Revision: 734
http://www.exim.org/viewvc/pcre2?view=rev&revision=734
Author: ph10
Date: 2017-04-06 19:02:40 +0100 (Thu, 06 Apr 2017)
Log Message:
-----------
Jason Hood's pcre2grep patches (modified a bit) to add --output to pcre2grep,
and also an inbuilt callout echo.
Modified Paths:
--------------
code/trunk/ChangeLog
code/trunk/RunGrepTest
code/trunk/RunGrepTest.bat
code/trunk/doc/html/pcre2_compile.html
code/trunk/doc/html/pcre2_dfa_match.html
code/trunk/doc/html/pcre2_match.html
code/trunk/doc/html/pcre2_substitute.html
code/trunk/doc/html/pcre2api.html
code/trunk/doc/html/pcre2grep.html
code/trunk/doc/html/pcre2test.html
code/trunk/doc/pcre2.txt
code/trunk/doc/pcre2grep.1
code/trunk/doc/pcre2grep.txt
code/trunk/doc/pcre2test.txt
code/trunk/src/pcre2grep.c
code/trunk/testdata/grepoutput
code/trunk/testdata/grepoutputC
Modified: code/trunk/ChangeLog
===================================================================
--- code/trunk/ChangeLog 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/ChangeLog 2017-04-06 18:02:40 UTC (rev 734)
@@ -113,7 +113,10 @@
19. Implemented PCRE2_ENDANCHORED.
+20. Applied Jason Hood's patches (slightly modified) to pcre2grep, to implement
+the --output=text (-O) option and the inbuilt callout echo.
+
Version 10.23 14-February-2017
------------------------------
Modified: code/trunk/RunGrepTest
===================================================================
--- code/trunk/RunGrepTest 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/RunGrepTest 2017-04-06 18:02:40 UTC (rev 734)
@@ -598,6 +598,10 @@
$valgrind $vjs $pcre2grep -Mo '(\n|[^-])*---' testNinputgrep >>testtrygrep
echo "RC=$?" >>testtrygrep
+echo "---------------------------- Test 120 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -HO '$0:$2$1$3' '(\w+) binary (\w+)(\.)?' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
# Now compare the results.
$cf $srcdir/testdata/grepoutput testtrygrep
@@ -667,6 +671,9 @@
echo "Testing pcre2grep script callouts"
$valgrind $vjs $pcre2grep '(T)(..(.))(?C"/bin/echo|Arg1: [$1] [$2] [$3]|Arg2: $|${1}$| ($4) ($14) ($0)")()' $srcdir/testdata/grepinputv >testtrygrep
$valgrind $vjs $pcre2grep '(T)(..(.))()()()()()()()(..)(?C"/bin/echo|Arg1: [$11] [${11}]")' $srcdir/testdata/grepinputv >>testtrygrep
+ $valgrind $vjs $pcre2grep '(T)(?C"|$0:$1$n")' $srcdir/testdata/grepinputv >>testtrygrep
+ $valgrind $vjs $pcre2grep '(T)(?C"|$1$n")(*F)' $srcdir/testdata/grepinputv >>testtrygrep
+ # The above has no newline, which 'diff -ub' ignores, so add one.
$cf $srcdir/testdata/grepoutputC testtrygrep
if [ $? != 0 ] ; then exit 1; fi
else
Modified: code/trunk/RunGrepTest.bat
===================================================================
--- code/trunk/RunGrepTest.bat 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/RunGrepTest.bat 2017-04-06 18:02:40 UTC (rev 734)
@@ -585,6 +585,10 @@
%pcre2grep% -Mo "(\n|[^-])*---" testNinputgrep >>testtrygrep
echo RC=^%ERRORLEVEL%>>testtrygrep
+echo ---------------------------- Test 120 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -HO "$0:$2$1$3" "(\w+) binary (\w+)(\.)?" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
:: Now compare the results.
%cf% %srcdir%\testdata\grepoutput testtrygrep %cfout%
@@ -654,6 +658,10 @@
echo Testing pcre2grep script callouts
%pcre2grep% "(T)(..(.))(?C'cmd|/c echo|Arg1: [$1] [$2] [$3]|Arg2: ^$|${1}^$| ($4) ($14) ($0)')()" %srcdir%/testdata/grepinputv >testtrygrep
%pcre2grep% "(T)(..(.))()()()()()()()(..)(?C'cmd|/c echo|Arg1: [$11] [${11}]')" %srcdir%/testdata/grepinputv >>testtrygrep
+ %pcre2grep% "(T)(?C'|$0:$1')" %srcdir%/testdata/grepinputv >>testtrygrep
+ %pcre2grep% --om-separator / "(T)(?C'|$1')" %srcdir%/testdata/grepinputv >>testtrygrep
+ :: The above has no newline, which 'diff -ub' ignores, so add one.
+ echo />>testtrygrep
%cf% %srcdir%\testdata\grepoutputC testtrygrep %cfout%
if ERRORLEVEL 1 exit /b 1
) else (
Modified: code/trunk/doc/html/pcre2_compile.html
===================================================================
--- code/trunk/doc/html/pcre2_compile.html 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/html/pcre2_compile.html 2017-04-06 18:02:40 UTC (rev 734)
@@ -60,6 +60,7 @@
PCRE2_DOLLAR_ENDONLY $ not to match newline at end
PCRE2_DOTALL . matches anything including NL
PCRE2_DUPNAMES Allow duplicate names for subpatterns
+ PCRE2_ENDANCHORED Pattern can match only at end of subject
PCRE2_EXTENDED Ignore white space and # comments
PCRE2_FIRSTLINE Force matching to be before newline
PCRE2_MATCH_UNSET_BACKREF Match unset back references
Modified: code/trunk/doc/html/pcre2_dfa_match.html
===================================================================
--- code/trunk/doc/html/pcre2_dfa_match.html 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/html/pcre2_dfa_match.html 2017-04-06 18:02:40 UTC (rev 734)
@@ -50,6 +50,7 @@
and <i>startoffset</i> values are code units, not characters. