRE2_NEVER_UTF option is passed  to  pcre2_compile(),  (*UTF)  is  not
+       restrict  them  to  non-UTF  data  for   security   reasons.   If   the
+       PCRE2_NEVER_UTF  option  is  passed  to  pcre2_compile(), (*UTF) is not
        allowed, and its appearance in a pattern causes an error.


    Unicode property support


-       Another  special  sequence that may appear at the start of a pattern is
-       (*UCP).  This has the same effect as setting the PCRE2_UCP  option:  it
-       causes  sequences such as \d and \w to use Unicode properties to deter-
+       Another special sequence that may appear at the start of a  pattern  is
+       (*UCP).   This  has the same effect as setting the PCRE2_UCP option: it
+       causes sequences such as \d and \w to use Unicode properties to  deter-
        mine character types, instead of recognizing only characters with codes
        less than 256 via a lookup table.


        Some applications that allow their users to supply patterns may wish to
-       restrict them for security reasons. If the  PCRE2_NEVER_UCP  option  is
+       restrict  them  for  security reasons. If the PCRE2_NEVER_UCP option is
        passed to pcre2_compile(), (*UCP) is not allowed, and its appearance in
        a pattern causes an error.


@@ -6079,38 +6079,38 @@
    Locking out empty string matching


        Starting a pattern with (*NOTEMPTY) or (*NOTEMPTY_ATSTART) has the same
-       effect  as  passing the PCRE2_NOTEMPTY or PCRE2_NOTEMPTY_ATSTART option
+       effect as passing the PCRE2_NOTEMPTY or  PCRE2_NOTEMPTY_ATSTART  option
        to whichever matching function is subsequently called to match the pat-
-       tern.  These  options  lock  out  the matching of empty strings, either
+       tern. These options lock out the  matching  of  empty  strings,  either
        entirely, or only at the start of the subject.


    Disabling auto-possessification


-       If a pattern starts with (*NO_AUTO_POSSESS), it has the same effect  as
-       setting  the PCRE2_NO_AUTO_POSSESS option. This stops PCRE2 from making
-       quantifiers possessive when what  follows  cannot  match  the  repeated
+       If  a pattern starts with (*NO_AUTO_POSSESS), it has the same effect as
+       setting the PCRE2_NO_AUTO_POSSESS option. This stops PCRE2 from  making
+       quantifiers  possessive  when  what  follows  cannot match the repeated
        item. For example, by default a+b is treated as a++b. For more details,
        see the pcre2api documentation.


    Disabling start-up optimizations


-       If a pattern starts with (*NO_START_OPT), it has  the  same  effect  as
+       If  a  pattern  starts  with (*NO_START_OPT), it has the same effect as
        setting the PCRE2_NO_START_OPTIMIZE option. This disables several opti-
-       mizations for quickly reaching "no match" results.  For  more  details,
+       mizations  for  quickly  reaching "no match" results. For more details,
        see the pcre2api documentation.


    Disabling automatic anchoring


-       If  a  pattern starts with (*NO_DOTSTAR_ANCHOR), it has the same effect
-       as setting the PCRE2_NO_DOTSTAR_ANCHOR option. This disables  optimiza-
+       If a pattern starts with (*NO_DOTSTAR_ANCHOR), it has the  same  effect
+       as  setting the PCRE2_NO_DOTSTAR_ANCHOR option. This disables optimiza-
        tions that apply to patterns whose top-level branches all start with .*
-       (match any number of arbitrary characters). For more details,  see  the
+       (match  any  number of arbitrary characters). For more details, see the
        pcre2api documentation.


    Disabling JIT compilation


-       If  a  pattern  that starts with (*NO_JIT) is successfully compiled, an
-       attempt by the application to apply the  JIT  optimization  by  calling
+       If a pattern that starts with (*NO_JIT) is  successfully  compiled,  an
+       attempt  by  the  application  to apply the JIT optimization by calling
        pcre2_jit_compile() is ignored.


    Setting match resource limits
@@ -6117,17 +6117,17 @@


        The pcre2_match() function contains a counter that is incremented every
        time it goes round its main loop. The caller of pcre2_match() can set a
-       limit  on  this counter, which therefore limits the amount of computing
+       limit on this counter, which therefore limits the amount  of  computing
        resource used for a match. The maximum depth of nested backtracking can
-       also  be  limited;  this indirectly restricts the amount of heap memory
-       that is used, but there is also an explicit memory limit  that  can  be
+       also be limited; this indirectly restricts the amount  of  heap  memory
+       that  is  used,  but there is also an explicit memory limit that can be
        set.


-       These  facilities  are  provided to catch runaway matches that are pro-
-       voked by patterns with huge matching trees (a typical example is a pat-
-       tern  with  nested unlimited repeats applied to a long string that does
-       not match). When one of these limits is reached, pcre2_match() gives an
-       error  return.  The limits can also be set by items at the start of the
+       These facilities are provided to catch runaway matches  that  are  pro-
+       voked  by patterns with huge matching trees. A common example is a pat-
+       tern with nested unlimited repeats applied to a long string  that  does
+       not  match. When one of these limits is reached, pcre2_match() gives an
+       error return. The limits can also be set by items at the start  of  the
        pattern of the form


          (*LIMIT_HEAP=d)
@@ -6135,35 +6135,35 @@
          (*LIMIT_DEPTH=d)


        where d is any number of decimal digits. However, the value of the set-
-       ting  must  be  less than the value set (or defaulted) by the caller of
-       pcre2_match() for it to have any effect. In other  words,  the  pattern
-       writer  can lower the limits set by the programmer, but not raise them.
-       If there is more than one setting of one of  these  limits,  the  lower
-       value  is used. The heap limit is specified in kibibytes (units of 1024
+       ting must be less than the value set (or defaulted) by  the  caller  of
+       pcre2_match()  for  it  to have any effect. In other words, the pattern
+       writer can lower the limits set by the programmer, but not raise  them.
+       If  there  is  more  than one setting of one of these limits, the lower
+       value is used. The heap limit is specified in kibibytes (units of  1024
        bytes).


-       Prior to release 10.30, LIMIT_DEPTH was  called  LIMIT_RECURSION.  This
+       Prior  to  release  10.30, LIMIT_DEPTH was called LIMIT_RECURSION. This
        name is still recognized for backwards compatibility.


        The heap limit applies only when the pcre2_match() or pcre2_dfa_match()
        interpreters are used for matching. It does not apply to JIT. The match
-       limit  is used (but in a different way) when JIT is being used, or when
+       limit is used (but in a different way) when JIT is being used, or  when
        pcre2_dfa_match() is called, to limit computing resource usage by those
-       matching  functions.  The depth limit is ignored by JIT but is relevant
-       for DFA matching, which uses function recursion for  recursions  within
-       the  pattern  and  for lookaround assertions and atomic groups. In this
+       matching functions. The depth limit is ignored by JIT but  is  relevant
+       for  DFA  matching, which uses function recursion for recursions within
+       the pattern and for lookaround assertions and atomic  groups.  In  this
        case, the depth limit controls the depth of such recursion.


    Newline conventions


-       PCRE2 supports six different conventions for indicating line breaks  in
-       strings:  a  single  CR (carriage return) character, a single LF (line-
+       PCRE2  supports six different conventions for indicating line breaks in
+       strings: a single CR (carriage return) character, a  single  LF  (line-
        feed) character, the two-character sequence CRLF, any of the three pre-
-       ceding,  any  Unicode  newline  sequence,  or the NUL character (binary
-       zero). The pcre2api page has further  discussion  about  newlines,  and
+       ceding, any Unicode newline sequence,  or  the  NUL  character  (binary
+       zero).  The  pcre2api  page  has further discussion about newlines, and
        shows how to set the newline convention when calling pcre2_compile().


-       It  is also possible to specify a newline convention by starting a pat-
+       It is also possible to specify a newline convention by starting a  pat-
        tern string with one of the following sequences:


          (*CR)        carriage return
@@ -6174,7 +6174,7 @@
          (*NUL)       the NUL character (binary zero)


        These override the default and the options given to the compiling func-
-       tion.  For  example,  on  a Unix system where LF is the default newline
+       tion. For example, on a Unix system where LF  is  the  default  newline
        sequence, the pattern


          (*CR)a.b
@@ -6183,30 +6183,30 @@
        no longer a newline. If more than one of these settings is present, the
        last one is used.


-       The newline convention affects where the circumflex and  dollar  asser-
+       The  newline  convention affects where the circumflex and dollar asser-
        tions are true. It also affects the interpretation of the dot metachar-
-       acter when PCRE2_DOTALL is not set, and the behaviour of  \N  when  not
-       followed  by  an opening brace. However, it does not affect what the \R
-       escape sequence matches.  By  default,  this  is  any  Unicode  newline
+       acter  when  PCRE2_DOTALL  is not set, and the behaviour of \N when not
+       followed by an opening brace. However, it does not affect what  the  \R
+       escape  sequence  matches.  By  default,  this  is  any Unicode newline
        sequence, for Perl compatibility. However, this can be changed; see the
        next section and the description of \R in the section entitled "Newline
-       sequences"  below. A change of \R setting can be combined with a change
+       sequences" below. A change of \R setting can be combined with a  change
        of newline convention.


    Specifying what \R matches


        It is possible to restrict \R to match only CR, LF, or CRLF (instead of
-       the  complete  set  of  Unicode  line  endings)  by  setting the option
-       PCRE2_BSR_ANYCRLF at compile time. This effect can also be achieved  by
-       starting  a  pattern  with (*BSR_ANYCRLF). For completeness, (*BSR_UNI-
+       the complete set  of  Unicode  line  endings)  by  setting  the  option
+       PCRE2_BSR_ANYCRLF  at compile time. This effect can also be achieved by
+       starting a pattern with (*BSR_ANYCRLF).  For  completeness,  (*BSR_UNI-
        CODE) is also recognized, corresponding to PCRE2_BSR_UNICODE.



EBCDIC CHARACTER CODES

-       PCRE2 can be compiled to run in an environment that uses EBCDIC as  its
-       character  code instead of ASCII or Unicode (typically a mainframe sys-
-       tem). In the sections below, character code values are  ASCII  or  Uni-
+       PCRE2  can be compiled to run in an environment that uses EBCDIC as its
+       character code instead of ASCII or Unicode (typically a mainframe  sys-
+       tem).  In  the  sections below, character code values are ASCII or Uni-
        code; in an EBCDIC environment these characters may have different code
        values, and there are no code points greater than 255.


@@ -6213,9 +6213,9 @@

CHARACTERS AND METACHARACTERS

-       A regular expression is a pattern that is  matched  against  a  subject
-       string  from  left  to right. Most characters stand for themselves in a
-       pattern, and match the corresponding characters in the  subject.  As  a
+       A  regular  expression  is  a pattern that is matched against a subject
+       string from left to right. Most characters stand for  themselves  in  a
+       pattern,  and  match  the corresponding characters in the subject. As a
        trivial example, the pattern


          The quick brown fox
@@ -6224,10 +6224,11 @@
        caseless matching is specified (the PCRE2_CASELESS option), letters are
        matched independently of case.


-       The  power  of  regular  expressions  comes from the ability to include
-       alternatives and repetitions in the pattern. These are encoded  in  the
-       pattern by the use of metacharacters, which do not stand for themselves
-       but instead are interpreted in some special way.
+       The power of regular expressions comes from the ability to include wild
+       cards, character classes, alternatives, and repetitions in the pattern.
+       These are encoded in the pattern by the use of metacharacters, which do
+       not  stand  for  themselves but instead are interpreted in some special
+       way.


        There are two different sets of metacharacters: those that  are  recog-
        nized  anywhere in the pattern except within square brackets, and those
@@ -6240,14 +6241,11 @@
          .      match any character except newline (by default)
          [      start character class definition
          |      start of alternative branch
-         (      start subpattern
-         )      end subpattern
-         ?      extends the meaning of (
-                also 0 or 1 quantifier
-                also quantifier minimizer
+         (      start group or control verb
+         )      end group or control verb
          *      0 or more quantifier
-         +      1 or more quantifier
-                also "possessive quantifier"
+         +      1 or more quantifier; also "possessive quantifier"
+         ?      0 or 1 quantifier; also quantifier minimizer
          {      start min/max quantifier


        Part  of  a  pattern  that is in square brackets is called a "character
@@ -6256,8 +6254,7 @@
          \      general escape character
          ^      negate the class, but only if the first character
          -      indicates character range
-         [      POSIX character class (only if followed by POSIX
-                  syntax)
+         [      POSIX character class (if followed by POSIX syntax)
          ]      terminates the character class


        The following sections describe the use of each of the metacharacters.
@@ -6266,7 +6263,7 @@
 BACKSLASH


        The backslash character has several uses. Firstly, if it is followed by
-       a character that is not a number or a letter, it takes away any special
+       a  character that is not a digit or a letter, it takes away any special
        meaning that character may have. This use of  backslash  as  an  escape
        character applies both inside and outside character classes.


@@ -6277,7 +6274,7 @@
        that it stands for itself.  In particular, if you want to match a back-
        slash, you write \\.


-       In a UTF mode, only ASCII numbers and letters have any special  meaning
+       In a UTF mode, only ASCII digits and letters have any  special  meaning
        after  a  backslash.  All  other characters (in particular, those whose
        code points are greater than 127) are treated as literals.


@@ -6287,14 +6284,14 @@
        are ignored. An escaping backslash can be used to include a white space
        or # character as part of the pattern.


-       If you want to remove the special meaning from a  sequence  of  charac-
-       ters,  you can do so by putting them between \Q and \E. This is differ-
-       ent from Perl in that $ and  @  are  handled  as  literals  in  \Q...\E
-       sequences  in PCRE2, whereas in Perl, $ and @ cause variable interpola-
-       tion. Also, Perl does "double-quotish backslash interpolation"  on  any
-       backslashes  between \Q and \E which, its documentation says, "may lead
-       to confusing results". PCRE2 treats a backslash between \Q and \E  just
-       like any other character. Note the following examples:
+       If you want to treat all characters in a sequence as literals, you  can
+       do so by putting them between \Q and \E. This is different from Perl in
+       that $ and @ are handled as literals in  \Q...\E  sequences  in  PCRE2,
+       whereas  in Perl, $ and @ cause variable interpolation. Also, Perl does
+       "double-quotish backslash interpolation" on any backslashes between  \Q
+       and  \E which, its documentation says, "may lead to confusing results".
+       PCRE2 treats a backslash between \Q and \E just like any other  charac-
+       ter. Note the following examples:


          Pattern            PCRE2 matches   Perl matches


@@ -6319,8 +6316,9 @@
        acters in patterns in a visible manner. There is no restriction on  the
        appearance  of non-printing characters in a pattern, but when a pattern
        is being prepared by text editing, it is often easier to use one of the
-       following  escape sequences than the binary character it represents. In
-       an ASCII or Unicode environment, these escapes are as follows:
+       following  escape  sequences  instead of the binary character it repre-
+       sents. In an ASCII or Unicode environment, these escapes  are  as  fol-
+       lows:


          \a          alarm, that is, the BEL character (hex 07)
          \cx         "control-x", where x is any printable ASCII character
@@ -6337,58 +6335,58 @@
          \N{U+hhh..} character with Unicode hex code point hhh..
          \uhhhh      character with hex code hhhh (when PCRE2_ALT_BSUX is set)


-       There are some legacy applications where  the  escape  sequence  \r  is
+       There  are  some  legacy  applications  where the escape sequence \r is
        expected to match a newline. If the PCRE2_EXTRA_ESCAPED_CR_IS_LF option
-       is set, \r in a pattern is converted to \n so  that  it  matches  a  LF
+       is  set,  \r  in  a  pattern is converted to \n so that it matches a LF
        (linefeed) instead of a CR (carriage return) character.


-       The  \N{U+hhh..}  escape sequence is recognized only when the PCRE2_UTF
+       The \N{U+hhh..} escape sequence is recognized only when  the  PCRE2_UTF
        option is set, that is, when PCRE2 is operating in a Unicode mode. Perl
-       also  uses  \N{name}  to specify characters by Unicode name; PCRE2 does
-       not support this.  Note that when \N is  not  followed  by  an  opening
-       brace  (curly  bracket)  it has an entirely different meaning, matching
+       also uses \N{name} to specify characters by Unicode  name;  PCRE2  does
+       not  support  this.   Note  that  when \N is not followed by an opening
+       brace (curly bracket) it has an entirely  different  meaning,  matching
        any character that is not a newline.


-       The precise effect of \cx on ASCII characters is as follows: if x is  a
-       lower  case  letter,  it  is converted to upper case. Then bit 6 of the
+       The  precise effect of \cx on ASCII characters is as follows: if x is a
+       lower case letter, it is converted to upper case. Then  bit  6  of  the
        character (hex 40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A
-       (A  is  41, Z is 5A), but \c{ becomes hex 3B ({ is 7B), and \c; becomes
-       hex 7B (; is 3B). If the code unit following \c has a value  less  than
+       (A is 41, Z is 5A), but \c{ becomes hex 3B ({ is 7B), and  \c;  becomes
+       hex  7B  (; is 3B). If the code unit following \c has a value less than
        32 or greater than 126, a compile-time error occurs.


-       When  PCRE2  is  compiled in EBCDIC mode, \N{U+hhh..} is not supported.
+       When PCRE2 is compiled in EBCDIC mode, \N{U+hhh..}  is  not  supported.
        \a, \e, \f, \n, \r, and \t generate the appropriate EBCDIC code values.
        The \c escape is processed as specified for Perl in the perlebcdic doc-
-       ument. The only characters that are allowed after \c are A-Z,  a-z,  or
-       one  of @, [, \, ], ^, _, or ?. Any other character provokes a compile-
-       time error. The sequence \c@ encodes character code  0;  after  \c  the
-       letters  (in either case) encode characters 1-26 (hex 01 to hex 1A); [,
-       \, ], ^, and _ encode characters 27-31 (hex 1B  to  hex  1F),  and  \c?
+       ument.  The  only characters that are allowed after \c are A-Z, a-z, or
+       one of @, [, \, ], ^, _, or ?. Any other character provokes a  compile-
+       time  error.  The  sequence  \c@ encodes character code 0; after \c the
+       letters (in either case) encode characters 1-26 (hex 01 to hex 1A);  [,
+       \,  ],  ^,  and  _  encode characters 27-31 (hex 1B to hex 1F), and \c?
        becomes either 255 (hex FF) or 95 (hex 5F).


-       Thus,  apart  from  \c?, these escapes generate the same character code
-       values as they do in an ASCII environment, though the meanings  of  the
-       values  mostly  differ. For example, \cG always generates code value 7,
+       Thus, apart from \c?, these escapes generate the  same  character  code
+       values  as  they do in an ASCII environment, though the meanings of the
+       values mostly differ. For example, \cG always generates code  value  7,
        which is BEL in ASCII but DEL in EBCDIC.


-       The sequence \c? generates DEL (127, hex 7F) in an  ASCII  environment,
-       but  because  127  is  not a control character in EBCDIC, Perl makes it
-       generate the APC character. Unfortunately, there are  several  variants
-       of  EBCDIC.  In  most  of them the APC character has the value 255 (hex
-       FF), but in the one Perl calls POSIX-BC its value is 95  (hex  5F).  If
+       The  sequence  \c? generates DEL (127, hex 7F) in an ASCII environment,
+       but because 127 is not a control character in  EBCDIC,  Perl  makes  it
+       generate  the  APC character. Unfortunately, there are several variants
+       of EBCDIC. In most of them the APC character has  the  value  255  (hex
+       FF),  but  in  the one Perl calls POSIX-BC its value is 95 (hex 5F). If
        certain other characters have POSIX-BC values, PCRE2 makes \c? generate
        95; otherwise it generates 255.


-       After \0 up to two further octal digits are read. If  there  are  fewer
-       than  two  digits,  just  those  that  are  present  are used. Thus the
+       After  \0  up  to two further octal digits are read. If there are fewer
+       than two digits, just  those  that  are  present  are  used.  Thus  the
        sequence \0\x\015 specifies two binary zeros followed by a CR character
        (code value 13). Make sure you supply two digits after the initial zero
        if the pattern character that follows is itself an octal digit.


-       The escape \o must be followed by a sequence of octal digits,  enclosed
-       in  braces.  An  error occurs if this is not the case. This escape is a
-       recent addition to Perl; it provides way of specifying  character  code
-       points  as  octal  numbers  greater than 0777, and it also allows octal
+       The  escape \o must be followed by a sequence of octal digits, enclosed
+       in braces. An error occurs if this is not the case. This  escape  is  a
+       recent  addition  to Perl; it provides way of specifying character code
+       points as octal numbers greater than 0777, and  it  also  allows  octal
        numbers and backreferences to be unambiguously specified.


        For greater clarity and unambiguity, it is best to avoid following \ by
@@ -6401,21 +6399,21 @@


        Outside a character class, PCRE2 reads the digit and any following dig-
        its as a decimal number. If the number is less than 10, begins with the
-       digit 8 or 9, or if there are at least  that  many  previous  capturing
-       left  parentheses  in the expression, the entire sequence is taken as a
-       backreference. A description of how this works is given later,  follow-
-       ing  the  discussion  of  parenthesized  subpatterns.  Otherwise, up to
-       three octal digits are read to form a character code.
+       digit  8  or  9,  or  if  there are at least that many previous capture
+       groups in the expression, the entire sequence is taken as a  backrefer-
+       ence.  A  description  of  how this works is given later, following the
+       discussion of parenthesized groups.  Otherwise, up to three octal  dig-
+       its are read to form a character code.


-       Inside a character class, PCRE2 handles \8 and \9 as the literal  char-
-       acters  "8"  and "9", and otherwise reads up to three octal digits fol-
+       Inside  a character class, PCRE2 handles \8 and \9 as the literal char-
+       acters "8" and "9", and otherwise reads up to three octal  digits  fol-
        lowing the backslash, using them to generate a data character. Any sub-
-       sequent  digits  stand for themselves. For example, outside a character
+       sequent digits stand for themselves. For example, outside  a  character
        class:


          \040   is another way of writing an ASCII space
          \40    is the same, provided there are fewer than 40
-                   previous capturing subpatterns
+                   previous capture groups
          \7     is always a backreference
          \11    might be a backreference, or another way of
                    writing a tab
@@ -6427,22 +6425,23 @@
                    the value 255 (decimal)
          \81    is always a backreference


-       Note that octal values of 100 or greater that are specified using  this
-       syntax  must  not be introduced by a leading zero, because no more than
+       Note  that octal values of 100 or greater that are specified using this
+       syntax must not be introduced by a leading zero, because no  more  than
        three octal digits are ever read.


-       By default, after \x that is not followed by {, from zero to two  hexa-
-       decimal  digits  are  read (letters can be in upper or lower case). Any
+       By  default, after \x that is not followed by {, from zero to two hexa-
+       decimal digits are read (letters can be in upper or  lower  case).  Any
        number of hexadecimal digits may appear between \x{ and }. If a charac-
-       ter  other  than  a  hexadecimal digit appears between \x{ and }, or if
+       ter other than a hexadecimal digit appears between \x{  and  },  or  if
        there is no terminating }, an error occurs.


-       If the PCRE2_ALT_BSUX option is set, the interpretation  of  \x  is  as
+       If  the  PCRE2_ALT_BSUX  option  is set, the interpretation of \x is as
        just described only when it is followed by two hexadecimal digits. Oth-
-       erwise, it matches a literal "x" character. In this mode,  support  for
-       code  points greater than 256 is provided by \u, which must be followed
-       by four hexadecimal digits; otherwise it matches a literal "u"  charac-
-       ter.
+       erwise,  it  matches a literal "x" character. In this mode, support for
+       code points greater than 256 is provided by \u, which must be  followed
+       by  four hexadecimal digits; otherwise it matches a literal "u" charac-
+       ter. This syntax makes PCRE2 behave like ECMAscript  (aka  JavaScript).
+       Code points greater than 0xFFFF are not supported.


        Characters whose value is less than 256 can be defined by either of the
        two syntaxes for \x (or by \u in PCRE2_ALT_BSUX mode). There is no dif-
@@ -6490,13 +6489,13 @@
        The  sequence  \g  followed  by a signed or unsigned number, optionally
        enclosed in braces, is an absolute or relative backreference.  A  named
        backreference  can  be  coded as \g{name}. Backreferences are discussed
-       later, following the discussion of parenthesized subpatterns.
+       later, following the discussion of parenthesized groups.


    Absolute and relative subroutine calls


        For compatibility with Oniguruma, the non-Perl syntax \g followed by  a
        name or a number enclosed either in angle brackets or single quotes, is
-       an alternative syntax for referencing a subpattern as  a  "subroutine".
+       an alternative syntax for referencing a capture group as a  subroutine.
        Details  are  discussed  later.   Note  that  \g{...} (Perl syntax) and
        \g<...> (Oniguruma syntax) are not synonymous. The former is a backref-
        erence; the latter is a subroutine call.
@@ -6653,23 +6652,25 @@


        When PCRE2 is built with Unicode support  (the  default),  three  addi-
        tional  escape sequences that match characters with specific properties
-       are available. In 8-bit non-UTF-8 mode, these sequences are  of  course
-       limited  to testing characters whose code points are less than 256, but
-       they do work in this mode.  In 32-bit non-UTF mode, code points greater
-       than  0x10ffff  (the  Unicode  limit) may be encountered. These are all
-       treated as being in the Unknown script and with an unassigned type. The
-       extra escape sequences are:
+       are available. They can be used in any mode, though in 8-bit and 16-bit
+       non-UTF  modes these sequences are of course limited to testing charac-
+       ters whose code points are less than U+0100 and U+10000,  respectively.
+       In  32-bit non-UTF mode, code points greater than 0x10ffff (the Unicode
+       limit) may be encountered. These  are  all  treated  as  being  in  the
+       Unknown  script and with an unassigned type. The extra escape sequences
+       are:


          \p{xx}   a character with the xx property
          \P{xx}   a character without the xx property
          \X       a Unicode extended grapheme cluster


-       The  property  names represented by xx above are limited to the Unicode
-       script names, the general category properties, "Any", which matches any
-       character  (including  newline),  and  some  special  PCRE2  properties
-       (described in the next section).  Other Perl properties such as  "InMu-
-       sicalSymbols"  are  not supported by PCRE2.  Note that \P{Any} does not
-       match any characters, so always causes a match failure.
+       The property names represented by xx above are case-sensitive. There is
+       support  for Unicode script names, Unicode general category properties,
+       "Any", which matches any character (including newline), and  some  spe-
+       cial  PCRE2  properties  (described  in  the next section).  Other Perl
+       properties such as "InMusicalSymbols" are not supported by PCRE2.  Note
+       that  \P{Any}  does  not match any characters, so always causes a match
+       failure.


        Sets of Unicode characters are defined as belonging to certain scripts.
        A  character from one of these sets can be matched using a script name.
@@ -6772,11 +6773,13 @@
        has the Lu, Ll, or Lt property, in other words, a letter  that  is  not
        classified as a modifier or "other".


-       The  Cs  (Surrogate)  property  applies only to characters in the range
-       U+D800 to U+DFFF. Such characters are not valid in Unicode strings  and
-       so  cannot  be  tested  by PCRE2, unless UTF validity checking has been
-       turned off (see the discussion of PCRE2_NO_UTF_CHECK  in  the  pcre2api
-       page). Perl does not support the Cs property.
+       The  Cs  (Surrogate)  property  applies  only  to characters whose code
+       points are in the range U+D800 to U+DFFF. These characters are no  dif-
+       ferent  to any other character when PCRE2 is not in UTF mode (using the
+       16-bit or 32-bit library).  However, they  are  not  valid  in  Unicode
+       strings and so cannot be tested by PCRE2 in UTF mode, unless UTF valid-
+       ity  checking  has   been   turned   off   (see   the   discussion   of
+       PCRE2_NO_UTF_CHECK in the pcre2api page).


        The  long  synonyms  for  property  names  that  Perl supports (such as
        \p{Letter}) are not supported by PCRE2, nor is it permitted  to  prefix
@@ -6917,8 +6920,8 @@
        The final use of backslash is for certain simple assertions. An  asser-
        tion  specifies a condition that has to be met at a particular point in
        a match, without consuming any characters from the subject string.  The
-       use  of subpatterns for more complicated assertions is described below.
-       The backslashed assertions are:
+       use  of groups for more complicated assertions is described below.  The
+       backslashed assertions are:


          \b     matches at a word boundary
          \B     matches when not at a word boundary
@@ -6935,40 +6938,41 @@
        A word boundary is a position in the subject string where  the  current
        character  and  the previous character do not both match \w or \W (i.e.
        one matches \w and the other matches \W), or the start or  end  of  the
-       string  if  the  first or last character matches \w, respectively. In a
-       UTF mode, the meanings of \w and \W  can  be  changed  by  setting  the
-       PCRE2_UCP option. When this is done, it also affects \b and \B. Neither
-       PCRE2 nor Perl has a separate "start of word" or "end of word"  metase-
-       quence.  However,  whatever follows \b normally determines which it is.
-       For example, the fragment \ba matches "a" at the start of a word.
+       string  if  the  first or last character matches \w, respectively. When
+       PCRE2 is built with Unicode support, the meanings of \w and \W  can  be
+       changed  by  setting  the  PCRE2_UCP option. When this is done, it also
+       affects \b and \B. Neither PCRE2 nor Perl  has  a  separate  "start  of
+       word"  or "end of word" metasequence. However, whatever follows \b nor-
+       mally determines which it is. For example, the fragment \ba matches "a"
+       at the start of a word.


-       The \A, \Z, and \z assertions differ from  the  traditional  circumflex
+       The  \A,  \Z,  and \z assertions differ from the traditional circumflex
        and dollar (described in the next section) in that they only ever match
-       at the very start and end of the subject string, whatever  options  are
-       set.  Thus,  they are independent of multiline mode. These three asser-
-       tions are not affected by the  PCRE2_NOTBOL  or  PCRE2_NOTEOL  options,
-       which  affect only the behaviour of the circumflex and dollar metachar-
-       acters. However, if the startoffset argument of pcre2_match()  is  non-
-       zero,  indicating  that  matching is to start at a point other than the
-       beginning of the subject, \A can never match.  The  difference  between
-       \Z  and \z is that \Z matches before a newline at the end of the string
+       at  the  very start and end of the subject string, whatever options are
+       set. Thus, they are independent of multiline mode. These  three  asser-
+       tions  are  not  affected  by the PCRE2_NOTBOL or PCRE2_NOTEOL options,
+       which affect only the behaviour of the circumflex and dollar  metachar-
+       acters.  However,  if the startoffset argument of pcre2_match() is non-
+       zero, indicating that matching is to start at a point  other  than  the
+       beginning  of  the subject, \A can never match.  The difference between
+       \Z and \z is that \Z matches before a newline at the end of the  string
        as well as at the very end, whereas \z matches only at the end.


-       The \G assertion is true only when the current matching position is  at
-       the  start point of the matching process, as specified by the startoff-
-       set argument of pcre2_match(). It differs from \A  when  the  value  of
-       startoffset  is  non-zero. By calling pcre2_match() multiple times with
-       appropriate arguments, you can mimic Perl's /g option,  and  it  is  in
+       The  \G assertion is true only when the current matching position is at
+       the start point of the matching process, as specified by the  startoff-
+       set  argument  of  pcre2_match().  It differs from \A when the value of
+       startoffset is non-zero. By calling pcre2_match() multiple  times  with
+       appropriate  arguments,  you  can  mimic Perl's /g option, and it is in
        this kind of implementation where \G can be useful.


-       Note,  however,  that  PCRE2's  implementation of \G, being true at the
-       starting character of the matching process, is  subtly  different  from
-       Perl's,  which  defines it as true at the end of the previous match. In
-       Perl, these can be different when the  previously  matched  string  was
+       Note, however, that PCRE2's implementation of \G,  being  true  at  the
+       starting  character  of  the matching process, is subtly different from
+       Perl's, which defines it as true at the end of the previous  match.  In
+       Perl,  these  can  be  different when the previously matched string was
        empty. Because PCRE2 does just one match at a time, it cannot reproduce
        this behaviour.


-       If all the alternatives of a pattern begin with \G, the  expression  is
+       If  all  the alternatives of a pattern begin with \G, the expression is
        anchored to the starting match position, and the "anchored" flag is set
        in the compiled regular expression.


@@ -6975,70 +6979,70 @@

CIRCUMFLEX AND DOLLAR

-       The circumflex and dollar  metacharacters  are  zero-width  assertions.
-       That  is,  they test for a particular condition being true without con-
+       The  circumflex  and  dollar  metacharacters are zero-width assertions.
+       That is, they test for a particular condition being true  without  con-
        suming any characters from the subject string. These two metacharacters
-       are  concerned  with matching the starts and ends of lines. If the new-
-       line convention is set so that only the two-character sequence CRLF  is
-       recognized  as  a newline, isolated CR and LF characters are treated as
+       are concerned with matching the starts and ends of lines. If  the  new-
+       line  convention is set so that only the two-character sequence CRLF is
+       recognized as a newline, isolated CR and LF characters are  treated  as
        ordinary data characters, and are not recognized as newlines.


        Outside a character class, in the default matching mode, the circumflex
-       character  is  an  assertion  that is true only if the current matching
-       point is at the start of the subject string. If the  startoffset  argu-
-       ment  of  pcre2_match() is non-zero, or if PCRE2_NOTBOL is set, circum-
-       flex can never match if the PCRE2_MULTILINE option is unset.  Inside  a
-       character  class,  circumflex  has  an  entirely different meaning (see
+       character is an assertion that is true only  if  the  current  matching
+       point  is  at the start of the subject string. If the startoffset argu-
+       ment of pcre2_match() is non-zero, or if PCRE2_NOTBOL is  set,  circum-
+       flex  can  never match if the PCRE2_MULTILINE option is unset. Inside a
+       character class, circumflex has  an  entirely  different  meaning  (see
        below).


-       Circumflex need not be the first character of the pattern if  a  number
-       of  alternatives are involved, but it should be the first thing in each
-       alternative in which it appears if the pattern is ever  to  match  that
-       branch.  If all possible alternatives start with a circumflex, that is,
-       if the pattern is constrained to match only at the start  of  the  sub-
-       ject,  it  is  said  to be an "anchored" pattern. (There are also other
+       Circumflex  need  not be the first character of the pattern if a number
+       of alternatives are involved, but it should be the first thing in  each
+       alternative  in  which  it appears if the pattern is ever to match that
+       branch. If all possible alternatives start with a circumflex, that  is,
+       if  the  pattern  is constrained to match only at the start of the sub-
+       ject, it is said to be an "anchored" pattern.  (There  are  also  other
        constructs that can cause a pattern to be anchored.)


-       The dollar character is an assertion that is true only if  the  current
-       matching  point  is  at  the  end of the subject string, or immediately
-       before a newline  at  the  end  of  the  string  (by  default),  unless
+       The  dollar  character is an assertion that is true only if the current
+       matching point is at the end of  the  subject  string,  or  immediately
+       before  a  newline  at  the  end  of  the  string  (by default), unless
        PCRE2_NOTEOL is set. Note, however, that it does not actually match the
        newline. Dollar need not be the last character of the pattern if a num-
        ber of alternatives are involved, but it should be the last item in any
-       branch in which it appears. Dollar has no special meaning in a  charac-
+       branch  in which it appears. Dollar has no special meaning in a charac-
        ter class.


-       The  meaning  of  dollar  can be changed so that it matches only at the
-       very end of the string, by setting the PCRE2_DOLLAR_ENDONLY  option  at
+       The meaning of dollar can be changed so that it  matches  only  at  the
+       very  end  of the string, by setting the PCRE2_DOLLAR_ENDONLY option at
        compile time. This does not affect the \Z assertion.


        The meanings of the circumflex and dollar metacharacters are changed if
-       the PCRE2_MULTILINE option is set. When this  is  the  case,  a  dollar
-       character  matches before any newlines in the string, as well as at the
-       very end, and a circumflex matches immediately after internal  newlines
-       as  well as at the start of the subject string. It does not match after
-       a newline that ends the string, for compatibility with  Perl.  However,
+       the  PCRE2_MULTILINE  option  is  set.  When this is the case, a dollar
+       character matches before any newlines in the string, as well as at  the
+       very  end, and a circumflex matches immediately after internal newlines
+       as well as at the start of the subject string. It does not match  after
+       a  newline  that ends the string, for compatibility with Perl. However,
        this can be changed by setting the PCRE2_ALT_CIRCUMFLEX option.


-       For  example, the pattern /^abc$/ matches the subject string "def\nabc"
-       (where \n represents a newline) in multiline mode, but  not  otherwise.
-       Consequently,  patterns  that  are anchored in single line mode because
-       all branches start with ^ are not anchored in  multiline  mode,  and  a
-       match  for  circumflex  is  possible  when  the startoffset argument of
-       pcre2_match() is non-zero. The PCRE2_DOLLAR_ENDONLY option  is  ignored
+       For example, the pattern /^abc$/ matches the subject string  "def\nabc"
+       (where  \n  represents a newline) in multiline mode, but not otherwise.
+       Consequently, patterns that are anchored in single  line  mode  because
+       all  branches  start  with  ^ are not anchored in multiline mode, and a
+       match for circumflex is  possible  when  the  startoffset  argument  of
+       pcre2_match()  is  non-zero. The PCRE2_DOLLAR_ENDONLY option is ignored
        if PCRE2_MULTILINE is set.


-       When  the  newline  convention (see "Newline conventions" below) recog-
-       nizes the two-character sequence CRLF as a newline, this is  preferred,
-       even  if  the  single  characters CR and LF are also recognized as new-
-       lines. For example, if the newline convention  is  "any",  a  multiline
-       mode  circumflex matches before "xyz" in the string "abc\r\nxyz" rather
-       than after CR, even though CR on its own is a valid newline.  (It  also
+       When the newline convention (see "Newline  conventions"  below)  recog-
+       nizes  the two-character sequence CRLF as a newline, this is preferred,
+       even if the single characters CR and LF are  also  recognized  as  new-
+       lines.  For  example,  if  the newline convention is "any", a multiline
+       mode circumflex matches before "xyz" in the string "abc\r\nxyz"  rather
+       than  after  CR, even though CR on its own is a valid newline. (It also
        matches at the very start of the string, of course.)


-       Note  that  the sequences \A, \Z, and \z can be used to match the start
-       and end of the subject in both modes, and if all branches of a  pattern
-       start  with \A it is always anchored, whether or not PCRE2_MULTILINE is
+       Note that the sequences \A, \Z, and \z can be used to match  the  start
+       and  end of the subject in both modes, and if all branches of a pattern
+       start with \A it is always anchored, whether or not PCRE2_MULTILINE  is
        set.



@@ -7045,73 +7049,73 @@
FULL STOP (PERIOD, DOT) AND \N

        Outside a character class, a dot in the pattern matches any one charac-
-       ter  in  the subject string except (by default) a character that signi-
+       ter in the subject string except (by default) a character  that  signi-
        fies the end of a line.


-       When a line ending is defined as a single character, dot never  matches
-       that  character; when the two-character sequence CRLF is used, dot does
-       not match CR if it is immediately followed  by  LF,  but  otherwise  it
-       matches  all characters (including isolated CRs and LFs). When any Uni-
-       code line endings are being recognized, dot does not match CR or LF  or
+       When  a line ending is defined as a single character, dot never matches
+       that character; when the two-character sequence CRLF is used, dot  does
+       not  match  CR  if  it  is immediately followed by LF, but otherwise it
+       matches all characters (including isolated CRs and LFs). When any  Uni-
+       code  line endings are being recognized, dot does not match CR or LF or
        any of the other line ending characters.


-       The  behaviour  of  dot  with regard to newlines can be changed. If the
-       PCRE2_DOTALL option is set, a dot matches any  one  character,  without
-       exception.   If  the two-character sequence CRLF is present in the sub-
+       The behaviour of dot with regard to newlines can  be  changed.  If  the
+       PCRE2_DOTALL  option  is  set, a dot matches any one character, without
+       exception.  If the two-character sequence CRLF is present in  the  sub-
        ject string, it takes two dots to match it.


-       The handling of dot is entirely independent of the handling of  circum-
-       flex  and  dollar,  the  only relationship being that they both involve
+       The  handling of dot is entirely independent of the handling of circum-
+       flex and dollar, the only relationship being  that  they  both  involve
        newlines. Dot has no special meaning in a character class.


-       The escape sequence \N when not followed by an  opening  brace  behaves
-       like  a dot, except that it is not affected by the PCRE2_DOTALL option.
-       In other words, it matches any character except one that signifies  the
+       The  escape  sequence  \N when not followed by an opening brace behaves
+       like a dot, except that it is not affected by the PCRE2_DOTALL  option.
+       In  other words, it matches any character except one that signifies the
        end of a line.


        When \N is followed by an opening brace it has a different meaning. See
-       the section entitled "Non-printing characters" above for details.  Perl
-       also  uses  \N{name}  to specify characters by Unicode name; PCRE2 does
+       the  section entitled "Non-printing characters" above for details. Perl
+       also uses \N{name} to specify characters by Unicode  name;  PCRE2  does
        not support this.



MATCHING A SINGLE CODE UNIT

-       Outside a character class, the escape sequence \C matches any one  code
-       unit,  whether or not a UTF mode is set. In the 8-bit library, one code
-       unit is one byte; in the 16-bit library it is a  16-bit  unit;  in  the
-       32-bit  library  it  is  a 32-bit unit. Unlike a dot, \C always matches
-       line-ending characters. The feature is provided in  Perl  in  order  to
+       Outside  a character class, the escape sequence \C matches any one code
+       unit, whether or not a UTF mode is set. In the 8-bit library, one  code
+       unit  is  one  byte;  in the 16-bit library it is a 16-bit unit; in the
+       32-bit library it is a 32-bit unit. Unlike a  dot,  \C  always  matches
+       line-ending  characters.  The  feature  is provided in Perl in order to
        match individual bytes in UTF-8 mode, but it is unclear how it can use-
        fully be used.


-       Because \C breaks up characters into individual  code  units,  matching
-       one  unit  with  \C  in UTF-8 or UTF-16 mode means that the rest of the
-       string may start with a malformed UTF  character.  This  has  undefined
+       Because  \C  breaks  up characters into individual code units, matching
+       one unit with \C in UTF-8 or UTF-16 mode means that  the  rest  of  the
+       string  may  start  with  a malformed UTF character. This has undefined
        results, because PCRE2 assumes that it is matching character by charac-
-       ter in a valid UTF string (by default it checks  the  subject  string's
-       validity  at  the  start  of  processing  unless the PCRE2_NO_UTF_CHECK
+       ter  in  a  valid UTF string (by default it checks the subject string's
+       validity at the  start  of  processing  unless  the  PCRE2_NO_UTF_CHECK
        option is used).


-       An  application  can  lock  out  the  use  of   \C   by   setting   the
-       PCRE2_NEVER_BACKSLASH_C  option  when  compiling  a pattern. It is also
+       An   application   can   lock   out  the  use  of  \C  by  setting  the
+       PCRE2_NEVER_BACKSLASH_C option when compiling a  pattern.  It  is  also
        possible to build PCRE2 with the use of \C permanently disabled.


-       PCRE2 does not allow \C to appear in lookbehind  assertions  (described
-       below)  in UTF-8 or UTF-16 modes, because this would make it impossible
-       to calculate the length of  the  lookbehind.  Neither  the  alternative
+       PCRE2  does  not allow \C to appear in lookbehind assertions (described
+       below) in UTF-8 or UTF-16 modes, because this would make it  impossible
+       to  calculate  the  length  of  the lookbehind. Neither the alternative
        matching function pcre2_dfa_match() nor the JIT optimizer support \C in
        these UTF modes.  The former gives a match-time error; the latter fails
        to optimize and so the match is always run using the interpreter.


-       In  the  32-bit  library,  however,  \C  is  always supported (when not
-       explicitly locked out) because it always matches a  single  code  unit,
+       In the 32-bit library,  however,  \C  is  always  supported  (when  not
+       explicitly  locked  out)  because it always matches a single code unit,
        whether or not UTF-32 is specified.


        In general, the \C escape sequence is best avoided. However, one way of
-       using it that avoids the problem of malformed UTF-8 or  UTF-16  charac-
-       ters  is  to use a lookahead to check the length of the next character,
-       as in this pattern, which could be used with  a  UTF-8  string  (ignore
+       using  it  that avoids the problem of malformed UTF-8 or UTF-16 charac-
+       ters is to use a lookahead to check the length of the  next  character,
+       as  in  this  pattern,  which could be used with a UTF-8 string (ignore
        white space and line breaks):


          (?| (?=[\x00-\x7f])(\C) |
@@ -7119,11 +7123,11 @@
              (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) |
              (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C))


-       In  this  example,  a  group  that starts with (?| resets the capturing
-       parentheses numbers in each alternative (see "Duplicate Subpattern Num-
-       bers" below). The assertions at the start of each branch check the next
-       UTF-8 character for values whose encoding uses 1, 2,  3,  or  4  bytes,
-       respectively. The character's individual bytes are then captured by the
+       In this example, a group that starts  with  (?|  resets  the  capturing
+       parentheses  numbers in each alternative (see "Duplicate Group Numbers"
+       below). The assertions at the start of each branch check the next UTF-8
+       character  for  values whose encoding uses 1, 2, 3, or 4 bytes, respec-
+       tively. The character's individual  bytes  are  then  captured  by  the
        appropriate number of \C groups.



@@ -7131,115 +7135,115 @@

        An opening square bracket introduces a character class, terminated by a
        closing square bracket. A closing square bracket on its own is not spe-
-       cial by default.  If a closing square bracket is required as  a  member
+       cial  by  default.  If a closing square bracket is required as a member
        of the class, it should be the first data character in the class (after
-       an initial circumflex, if present) or escaped with  a  backslash.  This
-       means  that,  by default, an empty class cannot be defined. However, if
-       the PCRE2_ALLOW_EMPTY_CLASS option is set, a closing square bracket  at
+       an  initial  circumflex,  if present) or escaped with a backslash. This
+       means that, by default, an empty class cannot be defined.  However,  if
+       the  PCRE2_ALLOW_EMPTY_CLASS option is set, a closing square bracket at
        the start does end the (empty) class.


-       A  character class matches a single character in the subject. A matched
+       A character class matches a single character in the subject. A  matched
        character must be in the set of characters defined by the class, unless
-       the  first  character in the class definition is a circumflex, in which
+       the first character in the class definition is a circumflex,  in  which
        case the subject character must not be in the set defined by the class.
-       If  a  circumflex is actually required as a member of the class, ensure
+       If a circumflex is actually required as a member of the  class,  ensure
        it is not the first character, or escape it with a backslash.


-       For example, the character class [aeiou] matches any lower case  vowel,
-       while  [^aeiou]  matches  any character that is not a lower case vowel.
+       For  example, the character class [aeiou] matches any lower case vowel,
+       while [^aeiou] matches any character that is not a  lower  case  vowel.
        Note that a circumflex is just a convenient notation for specifying the
-       characters  that  are in the class by enumerating those that are not. A
-       class that starts with a circumflex is not an assertion; it still  con-
-       sumes  a  character  from the subject string, and therefore it fails if
+       characters that are in the class by enumerating those that are  not.  A
+       class  that starts with a circumflex is not an assertion; it still con-
+       sumes a character from the subject string, and therefore  it  fails  if
        the current pointer is at the end of the string.


-       Characters in a class may be specified by their code points  using  \o,
-       \x,  or \N{U+hh..} in the usual way. When caseless matching is set, any
-       letters in a class represent both their upper case and lower case  ver-
-       sions,  so  for example, a caseless [aeiou] matches "A" as well as "a",
-       and a caseless [^aeiou] does not match "A", whereas a  caseful  version
+       Characters  in  a class may be specified by their code points using \o,
+       \x, or \N{U+hh..} in the usual way. When caseless matching is set,  any
+       letters  in a class represent both their upper case and lower case ver-
+       sions, so for example, a caseless [aeiou] matches "A" as well  as  "a",
+       and  a  caseless [^aeiou] does not match "A", whereas a caseful version
        would.


-       Characters  that  might  indicate  line breaks are never treated in any
-       special way  when  matching  character  classes,  whatever  line-ending
-       sequence  is  in  use,  and  whatever  setting  of the PCRE2_DOTALL and
-       PCRE2_MULTILINE options is used. A class such as  [^a]  always  matches
+       Characters that might indicate line breaks are  never  treated  in  any
+       special  way  when  matching  character  classes,  whatever line-ending
+       sequence is in use,  and  whatever  setting  of  the  PCRE2_DOTALL  and
+       PCRE2_MULTILINE  options  is  used. A class such as [^a] always matches
        one of these characters.


        The generic character type escape sequences \d, \D, \h, \H, \p, \P, \s,
-       \S, \v, \V, \w, and \W may appear in a character  class,  and  add  the
-       characters  that  they  match  to  the  class.  For example, [\dABCDEF]
-       matches any hexadecimal digit.  In  UTF  modes,  the  PCRE2_UCP  option
-       affects  the meanings of \d, \s, \w and their upper case partners, just
-       as it does when they appear outside a character class, as described  in
-       the  section  entitled  "Generic  character  types"  above.  The escape
-       sequence \b has a  different  meaning  inside  a  character  class;  it
-       matches  the  backspace character. The sequences \B, \R, and \X are not
-       special inside a character class. Like any  other  unrecognized  escape
-       sequences,  they  cause an error. The same is true for \N when not fol-
+       \S,  \v,  \V,  \w,  and \W may appear in a character class, and add the
+       characters that they  match  to  the  class.  For  example,  [\dABCDEF]
+       matches  any  hexadecimal  digit.  In  UTF  modes, the PCRE2_UCP option
+       affects the meanings of \d, \s, \w and their upper case partners,  just
+       as  it does when they appear outside a character class, as described in
+       the section  entitled  "Generic  character  types"  above.  The  escape
+       sequence  \b  has  a  different  meaning  inside  a character class; it
+       matches the backspace character. The sequences \B, \R, and \X  are  not
+       special  inside  a  character class. Like any other unrecognized escape
+       sequences, they cause an error. The same is true for \N when  not  fol-
        lowed by an opening brace.


-       The minus (hyphen) character can be used to specify a range of  charac-
-       ters  in  a  character  class.  For  example,  [d-m] matches any letter
-       between d and m, inclusive. If a  minus  character  is  required  in  a
-       class,  it  must  be  escaped  with a backslash or appear in a position
-       where it cannot be interpreted as indicating a range, typically as  the
+       The  minus (hyphen) character can be used to specify a range of charac-
+       ters in a character  class.  For  example,  [d-m]  matches  any  letter
+       between  d  and  m,  inclusive.  If  a minus character is required in a
+       class, it must be escaped with a backslash  or  appear  in  a  position
+       where  it cannot be interpreted as indicating a range, typically as the
        first or last character in the class, or immediately after a range. For
-       example, [b-d-z] matches letters in the range b to d, a hyphen  charac-
+       example,  [b-d-z] matches letters in the range b to d, a hyphen charac-
        ter, or z.


        Perl treats a hyphen as a literal if it appears before or after a POSIX
        class (see below) or before or after a character type escape such as as
-       \d  or  \H.   However,  unless  the hyphen is the last character in the
-       class, Perl outputs a warning in its warning  mode,  as  this  is  most
-       likely  a user error. As PCRE2 has no facility for warning, an error is
+       \d or \H.  However, unless the hyphen is  the  last  character  in  the
+       class,  Perl  outputs  a  warning  in its warning mode, as this is most
+       likely a user error. As PCRE2 has no facility for warning, an error  is
        given in these cases.


        It is not possible to have the literal character "]" as the end charac-
-       ter  of a range. A pattern such as [W-]46] is interpreted as a class of
-       two characters ("W" and "-") followed by a literal string "46]", so  it
-       would  match  "W46]"  or  "-46]". However, if the "]" is escaped with a
-       backslash it is interpreted as the end of range, so [W-\]46] is  inter-
-       preted  as a class containing a range followed by two other characters.
-       The octal or hexadecimal representation of "]" can also be used to  end
+       ter of a range. A pattern such as [W-]46] is interpreted as a class  of
+       two  characters ("W" and "-") followed by a literal string "46]", so it
+       would match "W46]" or "-46]". However, if the "]"  is  escaped  with  a
+       backslash  it is interpreted as the end of range, so [W-\]46] is inter-
+       preted as a class containing a range followed by two other  characters.
+       The  octal or hexadecimal representation of "]" can also be used to end
        a range.


        Ranges normally include all code points between the start and end char-
-       acters, inclusive. They can also be  used  for  code  points  specified
+       acters,  inclusive.  They  can  also  be used for code points specified
        numerically, for example [\000-\037]. Ranges can include any characters
-       that are valid for the current mode. In any  UTF  mode,  the  so-called
-       "surrogate"  characters (those whose code points lie between 0xd800 and
-       0xdfff inclusive) may not  be  specified  explicitly  by  default  (the
-       PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES  option  disables this check). How-
+       that  are  valid  for  the current mode. In any UTF mode, the so-called
+       "surrogate" characters (those whose code points lie between 0xd800  and
+       0xdfff  inclusive)  may  not  be  specified  explicitly by default (the
+       PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES option disables this  check).  How-
        ever, ranges such as [\x{d7ff}-\x{e000}], which include the surrogates,
        are always permitted.


-       There  is  a  special  case in EBCDIC environments for ranges whose end
+       There is a special case in EBCDIC environments  for  ranges  whose  end
        points are both specified as literal letters in the same case. For com-
-       patibility  with Perl, EBCDIC code points within the range that are not
-       letters are omitted. For example, [h-k] matches only  four  characters,
+       patibility with Perl, EBCDIC code points within the range that are  not
+       letters  are  omitted. For example, [h-k] matches only four characters,
        even though the codes for h and k are 0x88 and 0x92, a range of 11 code
-       points. However, if the range is specified  numerically,  for  example,
+       points.  However,  if  the range is specified numerically, for example,
        [\x88-\x92] or [h-\x92], all code points are included.


        If a range that includes letters is used when caseless matching is set,
        it matches the letters in either case. For example, [W-c] is equivalent
-       to  [][\\^_`wxyzabc],  matched  caselessly,  and  in a non-UTF mode, if
-       character tables for a French locale are in  use,  [\xc8-\xcb]  matches
+       to [][\\^_`wxyzabc], matched caselessly, and  in  a  non-UTF  mode,  if
+       character  tables  for  a French locale are in use, [\xc8-\xcb] matches
        accented E characters in both cases.


-       A  circumflex  can  conveniently  be used with the upper case character
-       types to specify a more restricted set of characters than the  matching
-       lower  case  type.  For example, the class [^\W_] matches any letter or
+       A circumflex can conveniently be used with  the  upper  case  character
+       types  to specify a more restricted set of characters than the matching
+       lower case type.  For example, the class [^\W_] matches any  letter  or
        digit, but not underscore, whereas [\w] includes underscore. A positive
        character class should be read as "something OR something OR ..." and a
        negative class as "NOT something AND NOT something AND NOT ...".


-       The only metacharacters that are recognized in  character  classes  are
-       backslash,  hyphen  (only  where  it can be interpreted as specifying a
-       range), circumflex (only at the start), opening  square  bracket  (only
-       when  it can be interpreted as introducing a POSIX class name, or for a
-       special compatibility feature - see the next  two  sections),  and  the
+       The  only  metacharacters  that are recognized in character classes are
+       backslash, hyphen (only where it can be  interpreted  as  specifying  a
+       range),  circumflex  (only  at the start), opening square bracket (only
+       when it can be interpreted as introducing a POSIX class name, or for  a
+       special  compatibility  feature  -  see the next two sections), and the
        terminating  closing  square  bracket.  However,  escaping  other  non-
        alphanumeric characters does no harm.


@@ -7247,7 +7251,7 @@
POSIX CHARACTER CLASSES

        Perl supports the POSIX notation for character classes. This uses names
-       enclosed  by [: and :] within the enclosing square brackets. PCRE2 also
+       enclosed by [: and :] within the enclosing square brackets. PCRE2  also
        supports this notation. For example,


          [01[:alpha:]%]
@@ -7270,13 +7274,13 @@
          word     "word" characters (same as \w)
          xdigit   hexadecimal digits


-       The  default  "space" characters are HT (9), LF (10), VT (11), FF (12),
-       CR (13), and space (32). If locale-specific matching is  taking  place,
-       the  list  of  space characters may be different; there may be fewer or
+       The default "space" characters are HT (9), LF (10), VT (11),  FF  (12),
+       CR  (13),  and space (32). If locale-specific matching is taking place,
+       the list of space characters may be different; there may  be  fewer  or
        more of them. "Space" and \s match the same set of characters.


-       The name "word" is a Perl extension, and "blank"  is  a  GNU  extension
-       from  Perl  5.8. Another Perl extension is negation, which is indicated
+       The  name  "word"  is  a Perl extension, and "blank" is a GNU extension
+       from Perl 5.8. Another Perl extension is negation, which  is  indicated
        by a ^ character after the colon. For example,


          [12[:^digit:]]
@@ -7287,9 +7291,9 @@


        By default, characters with values greater than 127 do not match any of
        the POSIX character classes, although this may be different for charac-
-       ters in the range 128-255 when locale-specific matching  is  happening.
-       However,  if the PCRE2_UCP option is passed to pcre2_compile(), some of
-       the classes are changed so that Unicode character properties are  used.
+       ters  in  the range 128-255 when locale-specific matching is happening.
+       However, if the PCRE2_UCP option is passed to pcre2_compile(), some  of
+       the  classes are changed so that Unicode character properties are used.
        This  is  achieved  by  replacing  certain  POSIX  classes  with  other
        sequences, as follows:


@@ -7303,10 +7307,10 @@
          [:upper:]  becomes  \p{Lu}
          [:word:]   becomes  \p{Xwd}


-       Negated versions, such as [:^alpha:] use \P instead of \p. Three  other
+       Negated  versions, such as [:^alpha:] use \P instead of \p. Three other
        POSIX classes are handled specially in UCP mode:


-       [:graph:] This  matches  characters that have glyphs that mark the page
+       [:graph:] This matches characters that have glyphs that mark  the  page
                  when printed. In Unicode property terms, it matches all char-
                  acters with the L, M, N, P, S, or Cf properties, except for:


@@ -7315,22 +7319,22 @@
                    U+2066 - U+2069  Various "isolate"s



-       [:print:] This  matches  the  same  characters  as [:graph:] plus space
-                 characters that are not controls, that  is,  characters  with
+       [:print:] This matches the same  characters  as  [:graph:]  plus  space
+                 characters  that  are  not controls, that is, characters with
                  the Zs property.


        [:punct:] This matches all characters that have the Unicode P (punctua-
-                 tion) property, plus those characters with code  points  less
+                 tion)  property,  plus those characters with code points less
                  than 256 that have the S (Symbol) property.


-       The  other  POSIX classes are unchanged, and match only characters with
+       The other POSIX classes are unchanged, and match only  characters  with
        code points less than 256.



COMPATIBILITY FEATURE FOR WORD BOUNDARIES

-       In the POSIX.2 compliant library that was included in 4.4BSD Unix,  the
-       ugly  syntax  [[:<:]]  and [[:>:]] is used for matching "start of word"
+       In  the POSIX.2 compliant library that was included in 4.4BSD Unix, the
+       ugly syntax [[:<:]] and [[:>:]] is used for matching  "start  of  word"
        and "end of word". PCRE2 treats these items as follows:


          [[:<:]]  is converted to  \b(?=\w)
@@ -7337,38 +7341,38 @@
          [[:>:]]  is converted to  \b(?<=\w)


        Only these exact character sequences are recognized. A sequence such as
-       [a[:<:]b]  provokes  error  for  an unrecognized POSIX class name. This
-       support is not compatible with Perl. It is provided to help  migrations
+       [a[:<:]b] provokes error for an unrecognized  POSIX  class  name.  This
+       support  is not compatible with Perl. It is provided to help migrations
        from other environments, and is best not used in any new patterns. Note
-       that \b matches at the start and the end of a word (see "Simple  asser-
-       tions"  above),  and in a Perl-style pattern the preceding or following
-       character normally shows which is wanted,  without  the  need  for  the
-       assertions  that  are used above in order to give exactly the POSIX be-
+       that  \b matches at the start and the end of a word (see "Simple asser-
+       tions" above), and in a Perl-style pattern the preceding  or  following
+       character  normally  shows  which  is  wanted, without the need for the
+       assertions that are used above in order to give exactly the  POSIX  be-
        haviour.



VERTICAL BAR

-       Vertical bar characters are used to separate alternative patterns.  For
+       Vertical  bar characters are used to separate alternative patterns. For
        example, the pattern


          gilbert|sullivan


-       matches  either "gilbert" or "sullivan". Any number of alternatives may
-       appear, and an empty  alternative  is  permitted  (matching  the  empty
+       matches either "gilbert" or "sullivan". Any number of alternatives  may
+       appear,  and  an  empty  alternative  is  permitted (matching the empty
        string). The matching process tries each alternative in turn, from left
-       to right, and the first one that succeeds is used. If the  alternatives
-       are  within a subpattern (defined below), "succeeds" means matching the
-       rest of the main pattern as well as the alternative in the subpattern.
+       to  right, and the first one that succeeds is used. If the alternatives
+       are within a group (defined below), "succeeds" means matching the  rest
+       of the main pattern as well as the alternative in the group.



INTERNAL OPTION SETTING

-       The settings  of  the  PCRE2_CASELESS,  PCRE2_MULTILINE,  PCRE2_DOTALL,
-       PCRE2_EXTENDED,  PCRE2_EXTENDED_MORE, and PCRE2_NO_AUTO_CAPTURE options
-       can be changed from  within  the  pattern  by  a  sequence  of  letters
-       enclosed  between "(?"  and ")". These options are Perl-compatible, and
-       are described in detail in the pcre2api documentation. The option  let-
+       The  settings  of  the  PCRE2_CASELESS,  PCRE2_MULTILINE, PCRE2_DOTALL,
+       PCRE2_EXTENDED, PCRE2_EXTENDED_MORE, and PCRE2_NO_AUTO_CAPTURE  options
+       can  be  changed  from  within  the  pattern  by  a sequence of letters
+       enclosed between "(?"  and ")". These options are Perl-compatible,  and
+       are  described in detail in the pcre2api documentation. The option let-
        ters are:


          i  for PCRE2_CASELESS
@@ -7379,50 +7383,50 @@
          xx for PCRE2_EXTENDED_MORE


        For example, (?im) sets caseless, multiline matching. It is also possi-
-       ble to unset these options by preceding the  relevant  letters  with  a
+       ble  to  unset  these  options by preceding the relevant letters with a
        hyphen, for example (?-im). The two "extended" options are not indepen-
        dent; unsetting either one cancels the effects of both of them.


-       A  combined  setting  and  unsetting  such  as  (?im-sx),  which   sets
-       PCRE2_CASELESS  and  PCRE2_MULTILINE  while  unsetting PCRE2_DOTALL and
-       PCRE2_EXTENDED, is also permitted. Only one hyphen may  appear  in  the
-       options  string.  If a letter appears both before and after the hyphen,
-       the option is unset. An empty options setting "(?)" is  allowed.  Need-
+       A   combined  setting  and  unsetting  such  as  (?im-sx),  which  sets
+       PCRE2_CASELESS and PCRE2_MULTILINE  while  unsetting  PCRE2_DOTALL  and
+       PCRE2_EXTENDED,  is  also  permitted. Only one hyphen may appear in the
+       options string. If a letter appears both before and after  the  hyphen,
+       the  option  is unset. An empty options setting "(?)" is allowed. Need-
        less to say, it has no effect.


-       If  the  first character following (? is a circumflex, it causes all of
-       the above options to be unset. Thus, (?^) is equivalent  to  (?-imnsx).
-       Letters  may  follow  the  circumflex  to  cause some options to be re-
+       If the first character following (? is a circumflex, it causes  all  of
+       the  above  options to be unset. Thus, (?^) is equivalent to (?-imnsx).
+       Letters may follow the circumflex to  cause  some  options  to  be  re-
        instated, but a hyphen may not appear.


-       The PCRE2-specific options PCRE2_DUPNAMES  and  PCRE2_UNGREEDY  can  be
-       changed  in  the  same  way as the Perl-compatible options by using the
+       The  PCRE2-specific  options  PCRE2_DUPNAMES  and PCRE2_UNGREEDY can be
+       changed in the same way as the Perl-compatible  options  by  using  the
        characters J and U respectively. However, these are not unset by (?^).


-       When one of these option changes occurs at  top  level  (that  is,  not
-       inside  subpattern parentheses), the change applies to the remainder of
-       the pattern that follows. An option change  within  a  subpattern  (see
-       below  for  a description of subpatterns) affects only that part of the
-       subpattern that follows it, so
+       When  one  of  these  option  changes occurs at top level (that is, not
+       inside group parentheses), the change applies to the remainder  of  the
+       pattern  that follows. An option change within a group (see below for a
+       description of groups) affects only that part of the group that follows
+       it, so


          (a(?i)b)c


-       matches abc and aBc and no other strings  (assuming  PCRE2_CASELESS  is
-       not  used).   By this means, options can be made to have different set-
+       matches  abc  and  aBc and no other strings (assuming PCRE2_CASELESS is
+       not used).  By this means, options can be made to have  different  set-
        tings in different parts of the pattern. Any changes made in one alter-
-       native do carry on into subsequent branches within the same subpattern.
-       For example,
+       native do carry on into subsequent branches within the same group.  For
+       example,


          (a(?i)b|c)


-       matches "ab", "aB", "c", and "C", even though  when  matching  "C"  the
-       first  branch  is  abandoned before the option setting. This is because
-       the effects of option settings happen at compile time. There  would  be
+       matches  "ab",  "aB",  "c",  and "C", even though when matching "C" the
+       first branch is abandoned before the option setting.  This  is  because
+       the  effects  of option settings happen at compile time. There would be
        some very weird behaviour otherwise.


-       As  a  convenient shorthand, if any option settings are required at the
-       start of a non-capturing subpattern (see the next section), the  option
-       letters may appear between the "?" and the ":". Thus the two patterns
+       As a convenient shorthand, if any option settings are required  at  the
+       start  of a non-capturing group (see the next section), the option let-
+       ters may appear between the "?" and the ":". Thus the two patterns


          (?i:saturday|sunday)
          (?:(?i)saturday|sunday)
@@ -7429,22 +7433,23 @@


        match exactly the same set of strings.


-       Note:  There  are  other  PCRE2-specific options that can be set by the
-       application when the compiling function is called. The pattern can con-
-       tain  special  leading  sequences  such as (*CRLF) to override what the
-       application has set or what has been defaulted. Details  are  given  in
-       the  section  entitled  "Newline  sequences"  above. There are also the
-       (*UTF) and (*UCP) leading sequences that can be used  to  set  UTF  and
-       Unicode  property  modes;  they are equivalent to setting the PCRE2_UTF
-       and PCRE2_UCP options, respectively. However, the application  can  set
-       the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP options, which lock out the use
-       of the (*UTF) and (*UCP) sequences.
+       Note: There are other PCRE2-specific options,  applying  to  the  whole
+       pattern,  which  can be set by the application when the compiling func-
+       tion is called. In addition, the pattern can  contain  special  leading
+       sequences  such  as (*CRLF) to override what the application has set or
+       what has been defaulted.  Details are given  in  the  section  entitled
+       "Newline sequences" above. There are also the (*UTF) and (*UCP) leading
+       sequences that can be used to set UTF and Unicode property modes;  they
+       are  equivalent to setting the PCRE2_UTF and PCRE2_UCP options, respec-
+       tively. However,  the  application  can  set  the  PCRE2_NEVER_UTF  and
+       PCRE2_NEVER_UCP  options,  which  lock  out  the  use of the (*UTF) and
+       (*UCP) sequences.



-SUBPATTERNS
+GROUPS

-       Subpatterns are delimited by parentheses (round brackets), which can be
-       nested.  Turning part of a pattern into a subpattern does two things:
+       Groups are delimited by parentheses  (round  brackets),  which  can  be
+       nested.  Turning part of a pattern into a group does two things:


        1. It localizes a set of alternatives. For example, the pattern


@@ -7453,16 +7458,15 @@
        matches  "cataract",  "caterpillar", or "cat". Without the parentheses,
        it would match "cataract", "erpillar" or an empty string.


-       2. It sets up the subpattern as  a  capturing  subpattern.  This  means
-       that, when the whole pattern matches, the portion of the subject string
-       that matched the subpattern is passed back to  the  caller,  separately
-       from  the portion that matched the whole pattern. (This applies only to
-       the traditional matching function; the DFA matching function  does  not
-       support capturing.)
+       2. It creates a "capture group". This means that, when the  whole  pat-
+       tern  matches, the portion of the subject string that matched the group
+       is passed back to the caller, separately from the portion that  matched
+       the  whole  pattern.   (This  applies  only to the traditional matching
+       function; the DFA matching function does not support capturing.)


        Opening parentheses are counted from left to right (starting from 1) to
-       obtain numbers for the  capturing  subpatterns.  For  example,  if  the
-       string "the red king" is matched against the pattern
+       obtain  numbers for capture groups. For example, if the string "the red
+       king" is matched against the pattern


          the ((red|white) (king|queen))


@@ -7469,22 +7473,21 @@
        the captured substrings are "red king", "red", and "king", and are num-
        bered 1, 2, and 3, respectively.


-       The fact that plain parentheses fulfil  two  functions  is  not  always
-       helpful.   There are often times when a grouping subpattern is required
-       without a capturing requirement. If an opening parenthesis is  followed
-       by  a question mark and a colon, the subpattern does not do any captur-
-       ing, and is not counted when computing the  number  of  any  subsequent
-       capturing  subpatterns. For example, if the string "the white queen" is
-       matched against the pattern
+       The  fact  that  plain  parentheses  fulfil two functions is not always
+       helpful.  There are often times when grouping is required without  cap-
+       turing.  If an opening parenthesis is followed by a question mark and a
+       colon, the group does not do any capturing, and  is  not  counted  when
+       computing  the number of any subsequent capture groups. For example, if
+       the string "the white queen" is matched against the pattern


          the ((?:red|white) (king|queen))


        the captured substrings are "white queen" and "queen", and are numbered
-       1 and 2. The maximum number of capturing subpatterns is 65535.
+       1 and 2. The maximum number of capture groups is 65535.


        As  a  convenient shorthand, if any option settings are required at the
-       start of a non-capturing subpattern,  the  option  letters  may  appear
-       between the "?" and the ":". Thus the two patterns
+       start of a non-capturing group, the option letters may  appear  between
+       the "?" and the ":". Thus the two patterns


          (?i:saturday|sunday)
          (?:(?i)saturday|sunday)
@@ -7491,17 +7494,17 @@


        match exactly the same set of strings. Because alternative branches are
        tried from left to right, and options are not reset until  the  end  of
-       the  subpattern is reached, an option setting in one branch does affect
-       subsequent branches, so the above patterns match "SUNDAY"  as  well  as
-       "Saturday".
+       the  group is reached, an option setting in one branch does affect sub-
+       sequent branches, so the above patterns match "SUNDAY" as well as "Sat-
+       urday".



-DUPLICATE SUBPATTERN NUMBERS
+DUPLICATE GROUP NUMBERS

-       Perl 5.10 introduced a feature whereby each alternative in a subpattern
-       uses the same numbers for its capturing parentheses. Such a  subpattern
-       starts  with (?| and is itself a non-capturing subpattern. For example,
-       consider this pattern:
+       Perl 5.10 introduced a feature whereby each alternative in a group uses
+       the same numbers for its capturing parentheses.  Such  a  group  starts
+       with  (?|  and  is  itself a non-capturing group. For example, consider
+       this pattern:


          (?|(Sat)ur|(Sun))day


@@ -7512,7 +7515,7 @@
        not all, of one of a number of alternatives. Inside a (?| group, paren-
        theses  are  numbered as usual, but the number is reset at the start of
        each branch. The numbers of any capturing parentheses that  follow  the
-       subpattern  start after the highest number used in any branch. The fol-
+       whole group start after the highest number used in any branch. The fol-
        lowing example is taken from the Perl documentation. The numbers under-
        neath show in which buffer the captured content will be stored.


@@ -7520,15 +7523,14 @@
          / ( a )  (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x
          # 1            2         2  3        2     3     4


-       A  backreference  to  a  numbered subpattern uses the most recent value
-       that is set for that number by any subpattern.  The  following  pattern
-       matches "abcabc" or "defdef":
+       A  backreference  to a capture group uses the most recent value that is
+       set for the group. The following pattern matches "abcabc" or "defdef":


          /(?|(abc)|(def))\1/


-       In  contrast,  a subroutine call to a numbered subpattern always refers
-       to the first one in the pattern with the given  number.  The  following
-       pattern matches "abcabc" or "defabc":
+       In contrast, a subroutine call to a capture group always refers to  the
+       first  one  in the pattern with the given number. The following pattern
+       matches "abcabc" or "defabc":


          /(?|(abc)|(def))(?1)/


@@ -7535,75 +7537,80 @@
        A relative reference such as (?-1) is no different: it is just a conve-
        nient way of computing an absolute group number.


-       If a condition test for a subpattern's having matched refers to a  non-
-       unique  number, the test is true if any of the subpatterns of that num-
-       ber have matched.
+       If a condition test for a group's having matched refers to a non-unique
+       number, the test is true if any group with that number has matched.


        An alternative approach to using this "branch reset" feature is to  use
-       duplicate named subpatterns, as described in the next section.
+       duplicate named groups, as described in the next section.



-NAMED SUBPATTERNS
+NAMED CAPTURE GROUPS

-       Identifying  capturing  parentheses  by number is simple, but it can be
-       very hard to keep track of the numbers in  complicated  patterns.  Fur-
-       thermore, if an expression is modified, the numbers may change. To help
-       with this difficulty, PCRE2 supports the naming  of  capturing  subpat-
-       terns.  This  feature  was not added to Perl until release 5.10. Python
-       had the feature earlier, and PCRE1 introduced it at release 4.0,  using
-       the Python syntax. PCRE2 supports both the Perl and the Python syntax.
+       Identifying capture groups by number is simple, but it can be very hard
+       to keep track of the numbers in complicated patterns.  Furthermore,  if
+       an  expression  is  modified, the numbers may change. To help with this
+       difficulty, PCRE2 supports the naming of capture groups.  This  feature
+       was  not  added to Perl until release 5.10. Python had the feature ear-
+       lier, and PCRE1 introduced it at release 4.0, using the Python  syntax.
+       PCRE2 supports both the Perl and the Python syntax.


-       In  PCRE2,  a  capturing  subpattern can be named in one of three ways:
+       In  PCRE2,  a  capture  group  can  be  named  in  one  of  three ways:
        (?<name>...) or (?'name'...) as in Perl, or (?P<name>...) as in Python.
-       Names  consist of up to 32 alphanumeric characters and underscores, but
-       must start with a non-digit. References to capturing  parentheses  from
-       other parts of the pattern, such as backreferences, recursion, and con-
-       ditions, can all be made by name as well as by number.
+       Names  may be up to 32 code units long. When PCRE2_UTF is not set, they
+       may contain only ASCII alphanumeric  characters  and  underscores,  but
+       must start with a non-digit. When PCRE2_UTF is set, the syntax of group
+       names is extended to allow any Unicode letter or Unicode decimal digit.
+       In other words, group names must match one of these patterns:


-       Named capturing parentheses are allocated numbers  as  well  as  names,
-       exactly  as if the names were not present. In both PCRE2 and Perl, cap-
-       turing subpatterns are primarily identified by numbers; any  names  are
-       just  aliases  for these numbers. The PCRE2 API provides function calls
-       for extracting the complete name-to-number  translation  table  from  a
-       compiled  pattern, as well as convenience functions for extracting cap-
-       tured substrings by name.
+         ^[_A-Za-z][_A-Za-z0-9]*\z   when PCRE2_UTF is not set
+         ^[_\p{L}][_\p{L}\p{Nd}]*\z  when PCRE2_UTF is set


-       Warning: When  more  than  one  subpattern  has  the  same  number,  as
-       described  in the previous section, a name given to one of them applies
-       to all of them.  Perl allows identically numbered subpatterns  to  have
-       different  names.  Consider this pattern, where there are two capturing
-       subpatterns, both numbered 1:
+       References  to  capture groups from other parts of the pattern, such as
+       backreferences, recursion, and conditions, can all be made by  name  as
+       well as by number.


+       Named capture groups are allocated numbers as well as names, exactly as
+       if the names were not present. In both PCRE2 and Perl,  capture  groups
+       are  primarily  identified  by  numbers; any names are just aliases for
+       these numbers. The PCRE2 API provides function calls for extracting the
+       complete  name-to-number  translation table from a compiled pattern, as
+       well as convenience functions for  extracting  captured  substrings  by
+       name.
+
+       Warning:  When  more  than  one  capture  group has the same number, as
+       described in the previous section, a name given to one of them  applies
+       to all of them. Perl allows identically numbered groups to have differ-
+       ent names.  Consider this pattern, where there are two capture  groups,
+       both numbered 1:
+
          (?|(?<AA>aa)|(?<BB>bb))


-       Perl allows this, with both names AA and BB  as  aliases  of  group  1.
+       Perl  allows  this,  with  both  names AA and BB as aliases of group 1.
        Thus, after a successful match, both names yield the same value (either
        "aa" or "bb").


-       In an attempt to reduce confusion, PCRE2 does not allow the same  group
+       In  an attempt to reduce confusion, PCRE2 does not allow the same group
        number to be associated with more than one name. The example above pro-
-       vokes a compile-time error. However, there is still  scope  for  confu-
+       vokes  a  compile-time  error. However, there is still scope for confu-
        sion. Consider this pattern:


          (?|(?<AA>aa)|(bb))


-       Although  the  second  subpattern number 1 is not explicitly named, the
-       name AA is still an alias for subpattern 1. Whether the pattern matches
-       "aa"  or  "bb",  a  reference  by  name  to group AA yields the matched
-       string.
+       Although the second group number 1 is not explicitly named, the name AA
+       is  still an alias for any group 1. Whether the pattern matches "aa" or
+       "bb", a reference by name to group AA yields the matched string.


        By default, a name must be unique within a pattern, except that  dupli-
-       cate  names  are  permitted  for  subpatterns with the same number, for
-       example:
+       cate names are permitted for groups with the same number, for example:


          (?|(?<AA>aa)|(?<AA>bb))


        The duplicate name constraint can be disabled by setting the PCRE2_DUP-
        NAMES option at compile time, or by the use of (?J) within the pattern.
-       Duplicate names can be useful for patterns where only one  instance  of
-       the  named parentheses can match. Suppose you want to match the name of
-       a weekday, either as a 3-letter abbreviation or as the full  name,  and
-       in  both  cases  you  want  to  extract  the abbreviation. This pattern
+       Duplicate  names  can be useful for patterns where only one instance of
+       the named capture group can match. Suppose you want to match  the  name
+       of  a  weekday,  either as a 3-letter abbreviation or as the full name,
+       and in both cases you want to extract the  abbreviation.  This  pattern
        (ignoring the line breaks) does the job:


          (?<DN>Mon|Fri|Sun)(?:day)?|
@@ -7612,33 +7619,32 @@
          (?<DN>Thu)(?:rsday)?|
          (?<DN>Sat)(?:urday)?


-       There are five capturing substrings, but only one is ever set  after  a
-       match.   The  convenience  functions  for  extracting  the data by name
-       returns the substring for the first (and in  this  example,  the  only)
-       subpattern  of  that  name  that  matched. This saves searching to find
-       which numbered subpattern it was. (An alternative way of  solving  this
-       problem is to use a "branch reset" subpattern, as described in the pre-
-       vious section.)
+       There  are five capture groups, but only one is ever set after a match.
+       The convenience functions for extracting the data by name  returns  the
+       substring  for  the first (and in this example, the only) group of that
+       name that matched. This saves searching to find which numbered group it
+       was.  (An  alternative  way of solving this problem is to use a "branch
+       reset" group, as described in the previous section.)


-       If you make a backreference to a non-unique named subpattern from else-
-       where  in  the  pattern,  the  subpatterns to which the name refers are
-       checked in the order in which they appear in the overall  pattern.  The
-       first one that is set is used for the reference. For example, this pat-
-       tern matches both "foofoo" and "barbar" but not "foobar" or "barfoo":
+       If you make a backreference to a non-unique named group from  elsewhere
+       in  the pattern, the groups to which the name refers are checked in the
+       order in which they appear in the overall pattern. The first  one  that
+       is  set  is  used  for the reference. For example, this pattern matches
+       both "foofoo" and "barbar" but not "foobar" or "barfoo":


          (?:(?<n>foo)|(?<n>bar))\k<n>



-       If you make a subroutine call to a non-unique named subpattern, the one
-       that  corresponds  to  the first occurrence of the name is used. In the
-       absence of duplicate numbers this is the one with the lowest number.
+       If you make a subroutine call to a non-unique named group, the one that
+       corresponds to the first occurrence of the name is used. In the absence
+       of duplicate numbers this is the one with the lowest number.


        If you use a named reference in a condition test (see the section about
-       conditions below), either to check whether a subpattern has matched, or
-       to check for recursion, all subpatterns with the same name are  tested.
-       If  the condition is true for any one of them, the overall condition is
+       conditions below), either to check whether a capture group has matched,
+       or to check for recursion, all groups with the same name are tested. If
+       the  condition  is  true  for any one of them, the overall condition is
        true. This is the same behaviour as  testing  by  number.  For  further
-       details  of  the  interfaces  for  handling  named subpatterns, see the
+       details  of  the  interfaces for handling named capture groups, see the
        pcre2api documentation.



@@ -7650,18 +7656,18 @@
          a literal data character
          the dot metacharacter
          the \C escape sequence
+         the \R escape sequence
          the \X escape sequence
-         the \R escape sequence
          an escape such as \d or \pL that matches a single character
          a character class
          a backreference
-         a parenthesized subpattern (including most assertions)
-         a subroutine call to a subpattern (recursive or otherwise)
+         a parenthesized group (including most assertions)
+         a subroutine call (recursive or otherwise)


        The  general repetition quantifier specifies a minimum and maximum num-
        ber of permitted matches, by giving the two numbers in  curly  brackets
        (braces),  separated  by  a comma. The numbers must be less than 65536,
-       and the first must be less than or equal to the second. For example:
+       and the first must be less than or equal to the second. For example,


          z{2,4}


@@ -7691,12 +7697,13 @@

        The quantifier {0} is permitted, causing the expression to behave as if
        the previous item and the quantifier were not present. This may be use-
-       ful for subpatterns that are referenced as subroutines  from  elsewhere
-       in the pattern (but see also the section entitled "Defining subpatterns
-       for use by reference only" below). Items other  than  subpatterns  that
-       have a {0} quantifier are omitted from the compiled pattern.
+       ful for capture groups that are referenced as  subroutines  from  else-
+       where  in the pattern (but see also the section entitled "Defining cap-
+       ture groups for use by reference only" below). Except for parenthesized
+       groups,  items that have a {0} quantifier are omitted from the compiled
+       pattern.


-       For  convenience, the three most common quantifiers have single-charac-
+       For convenience, the three most common quantifiers have  single-charac-
        ter abbreviations:


          *    is equivalent to {0,}
@@ -7703,22 +7710,21 @@
          +    is equivalent to {1,}
          ?    is equivalent to {0,1}


-       It is possible to construct infinite loops by  following  a  subpattern
-       that can match no characters with a quantifier that has no upper limit,
-       for example:
+       It  is  possible  to construct infinite loops by following a group that
+       can match no characters with a quantifier that has no upper limit,  for
+       example:


          (a?)*


-       Earlier versions of Perl and PCRE1 used to give  an  error  at  compile
+       Earlier  versions  of  Perl  and PCRE1 used to give an error at compile
        time for such patterns. However, because there are cases where this can
        be useful, such patterns are now accepted, but if any repetition of the
-       subpattern  does in fact match no characters, the loop is forcibly bro-
-       ken.
+       group does in fact match no characters, the loop is forcibly broken.


-       By default, the quantifiers are "greedy", that is, they match  as  much
-       as  possible  (up  to  the  maximum number of permitted times), without
-       causing the rest of the pattern to fail. The classic example  of  where
-       this gives problems is in trying to match comments in C programs. These
+       By default, quantifiers are "greedy", that is, they match  as  much  as
+       possible (up to the maximum number of permitted times), without causing
+       the rest of the pattern to fail. The  classic  example  of  where  this
+       gives  problems  is  in  trying  to match comments in C programs. These
        appear between /* and */ and within the comment,  individual  *  and  /
        characters  may  appear. An attempt to match C comments by applying the
        pattern
@@ -7730,12 +7736,10 @@
          /* first comment */  not comment  /* second comment */


        fails, because it matches the entire string owing to the greediness  of
-       the .*  item.
+       the  .*  item. However, if a quantifier is followed by a question mark,
+       it ceases to be greedy, and instead matches the minimum number of times
+       possible, so the pattern


-       If a quantifier is followed by a question mark, it ceases to be greedy,
-       and instead matches the minimum number of times possible, so  the  pat-
-       tern
-
          /\*.*?\*/


        does  the  right  thing with the C comments. The meaning of the various
@@ -7754,8 +7758,8 @@
        can be made greedy by following them with a  question  mark.  In  other
        words, it inverts the default behaviour.


-       When  a  parenthesized  subpattern  is quantified with a minimum repeat
-       count that is greater than 1 or with a limited maximum, more memory  is
+       When  a  parenthesized  group is quantified with a minimum repeat count
+       that is greater than 1 or  with  a  limited  maximum,  more  memory  is
        required  for  the  compiled  pattern, in proportion to the size of the
        minimum or maximum.


@@ -7791,15 +7795,15 @@
        trol  verbs  (*PRUNE)  and  (*SKIP) also disable this optimization, and
        there is an option, PCRE2_NO_DOTSTAR_ANCHOR, to do so explicitly.


-       When a capturing subpattern is repeated, the value captured is the sub-
-       string that matched the final iteration. For example, after
+       When a capture group is repeated, the value captured is  the  substring
+       that matched the final iteration. For example, after


          (tweedle[dume]{3}\s*)+


        has matched "tweedledum tweedledee" the value of the captured substring
-       is "tweedledee". However, if there are  nested  capturing  subpatterns,
-       the  corresponding captured values may have been set in previous itera-
-       tions. For example, after
+       is "tweedledee". However, if there are nested capture groups, the  cor-
+       responding  captured  values  may have been set in previous iterations.
+       For example, after


          (a|(b))+


@@ -7825,8 +7829,8 @@
        action of the matcher is to try again with only 5 digits  matching  the
        \d+  item,  and  then  with  4,  and  so on, before ultimately failing.
        "Atomic grouping" (a term taken from Jeffrey  Friedl's  book)  provides
-       the  means for specifying that once a subpattern has matched, it is not
-       to be re-evaluated in this way.
+       the means for specifying that once a group has matched, it is not to be
+       re-evaluated in this way.


        If we use atomic grouping for the previous example, the  matcher  gives
        up  immediately  on failing to match "foo" the first time. The notation
@@ -7839,28 +7843,27 @@


          (*atomic:\d+)foo


-       This  kind  of  parenthesis "locks up" the  part of the pattern it con-
-       tains once it has matched, and a failure further into  the  pattern  is
+       This kind of parenthesized group "locks up" the  part of the pattern it
+       contains once it has matched, and a failure further into the pattern is
        prevented  from  backtracking into it. Backtracking past it to previous
        items, however, works as normal.


-       An alternative description is that a subpattern of  this  type  matches
-       exactly  the  string of characters that an identical standalone pattern
-       would match, if anchored at the current point in the subject string.
+       An alternative description is that a group of this type matches exactly
+       the  string  of  characters  that an identical standalone pattern would
+       match, if anchored at the current point in the subject string.


-       Atomic grouping subpatterns are not capturing subpatterns. Simple cases
-       such as the above example can be thought of as a maximizing repeat that
-       must swallow everything it can. So, while both \d+ and  \d+?  are  pre-
-       pared  to  adjust  the number of digits they match in order to make the
-       rest of the pattern match, (?>\d+) can only match an entire sequence of
-       digits.
+       Atomic groups are not capture groups. Simple cases such  as  the  above
+       example  can  be  thought  of  as a maximizing repeat that must swallow
+       everything it can.  So, while both \d+ and \d+? are prepared to  adjust
+       the  number  of digits they match in order to make the rest of the pat-
+       tern match, (?>\d+) can only match an entire sequence of digits.


-       Atomic  groups in general can of course contain arbitrarily complicated
-       subpatterns, and can be nested. However, when  the  subpattern  for  an
-       atomic group is just a single repeated item, as in the example above, a
-       simpler notation, called a "possessive quantifier" can  be  used.  This
-       consists  of  an  additional  + character following a quantifier. Using
-       this notation, the previous example can be rewritten as
+       Atomic groups in general can of course contain arbitrarily  complicated
+       expressions, and can be nested. However, when the contents of an atomic
+       group is just a single repeated item, as in the example above,  a  sim-
+       pler  notation, called a "possessive quantifier" can be used. This con-
+       sists of an additional + character following a quantifier.  Using  this
+       notation, the previous example can be rewritten as


          \d++foo


@@ -7869,46 +7872,46 @@

          (abc|xyz){2,3}+


-       Possessive   quantifiers   are   always  greedy;  the  setting  of  the
-       PCRE2_UNGREEDY option is ignored. They are a  convenient  notation  for
-       the  simpler  forms of atomic group. However, there is no difference in
+       Possessive  quantifiers  are  always  greedy;  the   setting   of   the
+       PCRE2_UNGREEDY  option  is  ignored. They are a convenient notation for
+       the simpler forms of atomic group. However, there is no  difference  in
        the meaning of a possessive quantifier and the equivalent atomic group,
-       though  there  may  be a performance difference; possessive quantifiers
+       though there may be a performance  difference;  possessive  quantifiers
        should be slightly faster.


-       The possessive quantifier syntax is an extension to the Perl  5.8  syn-
-       tax.   Jeffrey  Friedl  originated the idea (and the name) in the first
+       The  possessive  quantifier syntax is an extension to the Perl 5.8 syn-
+       tax.  Jeffrey Friedl originated the idea (and the name)  in  the  first
        edition of his book. Mike McCloskey liked it, so implemented it when he
-       built Sun's Java package, and PCRE1 copied it from there. It ultimately
-       found its way into Perl at release 5.10.
+       built Sun's Java package, and PCRE1 copied it from there. It found  its
+       way into Perl at release 5.10.


-       PCRE2 has an optimization  that  automatically  "possessifies"  certain
-       simple  pattern constructs. For example, the sequence A+B is treated as
-       A++B because there is no point in backtracking into a sequence  of  A's
+       PCRE2  has  an  optimization  that automatically "possessifies" certain
+       simple pattern constructs. For example, the sequence A+B is treated  as
+       A++B  because  there is no point in backtracking into a sequence of A's
        when B must follow.  This feature can be disabled by the PCRE2_NO_AUTO-
        POSSESS option, or starting the pattern with (*NO_AUTO_POSSESS).


-       When a pattern contains an unlimited repeat inside  a  subpattern  that
-       can  itself  be  repeated  an  unlimited number of times, the use of an
-       atomic group is the only way to avoid some  failing  matches  taking  a
-       very long time indeed. The pattern
+       When  a  pattern  contains  an unlimited repeat inside a group that can
+       itself be repeated an unlimited number of times, the use of  an  atomic
+       group  is the only way to avoid some failing matches taking a very long
+       time indeed. The pattern


          (\D+|<\d+>)*[!?]


-       matches  an  unlimited number of substrings that either consist of non-
-       digits, or digits enclosed in <>, followed by either ! or  ?.  When  it
+       matches an unlimited number of substrings that either consist  of  non-
+       digits,  or  digits  enclosed in <>, followed by either ! or ?. When it
        matches, it runs quickly. However, if it is applied to


          aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa


-       it  takes  a  long  time  before reporting failure. This is because the
-       string can be divided between the internal \D+ repeat and the  external
-       *  repeat  in  a  large  number of ways, and all have to be tried. (The
-       example uses [!?] rather than a single character at  the  end,  because
-       both  PCRE2  and Perl have an optimization that allows for fast failure
-       when a single character is used. They remember the last single  charac-
-       ter  that  is required for a match, and fail early if it is not present
-       in the string.) If the pattern is changed so that  it  uses  an  atomic
+       it takes a long time before reporting  failure.  This  is  because  the
+       string  can be divided between the internal \D+ repeat and the external
+       * repeat in a large number of ways, and all  have  to  be  tried.  (The
+       example  uses  [!?]  rather than a single character at the end, because
+       both PCRE2 and Perl have an optimization that allows for  fast  failure
+       when  a single character is used. They remember the last single charac-
+       ter that is required for a match, and fail early if it is  not  present
+       in  the  string.)  If  the pattern is changed so that it uses an atomic
        group, like this:


          ((?>\D+)|<\d+>)*[!?]
@@ -7919,26 +7922,25 @@
 BACKREFERENCES


        Outside a character class, a backslash followed by a digit greater than
-       0 (and possibly further digits) is a backreference to a capturing  sub-
-       pattern  earlier  (that is, to its left) in the pattern, provided there
-       have been that many previous capturing left parentheses.
+       0  (and  possibly further digits) is a backreference to a capture group
+       earlier (that is, to its left) in the pattern, provided there have been
+       that many previous capture groups.


-       However, if the decimal number following the backslash is less than  8,
-       it  is  always  taken  as  a backreference, and causes an error only if
-       there are not that many capturing left parentheses in the  entire  pat-
-       tern.  In  other words, the parentheses that are referenced need not be
-       to the left of the reference for numbers less than 8. A "forward  back-
-       reference"  of  this  type can make sense when a repetition is involved
-       and the subpattern to the right has participated in an  earlier  itera-
-       tion.
+       However,  if the decimal number following the backslash is less than 8,
+       it is always taken as a backreference, and  causes  an  error  only  if
+       there  are not that many capture groups in the entire pattern. In other
+       words, the group that is referenced need not be to the left of the ref-
+       erence  for numbers less than 8. A "forward backreference" of this type
+       can make sense when a repetition is involved and the group to the right
+       has participated in an earlier iteration.


        It  is  not  possible  to have a numerical "forward backreference" to a
-       subpattern whose number is 8  or  more  using  this  syntax  because  a
-       sequence  such  as  \50 is interpreted as a character defined in octal.
-       See the subsection entitled "Non-printing characters" above for further
-       details  of  the  handling of digits following a backslash. There is no
-       such problem when named parentheses are used. A  backreference  to  any
-       subpattern is possible using named parentheses (see below).
+       group whose number is 8 or more using this syntax  because  a  sequence
+       such  as  \50  is  interpreted as a character defined in octal. See the
+       subsection entitled "Non-printing characters" above for further details
+       of  the  handling of digits following a backslash. Other forms of back-
+       referencing do not suffer from this restriction. In  particular,  there
+       is no problem when named capture groups are used (see below).


        Another  way  of  avoiding  the ambiguity inherent in the use of digits
        following a backslash is to use the \g  escape  sequence.  This  escape
@@ -7956,21 +7958,21 @@


          (abc(def)ghi)\g{-1}


-       The sequence \g{-1} is a reference to the most recently started captur-
-       ing subpattern before \g, that is, is it equivalent to \2 in this exam-
-       ple.   Similarly, \g{-2} would be equivalent to \1. The use of relative
-       references can be helpful in long patterns, and also in  patterns  that
-       are  created  by  joining  together  fragments  that contain references
-       within themselves.
+       The sequence \g{-1} is a reference to the most recently started capture
+       group before \g, that is, is it equivalent to \2 in this example. Simi-
+       larly, \g{-2} would be equivalent to \1. The use of relative references
+       can be helpful in long patterns, and also in patterns that are  created
+       by  joining  together  fragments  that  contain references within them-
+       selves.


-       The sequence \g{+1} is a reference to the  next  capturing  subpattern.
-       This  kind  of forward reference can be useful it patterns that repeat.
-       Perl does not support the use of + in this way.
+       The sequence \g{+1} is a reference to the next capture group. This kind
+       of  forward  reference can be useful in patterns that repeat. Perl does
+       not support the use of + in this way.


-       A backreference matches whatever actually matched the capturing subpat-
-       tern  in  the current subject string, rather than anything matching the
-       subpattern itself (see "Subpatterns as subroutines" below for a way  of
-       doing that). So the pattern
+       A backreference matches whatever actually  most  recently  matched  the
+       capture  group  in  the current subject string, rather than anything at
+       all that matches the group (see "Groups as subroutines" below for a way
+       of doing that). So the pattern


          (sens|respons)e and \1ibility


@@ -7982,14 +7984,14 @@
          ((?i)rah)\s+\1


        matches "rah rah" and "RAH RAH", but not "RAH  rah",  even  though  the
-       original capturing subpattern is matched caselessly.
+       original capture group is matched caselessly.


        There  are  several  different  ways of writing backreferences to named
-       subpatterns. The .NET syntax \k{name} and the Perl syntax  \k<name>  or
-       \k'name'  are supported, as is the Python syntax (?P=name). Perl 5.10's
-       unified backreference syntax, in which \g can be used for both  numeric
-       and  named  references,  is  also supported. We could rewrite the above
-       example in any of the following ways:
+       capture groups. The .NET syntax \k{name} and the Perl  syntax  \k<name>
+       or  \k'name'  are  supported,  as  is the Python syntax (?P=name). Perl
+       5.10's unified backreference syntax, in which \g can be used  for  both
+       numeric  and  named references, is also supported. We could rewrite the
+       above example in any of the following ways:


          (?<p1>(?i)rah)\s+\k<p1>
          (?'p1'(?i)rah)\s+\k{p1}
@@ -7996,12 +7998,12 @@
          (?P<p1>(?i)rah)\s+(?P=p1)
          (?<p1>(?i)rah)\s+\g{p1}


-       A subpattern that is referenced by  name  may  appear  in  the  pattern
+       A capture group that is referenced by name may appear  in  the  pattern
        before or after the reference.


-       There  may  be more than one backreference to the same subpattern. If a
-       subpattern has not actually been used in a particular match, any  back-
-       references to it always fail by default. For example, the pattern
+       There  may be more than one backreference to the same group. If a group
+       has not actually been used in a particular match, backreferences to  it
+       always fail by default. For example, the pattern


          (a|(bc))\2


@@ -8009,90 +8011,88 @@
        the PCRE2_MATCH_UNSET_BACKREF option is set at compile time, a backref-
        erence to an unset value matches an empty string.


-       Because  there may be many capturing parentheses in a pattern, all dig-
-       its following a backslash are taken as part of a  potential  backrefer-
-       ence  number.   If  the  pattern continues with a digit character, some
-       delimiter  must  be  used  to  terminate  the  backreference.  If   the
-       PCRE2_EXTENDED  or PCRE2_EXTENDED_MORE option is set, this can be white
-       space. Otherwise, the \g{ syntax or an empty  comment  (see  "Comments"
-       below) can be used.
+       Because  there may be many capture groups in a pattern, all digits fol-
+       lowing a backslash are taken as part of a potential backreference  num-
+       ber.  If  the  pattern continues with a digit character, some delimiter
+       must be used to terminate the backreference. If the  PCRE2_EXTENDED  or
+       PCRE2_EXTENDED_MORE  option is set, this can be white space. Otherwise,
+       the \g{} syntax or an empty comment (see "Comments" below) can be used.


    Recursive backreferences


-       A  backreference  that occurs inside the parentheses to which it refers
-       fails when the subpattern is first used, so, for example,  (a\1)  never
-       matches.   However,  such references can be useful inside repeated sub-
-       patterns. For example, the pattern
+       A backreference that occurs inside the group to which it  refers  fails
+       when  the  group  is  first used, so, for example, (a\1) never matches.
+       However, such references can be  useful  inside  repeated  groups.  For
+       example, the pattern


          (a|b\1)+


        matches any number of "a"s and also "aba", "ababbaa" etc. At each iter-
-       ation of the subpattern, the backreference matches the character string
-       corresponding to the previous iteration. In order for this to work, the
-       pattern  must  be  such that the first iteration does not need to match
-       the backreference. This can be done using alternation, as in the  exam-
+       ation of the group, the backreference matches the character string cor-
+       responding  to  the  previous iteration. In order for this to work, the
+       pattern must be such that the first iteration does not  need  to  match
+       the  backreference. This can be done using alternation, as in the exam-
        ple above, or by a quantifier with a minimum of zero.


-       Backreferences  of  this type cause the group that they reference to be
-       treated as an atomic group.  Once the whole group has been  matched,  a
-       subsequent  matching  failure cannot cause backtracking into the middle
+       Backreferences of this type cause the group that they reference  to  be
+       treated  as  an atomic group.  Once the whole group has been matched, a
+       subsequent matching failure cannot cause backtracking into  the  middle
        of the group.



ASSERTIONS

-       An assertion is a test on the characters  following  or  preceding  the
+       An  assertion  is  a  test on the characters following or preceding the
        current matching point that does not consume any characters. The simple
-       assertions coded as \b, \B, \A, \G, \Z,  \z,  ^  and  $  are  described
+       assertions  coded  as  \b,  \B,  \A,  \G, \Z, \z, ^ and $ are described
        above.


-       More  complicated  assertions  are  coded as subpatterns. There are two
-       kinds: those that look ahead of the current  position  in  the  subject
-       string,  and  those  that look behind it, and in each case an assertion
-       may be positive (must match for the assertion to be true)  or  negative
-       (must  not match for the assertion to be true). An assertion subpattern
-       is matched in the normal way, and if it  is  true,  matching  continues
-       after  it,  but with the matching position in the subject string is was
-       it was before the assertion was processed.
+       More complicated assertions are coded as  parenthesized  groups.  There
+       are  two  kinds:  those  that look ahead of the current position in the
+       subject string, and those that look behind it,  and  in  each  case  an
+       assertion  may be positive (must match for the assertion to be true) or
+       negative (must not match for the assertion to be  true).  An  assertion
+       group is matched in the normal way, and if it is true, matching contin-
+       ues after it, but with the matching position in the subject  string  is
+       was it was before the assertion was processed.


-       A lookaround assertion may also appear as the  condition  in  a  condi-
-       tional subpattern (see below). In this case, the result of matching the
+       A  lookaround  assertion  may  also appear as the condition in a condi-
+       tional group (see below). In this case,  the  result  of  matching  the
        assertion determines which branch of the condition is followed.


-       Assertion subpatterns are not capturing subpatterns.  If  an  assertion
-       contains  capturing  subpatterns  within  it, these are counted for the
-       purposes of numbering the capturing subpatterns in the  whole  pattern.
-       Within  each branch of an assertion, locally captured substrings may be
-       referenced in the usual way.  For example, a sequence such as (.)\g{-1}
-       can be used to check that two adjacent characters are the same.
+       Assertion  groups are not capture groups. If an assertion contains cap-
+       ture groups within it, these are counted for the purposes of  numbering
+       the  capture  groups  in  the  whole  pattern. Within each branch of an
+       assertion, locally captured substrings may be referenced in  the  usual
+       way.  For  example,  a  sequence such as (.)\g{-1} can be used to check
+       that two adjacent characters are the same.


-       When  a  branch within an assertion fails to match, any substrings that
-       were captured are discarded (as happens with any  pattern  branch  that
-       fails  to  match).  A  negative  assertion  is  true  only when all its
+       When a branch within an assertion fails to match, any  substrings  that
+       were  captured  are  discarded (as happens with any pattern branch that
+       fails to match). A  negative  assertion  is  true  only  when  all  its
        branches fail to match; this means that no captured substrings are ever
-       retained  after a successful negative assertion. When an assertion con-
+       retained after a successful negative assertion. When an assertion  con-
        tains a matching branch, what happens depends on the type of assertion.


-       For a positive assertion, internally captured substrings  in  the  suc-
-       cessful  branch are retained, and matching continues with the next pat-
-       tern item after the assertion. For a  negative  assertion,  a  matching
-       branch  means  that  the assertion is not true. If such an assertion is
-       being used as a condition in a conditional subpattern (see below), cap-
-       tured substrings are retained, because matching continues with the "no"
+       For  a  positive  assertion, internally captured substrings in the suc-
+       cessful branch are retained, and matching continues with the next  pat-
+       tern  item  after  the  assertion. For a negative assertion, a matching
+       branch means that the assertion is not true. If such  an  assertion  is
+       being  used as a condition in a conditional group (see below), captured
+       substrings are retained,  because  matching  continues  with  the  "no"
        branch of the condition. For other failing negative assertions, control
        passes to the previous backtracking point, thus discarding any captured
        strings within the assertion.


-       For  compatibility  with  Perl,  most  assertion  subpatterns  may   be
-       repeated;  though  it  makes  no sense to assert the same thing several
-       times, the side effect of capturing  parentheses  may  occasionally  be
-       useful.  However,  an  assertion  that forms the condition for a condi-
-       tional subpattern may not be quantified. In practice, for other  asser-
-       tions, there only three cases:
+       For  compatibility  with  Perl,  most assertion groups may be repeated;
+       though it makes no sense to assert the same thing  several  times,  the
+       side effect of capturing may occasionally be useful. However, an asser-
+       tion that forms the condition for a conditional group may not be  quan-
+       tified. In practice, for other assertions, there only three cases:


        (1)  If  the  quantifier  is  {0}, the assertion is never obeyed during
-       matching.  However, it may  contain  internal  capturing  parenthesized
-       groups that are called from elsewhere via the subroutine mechanism.
+       matching.  However, it may contain internal  capture  groups  that  are
+       called from elsewhere via the subroutine mechanism.


        (2)  If quantifier is {0,n} where n is greater than zero, it is treated
        as if it were {0,1}. At run time, the rest  of  the  pattern  match  is
@@ -8116,9 +8116,9 @@
          (*positive_lookbehind: or (*plb: is the same as (?<=
          (*negative_lookbehind: or (*nlb: is the same as (?<!


-       For example, (*pla:foo) is the same assertion as (?=foo).  However,  in
-       the  following sections, the various assertions are described using the
-       original symbolic forms.
+       For example, (*pla:foo) is the same assertion as (?=foo). In  the  fol-
+       lowing  sections, the various assertions are described using the origi-
+       nal symbolic forms.


    Lookahead assertions


@@ -8195,16 +8195,16 @@
        bers of code units, are never permitted in lookbehinds.


        "Subroutine" calls (see below) such as (?2) or (?&X) are  permitted  in
-       lookbehinds,  as  long as the subpattern matches a fixed-length string.
-       However, recursion, that is, a "subroutine" call into a group  that  is
-       already active, is not supported.
+       lookbehinds, as long as the called capture group matches a fixed-length
+       string. However, recursion, that is, a "subroutine" call into  a  group
+       that is already active, is not supported.


        Perl does not support backreferences in lookbehinds. PCRE2 does support
        them,   but   only    if    certain    conditions    are    met.    The
        PCRE2_MATCH_UNSET_BACKREF  option must not be set, there must be no use
-       of (?| in the pattern (it creates duplicate subpattern numbers), and if
-       the  backreference  is by name, the name must be unique. Of course, the
-       referenced subpattern must itself be of  fixed  length.  The  following
+       of (?| in the pattern (it creates duplicate group numbers), and if  the
+       backreference  is by name, the name must be unique. Of course, the ref-
+       erenced group must itself match a fixed length substring. The following
        pattern matches words containing at least two characters that begin and
        end with the same character:


@@ -8323,141 +8323,139 @@
        nism as capturing parentheses.


        Warning: The (*ACCEPT) control verb (see  below)  should  not  be  used
-       within  a  script  run  subpattern, because it causes an immediate exit
-       from the subpattern, bypassing the script run checking.
+       within a script run group, because it causes an immediate exit from the
+       group, bypassing the script run checking.



-CONDITIONAL SUBPATTERNS
+CONDITIONAL GROUPS

-       It is possible to cause the matching process to obey a subpattern  con-
-       ditionally  or to choose between two alternative subpatterns, depending
-       on the result of an assertion, or whether a specific capturing  subpat-
-       tern  has  already  been matched. The two possible forms of conditional
-       subpattern are:
+       It is possible to cause the matching process to obey a pattern fragment
+       conditionally or to choose between two alternative fragments, depending
+       on the result of an assertion, or whether a specific capture group  has
+       already been matched. The two possible forms of conditional group are:


          (?(condition)yes-pattern)
          (?(condition)yes-pattern|no-pattern)


-       If the condition is satisfied, the yes-pattern is used;  otherwise  the
-       no-pattern  (if present) is used. An absent no-pattern is equivalent to
-       an empty string (it always matches). If there are more than two  alter-
-       natives in the subpattern, a compile-time error occurs. Each of the two
-       alternatives may itself contain nested subpatterns of any form, includ-
-       ing  conditional  subpatterns;  the  restriction  to  two  alternatives
-       applies only at the level of the condition. This pattern fragment is an
-       example where the alternatives are complex:
+       If  the  condition is satisfied, the yes-pattern is used; otherwise the
+       no-pattern (if present) is used. An absent no-pattern is equivalent  to
+       an  empty string (it always matches). If there are more than two alter-
+       natives in the group, a compile-time error  occurs.  Each  of  the  two
+       alternatives  may  itself  contain nested groups of any form, including
+       conditional groups; the restriction to two alternatives applies only at
+       the  level of the condition itself. This pattern fragment is an example
+       where the alternatives are complex:


          (?(1) (A|B|C) | (D | (?(2)E|F) | E) )



-       There  are  five  kinds of condition: references to subpatterns, refer-
-       ences to recursion, two pseudo-conditions called  DEFINE  and  VERSION,
+       There are five kinds of condition: references to capture groups, refer-
+       ences  to  recursion,  two pseudo-conditions called DEFINE and VERSION,
        and assertions.


- Checking for a used subpattern by number
+ Checking for a used capture group by number

-       If  the  text between the parentheses consists of a sequence of digits,
-       the condition is true if a capturing subpattern of that number has pre-
-       viously  matched.  If  there is more than one capturing subpattern with
-       the same number (see the earlier  section  about  duplicate  subpattern
-       numbers),  the condition is true if any of them have matched. An alter-
-       native notation is to precede the digits with a plus or minus sign.  In
-       this  case, the subpattern number is relative rather than absolute. The
-       most recently opened parentheses can be referenced by (?(-1), the  next
-       most  recent  by (?(-2), and so on. Inside loops it can also make sense
-       to refer to subsequent groups. The next parentheses to be opened can be
-       referenced  as (?(+1), and so on. (The value zero in any of these forms
-       is not used; it provokes a compile-time error.)
+       If the text between the parentheses consists of a sequence  of  digits,
+       the  condition is true if a capture group of that number has previously
+       matched. If there is more than one capture group with the  same  number
+       (see  the earlier section about duplicate group numbers), the condition
+       is true if any of them have matched. An alternative notation is to pre-
+       cede the digits with a plus or minus sign. In this case, the group num-
+       ber is relative rather than absolute. The most recently opened  capture
+       group  can be referenced by (?(-1), the next most recent by (?(-2), and
+       so on. Inside loops it can also  make  sense  to  refer  to  subsequent
+       groups.  The next capture group can be referenced as (?(+1), and so on.
+       (The value zero in any of these forms is not used; it provokes  a  com-
+       pile-time error.)


-       Consider the following pattern, which  contains  non-significant  white
-       space  to  make it more readable (assume the PCRE2_EXTENDED option) and
+       Consider  the  following  pattern, which contains non-significant white
+       space to make it more readable (assume the PCRE2_EXTENDED  option)  and
        to divide it into three parts for ease of discussion:


          ( \( )?    [^()]+    (?(1) \) )


-       The first part matches an optional opening  parenthesis,  and  if  that
+       The  first  part  matches  an optional opening parenthesis, and if that
        character is present, sets it as the first captured substring. The sec-
-       ond part matches one or more characters that are not  parentheses.  The
-       third  part  is  a conditional subpattern that tests whether or not the
-       first set of parentheses matched. If they  did,  that  is,  if  subject
-       started  with an opening parenthesis, the condition is true, and so the
-       yes-pattern is executed and a closing parenthesis is  required.  Other-
-       wise,  since no-pattern is not present, the subpattern matches nothing.
-       In other words, this pattern matches  a  sequence  of  non-parentheses,
-       optionally enclosed in parentheses.
+       ond  part  matches one or more characters that are not parentheses. The
+       third part is a conditional group that tests whether or not  the  first
+       capture  group  matched. If it did, that is, if subject started with an
+       opening parenthesis, the condition is true, and so the  yes-pattern  is
+       executed  and  a  closing parenthesis is required. Otherwise, since no-
+       pattern is not present, the conditional group matches nothing. In other
+       words,  this  pattern matches a sequence of non-parentheses, optionally
+       enclosed in parentheses.


-       If  you  were  embedding  this pattern in a larger one, you could use a
+       If you were embedding this pattern in a larger one,  you  could  use  a
        relative reference:


          ...other stuff... ( \( )?    [^()]+    (?(-1) \) ) ...


-       This makes the fragment independent of the parentheses  in  the  larger
+       This  makes  the  fragment independent of the parentheses in the larger
        pattern.


- Checking for a used subpattern by name
+ Checking for a used capture group by name

-       Perl  uses  the  syntax  (?(<name>)...) or (?('name')...) to test for a
-       used subpattern by name. For compatibility  with  earlier  versions  of
-       PCRE1,  which had this facility before Perl, the syntax (?(name)...) is
-       also recognized. Note, however, that undelimited  names  consisting  of
-       the  letter  R followed by digits are ambiguous (see the following sec-
-       tion).
+       Perl uses the syntax (?(<name>)...) or (?('name')...)  to  test  for  a
+       used  capture group by name. For compatibility with earlier versions of
+       PCRE1, which had this facility before Perl, the syntax (?(name)...)  is
+       also  recognized.   Note, however, that undelimited names consisting of
+       the letter R followed by digits are ambiguous (see the  following  sec-
+       tion). Rewriting the above example to use a named group gives this:


-       Rewriting the above example to use a named subpattern gives this:
-
          (?<OPEN> \( )?    [^()]+    (?(<OPEN>) \) )


-       If the name used in a condition of this kind is a duplicate,  the  test
-       is  applied to all subpatterns of the same name, and is true if any one
-       of them has matched.
+       If  the  name used in a condition of this kind is a duplicate, the test
+       is applied to all groups of the same name, and is true if  any  one  of
+       them has matched.


    Checking for pattern recursion


-       "Recursion" in this sense refers to any subroutine-like call  from  one
-       part  of  the  pattern to another, whether or not it is actually recur-
-       sive. See the sections entitled "Recursive patterns"  and  "Subpatterns
-       as subroutines" below for details of recursion and subpattern calls.
+       "Recursion"  in  this sense refers to any subroutine-like call from one
+       part of the pattern to another, whether or not it  is  actually  recur-
+       sive.  See  the  sections  entitled "Recursive patterns" and "Groups as
+       subroutines" below for details of recursion and subroutine calls.


-       If  a  condition is the string (R), and there is no subpattern with the
-       name R, the condition is true if matching is currently in  a  recursion
-       or  subroutine  call  to the whole pattern or any subpattern. If digits
-       follow the letter R, and there is no subpattern  with  that  name,  the
-       condition is true if the most recent call is into a subpattern with the
-       given number, which must exist somewhere in the overall  pattern.  This
+       If a condition is the string (R), and there is no  capture  group  with
+       the  name R, the condition is true if matching is currently in a recur-
+       sion or subroutine call to the whole pattern or any capture  group.  If
+       digits  follow  the letter R, and there is no group with that name, the
+       condition is true if the most recent call is  into  a  group  with  the
+       given  number,  which must exist somewhere in the overall pattern. This
        is a contrived example that is equivalent to a+b:


          ((?(R1)a+|(?1)b))


-       However,  in both cases, if there is a subpattern with a matching name,
-       the condition tests for its being set,  as  described  in  the  section
-       above,  instead of testing for recursion. For example, creating a group
-       with the name R1 by adding (?<R1>)  to  the  above  pattern  completely
-       changes its meaning.
+       However, in both cases, if there is a capture  group  with  a  matching
+       name,  the  condition tests for its being set, as described in the sec-
+       tion above, instead of testing for recursion. For example,  creating  a
+       group  with  the  name  R1  by adding (?<R1>) to the above pattern com-
+       pletely changes its meaning.


        If a name preceded by ampersand follows the letter R, for example:


          (?(R&name)...)


-       the condition is true if the most recent recursion is into a subpattern
-       of that name (which must exist within the pattern).
+       the condition is true if the most recent recursion is into a  group  of
+       that name (which must exist within the pattern).


        This condition does not check the entire recursion stack. It tests only
-       the  current  level.  If the name used in a condition of this kind is a
-       duplicate, the test is applied to all subpatterns of the same name, and
-       is true if any one of them is the most recent recursion.
+       the current level. If the name used in a condition of this  kind  is  a
+       duplicate,  the  test is applied to all groups of the same name, and is
+       true if any one of them is the most recent recursion.


        At "top level", all these recursion test conditions are false.


- Defining subpatterns for use by reference only
+ Defining capture groups for use by reference only

        If the condition is the string (DEFINE), the condition is always false,
-       even if there is a group with the name DEFINE. In this case, there  may
-       be only one alternative in the subpattern. It is always skipped if con-
-       trol reaches this point in the pattern; the idea of DEFINE is  that  it
-       can  be  used  to  define subroutines that can be referenced from else-
-       where. (The use of subroutines is described below.) For example, a pat-
-       tern to match an IPv4 address such as "192.168.23.245" could be written
-       like this (ignore white space and line breaks):
+       even  if there is a group with the name DEFINE. In this case, there may
+       be only one alternative in the rest of the  conditional  group.  It  is
+       always  skipped  if control reaches this point in the pattern; the idea
+       of DEFINE is that it can be used to define subroutines that can be ref-
+       erenced  from  elsewhere.  (The use of subroutines is described below.)
+       For  example,  a  pattern  to   match   an   IPv4   address   such   as
+       "192.168.23.245"  could  be  written  like this (ignore white space and
+       line breaks):


          (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) )
          \b (?&byte) (\.(?&byte)){3} \b
@@ -8488,71 +8486,72 @@


    Assertion conditions


-       If the condition is not in any of the above  formats,  it  must  be  an
-       assertion.   This may be a positive or negative lookahead or lookbehind
-       assertion. Consider  this  pattern,  again  containing  non-significant
-       white space, and with the two alternatives on the second line:
+       If the condition is not in any of the  above  formats,  it  must  be  a
+       parenthesized  assertion.  This may be a positive or negative lookahead
+       or lookbehind assertion. Consider this pattern, again  containing  non-
+       significant  white  space,  and with the two alternatives on the second
+       line:


          (?(?=[^a-z]*[a-z])
          \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} )


-       The  condition  is  a  positive  lookahead  assertion  that  matches an
-       optional sequence of non-letters followed by a letter. In other  words,
-       it  tests  for the presence of at least one letter in the subject. If a
-       letter is found, the subject is matched against the first  alternative;
-       otherwise  it  is  matched  against  the  second.  This pattern matches
-       strings in one of the two forms dd-aaa-dd or dd-dd-dd,  where  aaa  are
+       The condition  is  a  positive  lookahead  assertion  that  matches  an
+       optional  sequence of non-letters followed by a letter. In other words,
+       it tests for the presence of at least one letter in the subject.  If  a
+       letter  is found, the subject is matched against the first alternative;
+       otherwise it is  matched  against  the  second.  This  pattern  matches
+       strings  in  one  of the two forms dd-aaa-dd or dd-dd-dd, where aaa are
        letters and dd are digits.


-       When  an  assertion that is a condition contains capturing subpatterns,
-       any capturing that occurs in a matching branch is retained  afterwards,
-       for both positive and negative assertions, because matching always con-
-       tinues after the assertion, whether it succeeds or fails. (Compare non-
-       conditional  assertions,  when  captures are retained only for positive
-       assertions that succeed.)
+       When an assertion that is a condition contains capture groups, any cap-
+       turing  that  occurs  in  a matching branch is retained afterwards, for
+       both positive and negative assertions, because matching always  contin-
+       ues  after  the  assertion, whether it succeeds or fails. (Compare non-
+       conditional assertions, for which captures are retained only for  posi-
+       tive assertions that succeed.)



COMMENTS

        There are two ways of including comments in patterns that are processed
-       by  PCRE2.  In  both  cases,  the start of the comment must not be in a
-       character class, nor in the middle of any  other  sequence  of  related
-       characters  such  as (?: or a subpattern name or number. The characters
-       that make up a comment play no part in the pattern matching.
+       by PCRE2. In both cases, the start of the comment  must  not  be  in  a
+       character  class,  nor  in  the middle of any other sequence of related
+       characters such as (?: or a group name or number. The  characters  that
+       make up a comment play no part in the pattern matching.


-       The sequence (?# marks the start of a comment that continues up to  the
-       next  closing parenthesis. Nested parentheses are not permitted. If the
-       PCRE2_EXTENDED or PCRE2_EXTENDED_MORE option is  set,  an  unescaped  #
-       character  also  introduces  a comment, which in this case continues to
-       immediately after the next newline character or character  sequence  in
+       The  sequence (?# marks the start of a comment that continues up to the
+       next closing parenthesis. Nested parentheses are not permitted. If  the
+       PCRE2_EXTENDED  or  PCRE2_EXTENDED_MORE  option  is set, an unescaped #
+       character also introduces a comment, which in this  case  continues  to
+       immediately  after  the next newline character or character sequence in
        the pattern. Which characters are interpreted as newlines is controlled
-       by an option passed to the compiling function or by a special  sequence
+       by  an option passed to the compiling function or by a special sequence
        at the start of the pattern, as described in the section entitled "New-
        line conventions" above. Note that the end of this type of comment is a
-       literal  newline  sequence in the pattern; escape sequences that happen
+       literal newline sequence in the pattern; escape sequences  that  happen
        to represent a newline do not count. For example, consider this pattern
-       when  PCRE2_EXTENDED is set, and the default newline convention (a sin-
+       when PCRE2_EXTENDED is set, and the default newline convention (a  sin-
        gle linefeed character) is in force:


          abc #comment \n still comment


-       On encountering the # character, pcre2_compile() skips  along,  looking
-       for  a newline in the pattern. The sequence \n is still literal at this
-       stage, so it does not terminate the comment. Only an  actual  character
+       On  encountering  the # character, pcre2_compile() skips along, looking
+       for a newline in the pattern. The sequence \n is still literal at  this
+       stage,  so  it does not terminate the comment. Only an actual character
        with the code value 0x0a (the default newline) does so.



RECURSIVE PATTERNS

-       Consider  the problem of matching a string in parentheses, allowing for
-       unlimited nested parentheses. Without the use of  recursion,  the  best
-       that  can  be  done  is  to use a pattern that matches up to some fixed
-       depth of nesting. It is not possible to  handle  an  arbitrary  nesting
+       Consider the problem of matching a string in parentheses, allowing  for
+       unlimited  nested  parentheses.  Without the use of recursion, the best
+       that can be done is to use a pattern that  matches  up  to  some  fixed
+       depth  of  nesting.  It  is not possible to handle an arbitrary nesting
        depth.


        For some time, Perl has provided a facility that allows regular expres-
-       sions to recurse (amongst other things). It does this by  interpolating
-       Perl  code in the expression at run time, and the code can refer to the
+       sions  to recurse (amongst other things). It does this by interpolating
+       Perl code in the expression at run time, and the code can refer to  the
        expression itself. A Perl pattern using code interpolation to solve the
        parentheses problem can be created like this:


@@ -8562,64 +8561,63 @@
        refers recursively to the pattern in which it appears.


        Obviously,  PCRE2  cannot  support  the  interpolation  of  Perl  code.
-       Instead,  it  supports  special syntax for recursion of the entire pat-
-       tern, and also for individual subpattern recursion. After its introduc-
-       tion  in  PCRE1  and  Python,  this  kind of recursion was subsequently
+       Instead, it supports special syntax for recursion of  the  entire  pat-
+       tern, and also for individual capture group recursion. After its intro-
+       duction in PCRE1 and Python, this kind of  recursion  was  subsequently
        introduced into Perl at release 5.10.


-       A special item that consists of (? followed by a  number  greater  than
-       zero  and  a  closing parenthesis is a recursive subroutine call of the
-       subpattern of the given number, provided that  it  occurs  inside  that
-       subpattern.  (If  not,  it is a non-recursive subroutine call, which is
-       described in the next section.) The special item  (?R)  or  (?0)  is  a
+       A  special  item  that consists of (? followed by a number greater than
+       zero and a closing parenthesis is a recursive subroutine  call  of  the
+       capture  group of the given number, provided that it occurs inside that
+       group. (If not,  it  is  a  non-recursive  subroutine  call,  which  is
+       described  in  the  next  section.)  The special item (?R) or (?0) is a
        recursive call of the entire regular expression.


-       This  PCRE2  pattern  solves the nested parentheses problem (assume the
+       This PCRE2 pattern solves the nested parentheses  problem  (assume  the
        PCRE2_EXTENDED option is set so that white space is ignored):


          \( ( [^()]++ | (?R) )* \)


-       First it matches an opening parenthesis. Then it matches any number  of
-       substrings  which  can  either  be  a sequence of non-parentheses, or a
-       recursive match of the pattern itself (that is, a  correctly  parenthe-
+       First  it matches an opening parenthesis. Then it matches any number of
+       substrings which can either be a  sequence  of  non-parentheses,  or  a
+       recursive  match  of the pattern itself (that is, a correctly parenthe-
        sized substring).  Finally there is a closing parenthesis. Note the use
        of a possessive quantifier to avoid backtracking into sequences of non-
        parentheses.


-       If  this  were  part of a larger pattern, you would not want to recurse
+       If this were part of a larger pattern, you would not  want  to  recurse
        the entire pattern, so instead you could use this:


          ( \( ( [^()]++ | (?1) )* \) )


-       We have put the pattern into parentheses, and caused the  recursion  to
+       We  have  put the pattern into parentheses, and caused the recursion to
        refer to them instead of the whole pattern.


-       In  a  larger  pattern,  keeping  track  of  parenthesis numbers can be
-       tricky. This is made easier by the use of relative references.  Instead
+       In a larger pattern,  keeping  track  of  parenthesis  numbers  can  be
+       tricky.  This is made easier by the use of relative references. Instead
        of (?1) in the pattern above you can write (?-2) to refer to the second
-       most recently opened parentheses  preceding  the  recursion.  In  other
-       words,  a  negative  number counts capturing parentheses leftwards from
+       most  recently  opened  parentheses  preceding  the recursion. In other
+       words, a negative number counts capturing  parentheses  leftwards  from
        the point at which it is encountered.


-       Be aware however, that if duplicate subpattern numbers are in use, rel-
-       ative  references refer to the earliest subpattern with the appropriate
+       Be  aware  however, that if duplicate capture group numbers are in use,
+       relative references refer to the earliest group  with  the  appropriate
        number. Consider, for example:


          (?|(a)|(b)) (c) (?-2)


-       The first two capturing groups (a) and (b) are  both  numbered  1,  and
-       group  (c)  is  number  2. When the reference (?-2) is encountered, the
-       second most recently opened parentheses has the number 1, but it is the
-       first  such  group  (the (a) group) to which the recursion refers. This
-       would be the same if an absolute reference  (?1)  was  used.  In  other
-       words,  relative  references are just a shorthand for computing a group
-       number.
+       The first two capture groups (a) and (b) are both numbered 1, and group
+       (c) is number 2. When the reference (?-2) is  encountered,  the  second
+       most  recently opened parentheses has the number 1, but it is the first
+       such group (the (a) group) to which the recursion refers. This would be
+       the  same if an absolute reference (?1) was used. In other words, rela-
+       tive references are just a shorthand for computing a group number.


-       It is also possible to refer to  subsequently  opened  parentheses,  by
-       writing  references  such  as (?+2). However, these cannot be recursive
-       because the reference is not inside the  parentheses  that  are  refer-
-       enced.  They are always non-recursive subroutine calls, as described in
-       the next section.
+       It is also possible to refer to subsequent capture groups,  by  writing
+       references  such  as  (?+2). However, these cannot be recursive because
+       the reference is not inside the parentheses that are  referenced.  They
+       are  always  non-recursive  subroutine  calls, as described in the next
+       section.


        An alternative approach is to use named parentheses.  The  Perl  syntax
        for  this  is  (?&name);  PCRE1's earlier syntax (?P>name) is also sup-
@@ -8627,8 +8625,8 @@


          (?<pn> \( ( [^()]++ | (?&pn) )* \) )


-       If there is more than one subpattern with the same name,  the  earliest
-       one is used.
+       If there is more than one group with the same name, the earliest one is
+       used.


        The example pattern that we have been looking at contains nested unlim-
        ited repeats, and so the use of a possessive  quantifier  for  matching
@@ -8650,10 +8648,10 @@
          (ab(cd)ef)


        the value for the inner capturing parentheses  (numbered  2)  is  "ef",
-       which  is the last value taken on at the top level. If a capturing sub-
-       pattern is not matched at the top level, its final  captured  value  is
-       unset,  even  if  it was (temporarily) set at a deeper level during the
-       matching process.
+       which  is  the last value taken on at the top level. If a capture group
+       is not matched at the top level, its final  captured  value  is  unset,
+       even  if it was (temporarily) set at a deeper level during the matching
+       process.


        Do not confuse the (?R) item with the condition (R),  which  tests  for
        recursion.   Consider  this pattern, which matches text in angle brack-
@@ -8663,9 +8661,9 @@


          < (?: (?(R) \d++  | [^<>]*+) | (?R)) * >


-       In this pattern, (?(R) is the start of a conditional  subpattern,  with
-       two  different  alternatives for the recursive and non-recursive cases.
-       The (?R) item is the actual recursive call.
+       In this pattern, (?(R) is the start of a conditional  group,  with  two
+       different  alternatives  for the recursive and non-recursive cases. The
+       (?R) item is the actual recursive call.


    Differences in recursion processing between PCRE2 and Perl


@@ -8672,7 +8670,7 @@
        Some former differences between PCRE2 and Perl no longer exist.


        Before release 10.30, recursion processing in PCRE2 differed from  Perl
-       in  that  a  recursive  subpattern call was always treated as an atomic
+       in  that  a  recursive  subroutine call was always treated as an atomic
        group. That is, once it had matched some of the subject string, it  was
        never  re-entered,  even if it contained untried alternatives and there
        was a subsequent matching failure. (Historical note:  PCRE  implemented
@@ -8709,10 +8707,10 @@


        Another way in which PCRE2 and Perl used to differ in  their  recursion
        processing  is  in  the  handling of captured values. Formerly in Perl,
-       when a subpattern was called recursively or as a  subpattern  (see  the
-       next  section),  it had no access to any values that were captured out-
-       side the recursion, whereas in PCRE2 these values  can  be  referenced.
-       Consider this pattern:
+       when a group was called recursively or as a subroutine  (see  the  next
+       section), it had no access to any values that were captured outside the
+       recursion, whereas in PCRE2 these values can  be  referenced.  Consider
+       this pattern:


          ^(.)(\1|a(?2))


@@ -8723,15 +8721,15 @@
        to fail in Perl, but in later versions (I tried 5.024) it now works.



-SUBPATTERNS AS SUBROUTINES
+GROUPS AS SUBROUTINES

-       If  the  syntax for a recursive subpattern call (either by number or by
-       name) is used outside the parentheses to which it refers, it operates a
-       bit like a subroutine in a programming language. More accurately, PCRE2
-       treats the referenced subpattern as an independent subpattern which  it
-       tries  to match at the current matching position. The called subpattern
-       may be defined before or after the reference. A numbered reference  can
-       be absolute or relative, as in these examples:
+       If  the syntax for a recursive group call (either by number or by name)
+       is used outside the parentheses to which it refers, it operates  a  bit
+       like  a  subroutine  in  a programming language. More accurately, PCRE2
+       treats the referenced group as an independent subpattern which it tries
+       to  match  at  the  current  matching position. The called group may be
+       defined before or after the reference.  A  numbered  reference  can  be
+       absolute or relative, as in these examples:


          (...(absolute)...)...(?2)...
          (...(relative)...)...(?-1)...
@@ -8755,18 +8753,18 @@
        calls can now occur. However, any capturing parentheses  that  are  set
        during the subroutine call revert to their previous values afterwards.


-       Processing  options  such as case-independence are fixed when a subpat-
-       tern is defined, so if it is used as a subroutine, such options  cannot
-       be changed for different calls. For example, consider this pattern:
+       Processing  options such as case-independence are fixed when a group is
+       defined, so if it is used as  a  subroutine,  such  options  cannot  be
+       changed for different calls. For example, consider this pattern:


          (abc)(?i:(?-1))


        It  matches  "abcabc". It does not match "abcABC" because the change of
-       processing option does not affect the called subpattern.
+       processing option does not affect the called group.


-       The behaviour of backtracking control verbs in subpatterns when  called
-       as subroutines is described in the section entitled "Backtracking verbs
-       in subroutines" below.
+       The behaviour of backtracking control verbs in groups  when  called  as
+       subroutines is described in the section entitled "Backtracking verbs in
+       subroutines" below.



ONIGURUMA SUBROUTINE SYNTAX
@@ -8773,9 +8771,9 @@

        For compatibility with Oniguruma, the non-Perl syntax \g followed by  a
        name or a number enclosed either in angle brackets or single quotes, is
-       an alternative syntax for referencing a  subpattern  as  a  subroutine,
-       possibly  recursively. Here are two of the examples used above, rewrit-
-       ten using this syntax:
+       an alternative syntax for calling a group  as  a  subroutine,  possibly
+       recursively.  Here  are two of the examples used above, rewritten using
+       this syntax:


          (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) )
          (sens|respons)e and \g'1'ibility
@@ -8905,8 +8903,8 @@
        by the DFA matching function.


        The behaviour of these verbs in repeated  groups,  assertions,  and  in
-       subpatterns called as subroutines (whether or not recursively) is docu-
-       mented below.
+       capture  groups  called  as subroutines (whether or not recursively) is
+       documented below.


    Optimizations that affect backtracking verbs


@@ -8931,8 +8929,8 @@
           (*ACCEPT) or (*ACCEPT:NAME)


        This verb causes the match to end successfully, skipping the  remainder
-       of  the pattern. However, when it is inside a subpattern that is called
-       as a subroutine, only that subpattern is ended  successfully.  Matching
+       of  the  pattern.  However,  when  it is inside a capture group that is
+       called as a subroutine, only that group is ended successfully. Matching
        then continues at the outer level. If (*ACCEPT) in triggered in a posi-
        tive assertion, the assertion succeeds; in a  negative  assertion,  the
        assertion fails.
@@ -8945,8 +8943,8 @@
        This matches "AB", "AAD", or "ACD"; when it matches "AB", "B"  is  cap-
        tured by the outer parentheses.


-       Warning:  (*ACCEPT)  should not be used within a script run subpattern,
-       because it causes an immediate exit from the subpattern, bypassing  the
+       Warning:  (*ACCEPT)  should  not  be  used  within  a script run group,
+       because it causes an immediate  exit  from  the  group,  bypassing  the
        script run checking.


          (*FAIL) or (*FAIL:NAME)
@@ -9184,10 +9182,10 @@
        to  the  caller. However, (*SKIP:NAME) searches only for names set with
        (*MARK), ignoring those set by other backtracking verbs.


-       A subpattern that does not contain a | character is just a part of  the
+       A group that does not contain a | character  is  just  a  part  of  the
        enclosing  alternative;  it  is  not a nested alternation with only one
-       alternative. The effect of (*THEN) extends beyond such a subpattern  to
-       the  enclosing alternative. Consider this pattern, where A, B, etc. are
+       alternative. The effect of (*THEN) extends beyond such a group  to  the
+       enclosing  alternative.   Consider  this  pattern, where A, B, etc. are
        complex pattern fragments that do not contain any | characters at  this
        level:


@@ -9195,20 +9193,20 @@

        If  A and B are matched, but there is a failure in C, matching does not
        backtrack into A; instead it moves to the next alternative, that is, D.
-       However,  if the subpattern containing (*THEN) is given an alternative,
-       it behaves differently:
+       However,  if  the  group containing (*THEN) is given an alternative, it
+       behaves differently:


          A (B(*THEN)C | (*FAIL)) | D


-       The effect of (*THEN) is now confined to the inner subpattern. After  a
-       failure in C, matching moves to (*FAIL), which causes the whole subpat-
-       tern to fail because there are no more alternatives  to  try.  In  this
-       case, matching does now backtrack into A.
+       The effect of (*THEN) is now confined to the inner group. After a fail-
+       ure  in  C,  matching moves to (*FAIL), which causes the whole group to
+       fail because there are no more  alternatives  to  try.  In  this  case,
+       matching does backtrack into A.


-       Note  that  a  conditional  subpattern  is not considered as having two
-       alternatives, because only one is ever used.  In  other  words,  the  |
-       character in a conditional subpattern has a different meaning. Ignoring
-       white space, consider:
+       Note  that a conditional group is not considered as having two alterna-
+       tives, because only one is ever used. In other words, the  |  character
+       in  a  conditional group has a different meaning. Ignoring white space,
+       consider:


          ^.*? (?(?=a) a | b(*THEN)c )


@@ -9216,10 +9214,10 @@
        ungreedy,  it  initially  matches  zero characters. The condition (?=a)
        then fails, the character "b" is matched,  but  "c"  is  not.  At  this
        point,  matching does not backtrack to .*? as might perhaps be expected
-       from the presence of the | character.  The  conditional  subpattern  is
-       part of the single alternative that comprises the whole pattern, and so
-       the match fails. (If there was a backtrack into  .*?,  allowing  it  to
-       match "b", the match would succeed.)
+       from the presence of the | character. The conditional group is part  of
+       the  single  alternative  that  comprises the whole pattern, and so the
+       match fails. (If there was a backtrack into .*?, allowing it  to  match
+       "b", the match would succeed.)


        The  verbs just described provide four different "strengths" of control
        when subsequent matching fails. (*THEN) is the weakest, carrying on the
@@ -9266,7 +9264,7 @@
        (*FAIL)  in any assertion has its normal effect: it forces an immediate
        backtrack. The behaviour of the other  backtracking  verbs  depends  on
        whether  or  not the assertion is standalone or acting as the condition
-       in a conditional subpattern.
+       in a conditional group.


        (*ACCEPT) in a standalone positive assertion causes  the  assertion  to
        succeed  without  any  further  processing; captured strings and a mark
@@ -9299,26 +9297,24 @@


    Backtracking verbs in subroutines


-       These  behaviours  occur whether or not the subpattern is called recur-
-       sively.
+       These behaviours occur whether or not the group is called recursively.


-       (*ACCEPT) in a subpattern called as a subroutine causes the  subroutine
-       match  to succeed without any further processing. Matching then contin-
-       ues after the subroutine call. Perl documents  this  behaviour.  Perl's
-       treatment of the other verbs in subroutines is different in some cases.
+       (*ACCEPT) in a group called as a subroutine causes the subroutine match
+       to succeed without any  further  processing.  Matching  then  continues
+       after the subroutine call. Perl documents this behaviour. Perl's treat-
+       ment of the other verbs in subroutines is different in some cases.


-       (*FAIL)  in  a subpattern called as a subroutine has its normal effect:
-       it forces an immediate backtrack.
+       (*FAIL) in a group called as a subroutine has  its  normal  effect:  it
+       forces an immediate backtrack.


-       (*COMMIT), (*SKIP), and (*PRUNE) cause the  subroutine  match  to  fail
-       when triggered by being backtracked to in a subpattern called as a sub-
-       routine. There is then a backtrack at the outer level.
+       (*COMMIT),  (*SKIP),  and  (*PRUNE)  cause the subroutine match to fail
+       when triggered by being backtracked to in a group called as  a  subrou-
+       tine. There is then a backtrack at the outer level.


        (*THEN), when triggered, skips to the next alternative in the innermost
-       enclosing group within the subpattern that has alternatives (its normal
-       behaviour). However, if there is no such group  within  the  subroutine
-       subpattern,  the subroutine match fails and there is a backtrack at the
-       outer level.
+       enclosing group that has alternatives (its normal behaviour).  However,
+       if there is no such group within the subroutine's group, the subroutine
+       match fails and there is a backtrack at the outer level.



SEE ALSO
@@ -9336,8 +9332,8 @@

REVISION

-       Last updated: 27 November 2018
-       Copyright (c) 1997-2018 University of Cambridge.
+       Last updated: 04 February 2019
+       Copyright (c) 1997-2019 University of Cambridge.
 ------------------------------------------------------------------------------



@@ -9361,9 +9357,9 @@
        code, so that most simple patterns do not use much memory  for  storing
        the compiled version. However, there is one case where the memory usage
        of a compiled pattern can be unexpectedly  large.  If  a  parenthesized
-       subpattern has a quantifier with a minimum greater than 1 and/or a lim-
-       ited maximum, the whole subpattern is repeated in  the  compiled  code.
-       For example, the pattern
+       group  has  a quantifier with a minimum greater than 1 and/or a limited
+       maximum, the whole group is repeated in the compiled code. For example,
+       the pattern


          (abc|def){2,4}


@@ -9571,8 +9567,8 @@

REVISION

-       Last updated: 25 April 2018
-       Copyright (c) 1997-2018 University of Cambridge.
+       Last updated: 03 February 2019
+       Copyright (c) 1997-2019 University of Cambridge.
 ------------------------------------------------------------------------------



@@ -10441,19 +10437,23 @@

CAPTURING

-         (...)           capturing group
-         (?<name>...)    named capturing group (Perl)
-         (?'name'...)    named capturing group (Perl)
-         (?P<name>...)   named capturing group (Python)
-         (?:...)         non-capturing group
-         (?|...)         non-capturing group; reset group numbers for
-                          capturing groups in each alternative
+         (...)           capture group
+         (?<name>...)    named capture group (Perl)
+         (?'name'...)    named capture group (Perl)
+         (?P<name>...)   named capture group (Python)
+         (?:...)         non-capture group
+         (?|...)         non-capture group; reset group numbers for
+                          capture groups in each alternative


+       In non-UTF modes, names may contain underscores and ASCII  letters  and
+       digits;  in  UTF  modes, any Unicode letters and Unicode decimal digits
+       are permitted. In both cases, a name must not start with a digit.


+
ATOMIC GROUPS

-         (?>...)         atomic, non-capturing group
-         (*atomic:...)   atomic, non-capturing group
+         (?>...)         atomic non-capture group
+         (*atomic:...)   atomic non-capture group



 COMMENT
@@ -10480,7 +10480,7 @@
        a mixture of setting and unsetting such as (?i-x) is allowed, but there
        may be only one hyphen. Setting (but no unsetting) is allowed after (?^
        for example (?^in). An option setting may appear at the start of a non-
-       capturing group, for example (?i:...).
+       capture group, for example (?i:...).


        The  following  are  recognized  only at the very start of a pattern or
        after one of the newline or \R options with similar syntax.  More  than
@@ -10577,19 +10577,19 @@
 SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)


          (?R)            recurse whole pattern
-         (?n)            call subpattern by absolute number
-         (?+n)           call subpattern by relative number
-         (?-n)           call subpattern by relative number
-         (?&name)        call subpattern by name (Perl)
-         (?P>name)       call subpattern by name (Python)
-         \g<name>        call subpattern by name (Oniguruma)
-         \g'name'        call subpattern by name (Oniguruma)
-         \g<n>           call subpattern by absolute number (Oniguruma)
-         \g'n'           call subpattern by absolute number (Oniguruma)
-         \g<+n>          call subpattern by relative number (PCRE2 extension)
-         \g'+n'          call subpattern by relative number (PCRE2 extension)
-         \g<-n>          call subpattern by relative number (PCRE2 extension)
-         \g'-n'          call subpattern by relative number (PCRE2 extension)
+         (?n)            call subroutine by absolute number
+         (?+n)           call subroutine by relative number
+         (?-n)           call subroutine by relative number
+         (?&name)        call subroutine by name (Perl)
+         (?P>name)       call subroutine by name (Python)
+         \g<name>        call subroutine by name (Oniguruma)
+         \g'name'        call subroutine by name (Oniguruma)
+         \g<n>           call subroutine by absolute number (Oniguruma)
+         \g'n'           call subroutine by absolute number (Oniguruma)
+         \g<+n>          call subroutine by relative number (PCRE2 extension)
+         \g'+n'          call subroutine by relative number (PCRE2 extension)
+         \g<-n>          call subroutine by relative number (PCRE2 extension)
+         \g'-n'          call subroutine by relative number (PCRE2 extension)



 CONDITIONAL PATTERNS
@@ -10606,7 +10606,7 @@
          (?(R)               overall recursion condition
          (?(Rn)              specific numbered group recursion condition
          (?(R&name)          specific named group recursion condition
-         (?(DEFINE)          define subpattern for reference
+         (?(DEFINE)          define groups for reference
          (?(VERSION[>]=n.m)  test PCRE2 version
          (?(assert)          assertion condition


@@ -10670,8 +10670,8 @@

REVISION

-       Last updated: 10 October 2018
-       Copyright (c) 1997-2018 University of Cambridge.
+       Last updated: 03 February 2019
+       Copyright (c) 1997-2019 University of Cambridge.
 ------------------------------------------------------------------------------



@@ -10704,15 +10704,16 @@
UNICODE PROPERTY SUPPORT

        When  PCRE2 is built with Unicode support, the escape sequences \p{..},
-       \P{..}, and \X can be used. The Unicode properties that can  be  tested
-       are  limited to the general category properties such as Lu for an upper
-       case letter or Nd for a decimal number, the Unicode script  names  such
-       as Arabic or Han, and the derived properties Any and L&. Full lists are
-       given in the pcre2pattern and pcre2syntax documentation. Only the short
-       names  for  properties are supported. For example, \p{L} matches a let-
-       ter. Its Perl synonym, \p{Letter}, is not supported.   Furthermore,  in
-       Perl,  many properties may optionally be prefixed by "Is", for compati-
-       bility with Perl 5.6. PCRE2 does not support this.
+       \P{..}, and \X can be used. This is not dependent on the PCRE2_UTF set-
+       ting.   The  Unicode  properties  that can be tested are limited to the
+       general category properties such as Lu for an upper case letter  or  Nd
+       for  a  decimal number, the Unicode script names such as Arabic or Han,
+       and the derived properties Any and L&. Full  lists  are  given  in  the
+       pcre2pattern  and  pcre2syntax  documentation. Only the short names for
+       properties are supported. For example, \p{L} matches a letter. Its Perl
+       synonym,  \p{Letter},  is  not  supported.   Furthermore, in Perl, many
+       properties may optionally be prefixed by "Is", for  compatibility  with
+       Perl 5.6. PCRE2 does not support this.



WIDE CHARACTERS AND UTF MODES
@@ -10719,51 +10720,57 @@

        Code points less than 256 can be specified in patterns by either braced
        or unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3).
-       Larger values have to use braced sequences. Unbraced octal code  points
+       Larger  values have to use braced sequences. Unbraced octal code points
        up to \777 are also recognized; larger ones can be coded using \o{...}.


-       The  escape sequence \N{U+<hex digits>} is recognized as another way of
-       specifying a Unicode character by code point in a UTF mode. It  is  not
+       The escape sequence \N{U+<hex digits>} is recognized as another way  of
+       specifying  a  Unicode character by code point in a UTF mode. It is not
        allowed in non-UTF modes.


-       In  UTF modes, repeat quantifiers apply to complete UTF characters, not
+       In UTF modes, repeat quantifiers apply to complete UTF characters,  not
        to individual code units.


-       In UTF modes, the dot metacharacter matches one UTF  character  instead
+       In  UTF  modes, the dot metacharacter matches one UTF character instead
        of a single code unit.


+       In UTF modes, capture group names are not restricted to ASCII, and  may
+       contain any Unicode letters and decimal digits, as well as underscore.
+
        The escape sequence \C can be used to match a single code unit in a UTF
        mode, but its use can lead to some strange effects because it breaks up
        multi-unit  characters  (see  the description of \C in the pcre2pattern
-       documentation).
+       documentation). For this reason, there is a build-time option that dis-
+       ables  support  for  \C completely. There is also a less draconian com-
+       pile-time option for locking out the use of \C when a pattern  is  com-
+       piled.


-       The use of \C is not supported by  the  alternative  matching  function
+       The  use  of  \C  is not supported by the alternative matching function
        pcre2_dfa_match() when in UTF-8 or UTF-16 mode, that is, when a charac-
-       ter may consist of more than one code unit. The  use  of  \C  in  these
-       modes  provokes a match-time error. Also, the JIT optimization does not
+       ter  may  consist  of  more  than one code unit. The use of \C in these
+       modes provokes a match-time error. Also, the JIT optimization does  not
        support \C in these modes. If JIT optimization is requested for a UTF-8
-       or  UTF-16  pattern  that contains \C, it will not succeed, and so when
+       or UTF-16 pattern that contains \C, it will not succeed,  and  so  when
        pcre2_match() is called, the matching will be carried out by the normal
        interpretive function.


        The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly test
-       characters of any code value, but,  by  default,  the  characters  that
-       PCRE2  recognizes as digits, spaces, or word characters remain the same
-       set as in non-UTF mode, all  with  code  points  less  than  256.  This
-       remains  true  even  when  PCRE2  is  built to include Unicode support,
-       because to do otherwise would slow down matching in many common  cases.
-       Note  that  this also applies to \b and \B, because they are defined in
-       terms of \w and \W. If you want to test for  a  wider  sense  of,  say,
-       "digit",  you  can  use explicit Unicode property tests such as \p{Nd}.
-       Alternatively, if you set the PCRE2_UCP option, the way that the  char-
-       acter  escapes  work  is changed so that Unicode properties are used to
+       characters  of  any  code  value,  but, by default, the characters that
+       PCRE2 recognizes as digits, spaces, or word characters remain the  same
+       set  as  in  non-UTF  mode,  all  with  code points less than 256. This
+       remains true even when PCRE2  is  built  to  include  Unicode  support,
+       because  to do otherwise would slow down matching in many common cases.
+       Note that this also applies to \b and \B, because they are  defined  in
+       terms  of  \w  and  \W.  If you want to test for a wider sense of, say,
+       "digit", you can use explicit Unicode property tests  such  as  \p{Nd}.
+       Alternatively,  if you set the PCRE2_UCP option, the way that the char-
+       acter escapes work is changed so that Unicode properties  are  used  to
        determine which characters match. There are more details in the section
        on generic character types in the pcre2pattern documentation.


-       Similarly,  characters that match the POSIX named character classes are
+       Similarly, characters that match the POSIX named character classes  are
        all low-valued characters, unless the PCRE2_UCP option is set.


-       However, the special  horizontal  and  vertical  white  space  matching
+       However,  the  special  horizontal  and  vertical  white space matching
        escapes (\h, \H, \v, and \V) do match all the appropriate Unicode char-
        acters, whether or not PCRE2_UCP is set.


@@ -10773,7 +10780,7 @@
        Case-insensitive matching in a UTF mode makes use of Unicode properties
        except for characters whose code points are less than 128 and that have
        at most two case-equivalent values. For these, a direct table lookup is
-       used  for speed. A few Unicode characters such as Greek sigma have more
+       used for speed. A few Unicode characters such as Greek sigma have  more
        than two code points that are case-equivalent, and these are treated as
        such.


@@ -10780,102 +10787,102 @@

SCRIPT RUNS

-       The  pattern constructs (*script_run:...) and (*atomic_script_run:...),
-       with synonyms (*sr:...) and (*asr:...), verify that the string  matched
-       within  the  parentheses is a script run. In concept, a script run is a
-       sequence of characters that are all from the same Unicode script.  How-
+       The pattern constructs (*script_run:...) and  (*atomic_script_run:...),
+       with  synonyms (*sr:...) and (*asr:...), verify that the string matched
+       within the parentheses is a script run. In concept, a script run  is  a
+       sequence  of characters that are all from the same Unicode script. How-
        ever, because some scripts are commonly used together, and because some
-       diacritical and other marks are used with multiple scripts, it  is  not
+       diacritical  and  other marks are used with multiple scripts, it is not
        that simple.


        Every Unicode character has a Script property, mostly with a value cor-
-       responding to the name of a script, such as Latin, Greek, or  Cyrillic.
+       responding  to the name of a script, such as Latin, Greek, or Cyrillic.
        There are also three special values:


        "Unknown" is used for code points that have not been assigned, and also
-       for the surrogate code points. In the PCRE2 32-bit library,  characters
-       whose  code  points  are  greater  than the Unicode maximum (U+10FFFF),
-       which are accessible only in non-UTF mode,  are  assigned  the  Unknown
+       for  the surrogate code points. In the PCRE2 32-bit library, characters
+       whose code points are greater  than  the  Unicode  maximum  (U+10FFFF),
+       which  are  accessible  only  in non-UTF mode, are assigned the Unknown
        script.


-       "Common"  is used for characters that are used with many scripts. These
-       include punctuation, emoji, mathematical, musical,  and  currency  sym-
+       "Common" is used for characters that are used with many scripts.  These
+       include  punctuation,  emoji,  mathematical, musical, and currency sym-
        bols, and the ASCII digits 0 to 9.


-       "Inherited"  is used for characters such as diacritical marks that mod-
+       "Inherited" is used for characters such as diacritical marks that  mod-
        ify a previous character. These are considered to take on the script of
        the character that they modify.


-       Some  Inherited characters are used with many scripts, but many of them
-       are only normally used with a small number  of  scripts.  For  example,
+       Some Inherited characters are used with many scripts, but many of  them
+       are  only  normally  used  with a small number of scripts. For example,
        U+102E0 (Coptic Epact thousands mark) is used only with Arabic and Cop-
-       tic. In order to make it possible to check  this,  a  Unicode  property
-       called  Script  Extension  exists.  Its value is a list of scripts that
-       apply to the character. For the majority of characters, the  list  con-
-       tains  just  one  script, the same one as the Script property. However,
-       for characters such as U+102E0 more than one Script  is  listed.  There
-       are  also  some Common characters that have a single, non-Common script
+       tic.  In  order  to  make it possible to check this, a Unicode property
+       called Script Extension exists. Its value is a  list  of  scripts  that
+       apply  to  the character. For the majority of characters, the list con-
+       tains just one script, the same one as the  Script  property.  However,
+       for  characters  such  as U+102E0 more than one Script is listed. There
+       are also some Common characters that have a single,  non-Common  script
        in their Script Extension list.


        The next section describes the basic rules for deciding whether a given
-       string  of  characters  is  a script run. Note, however, that there are
-       some special cases involving the Chinese Han script, and an  additional
-       constraint  for  decimal  digits.  These are covered in subsequent sec-
+       string of characters is a script run. Note,  however,  that  there  are
+       some  special cases involving the Chinese Han script, and an additional
+       constraint for decimal digits. These are  covered  in  subsequent  sec-
        tions.


    Basic script run rules


        A string that is less than two characters long is a script run. This is
-       the  only  case  in  which an Unknown character can be part of a script
-       run. Longer strings are checked using only the Script Extensions  prop-
+       the only case in which an Unknown character can be  part  of  a  script
+       run.  Longer strings are checked using only the Script Extensions prop-
        erty, not the basic Script property.


-       If  a character's Script Extension property is the single value "Inher-
+       If a character's Script Extension property is the single value  "Inher-
        ited", it is always accepted as part of a script run. This is also true
-       for  the  property  "Common", subject to the checking of decimal digits
+       for the property "Common", subject to the checking  of  decimal  digits
        described below. All the remaining characters in a script run must have
-       at  least one script in common in their Script Extension lists. In set-
+       at least one script in common in their Script Extension lists. In  set-
        theoretic terminology, the intersection of all the sets of scripts must
        not be empty.


-       A  simple example is an Internet name such as "google.com". The letters
+       A simple example is an Internet name such as "google.com". The  letters
        are all in the Latin script, and the dot is Common, so this string is a
        script run.  However, the Cyrillic letter "o" looks exactly the same as
-       the Latin "o"; a string that looks the same, but with Cyrillic "o"s  is
+       the  Latin "o"; a string that looks the same, but with Cyrillic "o"s is
        not a script run.


-       More  interesting examples involve characters with more than one script
+       More interesting examples involve characters with more than one  script
        in their Script Extension. Consider the following characters:


          U+060C  Arabic comma
          U+06D4  Arabic full stop


-       The first has the Script Extension list Arabic, Hanifi  Rohingya,  Syr-
-       iac,  and  Thaana; the second has just Arabic and Hanifi Rohingya. Both
-       of them could  appear  in  script  runs  of  either  Arabic  or  Hanifi
-       Rohingya.  The first could also appear in Syriac or Thaana script runs,
+       The  first  has the Script Extension list Arabic, Hanifi Rohingya, Syr-
+       iac, and Thaana; the second has just Arabic and Hanifi  Rohingya.  Both
+       of  them  could  appear  in  script  runs  of  either  Arabic or Hanifi
+       Rohingya. The first could also appear in Syriac or Thaana script  runs,
        but the second could not.


    The Chinese Han script


-       The Chinese Han script is  commonly  used  in  conjunction  with  other
-       scripts  for  writing certain languages. Japanese uses the Hiragana and
-       Katakana scripts together with Han; Korean uses Hangul  and  Han;  Tai-
-       wanese  Mandarin  uses  Bopomofo  and Han. These three combinations are
-       treated as special cases when checking script runs and are, in  effect,
-       "virtual  scripts".  Thus,  a script run may contain a mixture of Hira-
-       gana, Katakana, and Han, or a mixture of Hangul and Han, or  a  mixture
-       of  Bopomofo  and  Han,  but  not, for example, a mixture of Hangul and
-       Bopomofo and Han. PCRE2 (like Perl) follows Unicode's  Technical  Stan-
+       The  Chinese  Han  script  is  commonly  used in conjunction with other
+       scripts for writing certain languages. Japanese uses the  Hiragana  and
+       Katakana  scripts  together  with Han; Korean uses Hangul and Han; Tai-
+       wanese Mandarin uses Bopomofo and Han.  These  three  combinations  are
+       treated  as special cases when checking script runs and are, in effect,
+       "virtual scripts". Thus, a script run may contain a  mixture  of  Hira-
+       gana,  Katakana,  and Han, or a mixture of Hangul and Han, or a mixture
+       of Bopomofo and Han, but not, for example,  a  mixture  of  Hangul  and
+       Bopomofo  and  Han. PCRE2 (like Perl) follows Unicode's Technical Stan-
        dard     39     ("Unicode     Security     Mechanisms",     http://uni-
        code.org/reports/tr39/) in allowing such mixtures.


    Decimal digits


-       Unicode contains many sets of 10 decimal digits in  different  scripts,
-       and  some  scripts  (including the Common script) contain more than one
-       set. Some of these decimal digits them are  visually  indistinguishable
-       from  the  common  ASCII  digits.  In  addition  to the script checking
+       Unicode  contains  many sets of 10 decimal digits in different scripts,
+       and some scripts (including the Common script) contain  more  than  one
+       set.  Some  of these decimal digits them are visually indistinguishable
+       from the common ASCII  digits.  In  addition  to  the  script  checking
        described above, if a script run contains any decimal digits, they must
        all come from the same set of 10 adjacent characters.


@@ -10882,61 +10889,61 @@

VALIDITY OF UTF STRINGS

-       When  the  PCRE2_UTF  option is set, the strings passed as patterns and
+       When the PCRE2_UTF option is set, the strings passed  as  patterns  and
        subjects are (by default) checked for validity on entry to the relevant
-       functions.   If an invalid UTF string is passed, an negative error code
-       is returned. The code unit offset to the  offending  character  can  be
-       extracted  from  the match data block by calling pcre2_get_startchar(),
+       functions.  If an invalid UTF string is passed, an negative error  code
+       is  returned.  The  code  unit offset to the offending character can be
+       extracted from the match data block by  calling  pcre2_get_startchar(),
        which is used for this purpose after a UTF error.


        UTF-16 and UTF-32 strings can indicate their endianness by special code
-       knows  as  a  byte-order  mark (BOM). The PCRE2 functions do not handle
+       knows as a byte-order mark (BOM). The PCRE2  functions  do  not  handle
        this, expecting strings to be in host byte order.


        A UTF string is checked before any other processing takes place. In the
-       case  of  pcre2_match()  and  pcre2_dfa_match()  calls  with a non-zero
-       starting offset, the check is applied only to that part of the  subject
-       that  could be inspected during matching, and there is a check that the
-       starting offset points to the first code unit of a character or to  the
-       end  of  the subject. If there are no lookbehind assertions in the pat-
-       tern, the check starts at the starting offset. Otherwise, it starts  at
-       the  length of the longest lookbehind before the starting offset, or at
-       the start of the subject if there are not that many  characters  before
-       the  starting offset. Note that the sequences \b and \B are one-charac-
+       case of pcre2_match()  and  pcre2_dfa_match()  calls  with  a  non-zero
+       starting  offset, the check is applied only to that part of the subject
+       that could be inspected during matching, and there is a check that  the
+       starting  offset points to the first code unit of a character or to the
+       end of the subject. If there are no lookbehind assertions in  the  pat-
+       tern,  the check starts at the starting offset. Otherwise, it starts at
+       the length of the longest lookbehind before the starting offset, or  at
+       the  start  of the subject if there are not that many characters before
+       the starting offset. Note that the sequences \b and \B are  one-charac-
        ter lookbehinds.


-       In addition to checking the format of the string, there is a  check  to
+       In  addition  to checking the format of the string, there is a check to
        ensure that all code points lie in the range U+0 to U+10FFFF, excluding
-       the surrogate area. The so-called "non-character" code points  are  not
+       the  surrogate  area. The so-called "non-character" code points are not
        excluded because Unicode corrigendum #9 makes it clear that they should
        not be.


-       Characters in the "Surrogate Area" of Unicode are reserved for  use  by
-       UTF-16,  where they are used in pairs to encode code points with values
-       greater than 0xFFFF. The code points that are encoded by  UTF-16  pairs
-       are  available  independently  in  the  UTF-8 and UTF-32 encodings. (In
-       other words, the whole surrogate thing is  a  fudge  for  UTF-16  which
+       Characters  in  the "Surrogate Area" of Unicode are reserved for use by
+       UTF-16, where they are used in pairs to encode code points with  values
+       greater  than  0xFFFF. The code points that are encoded by UTF-16 pairs
+       are available independently in the  UTF-8  and  UTF-32  encodings.  (In
+       other  words,  the  whole  surrogate  thing is a fudge for UTF-16 which
        unfortunately messes up UTF-8 and UTF-32.)


-       In  some  situations, you may already know that your strings are valid,
-       and therefore want to skip these checks in  order  to  improve  perfor-
-       mance,  for  example in the case of a long subject string that is being
-       scanned repeatedly.  If you set the PCRE2_NO_UTF_CHECK option  at  com-
-       pile  time  or at match time, PCRE2 assumes that the pattern or subject
+       In some situations, you may already know that your strings  are  valid,
+       and  therefore  want  to  skip these checks in order to improve perfor-
+       mance, for example in the case of a long subject string that  is  being
+       scanned  repeatedly.   If you set the PCRE2_NO_UTF_CHECK option at com-
+       pile time or at match time, PCRE2 assumes that the pattern  or  subject
        it is given (respectively) contains only valid UTF code unit sequences.


-       Passing PCRE2_NO_UTF_CHECK to pcre2_compile() just disables  the  check
+       Passing  PCRE2_NO_UTF_CHECK  to pcre2_compile() just disables the check
        for the pattern; it does not also apply to subject strings. If you want
-       to disable the check for a subject string you must pass this option  to
+       to  disable the check for a subject string you must pass this option to
        pcre2_match() or pcre2_dfa_match().


-       If  you  pass an invalid UTF string when PCRE2_NO_UTF_CHECK is set, the
+       If you pass an invalid UTF string when PCRE2_NO_UTF_CHECK is  set,  the
        result is undefined and your program may crash or loop indefinitely.


-       Note that setting PCRE2_NO_UTF_CHECK at compile time does  not  disable
-       the  error  that  is given if an escape sequence for an invalid Unicode
-       code point is encountered in the pattern. If you want to  allow  escape
-       sequences  such  as  \x{d800}  (a surrogate code point) you can set the
+       Note  that  setting PCRE2_NO_UTF_CHECK at compile time does not disable
+       the error that is given if an escape sequence for  an  invalid  Unicode
+       code  point  is encountered in the pattern. If you want to allow escape
+       sequences such as \x{d800} (a surrogate code point)  you  can  set  the
        PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES extra option. However, this is pos-
        sible only in UTF-8 and UTF-32 modes, because these values are not rep-
        resentable in UTF-16.
@@ -10951,10 +10958,10 @@
          PCRE2_ERROR_UTF8_ERR4
          PCRE2_ERROR_UTF8_ERR5


-       The string ends with a truncated UTF-8 character;  the  code  specifies
-       how  many bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8
-       characters to be no longer than 4 bytes, the  encoding  scheme  (origi-
-       nally  defined  by  RFC  2279)  allows  for  up to 6 bytes, and this is
+       The  string  ends  with a truncated UTF-8 character; the code specifies
+       how many bytes are missing (1 to 5). Although RFC 3629 restricts  UTF-8
+       characters  to  be  no longer than 4 bytes, the encoding scheme (origi-
+       nally defined by RFC 2279) allows for  up  to  6  bytes,  and  this  is
        checked first; hence the possibility of 4 or 5 missing bytes.


          PCRE2_ERROR_UTF8_ERR6
@@ -10964,24 +10971,24 @@
          PCRE2_ERROR_UTF8_ERR10


        The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of
-       the  character  do  not have the binary value 0b10 (that is, either the
+       the character do not have the binary value 0b10 (that  is,  either  the
        most significant bit is 0, or the next bit is 1).


          PCRE2_ERROR_UTF8_ERR11
          PCRE2_ERROR_UTF8_ERR12


-       A character that is valid by the RFC 2279 rules is either 5 or 6  bytes
+       A  character that is valid by the RFC 2279 rules is either 5 or 6 bytes
        long; these code points are excluded by RFC 3629.


          PCRE2_ERROR_UTF8_ERR13


-       A  4-byte character has a value greater than 0x10fff; these code points
+       A 4-byte character has a value greater than 0x10fff; these code  points
        are excluded by RFC 3629.


          PCRE2_ERROR_UTF8_ERR14


-       A 3-byte character has a value in the  range  0xd800  to  0xdfff;  this
-       range  of code points are reserved by RFC 3629 for use with UTF-16, and
+       A  3-byte  character  has  a  value in the range 0xd800 to 0xdfff; this
+       range of code points are reserved by RFC 3629 for use with UTF-16,  and
        so are excluded from UTF-8.


          PCRE2_ERROR_UTF8_ERR15
@@ -10990,26 +10997,26 @@
          PCRE2_ERROR_UTF8_ERR18
          PCRE2_ERROR_UTF8_ERR19


-       A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it  codes
-       for  a  value that can be represented by fewer bytes, which is invalid.
-       For example, the two bytes 0xc0, 0xae give the value 0x2e,  whose  cor-
+       A  2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes
+       for a value that can be represented by fewer bytes, which  is  invalid.
+       For  example,  the two bytes 0xc0, 0xae give the value 0x2e, whose cor-
        rect coding uses just one byte.


          PCRE2_ERROR_UTF8_ERR20


        The two most significant bits of the first byte of a character have the
-       binary value 0b10 (that is, the most significant bit is 1 and the  sec-
-       ond  is  0). Such a byte can only validly occur as the second or subse-
+       binary  value 0b10 (that is, the most significant bit is 1 and the sec-
+       ond is 0). Such a byte can only validly occur as the second  or  subse-
        quent byte of a multi-byte character.


          PCRE2_ERROR_UTF8_ERR21


-       The first byte of a character has the value 0xfe or 0xff. These  values
+       The  first byte of a character has the value 0xfe or 0xff. These values
        can never occur in a valid UTF-8 string.


    Errors in UTF-16 strings


-       The  following  negative  error  codes  are  given  for  invalid UTF-16
+       The following  negative  error  codes  are  given  for  invalid  UTF-16
        strings:


          PCRE2_ERROR_UTF16_ERR1  Missing low surrogate at end of string
@@ -11019,7 +11026,7 @@


    Errors in UTF-32 strings


-       The following  negative  error  codes  are  given  for  invalid  UTF-32
+       The  following  negative  error  codes  are  given  for  invalid UTF-32
        strings:


          PCRE2_ERROR_UTF32_ERR1  Surrogate character (0xd800 to 0xdfff)
@@ -11035,8 +11042,8 @@


REVISION

-       Last updated: 12 October 2018
-       Copyright (c) 1997-2018 University of Cambridge.
+       Last updated: 03 February 2019
+       Copyright (c) 1997-2019 University of Cambridge.
 ------------------------------------------------------------------------------




Modified: code/trunk/doc/pcre2_substring_nametable_scan.3
===================================================================
--- code/trunk/doc/pcre2_substring_nametable_scan.3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2_substring_nametable_scan.3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2_SUBSTRING_NAMETABLE_SCAN 3 "21 October 2014" "PCRE2 10.00"
+.TH PCRE2_SUBSTRING_NAMETABLE_SCAN 3 "03 February 2019" "PCRE2 10.33"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH SYNOPSIS
@@ -15,8 +15,8 @@
 .rs
 .sp
 This convenience function finds, for a compiled pattern, the first and last
-entries for a given name in the table that translates capturing parenthesis
-names into numbers.
+entries for a given name in the table that translates capture group names into
+numbers.
 .sp
   \fIcode\fP    Compiled regular expression
   \fIname\fP    Name whose entries required


Modified: code/trunk/doc/pcre2api.3
===================================================================
--- code/trunk/doc/pcre2api.3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2api.3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2API 3 "04 January 2019" "PCRE2 10.33"
+.TH PCRE2API 3 "04 February 2019" "PCRE2 10.33"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .sp
@@ -1429,10 +1429,10 @@
 .sp
   PCRE2_DUPNAMES
 .sp
-If this bit is set, names used to identify capturing subpatterns need not be
-unique. This can be helpful for certain types of pattern when it is known that
-only one instance of the named subpattern can ever be matched. There are more
-details of named subpatterns below; see also the
+If this bit is set, names used to identify capture groups need not be unique.
+This can be helpful for certain types of pattern when it is known that only one
+instance of the named group can ever be matched. There are more details of
+named capture groups below; see also the
 .\" HREF
 \fBpcre2pattern\fP
 .\"
@@ -1466,11 +1466,11 @@
 If this bit is set, most white space characters in the pattern are totally
 ignored except when escaped or inside a character class. However, white space
 is not allowed within sequences such as (?> that introduce various
-parenthesized subpatterns, nor within numerical quantifiers such as {1,3}.
-Ignorable white space is permitted between an item and a following quantifier
-and between a quantifier and a following + that indicates possessiveness.
-PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be changed within
-a pattern by a (?x) option setting.
+parenthesized groups, nor within numerical quantifiers such as {1,3}. Ignorable
+white space is permitted between an item and a following quantifier and between
+a quantifier and a following + that indicates possessiveness. PCRE2_EXTENDED is
+equivalent to Perl's /x option, and it can be changed within a pattern by a
+(?x) option setting.
 .P
 When PCRE2 is compiled without Unicode support, PCRE2_EXTENDED recognizes as
 white space only those characters with code points less than 256 that are
@@ -1547,7 +1547,7 @@
 .sp
   PCRE2_MATCH_UNSET_BACKREF
 .sp
-If this option is set, a backreference to an unset subpattern group matches an
+If this option is set, a backreference to an unset capture group matches an
 empty string (by default this causes the current matching alternative to fail).
 A pattern such as (\e1)(a) succeeds when this option is set (assuming it can
 find an "a" in the subject), whereas it fails by default, for Perl
@@ -1608,7 +1608,7 @@
 the pattern. Any opening parenthesis that is not followed by ? behaves as if it
 were followed by ?: but named parentheses can still be used for capturing (and
 they acquire numbers in the usual way). This is the same as Perl's /n option.
-Note that, when this option is set, references to capturing groups
+Note that, when this option is set, references to capture groups
 (backreferences or recursion/subroutine calls) may only refer to named groups,
 though the reference can be by name or by number.
 .sp
@@ -1627,7 +1627,7 @@
 If this option is set, it disables an optimization that is applied when .* is
 the first significant item in a top-level branch of a pattern, and all the
 other branches also start with .* or with \eA or \eG or ^. The optimization is
-automatically disabled for .* if it is inside an atomic group or a capturing
+automatically disabled for .* if it is inside an atomic group or a capture
 group that is the subject of a backreference, or if the pattern contains
 (*PRUNE) or (*SKIP). When the optimization is not disabled, such a pattern is
 automatically anchored if PCRE2_DOTALL is set for all the .* items and
@@ -2025,7 +2025,7 @@
 .sp
   .* is not in an atomic group
 .\" JOIN
-  .* is not in a capturing group that is the subject
+  .* is not in a capture group that is the subject
        of a backreference
   PCRE2_DOTALL is in force for .*
   Neither (*PRUNE) nor (*SKIP) appears in the pattern
@@ -2037,12 +2037,12 @@
   PCRE2_INFO_BACKREFMAX
 .sp
 Return the number of the highest backreference in the pattern. The third
-argument should point to an \fBuint32_t\fP variable. Named subpatterns acquire
-numbers as well as names, and these count towards the highest backreference.
-Backreferences such as \e4 or \eg{12} match the captured characters of the
-given group, but in addition, the check that a capturing group is set in a
-conditional subpattern such as (?(3)a|b) is also a backreference. Zero is
-returned if there are no backreferences.
+argument should point to an \fBuint32_t\fP variable. Named capture groups
+acquire numbers as well as names, and these count towards the highest
+backreference. Backreferences such as \e4 or \eg{12} match the captured
+characters of the given group, but in addition, the check that a capture
+group is set in a conditional group such as (?(3)a|b) is also a backreference.
+Zero is returned if there are no backreferences.
 .sp
   PCRE2_INFO_BSR
 .sp
@@ -2053,9 +2053,9 @@
 .sp
   PCRE2_INFO_CAPTURECOUNT
 .sp
-Return the highest capturing subpattern number in the pattern. In patterns
-where (?| is not used, this is also the total number of capturing subpatterns.
-The third argument should point to an \fBuint32_t\fP variable.
+Return the highest capture group number in the pattern. In patterns where (?|
+is not used, this is also the total number of capture groups. The third
+argument should point to an \fBuint32_t\fP variable.
 .sp
   PCRE2_INFO_DEPTHLIMIT
 .sp
@@ -2103,7 +2103,7 @@
 backtracking positions when the pattern is processed by \fBpcre2_match()\fP
 without the use of JIT. The third argument should point to a \fBsize_t\fP
 variable. The frame size depends on the number of capturing parentheses in the
-pattern. Each additional capturing group adds two PCRE2_SIZE variables.
+pattern. Each additional capture group adds two PCRE2_SIZE variables.
 .sp
   PCRE2_INFO_HASBACKSLASHC
 .sp
@@ -2224,11 +2224,11 @@
 the parenthesis number. The rest of the entry is the corresponding name, zero
 terminated.
 .P
-The names are in alphabetical order. If (?| is used to create multiple groups
-with the same number, as described in the
-.\" HTML <a href="pcre2pattern.html#dupsubpatternnumber">
+The names are in alphabetical order. If (?| is used to create multiple capture
+groups with the same number, as described in the
+.\" HTML <a href="pcre2pattern.html#dupgroupnumber">
 .\" </a>
-section on duplicate subpattern numbers
+section on duplicate group numbers
 .\"
 in the
 .\" HREF
@@ -2237,11 +2237,11 @@
 page, the groups may be given the same name, but there is only one entry in the
 table. Different names for groups of the same number are not permitted.
 .P
-Duplicate names for subpatterns with different numbers are permitted, but only
-if PCRE2_DUPNAMES is set. They appear in the table in the order in which they
-were found in the pattern. In the absence of (?| this is the order of
+Duplicate names for capture groups with different numbers are permitted, but
+only if PCRE2_DUPNAMES is set. They appear in the table in the order in which
+they were found in the pattern. In the absence of (?| this is the order of
 increasing number; when (?| is used this is not necessarily the case because
-later subpatterns may have lower numbers.
+later capture groups may have lower numbers.
 .P
 As a simple example of the name/number table, consider the following pattern
 after compilation by the 8-bit library (assume PCRE2_EXTENDED is set, so white
@@ -2251,9 +2251,9 @@
   (?<date> (?<year>(\ed\ed)?\ed\ed) -
   (?<month>\ed\ed) - (?<day>\ed\ed) )
 .sp
-There are four named subpatterns, so the table has four entries, and each entry
-in the table is eight bytes long. The table is as follows, with non-printing
-bytes shows in hexadecimal, and undefined bytes shown as ??:
+There are four named capture groups, so the table has four entries, and each
+entry in the table is eight bytes long. The table is as follows, with
+non-printing bytes shows in hexadecimal, and undefined bytes shown as ??:
 .sp
   00 01 d  a  t  e  00 ??
   00 05 d  a  y  00 ?? ??
@@ -2260,7 +2260,7 @@
   00 04 m  o  n  t  h  00
   00 02 y  e  a  r  00 ??
 .sp
-When writing code to extract data from named subpatterns using the
+When writing code to extract data from named capture groups using the
 name-to-number map, remember that the length of the entries is likely to be
 different for each compiled pattern.
 .sp
@@ -2740,12 +2740,12 @@
 In general, a pattern matches a certain portion of the subject, and in
 addition, further substrings from the subject may be picked out by
 parenthesized parts of the pattern. Following the usage in Jeffrey Friedl's
-book, this is called "capturing" in what follows, and the phrase "capturing
-subpattern" or "capturing group" is used for a fragment of a pattern that picks
-out a substring. PCRE2 supports several other kinds of parenthesized subpattern
-that do not cause substrings to be captured. The \fBpcre2_pattern_info()\fP
-function can be used to find out how many capturing subpatterns there are in a
-compiled pattern.
+book, this is called "capturing" in what follows, and the phrase "capture
+group" (Perl terminology) is used for a fragment of a pattern that picks out a
+substring. PCRE2 supports several other kinds of parenthesized group that do
+not cause substrings to be captured. The \fBpcre2_pattern_info()\fP function
+can be used to find out how many capture groups there are in a compiled
+pattern.
 .P
 You can use auxiliary functions for accessing captured substrings
 .\" HTML <a href="#extractbynumber">
@@ -2798,9 +2798,8 @@
 For example, if the pattern (?=ab\eK) is matched against "ab", the start and
 end offset values for the match are 2 and 0.
 .P
-If a capturing subpattern group is matched repeatedly within a single match
-operation, it is the last portion of the subject that it matched that is
-returned.
+If a capture group is matched repeatedly within a single match operation, it is
+the last portion of the subject that it matched that is returned.
 .P
 If the ovector is too small to hold all the captured substring offsets, as much
 as possible is filled in, and the function returns a value of zero. If captured
@@ -2807,21 +2806,20 @@
 substrings are not of interest, \fBpcre2_match()\fP may be called with a match
 data block whose ovector is of minimum length (that is, one pair).
 .P
-It is possible for capturing subpattern number \fIn+1\fP to match some part of
-the subject when subpattern \fIn\fP has not been used at all. For example, if
-the string "abc" is matched against the pattern (a|(z))(bc) the return from the
-function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
-happens, both values in the offset pairs corresponding to unused subpatterns
-are set to PCRE2_UNSET.
-.P
-Offset values that correspond to unused subpatterns at the end of the
-expression are also set to PCRE2_UNSET. For example, if the string "abc" is
-matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched.
-The return from the function is 2, because the highest used capturing
-subpattern number is 1. The offsets for for the second and third capturing
-subpatterns (assuming the vector is large enough, of course) are set to
+It is possible for capture group number \fIn+1\fP to match some part of the
+subject when group \fIn\fP has not been used at all. For example, if the string
+"abc" is matched against the pattern (a|(z))(bc) the return from the function
+is 4, and groups 1 and 3 are matched, but 2 is not. When this happens, both
+values in the offset pairs corresponding to unused groups are set to
 PCRE2_UNSET.
 .P
+Offset values that correspond to unused groups at the end of the expression are
+also set to PCRE2_UNSET. For example, if the string "abc" is matched against
+the pattern (abc)(x(yz)?)? groups 2 and 3 are not matched. The return from the
+function is 2, because the highest used capture group number is 1. The offsets
+for for the second and third capture groupss (assuming the vector is large
+enough, of course) are set to PCRE2_UNSET.
+.P
 Elements in the ovector that do not correspond to capturing parentheses in the
 pattern are never changed. That is, if a pattern contains \fIn\fP capturing
 parentheses, no more than \fIovector[0]\fP to \fIovector[2n+1]\fP are set by
@@ -3006,11 +3004,11 @@
 .sp
 This error is returned when \fBpcre2_match()\fP detects a recursion loop within
 the pattern. Specifically, it means that either the whole pattern or a
-subpattern has been called recursively for the second time at the same position
-in the subject string. Some simple patterns that might do this are detected and
-faulted at compile time, but more complicated cases, in particular mutual
-recursions between two different subpatterns, cannot be detected until matching
-is attempted.
+capture group has been called recursively for the second time at the same
+position in the subject string. Some simple patterns that might do this are
+detected and faulted at compile time, but more complicated cases, in particular
+mutual recursions between two different groups, cannot be detected until
+matching is attempted.
 .
 .
 .\" HTML <a name="geterrormessage"></a>
@@ -3090,7 +3088,7 @@
 into a supplied buffer, whereas \fBpcre2_substring_get_bynumber()\fP copies it
 into new memory, obtained using the same memory allocation function that was
 used for the match data block. The first two arguments of these functions are a
-pointer to the match data block and a capturing group number.
+pointer to the match data block and a capture group number.
 .P
 The final arguments of \fBpcre2_substring_copy_bynumber()\fP are a pointer to
 the buffer and a pointer to a variable that contains its length in code units.
@@ -3162,9 +3160,9 @@
 calling \fBpcre2_substring_list_free()\fP.
 .P
 If this function encounters a substring that is unset, which can happen when
-capturing subpattern number \fIn+1\fP matches some part of the subject, but
-subpattern \fIn\fP has not been used at all, it returns an empty string. This
-can be distinguished from a genuine zero-length substring by inspecting the
+capture group number \fIn+1\fP matches some part of the subject, but group
+\fIn\fP has not been used at all, it returns an empty string. This can be
+distinguished from a genuine zero-length substring by inspecting the
 appropriate offset in the ovector, which contain PCRE2_UNSET for unset
 substrings, or by calling \fBpcre2_substring_length_bynumber()\fP.
 .
@@ -3194,20 +3192,20 @@
 .sp
   (a+)b(?<xxx>\ed+)...
 .sp
-the number of the subpattern called "xxx" is 2. If the name is known to be
+the number of the capture group called "xxx" is 2. If the name is known to be
 unique (PCRE2_DUPNAMES was not set), you can find the number from the name by
 calling \fBpcre2_substring_number_from_name()\fP. The first argument is the
 compiled pattern, and the second is the name. The yield of the function is the
-subpattern number, PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that
-name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of
-that name. Given the number, you can extract the substring directly from the
-ovector, or use one of the "bynumber" functions described above.
+group number, PCRE2_ERROR_NOSUBSTRING if there is no group with that name, or
+PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one group with that name.
+Given the number, you can extract the substring directly from the ovector, or
+use one of the "bynumber" functions described above.
 .P
 For convenience, there are also "byname" functions that correspond to the
 "bynumber" functions, the only difference being that the second argument is a
 name instead of a number. If PCRE2_DUPNAMES is set and there are duplicate
 names, these functions scan all the groups with the given name, and return the
-first named string that is set.
+captured substring from the first named group that is set.
 .P
 If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is
 returned. If all groups with the name have numbers that are greater than the
@@ -3216,18 +3214,18 @@
 set, PCRE2_ERROR_UNSET is returned.
 .P
 \fBWarning:\fP If the pattern uses the (?| feature to set up multiple
-subpatterns with the same number, as described in the
-.\" HTML <a href="pcre2pattern.html#dupsubpatternnumber">
+capture groups with the same number, as described in the
+.\" HTML <a href="pcre2pattern.html#dupgroupnumber">
 .\" </a>
-section on duplicate subpattern numbers
+section on duplicate group numbers
 .\"
 in the
 .\" HREF
 \fBpcre2pattern\fP
 .\"
-page, you cannot use names to distinguish the different subpatterns, because
+page, you cannot use names to distinguish the different capture groups, because
 names are not included in the compiled code. The matching process uses only
-numbers. For this reason, the use of different names for subpatterns of the
+numbers. For this reason, the use of different names for groups with the
 same number causes an error at compile time.
 .
 .
@@ -3288,7 +3286,7 @@
 In the replacement string, which is interpreted as a UTF string in UTF mode,
 and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK option is set, a
 dollar character is an escape character that can specify the insertion of
-characters from capturing groups or names from (*MARK) or other control verbs
+characters from capture groups or names from (*MARK) or other control verbs
 in the pattern. The following forms are always recognized:
 .sp
   $$                  insert a dollar character
@@ -3351,12 +3349,12 @@
 efficient to allocate a large buffer and free the excess afterwards, instead of
 using PCRE2_SUBSTITUTE_OVERFLOW_LENGTH.
 .P
-PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capturing groups that do
+PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capture groups that do
 not appear in the pattern to be treated as unset groups. This option should be
 used with care, because it means that a typo in a group name or number no
 longer causes the PCRE2_ERROR_NOSUBSTRING error.
 .P
-PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capturing groups (including unknown
+PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capture groups (including unknown
 groups when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) to be treated as empty
 strings when inserted as described above. If this option is not set, an attempt
 to insert an unset group causes the PCRE2_ERROR_UNSET error. This option does
@@ -3381,7 +3379,7 @@
 \eu and \el force the next character (if it is a letter) to upper or lower
 case, respectively, and then the state automatically reverts to no case
 forcing. Case forcing applies to all inserted  characters, including those from
-captured groups and letters within \eQ...\eE quoted sequences.
+capture groups and letters within \eQ...\eE quoted sequences.
 .P
 Note that case forcing sequences such as \eU...\eE do not nest. For example,
 the result of processing "\eUaa\eLBB\eEcc\eE" is "AAbbcc"; the final \eE has no
@@ -3388,7 +3386,8 @@
 effect.
 .P
 The second effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more
-flexibility to group substitution. The syntax is similar to that used by Bash:
+flexibility to capture group substitution. The syntax is similar to that used
+by Bash:
 .sp
   ${<n>:-<string>}
   ${<n>:+<string1>:<string2>}
@@ -3510,7 +3509,7 @@
 matches so far.
 .
 .
-.SH "DUPLICATE SUBPATTERN NAMES"
+.SH "DUPLICATE CAPTURE GROUP NAMES"
 .rs
 .sp
 .nf
@@ -3518,13 +3517,14 @@
 .B "  PCRE2_SPTR \fIname\fP, PCRE2_SPTR *\fIfirst\fP, PCRE2_SPTR *\fIlast\fP);"
 .fi
 .P
-When a pattern is compiled with the PCRE2_DUPNAMES option, names for
-subpatterns are not required to be unique. Duplicate names are always allowed
-for subpatterns with the same number, created by using the (?| feature. Indeed,
-if such subpatterns are named, they are required to use the same names.
+When a pattern is compiled with the PCRE2_DUPNAMES option, names for capture
+groups are not required to be unique. Duplicate names are always allowed for
+groups with the same number, created by using the (?| feature. Indeed, if such
+groups are named, they are required to use the same names.
 .P
-Normally, patterns with duplicate names are such that in any one match, only
-one of the named subpatterns participates. An example is shown in the
+Normally, patterns that use duplicate names are such that in any one match,
+only one of each set of identically-named groups participates. An example is
+shown in the
 .\" HREF
 \fBpcre2pattern\fP
 .\"
@@ -3705,9 +3705,8 @@
 On success, the yield of the function is a number greater than zero, which is
 the number of matched substrings. The offsets of the substrings are returned in
 the ovector, and can be extracted by number in the same way as for
-\fBpcre2_match()\fP, but the numbers bear no relation to any capturing groups
-that may exist in the pattern, because DFA matching does not support group
-capture.
+\fBpcre2_match()\fP, but the numbers bear no relation to any capture groups
+that may exist in the pattern, because DFA matching does not support capturing.
 .P
 Calls to the convenience functions that extract substrings by name
 return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used after a
@@ -3749,7 +3748,7 @@
 .sp
 This return is given if \fBpcre2_dfa_match()\fP encounters a condition item
 that uses a backreference for the condition, or a test for recursion in a
-specific group. These are not supported.
+specific capture group. These are not supported.
 .sp
   PCRE2_ERROR_DFA_WSSIZE
 .sp
@@ -3758,9 +3757,9 @@
 .sp
   PCRE2_ERROR_DFA_RECURSE
 .sp
-When a recursive subpattern is processed, the matching function calls itself
-recursively, using private memory for the ovector and \fIworkspace\fP. This
-error is given if the internal ovector is not large enough. This should be
+When a recursion or subroutine call is processed, the matching function calls
+itself recursively, using private memory for the ovector and \fIworkspace\fP.
+This error is given if the internal ovector is not large enough. This should be
 extremely rare, as a vector of size 1000 is used.
 .sp
   PCRE2_ERROR_DFA_BADRESTART
@@ -3793,6 +3792,6 @@
 .rs
 .sp
 .nf
-Last updated: 04 January 2019
+Last updated: 04 February 2019
 Copyright (c) 1997-2019 University of Cambridge.
 .fi


Modified: code/trunk/doc/pcre2callout.3
===================================================================
--- code/trunk/doc/pcre2callout.3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2callout.3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2CALLOUT 3 "17 September 2018" "PCRE2 10.33"
+.TH PCRE2CALLOUT 3 "03 February 2019" "PCRE2 10.33"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH SYNOPSIS
@@ -137,7 +137,7 @@
 branch, automatic anchoring occurs if all branches are anchorable.
 .P
 This optimization is disabled, however, if .* is in an atomic group or if there
-is a backreference to the capturing group in which it appears. It is also
+is a backreference to the capture group in which it appears. It is also
 disabled if the pattern contains (*PRUNE) or (*SKIP). However, the presence of
 callouts does not affect it.
 .P
@@ -331,8 +331,8 @@
 alternation bar or a closing parenthesis, the length is one, unless a closing
 parenthesis is followed by a quantifier, in which case its length is included.
 (This changed in release 10.23. In earlier releases, before an opening
-parenthesis the length was that of the entire subpattern, and before an
-alternation bar or a closing parenthesis the length was zero.)
+parenthesis the length was that of the entire group, and before an alternation
+bar or a closing parenthesis the length was zero.)
 .P
 The \fIpattern_position\fP and \fInext_item_length\fP fields are intended to
 help in distinguishing between different automatic callouts, which all have the
@@ -452,6 +452,6 @@
 .rs
 .sp
 .nf
-Last updated: 17 September 2018
-Copyright (c) 1997-2018 University of Cambridge.
+Last updated: 03 February 2019
+Copyright (c) 1997-2019 University of Cambridge.
 .fi


Modified: code/trunk/doc/pcre2compat.3
===================================================================
--- code/trunk/doc/pcre2compat.3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2compat.3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2COMPAT 3 "28 July 2018" "PCRE2 10.32"
+.TH PCRE2COMPAT 3 "03 February 2019" "PCRE2 10.33"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "DIFFERENCES BETWEEN PCRE2 AND PERL"
@@ -23,10 +23,9 @@
 assertion just once). Perl allows some repeat quantifiers on other assertions,
 for example, \eb* (but not \eb{3}), but these do not seem to have any use.
 .P
-3. Capturing subpatterns that occur inside negative lookaround assertions are
-counted, but their entries in the offsets vector are set only when a negative
-assertion is a condition that has a matching branch (that is, the condition is
-false).
+3. Capture groups that occur inside negative lookaround assertions are counted,
+but their entries in the offsets vector are set only when a negative assertion
+is a condition that has a matching branch (that is, the condition is false).
 .P
 4. The following Perl escape sequences are not supported: \eF, \el, \eL, \eu,
 \eU, and \eN when followed by a character name. \eN on its own, matching a
@@ -79,13 +78,13 @@
 to PCRE2 release 10.23, but from release 10.30 this changed, and backtracking
 into subroutine calls is now supported, as in Perl.
 .P
-9. If any of the backtracking control verbs are used in a subpattern that is
-called as a subroutine (whether or not recursively), their effect is confined
-to that subpattern; it does not extend to the surrounding pattern. This is not
-always the case in Perl. In particular, if (*THEN) is present in a group that
-is called as a subroutine, its action is limited to that group, even if the
-group does not contain any | characters. Note that such subpatterns are
-processed as anchored at the point where they are tested.
+9. If any of the backtracking control verbs are used in a group that is called
+as a subroutine (whether or not recursively), their effect is confined to that
+group; it does not extend to the surrounding pattern. This is not always the
+case in Perl. In particular, if (*THEN) is present in a group that is called as
+a subroutine, its action is limited to that group, even if the group does not
+contain any | characters. Note that such groups are processed as anchored
+at the point where they are tested.
 .P
 10. If a pattern contains more than one backtracking control verb, the first
 one that is backtracked onto acts. For example, in the pattern
@@ -101,21 +100,20 @@
 the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE2 it is set to
 "b".
 .P
-13. PCRE2's handling of duplicate subpattern numbers and duplicate subpattern
-names is not as general as Perl's. This is a consequence of the fact the PCRE2
-works internally just with numbers, using an external table to translate
-between numbers and names. In particular, a pattern such as (?|(?<a>A)|(?<b>B),
-where the two capturing parentheses have the same number but different names,
-is not supported, and causes an error at compile time. If it were allowed, it
-would not be possible to distinguish which parentheses matched, because both
-names map to capturing subpattern number 1. To avoid this confusing situation,
-an error is given at compile time.
+13. PCRE2's handling of duplicate capture group numbers and names is not as
+general as Perl's. This is a consequence of the fact the PCRE2 works internally
+just with numbers, using an external table to translate between numbers and
+names. In particular, a pattern such as (?|(?<a>A)|(?<b>B), where the two
+capture groups have the same number but different names, is not supported, and
+causes an error at compile time. If it were allowed, it would not be possible
+to distinguish which group matched, because both names map to capture group
+number 1. To avoid this confusing situation, an error is given at compile time.
 .P
 14. Perl used to recognize comments in some places that PCRE2 does not, for
-example, between the ( and ? at the start of a subpattern. If the /x modifier
-is set, Perl allowed white space between ( and ? though the latest Perls give
-an error (for a while it was just deprecated). There may still be some cases
-where Perl behaves differently.
+example, between the ( and ? at the start of a group. If the /x modifier is
+set, Perl allowed white space between ( and ? though the latest Perls give an
+error (for a while it was just deprecated). There may still be some cases where
+Perl behaves differently.
 .P
 15. Perl, when in warning mode, gives warnings for character classes such as
 [A-\ed] or [a-[:digit:]]. It then treats the hyphens as literals. PCRE2 has no
@@ -200,6 +198,6 @@
 .rs
 .sp
 .nf
-Last updated: 28 July 2018
-Copyright (c) 1997-2018 University of Cambridge.
+Last updated: 03 February 2019
+Copyright (c) 1997-2019 University of Cambridge.
 .fi


Modified: code/trunk/doc/pcre2limits.3
===================================================================
--- code/trunk/doc/pcre2limits.3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2limits.3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2LIMITS 3 "30 March 2017" "PCRE2 10.30"
+.TH PCRE2LIMITS 3 "03 February 2019" "PCRE2 10.33"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "SIZE AND OTHER LIMITATIONS"
@@ -34,16 +34,16 @@
 .P
 The maximum length of a lookbehind assertion is 65535 characters.
 .P
-There is no limit to the number of parenthesized subpatterns, but there can be
-no more than 65535 capturing subpatterns. There is, however, a limit to the
-depth of nesting of parenthesized subpatterns of all kinds. This is imposed in
-order to limit the amount of system stack used at compile time. The default
-limit can be specified when PCRE2 is built; if not, the default is set to 250.
-An application can change this limit by calling pcre2_set_parens_nest_limit()
-to set the limit in a compile context.
+There is no limit to the number of parenthesized groups, but there can be no
+more than 65535 capture groups, and there is a limit to the depth of nesting of
+parenthesized subpatterns of all kinds. This is imposed in order to limit the
+amount of system stack used at compile time. The default limit can be specified
+when PCRE2 is built; if not, the default is set to 250. An application can
+change this limit by calling pcre2_set_parens_nest_limit() to set the limit in
+a compile context.
 .P
-The maximum length of name for a named subpattern is 32 code units, and the
-maximum number of named subpatterns is 10000.
+The maximum length of name for a named capture group is 32 code units, and the
+maximum number of such groups is 10000.
 .P
 The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb
 is 255 code units for the 8-bit library and 65535 code units for the 16-bit and
@@ -67,6 +67,6 @@
 .rs
 .sp
 .nf
-Last updated: 30 March 2017
-Copyright (c) 1997-2017 University of Cambridge.
+Last updated: 02 February 2019
+Copyright (c) 1997-2019 University of Cambridge.
 .fi


Modified: code/trunk/doc/pcre2pattern.3
===================================================================
--- code/trunk/doc/pcre2pattern.3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2pattern.3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2PATTERN 3 "27 November 2018" "PCRE2 10.33"
+.TH PCRE2PATTERN 3 "04 February 2019" "PCRE2 10.33"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 REGULAR EXPRESSION DETAILS"
@@ -20,13 +20,13 @@
 by O'Reilly, covers regular expressions in great detail. This description of
 PCRE2's regular expressions is intended as reference material.
 .P
-This document discusses the patterns that are supported by PCRE2 when its main
-matching function, \fBpcre2_match()\fP, is used. PCRE2 also has an alternative
-matching function, \fBpcre2_dfa_match()\fP, which matches using a different
-algorithm that is not Perl-compatible. Some of the features discussed below are
-not available when DFA matching is used. The advantages and disadvantages of
-the alternative function, and how it differs from the normal function, are
-discussed in the
+This document discusses the regular expression patterns that are supported by
+PCRE2 when its main matching function, \fBpcre2_match()\fP, is used. PCRE2 also
+has an alternative matching function, \fBpcre2_dfa_match()\fP, which matches
+using a different algorithm that is not Perl-compatible. Some of the features
+discussed below are not available when DFA matching is used. The advantages and
+disadvantages of the alternative function, and how it differs from the normal
+function, are discussed in the
 .\" HREF
 \fBpcre2matching\fP
 .\"
@@ -149,8 +149,8 @@
 also an explicit memory limit that can be set.
 .P
 These facilities are provided to catch runaway matches that are provoked by
-patterns with huge matching trees (a typical example is a pattern with nested
-unlimited repeats applied to a long string that does not match). When one of
+patterns with huge matching trees. A common example is a pattern with nested
+unlimited repeats applied to a long string that does not match. When one of
 these limits is reached, \fBpcre2_match()\fP gives an error return. The limits
 can also be set by items at the start of the pattern of the form
 .sp
@@ -264,10 +264,10 @@
 caseless matching is specified (the PCRE2_CASELESS option), letters are matched
 independently of case.
 .P
-The power of regular expressions comes from the ability to include alternatives
-and repetitions in the pattern. These are encoded in the pattern by the use of
-\fImetacharacters\fP, which do not stand for themselves but instead are
-interpreted in some special way.
+The power of regular expressions comes from the ability to include wild cards,
+character classes, alternatives, and repetitions in the pattern. These are
+encoded in the pattern by the use of \fImetacharacters\fP, which do not stand
+for themselves but instead are interpreted in some special way.
 .P
 There are two different sets of metacharacters: those that are recognized
 anywhere in the pattern except within square brackets, and those that are
@@ -280,14 +280,11 @@
   .      match any character except newline (by default)
   [      start character class definition
   |      start of alternative branch
-  (      start subpattern
-  )      end subpattern
-  ?      extends the meaning of (
-         also 0 or 1 quantifier
-         also quantifier minimizer
+  (      start group or control verb
+  )      end group or control verb
   *      0 or more quantifier
-  +      1 or more quantifier
-         also "possessive quantifier"
+  +      1 or more quantifier; also "possessive quantifier"
+  ?      0 or 1 quantifier; also quantifier minimizer
   {      start min/max quantifier
 .sp
 Part of a pattern that is in square brackets is called a "character class". In
@@ -296,9 +293,7 @@
   \e      general escape character
   ^      negate the class, but only if the first character
   -      indicates character range
-.\" JOIN
-  [      POSIX character class (only if followed by POSIX
-           syntax)
+  [      POSIX character class (if followed by POSIX syntax)
   ]      terminates the character class
 .sp
 The following sections describe the use of each of the metacharacters.
@@ -308,7 +303,7 @@
 .rs
 .sp
 The backslash character has several uses. Firstly, if it is followed by a
-character that is not a number or a letter, it takes away any special meaning
+character that is not a digit or a letter, it takes away any special meaning
 that character may have. This use of backslash as an escape character applies
 both inside and outside character classes.
 .P
@@ -318,7 +313,7 @@
 precede a non-alphanumeric with backslash to specify that it stands for itself.
 In particular, if you want to match a backslash, you write \e\e.
 .P
-In a UTF mode, only ASCII numbers and letters have any special meaning after a
+In a UTF mode, only ASCII digits and letters have any special meaning after a
 backslash. All other characters (in particular, those whose code points are
 greater than 127) are treated as literals.
 .P
@@ -328,13 +323,13 @@
 escaping backslash can be used to include a white space or # character as part
 of the pattern.
 .P
-If you want to remove the special meaning from a sequence of characters, you
-can do so by putting them between \eQ and \eE. This is different from Perl in
-that $ and @ are handled as literals in \eQ...\eE sequences in PCRE2, whereas
-in Perl, $ and @ cause variable interpolation. Also, Perl does "double-quotish
-backslash interpolation" on any backslashes between \eQ and \eE which, its
-documentation says, "may lead to confusing results". PCRE2 treats a backslash
-between \eQ and \eE just like any other character. Note the following examples:
+If you want to treat all characters in a sequence as literals, you can do so by
+putting them between \eQ and \eE. This is different from Perl in that $ and @
+are handled as literals in \eQ...\eE sequences in PCRE2, whereas in Perl, $ and
+@ cause variable interpolation. Also, Perl does "double-quotish backslash
+interpolation" on any backslashes between \eQ and \eE which, its documentation
+says, "may lead to confusing results". PCRE2 treats a backslash between \eQ and
+\eE just like any other character. Note the following examples:
 .sp
   Pattern            PCRE2 matches   Perl matches
 .sp
@@ -362,8 +357,8 @@
 in patterns in a visible manner. There is no restriction on the appearance of
 non-printing characters in a pattern, but when a pattern is being prepared by
 text editing, it is often easier to use one of the following escape sequences
-than the binary character it represents. In an ASCII or Unicode environment,
-these escapes are as follows:
+instead of the binary character it represents. In an ASCII or Unicode
+environment, these escapes are as follows:
 .sp
   \ea          alarm, that is, the BEL character (hex 07)
   \ecx         "control-x", where x is any printable ASCII character
@@ -441,17 +436,17 @@
 .P
 Outside a character class, PCRE2 reads the digit and any following digits as a
 decimal number. If the number is less than 10, begins with the digit 8 or 9, or
-if there are at least that many previous capturing left parentheses in the
-expression, the entire sequence is taken as a \fIbackreference\fP. A
-description of how this works is given
+if there are at least that many previous capture groups in the expression, the
+entire sequence is taken as a \fIbackreference\fP. A description of how this
+works is given
 .\" HTML <a href="#backreferences">
 .\" </a>
 later,
 .\"
 following the discussion of
-.\" HTML <a href="#subpattern">
+.\" HTML <a href="#group">
 .\" </a>
-parenthesized subpatterns.
+parenthesized groups.
 .\"
 Otherwise, up to three octal digits are read to form a character code.
 .P
@@ -463,7 +458,7 @@
   \e040   is another way of writing an ASCII space
 .\" JOIN
   \e40    is the same, provided there are fewer than 40
-            previous capturing subpatterns
+            previous capture groups
   \e7     is always a backreference
 .\" JOIN
   \e11    might be a backreference, or another way of
@@ -493,7 +488,9 @@
 described only when it is followed by two hexadecimal digits. Otherwise, it
 matches a literal "x" character. In this mode, support for code points greater
 than 256 is provided by \eu, which must be followed by four hexadecimal digits;
-otherwise it matches a literal "u" character.
+otherwise it matches a literal "u" character. This syntax makes PCRE2 behave 
+like ECMAscript (aka JavaScript). Code points greater than 0xFFFF are not
+supported.
 .P
 Characters whose value is less than 256 can be defined by either of the two
 syntaxes for \ex (or by \eu in PCRE2_ALT_BSUX mode). There is no difference in
@@ -553,9 +550,9 @@
 later,
 .\"
 following the discussion of
-.\" HTML <a href="#subpattern">
+.\" HTML <a href="#group">
 .\" </a>
-parenthesized subpatterns.
+parenthesized groups.
 .\"
 .
 .
@@ -564,7 +561,7 @@
 .sp
 For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or
 a number enclosed either in angle brackets or single quotes, is an alternative
-syntax for referencing a subpattern as a "subroutine". Details are discussed
+syntax for referencing a capture group as a subroutine. Details are discussed
 .\" HTML <a href="#onigurumasubroutines">
 .\" </a>
 later.
@@ -571,7 +568,7 @@
 .\"
 Note that \eg{...} (Perl syntax) and \eg<...> (Oniguruma syntax) are \fInot\fP
 synonymous. The former is a backreference; the latter is a
-.\" HTML <a href="#subpatternsassubroutines">
+.\" HTML <a href="#groupsassubroutines">
 .\" </a>
 subroutine
 .\"
@@ -751,21 +748,22 @@
 .rs
 .sp
 When PCRE2 is built with Unicode support (the default), three additional escape
-sequences that match characters with specific properties are available. In
-8-bit non-UTF-8 mode, these sequences are of course limited to testing
-characters whose code points are less than 256, but they do work in this mode.
-In 32-bit non-UTF mode, code points greater than 0x10ffff (the Unicode limit)
-may be encountered. These are all treated as being in the Unknown script and
-with an unassigned type. The extra escape sequences are:
+sequences that match characters with specific properties are available. They
+can be used in any mode, though in 8-bit and 16-bit non-UTF modes these
+sequences are of course limited to testing characters whose code points are
+less than U+0100 and U+10000, respectively. In 32-bit non-UTF mode, code points
+greater than 0x10ffff (the Unicode limit) may be encountered. These are all
+treated as being in the Unknown script and with an unassigned type. The extra
+escape sequences are:
 .sp
   \ep{\fIxx\fP}   a character with the \fIxx\fP property
   \eP{\fIxx\fP}   a character without the \fIxx\fP property
   \eX       a Unicode extended grapheme cluster
 .sp
-The property names represented by \fIxx\fP above are limited to the Unicode
-script names, the general category properties, "Any", which matches any
-character (including newline), and some special PCRE2 properties (described
-in the
+The property names represented by \fIxx\fP above are case-sensitive. There is
+support for Unicode script names, Unicode general category properties, "Any",
+which matches any character (including newline), and some special PCRE2
+properties (described in the
 .\" HTML <a href="#extraprops">
 .\" </a>
 next section).
@@ -999,14 +997,16 @@
 the Lu, Ll, or Lt property, in other words, a letter that is not classified as
 a modifier or "other".
 .P
-The Cs (Surrogate) property applies only to characters in the range U+D800 to
-U+DFFF. Such characters are not valid in Unicode strings and so
-cannot be tested by PCRE2, unless UTF validity checking has been turned off
-(see the discussion of PCRE2_NO_UTF_CHECK in the
+The Cs (Surrogate) property applies only to characters whose code points are in
+the range U+D800 to U+DFFF. These characters are no different to any other
+character when PCRE2 is not in UTF mode (using the 16-bit or 32-bit library).
+However, they are not valid in Unicode strings and so cannot be tested by PCRE2
+in UTF mode, unless UTF validity checking has been turned off (see the
+discussion of PCRE2_NO_UTF_CHECK in the
 .\" HREF
 \fBpcre2api\fP
 .\"
-page). Perl does not support the Cs property.
+page).
 .P
 The long synonyms for property names that Perl supports (such as \ep{Letter})
 are not supported by PCRE2, nor is it permitted to prefix any of these
@@ -1130,7 +1130,7 @@
 However, in this case, the part of the subject before the real match does not
 have to be of fixed length, as lookbehind assertions do. The use of \eK does
 not interfere with the setting of
-.\" HTML <a href="#subpattern">
+.\" HTML <a href="#group">
 .\" </a>
 captured substrings.
 .\"
@@ -1161,7 +1161,7 @@
 The final use of backslash is for certain simple assertions. An assertion
 specifies a condition that has to be met at a particular point in a match,
 without consuming any characters from the subject string. The use of
-subpatterns for more complicated assertions is described
+groups for more complicated assertions is described
 .\" HTML <a href="#bigassertions">
 .\" </a>
 below.
@@ -1183,12 +1183,12 @@
 A word boundary is a position in the subject string where the current character
 and the previous character do not both match \ew or \eW (i.e. one matches
 \ew and the other matches \eW), or the start or end of the string if the
-first or last character matches \ew, respectively. In a UTF mode, the meanings
-of \ew and \eW can be changed by setting the PCRE2_UCP option. When this is
-done, it also affects \eb and \eB. Neither PCRE2 nor Perl has a separate "start
-of word" or "end of word" metasequence. However, whatever follows \eb normally
-determines which it is. For example, the fragment \eba matches "a" at the start
-of a word.
+first or last character matches \ew, respectively. When PCRE2 is built with 
+Unicode support, the meanings of \ew and \eW can be changed by setting the
+PCRE2_UCP option. When this is done, it also affects \eb and \eB. Neither PCRE2
+nor Perl has a separate "start of word" or "end of word" metasequence. However,
+whatever follows \eb normally determines which it is. For example, the fragment
+\eba matches "a" at the start of a word.
 .P
 The \eA, \eZ, and \ez assertions differ from the traditional circumflex and
 dollar (described in the next section) in that they only ever match at the very
@@ -1380,9 +1380,9 @@
 .sp
 In this example, a group that starts with (?| resets the capturing parentheses
 numbers in each alternative (see
-.\" HTML <a href="#dupsubpatternnumber">
+.\" HTML <a href="#dupgroupnumber">
 .\" </a>
-"Duplicate Subpattern Numbers"
+"Duplicate Group Numbers"
 .\"
 below). The assertions at the start of each branch check the next UTF-8
 character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The
@@ -1624,13 +1624,13 @@
 matches either "gilbert" or "sullivan". Any number of alternatives may appear,
 and an empty alternative is permitted (matching the empty string). The matching
 process tries each alternative in turn, from left to right, and the first one
-that succeeds is used. If the alternatives are within a subpattern
-.\" HTML <a href="#subpattern">
+that succeeds is used. If the alternatives are within a group
+.\" HTML <a href="#group">
 .\" </a>
 (defined below),
 .\"
 "succeeds" means matching the rest of the main pattern as well as the
-alternative in the subpattern.
+alternative in the group.
 .
 .
 .SH "INTERNAL OPTION SETTING"
@@ -1673,9 +1673,9 @@
 respectively. However, these are not unset by (?^).
 .P
 When one of these option changes occurs at top level (that is, not inside
-subpattern parentheses), the change applies to the remainder of the pattern
-that follows. An option change within a subpattern (see below for a description
-of subpatterns) affects only that part of the subpattern that follows it, so
+group parentheses), the change applies to the remainder of the pattern
+that follows. An option change within a group (see below for a description
+of groups) affects only that part of the group that follows it, so
 .sp
   (a(?i)b)c
 .sp
@@ -1682,7 +1682,7 @@
 matches abc and aBc and no other strings (assuming PCRE2_CASELESS is not used).
 By this means, options can be made to have different settings in different
 parts of the pattern. Any changes made in one alternative do carry on
-into subsequent branches within the same subpattern. For example,
+into subsequent branches within the same group. For example,
 .sp
   (a(?i)b|c)
 .sp
@@ -1692,7 +1692,7 @@
 behaviour otherwise.
 .P
 As a convenient shorthand, if any option settings are required at the start of
-a non-capturing subpattern (see the next section), the option letters may
+a non-capturing group (see the next section), the option letters may
 appear between the "?" and the ":". Thus the two patterns
 .sp
   (?i:saturday|sunday)
@@ -1700,10 +1700,11 @@
 .sp
 match exactly the same set of strings.
 .P
-\fBNote:\fP There are other PCRE2-specific options that can be set by the
-application when the compiling function is called. The pattern can contain
-special leading sequences such as (*CRLF) to override what the application has
-set or what has been defaulted. Details are given in the section entitled
+\fBNote:\fP There are other PCRE2-specific options, applying to the whole
+pattern, which can be set by the application when the compiling function is
+called. In addition, the pattern can contain special leading sequences such as
+(*CRLF) to override what the application has set or what has been defaulted.
+Details are given in the section entitled
 .\" HTML <a href="#newlineseq">
 .\" </a>
 "Newline sequences"
@@ -1715,12 +1716,12 @@
 (*UTF) and (*UCP) sequences.
 .
 .
-.\" HTML <a name="subpattern"></a>
-.SH SUBPATTERNS
+.\" HTML <a name="group"></a>
+.SH GROUPS
 .rs
 .sp
-Subpatterns are delimited by parentheses (round brackets), which can be nested.
-Turning part of a pattern into a subpattern does two things:
+Groups are delimited by parentheses (round brackets), which can be nested.
+Turning part of a pattern into a group does two things:
 .sp
 1. It localizes a set of alternatives. For example, the pattern
 .sp
@@ -1729,15 +1730,15 @@
 matches "cataract", "caterpillar", or "cat". Without the parentheses, it would
 match "cataract", "erpillar" or an empty string.
 .sp
-2. It sets up the subpattern as a capturing subpattern. This means that, when
-the whole pattern matches, the portion of the subject string that matched the
-subpattern is passed back to the caller, separately from the portion that
-matched the whole pattern. (This applies only to the traditional matching
-function; the DFA matching function does not support capturing.)
+2. It creates a "capture group". This means that, when the whole pattern
+matches, the portion of the subject string that matched the group is passed
+back to the caller, separately from the portion that matched the whole pattern.
+(This applies only to the traditional matching function; the DFA matching
+function does not support capturing.)
 .P
 Opening parentheses are counted from left to right (starting from 1) to obtain
-numbers for the capturing subpatterns. For example, if the string "the red
-king" is matched against the pattern
+numbers for capture groups. For example, if the string "the red king" is
+matched against the pattern
 .sp
   the ((red|white) (king|queen))
 .sp
@@ -1745,38 +1746,37 @@
 2, and 3, respectively.
 .P
 The fact that plain parentheses fulfil two functions is not always helpful.
-There are often times when a grouping subpattern is required without a
-capturing requirement. If an opening parenthesis is followed by a question mark
-and a colon, the subpattern does not do any capturing, and is not counted when
-computing the number of any subsequent capturing subpatterns. For example, if
-the string "the white queen" is matched against the pattern
+There are often times when grouping is required without capturing. If an
+opening parenthesis is followed by a question mark and a colon, the group
+does not do any capturing, and is not counted when computing the number of any
+subsequent capture groups. For example, if the string "the white queen"
+is matched against the pattern
 .sp
   the ((?:red|white) (king|queen))
 .sp
 the captured substrings are "white queen" and "queen", and are numbered 1 and
-2. The maximum number of capturing subpatterns is 65535.
+2. The maximum number of capture groups is 65535.
 .P
 As a convenient shorthand, if any option settings are required at the start of
-a non-capturing subpattern, the option letters may appear between the "?" and
-the ":". Thus the two patterns
+a non-capturing group, the option letters may appear between the "?" and the
+":". Thus the two patterns
 .sp
   (?i:saturday|sunday)
   (?:(?i)saturday|sunday)
 .sp
 match exactly the same set of strings. Because alternative branches are tried
-from left to right, and options are not reset until the end of the subpattern
-is reached, an option setting in one branch does affect subsequent branches, so
+from left to right, and options are not reset until the end of the group is
+reached, an option setting in one branch does affect subsequent branches, so
 the above patterns match "SUNDAY" as well as "Saturday".
 .
 .
-.\" HTML <a name="dupsubpatternnumber"></a>
-.SH "DUPLICATE SUBPATTERN NUMBERS"
+.\" HTML <a name="dupgroupnumber"></a>
+.SH "DUPLICATE GROUP NUMBERS"
 .rs
 .sp
-Perl 5.10 introduced a feature whereby each alternative in a subpattern uses
-the same numbers for its capturing parentheses. Such a subpattern starts with
-(?| and is itself a non-capturing subpattern. For example, consider this
-pattern:
+Perl 5.10 introduced a feature whereby each alternative in a group uses the
+same numbers for its capturing parentheses. Such a group starts with (?| and is
+itself a non-capturing group. For example, consider this pattern:
 .sp
   (?|(Sat)ur|(Sun))day
 .sp
@@ -1786,7 +1786,7 @@
 is useful when you want to capture part, but not all, of one of a number of
 alternatives. Inside a (?| group, parentheses are numbered as usual, but the
 number is reset at the start of each branch. The numbers of any capturing
-parentheses that follow the subpattern start after the highest number used in
+parentheses that follow the whole group start after the highest number used in
 any branch. The following example is taken from the Perl documentation. The
 numbers underneath show in which buffer the captured content will be stored.
 .sp
@@ -1794,13 +1794,12 @@
   / ( a )  (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x
   # 1            2         2  3        2     3     4
 .sp
-A backreference to a numbered subpattern uses the most recent value that is
-set for that number by any subpattern. The following pattern matches "abcabc"
-or "defdef":
+A backreference to a capture group uses the most recent value that is set for
+the group. The following pattern matches "abcabc" or "defdef":
 .sp
   /(?|(abc)|(def))\e1/
 .sp
-In contrast, a subroutine call to a numbered subpattern always refers to the
+In contrast, a subroutine call to a capture group always refers to the
 first one in the pattern with the given number. The following pattern matches
 "abcabc" or "defabc":
 .sp
@@ -1814,29 +1813,35 @@
 .\" </a>
 condition test
 .\"
-for a subpattern's having matched refers to a non-unique number, the test is
-true if any of the subpatterns of that number have matched.
+for a group's having matched refers to a non-unique number, the test is
+true if any group with that number has matched.
 .P
 An alternative approach to using this "branch reset" feature is to use
-duplicate named subpatterns, as described in the next section.
+duplicate named groups, as described in the next section.
 .
 .
-.SH "NAMED SUBPATTERNS"
+.SH "NAMED CAPTURE GROUPS"
 .rs
 .sp
-Identifying capturing parentheses by number is simple, but it can be very hard
-to keep track of the numbers in complicated patterns. Furthermore, if an
-expression is modified, the numbers may change. To help with this difficulty,
-PCRE2 supports the naming of capturing subpatterns. This feature was not added
-to Perl until release 5.10. Python had the feature earlier, and PCRE1
-introduced it at release 4.0, using the Python syntax. PCRE2 supports both the
-Perl and the Python syntax.
+Identifying capture groups by number is simple, but it can be very hard to keep
+track of the numbers in complicated patterns. Furthermore, if an expression is
+modified, the numbers may change. To help with this difficulty, PCRE2 supports
+the naming of capture groups. This feature was not added to Perl until release
+5.10. Python had the feature earlier, and PCRE1 introduced it at release 4.0,
+using the Python syntax. PCRE2 supports both the Perl and the Python syntax.
 .P
-In PCRE2, a capturing subpattern can be named in one of three ways:
-(?<name>...) or (?'name'...) as in Perl, or (?P<name>...) as in Python. Names
-consist of up to 32 alphanumeric characters and underscores, but must start
-with a non-digit. References to capturing parentheses from other parts of the
-pattern, such as
+In PCRE2, a capture group can be named in one of three ways: (?<name>...) or
+(?'name'...) as in Perl, or (?P<name>...) as in Python. Names may be up to 32
+code units long. When PCRE2_UTF is not set, they may contain only ASCII
+alphanumeric characters and underscores, but must start with a non-digit. When
+PCRE2_UTF is set, the syntax of group names is extended to allow any Unicode
+letter or Unicode decimal digit. In other words, group names must match one of
+these patterns:
+.sp
+  ^[_A-Za-z][_A-Za-z0-9]*\ez   when PCRE2_UTF is not set
+  ^[_\ep{L}][_\ep{L}\ep{Nd}]*\ez  when PCRE2_UTF is set
+.sp
+References to capture groups from other parts of the pattern, such as
 .\" HTML <a href="#backreferences">
 .\" </a>
 backreferences,
@@ -1852,17 +1857,17 @@
 .\"
 can all be made by name as well as by number.
 .P
-Named capturing parentheses are allocated numbers as well as names, exactly as
-if the names were not present. In both PCRE2 and Perl, capturing subpatterns
+Named capture groups are allocated numbers as well as names, exactly as
+if the names were not present. In both PCRE2 and Perl, capture groups
 are primarily identified by numbers; any names are just aliases for these
 numbers. The PCRE2 API provides function calls for extracting the complete
 name-to-number translation table from a compiled pattern, as well as
 convenience functions for extracting captured substrings by name.
 .P
-\fBWarning:\fP When more than one subpattern has the same number, as described
-in the previous section, a name given to one of them applies to all of them.
-Perl allows identically numbered subpatterns to have different names. Consider
-this pattern, where there are two capturing subpatterns, both numbered 1:
+\fBWarning:\fP When more than one capture group has the same number, as
+described in the previous section, a name given to one of them applies to all
+of them. Perl allows identically numbered groups to have different names.
+Consider this pattern, where there are two capture groups, both numbered 1:
 .sp
   (?|(?<AA>aa)|(?<BB>bb))
 .sp
@@ -1876,20 +1881,20 @@
 .sp
   (?|(?<AA>aa)|(bb))
 .sp
-Although the second subpattern number 1 is not explicitly named, the name AA is
-still an alias for subpattern 1. Whether the pattern matches "aa" or "bb", a
+Although the second group number 1 is not explicitly named, the name AA is
+still an alias for any group 1. Whether the pattern matches "aa" or "bb", a
 reference by name to group AA yields the matched string.
 .P
 By default, a name must be unique within a pattern, except that duplicate names
-are permitted for subpatterns with the same number, for example:
+are permitted for groups with the same number, for example:
 .sp
   (?|(?<AA>aa)|(?<AA>bb))
 .sp
 The duplicate name constraint can be disabled by setting the PCRE2_DUPNAMES
 option at compile time, or by the use of (?J) within the pattern. Duplicate
-names can be useful for patterns where only one instance of the named
-parentheses can match. Suppose you want to match the name of a weekday, either
-as a 3-letter abbreviation or as the full name, and in both cases you want to
+names can be useful for patterns where only one instance of the named capture
+group can match. Suppose you want to match the name of a weekday, either as a
+3-letter abbreviation or as the full name, and in both cases you want to
 extract the abbreviation. This pattern (ignoring the line breaks) does the job:
 .sp
   (?<DN>Mon|Fri|Sun)(?:day)?|
@@ -1898,23 +1903,23 @@
   (?<DN>Thu)(?:rsday)?|
   (?<DN>Sat)(?:urday)?
 .sp
-There are five capturing substrings, but only one is ever set after a match.
-The convenience functions for extracting the data by name returns the substring
-for the first (and in this example, the only) subpattern of that name that
-matched. This saves searching to find which numbered subpattern it was. (An
-alternative way of solving this problem is to use a "branch reset" subpattern,
-as described in the previous section.)
+There are five capture groups, but only one is ever set after a match. The
+convenience functions for extracting the data by name returns the substring for
+the first (and in this example, the only) group of that name that matched. This
+saves searching to find which numbered group it was. (An alternative way of
+solving this problem is to use a "branch reset" group, as described in the
+previous section.)
 .P
-If you make a backreference to a non-unique named subpattern from elsewhere in
-the pattern, the subpatterns to which the name refers are checked in the order
-in which they appear in the overall pattern. The first one that is set is used
-for the reference. For example, this pattern matches both "foofoo" and
-"barbar" but not "foobar" or "barfoo":
+If you make a backreference to a non-unique named group from elsewhere in the
+pattern, the groups to which the name refers are checked in the order in which
+they appear in the overall pattern. The first one that is set is used for the
+reference. For example, this pattern matches both "foofoo" and "barbar" but not
+"foobar" or "barfoo":
 .sp
   (?:(?<n>foo)|(?<n>bar))\ek<n>
 .sp
 .P
-If you make a subroutine call to a non-unique named subpattern, the one that
+If you make a subroutine call to a non-unique named group, the one that
 corresponds to the first occurrence of the name is used. In the absence of
 duplicate numbers this is the one with the lowest number.
 .P
@@ -1925,11 +1930,11 @@
 .\" </a>
 section about conditions
 .\"
-below), either to check whether a subpattern has matched, or to check for
-recursion, all subpatterns with the same name are tested. If the condition is
-true for any one of them, the overall condition is true. This is the same
-behaviour as testing by number. For further details of the interfaces for
-handling named subpatterns, see the
+below), either to check whether a capture group has matched, or to check for
+recursion, all groups with the same name are tested. If the condition is true
+for any one of them, the overall condition is true. This is the same behaviour
+as testing by number. For further details of the interfaces for handling named
+capture groups, see the
 .\" HREF
 \fBpcre2api\fP
 .\"
@@ -1945,18 +1950,18 @@
   a literal data character
   the dot metacharacter
   the \eC escape sequence
+  the \eR escape sequence
   the \eX escape sequence
-  the \eR escape sequence
   an escape such as \ed or \epL that matches a single character
   a character class
   a backreference
-  a parenthesized subpattern (including most assertions)
-  a subroutine call to a subpattern (recursive or otherwise)
+  a parenthesized group (including most assertions)
+  a subroutine call (recursive or otherwise)
 .sp
 The general repetition quantifier specifies a minimum and maximum number of
 permitted matches, by giving the two numbers in curly brackets (braces),
 separated by a comma. The numbers must be less than 65536, and the first must
-be less than or equal to the second. For example:
+be less than or equal to the second. For example,
 .sp
   z{2,4}
 .sp
@@ -1984,8 +1989,8 @@
 .P
 The quantifier {0} is permitted, causing the expression to behave as if the
 previous item and the quantifier were not present. This may be useful for
-subpatterns that are referenced as
-.\" HTML <a href="#subpatternsassubroutines">
+capture groups that are referenced as
+.\" HTML <a href="#groupsassubroutines">
 .\" </a>
 subroutines
 .\"
@@ -1992,10 +1997,10 @@
 from elsewhere in the pattern (but see also the section entitled
 .\" HTML <a href="#subdefine">
 .\" </a>
-"Defining subpatterns for use by reference only"
+"Defining capture groups for use by reference only"
 .\"
-below). Items other than subpatterns that have a {0} quantifier are omitted
-from the compiled pattern.
+below). Except for parenthesized groups, items that have a {0} quantifier are
+omitted from the compiled pattern.
 .P
 For convenience, the three most common quantifiers have single-character
 abbreviations:
@@ -2004,22 +2009,22 @@
   +    is equivalent to {1,}
   ?    is equivalent to {0,1}
 .sp
-It is possible to construct infinite loops by following a subpattern that can
-match no characters with a quantifier that has no upper limit, for example:
+It is possible to construct infinite loops by following a group that can match
+no characters with a quantifier that has no upper limit, for example:
 .sp
   (a?)*
 .sp
 Earlier versions of Perl and PCRE1 used to give an error at compile time for
 such patterns. However, because there are cases where this can be useful, such
-patterns are now accepted, but if any repetition of the subpattern does in fact
+patterns are now accepted, but if any repetition of the group does in fact
 match no characters, the loop is forcibly broken.
 .P
-By default, the quantifiers are "greedy", that is, they match as much as
-possible (up to the maximum number of permitted times), without causing the
-rest of the pattern to fail. The classic example of where this gives problems
-is in trying to match comments in C programs. These appear between /* and */
-and within the comment, individual * and / characters may appear. An attempt to
-match C comments by applying the pattern
+By default, quantifiers are "greedy", that is, they match as much as possible
+(up to the maximum number of permitted times), without causing the rest of the
+pattern to fail. The classic example of where this gives problems is in trying
+to match comments in C programs. These appear between /* and */ and within the
+comment, individual * and / characters may appear. An attempt to match C
+comments by applying the pattern
 .sp
   /\e*.*\e*/
 .sp
@@ -2028,10 +2033,9 @@
   /* first comment */  not comment  /* second comment */
 .sp
 fails, because it matches the entire string owing to the greediness of the .*
-item.
-.P
-If a quantifier is followed by a question mark, it ceases to be greedy, and
-instead matches the minimum number of times possible, so the pattern
+item. However, if a quantifier is followed by a question mark, it ceases to be
+greedy, and instead matches the minimum number of times possible, so the
+pattern
 .sp
   /\e*.*?\e*/
 .sp
@@ -2050,7 +2054,7 @@
 greedy by following them with a question mark. In other words, it inverts the
 default behaviour.
 .P
-When a parenthesized subpattern is quantified with a minimum repeat count that
+When a parenthesized group is quantified with a minimum repeat count that
 is greater than 1 or with a limited maximum, more memory is required for the
 compiled pattern, in proportion to the size of the minimum or maximum.
 .P
@@ -2085,15 +2089,14 @@
 (*PRUNE) and (*SKIP) also disable this optimization, and there is an option,
 PCRE2_NO_DOTSTAR_ANCHOR, to do so explicitly.
 .P
-When a capturing subpattern is repeated, the value captured is the substring
-that matched the final iteration. For example, after
+When a capture group is repeated, the value captured is the substring that
+matched the final iteration. For example, after
 .sp
   (tweedle[dume]{3}\es*)+
 .sp
 has matched "tweedledum tweedledee" the value of the captured substring is
-"tweedledee". However, if there are nested capturing subpatterns, the
-corresponding captured values may have been set in previous iterations. For
-example, after
+"tweedledee". However, if there are nested capture groups, the corresponding
+captured values may have been set in previous iterations. For example, after
 .sp
   (a|(b))+
 .sp
@@ -2119,7 +2122,7 @@
 action of the matcher is to try again with only 5 digits matching the \ed+
 item, and then with 4, and so on, before ultimately failing. "Atomic grouping"
 (a term taken from Jeffrey Friedl's book) provides the means for specifying
-that once a subpattern has matched, it is not to be re-evaluated in this way.
+that once a group has matched, it is not to be re-evaluated in this way.
 .P
 If we use atomic grouping for the previous example, the matcher gives up
 immediately on failing to match "foo" the first time. The notation is a kind of
@@ -2132,23 +2135,23 @@
 .sp
   (*atomic:\ed+)foo
 .sp
-This kind of parenthesis "locks up" the  part of the pattern it contains once
-it has matched, and a failure further into the pattern is prevented from
-backtracking into it. Backtracking past it to previous items, however, works as
-normal.
+This kind of parenthesized group "locks up" the  part of the pattern it
+contains once it has matched, and a failure further into the pattern is
+prevented from backtracking into it. Backtracking past it to previous items,
+however, works as normal.
 .P
-An alternative description is that a subpattern of this type matches exactly
-the string of characters that an identical standalone pattern would match, if
+An alternative description is that a group of this type matches exactly the
+string of characters that an identical standalone pattern would match, if
 anchored at the current point in the subject string.
 .P
-Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as
-the above example can be thought of as a maximizing repeat that must swallow
-everything it can. So, while both \ed+ and \ed+? are prepared to adjust the
-number of digits they match in order to make the rest of the pattern match,
-(?>\ed+) can only match an entire sequence of digits.
+Atomic groups are not capture groups. Simple cases such as the above example
+can be thought of as a maximizing repeat that must swallow everything it can.
+So, while both \ed+ and \ed+? are prepared to adjust the number of digits they
+match in order to make the rest of the pattern match, (?>\ed+) can only match
+an entire sequence of digits.
 .P
 Atomic groups in general can of course contain arbitrarily complicated
-subpatterns, and can be nested. However, when the subpattern for an atomic
+expressions, and can be nested. However, when the contents of an atomic
 group is just a single repeated item, as in the example above, a simpler
 notation, called a "possessive quantifier" can be used. This consists of an
 additional + character following a quantifier. Using this notation, the
@@ -2170,8 +2173,8 @@
 The possessive quantifier syntax is an extension to the Perl 5.8 syntax.
 Jeffrey Friedl originated the idea (and the name) in the first edition of his
 book. Mike McCloskey liked it, so implemented it when he built Sun's Java
-package, and PCRE1 copied it from there. It ultimately found its way into Perl
-at release 5.10.
+package, and PCRE1 copied it from there. It found its way into Perl at release
+5.10.
 .P
 PCRE2 has an optimization that automatically "possessifies" certain simple
 pattern constructs. For example, the sequence A+B is treated as A++B because
@@ -2179,10 +2182,9 @@
 This feature can be disabled by the PCRE2_NO_AUTOPOSSESS option, or starting
 the pattern with (*NO_AUTO_POSSESS).
 .P
-When a pattern contains an unlimited repeat inside a subpattern that can itself
-be repeated an unlimited number of times, the use of an atomic group is the
-only way to avoid some failing matches taking a very long time indeed. The
-pattern
+When a pattern contains an unlimited repeat inside a group that can itself be
+repeated an unlimited number of times, the use of an atomic group is the only
+way to avoid some failing matches taking a very long time indeed. The pattern
 .sp
   (\eD+|<\ed+>)*[!?]
 .sp
@@ -2211,20 +2213,19 @@
 .rs
 .sp
 Outside a character class, a backslash followed by a digit greater than 0 (and
-possibly further digits) is a backreference to a capturing subpattern earlier
-(that is, to its left) in the pattern, provided there have been that many
-previous capturing left parentheses.
+possibly further digits) is a backreference to a capture group earlier (that
+is, to its left) in the pattern, provided there have been that many previous
+capture groups.
 .P
 However, if the decimal number following the backslash is less than 8, it is
-always taken as a backreference, and causes an error only if there are not
-that many capturing left parentheses in the entire pattern. In other words, the
-parentheses that are referenced need not be to the left of the reference for
-numbers less than 8. A "forward backreference" of this type can make sense
-when a repetition is involved and the subpattern to the right has participated
-in an earlier iteration.
+always taken as a backreference, and causes an error only if there are not that
+many capture groups in the entire pattern. In other words, the group that is
+referenced need not be to the left of the reference for numbers less than 8. A
+"forward backreference" of this type can make sense when a repetition is
+involved and the group to the right has participated in an earlier iteration.
 .P
-It is not possible to have a numerical "forward backreference" to a subpattern
-whose number is 8 or more using this syntax because a sequence such as \e50 is
+It is not possible to have a numerical "forward backreference" to a group whose
+number is 8 or more using this syntax because a sequence such as \e50 is
 interpreted as a character defined in octal. See the subsection entitled
 "Non-printing characters"
 .\" HTML <a href="#digitsafterbackslash">
@@ -2231,9 +2232,9 @@
 .\" </a>
 above
 .\"
-for further details of the handling of digits following a backslash. There is
-no such problem when named parentheses are used. A backreference to any
-subpattern is possible using named parentheses (see below).
+for further details of the handling of digits following a backslash. Other
+forms of backreferencing do not suffer from this restriction. In particular,
+there is no problem when named capture groups are used (see below).
 .P
 Another way of avoiding the ambiguity inherent in the use of digits following a
 backslash is to use the \eg escape sequence. This escape must be followed by a
@@ -2250,22 +2251,22 @@
 .sp
   (abc(def)ghi)\eg{-1}
 .sp
-The sequence \eg{-1} is a reference to the most recently started capturing
-subpattern before \eg, that is, is it equivalent to \e2 in this example.
-Similarly, \eg{-2} would be equivalent to \e1. The use of relative references
-can be helpful in long patterns, and also in patterns that are created by
-joining together fragments that contain references within themselves.
+The sequence \eg{-1} is a reference to the most recently started capture group
+before \eg, that is, is it equivalent to \e2 in this example. Similarly,
+\eg{-2} would be equivalent to \e1. The use of relative references can be
+helpful in long patterns, and also in patterns that are created by joining
+together fragments that contain references within themselves.
 .P
-The sequence \eg{+1} is a reference to the next capturing subpattern. This kind
-of forward reference can be useful it patterns that repeat. Perl does not
-support the use of + in this way.
+The sequence \eg{+1} is a reference to the next capture group. This kind of
+forward reference can be useful in patterns that repeat. Perl does not support
+the use of + in this way.
 .P
-A backreference matches whatever actually matched the capturing subpattern in
-the current subject string, rather than anything matching the subpattern
-itself (see
-.\" HTML <a href="#subpatternsassubroutines">
+A backreference matches whatever actually most recently matched the capture
+group in the current subject string, rather than anything at all that matches
+the group (see
+.\" HTML <a href="#groupsassubroutines">
 .\" </a>
-"Subpatterns as subroutines"
+"Groups as subroutines"
 .\"
 below for a way of doing that). So the pattern
 .sp
@@ -2278,14 +2279,14 @@
   ((?i)rah)\es+\e1
 .sp
 matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original
-capturing subpattern is matched caselessly.
+capture group is matched caselessly.
 .P
-There are several different ways of writing backreferences to named
-subpatterns. The .NET syntax \ek{name} and the Perl syntax \ek<name> or
-\ek'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified
+There are several different ways of writing backreferences to named capture
+groups. The .NET syntax \ek{name} and the Perl syntax \ek<name> or \ek'name'
+are supported, as is the Python syntax (?P=name). Perl 5.10's unified
 backreference syntax, in which \eg can be used for both numeric and named
-references, is also supported. We could rewrite the above example in any of
-the following ways:
+references, is also supported. We could rewrite the above example in any of the
+following ways:
 .sp
   (?<p1>(?i)rah)\es+\ek<p1>
   (?'p1'(?i)rah)\es+\ek{p1}
@@ -2292,12 +2293,12 @@
   (?P<p1>(?i)rah)\es+(?P=p1)
   (?<p1>(?i)rah)\es+\eg{p1}
 .sp
-A subpattern that is referenced by name may appear in the pattern before or
+A capture group that is referenced by name may appear in the pattern before or
 after the reference.
 .P
-There may be more than one backreference to the same subpattern. If a
-subpattern has not actually been used in a particular match, any backreferences
-to it always fail by default. For example, the pattern
+There may be more than one backreference to the same group. If a group has not
+actually been used in a particular match, backreferences to it always fail by
+default. For example, the pattern
 .sp
   (a|(bc))\e2
 .sp
@@ -2305,12 +2306,11 @@
 PCRE2_MATCH_UNSET_BACKREF option is set at compile time, a backreference to an
 unset value matches an empty string.
 .P
-Because there may be many capturing parentheses in a pattern, all digits
-following a backslash are taken as part of a potential backreference number.
-If the pattern continues with a digit character, some delimiter must be used to
-terminate the backreference. If the PCRE2_EXTENDED or PCRE2_EXTENDED_MORE
-option is set, this can be white space. Otherwise, the \eg{ syntax or an empty
-comment (see
+Because there may be many capture groups in a pattern, all digits following a
+backslash are taken as part of a potential backreference number. If the pattern
+continues with a digit character, some delimiter must be used to terminate the
+backreference. If the PCRE2_EXTENDED or PCRE2_EXTENDED_MORE option is set, this
+can be white space. Otherwise, the \eg{} syntax or an empty comment (see
 .\" HTML <a href="#comments">
 .\" </a>
 "Comments"
@@ -2321,19 +2321,18 @@
 .SS "Recursive backreferences"
 .rs
 .sp
-A backreference that occurs inside the parentheses to which it refers fails
-when the subpattern is first used, so, for example, (a\e1) never matches.
-However, such references can be useful inside repeated subpatterns. For
-example, the pattern
+A backreference that occurs inside the group to which it refers fails when the
+group is first used, so, for example, (a\e1) never matches. However, such
+references can be useful inside repeated groups. For example, the pattern
 .sp
   (a|b\e1)+
 .sp
 matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of
-the subpattern, the backreference matches the character string corresponding
-to the previous iteration. In order for this to work, the pattern must be such
-that the first iteration does not need to match the backreference. This can be
-done using alternation, as in the example above, or by a quantifier with a
-minimum of zero.
+the group, the backreference matches the character string corresponding to the
+previous iteration. In order for this to work, the pattern must be such that
+the first iteration does not need to match the backreference. This can be done
+using alternation, as in the example above, or by a quantifier with a minimum
+of zero.
 .P
 Backreferences of this type cause the group that they reference to be treated
 as an
@@ -2357,28 +2356,28 @@
 above.
 .\"
 .P
-More complicated assertions are coded as subpatterns. There are two kinds:
-those that look ahead of the current position in the subject string, and those
-that look behind it, and in each case an assertion may be positive (must match
-for the assertion to be true) or negative (must not match for the assertion to
-be true). An assertion subpattern is matched in the normal way, and if it is
-true, matching continues after it, but with the matching position in the
-subject string is was it was before the assertion was processed.
+More complicated assertions are coded as parenthesized groups. There are two
+kinds: those that look ahead of the current position in the subject string, and
+those that look behind it, and in each case an assertion may be positive (must
+match for the assertion to be true) or negative (must not match for the
+assertion to be true). An assertion group is matched in the normal way,
+and if it is true, matching continues after it, but with the matching position
+in the subject string is was it was before the assertion was processed.
 .P
 A lookaround assertion may also appear as the condition in a
 .\" HTML <a href="#conditions">
 .\" </a>
-conditional subpattern
+conditional group
 .\"
 (see below). In this case, the result of matching the assertion determines
 which branch of the condition is followed.
 .P
-Assertion subpatterns are not capturing subpatterns. If an assertion contains
-capturing subpatterns within it, these are counted for the purposes of
-numbering the capturing subpatterns in the whole pattern. Within each branch of
-an assertion, locally captured substrings may be referenced in the usual way.
-For example, a sequence such as (.)\eg{-1} can be used to check that two
-adjacent characters are the same.
+Assertion groups are not capture groups. If an assertion contains capture
+groups within it, these are counted for the purposes of numbering the capture
+groups in the whole pattern. Within each branch of an assertion, locally
+captured substrings may be referenced in the usual way. For example, a sequence
+such as (.)\eg{-1} can be used to check that two adjacent characters are the
+same.
 .P
 When a branch within an assertion fails to match, any substrings that were
 captured are discarded (as happens with any pattern branch that fails to
@@ -2393,7 +2392,7 @@
 assertion is not true. If such an assertion is being used as a condition in a
 .\" HTML <a href="#conditions">
 .\" </a>
-conditional subpattern
+conditional group
 .\"
 (see below), captured substrings are retained, because matching continues with
 the "no" branch of the condition. For other failing negative assertions,
@@ -2400,16 +2399,16 @@
 control passes to the previous backtracking point, thus discarding any captured
 strings within the assertion.
 .P
-For compatibility with Perl, most assertion subpatterns may be repeated; though
-it makes no sense to assert the same thing several times, the side effect of
-capturing parentheses may occasionally be useful. However, an assertion that
-forms the condition for a conditional subpattern may not be quantified. In
-practice, for other assertions, there only three cases:
+For compatibility with Perl, most assertion groups may be repeated; though it
+makes no sense to assert the same thing several times, the side effect of
+capturing may occasionally be useful. However, an assertion that forms the
+condition for a conditional group may not be quantified. In practice, for
+other assertions, there only three cases:
 .sp
 (1) If the quantifier is {0}, the assertion is never obeyed during matching.
-However, it may contain internal capturing parenthesized groups that are called
-from elsewhere via the
-.\" HTML <a href="#subpatternsassubroutines">
+However, it may contain internal capture groups that are called from elsewhere
+via the
+.\" HTML <a href="#groupsassubroutines">
 .\" </a>
 subroutine mechanism.
 .\"
@@ -2436,9 +2435,9 @@
   (*positive_lookbehind: or (*plb: is the same as (?<=
   (*negative_lookbehind: or (*nlb: is the same as (?<!
 .sp
-For example, (*pla:foo) is the same assertion as (?=foo). However, in the
-following sections, the various assertions are described using the original
-symbolic forms.
+For example, (*pla:foo) is the same assertion as (?=foo). In the following
+sections, the various assertions are described using the original symbolic
+forms.
 .
 .
 .SS "Lookahead assertions"
@@ -2522,12 +2521,12 @@
 \eX and \eR escapes, which can match different numbers of code units, are never
 permitted in lookbehinds.
 .P
-.\" HTML <a href="#subpatternsassubroutines">
+.\" HTML <a href="#groupsassubroutines">
 .\" </a>
 "Subroutine"
 .\"
 calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long
-as the subpattern matches a fixed-length string. However,
+as the called capture group matches a fixed-length string. However,
 .\" HTML <a href="#recursion">
 .\" </a>
 recursion,
@@ -2538,10 +2537,10 @@
 Perl does not support backreferences in lookbehinds. PCRE2 does support them,
 but only if certain conditions are met. The PCRE2_MATCH_UNSET_BACKREF option
 must not be set, there must be no use of (?| in the pattern (it creates
-duplicate subpattern numbers), and if the backreference is by name, the name
-must be unique. Of course, the referenced subpattern must itself be of fixed
-length. The following pattern matches words containing at least two characters
-that begin and end with the same character:
+duplicate group numbers), and if the backreference is by name, the name
+must be unique. Of course, the referenced group must itself match a fixed
+length substring. The following pattern matches words containing at least two
+characters that begin and end with the same character:
 .sp
    \eb(\ew)\ew++(?<=\e1)
 .P
@@ -2669,18 +2668,18 @@
 .\" </a>
 (see below)
 .\"
-should not be used within a script run subpattern, because it causes an
-immediate exit from the subpattern, bypassing the script run checking.
+should not be used within a script run group, because it causes an immediate
+exit from the group, bypassing the script run checking.
 .
 .
 .\" HTML <a name="conditions"></a>
-.SH "CONDITIONAL SUBPATTERNS"
+.SH "CONDITIONAL GROUPS"
 .rs
 .sp
-It is possible to cause the matching process to obey a subpattern
-conditionally or to choose between two alternative subpatterns, depending on
-the result of an assertion, or whether a specific capturing subpattern has
-already been matched. The two possible forms of conditional subpattern are:
+It is possible to cause the matching process to obey a pattern fragment
+conditionally or to choose between two alternative fragments, depending on
+the result of an assertion, or whether a specific capture group has
+already been matched. The two possible forms of conditional group are:
 .sp
   (?(condition)yes-pattern)
   (?(condition)yes-pattern|no-pattern)
@@ -2688,38 +2687,36 @@
 If the condition is satisfied, the yes-pattern is used; otherwise the
 no-pattern (if present) is used. An absent no-pattern is equivalent to an empty
 string (it always matches). If there are more than two alternatives in the
-subpattern, a compile-time error occurs. Each of the two alternatives may
-itself contain nested subpatterns of any form, including conditional
-subpatterns; the restriction to two alternatives applies only at the level of
-the condition. This pattern fragment is an example where the alternatives are
-complex:
+group, a compile-time error occurs. Each of the two alternatives may itself
+contain nested groups of any form, including conditional groups; the
+restriction to two alternatives applies only at the level of the condition
+itself. This pattern fragment is an example where the alternatives are complex:
 .sp
   (?(1) (A|B|C) | (D | (?(2)E|F) | E) )
 .sp
 .P
-There are five kinds of condition: references to subpatterns, references to
+There are five kinds of condition: references to capture groups, references to
 recursion, two pseudo-conditions called DEFINE and VERSION, and assertions.
 .
 .
-.SS "Checking for a used subpattern by number"
+.SS "Checking for a used capture group by number"
 .rs
 .sp
 If the text between the parentheses consists of a sequence of digits, the
-condition is true if a capturing subpattern of that number has previously
-matched. If there is more than one capturing subpattern with the same number
-(see the earlier
+condition is true if a capture group of that number has previously matched. If
+there is more than one capture group with the same number (see the earlier
 .\"
 .\" HTML <a href="#recursion">
 .\" </a>
-section about duplicate subpattern numbers),
+section about duplicate group numbers),
 .\"
 the condition is true if any of them have matched. An alternative notation is
-to precede the digits with a plus or minus sign. In this case, the subpattern
-number is relative rather than absolute. The most recently opened parentheses
-can be referenced by (?(-1), the next most recent by (?(-2), and so on. Inside
-loops it can also make sense to refer to subsequent groups. The next
-parentheses to be opened can be referenced as (?(+1), and so on. (The value
-zero in any of these forms is not used; it provokes a compile-time error.)
+to precede the digits with a plus or minus sign. In this case, the group number
+is relative rather than absolute. The most recently opened capture group can be
+referenced by (?(-1), the next most recent by (?(-2), and so on. Inside loops
+it can also make sense to refer to subsequent groups. The next capture group
+can be referenced as (?(+1), and so on. (The value zero in any of these forms
+is not used; it provokes a compile-time error.)
 .P
 Consider the following pattern, which contains non-significant white space to
 make it more readable (assume the PCRE2_EXTENDED option) and to divide it into
@@ -2730,12 +2727,12 @@
 The first part matches an optional opening parenthesis, and if that
 character is present, sets it as the first captured substring. The second part
 matches one or more characters that are not parentheses. The third part is a
-conditional subpattern that tests whether or not the first set of parentheses
-matched. If they did, that is, if subject started with an opening parenthesis,
+conditional group that tests whether or not the first capture group
+matched. If it did, that is, if subject started with an opening parenthesis,
 the condition is true, and so the yes-pattern is executed and a closing
 parenthesis is required. Otherwise, since no-pattern is not present, the
-subpattern matches nothing. In other words, this pattern matches a sequence of
-non-parentheses, optionally enclosed in parentheses.
+conditional group matches nothing. In other words, this pattern matches a
+sequence of non-parentheses, optionally enclosed in parentheses.
 .P
 If you were embedding this pattern in a larger one, you could use a relative
 reference:
@@ -2745,21 +2742,20 @@
 This makes the fragment independent of the parentheses in the larger pattern.
 .
 .
-.SS "Checking for a used subpattern by name"
+.SS "Checking for a used capture group by name"
 .rs
 .sp
 Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used
-subpattern by name. For compatibility with earlier versions of PCRE1, which had
-this facility before Perl, the syntax (?(name)...) is also recognized. Note,
-however, that undelimited names consisting of the letter R followed by digits
-are ambiguous (see the following section).
-.P
-Rewriting the above example to use a named subpattern gives this:
+capture group by name. For compatibility with earlier versions of PCRE1, which
+had this facility before Perl, the syntax (?(name)...) is also recognized.
+Note, however, that undelimited names consisting of the letter R followed by
+digits are ambiguous (see the following section). Rewriting the above example
+to use a named group gives this:
 .sp
   (?<OPEN> \e( )?    [^()]+    (?(<OPEN>) \e) )
 .sp
 If the name used in a condition of this kind is a duplicate, the test is
-applied to all subpatterns of the same name, and is true if any one of them has
+applied to all groups of the same name, and is true if any one of them has
 matched.
 .
 .
@@ -2774,22 +2770,22 @@
 "Recursive patterns"
 .\"
 and
-.\" HTML <a href="#subpatternsassubroutines">
+.\" HTML <a href="#groupsassubroutines">
 .\" </a>
-"Subpatterns as subroutines"
+"Groups as subroutines"
 .\"
-below for details of recursion and subpattern calls.
+below for details of recursion and subroutine calls.
 .P
-If a condition is the string (R), and there is no subpattern with the name R,
-the condition is true if matching is currently in a recursion or subroutine
-call to the whole pattern or any subpattern. If digits follow the letter R, and
-there is no subpattern with that name, the condition is true if the most recent
-call is into a subpattern with the given number, which must exist somewhere in
-the overall pattern. This is a contrived example that is equivalent to a+b:
+If a condition is the string (R), and there is no capture group with the name
+R, the condition is true if matching is currently in a recursion or subroutine
+call to the whole pattern or any capture group. If digits follow the letter R,
+and there is no group with that name, the condition is true if the most recent
+call is into a group with the given number, which must exist somewhere in the
+overall pattern. This is a contrived example that is equivalent to a+b:
 .sp
   ((?(R1)a+|(?1)b))
 .sp
-However, in both cases, if there is a subpattern with a matching name, the
+However, in both cases, if there is a capture group with a matching name, the
 condition tests for its being set, as described in the section above, instead
 of testing for recursion. For example, creating a group with the name R1 by
 adding (?<R1>) to the above pattern completely changes its meaning.
@@ -2798,12 +2794,12 @@
 .sp
   (?(R&name)...)
 .sp
-the condition is true if the most recent recursion is into a subpattern of that
-name (which must exist within the pattern).
+the condition is true if the most recent recursion is into a group of that name
+(which must exist within the pattern).
 .P
 This condition does not check the entire recursion stack. It tests only the
 current level. If the name used in a condition of this kind is a duplicate, the
-test is applied to all subpatterns of the same name, and is true if any one of
+test is applied to all groups of the same name, and is true if any one of
 them is the most recent recursion.
 .P
 At "top level", all these recursion test conditions are false.
@@ -2810,15 +2806,15 @@
 .
 .
 .\" HTML <a name="subdefine"></a>
-.SS "Defining subpatterns for use by reference only"
+.SS "Defining capture groups for use by reference only"
 .rs
 .sp
 If the condition is the string (DEFINE), the condition is always false, even if
 there is a group with the name DEFINE. In this case, there may be only one
-alternative in the subpattern. It is always skipped if control reaches this
-point in the pattern; the idea of DEFINE is that it can be used to define
-subroutines that can be referenced from elsewhere. (The use of
-.\" HTML <a href="#subpatternsassubroutines">
+alternative in the rest of the conditional group. It is always skipped if
+control reaches this point in the pattern; the idea of DEFINE is that it can be
+used to define subroutines that can be referenced from elsewhere. (The use of
+.\" HTML <a href="#groupsassubroutines">
 .\" </a>
 subroutines
 .\"
@@ -2858,10 +2854,10 @@
 .SS "Assertion conditions"
 .rs
 .sp
-If the condition is not in any of the above formats, it must be an assertion.
-This may be a positive or negative lookahead or lookbehind assertion. Consider
-this pattern, again containing non-significant white space, and with the two
-alternatives on the second line:
+If the condition is not in any of the above formats, it must be a parenthesized
+assertion. This may be a positive or negative lookahead or lookbehind
+assertion. Consider this pattern, again containing non-significant white space,
+and with the two alternatives on the second line:
 .sp
   (?(?=[^a-z]*[a-z])
   \ed{2}-[a-z]{3}-\ed{2}  |  \ed{2}-\ed{2}-\ed{2} )
@@ -2873,11 +2869,11 @@
 against the second. This pattern matches strings in one of the two forms
 dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits.
 .P
-When an assertion that is a condition contains capturing subpatterns, any
+When an assertion that is a condition contains capture groups, any
 capturing that occurs in a matching branch is retained afterwards, for both
 positive and negative assertions, because matching always continues after the
 assertion, whether it succeeds or fails. (Compare non-conditional assertions,
-when captures are retained only for positive assertions that succeed.)
+for which captures are retained only for positive assertions that succeed.)
 .
 .
 .\" HTML <a name="comments"></a>
@@ -2887,7 +2883,7 @@
 There are two ways of including comments in patterns that are processed by
 PCRE2. In both cases, the start of the comment must not be in a character
 class, nor in the middle of any other sequence of related characters such as
-(?: or a subpattern name or number. The characters that make up a comment play
+(?: or a group name or number. The characters that make up a comment play
 no part in the pattern matching.
 .P
 The sequence (?# marks the start of a comment that continues up to the next
@@ -2937,13 +2933,13 @@
 .P
 Obviously, PCRE2 cannot support the interpolation of Perl code. Instead, it
 supports special syntax for recursion of the entire pattern, and also for
-individual subpattern recursion. After its introduction in PCRE1 and Python,
+individual capture group recursion. After its introduction in PCRE1 and Python,
 this kind of recursion was subsequently introduced into Perl at release 5.10.
 .P
 A special item that consists of (? followed by a number greater than zero and a
-closing parenthesis is a recursive subroutine call of the subpattern of the
-given number, provided that it occurs inside that subpattern. (If not, it is a
-.\" HTML <a href="#subpatternsassubroutines">
+closing parenthesis is a recursive subroutine call of the capture group of the
+given number, provided that it occurs inside that group. (If not, it is a
+.\" HTML <a href="#groupsassubroutines">
 .\" </a>
 non-recursive subroutine
 .\"
@@ -2976,16 +2972,16 @@
 capturing parentheses leftwards from the point at which it is encountered.
 .P
 Be aware however, that if
-.\" HTML <a href="#dupsubpatternnumber">
+.\" HTML <a href="#dupgroupnumber">
 .\" </a>
-duplicate subpattern numbers
+duplicate capture group numbers
 .\"
-are in use, relative references refer to the earliest subpattern with the
+are in use, relative references refer to the earliest group with the
 appropriate number. Consider, for example:
 .sp
   (?|(a)|(b)) (c) (?-2)
 .sp
-The first two capturing groups (a) and (b) are both numbered 1, and group (c)
+The first two capture groups (a) and (b) are both numbered 1, and group (c)
 is number 2. When the reference (?-2) is encountered, the second most recently
 opened parentheses has the number 1, but it is the first such group (the (a)
 group) to which the recursion refers. This would be the same if an absolute
@@ -2992,10 +2988,10 @@
 reference (?1) was used. In other words, relative references are just a
 shorthand for computing a group number.
 .P
-It is also possible to refer to subsequently opened parentheses, by writing
+It is also possible to refer to subsequent capture groups, by writing
 references such as (?+2). However, these cannot be recursive because the
 reference is not inside the parentheses that are referenced. They are always
-.\" HTML <a href="#subpatternsassubroutines">
+.\" HTML <a href="#groupsassubroutines">
 .\" </a>
 non-recursive subroutine
 .\"
@@ -3007,7 +3003,7 @@
 .sp
   (?<pn> \e( ( [^()]++ | (?&pn) )* \e) )
 .sp
-If there is more than one subpattern with the same name, the earliest one is
+If there is more than one group with the same name, the earliest one is
 used.
 .P
 The example pattern that we have been looking at contains nested unlimited
@@ -3033,9 +3029,9 @@
   (ab(cd)ef)
 .sp
 the value for the inner capturing parentheses (numbered 2) is "ef", which is
-the last value taken on at the top level. If a capturing subpattern is not
-matched at the top level, its final captured value is unset, even if it was
-(temporarily) set at a deeper level during the matching process.
+the last value taken on at the top level. If a capture group is not matched at
+the top level, its final captured value is unset, even if it was (temporarily)
+set at a deeper level during the matching process.
 .P
 Do not confuse the (?R) item with the condition (R), which tests for recursion.
 Consider this pattern, which matches text in angle brackets, allowing for
@@ -3044,9 +3040,9 @@
 .sp
   < (?: (?(R) \ed++  | [^<>]*+) | (?R)) * >
 .sp
-In this pattern, (?(R) is the start of a conditional subpattern, with two
-different alternatives for the recursive and non-recursive cases. The (?R) item
-is the actual recursive call.
+In this pattern, (?(R) is the start of a conditional group, with two different
+alternatives for the recursive and non-recursive cases. The (?R) item is the
+actual recursive call.
 .
 .
 .\" HTML <a name="recursiondifference"></a>
@@ -3056,7 +3052,7 @@
 Some former differences between PCRE2 and Perl no longer exist.
 .P
 Before release 10.30, recursion processing in PCRE2 differed from Perl in that
-a recursive subpattern call was always treated as an atomic group. That is,
+a recursive subroutine call was always treated as an atomic group. That is,
 once it had matched some of the subject string, it was never re-entered, even
 if it contained untried alternatives and there was a subsequent matching
 failure. (Historical note: PCRE implemented recursion before Perl did.)
@@ -3089,7 +3085,7 @@
 .P
 Another way in which PCRE2 and Perl used to differ in their recursion
 processing is in the handling of captured values. Formerly in Perl, when a
-subpattern was called recursively or as a subpattern (see the next section), it
+group was called recursively or as a subroutine (see the next section), it
 had no access to any values that were captured outside the recursion, whereas
 in PCRE2 these values can be referenced. Consider this pattern:
 .sp
@@ -3102,17 +3098,16 @@
 later versions (I tried 5.024) it now works.
 .
 .
-.\" HTML <a name="subpatternsassubroutines"></a>
-.SH "SUBPATTERNS AS SUBROUTINES"
+.\" HTML <a name="groupsassubroutines"></a>
+.SH "GROUPS AS SUBROUTINES"
 .rs
 .sp
-If the syntax for a recursive subpattern call (either by number or by
-name) is used outside the parentheses to which it refers, it operates a bit
-like a subroutine in a programming language. More accurately, PCRE2 treats the
-referenced subpattern as an independent subpattern which it tries to match at
-the current matching position. The called subpattern may be defined before or
-after the reference. A numbered reference can be absolute or relative, as in
-these examples:
+If the syntax for a recursive group call (either by number or by name) is used
+outside the parentheses to which it refers, it operates a bit like a subroutine
+in a programming language. More accurately, PCRE2 treats the referenced group
+as an independent subpattern which it tries to match at the current matching
+position. The called group may be defined before or after the reference. A
+numbered reference can be absolute or relative, as in these examples:
 .sp
   (...(absolute)...)...(?2)...
   (...(relative)...)...(?-1)...
@@ -3135,7 +3130,7 @@
 occur. However, any capturing parentheses that are set during the subroutine
 call revert to their previous values afterwards.
 .P
-Processing options such as case-independence are fixed when a subpattern is
+Processing options such as case-independence are fixed when a group is
 defined, so if it is used as a subroutine, such options cannot be changed for
 different calls. For example, consider this pattern:
 .sp
@@ -3142,7 +3137,7 @@
   (abc)(?i:(?-1))
 .sp
 It matches "abcabc". It does not match "abcABC" because the change of
-processing option does not affect the called subpattern.
+processing option does not affect the called group.
 .P
 The behaviour of
 .\" HTML <a href="#backtrackcontrol">
@@ -3149,7 +3144,7 @@
 .\" </a>
 backtracking control verbs
 .\"
-in subpatterns when called as subroutines is described in the section entitled
+in groups when called as subroutines is described in the section entitled
 .\" HTML <a href="#btsub">
 .\" </a>
 "Backtracking verbs in subroutines"
@@ -3163,8 +3158,8 @@
 .sp
 For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or
 a number enclosed either in angle brackets or single quotes, is an alternative
-syntax for referencing a subpattern as a subroutine, possibly recursively. Here
-are two of the examples used above, rewritten using this syntax:
+syntax for calling a group as a subroutine, possibly recursively. Here are two
+of the examples used above, rewritten using this syntax:
 .sp
   (?<pn> \e( ( (?>[^()]+) | \eg<pn> )* \e) )
   (sens|respons)e and \eg'1'ibility
@@ -3306,7 +3301,7 @@
 and in
 .\" HTML <a href="#btsub">
 .\" </a>
-subpatterns called as subroutines
+capture groups called as subroutines
 .\"
 (whether or not recursively) is documented below.
 .
@@ -3347,8 +3342,8 @@
    (*ACCEPT) or (*ACCEPT:NAME)
 .sp
 This verb causes the match to end successfully, skipping the remainder of the
-pattern. However, when it is inside a subpattern that is called as a
-subroutine, only that subpattern is ended successfully. Matching then continues
+pattern. However, when it is inside a capture group that is called as a
+subroutine, only that group is ended successfully. Matching then continues
 at the outer level. If (*ACCEPT) in triggered in a positive assertion, the
 assertion succeeds; in a negative assertion, the assertion fails.
 .P
@@ -3360,9 +3355,8 @@
 This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is captured by
 the outer parentheses.
 .P
-\fBWarning:\fP (*ACCEPT) should not be used within a script run subpattern,
-because it causes an immediate exit from the subpattern, bypassing the script
-run checking.
+\fBWarning:\fP (*ACCEPT) should not be used within a script run group, because
+it causes an immediate exit from the group, bypassing the script run checking.
 .sp
   (*FAIL) or (*FAIL:NAME)
 .sp
@@ -3602,30 +3596,28 @@
 caller. However, (*SKIP:NAME) searches only for names set with (*MARK),
 ignoring those set by other backtracking verbs.
 .P
-A subpattern that does not contain a | character is just a part of the
-enclosing alternative; it is not a nested alternation with only one
-alternative. The effect of (*THEN) extends beyond such a subpattern to the
-enclosing alternative. Consider this pattern, where A, B, etc. are complex
-pattern fragments that do not contain any | characters at this level:
+A group that does not contain a | character is just a part of the enclosing
+alternative; it is not a nested alternation with only one alternative. The
+effect of (*THEN) extends beyond such a group to the enclosing alternative.
+Consider this pattern, where A, B, etc. are complex pattern fragments that do
+not contain any | characters at this level:
 .sp
   A (B(*THEN)C) | D
 .sp
 If A and B are matched, but there is a failure in C, matching does not
 backtrack into A; instead it moves to the next alternative, that is, D.
-However, if the subpattern containing (*THEN) is given an alternative, it
+However, if the group containing (*THEN) is given an alternative, it
 behaves differently:
 .sp
   A (B(*THEN)C | (*FAIL)) | D
 .sp
-The effect of (*THEN) is now confined to the inner subpattern. After a failure
-in C, matching moves to (*FAIL), which causes the whole subpattern to fail
-because there are no more alternatives to try. In this case, matching does now
-backtrack into A.
+The effect of (*THEN) is now confined to the inner group. After a failure in C,
+matching moves to (*FAIL), which causes the whole group to fail because there
+are no more alternatives to try. In this case, matching does backtrack into A.
 .P
-Note that a conditional subpattern is not considered as having two
-alternatives, because only one is ever used. In other words, the | character in
-a conditional subpattern has a different meaning. Ignoring white space,
-consider:
+Note that a conditional group is not considered as having two alternatives,
+because only one is ever used. In other words, the | character in a conditional
+group has a different meaning. Ignoring white space, consider:
 .sp
   ^.*? (?(?=a) a | b(*THEN)c )
 .sp
@@ -3633,7 +3625,7 @@
 it initially matches zero characters. The condition (?=a) then fails, the
 character "b" is matched, but "c" is not. At this point, matching does not
 backtrack to .*? as might perhaps be expected from the presence of the |
-character. The conditional subpattern is part of the single alternative that
+character. The conditional group is part of the single alternative that
 comprises the whole pattern, and so the match fails. (If there was a backtrack
 into .*?, allowing it to match "b", the match would succeed.)
 .P
@@ -3690,7 +3682,7 @@
 (*FAIL) in any assertion has its normal effect: it forces an immediate
 backtrack. The behaviour of the other backtracking verbs depends on whether or
 not the assertion is standalone or acting as the condition in a conditional
-subpattern.
+group.
 .P
 (*ACCEPT) in a standalone positive assertion causes the assertion to succeed
 without any further processing; captured strings and a mark name (if set) are
@@ -3725,25 +3717,24 @@
 .SS "Backtracking verbs in subroutines"
 .rs
 .sp
-These behaviours occur whether or not the subpattern is called recursively.
+These behaviours occur whether or not the group is called recursively.
 .P
-(*ACCEPT) in a subpattern called as a subroutine causes the subroutine match to
+(*ACCEPT) in a group called as a subroutine causes the subroutine match to
 succeed without any further processing. Matching then continues after the
 subroutine call. Perl documents this behaviour. Perl's treatment of the other
 verbs in subroutines is different in some cases.
 .P
-(*FAIL) in a subpattern called as a subroutine has its normal effect: it forces
+(*FAIL) in a group called as a subroutine has its normal effect: it forces
 an immediate backtrack.
 .P
 (*COMMIT), (*SKIP), and (*PRUNE) cause the subroutine match to fail when
-triggered by being backtracked to in a subpattern called as a subroutine. There
-is then a backtrack at the outer level.
+triggered by being backtracked to in a group called as a subroutine. There is
+then a backtrack at the outer level.
 .P
 (*THEN), when triggered, skips to the next alternative in the innermost
-enclosing group within the subpattern that has alternatives (its normal
-behaviour). However, if there is no such group within the subroutine
-subpattern, the subroutine match fails and there is a backtrack at the outer
-level.
+enclosing group that has alternatives (its normal behaviour). However, if there
+is no such group within the subroutine's group, the subroutine match fails and
+there is a backtrack at the outer level.
 .
 .
 .SH "SEE ALSO"
@@ -3767,6 +3758,6 @@
 .rs
 .sp
 .nf
-Last updated: 27 November 2018
-Copyright (c) 1997-2018 University of Cambridge.
+Last updated: 04 February 2019
+Copyright (c) 1997-2019 University of Cambridge.
 .fi


Modified: code/trunk/doc/pcre2perform.3
===================================================================
--- code/trunk/doc/pcre2perform.3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2perform.3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2PERFORM 3 "25 April 2018" "PCRE2 10.32"
+.TH PCRE2PERFORM 3 "03 February 2019" "PCRE2 10.33"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 PERFORMANCE"
@@ -14,9 +14,9 @@
 Patterns are compiled by PCRE2 into a reasonably efficient interpretive code,
 so that most simple patterns do not use much memory for storing the compiled
 version. However, there is one case where the memory usage of a compiled
-pattern can be unexpectedly large. If a parenthesized subpattern has a
-quantifier with a minimum greater than 1 and/or a limited maximum, the whole
-subpattern is repeated in the compiled code. For example, the pattern
+pattern can be unexpectedly large. If a parenthesized group has a quantifier
+with a minimum greater than 1 and/or a limited maximum, the whole group is
+repeated in the compiled code. For example, the pattern
 .sp
   (abc|def){2,4}
 .sp
@@ -239,6 +239,6 @@
 .rs
 .sp
 .nf
-Last updated: 25 April 2018
-Copyright (c) 1997-2018 University of Cambridge.
+Last updated: 03 February 2019
+Copyright (c) 1997-2019 University of Cambridge.
 .fi


Modified: code/trunk/doc/pcre2syntax.3
===================================================================
--- code/trunk/doc/pcre2syntax.3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2syntax.3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2SYNTAX 3 "10 October 2018" "PCRE2 10.33"
+.TH PCRE2SYNTAX 3 "03 February 2019" "PCRE2 10.33"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY"
@@ -398,20 +398,24 @@
 .SH "CAPTURING"
 .rs
 .sp
-  (...)           capturing group
-  (?<name>...)    named capturing group (Perl)
-  (?'name'...)    named capturing group (Perl)
-  (?P<name>...)   named capturing group (Python)
-  (?:...)         non-capturing group
-  (?|...)         non-capturing group; reset group numbers for
-                   capturing groups in each alternative
+  (...)           capture group
+  (?<name>...)    named capture group (Perl)
+  (?'name'...)    named capture group (Perl)
+  (?P<name>...)   named capture group (Python)
+  (?:...)         non-capture group
+  (?|...)         non-capture group; reset group numbers for
+                   capture groups in each alternative
+.sp
+In non-UTF modes, names may contain underscores and ASCII letters and digits;
+in UTF modes, any Unicode letters and Unicode decimal digits are permitted. In
+both cases, a name must not start with a digit.
 .
 .
 .SH "ATOMIC GROUPS"
 .rs
 .sp
-  (?>...)         atomic, non-capturing group
-  (*atomic:...)   atomic, non-capturing group
+  (?>...)         atomic non-capture group
+  (*atomic:...)   atomic non-capture group
 .
 .
 .SH "COMMENT"
@@ -439,7 +443,7 @@
 Unsetting x or xx unsets both. Several options may be set at once, and a
 mixture of setting and unsetting such as (?i-x) is allowed, but there may be
 only one hyphen. Setting (but no unsetting) is allowed after (?^ for example
-(?^in). An option setting may appear at the start of a non-capturing group, for
+(?^in). An option setting may appear at the start of a non-capture group, for
 example (?i:...).
 .P
 The following are recognized only at the very start of a pattern or after one
@@ -542,19 +546,19 @@
 .rs
 .sp
   (?R)            recurse whole pattern
-  (?n)            call subpattern by absolute number
-  (?+n)           call subpattern by relative number
-  (?-n)           call subpattern by relative number
-  (?&name)        call subpattern by name (Perl)
-  (?P>name)       call subpattern by name (Python)
-  \eg<name>        call subpattern by name (Oniguruma)
-  \eg'name'        call subpattern by name (Oniguruma)
-  \eg<n>           call subpattern by absolute number (Oniguruma)
-  \eg'n'           call subpattern by absolute number (Oniguruma)
-  \eg<+n>          call subpattern by relative number (PCRE2 extension)
-  \eg'+n'          call subpattern by relative number (PCRE2 extension)
-  \eg<-n>          call subpattern by relative number (PCRE2 extension)
-  \eg'-n'          call subpattern by relative number (PCRE2 extension)
+  (?n)            call subroutine by absolute number
+  (?+n)           call subroutine by relative number
+  (?-n)           call subroutine by relative number
+  (?&name)        call subroutine by name (Perl)
+  (?P>name)       call subroutine by name (Python)
+  \eg<name>        call subroutine by name (Oniguruma)
+  \eg'name'        call subroutine by name (Oniguruma)
+  \eg<n>           call subroutine by absolute number (Oniguruma)
+  \eg'n'           call subroutine by absolute number (Oniguruma)
+  \eg<+n>          call subroutine by relative number (PCRE2 extension)
+  \eg'+n'          call subroutine by relative number (PCRE2 extension)
+  \eg<-n>          call subroutine by relative number (PCRE2 extension)
+  \eg'-n'          call subroutine by relative number (PCRE2 extension)
 .
 .
 .SH "CONDITIONAL PATTERNS"
@@ -572,7 +576,7 @@
   (?(R)               overall recursion condition
   (?(Rn)              specific numbered group recursion condition
   (?(R&name)          specific named group recursion condition
-  (?(DEFINE)          define subpattern for reference
+  (?(DEFINE)          define groups for reference
   (?(VERSION[>]=n.m)  test PCRE2 version
   (?(assert)          assertion condition
 .sp
@@ -643,6 +647,6 @@
 .rs
 .sp
 .nf
-Last updated: 10 October 2018
-Copyright (c) 1997-2018 University of Cambridge.
+Last updated: 03 February 2019
+Copyright (c) 1997-2019 University of Cambridge.
 .fi


Modified: code/trunk/doc/pcre2test.1
===================================================================
--- code/trunk/doc/pcre2test.1    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2test.1    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2TEST 1 "12 November 2018" "PCRE 10.33"
+.TH PCRE2TEST 1 "03 February 2019" "PCRE 10.33"
 .SH NAME
 pcre2test - a program for testing Perl-compatible regular expressions.
 .SH SYNOPSIS
@@ -672,7 +672,7 @@
 some typical examples:
 .sp
     re> /(?i)(^a|^b)/m,info
-  Capturing subpattern count = 1
+  Capture group count = 1
   Compile options: multiline
   Overall options: caseless multiline
   First code unit at start or follows newline
@@ -679,7 +679,7 @@
   Subject length lower bound = 1
 .sp
     re> /(?i)abc/info
-  Capturing subpattern count = 0
+  Capture group count = 0
   Compile options: <none>
   Overall options: caseless
   First code unit = 'a' (caseless)
@@ -1325,8 +1325,8 @@
 .sp
 The \fBcopy\fP and \fBget\fP modifiers can be used to test the
 \fBpcre2_substring_copy_xxx()\fP and \fBpcre2_substring_get_xxx()\fP functions.
-They can be given more than once, and each can specify a group name or number,
-for example:
+They can be given more than once, and each can specify a capture group name or
+number, for example:
 .sp
    abcd\e=copy=1,copy=3,get=G1
 .sp
@@ -2056,6 +2056,6 @@
 .rs
 .sp
 .nf
-Last updated: 12 November 2018
-Copyright (c) 1997-2018 University of Cambridge.
+Last updated: 03 February 2019
+Copyright (c) 1997-2019 University of Cambridge.
 .fi


Modified: code/trunk/doc/pcre2test.txt
===================================================================
--- code/trunk/doc/pcre2test.txt    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2test.txt    2019-02-06 18:11:36 UTC (rev 1066)
@@ -646,7 +646,7 @@
        are some typical examples:


            re> /(?i)(^a|^b)/m,info
-         Capturing subpattern count = 1
+         Capture group count = 1
          Compile options: multiline
          Overall options: caseless multiline
          First code unit at start or follows newline
@@ -653,7 +653,7 @@
          Subject length lower bound = 1


            re> /(?i)abc/info
-         Capturing subpattern count = 0
+         Capture group count = 0
          Compile options: <none>
          Overall options: caseless
          First code unit = 'a' (caseless)
@@ -1214,8 +1214,8 @@


        The copy  and  get  modifiers  can  be  used  to  test  the  pcre2_sub-
        string_copy_xxx() and pcre2_substring_get_xxx() functions.  They can be
-       given more than once, and each can specify a group name or number,  for
-       example:
+       given more than once, and each can specify a capture group name or num-
+       ber, for example:


           abcd\=copy=1,copy=3,get=G1


@@ -1887,5 +1887,5 @@

REVISION

-       Last updated: 12 November 2018
-       Copyright (c) 1997-2018 University of Cambridge.
+       Last updated: 03 February 2019
+       Copyright (c) 1997-2019 University of Cambridge.


Modified: code/trunk/doc/pcre2unicode.3
===================================================================
--- code/trunk/doc/pcre2unicode.3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/doc/pcre2unicode.3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1,4 +1,4 @@
-.TH PCRE2UNICODE 3 "12 October 2018" "PCRE2 10.33"
+.TH PCRE2UNICODE 3 "03 February 2019" "PCRE2 10.33"
 .SH NAME
 PCRE - Perl-compatible regular expressions (revised API)
 .SH "UNICODE AND UTF SUPPORT"
@@ -27,10 +27,11 @@
 .rs
 .sp
 When PCRE2 is built with Unicode support, the escape sequences \ep{..},
-\eP{..}, and \eX can be used. The Unicode properties that can be tested are
-limited to the general category properties such as Lu for an upper case letter
-or Nd for a decimal number, the Unicode script names such as Arabic or Han, and
-the derived properties Any and L&. Full lists are given in the
+\eP{..}, and \eX can be used. This is not dependent on the PCRE2_UTF setting.
+The Unicode properties that can be tested are limited to the general category
+properties such as Lu for an upper case letter or Nd for a decimal number, the
+Unicode script names such as Arabic or Han, and the derived properties Any and
+L&. Full lists are given in the
 .\" HREF
 \fBpcre2pattern\fP
 .\"
@@ -62,6 +63,9 @@
 In UTF modes, the dot metacharacter matches one UTF character instead of a
 single code unit.
 .P
+In UTF modes, capture group names are not restricted to ASCII, and may contain
+any Unicode letters and decimal digits, as well as underscore.
+.P
 The escape sequence \eC can be used to match a single code unit in a UTF mode,
 but its use can lead to some strange effects because it breaks up multi-unit
 characters (see the description of \eC in the
@@ -68,7 +72,9 @@
 .\" HREF
 \fBpcre2pattern\fP
 .\"
-documentation).
+documentation). For this reason, there is a build-time option that disables 
+support for \eC completely. There is also a less draconian compile-time option
+for locking out the use of \eC when a pattern is compiled.
 .P
 The use of \eC is not supported by the alternative matching function
 \fBpcre2_dfa_match()\fP when in UTF-8 or UTF-16 mode, that is, when a character
@@ -387,6 +393,6 @@
 .rs
 .sp
 .nf
-Last updated: 12 October 2018
-Copyright (c) 1997-2018 University of Cambridge.
+Last updated: 03 February 2019
+Copyright (c) 1997-2019 University of Cambridge.
 .fi


Modified: code/trunk/src/pcre2_compile.c
===================================================================
--- code/trunk/src/pcre2_compile.c    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/src/pcre2_compile.c    2019-02-06 18:11:36 UTC (rev 1066)
@@ -2194,6 +2194,7 @@
 Arguments:
   ptrptr      points to the character pointer variable
   ptrend      points to the end of the input string
+  utf         true if the input is UTF-encoded
   terminator  the terminator of a subpattern name must be this
   offsetptr   where to put the offset from the start of the pattern
   nameptr     where to put a pointer to the name in the input
@@ -2206,13 +2207,12 @@
 */


static BOOL
-read_name(PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend, uint32_t terminator,
+read_name(PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend, BOOL utf, uint32_t terminator,
PCRE2_SIZE *offsetptr, PCRE2_SPTR *nameptr, uint32_t *namelenptr,
int *errorcodeptr, compile_block *cb)
{
PCRE2_SPTR ptr = *ptrptr;
BOOL is_group = (*ptr != CHAR_ASTERISK);
-uint32_t namelen = 0;

 if (++ptr >= ptrend)               /* No characters in name */
   {
@@ -2221,35 +2221,74 @@
   goto FAILED;
   }


-/* A group name must not start with a digit. If either of the others start with
-a digit it just won't be recognized. */
+*nameptr = ptr;
+*offsetptr = (PCRE2_SIZE)(ptr - cb->start_pattern);

-if (is_group && IS_DIGIT(*ptr))
+/* In UTF mode, a group name may contain letters and decimal digits as defined
+by Unicode properties, and underscores, but must not start with a digit. */
+
+#ifdef SUPPORT_UNICODE
+if (utf && is_group)
   {
-  *errorcodeptr = ERR44;
-  goto FAILED;
+  uint32_t c, type;
+
+  GETCHAR(c, ptr);
+  type = UCD_CHARTYPE(c);
+
+  if (type == ucp_Nd)
+    {
+    *errorcodeptr = ERR44;
+    goto FAILED;
+    }
+
+  for(;;)
+    {
+    if (type != ucp_Nd && PRIV(ucp_gentype)[type] != ucp_L &&
+        c != CHAR_UNDERSCORE) break;
+    ptr++;
+    FORWARDCHAR(ptr);
+    if (ptr >= ptrend) break;
+    GETCHAR(c, ptr);
+    type = UCD_CHARTYPE(c);
+    }
   }
+else
+#else
+(void)utf;  /* Avoid compiler warning */
+#endif      /* SUPPORT_UNICODE */


-*nameptr = ptr;
-*offsetptr = (PCRE2_SIZE)(ptr - cb->start_pattern);
+/* Handle non-group names and group names in non-UTF modes. A group name must
+not start with a digit. If either of the others start with a digit it just
+won't be recognized. */

-while (ptr < ptrend && MAX_255(*ptr) && (cb->ctypes[*ptr] & ctype_word) != 0)
   {
-  ptr++;
-  namelen++;
-  if (namelen > MAX_NAME_SIZE)
+  if (is_group && IS_DIGIT(*ptr))
     {
-    *errorcodeptr = ERR48;
+    *errorcodeptr = ERR44;
     goto FAILED;
     }
+
+  while (ptr < ptrend && MAX_255(*ptr) && (cb->ctypes[*ptr] & ctype_word) != 0)
+    {
+    ptr++;
+    }
   }


+/* Check name length */
+
+if (ptr > *nameptr + MAX_NAME_SIZE)
+ {
+ *errorcodeptr = ERR48;
+ goto FAILED;
+ }
+*namelenptr = ptr - *nameptr;
+
/* Subpattern names must not be empty, and their terminator is checked here.
(What follows a verb or alpha assertion name is checked separately.) */

 if (is_group)
   {
-  if (namelen == 0)
+  if (ptr == *nameptr)
     {
     *errorcodeptr = ERR62;   /* Subpattern name expected */
     goto FAILED;
@@ -2262,7 +2301,6 @@
   ptr++;
   }


-*namelenptr = namelen;
*ptrptr = ptr;
return TRUE;

@@ -2981,7 +3019,7 @@

       /* Not a numerical recursion */


-      if (!read_name(&ptr, ptrend, terminator, &offset, &name, &namelen,
+      if (!read_name(&ptr, ptrend, utf, terminator, &offset, &name, &namelen,
           &errorcode, cb)) goto ESCAPE_FAILED;


       /* \k and \g when used with braces are back references, whereas \g used
@@ -3554,8 +3592,8 @@
         uint32_t meta;


         vn = alasnames;
-        if (!read_name(&ptr, ptrend, 0, &offset, &name, &namelen, &errorcode,
-          cb)) goto FAILED;
+        if (!read_name(&ptr, ptrend, utf, 0, &offset, &name, &namelen,
+          &errorcode, cb)) goto FAILED;
         if (ptr >= ptrend || *ptr != CHAR_COLON)
           {
           errorcode = ERR95;  /* Malformed */
@@ -3651,8 +3689,8 @@
       else
         {
         vn = verbnames;
-        if (!read_name(&ptr, ptrend, 0, &offset, &name, &namelen, &errorcode,
-          cb)) goto FAILED;
+        if (!read_name(&ptr, ptrend, utf, 0, &offset, &name, &namelen,
+          &errorcode, cb)) goto FAILED;
         if (ptr >= ptrend || (*ptr != CHAR_COLON &&
                               *ptr != CHAR_RIGHT_PARENTHESIS))
           {
@@ -3907,7 +3945,7 @@
         errorcode = ERR41;
         goto FAILED;
         }
-      if (!read_name(&ptr, ptrend, CHAR_RIGHT_PARENTHESIS, &offset, &name,
+      if (!read_name(&ptr, ptrend, utf, CHAR_RIGHT_PARENTHESIS, &offset, &name,
           &namelen, &errorcode, cb)) goto FAILED;
       *parsed_pattern++ = META_BACKREF_BYNAME;
       *parsed_pattern++ = namelen;
@@ -3967,7 +4005,7 @@


       case CHAR_AMPERSAND:
       RECURSE_BY_NAME:
-      if (!read_name(&ptr, ptrend, CHAR_RIGHT_PARENTHESIS, &offset, &name,
+      if (!read_name(&ptr, ptrend, utf, CHAR_RIGHT_PARENTHESIS, &offset, &name,
           &namelen, &errorcode, cb)) goto FAILED;
       *parsed_pattern++ = META_RECURSE_BYNAME;
       *parsed_pattern++ = namelen;
@@ -4215,7 +4253,7 @@
           terminator = CHAR_RIGHT_PARENTHESIS;
           ptr--;   /* Point to char before name */
           }
-        if (!read_name(&ptr, ptrend, terminator, &offset, &name, &namelen,
+        if (!read_name(&ptr, ptrend, utf, terminator, &offset, &name, &namelen,
             &errorcode, cb)) goto FAILED;


         /* Handle (?(R&name) */
@@ -4349,7 +4387,7 @@
       terminator = CHAR_APOSTROPHE;    /* Terminator */


       DEFINE_NAME:
-      if (!read_name(&ptr, ptrend, terminator, &offset, &name, &namelen,
+      if (!read_name(&ptr, ptrend, utf, terminator, &offset, &name, &namelen,
           &errorcode, cb)) goto FAILED;


       /* We have a name for this capturing group. It is also assigned a number,


Modified: code/trunk/src/pcre2_error.c
===================================================================
--- code/trunk/src/pcre2_error.c    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/src/pcre2_error.c    2019-02-06 18:11:36 UTC (rev 1066)
@@ -95,7 +95,7 @@
   /* 25 */
   "lookbehind assertion is not fixed length\0"
   "a relative value of zero is not allowed\0"
-  "conditional group contains more than two branches\0"
+  "conditional subpattern contains more than two branches\0"
   "assertion expected after (?( or (?(?C)\0"
   "digit expected after (?+ or (?-\0"
   /* 30 */
@@ -113,14 +113,14 @@
   /* 40 */
   "invalid escape sequence in (*VERB) name\0"
   "unrecognized character after (?P\0"
-  "syntax error in subpattern name (missing terminator)\0"
+  "syntax error in subpattern name (missing terminator?)\0"
   "two named subpatterns have the same name (PCRE2_DUPNAMES not set)\0"
-  "group name must start with a non-digit\0"
+  "subpattern name must start with a non-digit\0"
   /* 45 */
   "this version of PCRE2 does not have support for \\P, \\p, or \\X\0"
   "malformed \\P or \\p sequence\0"
   "unknown property name after \\P or \\p\0"
-  "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0"
+  "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " code units)\0"
   "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0"
   /* 50 */
   "invalid range in character class\0"
@@ -127,7 +127,7 @@
   "octal value is greater than \\377 in 8-bit non-UTF-8 mode\0"
   "internal error: overran compiling workspace\0"
   "internal error: previously-checked referenced subpattern not found\0"
-  "DEFINE group contains more than one branch\0"
+  "DEFINE subpattern contains more than one branch\0"
   /* 55 */
   "missing opening brace after \\o\0"
   "internal error: unknown newline setting\0"
@@ -137,7 +137,7 @@
   "obsolete error (should not occur)\0"  /* Was the above */
   /* 60 */
   "(*VERB) not recognized or malformed\0"
-  "group number is too big\0"
+  "subpattern number is too big\0"
   "subpattern name expected\0"
   "internal error: parsed pattern overflow\0"
   "non-octal character in \\o{} (closing brace missing?)\0"


Modified: code/trunk/src/pcre2test.c
===================================================================
--- code/trunk/src/pcre2test.c    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/src/pcre2test.c    2019-02-06 18:11:36 UTC (rev 1066)
@@ -169,7 +169,7 @@
 /* void vms_setsymbol( char *, char *, int ); Original code from [1]. */
 #endif


-/* VC and older compilers don't support %td or %zu, and even some that claim to
+/* VC and older compilers don't support %td or %zu, and even some that claim to
be C99 don't support it (hence DISABLE_PERCENT_ZT). */

 #if defined(_MSC_VER) || !defined(__STDC_VERSION__) || __STDC_VERSION__ < 199901L || defined(DISABLE_PERCENT_ZT)
@@ -539,7 +539,7 @@
   uint32_t  jitstack;         /* Must be in same position as datctl */
    uint8_t  replacement[REPLACE_MODSIZE];  /* So must this */
   uint32_t  substitute_skip;  /* Must be in same position as patctl */
-  uint32_t  substitute_stop;  /* Must be in same position as patctl */ 
+  uint32_t  substitute_stop;  /* Must be in same position as patctl */
   uint32_t  jit;
   uint32_t  stackguard_test;
   uint32_t  tables_id;
@@ -561,7 +561,7 @@
   uint32_t  jitstack;         /* Must be in same position as patctl */
    uint8_t  replacement[REPLACE_MODSIZE];  /* So must this */
   uint32_t  substitute_skip;  /* Must be in same position as patctl */
-  uint32_t  substitute_stop;  /* Must be in same position as patctl */ 
+  uint32_t  substitute_stop;  /* Must be in same position as patctl */
   uint32_t  startend[2];
   uint32_t  cerror[2];
   uint32_t  cfail[2];
@@ -3049,13 +3049,14 @@




-#ifdef SUPPORT_PCRE2_8
 /*************************************************
 *       Convert character value to UTF-8         *
 *************************************************/


/* This function takes an integer value in the range 0 - 0x7fffffff
-and encodes it as a UTF-8 character in 0 to 6 bytes.
+and encodes it as a UTF-8 character in 0 to 6 bytes. It is needed even when the
+8-bit library is not supported, to generate UTF-8 output for non-ASCII
+characters.

 Arguments:
   cvalue     the character value
@@ -3081,7 +3082,6 @@
 *utf8bytes = utf8_table2[i] | cvalue;
 return i + 1;
 }
-#endif  /* SUPPORT_PCRE2_8 */




@@ -4374,6 +4374,7 @@
show_pattern_info(void)
{
uint32_t compile_options, overall_options, extra_options;
+BOOL utf = (FLD(compiled_code, overall_options) & PCRE2_UTF) != 0;

 if ((pat_patctl.control & (CTL_BINCODE|CTL_FULLBINCODE)) != 0)
   {
@@ -4463,7 +4464,7 @@
       != 0)
     return PR_ABEND;


- fprintf(outfile, "Capturing subpattern count = %d\n", capture_count);
+ fprintf(outfile, "Capture group count = %d\n", capture_count);

   if (backrefmax > 0)
     fprintf(outfile, "Max back reference = %d\n", backrefmax);
@@ -4482,14 +4483,60 @@


   if (namecount > 0)
     {
-    fprintf(outfile, "Named capturing subpatterns:\n");
+    fprintf(outfile, "Named capture groups:\n");
     for (; namecount > 0; namecount--)
       {
       int imm2_size = test_mode == PCRE8_MODE ? 2 : 1;
       uint32_t length = (uint32_t)STRLEN(nametable + imm2_size);
       fprintf(outfile, "  ");
-      PCHARSV(nametable, imm2_size, length, FALSE, outfile);
+
+      /* In UTF mode the name may be a UTF string containing non-ASCII
+      letters and digits. We must output it as a UTF-8 string. In non-UTF mode,
+      use the normal string printing functions, which use escapes for all
+      non-ASCII characters. */
+
+      if (utf)
+        {
+#ifdef SUPPORT_PCRE2_32
+        if (test_mode == PCRE32_MODE)
+          {
+          PCRE2_SPTR32 nameptr = (PCRE2_SPTR32)nametable + imm2_size;
+          while (*nameptr != 0)
+            {
+            uint8_t u8buff[6];
+            int len = ord2utf8(*nameptr++, u8buff);
+            fprintf(outfile, "%.*s", len, u8buff);
+            }
+          }
+#endif
+#ifdef SUPPORT_PCRE2_16
+        if (test_mode == PCRE16_MODE)
+          {
+          PCRE2_SPTR16 nameptr = (PCRE2_SPTR16)nametable + imm2_size;
+          while (*nameptr != 0)
+            {
+            int len;
+            uint8_t u8buff[6];
+            uint32_t c = *nameptr++ & 0xffff;
+            if (c >= 0xD800 && c < 0xDC00)
+              c = ((c & 0x3ff) << 10) + (*nameptr++ & 0x3ff) + 0x10000;
+            len = ord2utf8(c, u8buff);
+            fprintf(outfile, "%.*s", len, u8buff);
+            }
+          }
+#endif
+#ifdef SUPPORT_PCRE2_8
+        if (test_mode == PCRE8_MODE)
+          fprintf(outfile, "%s", (PCRE2_SPTR8)nametable + imm2_size);
+#endif
+        }
+      else  /* Not UTF mode */
+        {
+        PCHARSV(nametable, imm2_size, length, FALSE, outfile);
+        }
+
       while (length++ < nameentrysize - imm2_size) putc(' ', outfile);
+
 #ifdef SUPPORT_PCRE2_32
       if (test_mode == PCRE32_MODE)
         fprintf(outfile, "%3d\n", (int)(((PCRE2_SPTR32)nametable)[0]));
@@ -4503,6 +4550,7 @@
         fprintf(outfile, "%3d\n", (int)(
         ((((PCRE2_SPTR8)nametable)[0]) << 8) | ((PCRE2_SPTR8)nametable)[1]));
 #endif
+
       nametable = (void*)((PCRE2_SPTR8)nametable + nameentrysize * code_unit_size);
       }
     }
@@ -5971,30 +6019,30 @@
 (void)data_ptr;   /* Not used */


fprintf(outfile, "%2d(%d) Old %" SIZ_FORM " %" SIZ_FORM " \"",
- scb->subscount, scb->oveccount,
+ scb->subscount, scb->oveccount,
SIZ_CAST scb->ovector[0], SIZ_CAST scb->ovector[1]);

-PCHARSV(scb->input, scb->ovector[0], scb->ovector[1] - scb->ovector[0],
+PCHARSV(scb->input, scb->ovector[0], scb->ovector[1] - scb->ovector[0],
utf, outfile);

fprintf(outfile, "\" New %" SIZ_FORM " %" SIZ_FORM " \"",
SIZ_CAST scb->output_offsets[0], SIZ_CAST scb->output_offsets[1]);

-PCHARSV(scb->output, scb->output_offsets[0],
+PCHARSV(scb->output, scb->output_offsets[0],
scb->output_offsets[1] - scb->output_offsets[0], utf, outfile);

-if (scb->subscount == dat_datctl.substitute_stop)
+if (scb->subscount == dat_datctl.substitute_stop)
{
yield = -1;
- fprintf(outfile, " STOPPED");
- }
-else if (scb->subscount == dat_datctl.substitute_skip)
+ fprintf(outfile, " STOPPED");
+ }
+else if (scb->subscount == dat_datctl.substitute_skip)
{
yield = +1;
- fprintf(outfile, " SKIPPED");
- }
+ fprintf(outfile, " SKIPPED");
+ }

-fprintf(outfile, "\"\n");
+fprintf(outfile, "\"\n");
return yield;
}

@@ -6867,11 +6915,11 @@

if (p[-1] != 0 && !decode_modifiers(p, CTX_DAT, NULL, &dat_datctl))
return PR_OK;
-
-/* Setting substitute_{skip,fail} implies a substitute callout. */

+/* Setting substitute_{skip,fail} implies a substitute callout. */
+
if (dat_datctl.substitute_skip != 0 || dat_datctl.substitute_stop != 0)
- dat_datctl.control2 |= CTL2_SUBSTITUTE_CALLOUT;
+ dat_datctl.control2 |= CTL2_SUBSTITUTE_CALLOUT;

 /* Check for mutually exclusive modifiers. At present, these are all in the
 first control word. */
@@ -8129,7 +8177,7 @@
     break;
     }


-/* For VMS, return the value by setting a symbol, for certain values only. This
+/* For VMS, return the value by setting a symbol, for certain values only. This
is contributed code which the PCRE2 developers have no means of testing. */

#ifdef __VMS

Modified: code/trunk/testdata/testinput10
===================================================================
--- code/trunk/testdata/testinput10    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testinput10    2019-02-06 18:11:36 UTC (rev 1066)
@@ -480,5 +480,13 @@


 /(?<=abc)(|def)/g,utf,replace=<$0>,substitute_callout
     123abcáyzabcdef789abcሴqr
+    
+# Check name length with non-ASCII characters 


+/(?'ABáC678901234567890123456789012'...)/utf
+
+/(?'ABáC6789012345678901234567890123'...)/utf
+
+/(?'ABZC6789012345678901234567890123'...)/utf
+
# End of testinput10

Modified: code/trunk/testdata/testinput4
===================================================================
--- code/trunk/testdata/testinput4    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testinput4    2019-02-06 18:11:36 UTC (rev 1066)
@@ -2457,4 +2457,27 @@


# -------

+# Test group names containing non-ASCII letters and digits
+
+/(?'ABáC'...)\g{ABáC}/utf
+    abcabcdefg
+
+/(?'XʰABC'...)/utf
+    xyzpq
+
+/(?'XאABC'...)/utf
+    12345
+
+/(?'XᾈABC'...)/utf
+    %^&*(...
+
+/(?'𐨐ABC'...)/utf
+    abcde
+
+/^(?'אABC'...)(?&אABC)(?P=אABC)/utf
+    123123123456
+
+/^(?'אABC'...)(?&אABC)/utf
+    123123123456
+
 # End of testinput4


Modified: code/trunk/testdata/testinput5
===================================================================
--- code/trunk/testdata/testinput5    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testinput5    2019-02-06 18:11:36 UTC (rev 1066)
@@ -2152,4 +2152,19 @@


# -------

+# Test reference and errors in non-ASCII characters in group names
+
+/(?'𑠅ABC'...)/I,utf
+ abcde\=copy=𑠅ABC
+
+# Bad ones
+
+/(?'AB၌C'...)\g{AB၌C}/utf
+
+/(?'٠ABC'...)/utf
+
+/(?'²ABC'...)/utf
+
+/(?'X²ABC'...)/utf
+
# End of testinput5

Modified: code/trunk/testdata/testoutput10
===================================================================
--- code/trunk/testdata/testoutput10    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput10    2019-02-06 18:11:36 UTC (rev 1066)
@@ -248,7 +248,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc4
 Last code unit = \x80
@@ -261,7 +261,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xe1
 Last code unit = \x80
@@ -274,7 +274,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xf0
 Last code unit = \x80
@@ -287,7 +287,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xf4
 Last code unit = \x80
@@ -300,7 +300,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xf4
 Last code unit = \xbf
@@ -313,7 +313,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc3
 Last code unit = \xbf
@@ -326,7 +326,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc4
 Last code unit = \x80
@@ -339,7 +339,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc2
 Last code unit = \x80
@@ -352,7 +352,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc3
 Last code unit = \xbf
@@ -365,7 +365,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xed
 Last code unit = \xb4
@@ -380,7 +380,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xe6
 Last code unit = \x9e
@@ -395,7 +395,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc2
 Last code unit = \x80
@@ -408,7 +408,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc2
 Last code unit = \x84
@@ -421,7 +421,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc4
 Last code unit = \x84
@@ -434,7 +434,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xe0
 Last code unit = \xa1
@@ -447,7 +447,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xf0
 Last code unit = \xab
@@ -460,7 +460,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
@@ -495,7 +495,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc4
 Last code unit = \x80
@@ -514,7 +514,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: x \xc4 
 Subject length lower bound = 1
@@ -531,7 +531,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: a x \xc4 
 Subject length lower bound = 1
@@ -548,7 +548,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: a x \xc4 
 Subject length lower bound = 1
@@ -566,7 +566,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: x \xc4 
 Subject length lower bound = 1
@@ -578,7 +578,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc4
 Last code unit = \x80
@@ -592,7 +592,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'a'
 Last code unit = \x80
@@ -606,7 +606,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'a'
 Last code unit = \x81
@@ -619,7 +619,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


 /[\x{100}]/IB,utf
@@ -629,7 +629,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc4
 Last code unit = \x80
@@ -648,7 +648,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc3
 Last code unit = \xbf
@@ -663,7 +663,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 1


@@ -678,7 +678,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 First code unit = \xc4
 Last code unit = 'z'
@@ -685,7 +685,7 @@
 Subject length lower bound = 7


 /\777/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc7
 Last code unit = \xbf
@@ -703,7 +703,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc4
 Last code unit = \x80
@@ -717,7 +717,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc4
 Last code unit = 'X'
@@ -761,7 +761,7 @@
  0: \x{1234}


/(*CRLF)(*UTF)(*BSR_UNICODE)a\Rb/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: utf
\R matches any Unicode newline
@@ -771,7 +771,7 @@
Subject length lower bound = 3

/\h/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x20 \xc2 \xe1 \xe2 \xe3
Subject length lower bound = 1
@@ -795,7 +795,7 @@
0: \x{3000}

/\v/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x0a \x0b \x0c \x0d \xc2 \xe2
Subject length lower bound = 1
@@ -813,7 +813,7 @@
0: \x{2028}

/\h*A/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x20 A \xc2 \xe1 \xe2 \xe3
Last code unit = 'A'
@@ -822,7 +822,7 @@
0: A

/\v+A/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x0a \x0b \x0c \x0d \xc2 \xe2
Last code unit = 'A'
@@ -829,7 +829,7 @@
Subject length lower bound = 2

/\s?xxx\s/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 x
Last code unit = 'x'
@@ -836,7 +836,7 @@
Subject length lower bound = 4

/\sxxx\s/I,utf,tables=2
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 \xc2
Last code unit = 'x'
@@ -847,7 +847,7 @@
0: \x{a0}xxx\x{85}

/\S \S/I,utf,tables=2
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0e \x0f
\x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d \x1e
@@ -883,25 +883,25 @@
No match

/\x{1234}+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Starting code units: \xe1
Subject length lower bound = 1

/\x{1234}+?/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Starting code units: \xe1
Subject length lower bound = 1

/\x{1234}++/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Starting code units: \xe1
Subject length lower bound = 1

 /\x{1234}{2}/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: \xe1 
 Subject length lower bound = 2
@@ -913,7 +913,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 1


@@ -925,7 +925,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'X'
 Last code unit = \x80
@@ -932,7 +932,7 @@
 Subject length lower bound = 2


 /\R/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x0a \x0b \x0c \x0d \xc2 \xe2 
 Subject length lower bound = 1
@@ -944,7 +944,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xc7
 Last code unit = \xbf
@@ -1105,7 +1105,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 First code unit = 'A' (caseless)
 Subject length lower bound = 5
@@ -1117,7 +1117,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = \xb0
@@ -1130,7 +1130,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = \xb0
@@ -1143,7 +1143,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 First code unit = 'A' (caseless)
 Last code unit = 'B' (caseless)
@@ -1150,7 +1150,7 @@
 Subject length lower bound = 3


/\x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f}/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Starting code units: \xd0 \xd1
Subject length lower bound = 17
@@ -1176,17 +1176,17 @@
------------------------------------------------------------------

/\h/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: \x09 \x20 \xa0
Subject length lower bound = 1

/\v/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: \x0a \x0b \x0c \x0d \x85
Subject length lower bound = 1

/\R/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: \x0a \x0b \x0c \x0d \x85
Subject length lower bound = 1

@@ -1199,7 +1199,7 @@
------------------------------------------------------------------

/\x{212a}+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Starting code units: K k \xe2
Subject length lower bound = 1
@@ -1207,7 +1207,7 @@
0: KKkk\x{212a}

 /s+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: S s \xc5 
 Subject length lower bound = 1
@@ -1222,7 +1222,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: A \xc4 
 Last code unit = 'A'
@@ -1239,7 +1239,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: 0 1 2 3 4 5 6 7 8 9 \xc4 
 Subject length lower bound = 1
@@ -1251,7 +1251,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: Z \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd 
   \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc 
@@ -1273,7 +1273,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: z { | } ~ \x7f \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 
   \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 
@@ -1289,7 +1289,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: - ] a d z \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc 
   \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb 
@@ -1314,7 +1314,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: a b \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd 
   \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc 
@@ -1332,7 +1332,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 \xc4 
 Subject length lower bound = 1
@@ -1345,7 +1345,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: 0 1 2 3 4 5 6 7 8 9 \xc4 
 Subject length lower bound = 1
@@ -1358,7 +1358,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
   Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
@@ -1373,7 +1373,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
@@ -1395,7 +1395,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0e \x0f 
   \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d \x1e 
@@ -1416,7 +1416,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
@@ -1435,7 +1435,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce 
   \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd 
@@ -1462,7 +1462,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: Z z { | } ~ \x7f \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 
   \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 
@@ -1503,7 +1503,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: Z z { | } ~ \x7f \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 
   \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 
@@ -1520,7 +1520,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: \xce \xcf 
 Last code unit = 'B' (caseless)
@@ -1531,7 +1531,7 @@
 Failed: error -3: UTF-8 error: 1 byte missing at end


/(?<=(a)(?-1))x/I,utf
-Capturing subpattern count = 1
+Capture group count = 1
Max lookbehind = 2
Options: utf
First code unit = 'x'
@@ -1579,7 +1579,7 @@
# but subjects containing them must not be UTF-checked.

 /\x{d800}/I,utf,allow_surrogate_escapes
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Extra options: allow_surrogate_escapes
 First code unit = \xed
@@ -1602,7 +1602,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: utf
 Overall options: anchored utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
@@ -1635,5 +1635,14 @@
  3(2) Old 13 16 "def" New 17 22 "<def>"
  4(2) Old 22 22 "" New 28 30 "<>"
  4: 123abc<>\x{e1}yzabc<><def>789abc<>\x{1234}qr
+    
+# Check name length with non-ASCII characters 


+/(?'ABáC678901234567890123456789012'...)/utf
+
+/(?'ABáC6789012345678901234567890123'...)/utf
+Failed: error 148 at offset 36: subpattern name is too long (maximum 32 code units)
+
+/(?'ABZC6789012345678901234567890123'...)/utf
+
# End of testinput10

Modified: code/trunk/testdata/testoutput11-16
===================================================================
--- code/trunk/testdata/testoutput11-16    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput11-16    2019-02-06 18:11:36 UTC (rev 1066)
@@ -13,11 +13,11 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


/\x{100}/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = \x{100}
Subject length lower bound = 1

@@ -215,7 +215,7 @@
 (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
 \)  )*                       # optional trailing comment
 /Ix
-Capturing subpattern count = 0
+Capture group count = 0
 Contains explicit CR or LF match
 Options: extended
 Starting code units: \x09 \x20 ! " # $ % & ' ( * + - / 0 1 2 3 4 5 6 7 8 
@@ -260,7 +260,7 @@
 ------------------------------------------------------------------


 /\h+/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x09 \x20 \xa0 \xff 
 Subject length lower bound = 1
     \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
@@ -275,7 +275,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x09 \x20 \xa0 \xff 
 Subject length lower bound = 1
     \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
@@ -284,7 +284,7 @@
  0: \x{200a}\xa0\x{2000}


 /\H+/I
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1
     \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f}
  0: \x{167f}\x{1681}\x{180d}\x{180f}
@@ -306,7 +306,7 @@
  0: \x9f\xa1\x{2fff}\x{3001}


 /\v+/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x0a \x0b \x0c \x0d \x85 \xff 
 Subject length lower bound = 1
     \x{2027}\x{2030}\x{2028}\x{2029}
@@ -321,7 +321,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x0a \x0b \x0c \x0d \x85 \xff 
 Subject length lower bound = 1
     \x{2027}\x{2030}\x{2028}\x{2029}
@@ -330,7 +330,7 @@
  0: \x85\x0a\x0b\x0c\x0d


 /\V+/I
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1
     \x{2028}\x{2029}\x{2027}\x{2030}
  0: \x{2027}\x{2030}
@@ -344,7 +344,7 @@
  0: \x09\x0e\x84\x86


/\R+/I,bsr=unicode
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
Starting code units: \x0a \x0b \x0c \x0d \x85 \xff
Subject length lower bound = 1
@@ -354,7 +354,7 @@
0: \x85\x0a\x0b\x0c\x0d

 /\x{d800}\x{d7ff}\x{dc00}\x{dc00}\x{dcff}\x{dd00}/I
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = \x{d800}
 Last code unit = \x{dd00}
 Subject length lower bound = 6
@@ -600,7 +600,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0a \x0b 
   \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a 
   \x1b \x1c \x1d \x1e \x1f ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 
@@ -624,7 +624,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0e 
   \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d 
   \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : ; < = > 


Modified: code/trunk/testdata/testoutput11-32
===================================================================
--- code/trunk/testdata/testoutput11-32    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput11-32    2019-02-06 18:11:36 UTC (rev 1066)
@@ -13,11 +13,11 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


/\x{100}/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = \x{100}
Subject length lower bound = 1

@@ -215,7 +215,7 @@
 (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
 \)  )*                       # optional trailing comment
 /Ix
-Capturing subpattern count = 0
+Capture group count = 0
 Contains explicit CR or LF match
 Options: extended
 Starting code units: \x09 \x20 ! " # $ % & ' ( * + - / 0 1 2 3 4 5 6 7 8 
@@ -260,7 +260,7 @@
 ------------------------------------------------------------------


 /\h+/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x09 \x20 \xa0 \xff 
 Subject length lower bound = 1
     \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
@@ -275,7 +275,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x09 \x20 \xa0 \xff 
 Subject length lower bound = 1
     \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
@@ -284,7 +284,7 @@
  0: \x{200a}\xa0\x{2000}


 /\H+/I
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1
     \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f}
  0: \x{167f}\x{1681}\x{180d}\x{180f}
@@ -306,7 +306,7 @@
  0: \x9f\xa1\x{2fff}\x{3001}


 /\v+/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x0a \x0b \x0c \x0d \x85 \xff 
 Subject length lower bound = 1
     \x{2027}\x{2030}\x{2028}\x{2029}
@@ -321,7 +321,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x0a \x0b \x0c \x0d \x85 \xff 
 Subject length lower bound = 1
     \x{2027}\x{2030}\x{2028}\x{2029}
@@ -330,7 +330,7 @@
  0: \x85\x0a\x0b\x0c\x0d


 /\V+/I
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1
     \x{2028}\x{2029}\x{2027}\x{2030}
  0: \x{2027}\x{2030}
@@ -344,7 +344,7 @@
  0: \x09\x0e\x84\x86


/\R+/I,bsr=unicode
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
Starting code units: \x0a \x0b \x0c \x0d \x85 \xff
Subject length lower bound = 1
@@ -354,7 +354,7 @@
0: \x85\x0a\x0b\x0c\x0d

/\x{d800}\x{d7ff}\x{dc00}\x{dc00}\x{dcff}\x{dd00}/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = \x{d800}
Last code unit = \x{dd00}
Subject length lower bound = 6
@@ -558,19 +558,19 @@
Failed: error 134 at offset 14: character code point value in \x{} or \o{} is too large

/\x{7fffffff}\x{7fffffff}/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = \x{7fffffff}
Last code unit = \x{7fffffff}
Subject length lower bound = 2

/\x{80000000}\x{80000000}/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = \x{80000000}
Last code unit = \x{80000000}
Subject length lower bound = 2

 /\x{ffffffff}\x{ffffffff}/I
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = \x{ffffffff}
 Last code unit = \x{ffffffff}
 Subject length lower bound = 2
@@ -588,7 +588,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless
 First code unit = \x{400000}
 Last code unit = \x{800000}
@@ -603,7 +603,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0a \x0b 
   \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a 
   \x1b \x1c \x1d \x1e \x1f ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 
@@ -627,7 +627,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0e 
   \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d 
   \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : ; < = > 


Modified: code/trunk/testdata/testoutput12-16
===================================================================
--- code/trunk/testdata/testoutput12-16    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput12-16    2019-02-06 18:11:36 UTC (rev 1066)
@@ -18,7 +18,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{ffff}
 Subject length lower bound = 1
@@ -30,7 +30,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d800}
 Last code unit = \x{dc00}
@@ -43,7 +43,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Subject length lower bound = 1
@@ -55,7 +55,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{1000}
 Subject length lower bound = 1
@@ -67,7 +67,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d800}
 Last code unit = \x{dc00}
@@ -80,7 +80,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{dbc0}
 Last code unit = \x{dc00}
@@ -93,7 +93,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{dbff}
 Last code unit = \x{dfff}
@@ -106,7 +106,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xff
 Subject length lower bound = 1
@@ -118,7 +118,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Subject length lower bound = 1
@@ -130,7 +130,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x80
 Subject length lower bound = 1
@@ -142,7 +142,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xff
 Subject length lower bound = 1
@@ -154,7 +154,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d55c}
 Last code unit = \x{c5b4}
@@ -169,7 +169,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{65e5}
 Last code unit = \x{8a9e}
@@ -184,7 +184,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x80
 Subject length lower bound = 1
@@ -196,7 +196,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x84
 Subject length lower bound = 1
@@ -208,7 +208,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{104}
 Subject length lower bound = 1
@@ -220,7 +220,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{861}
 Subject length lower bound = 1
@@ -232,7 +232,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d844}
 Last code unit = \x{deab}
@@ -245,7 +245,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
@@ -281,7 +281,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Last code unit = \x{100}
@@ -300,7 +300,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: x \xff 
 Subject length lower bound = 1
@@ -317,7 +317,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: a x \xff 
 Subject length lower bound = 1
@@ -334,7 +334,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: a x \xff 
 Subject length lower bound = 1
@@ -352,7 +352,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: x \xff 
 Subject length lower bound = 1
@@ -364,7 +364,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Subject length lower bound = 1
@@ -377,7 +377,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'a'
 Last code unit = \x{100}
@@ -391,7 +391,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'a'
 Last code unit = \x{101}
@@ -404,7 +404,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


 /[\x{100}]/IB,utf
@@ -414,7 +414,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Subject length lower bound = 1
@@ -432,7 +432,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xff
 Subject length lower bound = 1
@@ -446,7 +446,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 1


@@ -461,7 +461,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 First code unit = \x{100}
 Last code unit = 'z'
@@ -468,7 +468,7 @@
 Subject length lower bound = 7


 /\777/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{1ff}
 Subject length lower bound = 1
@@ -485,7 +485,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Last code unit = \x{200}
@@ -499,7 +499,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Last code unit = 'X'
@@ -547,7 +547,7 @@
  0: \x{11234}


/(*UTF)\x{11234}/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: utf
First code unit = \x{d804}
@@ -565,7 +565,7 @@
abcd\x{11234}pqr

/(*CRLF)(*UTF16)(*BSR_UNICODE)a\Rb/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: utf
\R matches any Unicode newline
@@ -578,7 +578,7 @@
Failed: error 160 at offset 14: (*VERB) not recognized or malformed

/\h/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x20 \xa0 \xff
Subject length lower bound = 1
@@ -602,7 +602,7 @@
0: \x{3000}

/\v/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x0a \x0b \x0c \x0d \x85 \xff
Subject length lower bound = 1
@@ -620,7 +620,7 @@
0: \x{2028}

/\h*A/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x20 A \xa0 \xff
Last code unit = 'A'
@@ -631,7 +631,7 @@
0: \x{2000}A

/\R*A/I,bsr=unicode,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches any Unicode newline
Starting code units: \x0a \x0b \x0c \x0d A \x85 \xff
@@ -643,7 +643,7 @@
0: \x{2028}A

/\v+A/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x0a \x0b \x0c \x0d \x85 \xff
Last code unit = 'A'
@@ -650,7 +650,7 @@
Subject length lower bound = 2

/\s?xxx\s/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 x
Last code unit = 'x'
@@ -657,7 +657,7 @@
Subject length lower bound = 4

/\sxxx\s/I,utf,tables=2
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 \x85 \xa0
Last code unit = 'x'
@@ -668,7 +668,7 @@
0: \x{a0}xxx\x{85}

/\S \S/I,utf,tables=2
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0e \x0f
\x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d \x1e
@@ -708,25 +708,25 @@
Failed: error -33: bad offset value

/\x{1234}+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
First code unit = \x{1234}
Subject length lower bound = 1

/\x{1234}+?/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
First code unit = \x{1234}
Subject length lower bound = 1

/\x{1234}++/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
First code unit = \x{1234}
Subject length lower bound = 1

 /\x{1234}{2}/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 First code unit = \x{1234}
 Last code unit = \x{1234}
@@ -739,7 +739,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 1


@@ -751,7 +751,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'X'
 Last code unit = \x{200}
@@ -758,7 +758,7 @@
 Subject length lower bound = 2


 /\R/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x0a \x0b \x0c \x0d \x85 \xff 
 Subject length lower bound = 1
@@ -936,7 +936,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 First code unit = 'A' (caseless)
 Last code unit = \x{1fb0} (caseless)
@@ -949,7 +949,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = \x{1fb0}
@@ -962,7 +962,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = \x{1fb0}
@@ -975,7 +975,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 First code unit = 'A' (caseless)
 Last code unit = \x{1fb0} (caseless)
@@ -982,7 +982,7 @@
 Subject length lower bound = 3


/\x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f}/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
First code unit = \x{401} (caseless)
Last code unit = \x{42f} (caseless)
@@ -1017,7 +1017,7 @@
------------------------------------------------------------------

/\x{212a}+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Starting code units: K k \xff
Subject length lower bound = 1
@@ -1025,7 +1025,7 @@
0: KKkk\x{212a}

 /s+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: S s \xff 
 Subject length lower bound = 1
@@ -1048,7 +1048,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: A \xff 
 Last code unit = 'A'
@@ -1065,7 +1065,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: 0 1 2 3 4 5 6 7 8 9 \xff 
 Subject length lower bound = 1
@@ -1077,7 +1077,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: Z \xff 
 Subject length lower bound = 1
@@ -1095,7 +1095,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: z { | } ~ \x7f \x80 \x81 \x82 \x83 \x84 \x85 \x86 \x87 
   \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 \x93 \x94 \x95 \x96 
@@ -1115,7 +1115,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: - ] a d z \xff 
 Subject length lower bound = 1
@@ -1136,7 +1136,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: a b \xff 
 Last code unit = 'z'
@@ -1150,7 +1150,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 \xff 
 Subject length lower bound = 1
@@ -1163,7 +1163,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: 0 1 2 3 4 5 6 7 8 9 \xff 
 Subject length lower bound = 1
@@ -1176,7 +1176,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
   Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
@@ -1191,7 +1191,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
@@ -1217,7 +1217,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0e \x0f 
   \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d \x1e 
@@ -1243,7 +1243,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
@@ -1266,7 +1266,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: \xff 
 Subject length lower bound = 1
@@ -1289,7 +1289,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: Z z { | } ~ \x7f \x80 \x81 \x82 \x83 \x84 \x85 \x86 
   \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 \x93 \x94 \x95 
@@ -1335,7 +1335,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: Z z { | } ~ \x7f \x80 \x81 \x82 \x83 \x84 \x85 \x86 
   \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 \x93 \x94 \x95 
@@ -1357,7 +1357,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: \xff 
 Last code unit = 'B' (caseless)
@@ -1443,7 +1443,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: utf
 Overall options: anchored utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 


Modified: code/trunk/testdata/testoutput12-32
===================================================================
--- code/trunk/testdata/testoutput12-32    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput12-32    2019-02-06 18:11:36 UTC (rev 1066)
@@ -18,7 +18,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{ffff}
 Subject length lower bound = 1
@@ -30,7 +30,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{10000}
 Subject length lower bound = 1
@@ -42,7 +42,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Subject length lower bound = 1
@@ -54,7 +54,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{1000}
 Subject length lower bound = 1
@@ -66,7 +66,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{10000}
 Subject length lower bound = 1
@@ -78,7 +78,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100000}
 Subject length lower bound = 1
@@ -90,7 +90,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{10ffff}
 Subject length lower bound = 1
@@ -102,7 +102,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xff
 Subject length lower bound = 1
@@ -114,7 +114,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Subject length lower bound = 1
@@ -126,7 +126,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x80
 Subject length lower bound = 1
@@ -138,7 +138,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xff
 Subject length lower bound = 1
@@ -150,7 +150,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d55c}
 Last code unit = \x{c5b4}
@@ -165,7 +165,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{65e5}
 Last code unit = \x{8a9e}
@@ -180,7 +180,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x80
 Subject length lower bound = 1
@@ -192,7 +192,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x84
 Subject length lower bound = 1
@@ -204,7 +204,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{104}
 Subject length lower bound = 1
@@ -216,7 +216,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{861}
 Subject length lower bound = 1
@@ -228,7 +228,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{212ab}
 Subject length lower bound = 1
@@ -240,7 +240,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
@@ -276,7 +276,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Last code unit = \x{100}
@@ -295,7 +295,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: x \xff 
 Subject length lower bound = 1
@@ -312,7 +312,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: a x \xff 
 Subject length lower bound = 1
@@ -329,7 +329,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: a x \xff 
 Subject length lower bound = 1
@@ -347,7 +347,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: x \xff 
 Subject length lower bound = 1
@@ -359,7 +359,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Subject length lower bound = 1
@@ -372,7 +372,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'a'
 Last code unit = \x{100}
@@ -386,7 +386,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'a'
 Last code unit = \x{101}
@@ -399,7 +399,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


 /[\x{100}]/IB,utf
@@ -409,7 +409,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Subject length lower bound = 1
@@ -427,7 +427,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xff
 Subject length lower bound = 1
@@ -441,7 +441,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 1


@@ -456,7 +456,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 First code unit = \x{100}
 Last code unit = 'z'
@@ -463,7 +463,7 @@
 Subject length lower bound = 7


 /\777/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{1ff}
 Subject length lower bound = 1
@@ -480,7 +480,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Last code unit = \x{200}
@@ -494,7 +494,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{100}
 Last code unit = 'X'
@@ -542,7 +542,7 @@
   abcd\x{11234}pqr


/(*UTF)\x{11234}/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: utf
First code unit = \x{11234}
@@ -562,7 +562,7 @@
Failed: error 160 at offset 14: (*VERB) not recognized or malformed

/(*CRLF)(*UTF32)(*BSR_UNICODE)a\Rb/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: utf
\R matches any Unicode newline
@@ -572,7 +572,7 @@
Subject length lower bound = 3

/\h/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x20 \xa0 \xff
Subject length lower bound = 1
@@ -596,7 +596,7 @@
0: \x{3000}

/\v/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x0a \x0b \x0c \x0d \x85 \xff
Subject length lower bound = 1
@@ -614,7 +614,7 @@
0: \x{2028}

/\h*A/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x20 A \xa0 \xff
Last code unit = 'A'
@@ -625,7 +625,7 @@
0: \x{2000}A

/\R*A/I,bsr=unicode,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches any Unicode newline
Starting code units: \x0a \x0b \x0c \x0d A \x85 \xff
@@ -637,7 +637,7 @@
0: \x{2028}A

/\v+A/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x0a \x0b \x0c \x0d \x85 \xff
Last code unit = 'A'
@@ -644,7 +644,7 @@
Subject length lower bound = 2

/\s?xxx\s/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 x
Last code unit = 'x'
@@ -651,7 +651,7 @@
Subject length lower bound = 4

/\sxxx\s/I,utf,tables=2
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 \x85 \xa0
Last code unit = 'x'
@@ -662,7 +662,7 @@
0: \x{a0}xxx\x{85}

/\S \S/I,utf,tables=2
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0e \x0f
\x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d \x1e
@@ -702,25 +702,25 @@
Failed: error -33: bad offset value

/\x{1234}+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
First code unit = \x{1234}
Subject length lower bound = 1

/\x{1234}+?/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
First code unit = \x{1234}
Subject length lower bound = 1

/\x{1234}++/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
First code unit = \x{1234}
Subject length lower bound = 1

 /\x{1234}{2}/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 First code unit = \x{1234}
 Last code unit = \x{1234}
@@ -733,7 +733,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 1


@@ -745,7 +745,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'X'
 Last code unit = \x{200}
@@ -752,7 +752,7 @@
 Subject length lower bound = 2


 /\R/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x0a \x0b \x0c \x0d \x85 \xff 
 Subject length lower bound = 1
@@ -930,7 +930,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 First code unit = 'A' (caseless)
 Last code unit = \x{1fb0} (caseless)
@@ -943,7 +943,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = \x{1fb0}
@@ -956,7 +956,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = \x{1fb0}
@@ -969,7 +969,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 First code unit = 'A' (caseless)
 Last code unit = \x{1fb0} (caseless)
@@ -976,7 +976,7 @@
 Subject length lower bound = 3


/\x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f}/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
First code unit = \x{401} (caseless)
Last code unit = \x{42f} (caseless)
@@ -1011,7 +1011,7 @@
------------------------------------------------------------------

/\x{212a}+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Starting code units: K k \xff
Subject length lower bound = 1
@@ -1019,7 +1019,7 @@
0: KKkk\x{212a}

 /s+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: S s \xff 
 Subject length lower bound = 1
@@ -1042,7 +1042,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: A \xff 
 Last code unit = 'A'
@@ -1059,7 +1059,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: 0 1 2 3 4 5 6 7 8 9 \xff 
 Subject length lower bound = 1
@@ -1071,7 +1071,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: Z \xff 
 Subject length lower bound = 1
@@ -1089,7 +1089,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: z { | } ~ \x7f \x80 \x81 \x82 \x83 \x84 \x85 \x86 \x87 
   \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 \x93 \x94 \x95 \x96 
@@ -1109,7 +1109,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: - ] a d z \xff 
 Subject length lower bound = 1
@@ -1130,7 +1130,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Starting code units: a b \xff 
 Last code unit = 'z'
@@ -1144,7 +1144,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 \xff 
 Subject length lower bound = 1
@@ -1157,7 +1157,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: 0 1 2 3 4 5 6 7 8 9 \xff 
 Subject length lower bound = 1
@@ -1170,7 +1170,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
   Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
@@ -1185,7 +1185,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
@@ -1211,7 +1211,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0e \x0f 
   \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d \x1e 
@@ -1237,7 +1237,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
@@ -1260,7 +1260,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: \xff 
 Subject length lower bound = 1
@@ -1283,7 +1283,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: Z z { | } ~ \x7f \x80 \x81 \x82 \x83 \x84 \x85 \x86 
   \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 \x93 \x94 \x95 
@@ -1329,7 +1329,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: Z z { | } ~ \x7f \x80 \x81 \x82 \x83 \x84 \x85 \x86 
   \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 \x93 \x94 \x95 
@@ -1351,7 +1351,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 Starting code units: \xff 
 Last code unit = 'B' (caseless)
@@ -1418,7 +1418,7 @@
 # errors in 16-bit mode.


 /\x{d800}/I,utf,allow_surrogate_escapes
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Extra options: allow_surrogate_escapes
 First code unit = \x{d800}
@@ -1440,7 +1440,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: utf
 Overall options: anchored utf
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 


Modified: code/trunk/testdata/testoutput15
===================================================================
--- code/trunk/testdata/testoutput15    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput15    2019-02-06 18:11:36 UTC (rev 1066)
@@ -7,7 +7,7 @@
 # (2) Other tests that must not be run with JIT.


/(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a z
Last code unit = 'z'
Subject length lower bound = 2
@@ -24,7 +24,7 @@
No match

 !((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)!I
-Capturing subpattern count = 1
+Capture group count = 1
 May match empty string
 Subject length lower bound = 0
    /* this is a C style comment */\=find_limits
@@ -117,7 +117,7 @@
 Failed: error 160 at offset 24: (*VERB) not recognized or malformed


/(*LIMIT_DEPTH=4294967280)abc/I
-Capturing subpattern count = 0
+Capture group count = 0
Depth limit = 4294967280
First code unit = 'a'
Last code unit = 'c'
@@ -137,7 +137,7 @@
Failed: error -53: matching depth limit exceeded

/(*LIMIT_MATCH=3000)(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Match limit = 3000
Starting code units: a z
Last code unit = 'z'
@@ -150,7 +150,7 @@
Failed: error -47: match limit exceeded

/(*LIMIT_MATCH=60000)(*LIMIT_MATCH=3000)(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Match limit = 3000
Starting code units: a z
Last code unit = 'z'
@@ -160,7 +160,7 @@
Failed: error -47: match limit exceeded

/(*LIMIT_MATCH=60000)(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Match limit = 60000
Starting code units: a z
Last code unit = 'z'
@@ -173,7 +173,7 @@
Failed: error -47: match limit exceeded

/(*LIMIT_DEPTH=10)(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Depth limit = 10
Starting code units: a z
Last code unit = 'z'
@@ -186,7 +186,7 @@
Failed: error -53: matching depth limit exceeded

/(*LIMIT_DEPTH=10)(*LIMIT_DEPTH=1000)(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Depth limit = 1000
Starting code units: a z
Last code unit = 'z'
@@ -196,7 +196,7 @@
No match

/(*LIMIT_DEPTH=1000)(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Depth limit = 1000
Starting code units: a z
Last code unit = 'z'
@@ -269,7 +269,7 @@
# when JIT is used.

 /(?R)/I
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     abcd
@@ -276,7 +276,7 @@
 Failed: error -52: nested recursion at the same subject position


 /(a|(?R))/I
-Capturing subpattern count = 1
+Capture group count = 1
 May match empty string
 Subject length lower bound = 0
     abcd
@@ -286,7 +286,7 @@
 Failed: error -52: nested recursion at the same subject position


 /(ab|(bc|(de|(?R))))/I
-Capturing subpattern count = 3
+Capture group count = 3
 May match empty string
 Subject length lower bound = 0
     abcd
@@ -296,7 +296,7 @@
 Failed: error -52: nested recursion at the same subject position


 /(ab|(bc|(de|(?1))))/I
-Capturing subpattern count = 3
+Capture group count = 3
 May match empty string
 Subject length lower bound = 0
     abcd
@@ -306,7 +306,7 @@
 Failed: error -52: nested recursion at the same subject position


 /x(ab|(bc|(de|(?1)x)x)x)/I
-Capturing subpattern count = 3
+Capture group count = 3
 First code unit = 'x'
 Subject length lower bound = 3
     xab123
@@ -352,7 +352,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Subject length lower bound = 1
     abcd
 Failed: error -52: nested recursion at the same subject position
@@ -367,7 +367,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: no_auto_possess
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
   Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
@@ -390,7 +390,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: no_auto_possess
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 


Modified: code/trunk/testdata/testoutput16
===================================================================
--- code/trunk/testdata/testoutput16    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput16    2019-02-06 18:11:36 UTC (rev 1066)
@@ -3,7 +3,7 @@
 # are different without JIT.


/abc/I,jit,jitverify
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'c'
Subject length lower bound = 3
@@ -10,7 +10,7 @@
JIT support is not available in this version of PCRE2

/a*/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Subject length lower bound = 0


Modified: code/trunk/testdata/testoutput17
===================================================================
--- code/trunk/testdata/testoutput17    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput17    2019-02-06 18:11:36 UTC (rev 1066)
@@ -6,7 +6,7 @@
 # JIT does not support this pattern (callout at start of condition).


/(?(?C1)(?=a)a)/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Subject length lower bound = 0
JIT compilation was not successful (no more memory)
@@ -14,7 +14,7 @@
# The following pattern cannot be compiled by JIT.

/b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*b*/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Subject length lower bound = 0
JIT compilation was not successful (no more memory)
@@ -26,7 +26,7 @@
Failed: error -46: JIT stack limit reached

/abcd/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'd'
Subject length lower bound = 4
@@ -38,7 +38,7 @@
No match (JIT)

/(*NO_JIT)abcd/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'd'
Subject length lower bound = 4
@@ -174,7 +174,7 @@
No match (JIT)

/abcd/I,jit=2
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'd'
Subject length lower bound = 4
@@ -192,7 +192,7 @@
# Limits tests that give different output with JIT.

/(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a z
Last code unit = 'z'
Subject length lower bound = 2
@@ -207,7 +207,7 @@
No match (JIT)

!((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)!I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
Subject length lower bound = 0
JIT compilation was successful
@@ -294,7 +294,7 @@
Failed: error -47: match limit exceeded

/(*LIMIT_MATCH=3000)(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Match limit = 3000
Starting code units: a z
Last code unit = 'z'
@@ -308,7 +308,7 @@
Failed: error -47: match limit exceeded

/(*LIMIT_MATCH=60000)(*LIMIT_MATCH=3000)(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Match limit = 3000
Starting code units: a z
Last code unit = 'z'
@@ -319,7 +319,7 @@
Failed: error -47: match limit exceeded

/(*LIMIT_MATCH=60000)(a+)*zz/I
-Capturing subpattern count = 1
+Capture group count = 1
Match limit = 60000
Starting code units: a z
Last code unit = 'z'
@@ -371,7 +371,7 @@

/^abc\Kdef/info,push
** Applies only to compile when pattern is stacked with 'push': jitverify
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -383,7 +383,7 @@

/^abc\Kdef/info,push
** Applies only to compile when pattern is stacked with 'push': jitverify
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -423,7 +423,7 @@
# when JIT is used.

/(?R)/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Subject length lower bound = 0
JIT compilation was successful
@@ -431,7 +431,7 @@
Failed: error -46: JIT stack limit reached

/(a|(?R))/I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
Subject length lower bound = 0
JIT compilation was successful
@@ -442,7 +442,7 @@
Failed: error -46: JIT stack limit reached

/(ab|(bc|(de|(?R))))/I
-Capturing subpattern count = 3
+Capture group count = 3
May match empty string
Subject length lower bound = 0
JIT compilation was successful
@@ -453,7 +453,7 @@
Failed: error -46: JIT stack limit reached

/(ab|(bc|(de|(?1))))/I
-Capturing subpattern count = 3
+Capture group count = 3
May match empty string
Subject length lower bound = 0
JIT compilation was successful
@@ -464,7 +464,7 @@
Failed: error -46: JIT stack limit reached

 /x(ab|(bc|(de|(?1)x)x)x)/I
-Capturing subpattern count = 3
+Capture group count = 3
 First code unit = 'x'
 Subject length lower bound = 3
 JIT compilation was successful
@@ -511,7 +511,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Subject length lower bound = 1
 JIT compilation was successful
     abcd


Modified: code/trunk/testdata/testoutput2
===================================================================
--- code/trunk/testdata/testoutput2    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput2    2019-02-06 18:11:36 UTC (rev 1066)
@@ -47,12 +47,12 @@
  0: DE


/(a)b|/I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
Subject length lower bound = 0

/abc/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'c'
Subject length lower bound = 3
@@ -69,7 +69,7 @@
No match

/^abc/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -85,30 +85,30 @@
No match

/a+bc/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'c'
Subject length lower bound = 3

/a*bc/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b
Last code unit = 'c'
Subject length lower bound = 2

/a{3}bc/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'c'
Subject length lower bound = 5

/(abc|a+z)/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 2

/^abc$/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -159,19 +159,19 @@
Failed: error 111 at offset 2: unrecognized character after (? or (?-

/.*b/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit at start or follows newline
Last code unit = 'b'
Subject length lower bound = 1

/.*?b/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit at start or follows newline
Last code unit = 'b'
Subject length lower bound = 1

 /cat|dog|elephant/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: c d e 
 Subject length lower bound = 3
     this sentence eventually mentions a cat
@@ -180,7 +180,7 @@
  0: elephant


 /cat|dog|elephant/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: c d e 
 Subject length lower bound = 3
     this sentence eventually mentions a cat
@@ -189,7 +189,7 @@
  0: elephant


/cat|dog|elephant/Ii
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless
Starting code units: C D E c d e
Subject length lower bound = 3
@@ -199,12 +199,12 @@
0: elephant

/a|[bcd]/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b c d
Subject length lower bound = 1

/(a|[^\dZ])/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a
\x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19
\x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / : ; < = >
@@ -222,7 +222,7 @@
Subject length lower bound = 1

/(a|b)*[\s]/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 a b
Subject length lower bound = 1

@@ -233,7 +233,7 @@
Failed: error 109 at offset 4: quantifier does not follow a repeatable item

/(a)(b)(c)\2/I
-Capturing subpattern count = 3
+Capture group count = 3
Max back reference = 2
First code unit = 'a'
Last code unit = 'c'
@@ -267,7 +267,7 @@
3: c

/(a)bc|(a)(b)\2/I
-Capturing subpattern count = 3
+Capture group count = 3
Max back reference = 2
First code unit = 'a'
Subject length lower bound = 3
@@ -312,7 +312,7 @@
3: b

/abc$/I,dollar_endonly
-Capturing subpattern count = 0
+Capture group count = 0
Options: dollar_endonly
First code unit = 'a'
Last code unit = 'c'
@@ -329,7 +329,7 @@
Failed: error 115 at offset 16: reference to non-existent subpattern

/the quick brown fox/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 't'
Last code unit = 'x'
Subject length lower bound = 19
@@ -339,7 +339,7 @@
0: the quick brown fox

/the quick brown fox/I,anchored
-Capturing subpattern count = 0
+Capture group count = 0
Options: anchored
First code unit = 't'
Subject length lower bound = 19
@@ -353,7 +353,7 @@
Failed: error 111 at offset 4: unrecognized character after (? or (?-

 /^abc|def/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: a d 
 Subject length lower bound = 3
     abcdef
@@ -362,7 +362,7 @@
  0: def


 /.*((abc)$|(def))/I
-Capturing subpattern count = 3
+Capture group count = 3
 First code unit at start or follows newline
 Subject length lower bound = 3
     defabc
@@ -382,7 +382,7 @@
 Failed: error 106 at offset 4: missing terminating ] for character class


/[^aeiou ]{3,}/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a
\x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19
\x1a \x1b \x1c \x1d \x1e \x1f ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6
@@ -402,7 +402,7 @@
0: -pr

/<.*>/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = '<'
Last code unit = '>'
Subject length lower bound = 2
@@ -410,7 +410,7 @@
0: <def>ghi<klm>

/<.*?>/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = '<'
Last code unit = '>'
Subject length lower bound = 2
@@ -418,7 +418,7 @@
0: <def>

/<.*>/I,ungreedy
-Capturing subpattern count = 0
+Capture group count = 0
Options: ungreedy
First code unit = '<'
Last code unit = '>'
@@ -427,7 +427,7 @@
0: <def>

/(?U)<.*>/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = '<'
Last code unit = '>'
Subject length lower bound = 2
@@ -435,7 +435,7 @@
0: <def>

/<.*?>/I,ungreedy
-Capturing subpattern count = 0
+Capture group count = 0
Options: ungreedy
First code unit = '<'
Last code unit = '>'
@@ -444,7 +444,7 @@
0: <def>ghi<klm>

/={3,}/I,ungreedy
-Capturing subpattern count = 0
+Capture group count = 0
Options: ungreedy
First code unit = '='
Last code unit = '='
@@ -453,7 +453,7 @@
0: ===

/(?U)={3,}?/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = '='
Last code unit = '='
Subject length lower bound = 3
@@ -461,7 +461,7 @@
0: ========

/(?<!bar|cattle)foo/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 6
First code unit = 'f'
Last code unit = 'o'
@@ -485,18 +485,18 @@
/(?<!(foo)a\1)bar/

/(?i)abc/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a' (caseless)
Last code unit = 'c' (caseless)
Subject length lower bound = 3

/(a|(?m)a)/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 1

/(?i)^1234/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = '1'
@@ -503,7 +503,7 @@
Subject length lower bound = 4

/(^b|(?i)^d)/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
Starting code units: D b d
@@ -510,7 +510,7 @@
Subject length lower bound = 1

/(?s).*/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Compile options: <none>
Overall options: anchored
@@ -517,37 +517,37 @@
Subject length lower bound = 0

/[abcd]/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b c d
Subject length lower bound = 1

/(?i)[abcd]/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: A B C D a b c d
Subject length lower bound = 1

/(?m)[xy]|(b|c)/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: b c x y
Subject length lower bound = 1

/(^a|^b)/Im
-Capturing subpattern count = 1
+Capture group count = 1
Options: multiline
First code unit at start or follows newline
Subject length lower bound = 1

/(?i)(^a|^b)/Im
-Capturing subpattern count = 1
+Capture group count = 1
Options: multiline
First code unit at start or follows newline
Subject length lower bound = 1

/(a)(?(1)a|b|c)/
-Failed: error 127 at offset 3: conditional group contains more than two branches
+Failed: error 127 at offset 3: conditional subpattern contains more than two branches

/(?(?=a)a|b|c)/
-Failed: error 127 at offset 0: conditional group contains more than two branches
+Failed: error 127 at offset 0: conditional subpattern contains more than two branches

/(?(1a)/
Failed: error 124 at offset 4: missing closing parenthesis for condition
@@ -565,7 +565,7 @@
Failed: error 128 at offset 2: assertion expected after (?( or (?(?C)

/((?s)blah)\s+\1/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'b'
Last code unit = 'h'
@@ -572,7 +572,7 @@
Subject length lower bound = 9

 /((?i)blah)\s+\1/I
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 First code unit = 'b' (caseless)
 Last code unit = 'h' (caseless)
@@ -587,17 +587,17 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 First code unit = 'b' (caseless)
 Subject length lower bound = 1


/(a*b|(?i:c*(?-i)d))/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: C a b c d
Subject length lower bound = 1

 /a$/I
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'a'
 Subject length lower bound = 1
     a
@@ -611,7 +611,7 @@
 No match


/a$/Im
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
First code unit = 'a'
Subject length lower bound = 1
@@ -626,7 +626,7 @@
No match

/\Aabc/Im
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
Compile options: multiline
Overall options: anchored multiline
@@ -634,7 +634,7 @@
Subject length lower bound = 3

/^abc/Im
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
First code unit at start or follows newline
Last code unit = 'c'
@@ -641,7 +641,7 @@
Subject length lower bound = 3

/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/I
-Capturing subpattern count = 5
+Capture group count = 5
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -655,13 +655,13 @@
5: def

/(?<=foo)[ab]/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 3
Starting code units: a b
Subject length lower bound = 1

/(?<!foo)(alpha|omega)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max lookbehind = 3
Starting code units: a o
Last code unit = 'a'
@@ -668,12 +668,12 @@
Subject length lower bound = 5

/(?!alphabet)[ab]/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b
Subject length lower bound = 1

/(?<=foo\n)^bar/Im
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 4
Contains explicit CR or LF match
Options: multiline
@@ -690,7 +690,7 @@
No match

/^(?<=foo\n)bar/Im
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 4
Contains explicit CR or LF match
Options: multiline
@@ -708,7 +708,7 @@
No match

/(?>^abc)/Im
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
First code unit at start or follows newline
Last code unit = 'c'
@@ -733,7 +733,7 @@
/The next three are in testinput2 because they have variable length branches/

/(?<=bullock|donkey)-cart/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 7
First code unit = '-'
Last code unit = 't'
@@ -749,13 +749,13 @@
No match

/(?<=ab(?i)x|y|z)/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 3
May match empty string
Subject length lower bound = 0

/(?>.*)(?<=(abcd)|(xyz))/I
-Capturing subpattern count = 2
+Capture group count = 2
Max lookbehind = 4
May match empty string
Subject length lower bound = 0
@@ -768,7 +768,7 @@
2: xyz

/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 4
First code unit = 'Z'
Last code unit = 'Z'
@@ -796,7 +796,7 @@
No match

/(?<!(foo)a)bar/I
-Capturing subpattern count = 1
+Capture group count = 1
Max lookbehind = 4
First code unit = 'b'
Last code unit = 'r'
@@ -812,7 +812,7 @@
# This one is here because Perl behaves differently; see also the following.

/^(a\1?){4}$/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Compile options: <none>
Overall options: anchored
@@ -949,7 +949,7 @@
Failed: error 101 at offset 4: \ at end of pattern

/(a)bc(d)/I
-Capturing subpattern count = 2
+Capture group count = 2
First code unit = 'a'
Last code unit = 'd'
Subject length lower bound = 4
@@ -969,7 +969,7 @@
Copy substring 5 failed (-49): unknown substring

 /(.{20})/I
-Capturing subpattern count = 1
+Capture group count = 1
 Subject length lower bound = 20
     abcdefghijklmnopqrstuvwxyz
  0: abcdefghijklmnopqrst
@@ -984,7 +984,7 @@
  1G abcdefghijklmnopqrst (20)


 /(.{15})/I
-Capturing subpattern count = 1
+Capture group count = 1
 Subject length lower bound = 15
     abcdefghijklmnopqrstuvwxyz
  0: abcdefghijklmno
@@ -996,7 +996,7 @@
  1G abcdefghijklmno (15)


 /(.{16})/I
-Capturing subpattern count = 1
+Capture group count = 1
 Subject length lower bound = 16
     abcdefghijklmnopqrstuvwxyz
  0: abcdefghijklmnop
@@ -1010,7 +1010,7 @@
  1L abcdefghijklmnop


/^(a|(bc))de(f)/I
-Capturing subpattern count = 3
+Capture group count = 3
Compile options: <none>
Overall options: anchored
Starting code units: a b
@@ -1049,7 +1049,7 @@
0C adef (4)

 /^abc\00def/I
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 First code unit = 'a'
@@ -1062,7 +1062,7 @@
 /word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+
 )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+
 )?)?)?)?)?)?)?)?)?otherword/I
-Capturing subpattern count = 8
+Capture group count = 8
 Contains explicit CR or LF match
 First code unit = 'w'
 Last code unit = 'd'
@@ -1076,7 +1076,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit at start or follows newline
 Last code unit = 'X'
 Subject length lower bound = 1
@@ -1089,7 +1089,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: dotall
 Overall options: anchored dotall
 Last code unit = 'X'
@@ -1108,7 +1108,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 First code unit at start or follows newline
 Subject length lower bound = 1


@@ -1125,7 +1125,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Compile options: dotall
 Overall options: anchored dotall
 Subject length lower bound = 1
@@ -1143,7 +1143,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Compile options: <none>
 Overall options: anchored
 Subject length lower bound = 1
@@ -1161,13 +1161,13 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Subject length lower bound = 1


/\Biss\B/I,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
First code unit = 'i'
Last code unit = 's'
@@ -1177,7 +1177,7 @@
0+ issippi

/iss/I,aftertext,altglobal
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'i'
Last code unit = 's'
Subject length lower bound = 3
@@ -1188,7 +1188,7 @@
0+ ippi

/\Biss\B/I,aftertext,altglobal
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
First code unit = 'i'
Last code unit = 's'
@@ -1198,7 +1198,7 @@
0+ issippi

/\Biss\B/Ig,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
First code unit = 'i'
Last code unit = 's'
@@ -1213,7 +1213,7 @@
No match

/(?<=[Ms])iss/Ig,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
First code unit = 'i'
Last code unit = 's'
@@ -1225,7 +1225,7 @@
0+ ippi

/(?<=[Ms])iss/I,aftertext,altglobal
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
First code unit = 'i'
Last code unit = 's'
@@ -1235,7 +1235,7 @@
0+ issippi

/^iss/Ig,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'i'
@@ -1245,7 +1245,7 @@
0+ issippi

/.*iss/Ig,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
First code unit at start or follows newline
Last code unit = 's'
Subject length lower bound = 3
@@ -1256,7 +1256,7 @@
0+ pqr

 /.i./Ig,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
 Last code unit = 'i'
 Subject length lower bound = 3
     Mississippi
@@ -1285,7 +1285,7 @@
  0+ souri river


/^.is/Ig,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
Subject length lower bound = 3
@@ -1294,7 +1294,7 @@
0+ sissippi

/^ab\n/Ig,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
Contains explicit CR or LF match
Compile options: <none>
Overall options: anchored
@@ -1305,7 +1305,7 @@
0+ ab\x0acd

/^ab\n/Igm,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
Contains explicit CR or LF match
Options: multiline
First code unit at start or follows newline
@@ -1329,205 +1329,205 @@
0+ xyz

/abc/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'c'
Subject length lower bound = 3

/abc|bac/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b
Last code unit = 'c'
Subject length lower bound = 3

/(abc|bac)/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b
Last code unit = 'c'
Subject length lower bound = 3

/(abc|(c|dc))/I
-Capturing subpattern count = 2
+Capture group count = 2
Starting code units: a c d
Last code unit = 'c'
Subject length lower bound = 1

/(abc|(d|de)c)/I
-Capturing subpattern count = 2
+Capture group count = 2
Starting code units: a d
Last code unit = 'c'
Subject length lower bound = 2

/a*/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Subject length lower bound = 0

/a+/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Subject length lower bound = 1

/(baa|a+)/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b
Last code unit = 'a'
Subject length lower bound = 1

/a{0,3}/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Subject length lower bound = 0

/baa{3,}/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'b'
Last code unit = 'a'
Subject length lower bound = 5

/"([^\\"]+|\\.)*"/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = '"'
Last code unit = '"'
Subject length lower bound = 2

/(abc|ab[cd])/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 3

/(a|.)/I
-Capturing subpattern count = 1
+Capture group count = 1
Subject length lower bound = 1

/a|ba|\w/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P
Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z
Subject length lower bound = 1

/abc(?=pqr)/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'r'
Subject length lower bound = 3

/...(?<=abc)/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 3
Subject length lower bound = 3

/abc(?!pqr)/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'c'
Subject length lower bound = 3

/ab./I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 3

/ab[xyz]/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 3

/abc*/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2

/ab.c*/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 3

/a.c*/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Subject length lower bound = 2

/.c*/I
-Capturing subpattern count = 0
+Capture group count = 0
Subject length lower bound = 1

/ac*/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Subject length lower bound = 1

/(a.c*|b.c*)/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b
Subject length lower bound = 2

/a.c*|aba/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Subject length lower bound = 2

/.+a/I
-Capturing subpattern count = 0
+Capture group count = 0
Last code unit = 'a'
Subject length lower bound = 2

/(?=abcda)a.*/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'a'
Subject length lower bound = 1

/(?=a)a.*/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Subject length lower bound = 1

/a(b)*/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 1

/a\d*/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Subject length lower bound = 1

/ab\d*/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2

/a(\d)*/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 1

/abcde{0,0}/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'd'
Subject length lower bound = 4

/ab\d+/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 3

/a(?(1)b)(.)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'a'
Subject length lower bound = 2

/a(?(1)bag|big)(.)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'a'
Last code unit = 'g'
@@ -1534,13 +1534,13 @@
Subject length lower bound = 5

/a(?(1)bag|big)*(.)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'a'
Subject length lower bound = 2

/a(?(1)bag|big)+(.)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'a'
Last code unit = 'g'
@@ -1547,7 +1547,7 @@
Subject length lower bound = 5

/a(?(1)b..|b..)(.)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'a'
Last code unit = 'b'
@@ -1554,13 +1554,13 @@
Subject length lower bound = 5

/ab\d{0}e/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'e'
Subject length lower bound = 3

 /a?b?/I
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     a
@@ -1576,7 +1576,7 @@
 No match


 /|-/I
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     abcd
@@ -1590,7 +1590,7 @@
 No match


 /^.?abcd/I
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Last code unit = 'd'
@@ -1604,7 +1604,7 @@
   )*            # Zero or more contents
   \)            # Closing )
   /Ix
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = '('
 Last code unit = ')'
@@ -1632,7 +1632,7 @@
 No match


/\( ( (?>[^()]+) | (?R) )* \) /Igx
-Capturing subpattern count = 1
+Capture group count = 1
Options: extended
First code unit = '('
Last code unit = ')'
@@ -1647,7 +1647,7 @@
1: z

/\( (?: (?>[^()]+) | (?R) ) \) /Ix
-Capturing subpattern count = 0
+Capture group count = 0
Options: extended
First code unit = '('
Last code unit = ')'
@@ -1665,7 +1665,7 @@
No match

/\( (?: (?>[^()]+) | (?R) )? \) /Ix
-Capturing subpattern count = 0
+Capture group count = 0
Options: extended
First code unit = '('
Last code unit = ')'
@@ -1676,7 +1676,7 @@
0: (fsh)

/\( ( (?>[^()]+) | (?R) )* \) /Ix
-Capturing subpattern count = 1
+Capture group count = 1
Options: extended
First code unit = '('
Last code unit = ')'
@@ -1686,7 +1686,7 @@
1: cd

/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix
-Capturing subpattern count = 2
+Capture group count = 2
Options: extended
First code unit = '('
Last code unit = ')'
@@ -1697,7 +1697,7 @@
2: cd

/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix
-Capturing subpattern count = 3
+Capture group count = 3
Options: extended
First code unit = '('
Last code unit = ')'
@@ -1714,7 +1714,7 @@
3: cd

/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix
-Capturing subpattern count = 3
+Capture group count = 3
Options: extended
First code unit = '('
Last code unit = ')'
@@ -1731,7 +1731,7 @@
3: cd

/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix
-Capturing subpattern count = 11
+Capture group count = 11
Options: extended
First code unit = '('
Last code unit = ')'
@@ -1751,7 +1751,7 @@
11: cd

/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix
-Capturing subpattern count = 3
+Capture group count = 3
Options: extended
First code unit = '('
Last code unit = ')'
@@ -1762,7 +1762,7 @@
2: 123

 /\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix
-Capturing subpattern count = 3
+Capture group count = 3
 Options: extended
 First code unit = '('
 Last code unit = ')'
@@ -1786,7 +1786,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
@@ -1801,7 +1801,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
@@ -1826,7 +1826,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z 
@@ -1841,7 +1841,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
@@ -1860,7 +1860,7 @@
 Subject length lower bound = 1


 /[_[:alpha:]]/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z 
   _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
 Subject length lower bound = 1
@@ -1873,7 +1873,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
@@ -1892,7 +1892,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x80 \x81 \x82 \x83 \x84 \x85 \x86 \x87 \x88 \x89 \x8a 
@@ -1914,7 +1914,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x09 \x20 
@@ -1928,7 +1928,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0a \x0b 
@@ -1948,7 +1948,7 @@
 Subject length lower bound = 1


 /[\n\x0b\x0c\x0d[:blank:]]/I
-Capturing subpattern count = 0
+Capture group count = 0
 Contains explicit CR or LF match
 Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 
 Subject length lower bound = 1
@@ -1961,7 +1961,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
@@ -1977,7 +1977,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: 0 1 2 3 4 5 6 7 8 9 
@@ -1991,7 +1991,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : 
@@ -2007,7 +2007,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: a b c d e f g h i j k l m n o p q r s t u v w x y z 
@@ -2021,7 +2021,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 
@@ -2037,7 +2037,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: ! " # $ % & ' ( ) * + , - . / : ; < = > ? @ [ \ ] ^ 
@@ -2052,7 +2052,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 
@@ -2066,7 +2066,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z 
@@ -2080,7 +2080,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F a b c d e f 
@@ -2094,7 +2094,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
@@ -2109,7 +2109,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 
@@ -2134,7 +2134,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
@@ -2161,7 +2161,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0a \x0b 
@@ -2187,7 +2187,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: % 0 1 A B C D E F G H I J K L M N O P Q R S T U V W 
   X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z 
 Subject length lower bound = 1
@@ -2202,7 +2202,7 @@
 Failed: error 130 at offset 3: unknown POSIX class name


/[[:upper:]]/Ii
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless
Starting code units: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
a b c d e f g h i j k l m n o p q r s t u v w x y z
@@ -2213,7 +2213,7 @@
0: a

/[[:lower:]]/Ii
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless
Starting code units: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
a b c d e f g h i j k l m n o p q r s t u v w x y z
@@ -2224,7 +2224,7 @@
0: a

/((?-i)[[:lower:]])[[:lower:]]/Ii
-Capturing subpattern count = 1
+Capture group count = 1
Options: caseless
Starting code units: a b c d e f g h i j k l m n o p q r s t u v w x y z
Subject length lower bound = 2
@@ -2249,7 +2249,7 @@
# This one's here because of the large output vector needed

/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I
-Capturing subpattern count = 271
+Capture group count = 271
Max back reference = 270
Starting code units: 0 1 2 3 4 5 6 7 8 9
Subject length lower bound = 0
@@ -2530,7 +2530,7 @@
# This one's here because Perl does this differently and PCRE2 can't at present

/(main(O)?)+/I
-Capturing subpattern count = 2
+Capture group count = 2
First code unit = 'm'
Last code unit = 'n'
Subject length lower bound = 4
@@ -2545,7 +2545,7 @@
# These are all cases where Perl does it differently (nested captures)

/^(a(b)?)+$/I
-Capturing subpattern count = 2
+Capture group count = 2
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2556,7 +2556,7 @@
2: b

/^(aa(bb)?)+$/I
-Capturing subpattern count = 2
+Capture group count = 2
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2567,7 +2567,7 @@
2: bb

/^(aa|aa(bb))+$/I
-Capturing subpattern count = 2
+Capture group count = 2
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2578,7 +2578,7 @@
2: bb

/^(aa(bb)??)+$/I
-Capturing subpattern count = 2
+Capture group count = 2
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2589,7 +2589,7 @@
2: bb

/^(?:aa(bb)?)+$/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2599,7 +2599,7 @@
1: bb

/^(aa(b(b))?)+$/I
-Capturing subpattern count = 3
+Capture group count = 3
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2611,7 +2611,7 @@
3: b

/^(?:aa(b(b))?)+$/I
-Capturing subpattern count = 2
+Capture group count = 2
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2622,7 +2622,7 @@
2: b

/^(?:aa(b(?:b))?)+$/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2632,7 +2632,7 @@
1: bb

/^(?:aa(bb(?:b))?)+$/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2642,7 +2642,7 @@
1: bbb

/^(?:aa(b(?:bb))?)+$/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2652,7 +2652,7 @@
1: bbb

/^(?:aa(?:b(b))?)+$/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2662,7 +2662,7 @@
1: b

/^(?:aa(?:b(bb))?)+$/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2672,7 +2672,7 @@
1: bb

/^(aa(b(bb))?)+$/I
-Capturing subpattern count = 3
+Capture group count = 3
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -2684,7 +2684,7 @@
3: bb

 /^(aa(bb(bb))?)+$/I
-Capturing subpattern count = 3
+Capture group count = 3
 Compile options: <none>
 Overall options: anchored
 First code unit = 'a'
@@ -2703,7 +2703,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -2715,7 +2715,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -2727,7 +2727,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 
 Subject length lower bound = 1


@@ -2738,7 +2738,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0e \x0f 
   \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d \x1e 
   \x1f ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : ; < = > ? @ A B C 
@@ -2763,7 +2763,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'a'
 Last code unit = 'b' (caseless)
 Subject length lower bound = 2
@@ -2785,7 +2785,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 First code unit = 'a'
 Last code unit = 'b' (caseless)
 Subject length lower bound = 2
@@ -2806,7 +2806,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a' (caseless)
 Last code unit = 'c' (caseless)
@@ -2820,7 +2820,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a' (caseless)
 Last code unit = 'c' (caseless)
@@ -2833,7 +2833,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = '1'
 Last code unit = '0'
 Subject length lower bound = 300
@@ -2845,7 +2845,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = '1'
 Last code unit = '0'
 Subject length lower bound = 300
@@ -2856,7 +2856,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     \
@@ -2869,7 +2869,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'x'
 Subject length lower bound = 1


@@ -2880,7 +2880,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = ' '
 Subject length lower bound = 1


@@ -2891,7 +2891,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'a'
 Subject length lower bound = 1
   abc
@@ -2908,7 +2908,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'a'
 Last code unit = 'b'
 Subject length lower bound = 2
@@ -2922,7 +2922,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'a'
 Last code unit = 'c'
 Subject length lower bound = 3
@@ -2935,7 +2935,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
   Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
 Subject length lower bound = 1
@@ -2950,7 +2950,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0


@@ -2961,7 +2961,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'x'
 Subject length lower bound = 1


@@ -3011,12 +3011,12 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 May match empty string
 Subject length lower bound = 0


/^(\w++|\s++)*$/I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
Compile options: <none>
Overall options: anchored
@@ -3029,7 +3029,7 @@
No match

 /(\d++)(\w)/I
-Capturing subpattern count = 2
+Capture group count = 2
 Starting code units: 0 1 2 3 4 5 6 7 8 9 
 Subject length lower bound = 2
     12345a
@@ -3041,7 +3041,7 @@
 No match


/a++b/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
@@ -3049,7 +3049,7 @@
0: aaab

/(a++b)/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
@@ -3058,7 +3058,7 @@
1: aaab

/(a++)b/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
@@ -3067,7 +3067,7 @@
1: aaa

/([^()]++|\([^()]*\))+/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a
\x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19
\x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( * + , - . / 0 1 2 3 4 5
@@ -3088,7 +3088,7 @@
1: x

 /\(([^()]++|\([^()]+\))+\)/I
-Capturing subpattern count = 1
+Capture group count = 1
 First code unit = '('
 Last code unit = ')'
 Subject length lower bound = 3
@@ -3123,7 +3123,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 First code unit = 'a'
 Last code unit = 'c'
 Subject length lower bound = 3
@@ -3149,7 +3149,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'x'
 Last code unit = 'b'
 Subject length lower bound = 3
@@ -3165,7 +3165,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'x'
 Last code unit = 'b'
 Subject length lower bound = 3
@@ -3193,7 +3193,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 5
+Capture group count = 5
 Compile options: <none>
 Overall options: anchored
 First code unit = 'a'
@@ -3209,7 +3209,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 First code unit = 'x'
@@ -3228,7 +3228,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Compile options: <none>
 Overall options: anchored
 First code unit = 'x'
@@ -3282,7 +3282,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 
 Subject length lower bound = 1


@@ -3293,7 +3293,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 
 Subject length lower bound = 1


@@ -3304,12 +3304,12 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 a b c d e 
 Subject length lower bound = 1


 /< (?: (?(R) \d++  | [^<>]*+) | (?R)) * >/Ix
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = '<'
 Last code unit = '>'
@@ -3338,7 +3338,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Max lookbehind = 1
 First code unit = '8'
 Last code unit = 'X'
@@ -3352,7 +3352,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Max lookbehind = 1
 First code unit = '$'
 Last code unit = 'X'
@@ -3359,29 +3359,29 @@
 Subject length lower bound = 404


/(.*)\d+\1/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Subject length lower bound = 1

/(.*)\d+/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit at start or follows newline
Subject length lower bound = 1

/(.*)\d+\1/Is
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Options: dotall
Subject length lower bound = 1

/(.*)\d+/Is
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: dotall
Overall options: anchored dotall
Subject length lower bound = 1

/(.*(xyz))\d+\2/I
-Capturing subpattern count = 2
+Capture group count = 2
Max back reference = 2
First code unit at start or follows newline
Last code unit = 'z'
@@ -3388,7 +3388,7 @@
Subject length lower bound = 7

 /((.*))\d+\1/I
-Capturing subpattern count = 2
+Capture group count = 2
 Max back reference = 1
 Subject length lower bound = 1
     abc123bc
@@ -3397,19 +3397,19 @@
  2: bc


/a[b]/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2

/(?=a).*/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
First code unit = 'a'
Subject length lower bound = 0

/(?=abc).xyz/Ii
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless
First code unit = 'a' (caseless)
Last code unit = 'z' (caseless)
@@ -3416,53 +3416,53 @@
Subject length lower bound = 4

/(?=abc)(?i).xyz/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'z' (caseless)
Subject length lower bound = 4

/(?=a)(?=b)/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
First code unit = 'a'
Subject length lower bound = 0

/(?=.)a/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Subject length lower bound = 1

/((?=abcda)a)/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'a'
Subject length lower bound = 1

/((?=abcda)ab)/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2

/()a/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 1

/(?:(?=.)|(?<!x))a/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
First code unit = 'a'
Subject length lower bound = 1

/(?(1)ab|ac)(.)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'a'
Subject length lower bound = 3

/(?(1)abz|acz)(.)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'a'
Last code unit = 'z'
@@ -3469,71 +3469,71 @@
Subject length lower bound = 4

/(?(1)abz)(.)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Subject length lower bound = 1

/(?(1)abz)(1)23/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Last code unit = '3'
Subject length lower bound = 3

/(a)+/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 1

/(a){2,3}/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'a'
Subject length lower bound = 2

/(a)*/I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
Subject length lower bound = 0

/[a]/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Subject length lower bound = 1

/[ab]/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b
Subject length lower bound = 1

/[ab]/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b
Subject length lower bound = 1

/[^a]/I
-Capturing subpattern count = 0
+Capture group count = 0
Subject length lower bound = 1

/\d456/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9
Last code unit = '6'
Subject length lower bound = 4

/\d456/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9
Last code unit = '6'
Subject length lower bound = 4

/a^b/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2

/^a/Im
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
First code unit at start or follows newline
Last code unit = 'a'
@@ -3547,24 +3547,24 @@
No match

/c|abc/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a c
Last code unit = 'c'
Subject length lower bound = 1

/(?i)[ab]/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: A B a b
Subject length lower bound = 1

/[ab](?i)cd/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b
Last code unit = 'd' (caseless)
Subject length lower bound = 3

/abc(?C)def/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'f'
Subject length lower bound = 6
@@ -3585,7 +3585,7 @@
No match

/abc(?C)de(?C1)f/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'f'
Subject length lower bound = 6
@@ -3596,7 +3596,7 @@
0: abcdef

/(?C1)\dabc(?C2)def/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9
Last code unit = 'f'
Subject length lower bound = 7
@@ -3613,7 +3613,7 @@
No match

/(?C1)\dabc(?C2)def/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9
Last code unit = 'f'
Subject length lower bound = 7
@@ -3630,7 +3630,7 @@
No match

/(?C255)ab/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
@@ -3645,7 +3645,7 @@
Failed: error 139 at offset 5: closing parenthesis for (?C expected

/abc(?C)def/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'f'
Subject length lower bound = 6
@@ -3655,7 +3655,7 @@
0: abcdef

/(abc)(?C)de(?C1)f/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'f'
Subject length lower bound = 6
@@ -3687,7 +3687,7 @@
No match

 /(?C0)(abc(?C1))*/I
-Capturing subpattern count = 1
+Capture group count = 1
 May match empty string
 Subject length lower bound = 0
     abcabcabc
@@ -3715,7 +3715,7 @@
  1: abc


 /(\d{3}(?C))*/I
-Capturing subpattern count = 1
+Capture group count = 1
 May match empty string
 Subject length lower bound = 0
     123\=callout_capture
@@ -3750,7 +3750,7 @@
  1: 789


 /((xyz)(?C)p|(?C1)xyzabc)/I
-Capturing subpattern count = 2
+Capture group count = 2
 First code unit = 'x'
 Subject length lower bound = 4
     xyzabc\=callout_capture
@@ -3766,7 +3766,7 @@
  1: xyzabc


/(X)((xyz)(?C)p|(?C1)xyzabc)/I
-Capturing subpattern count = 3
+Capture group count = 3
First code unit = 'X'
Last code unit = 'x'
Subject length lower bound = 5
@@ -3786,7 +3786,7 @@
2: xyzabc

/(?=(abc))(?C)abcdef/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'f'
Subject length lower bound = 6
@@ -3799,7 +3799,7 @@
1: abc

/(?!(abc)(?C1)d)(?C2)abcxyz/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'z'
Subject length lower bound = 6
@@ -3814,7 +3814,7 @@
0: abcxyz

/(?<=(abc)(?C))xyz/I
-Capturing subpattern count = 1
+Capture group count = 1
Max lookbehind = 3
First code unit = 'x'
Last code unit = 'z'
@@ -3828,7 +3828,7 @@
1: abc

/a(b+)(c*)(?C1)/I
-Capturing subpattern count = 2
+Capture group count = 2
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
@@ -3840,7 +3840,7 @@
No match

/a(b+?)(c*?)(?C1)/I
-Capturing subpattern count = 2
+Capture group count = 2
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
@@ -3866,13 +3866,13 @@
No match

/(?C)abc/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'c'
Subject length lower bound = 3

/(?C)^abc/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -3879,12 +3879,12 @@
Subject length lower bound = 3

/(?C)a|b/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b
Subject length lower bound = 1

 /a|(b)(?C)/I
-Capturing subpattern count = 1
+Capture group count = 1
 Starting code units: a b 
 Subject length lower bound = 1
     b
@@ -3894,7 +3894,7 @@
  1: b


 /x(ab|(bc|(de|(?R))))/I
-Capturing subpattern count = 3
+Capture group count = 3
 First code unit = 'x'
 Subject length lower bound = 3
     xab
@@ -3924,7 +3924,7 @@
 No match


/^([^()]|\((?1)*\))*$/I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
Compile options: <none>
Overall options: anchored
@@ -3943,7 +3943,7 @@
No match

 /^>abc>([^()]|\((?1)*\))*<xyz<$/I
-Capturing subpattern count = 1
+Capture group count = 1
 Compile options: <none>
 Overall options: anchored
 First code unit = '>'
@@ -3970,7 +3970,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 First code unit = 'a'
 Last code unit = 'b'
 Subject length lower bound = 2
@@ -3988,13 +3988,13 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 First code unit = 'a'
 Last code unit = 'b'
 Subject length lower bound = 2


/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/I
-Capturing subpattern count = 2
+Capture group count = 2
Compile options: <none>
Overall options: anchored
Starting code units: ( - 0 1 2 3 4 5 6 7 8 9
@@ -4014,7 +4014,7 @@
No match

/^(x(y|(?1){2})z)/I
-Capturing subpattern count = 2
+Capture group count = 2
Compile options: <none>
Overall options: anchored
First code unit = 'x'
@@ -4034,7 +4034,7 @@
No match

/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/Ix
-Capturing subpattern count = 2
+Capture group count = 2
Options: extended
First code unit = '<'
Last code unit = '>'
@@ -4074,7 +4074,7 @@
Failed: error 114 at offset 10: missing closing parenthesis

/^(abc)def(?1)/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -4084,7 +4084,7 @@
1: abc

/^(a|b|c)=(?1)+/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
Starting code units: a b c
@@ -4100,7 +4100,7 @@
1: a

 /^(a|b|c)=((?1))+/I
-Capturing subpattern count = 2
+Capture group count = 2
 Compile options: <none>
 Overall options: anchored
 Starting code units: a b c 
@@ -4134,8 +4134,8 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
   longername2   2
   name1         1
 First code unit = 'a'
@@ -4168,8 +4168,8 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 3
-Named capturing subpatterns:
+Capture group count = 3
+Named capture groups:
   a   3
   c   1
   d   2
@@ -4193,9 +4193,9 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
-Named capturing subpatterns:
+Named capture groups:
   a   1
 First code unit = 'a'
 Last code unit = 'd'
@@ -4202,9 +4202,9 @@
 Subject length lower bound = 10


 /^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii
-Capturing subpattern count = 4
+Capture group count = 4
 Max back reference = 4
-Named capturing subpatterns:
+Named capture groups:
   four    4
   one     1
   three   3
@@ -4240,7 +4240,7 @@
 No match


/((?(R)a|b))\1(?1)?/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Subject length lower bound = 2
bb
@@ -4251,7 +4251,7 @@
1: b

/(.*)a/Is
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: dotall
Overall options: anchored dotall
Last code unit = 'a'
@@ -4258,7 +4258,7 @@
Subject length lower bound = 1

/(.*)a\1/Is
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Options: dotall
Last code unit = 'a'
@@ -4265,7 +4265,7 @@
Subject length lower bound = 1

/(.*)a(b)\2/Is
-Capturing subpattern count = 2
+Capture group count = 2
Max back reference = 2
Compile options: dotall
Overall options: anchored dotall
@@ -4273,7 +4273,7 @@
Subject length lower bound = 3

/((.*)a|(.*)b)z/Is
-Capturing subpattern count = 3
+Capture group count = 3
Compile options: dotall
Overall options: anchored dotall
Last code unit = 'z'
@@ -4280,7 +4280,7 @@
Subject length lower bound = 2

/((.*)a|(.*)b)z\1/Is
-Capturing subpattern count = 3
+Capture group count = 3
Max back reference = 1
Options: dotall
Last code unit = 'z'
@@ -4287,7 +4287,7 @@
Subject length lower bound = 3

/((.*)a|(.*)b)z\2/Is
-Capturing subpattern count = 3
+Capture group count = 3
Max back reference = 2
Options: dotall
Last code unit = 'z'
@@ -4294,7 +4294,7 @@
Subject length lower bound = 2

/((.*)a|(.*)b)z\3/Is
-Capturing subpattern count = 3
+Capture group count = 3
Max back reference = 3
Options: dotall
Last code unit = 'z'
@@ -4301,7 +4301,7 @@
Subject length lower bound = 2

/((.*)a|^(.*)b)z\3/Is
-Capturing subpattern count = 3
+Capture group count = 3
Max back reference = 3
Compile options: dotall
Overall options: anchored dotall
@@ -4309,7 +4309,7 @@
Subject length lower bound = 2

/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is
-Capturing subpattern count = 31
+Capture group count = 31
May match empty string
Compile options: dotall
Overall options: anchored dotall
@@ -4316,7 +4316,7 @@
Subject length lower bound = 0

/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is
-Capturing subpattern count = 31
+Capture group count = 31
Max back reference = 31
May match empty string
Options: dotall
@@ -4323,7 +4323,7 @@
Subject length lower bound = 0

 /(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is
-Capturing subpattern count = 32
+Capture group count = 32
 Max back reference = 32
 May match empty string
 Options: dotall
@@ -4341,7 +4341,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: no_auto_capture
 First code unit = 'a'
 Last code unit = 'c'
@@ -4361,8 +4361,8 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
   one   1
 Options: no_auto_capture
 First code unit = 'a'
@@ -4384,8 +4384,8 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
   named   1
 Options: no_auto_capture
 First code unit = 'a'
@@ -4393,7 +4393,7 @@
 Subject length lower bound = 3


/(aaa(?C1)bbb|ab)/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
@@ -4421,8 +4421,8 @@
No match

 /ab(?P<one>cd)ef(?P<two>gh)/I
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
   one   1
   two   2
 First code unit = 'a'
@@ -4461,8 +4461,8 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
   Tes    1
   Test   2
 May match empty string
@@ -4478,8 +4478,8 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
   Tes    2
   Test   1
 May match empty string
@@ -4486,8 +4486,8 @@
 Subject length lower bound = 0


/(?P<Z>zz)(?P<A>aa)/I
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
A 2
Z 1
First code unit = 'z'
@@ -4511,8 +4511,8 @@
Failed: error 143 at offset 31: two named subpatterns have the same name (PCRE2_DUPNAMES not set)

"\[((?P<elem>\d+)(,(?P>elem))*)\]"I
-Capturing subpattern count = 3
-Named capturing subpatterns:
+Capture group count = 3
+Named capture groups:
elem 2
First code unit = '['
Last code unit = ']'
@@ -4527,8 +4527,8 @@
No match

 "\[((?P<elem>\d+)(,(?P>elem))*)?\]"I
-Capturing subpattern count = 3
-Named capturing subpatterns:
+Capture group count = 3
+Named capture groups:
   elem   2
 First code unit = '['
 Last code unit = ']'
@@ -4556,7 +4556,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
+Capture group count = 2
 May match empty string
 Subject length lower bound = 0


@@ -4575,7 +4575,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
+Capture group count = 2
 May match empty string
 Subject length lower bound = 0


@@ -4605,7 +4605,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
+Capture group count = 2
 May match empty string
 Subject length lower bound = 0


@@ -4638,7 +4638,7 @@
------------------------------------------------------------------

/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii
-Capturing subpattern count = 3
+Capture group count = 3
Options: caseless
Last code unit = 'g' (caseless)
Subject length lower bound = 8
@@ -4647,7 +4647,7 @@
1: Baby Bjorn Active Carrier - With free SHIPPING!!

 /((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii
-Capturing subpattern count = 3
+Capture group count = 3
 Options: caseless
 Last code unit = 'g' (caseless)
 Subject length lower bound = 8
@@ -4664,7 +4664,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Last code unit = 'b'
 Subject length lower bound = 1


@@ -4682,7 +4682,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Last code unit = 'c'
 Subject length lower bound = 1


@@ -4697,7 +4697,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'a'
 Last code unit = 'f'
 Subject length lower bound = 6
@@ -4719,7 +4719,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: auto_callout
 First code unit = 'a'
 Last code unit = 'e'
@@ -4754,7 +4754,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: auto_callout
 Starting code units: a b 
 Last code unit = 'b'
@@ -4797,7 +4797,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: auto_callout
 Starting code units: a b 
 Last code unit = 'b'
@@ -4840,7 +4840,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: auto_callout
 First code unit = 'a'
 Last code unit = 'b'
@@ -4897,7 +4897,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: auto_callout
 Starting code units: a d 
 Last code unit = 'x'
@@ -4971,7 +4971,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: auto_callout
 Starting code units: a d 
 Last code unit = 'x'
@@ -5019,7 +5019,7 @@
 No match


 /(ab|cd){3,4}/I,auto_callout
-Capturing subpattern count = 1
+Capture group count = 1
 Options: auto_callout
 Starting code units: a c 
 Subject length lower bound = 6
@@ -5111,7 +5111,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: auto_callout
 Starting code units: a b x 
 Subject length lower bound = 2
@@ -5161,7 +5161,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: auto_callout
 Starting code units: a b x 
 Subject length lower bound = 2
@@ -5262,7 +5262,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: auto_callout
 Starting code units: a b x 
 Last code unit = '3'
@@ -5294,7 +5294,7 @@
  1: aac


/\b.*/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
May match empty string
Subject length lower bound = 0
@@ -5302,7 +5302,7 @@
0: cd

/\b.*/Is
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
May match empty string
Options: dotall
@@ -5311,7 +5311,7 @@
0: cd

/(?!.bcd).*/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Subject length lower bound = 0
Xbcd12345
@@ -5318,7 +5318,7 @@
0: bcd12345

/abcde/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'e'
Subject length lower bound = 5
@@ -5337,7 +5337,7 @@
No match

"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I
-Capturing subpattern count = 3
+Capture group count = 3
Compile options: <none>
Overall options: anchored
Starting code units: 0 1 2 3 4 5 6 7 8 9
@@ -5393,31 +5393,31 @@
No match

/0{0,2}ABC/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 A
Last code unit = 'C'
Subject length lower bound = 3

/\d{3,}ABC/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9
Last code unit = 'C'
Subject length lower bound = 6

/\d*ABC/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9 A
Last code unit = 'C'
Subject length lower bound = 3

/[abc]+DE/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: a b c
Last code unit = 'E'
Subject length lower bound = 3

/[abc]?123/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 1 a b c
Last code unit = '3'
Subject length lower bound = 3
@@ -5435,7 +5435,7 @@
0: c123

/^(?:\d){3,5}X/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
Starting code units: 0 1 2 3 4 5 6 7 8 9
@@ -5462,7 +5462,7 @@
No match

"<(\w+)/?>(.)*</(\1)>"Igms
-Capturing subpattern count = 3
+Capture group count = 3
Max back reference = 1
Options: dotall multiline
First code unit = '<'
@@ -5475,7 +5475,7 @@
3: seite

/line\nbreak/I
-Capturing subpattern count = 0
+Capture group count = 0
Contains explicit CR or LF match
First code unit = 'l'
Last code unit = 'k'
@@ -5486,7 +5486,7 @@
0: line\x0abreak

/line\nbreak/I,firstline
-Capturing subpattern count = 0
+Capture group count = 0
Contains explicit CR or LF match
Options: firstline
First code unit = 'l'
@@ -5499,7 +5499,7 @@
No match

/line\nbreak/Im,firstline
-Capturing subpattern count = 0
+Capture group count = 0
Contains explicit CR or LF match
Options: firstline multiline
First code unit = 'l'
@@ -5512,7 +5512,7 @@
No match

/(?i)(?-i)AbCd/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'A'
Last code unit = 'd'
Subject length lower bound = 4
@@ -5532,7 +5532,7 @@
Failed: error 105 at offset 11: number too big in {} quantifier

"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'a' (caseless)
Last code unit = 'B'
@@ -5542,9 +5542,9 @@
1: k

 "(?P<n0>a)(?P<n1>b)(?P<n2>c)(?P<n3>d)(?P<n4>e)(?P<n5>f)(?P<n6>g)(?P<n7>h)(?P<n8>i)(?P<n9>j)(?P<n10>k)(?P<n11>l)A\11B"I
-Capturing subpattern count = 12
+Capture group count = 12
 Max back reference = 11
-Named capturing subpatterns:
+Named capture groups:
   n0    1
   n1    2
   n10  11
@@ -5576,7 +5576,7 @@
 12: l


"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I
-Capturing subpattern count = 12
+Capture group count = 12
Max back reference = 11
First code unit = 'a'
Last code unit = 'B'
@@ -5597,8 +5597,8 @@
12: l

 "(?P<name0>a)(?P<name1>a)(?P<name2>a)(?P<name3>a)(?P<name4>a)(?P<name5>a)(?P<name6>a)(?P<name7>a)(?P<name8>a)(?P<name9>a)(?P<name10>a)(?P<name11>a)(?P<name12>a)(?P<name13>a)(?P<name14>a)(?P<name15>a)(?P<name16>a)(?P<name17>a)(?P<name18>a)(?P<name19>a)(?P<name20>a)(?P<name21>a)(?P<name22>a)(?P<name23>a)(?P<name24>a)(?P<name25>a)(?P<name26>a)(?P<name27>a)(?P<name28>a)(?P<name29>a)(?P<name30>a)(?P<name31>a)(?P<name32>a)(?P<name33>a)(?P<name34>a)(?P<name35>a)(?P<name36>a)(?P<name37>a)(?P<name38>a)(?P<name39>a)(?P<name40>a)(?P<name41>a)(?P<name42>a)(?P<name43>a)(?P<name44>a)(?P<name45>a)(?P<name46>a)(?P<name47>a)(?P<name48>a)(?P<name49>a)(?P<name50>a)(?P<name51>a)(?P<name52>a)(?P<name53>a)(?P<name54>a)(?P<name55>a)(?P<name56>a)(?P<name57>a)(?P<name58>a)(?P<name59>a)(?P<name60>a)(?P<name61>a)(?P<name62>a)(?P<name63>a)(?P<name64>a)(?P<name65>a)(?P<name66>a)(?P<name67>a)(?P<name68>a)(?P<name69>a)(?P<name70>a)(?P<name71>a)(?P<name72>a)(?P<name73>a)(?P<name74>a)(?P<name75>a)(?P<name76>a)(?P<name77>a)(?P<name78>a)(?P<name79>a)(?P<name80>a)(?P<name81>a)(?P<name82>a)(?P<name83>a)(?P<name84>a)(?P<name85>a)(?P<name86>a)(?P<name87>a)(?P<name88>a)(?P<name89>a)(?P<name90>a)(?P<name91>a)(?P<name92>a)(?P<name93>a)(?P<name94>a)(?P<name95>a)(?P<name96>a)(?P<name97>a)(?P<name98>a)(?P<name99>a)(?P<name100>a)"I
-Capturing subpattern count = 101
-Named capturing subpatterns:
+Capture group count = 101
+Named capture groups:
   name0     1
   name1     2
   name10   11
@@ -5722,7 +5722,7 @@
 14: a


"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I
-Capturing subpattern count = 101
+Capture group count = 101
First code unit = 'a'
Last code unit = 'a'
Subject length lower bound = 101
@@ -5745,7 +5745,7 @@
14: a

 /[^()]*(?:\((?R)\)[^()]*)*/I
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     (this(and)that
@@ -5756,7 +5756,7 @@
  0: (this(and)that)stuff


 /[^()]*(?:\((?>(?R))\)[^()]*)*/I
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     (this(and)that
@@ -5765,7 +5765,7 @@
  0: (this(and)that)


 /[^()]*(?:\((?R)\))*[^()]*/I
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     (this(and)that
@@ -5774,7 +5774,7 @@
  0: (this(and)that)


 /(?:\((?R)\))*[^()]*/I
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     (this(and)that
@@ -5785,7 +5785,7 @@
  0: ((this))


 /(?:\((?R)\))|[^()]*/I
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     (this(and)that
@@ -5798,7 +5798,7 @@
  0: ((this))


/\x{0000ff}/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = \xff
Subject length lower bound = 1

@@ -5806,8 +5806,8 @@
Failed: error 143 at offset 18: two named subpatterns have the same name (PCRE2_DUPNAMES not set)

/^((?P<A>a1)|(?P<A>a2)b)/I,dupnames
-Capturing subpattern count = 3
-Named capturing subpatterns:
+Capture group count = 3
+Named capture groups:
A 2
A 3
Compile options: dupnames
@@ -5834,8 +5834,8 @@
C a1 (2) A (non-unique)

/(?|(?<a>)(?<b>)(?<a>)|(?<a>)(?<b>)(?<a>))/I,dupnames
-Capturing subpattern count = 3
-Named capturing subpatterns:
+Capture group count = 3
+Named capture groups:
a 1
a 3
b 2
@@ -5844,8 +5844,8 @@
Subject length lower bound = 0

/^(?P<A>a)(?P<A>b)/I,dupnames
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
A 1
A 2
Compile options: dupnames
@@ -5859,8 +5859,8 @@
C a (1) A (non-unique)

/^(?P<A>a)(?P<A>b)|cd/I,dupnames
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
A 1
A 2
Options: dupnames
@@ -5876,8 +5876,8 @@
Copy substring 'A' failed (-55): requested value is not set

/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/I,dupnames
-Capturing subpattern count = 4
-Named capturing subpatterns:
+Capture group count = 4
+Named capture groups:
A 1
A 2
A 3
@@ -5894,8 +5894,8 @@
C ef (2) A (non-unique)

/^((?P<A>a1)|(?P<A>a2)b)/I,dupnames
-Capturing subpattern count = 3
-Named capturing subpatterns:
+Capture group count = 3
+Named capture groups:
A 2
A 3
Compile options: dupnames
@@ -5922,8 +5922,8 @@
G a1 (2) A (non-unique)

/^(?P<A>a)(?P<A>b)/I,dupnames
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
A 1
A 2
Compile options: dupnames
@@ -5937,8 +5937,8 @@
G a (1) A (non-unique)

/^(?P<A>a)(?P<A>b)|cd/I,dupnames
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
A 1
A 2
Options: dupnames
@@ -5954,8 +5954,8 @@
Get substring 'A' failed (-55): requested value is not set

/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/I,dupnames
-Capturing subpattern count = 4
-Named capturing subpatterns:
+Capture group count = 4
+Named capture groups:
A 1
A 2
A 3
@@ -5972,8 +5972,8 @@
G ef (2) A (non-unique)

/(?J)^((?P<A>a1)|(?P<A>a2)b)/I
-Capturing subpattern count = 3
-Named capturing subpatterns:
+Capture group count = 3
+Named capture groups:
A 2
A 3
Compile options: <none>
@@ -6001,8 +6001,8 @@
# a random value.

/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<C>d)/I
-Capturing subpattern count = 4
-Named capturing subpatterns:
+Capture group count = 4
+Named capture groups:
A 1
B 2
B 3
@@ -6023,9 +6023,9 @@
C d (1) C (group 4)

/^(?P<A>a)?(?(A)a|b)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
-Named capturing subpatterns:
+Named capture groups:
A 1
Compile options: <none>
Overall options: anchored
@@ -6040,9 +6040,9 @@
No match

/(?:(?(ZZ)a|b)(?P<ZZ>X))+/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
-Named capturing subpatterns:
+Named capture groups:
ZZ 1
Last code unit = 'X'
Subject length lower bound = 2
@@ -6057,9 +6057,9 @@
Failed: error 115 at offset 6: reference to non-existent subpattern

/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
-Named capturing subpatterns:
+Named capture groups:
ZZ 1
Last code unit = 'X'
Subject length lower bound = 3
@@ -6068,9 +6068,9 @@
1: X

/(?:(?(ZZ)a|\(b\))\\(?P<ZZ>X))+/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
-Named capturing subpatterns:
+Named capture groups:
ZZ 1
Last code unit = 'X'
Subject length lower bound = 3
@@ -6079,12 +6079,12 @@
1: X

/(?P<ABC/I
-Failed: error 142 at offset 7: syntax error in subpattern name (missing terminator)
+Failed: error 142 at offset 7: syntax error in subpattern name (missing terminator?)

 /(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
-Named capturing subpatterns:
+Named capture groups:
   A   1
 Subject length lower bound = 2
     bXXaYYaY
@@ -6095,9 +6095,9 @@
  1: X


 /()()()()()()()()()(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I
-Capturing subpattern count = 10
+Capture group count = 10
 Max back reference = 10
-Named capturing subpatterns:
+Named capture groups:
   A  10
 Subject length lower bound = 2
     bXXaYYaY
@@ -6114,7 +6114,7 @@
 10: Y


/\s*,\s*/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 ,
Last code unit = ','
Subject length lower bound = 1
@@ -6124,7 +6124,7 @@
0: \x0c,\x0d

/^abc/Im,newline=lf
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
Forced newline is LF
First code unit at start or follows newline
@@ -6147,7 +6147,7 @@
No match

/^abc/Im,newline=crlf
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
Forced newline is CRLF
First code unit at start or follows newline
@@ -6162,7 +6162,7 @@
No match

/^abc/Im,newline=cr
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
Forced newline is CR
First code unit at start or follows newline
@@ -6180,7 +6180,7 @@
** Invalid value in 'newline=bad'

/.*/I,newline=lf
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Forced newline is LF
First code unit at start or follows newline
@@ -6193,7 +6193,7 @@
0: abc\x0d

/.*/I,newline=cr
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Forced newline is CR
First code unit at start or follows newline
@@ -6206,7 +6206,7 @@
0: abc

/.*/I,newline=crlf
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Forced newline is CRLF
First code unit at start or follows newline
@@ -6219,7 +6219,7 @@
0: abc

/\w+(.)(.)?def/Is
-Capturing subpattern count = 2
+Capture group count = 2
Options: dotall
Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P
Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z
@@ -6237,8 +6237,8 @@
2: \x0a

 /(?P<B>25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
   B   1
 Starting code units: 0 1 2 3 4 5 6 7 8 9 
 Last code unit = '.'
@@ -6250,7 +6250,7 @@
  ()()()()()()()()()()()()()()()()()()()()
  ()()()()()()()()()()()()()()()()()()()()
  (.(.))/Ix
-Capturing subpattern count = 102
+Capture group count = 102
 Options: extended
 Subject length lower bound = 2
     XY\=ovector=133
@@ -6359,42 +6359,42 @@
 102: Y


/(a*b|(?i:c*(?-i)d))/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: C a b c d
Subject length lower bound = 1

/()[ab]xyz/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b
Last code unit = 'z'
Subject length lower bound = 4

/(|)[ab]xyz/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b
Last code unit = 'z'
Subject length lower bound = 4

/(|c)[ab]xyz/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b c
Last code unit = 'z'
Subject length lower bound = 4

/(|c?)[ab]xyz/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b c
Last code unit = 'z'
Subject length lower bound = 4

/(d?|c?)[ab]xyz/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b c d
Last code unit = 'z'
Subject length lower bound = 4

 /(d?|c)[ab]xyz/I
-Capturing subpattern count = 1
+Capture group count = 1
 Starting code units: a b c d 
 Last code unit = 'z'
 Subject length lower bound = 4
@@ -6409,7 +6409,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: a b 
@@ -6426,7 +6426,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: a b 
@@ -6443,7 +6443,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 Starting code units: a b 
@@ -6460,7 +6460,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: <none>
 Overall options: anchored
 First code unit = 'a'
@@ -6482,7 +6482,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: caseless
 Overall options: anchored caseless
 Starting code units: A a 
@@ -6494,22 +6494,22 @@
  0: aaaa5


/(a*|b*)[cd]/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b c d
Subject length lower bound = 1

/(a+|b*)[cd]/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b c d
Subject length lower bound = 1

/(a*|b+)[cd]/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b c d
Subject length lower bound = 1

/(a+|b+)[cd]/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b
Subject length lower bound = 2

@@ -6521,7 +6521,7 @@
))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))
)))
/Ix
-Capturing subpattern count = 203
+Capture group count = 203
Options: extended
First code unit = 'a'
Subject length lower bound = 1
@@ -7138,8 +7138,8 @@
------------------------------------------------------------------

/(?P<abc>x)(?P<xyz>y)/I
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
abc 1
xyz 2
First code unit = 'x'
@@ -7153,8 +7153,8 @@
C y (1) xyz (group 2)

/(?<abc>x)(?'xyz'y)/I
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
abc 1
xyz 2
First code unit = 'x'
@@ -7168,10 +7168,10 @@
C y (1) xyz (group 2)

/(?<abc'x)(?'xyz'y)/I
-Failed: error 142 at offset 6: syntax error in subpattern name (missing terminator)
+Failed: error 142 at offset 6: syntax error in subpattern name (missing terminator?)

/(?<abc>x)(?'xyz>y)/I
-Failed: error 142 at offset 15: syntax error in subpattern name (missing terminator)
+Failed: error 142 at offset 15: syntax error in subpattern name (missing terminator?)

/(?P'abc'x)(?P<xyz>y)/I
Failed: error 141 at offset 3: unrecognized character after (?P
@@ -7364,9 +7364,9 @@
------------------------------------------------------------------

 /^\W*(?:(?<one>(?<two>.)\W*(?&one)\W*\k<two>|)|(?<three>(?<four>.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii
-Capturing subpattern count = 4
+Capture group count = 4
 Max back reference = 4
-Named capturing subpatterns:
+Named capture groups:
   four    4
   one     1
   three   3
@@ -7402,7 +7402,7 @@
 No match


/(?=(\w+))\1:/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P
Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z
@@ -7413,9 +7413,9 @@
1: abcd

/(?=(?'abc'\w+))\k<abc>:/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
-Named capturing subpatterns:
+Named capture groups:
abc 1
Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P
Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z
@@ -7450,7 +7450,7 @@
No match

/(?(<bc))/
-Failed: error 142 at offset 6: syntax error in subpattern name (missing terminator)
+Failed: error 142 at offset 6: syntax error in subpattern name (missing terminator?)

/(?(''))/
Failed: error 162 at offset 4: subpattern name expected
@@ -7474,10 +7474,10 @@
Failed: error 115 at offset 27: reference to non-existent subpattern

/^(?(DEFINE) abc | xyz ) /x
-Failed: error 154 at offset 4: DEFINE group contains more than one branch
+Failed: error 154 at offset 4: DEFINE subpattern contains more than one branch

/(?(DEFINE) abc) xyz/Ix
-Capturing subpattern count = 0
+Capture group count = 0
Options: extended
First code unit = 'x'
Last code unit = 'z'
@@ -7621,8 +7621,8 @@
No match

/(?&abc)X(?<abc>P)/I
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
abc 1
Last code unit = 'P'
Subject length lower bound = 3
@@ -7631,8 +7631,8 @@
1: P

/(?1)X(?<abc>P)/I
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
abc 1
Last code unit = 'P'
Subject length lower bound = 3
@@ -7933,7 +7933,7 @@
No match

/\g{A/
-Failed: error 142 at offset 4: syntax error in subpattern name (missing terminator)
+Failed: error 142 at offset 4: syntax error in subpattern name (missing terminator?)

/(?|(abc)|(xyz))/B
------------------------------------------------------------------
@@ -8390,10 +8390,10 @@
Failed: error 166 at offset 7: (*MARK) must have an argument

/(?i:A{1,}\6666666666)/
-Failed: error 161 at offset 19: group number is too big
+Failed: error 161 at offset 19: subpattern number is too big

/\g6666666666/
-Failed: error 161 at offset 7: group number is too big
+Failed: error 161 at offset 7: subpattern number is too big

/[\g6666666666]/B
------------------------------------------------------------------
@@ -8524,7 +8524,7 @@
No match

/a\Rb/I,bsr=anycrlf
-Capturing subpattern count = 0
+Capture group count = 0
\R matches CR, LF, or CRLF
First code unit = 'a'
Last code unit = 'b'
@@ -8542,7 +8542,7 @@
No match

/a\Rb/I,bsr=unicode
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
First code unit = 'a'
Last code unit = 'b'
@@ -8559,7 +8559,7 @@
0: a\x0bb

/a\R?b/I,bsr=anycrlf
-Capturing subpattern count = 0
+Capture group count = 0
\R matches CR, LF, or CRLF
First code unit = 'a'
Last code unit = 'b'
@@ -8577,7 +8577,7 @@
No match

/a\R?b/I,bsr=unicode
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
First code unit = 'a'
Last code unit = 'b'
@@ -8594,7 +8594,7 @@
0: a\x0bb

/a\R{2,4}b/I,bsr=anycrlf
-Capturing subpattern count = 0
+Capture group count = 0
\R matches CR, LF, or CRLF
First code unit = 'a'
Last code unit = 'b'
@@ -8612,7 +8612,7 @@
No match

/a\R{2,4}b/I,bsr=unicode
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
First code unit = 'a'
Last code unit = 'b'
@@ -8632,7 +8632,7 @@
No match

/(*BSR_ANYCRLF)a\Rb/I
-Capturing subpattern count = 0
+Capture group count = 0
\R matches CR, LF, or CRLF
First code unit = 'a'
Last code unit = 'b'
@@ -8643,7 +8643,7 @@
0: a\x0db

/(*BSR_UNICODE)a\Rb/I
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
First code unit = 'a'
Last code unit = 'b'
@@ -8652,7 +8652,7 @@
0: a\x85b

/(*BSR_ANYCRLF)(*CRLF)a\Rb/I
-Capturing subpattern count = 0
+Capture group count = 0
\R matches CR, LF, or CRLF
Forced newline is CRLF
First code unit = 'a'
@@ -8664,7 +8664,7 @@
0: a\x0db

/(*CRLF)(*BSR_UNICODE)a\Rb/I
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
Forced newline is CRLF
First code unit = 'a'
@@ -8674,7 +8674,7 @@
0: a\x85b

/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I
-Capturing subpattern count = 0
+Capture group count = 0
\R matches CR, LF, or CRLF
Forced newline is CR
First code unit = 'a'
@@ -8893,12 +8893,12 @@
Failed: error 109 at offset 8: quantifier does not follow a repeatable item

/(abc|pqr|123){0}[xyz]/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: x y z
Subject length lower bound = 1

/(?(?=.*b)b|^)/I,auto_callout
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Options: auto_callout
Subject length lower bound = 0
@@ -8938,11 +8938,11 @@
0: b

/(?(?=b).*b|^d)/I
-Capturing subpattern count = 0
+Capture group count = 0
Subject length lower bound = 1

/(?(?=.*b).*b|^d)/I
-Capturing subpattern count = 0
+Capture group count = 0
Subject length lower bound = 1

/xyz/auto_callout
@@ -9680,48 +9680,48 @@
Failed: error 125 at offset 0: lookbehind assertion is not fixed length

/(a|bc)\1/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Starting code units: a b
Subject length lower bound = 2

/(a|bc)\1{2,3}/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Starting code units: a b
Subject length lower bound = 3

/(a|bc)(?1)/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b
Subject length lower bound = 2

/(a|b\1)(a|b\1)/I
-Capturing subpattern count = 2
+Capture group count = 2
Max back reference = 1
Starting code units: a b
Subject length lower bound = 2

/(a|b\1){2}/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Starting code units: a b
Subject length lower bound = 2

/(a|bbbb\1)(a|bbbb\1)/I
-Capturing subpattern count = 2
+Capture group count = 2
Max back reference = 1
Starting code units: a b
Subject length lower bound = 2

/(a|bbbb\1){2}/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Starting code units: a b
Subject length lower bound = 2

/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'F'
@@ -9729,7 +9729,7 @@
Subject length lower bound = 22

/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/Iis
-Capturing subpattern count = 11
+Capture group count = 11
Options: caseless dotall
First code unit = '<'
Last code unit = '>'
@@ -9736,24 +9736,24 @@
Subject length lower bound = 47

"(?>.*/)foo"I
-Capturing subpattern count = 0
+Capture group count = 0
Last code unit = 'o'
Subject length lower bound = 4

/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /Ix
-Capturing subpattern count = 0
+Capture group count = 0
Options: extended
Last code unit = '-'
Subject length lower bound = 8

/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/Ii
-Capturing subpattern count = 1
+Capture group count = 1
Options: caseless
Starting code units: A B C a b c
Subject length lower bound = 1

 /(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: c d 
 Last code unit = 'b'
 Subject length lower bound = 41
@@ -9763,7 +9763,7 @@
  (?(1) (.*?)\1 | ([^\s]+))       # if quote found, match up to next matching
                                  # quote, otherwise match up to next space
 /Iisx
-Capturing subpattern count = 3
+Capture group count = 3
 Max back reference = 1
 Options: caseless dotall extended
 First code unit = '<'
@@ -9779,7 +9779,7 @@
   [0-9a-f]{1,4} $             # final hex number at end of string
   (?(1)|.)                    # check that there was an empty component
   /Iix
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 Compile options: caseless extended
 Overall options: anchored caseless extended
@@ -9787,8 +9787,8 @@
 Subject length lower bound = 2


 /(?|(?<a>A)|(?<a>B))/I
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
   a   1
 Starting code units: A B 
 Subject length lower bound = 1
@@ -9807,9 +9807,9 @@
 /(?:a(?<quote> (?<apostrophe>')|(?<realquote>")) |
     b(?<quote> (?<apostrophe>')|(?<realquote>")) )
     (?('quote')[a-z]+|[0-9]+)/Ix,dupnames
-Capturing subpattern count = 6
+Capture group count = 6
 Max back reference = 4
-Named capturing subpatterns:
+Named capture groups:
   apostrophe   2
   apostrophe   5
   quote        1
@@ -9869,9 +9869,9 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 4
+Capture group count = 4
 Max back reference = 4
-Named capturing subpatterns:
+Named capture groups:
   D   4
   D   1
 Compile options: dupnames extended
@@ -9917,9 +9917,9 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 4
+Capture group count = 4
 Max back reference = 4
-Named capturing subpatterns:
+Named capture groups:
   A   1
   A   4
 Options: dupnames extended
@@ -9979,7 +9979,7 @@
  3: a


/(\3)(\1)(a)/I,alt_bsux,allow_empty_class,match_unset_backref,dupnames
-Capturing subpattern count = 3
+Capture group count = 3
Max back reference = 3
Options: alt_bsux allow_empty_class dupnames match_unset_backref
Last code unit = 'a'
@@ -9991,7 +9991,7 @@
3: a

/(\3)(\1)(a)/I
-Capturing subpattern count = 3
+Capture group count = 3
Max back reference = 3
Last code unit = 'a'
Subject length lower bound = 3
@@ -10000,8 +10000,8 @@
No match

/i(?(DEFINE)(?<s>a))/I
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
s 1
First code unit = 'i'
Subject length lower bound = 1
@@ -10009,7 +10009,7 @@
0: i

/()i(?(1)a)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'i'
Subject length lower bound = 1
@@ -10507,7 +10507,7 @@
------------------------------------------------------------------

/(?P<abn>(?P=abn)(?<badstufxxx)/B
-Failed: error 142 at offset 29: syntax error in subpattern name (missing terminator)
+Failed: error 142 at offset 29: syntax error in subpattern name (missing terminator?)

 /(?P<abn>(?P=axn)xxx)/B
 Failed: error 115 at offset 12: reference to non-existent subpattern
@@ -10619,13 +10619,13 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 First code unit = 'a'
 Last code unit = '4'
 Subject length lower bound = 5


/([abc])++1234/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b c
Last code unit = '4'
Subject length lower bound = 5
@@ -10634,7 +10634,7 @@
Failed: error 125 at offset 0: lookbehind assertion is not fixed length

/(^ab)/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -10641,7 +10641,7 @@
Subject length lower bound = 2

/(^ab)++/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -10648,7 +10648,7 @@
Subject length lower bound = 2

/(^ab|^)+/I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
Compile options: <none>
Overall options: anchored
@@ -10655,7 +10655,7 @@
Subject length lower bound = 0

/(^ab|^)++/I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
Compile options: <none>
Overall options: anchored
@@ -10662,7 +10662,7 @@
Subject length lower bound = 0

/(?:^ab)/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -10669,7 +10669,7 @@
Subject length lower bound = 2

/(?:^ab)++/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -10676,7 +10676,7 @@
Subject length lower bound = 2

/(?:^ab|^)+/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Compile options: <none>
Overall options: anchored
@@ -10683,7 +10683,7 @@
Subject length lower bound = 0

/(?:^ab|^)++/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Compile options: <none>
Overall options: anchored
@@ -10690,93 +10690,93 @@
Subject length lower bound = 0

/(.*ab)/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit at start or follows newline
Last code unit = 'b'
Subject length lower bound = 2

/(.*ab)++/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit at start or follows newline
Last code unit = 'b'
Subject length lower bound = 2

/(.*ab|.*)+/I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
First code unit at start or follows newline
Subject length lower bound = 0

/(.*ab|.*)++/I
-Capturing subpattern count = 1
+Capture group count = 1
May match empty string
First code unit at start or follows newline
Subject length lower bound = 0

/(?:.*ab)/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit at start or follows newline
Last code unit = 'b'
Subject length lower bound = 2

/(?:.*ab)++/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit at start or follows newline
Last code unit = 'b'
Subject length lower bound = 2

/(?:.*ab|.*)+/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
First code unit at start or follows newline
Subject length lower bound = 0

/(?:.*ab|.*)++/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
First code unit at start or follows newline
Subject length lower bound = 0

/(?=a)[bcd]/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Subject length lower bound = 1

/((?=a))[bcd]/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 1

/((?=a))+[bcd]/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 1

/((?=a))++[bcd]/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Subject length lower bound = 1

/(?=a+)[bcd]/Ii
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless
First code unit = 'a' (caseless)
Subject length lower bound = 1

/(?=a+?)[bcd]/Ii
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless
First code unit = 'a' (caseless)
Subject length lower bound = 1

/(?=a++)[bcd]/Ii
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless
First code unit = 'a' (caseless)
Subject length lower bound = 1

/(?=a{3})[bcd]/Ii
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless
First code unit = 'a' (caseless)
Last code unit = 'a' (caseless)
@@ -10922,22 +10922,22 @@
3: b

/(?(DEFINE)(a(?2)|b)(b(?1)|a))(?:(?1)|(?2))/I
-Capturing subpattern count = 2
+Capture group count = 2
May match empty string
Subject length lower bound = 0

/(a(?2)|b)(b(?1)|a)(?:(?1)|(?2))/I
-Capturing subpattern count = 2
+Capture group count = 2
Starting code units: a b
Subject length lower bound = 3

/(a(?2)|b)(b(?1)|a)(?1)(?2)/I
-Capturing subpattern count = 2
+Capture group count = 2
Starting code units: a b
Subject length lower bound = 4

/(abc)(?1)/I
-Capturing subpattern count = 1
+Capture group count = 1
First code unit = 'a'
Last code unit = 'c'
Subject length lower bound = 6
@@ -11206,7 +11206,7 @@
No match

/\btype\b\W*?\btext\b\W*?\bjavascript\b/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
First code unit = 't'
Last code unit = 't'
@@ -11213,13 +11213,13 @@
Subject length lower bound = 18

/\btype\b\W*?\btext\b\W*?\bjavascript\b|\burl\b\W*?\bshell:|<input\b.*?\btype\b\W*?\bimage\b|\bonkeyup\b\W*?\=/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
Starting code units: < o t u
Subject length lower bound = 8

 /a(*SKIP)c|b(*ACCEPT)|/I,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     a
@@ -11227,7 +11227,7 @@
  0+ 


 /a(*SKIP)c|b(*ACCEPT)cd(*ACCEPT)|x/I
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: a b x 
 Subject length lower bound = 0
     ax
@@ -11245,7 +11245,7 @@
 No match


 /(*ACCEPT)a/I,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 0
     bax
  0: 
@@ -11252,7 +11252,7 @@
  0+ bax


 /z(*ACCEPT)a/I,aftertext
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'z'
 Subject length lower bound = 0
     baxzbx
@@ -11755,13 +11755,13 @@
 # settings of the anchored and startline bits.


/(?>.*?a)(?<=ba)/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 2
Last code unit = 'a'
Subject length lower bound = 1

/(?:.*?a)(?<=ba)/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 2
First code unit at start or follows newline
Last code unit = 'a'
@@ -11768,18 +11768,18 @@
Subject length lower bound = 1

/.*?a(*PRUNE)b/I
-Capturing subpattern count = 0
+Capture group count = 0
Last code unit = 'b'
Subject length lower bound = 2

/.*?a(*PRUNE)b/Is
-Capturing subpattern count = 0
+Capture group count = 0
Options: dotall
Last code unit = 'b'
Subject length lower bound = 2

/^a(*PRUNE)b/Is
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: dotall
Overall options: anchored dotall
First code unit = 'a'
@@ -11786,23 +11786,23 @@
Subject length lower bound = 2

/.*?a(*SKIP)b/I
-Capturing subpattern count = 0
+Capture group count = 0
Last code unit = 'b'
Subject length lower bound = 2

/(?>.*?a)b/Is
-Capturing subpattern count = 0
+Capture group count = 0
Options: dotall
Last code unit = 'b'
Subject length lower bound = 2

/(?>.*?a)b/I
-Capturing subpattern count = 0
+Capture group count = 0
Last code unit = 'b'
Subject length lower bound = 2

/(?>^a)b/Is
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: dotall
Overall options: anchored dotall
First code unit = 'a'
@@ -11809,29 +11809,29 @@
Subject length lower bound = 2

/(?>.*?)(?<=(abcd)|(wxyz))/I
-Capturing subpattern count = 2
+Capture group count = 2
Max lookbehind = 4
May match empty string
Subject length lower bound = 0

/(?>.*)(?<=(abcd)|(wxyz))/I
-Capturing subpattern count = 2
+Capture group count = 2
Max lookbehind = 4
May match empty string
Subject length lower bound = 0

"(?>.*)foo"I
-Capturing subpattern count = 0
+Capture group count = 0
Last code unit = 'o'
Subject length lower bound = 3

"(?>.*?)foo"I
-Capturing subpattern count = 0
+Capture group count = 0
Last code unit = 'o'
Subject length lower bound = 3

/(?>^abc)/Im
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
First code unit at start or follows newline
Last code unit = 'c'
@@ -11838,13 +11838,13 @@
Subject length lower bound = 3

/(?>.*abc)/Im
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
Last code unit = 'c'
Subject length lower bound = 3

/(?:.*abc)/Im
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
First code unit at start or follows newline
Last code unit = 'c'
@@ -12057,8 +12057,8 @@
0: ba

 /(?|(?<n>f)|(?<n>b))/I,dupnames
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
   n   1
 Options: dupnames
 Starting code units: b f 
@@ -12079,9 +12079,9 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 3
+Capture group count = 3
 Max back reference = 2
-Named capturing subpatterns:
+Named capture groups:
   a   1
   a   2
 Options: dupnames
@@ -13124,7 +13124,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: a b c d 
 Last code unit = 'd'
 Subject length lower bound = 1
@@ -13137,7 +13137,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: a b c 
 Last code unit = 'd'
 Subject length lower bound = 2
@@ -13150,7 +13150,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: a b c d 
 Last code unit = 'd'
 Subject length lower bound = 1
@@ -13163,7 +13163,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: a b c 
 Last code unit = 'd'
 Subject length lower bound = 5
@@ -13176,7 +13176,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: a b c d 
 Last code unit = 'd'
 Subject length lower bound = 1
@@ -13254,40 +13254,40 @@
 Failed: error 150 at offset 5: invalid range in character class


/(?<0abc>xx)/
-Failed: error 144 at offset 3: group name must start with a non-digit
+Failed: error 144 at offset 3: subpattern name must start with a non-digit

/(?&1abc)xx(?<1abc>y)/
-Failed: error 144 at offset 3: group name must start with a non-digit
+Failed: error 144 at offset 3: subpattern name must start with a non-digit

/(?<ab-cd>xx)/
-Failed: error 142 at offset 5: syntax error in subpattern name (missing terminator)
+Failed: error 142 at offset 5: syntax error in subpattern name (missing terminator?)

/(?'0abc'xx)/
-Failed: error 144 at offset 3: group name must start with a non-digit
+Failed: error 144 at offset 3: subpattern name must start with a non-digit

/(?P<0abc>xx)/
-Failed: error 144 at offset 4: group name must start with a non-digit
+Failed: error 144 at offset 4: subpattern name must start with a non-digit

/\k<5ghj>/
-Failed: error 144 at offset 3: group name must start with a non-digit
+Failed: error 144 at offset 3: subpattern name must start with a non-digit

/\k'5ghj'/
-Failed: error 144 at offset 3: group name must start with a non-digit
+Failed: error 144 at offset 3: subpattern name must start with a non-digit

/\k{2fgh}/
-Failed: error 144 at offset 3: group name must start with a non-digit
+Failed: error 144 at offset 3: subpattern name must start with a non-digit

/(?P=8yuki)/
-Failed: error 144 at offset 4: group name must start with a non-digit
+Failed: error 144 at offset 4: subpattern name must start with a non-digit

/\g{4df}/
Failed: error 157 at offset 2: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number

/(?&1abc)xx(?<1abc>y)/
-Failed: error 144 at offset 3: group name must start with a non-digit
+Failed: error 144 at offset 3: subpattern name must start with a non-digit

/(?P>1abc)xx(?<1abc>y)/
-Failed: error 144 at offset 4: group name must start with a non-digit
+Failed: error 144 at offset 4: subpattern name must start with a non-digit

/\g'3gh'/
Failed: error 157 at offset 2: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number
@@ -13296,16 +13296,16 @@
Failed: error 157 at offset 2: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number

/(?(<4gh>)abc)/
-Failed: error 144 at offset 4: group name must start with a non-digit
+Failed: error 144 at offset 4: subpattern name must start with a non-digit

/(?('4gh')abc)/
-Failed: error 144 at offset 4: group name must start with a non-digit
+Failed: error 144 at offset 4: subpattern name must start with a non-digit

/(?(4gh)abc)/
Failed: error 124 at offset 4: missing closing parenthesis for condition

/(?(R&6yh)abc)/
-Failed: error 144 at offset 5: group name must start with a non-digit
+Failed: error 144 at offset 5: subpattern name must start with a non-digit

/(((a\2)|(a*)\g<-1>))*a?/B
------------------------------------------------------------------
@@ -13487,7 +13487,7 @@
0+ dab

 /(?(VERSION>=10.0)yes|no)/I
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 2
     yesno
  0: yes
@@ -13506,7 +13506,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Subject length lower bound = 0
     yesno
@@ -13514,7 +13514,7 @@
  0+ yesno


 /(?(VERSION=8)yes|no){3}/I
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 6
     yesnononoyes
  0: nonono
@@ -13523,9 +13523,9 @@
 No match


/(?:(?<VERSION>abc)|xyz)(?(VERSION)yes|no)/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
-Named capturing subpatterns:
+Named capture groups:
VERSION 1
Starting code units: a x
Subject length lower bound = 5
@@ -13553,18 +13553,18 @@
Failed: error 179 at offset 16: syntax error or number too big in (?(VERSION condition

/abcd/I
-Capturing subpattern count = 0
+Capture group count = 0
First code unit = 'a'
Last code unit = 'd'
Subject length lower bound = 4

/abcd/I,no_start_optimize
-Capturing subpattern count = 0
+Capture group count = 0
Options: no_start_optimize
Subject length lower bound = 0

/(|ab)*?d/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a d
Last code unit = 'd'
Subject length lower bound = 1
@@ -13575,7 +13575,7 @@
0: d

 /(|ab)*?d/I,no_start_optimize
-Capturing subpattern count = 1
+Capture group count = 1
 Options: no_start_optimize
 Subject length lower bound = 0
    abd
@@ -13839,7 +13839,7 @@
 get substring list failed (-2): partial match


/^abc/info
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -13846,7 +13846,7 @@
Subject length lower bound = 3

/^abc/info,no_dotstar_anchor
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: no_dotstar_anchor
Overall options: anchored no_dotstar_anchor
First code unit = 'a'
@@ -13853,7 +13853,7 @@
Subject length lower bound = 3

/.*\d/info,auto_callout
-Capturing subpattern count = 0
+Capture group count = 0
Options: auto_callout
First code unit at start or follows newline
Subject length lower bound = 1
@@ -13868,7 +13868,7 @@
No match

/.*\d/info,no_dotstar_anchor,auto_callout
-Capturing subpattern count = 0
+Capture group count = 0
Options: auto_callout no_dotstar_anchor
Subject length lower bound = 1
\= Expect no match
@@ -13889,18 +13889,18 @@
No match

/.*\d/dotall,info
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: dotall
Overall options: anchored dotall
Subject length lower bound = 1

/.*\d/dotall,no_dotstar_anchor,info
-Capturing subpattern count = 0
+Capture group count = 0
Options: dotall no_dotstar_anchor
Subject length lower bound = 1

/(*NO_DOTSTAR_ANCHOR)(?s).*\d/info
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: no_dotstar_anchor
Subject length lower bound = 1
@@ -14323,7 +14323,7 @@
0+

/((?2){73}(?2))((?1))/info
-Capturing subpattern count = 2
+Capture group count = 2
May match empty string
Subject length lower bound = 0

@@ -14383,8 +14383,8 @@
/(?x:((?'a')) # comment (with parentheses) and | vertical
(?-x:#not a comment (?'b')) # this is a comment ()
(?'c')) # not a comment (?'d')/info
-Capturing subpattern count = 5
-Named capturing subpatterns:
+Capture group count = 5
+Named capture groups:
a 2
b 3
c 4
@@ -14394,8 +14394,8 @@
Subject length lower bound = 32

/(?|(?'a')(2)(?'b')|(?'a')(?'a')(3))/I,dupnames
-Capturing subpattern count = 3
-Named capturing subpatterns:
+Capture group count = 3
+Named capture groups:
a 1
a 2
b 3
@@ -14482,7 +14482,7 @@
"(?J:(?|(?'R')(\k'R')|((?'R'))))"

/(?<=|(\,\$(?73591620449005828816)\xa8.{7}){6}\x09)/
-Failed: error 161 at offset 17: group number is too big
+Failed: error 161 at offset 17: subpattern number is too big

/^(?:(?(1)x|)+)+$()/B
------------------------------------------------------------------
@@ -14533,8 +14533,8 @@
Failed: error 162 at offset 14: subpattern name expected

/((?x)(?#))#(?'abc')/I
-Capturing subpattern count = 2
-Named capturing subpatterns:
+Capture group count = 2
+Named capture groups:
abc 2
First code unit = '#'
Subject length lower bound = 1
@@ -14543,8 +14543,8 @@
Failed: error 162 at offset 9: subpattern name expected

/[[:\\](?'abc')[a:]/I
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
abc 1
Starting code units: : [ \
Subject length lower bound = 2
@@ -14578,16 +14578,16 @@
Failed: error 162 at offset 16: subpattern name expected

/(?(?C{\Q})(?!(?'abc')))/I
-Capturing subpattern count = 1
-Named capturing subpatterns:
+Capture group count = 1
+Named capture groups:
abc 1
May match empty string
Subject length lower bound = 0

/(?1){3918}(((((0(\k'R'))))(?J)(?'R'(?'R'\3){99})))/I
-Capturing subpattern count = 8
+Capture group count = 8
Max back reference = 8
-Named capturing subpatterns:
+Named capture groups:
R 7
R 8
Duplicate name status changes
@@ -14595,33 +14595,33 @@
Subject length lower bound = 65535

/(?|(aaa)|(b))\g{1}/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Starting code units: a b
Subject length lower bound = 0

/(?|(aaa)|(b))(?1)/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b
Subject length lower bound = 4

/(?|(aaa)|(b))/I
-Capturing subpattern count = 1
+Capture group count = 1
Starting code units: a b
Subject length lower bound = 1

/(?|(?'a'aaa)|(?'a'b))\k'a'/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
-Named capturing subpatterns:
+Named capture groups:
a 1
Starting code units: a b
Subject length lower bound = 0

/(?|(?'a'aaa)|(?'a'b))(?'a'cccc)\k'a'/I,dupnames
-Capturing subpattern count = 2
+Capture group count = 2
Max back reference = 2
-Named capturing subpatterns:
+Named capture groups:
a 1
a 2
Options: dupnames
@@ -14673,10 +14673,10 @@
0: ab

/(?(8000000000/
-Failed: error 161 at offset 8: group number is too big
+Failed: error 161 at offset 8: subpattern number is too big

/((?(R8000000000)))/
-Failed: error 161 at offset 9: group number is too big
+Failed: error 161 at offset 9: subpattern number is too big

/0(?0)|(1)(*THEN)(*SKIP:0)(*FAIL)/
\= Expect no match
@@ -14684,7 +14684,7 @@
No match

/(?(1)()\983040\2)/
-Failed: error 161 at offset 14: group number is too big
+Failed: error 161 at offset 14: subpattern number is too big

/(*LIMIT_MATCH=)abc/
Failed: error 160 at offset 14: (*VERB) not recognized or malformed
@@ -14883,7 +14883,7 @@
1: AAbbaa..AAbBaa

/^(o(\1{72}{\"{\\{00000059079}\d*){74}}){19}/I
-Capturing subpattern count = 2
+Capture group count = 2
Max back reference = 1
Compile options: <none>
Overall options: anchored
@@ -14892,10 +14892,10 @@
Subject length lower bound = 65535

/((p(?'K/
-Failed: error 142 at offset 7: syntax error in subpattern name (missing terminator)
+Failed: error 142 at offset 7: syntax error in subpattern name (missing terminator?)

/((p(?'K/no_auto_capture
-Failed: error 142 at offset 7: syntax error in subpattern name (missing terminator)
+Failed: error 142 at offset 7: syntax error in subpattern name (missing terminator?)

 /abc/replace=A$3123456789Z
     abc
@@ -14905,7 +14905,7 @@
 Failed: error 187 at offset 0: lookbehind assertion is too long


/(?<!a{65535})x/I
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 65535
First code unit = 'x'
Subject length lower bound = 1
@@ -14919,7 +14919,7 @@
Failed: error -60: match with end before start or start moved backwards is not supported

/(?'abcdefghijklmnopqrstuvwxyzABCDEFG'toolong)/
-Failed: error 148 at offset 36: subpattern name is too long (maximum 32 characters)
+Failed: error 148 at offset 36: subpattern name is too long (maximum 32 code units)

/(?'abcdefghijklmnopqrstuvwxyzABCDEF'justright)/

@@ -14941,7 +14941,7 @@
((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))
((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))
((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))"xI
-Capturing subpattern count = 12
+Capture group count = 12
May match empty string
Options: extended
First code unit at start or follows newline
@@ -14952,7 +14952,7 @@
((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))
((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))
a)"xI
-Capturing subpattern count = 12
+Capture group count = 12
Max lookbehind = 2
May match empty string
Options: extended
@@ -14962,7 +14962,7 @@
((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))
((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))
((?-2)(?-2))((?-2)(?-2))((?-2)(?-2))"xI
-Capturing subpattern count = 13
+Capture group count = 13
May match empty string
Options: extended
Subject length lower bound = 0
@@ -14979,7 +14979,7 @@

/\[()]{1024}/I,expand
Expanded: ()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()
-Capturing subpattern count = 1024
+Capture group count = 1024
May match empty string
Subject length lower bound = 0

@@ -14986,7 +14986,7 @@
# Test minlength capped at 65535

 /(A{65000})\1{65000}/I
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 First code unit = 'A'
 Last code unit = 'A'
@@ -15008,7 +15008,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 May match empty string
 Subject length lower bound = 0


@@ -15026,7 +15026,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 May match empty string
 Subject length lower bound = 0


@@ -15044,7 +15044,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 May match empty string
 Subject length lower bound = 0


@@ -15062,7 +15062,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 May match empty string
 Subject length lower bound = 0


@@ -15510,7 +15510,7 @@
------------------------------------------------------------------

/(?=.*[A-Z])/I
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Subject length lower bound = 0

@@ -15592,7 +15592,7 @@
# complicated to find a minimum matching length.

"()X|((((((((()))))))((((())))))\2())((((((\2\2)))\2)(\22((((\2\2)2))\2)))(2\ZZZ)+:)Z^|91ZiZZnter(ZZ |91Z(ZZ ZZ(\r2Z( or#(\Z2(Z\Z(\2\2)2))\2Z)Z(\22Z((\Z2(Z\Z(\2\2)2))\2Z+:)Z|91Z(ZZ ZZ(\r2Z( or#(\Z2(Z\Z((Z*(\2(Z\':))\0)i|||||||||||||||loZ\2\2)2))\2Z)Z(\22Z((\Z2(Z\Z(\2\2)2))\2Z)))int \)\0nte!rnal errpr\2\\21r(2\ZZZ)+:)Z!|91Z(ZZ ZZ(\r2Z( or#(\Z2(Z\Z(\2\2)2))\2Z)Z(\22Z((\Z2(Z\Z(\2\2)2))\2Z)))int \)\0(2\ZZZ)+:)Z^|91ZiZZnter(ZZ |91Z(ZZ ZZ(\r2Z( or#(\Z2(Z\Z(\2\2)2))\2Z)Z(\22Z((\Z2(Z\Z(\2\2)2))\2Z)))int \)\0(2\ZZZ)+:)Z^)))int \)\0(2\ZZZ)+:)Z^|91ZiZZnter(ZZernZal ZZ(\r2Z( or#(\Z2(Z\Z(\2\2)2))\2Z)Z(\22Z((\Z2(Z\Z(\2\2)2))\2Z)))int \))\ZZ(\r2Z( or#(\Z2(Z\Z(\2\2)2))\2Z)Z(\22Z((\Z2(Z\Z(\2\2)))\2))))((((((\2\2))))))"I
-Capturing subpattern count = 108
+Capture group count = 108
Max back reference = 22
Contains explicit CR or LF match
Subject length lower bound = 1
@@ -15626,13 +15626,13 @@
Failed: error -37: callout error code

/()(\g+65534)/
-Failed: error 161 at offset 11: group number is too big
+Failed: error 161 at offset 11: subpattern number is too big

/()(\g+65533)/
Failed: error 115 at offset 10: reference to non-existent subpattern

/\xC1\x00\x00\x00?\x9A(\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\2*\x00k\d+\x00‎\x00\x00\x00\x00\x00\2*\x00\x00\1*.){36}int^\x00\x00?\xFF\xFF\x00\x9A(\1{50779}?)J\w2/I
-Capturing subpattern count = 2
+Capture group count = 2
Max back reference = 2
First code unit = \xc1
Last code unit = '2'
@@ -15639,7 +15639,7 @@
Subject length lower bound = 65535

/(a)(b)\2\1\1\1\1/I
-Capturing subpattern count = 2
+Capture group count = 2
Max back reference = 2
First code unit = 'a'
Last code unit = 'b'
@@ -15646,9 +15646,9 @@
Subject length lower bound = 7

/(?<a>a)(?<b>b)\g{b}\g{a}\g{a}\g{a}\g{a}(?<a>xx)(?<b>zz)/I,dupnames
-Capturing subpattern count = 4
+Capture group count = 4
Max back reference = 4
-Named capturing subpatterns:
+Named capture groups:
a 1
a 3
b 2
@@ -15816,7 +15816,7 @@
# the start of a branch.

/(?(DEFINE)(a))^bc/I
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: <none>
Overall options: anchored
First code unit = 'b'
@@ -15823,7 +15823,7 @@
Subject length lower bound = 2

/(a){0}.*bc/sI
-Capturing subpattern count = 1
+Capture group count = 1
Compile options: dotall
Overall options: anchored dotall
Last code unit = 'c'
@@ -15833,7 +15833,7 @@
# no alternative branch.

/(?(VERSION>=999)yes)^bc/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
Subject length lower bound = 2
@@ -15841,12 +15841,12 @@
# This should not be anchored.

/(?(VERSION>=999)yes|no)^bc/I
-Capturing subpattern count = 0
+Capture group count = 0
Last code unit = 'c'
Subject length lower bound = 4

 /(*LIMIT_HEAP=0)xxx/I
-Capturing subpattern count = 0
+Capture group count = 0
 Heap limit = 0
 First code unit = 'x'
 Last code unit = 'x'
@@ -16122,7 +16122,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended_more
 Starting code units: a b c 
 Subject length lower bound = 1
@@ -16134,7 +16134,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended extended_more
 Starting code units: a b c 
 Subject length lower bound = 1
@@ -16218,7 +16218,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Extra options: bad_escape_is_literal
 First code unit = 'N'
 Last code unit = 'c'
@@ -16324,7 +16324,7 @@
  0: (*CR)abc


/cat|dog/I,match_word
-Capturing subpattern count = 0
+Capture group count = 0
Max lookbehind = 1
Extra options: match_word
Starting code units: c d
@@ -16340,7 +16340,7 @@
No match

/(cat)|dog/I,match_line,literal
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: literal
Overall options: anchored literal
Extra options: match_line
@@ -16408,7 +16408,7 @@
# Perl gets the second of these wrong, giving no match.

"(?<=(a))\1?b"I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Max lookbehind = 1
Last code unit = 'b'
@@ -16421,7 +16421,7 @@
1: a

"(?=(a))\1?b"I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'a'
Last code unit = 'b'
@@ -16650,7 +16650,7 @@
Failed: error 194 at offset 5: invalid hyphen in option setting

 /(?(?=^))b/I
-Capturing subpattern count = 0
+Capture group count = 0
 Last code unit = 'b'
 Subject length lower bound = 1
     abc
@@ -16657,7 +16657,7 @@
  0: b


 /(?(?=^)|)b/I
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = 'b'
 Subject length lower bound = 1
     abc
@@ -16664,7 +16664,7 @@
  0: b


/(?(?=^)|^)b/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'b'
@@ -16676,7 +16676,7 @@
No match

/(?(1)^|^())/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
May match empty string
Compile options: <none>
@@ -16684,13 +16684,13 @@
Subject length lower bound = 0

/(?(1)^())b/I
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Last code unit = 'b'
Subject length lower bound = 1

/(?(1)^())+b/I,aftertext
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Last code unit = 'b'
Subject length lower bound = 1
@@ -16699,7 +16699,7 @@
0+ c

/(?(1)^()|^)+b/I,aftertext
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Compile options: <none>
Overall options: anchored
@@ -16713,7 +16713,7 @@
No match

/(?(1)^()|^)*b/I,aftertext
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
First code unit = 'b'
Subject length lower bound = 1
@@ -16728,7 +16728,7 @@
0+ c

/(?(1)^())+b/I,aftertext
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Last code unit = 'b'
Subject length lower bound = 1
@@ -16737,7 +16737,7 @@
0+ c

/(?(1)^a()|^a)+b/I,aftertext
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Compile options: <none>
Overall options: anchored
@@ -16752,7 +16752,7 @@
No match

/(?(1)^|^(a))+b/I,aftertext
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Compile options: <none>
Overall options: anchored
@@ -16767,7 +16767,7 @@
No match

/(?(1)^a()|^a)*b/I,aftertext
-Capturing subpattern count = 1
+Capture group count = 1
Max back reference = 1
Last code unit = 'b'
Subject length lower bound = 1
@@ -16894,7 +16894,7 @@
0: foobar

/(*:XX)^abc/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -16901,7 +16901,7 @@
Subject length lower bound = 3

/(*COMMIT:XX)^abc/I
-Capturing subpattern count = 0
+Capture group count = 0
Compile options: <none>
Overall options: anchored
First code unit = 'a'
@@ -16908,7 +16908,7 @@
Subject length lower bound = 3

/(*ACCEPT:XX)^abc/I
-Capturing subpattern count = 0
+Capture group count = 0
Subject length lower bound = 0

# End of testinput2

Modified: code/trunk/testdata/testoutput20
===================================================================
--- code/trunk/testdata/testoutput20    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput20    2019-02-06 18:11:36 UTC (rev 1066)
@@ -32,9 +32,9 @@
 #load testsaved2


#pop info
-Capturing subpattern count = 2
+Capture group count = 2
Max back reference = 2
-Named capturing subpatterns:
+Named capture groups:
n 1
n 2
Options: dupnames
@@ -66,8 +66,8 @@
4: A

 #pop info
-Capturing subpattern count = 4
-Named capturing subpatterns:
+Capture group count = 4
+Named capture groups:
   ADDR          2
   ADDRESS_PAT   4
   NAME          1


Modified: code/trunk/testdata/testoutput21
===================================================================
--- code/trunk/testdata/testoutput21    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput21    2019-02-06 18:11:36 UTC (rev 1066)
@@ -79,7 +79,7 @@
 Failed: error 183 at offset 4: using \C is disabled by the application


/ab\Cde/info
-Capturing subpattern count = 0
+Capture group count = 0
Contains \C
First code unit = 'a'
Last code unit = 'e'

Modified: code/trunk/testdata/testoutput22-16
===================================================================
--- code/trunk/testdata/testoutput22-16    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput22-16    2019-02-06 18:11:36 UTC (rev 1066)
@@ -4,7 +4,7 @@
 # in some widths and not in others.


/ab\Cde/utf,info
-Capturing subpattern count = 0
+Capture group count = 0
Contains \C
Options: utf
First code unit = 'a'

Modified: code/trunk/testdata/testoutput22-32
===================================================================
--- code/trunk/testdata/testoutput22-32    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput22-32    2019-02-06 18:11:36 UTC (rev 1066)
@@ -4,7 +4,7 @@
 # in some widths and not in others.


/ab\Cde/utf,info
-Capturing subpattern count = 0
+Capture group count = 0
Contains \C
Options: utf
First code unit = 'a'

Modified: code/trunk/testdata/testoutput22-8
===================================================================
--- code/trunk/testdata/testoutput22-8    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput22-8    2019-02-06 18:11:36 UTC (rev 1066)
@@ -4,7 +4,7 @@
 # in some widths and not in others.


/ab\Cde/utf,info
-Capturing subpattern count = 0
+Capture group count = 0
Contains \C
Options: utf
First code unit = 'a'

Modified: code/trunk/testdata/testoutput3
===================================================================
--- code/trunk/testdata/testoutput3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -78,13 +78,13 @@
  0: \xE9cole


/\w/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P
Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z
Subject length lower bound = 1

 /\w/I,locale=fr_FR
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
   Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
   \xAA \xB5 \xBA \xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 \xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF \xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF \xE0 \xE1 \xE2 
@@ -153,7 +153,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z 
   a b c d e f g h i j k l m n o p q r s t u v w x y z \xAA \xB5 \xBA \xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 
   \xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF \xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF \xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 \xE8 \xE9 \xEA \xEB \xEC \xED 


Modified: code/trunk/testdata/testoutput3A
===================================================================
--- code/trunk/testdata/testoutput3A    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput3A    2019-02-06 18:11:36 UTC (rev 1066)
@@ -78,13 +78,13 @@
  0: \xE9cole


/\w/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P
Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z
Subject length lower bound = 1

 /\w/I,locale=fr_FR
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
   Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
   \xAA \xB5 \xBA \xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 \xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF \xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF \xE0 \xE1 \xE2 
@@ -153,7 +153,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z 
   a b c d e f g h i j k l m n o p q r s t u v w x y z \xAA \xB5 \xBA \xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 
   \xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF \xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF \xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 \xE8 \xE9 \xEA \xEB \xEC \xED 


Modified: code/trunk/testdata/testoutput3B
===================================================================
--- code/trunk/testdata/testoutput3B    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput3B    2019-02-06 18:11:36 UTC (rev 1066)
@@ -78,13 +78,13 @@
  0: \xE9cole


/\w/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P
Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z
Subject length lower bound = 1

 /\w/I,locale=fr_FR
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
   Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
   \xAA \xB5 \xBA \xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 \xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF \xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF \xE0 \xE1 \xE2 
@@ -153,7 +153,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Starting code units: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z 
   a b c d e f g h i j k l m n o p q r s t u v w x y z \xAA \xB5 \xBA \xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 
   \xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF \xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF \xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 \xE8 \xE9 \xEA \xEB \xEC \xED 


Modified: code/trunk/testdata/testoutput4
===================================================================
--- code/trunk/testdata/testoutput4    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput4    2019-02-06 18:11:36 UTC (rev 1066)
@@ -3975,4 +3975,41 @@


# -------

+# Test group names containing non-ASCII letters and digits
+
+/(?'ABáC'...)\g{ABáC}/utf
+    abcabcdefg
+ 0: abcabc
+ 1: abc
+
+/(?'XʰABC'...)/utf
+    xyzpq
+ 0: xyz
+ 1: xyz
+
+/(?'XאABC'...)/utf
+    12345
+ 0: 123
+ 1: 123
+
+/(?'XᾈABC'...)/utf
+    %^&*(...
+ 0: %^&
+ 1: %^&
+
+/(?'𐨐ABC'...)/utf
+    abcde
+ 0: abc
+ 1: abc
+
+/^(?'אABC'...)(?&אABC)(?P=אABC)/utf
+    123123123456
+ 0: 123123123
+ 1: 123
+
+/^(?'אABC'...)(?&אABC)/utf
+    123123123456
+ 0: 123123
+ 1: 123
+
 # End of testinput4


Modified: code/trunk/testdata/testoutput5
===================================================================
--- code/trunk/testdata/testoutput5    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput5    2019-02-06 18:11:36 UTC (rev 1066)
@@ -147,7 +147,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -164,7 +164,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Last code unit = 'X'
 Subject length lower bound = 4
@@ -179,7 +179,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 3
     \x{212ab}\x{212ab}\x{212ab}\x{861}
@@ -193,7 +193,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: utf
 Overall options: anchored utf
 Starting code units: a b 
@@ -238,7 +238,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: utf
 Subject length lower bound = 0
@@ -251,7 +251,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'a'
 Subject length lower bound = 1
@@ -264,7 +264,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'a'
 Last code unit = 'b'
@@ -291,7 +291,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 First code unit = \xff
 Subject length lower bound = 1
     >\xff<
@@ -304,7 +304,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


 /[Ä-Ü]/utf
@@ -343,7 +343,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Options: utf
 Last code unit = 'z'
 Subject length lower bound = 7
@@ -363,7 +363,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
+Capture group count = 2
 May match empty string
 Options: utf
 Subject length lower bound = 0
@@ -394,7 +394,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
+Capture group count = 2
 May match empty string
 Options: utf
 Subject length lower bound = 0
@@ -414,7 +414,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
+Capture group count = 2
 May match empty string
 Options: utf
 Subject length lower bound = 0
@@ -445,7 +445,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 2
+Capture group count = 2
 May match empty string
 Options: utf
 Subject length lower bound = 0
@@ -471,7 +471,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Compile options: no_start_optimize utf
 Overall options: anchored no_start_optimize utf
 Subject length lower bound = 0
@@ -713,7 +713,7 @@
  0: \x{1ec5}


/a\Rb/I,bsr=anycrlf,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches CR, LF, or CRLF
First code unit = 'a'
@@ -732,7 +732,7 @@
No match

/a\Rb/I,bsr=unicode,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches any Unicode newline
First code unit = 'a'
@@ -750,7 +750,7 @@
0: a\x{0b}b

/a\R?b/I,bsr=anycrlf,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches CR, LF, or CRLF
First code unit = 'a'
@@ -769,7 +769,7 @@
No match

/a\R?b/I,bsr=unicode,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches any Unicode newline
First code unit = 'a'
@@ -1410,22 +1410,22 @@
2: \x{0d}

/[^\x{1234}]+/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Subject length lower bound = 1

/[^\x{1234}]+?/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Subject length lower bound = 1

/[^\x{1234}]++/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Subject length lower bound = 1

/[^\x{1234}]{2}/Ii,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless utf
Subject length lower bound = 2

@@ -1705,7 +1705,7 @@
------------------------------------------------------------------

 /(?<=\x{1234}\x{1234})\bxy/I,utf
-Capturing subpattern count = 0
+Capture group count = 0
 Max lookbehind = 2
 Options: utf
 First code unit = 'x'
@@ -1770,7 +1770,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


 /[\p{^L}]/IB
@@ -1780,7 +1780,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


 /[\P{L}]/IB
@@ -1790,7 +1790,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


 /[\P{^L}]/IB
@@ -1800,7 +1800,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Subject length lower bound = 1


 /[abc\p{L}\x{0660}]/IB,utf
@@ -1810,7 +1810,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 1


@@ -1821,7 +1821,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 1
     1234
@@ -1834,7 +1834,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 Subject length lower bound = 1
     1234
@@ -3000,7 +3000,7 @@
         Ket
         End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: caseless utf
 First code unit = 'A' (caseless)
 Last code unit = 'B' (caseless)
@@ -3916,7 +3916,7 @@
 ------------------------------------------------------------------


/^s?c/Iim,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: caseless multiline utf
First code unit at start or follows newline
Last code unit = 'c' (caseless)
@@ -4892,4 +4892,31 @@

# -------

+# Test reference and errors in non-ASCII characters in group names
+
+/(?'𑠅ABC'...)/I,utf
+Capture group count = 1
+Named capture groups:
+ 𑠅ABC 1
+Options: utf
+Subject length lower bound = 3
+ abcde\=copy=𑠅ABC
+ 0: abc
+ 1: abc
+ C abc (3) 𑠅ABC (group 1)
+
+# Bad ones
+
+/(?'AB၌C'...)\g{AB၌C}/utf
+Failed: error 142 at offset 5: syntax error in subpattern name (missing terminator?)
+
+/(?'٠ABC'...)/utf
+Failed: error 144 at offset 3: subpattern name must start with a non-digit
+
+/(?'²ABC'...)/utf
+Failed: error 162 at offset 3: subpattern name expected
+
+/(?'X²ABC'...)/utf
+Failed: error 142 at offset 4: syntax error in subpattern name (missing terminator?)
+
# End of testinput5

Modified: code/trunk/testdata/testoutput6
===================================================================
--- code/trunk/testdata/testoutput6    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput6    2019-02-06 18:11:36 UTC (rev 1066)
@@ -5978,7 +5978,7 @@
  0: Content-Type:xxxyyyz


/^abc/Im,newline=lf
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
Forced newline is LF
First code unit at start or follows newline
@@ -6001,7 +6001,7 @@
No match

/^abc/Im,newline=crlf
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
Forced newline is CRLF
First code unit at start or follows newline
@@ -6016,7 +6016,7 @@
No match

/^abc/Im,newline=cr
-Capturing subpattern count = 0
+Capture group count = 0
Options: multiline
Forced newline is CR
First code unit at start or follows newline
@@ -6031,7 +6031,7 @@
No match

/.*/I,newline=lf
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Forced newline is LF
First code unit at start or follows newline
@@ -6044,7 +6044,7 @@
0: abc\x0d

/.*/I,newline=cr
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Forced newline is CR
First code unit at start or follows newline
@@ -6057,7 +6057,7 @@
0: abc

/.*/I,newline=crlf
-Capturing subpattern count = 0
+Capture group count = 0
May match empty string
Forced newline is CRLF
First code unit at start or follows newline
@@ -6070,7 +6070,7 @@
0: abc

/\w+(.)(.)?def/Is
-Capturing subpattern count = 2
+Capture group count = 2
Options: dotall
Starting code units: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P
Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z
@@ -6447,7 +6447,7 @@
0: \x0aA

/a\Rb/I,bsr=anycrlf
-Capturing subpattern count = 0
+Capture group count = 0
\R matches CR, LF, or CRLF
First code unit = 'a'
Last code unit = 'b'
@@ -6465,7 +6465,7 @@
No match

/a\Rb/I,bsr=unicode
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
First code unit = 'a'
Last code unit = 'b'
@@ -6482,7 +6482,7 @@
0: a\x0bb

/a\R?b/I,bsr=anycrlf
-Capturing subpattern count = 0
+Capture group count = 0
\R matches CR, LF, or CRLF
First code unit = 'a'
Last code unit = 'b'
@@ -6500,7 +6500,7 @@
No match

/a\R?b/I,bsr=unicode
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
First code unit = 'a'
Last code unit = 'b'
@@ -6517,7 +6517,7 @@
0: a\x0bb

/a\R{2,4}b/I,bsr=anycrlf
-Capturing subpattern count = 0
+Capture group count = 0
\R matches CR, LF, or CRLF
First code unit = 'a'
Last code unit = 'b'
@@ -6535,7 +6535,7 @@
No match

/a\R{2,4}b/I,bsr=unicode
-Capturing subpattern count = 0
+Capture group count = 0
\R matches any Unicode newline
First code unit = 'a'
Last code unit = 'b'
@@ -6831,7 +6831,7 @@
0+ CBA

 /(abc|def|xyz)/I
-Capturing subpattern count = 1
+Capture group count = 1
 Starting code units: a d x 
 Subject length lower bound = 3
     terhjk;abcdaadsfe
@@ -6843,7 +6843,7 @@
 No match


 /(abc|def|xyz)/I,no_start_optimize
-Capturing subpattern count = 1
+Capture group count = 1
 Options: no_start_optimize
 Subject length lower bound = 0
     terhjk;abcdaadsfe


Modified: code/trunk/testdata/testoutput7
===================================================================
--- code/trunk/testdata/testoutput7    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput7    2019-02-06 18:11:36 UTC (rev 1066)
@@ -1030,7 +1030,7 @@
 No match


/a\Rb/I,bsr=anycrlf,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches CR, LF, or CRLF
First code unit = 'a'
@@ -1049,7 +1049,7 @@
No match

/a\Rb/I,bsr=unicode,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches any Unicode newline
First code unit = 'a'
@@ -1067,7 +1067,7 @@
0: a\x{0b}b

/a\R?b/I,bsr=anycrlf,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches CR, LF, or CRLF
First code unit = 'a'
@@ -1086,7 +1086,7 @@
No match

/a\R?b/I,bsr=unicode,utf
-Capturing subpattern count = 0
+Capture group count = 0
Options: utf
\R matches any Unicode newline
First code unit = 'a'

Modified: code/trunk/testdata/testoutput8-16-2
===================================================================
--- code/trunk/testdata/testoutput8-16-2    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput8-16-2    2019-02-06 18:11:36 UTC (rev 1066)
@@ -67,7 +67,7 @@
   2   2 Ket
   4     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -80,7 +80,7 @@
   4   4 Ket
   6     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -376,7 +376,7 @@
  10  10 Ket
  12     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -390,7 +390,7 @@
   8   8 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d55c}
 Last code unit = \x{c5b4}
@@ -404,7 +404,7 @@
   8   8 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{65e5}
 Last code unit = \x{8a9e}
@@ -904,7 +904,7 @@
  79  79 Ket
  81     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -938,7 +938,7 @@
  43  43 Ket
  45     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -1011,7 +1011,7 @@
 133 133 Ket
 135     End
 ------------------------------------------------------------------
-Capturing subpattern count = 10
+Capture group count = 10
 May match empty string
 Subject length lower bound = 0



Modified: code/trunk/testdata/testoutput8-16-3
===================================================================
--- code/trunk/testdata/testoutput8-16-3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput8-16-3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -67,7 +67,7 @@
   3   3 Ket
   6     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -80,7 +80,7 @@
   5   5 Ket
   8     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -376,7 +376,7 @@
  11  11 Ket
  14     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -390,7 +390,7 @@
   9   9 Ket
  12     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d55c}
 Last code unit = \x{c5b4}
@@ -404,7 +404,7 @@
   9   9 Ket
  12     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{65e5}
 Last code unit = \x{8a9e}
@@ -903,7 +903,7 @@
 110 110 Ket
 113     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -937,7 +937,7 @@
  58  58 Ket
  61     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -1010,7 +1010,7 @@
 194 194 Ket
 197     End
 ------------------------------------------------------------------
-Capturing subpattern count = 10
+Capture group count = 10
 May match empty string
 Subject length lower bound = 0



Modified: code/trunk/testdata/testoutput8-16-4
===================================================================
--- code/trunk/testdata/testoutput8-16-4    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput8-16-4    2019-02-06 18:11:36 UTC (rev 1066)
@@ -67,7 +67,7 @@
   3   3 Ket
   6     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -80,7 +80,7 @@
   5   5 Ket
   8     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -376,7 +376,7 @@
  11  11 Ket
  14     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -390,7 +390,7 @@
   9   9 Ket
  12     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d55c}
 Last code unit = \x{c5b4}
@@ -404,7 +404,7 @@
   9   9 Ket
  12     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{65e5}
 Last code unit = \x{8a9e}
@@ -903,7 +903,7 @@
 110 110 Ket
 113     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -937,7 +937,7 @@
  58  58 Ket
  61     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -1010,7 +1010,7 @@
 194 194 Ket
 197     End
 ------------------------------------------------------------------
-Capturing subpattern count = 10
+Capture group count = 10
 May match empty string
 Subject length lower bound = 0



Modified: code/trunk/testdata/testoutput8-32-2
===================================================================
--- code/trunk/testdata/testoutput8-32-2    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput8-32-2    2019-02-06 18:11:36 UTC (rev 1066)
@@ -67,7 +67,7 @@
   2   2 Ket
   4     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -80,7 +80,7 @@
   4   4 Ket
   6     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -376,7 +376,7 @@
  10  10 Ket
  12     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -390,7 +390,7 @@
   8   8 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d55c}
 Last code unit = \x{c5b4}
@@ -404,7 +404,7 @@
   8   8 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{65e5}
 Last code unit = \x{8a9e}
@@ -903,7 +903,7 @@
  79  79 Ket
  81     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -937,7 +937,7 @@
  43  43 Ket
  45     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -1010,7 +1010,7 @@
 133 133 Ket
 135     End
 ------------------------------------------------------------------
-Capturing subpattern count = 10
+Capture group count = 10
 May match empty string
 Subject length lower bound = 0



Modified: code/trunk/testdata/testoutput8-32-3
===================================================================
--- code/trunk/testdata/testoutput8-32-3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput8-32-3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -67,7 +67,7 @@
   2   2 Ket
   4     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -80,7 +80,7 @@
   4   4 Ket
   6     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -376,7 +376,7 @@
  10  10 Ket
  12     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -390,7 +390,7 @@
   8   8 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d55c}
 Last code unit = \x{c5b4}
@@ -404,7 +404,7 @@
   8   8 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{65e5}
 Last code unit = \x{8a9e}
@@ -903,7 +903,7 @@
  79  79 Ket
  81     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -937,7 +937,7 @@
  43  43 Ket
  45     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -1010,7 +1010,7 @@
 133 133 Ket
 135     End
 ------------------------------------------------------------------
-Capturing subpattern count = 10
+Capture group count = 10
 May match empty string
 Subject length lower bound = 0



Modified: code/trunk/testdata/testoutput8-32-4
===================================================================
--- code/trunk/testdata/testoutput8-32-4    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput8-32-4    2019-02-06 18:11:36 UTC (rev 1066)
@@ -67,7 +67,7 @@
   2   2 Ket
   4     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -80,7 +80,7 @@
   4   4 Ket
   6     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -376,7 +376,7 @@
  10  10 Ket
  12     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -390,7 +390,7 @@
   8   8 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{d55c}
 Last code unit = \x{c5b4}
@@ -404,7 +404,7 @@
   8   8 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \x{65e5}
 Last code unit = \x{8a9e}
@@ -903,7 +903,7 @@
  79  79 Ket
  81     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -937,7 +937,7 @@
  43  43 Ket
  45     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -1010,7 +1010,7 @@
 133 133 Ket
 135     End
 ------------------------------------------------------------------
-Capturing subpattern count = 10
+Capture group count = 10
 May match empty string
 Subject length lower bound = 0



Modified: code/trunk/testdata/testoutput8-8-2
===================================================================
--- code/trunk/testdata/testoutput8-8-2    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput8-8-2    2019-02-06 18:11:36 UTC (rev 1066)
@@ -67,7 +67,7 @@
   3   3 Ket
   6     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -80,7 +80,7 @@
   5   5 Ket
   8     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -376,7 +376,7 @@
  14  14 Ket
  17     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -390,7 +390,7 @@
  15  15 Ket
  18     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xed
 Last code unit = \xb4
@@ -404,7 +404,7 @@
  15  15 Ket
  18     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xe6
 Last code unit = \x9e
@@ -904,7 +904,7 @@
 119 119 Ket
 122     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -938,7 +938,7 @@
  61  61 Ket
  64     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -1011,7 +1011,7 @@
 205 205 Ket
 208     End
 ------------------------------------------------------------------
-Capturing subpattern count = 10
+Capture group count = 10
 May match empty string
 Subject length lower bound = 0



Modified: code/trunk/testdata/testoutput8-8-3
===================================================================
--- code/trunk/testdata/testoutput8-8-3    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput8-8-3    2019-02-06 18:11:36 UTC (rev 1066)
@@ -67,7 +67,7 @@
   4   4 Ket
   8     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -80,7 +80,7 @@
   6   6 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -376,7 +376,7 @@
  15  15 Ket
  19     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -390,7 +390,7 @@
  16  16 Ket
  20     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xed
 Last code unit = \xb4
@@ -404,7 +404,7 @@
  16  16 Ket
  20     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xe6
 Last code unit = \x9e
@@ -903,7 +903,7 @@
 150 150 Ket
 154     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -937,7 +937,7 @@
  76  76 Ket
  80     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -1010,7 +1010,7 @@
 266 266 Ket
 270     End
 ------------------------------------------------------------------
-Capturing subpattern count = 10
+Capture group count = 10
 May match empty string
 Subject length lower bound = 0



Modified: code/trunk/testdata/testoutput8-8-4
===================================================================
--- code/trunk/testdata/testoutput8-8-4    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput8-8-4    2019-02-06 18:11:36 UTC (rev 1066)
@@ -67,7 +67,7 @@
   5   5 Ket
  10     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 May match empty string
 Options: extended
 Subject length lower bound = 0
@@ -80,7 +80,7 @@
   7   7 Ket
  12     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: extended
 First code unit = 'a'
 Subject length lower bound = 1
@@ -376,7 +376,7 @@
  16  16 Ket
  21     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = 'A'
 Last code unit = '.'
@@ -390,7 +390,7 @@
  17  17 Ket
  22     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xed
 Last code unit = \xb4
@@ -404,7 +404,7 @@
  17  17 Ket
  22     End
 ------------------------------------------------------------------
-Capturing subpattern count = 0
+Capture group count = 0
 Options: utf
 First code unit = \xe6
 Last code unit = \x9e
@@ -903,7 +903,7 @@
 181 181 Ket
 186     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -937,7 +937,7 @@
  91  91 Ket
  96     End
 ------------------------------------------------------------------
-Capturing subpattern count = 1
+Capture group count = 1
 Max back reference = 1
 May match empty string
 Subject length lower bound = 0
@@ -1010,7 +1010,7 @@
 327 327 Ket
 332     End
 ------------------------------------------------------------------
-Capturing subpattern count = 10
+Capture group count = 10
 May match empty string
 Subject length lower bound = 0



Modified: code/trunk/testdata/testoutput9
===================================================================
--- code/trunk/testdata/testoutput9    2019-02-03 14:49:39 UTC (rev 1065)
+++ code/trunk/testdata/testoutput9    2019-02-06 18:11:36 UTC (rev 1066)
@@ -215,7 +215,7 @@
 (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
 \)  )*                       # optional trailing comment
 /Ix
-Capturing subpattern count = 0
+Capture group count = 0
 Contains explicit CR or LF match
 Options: extended
 Starting code units: \x09 \x20 ! " # $ % & ' ( * + - / 0 1 2 3 4 5 6 7 8 
@@ -224,25 +224,25 @@
 Subject length lower bound = 3


/\h/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: \x09 \x20 \xa0
Subject length lower bound = 1

/\H/I
-Capturing subpattern count = 0
+Capture group count = 0
Subject length lower bound = 1

/\v/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: \x0a \x0b \x0c \x0d \x85
Subject length lower bound = 1

/\V/I
-Capturing subpattern count = 0
+Capture group count = 0
Subject length lower bound = 1

/\R/I
-Capturing subpattern count = 0
+Capture group count = 0
Starting code units: \x0a \x0b \x0c \x0d \x85
Subject length lower bound = 1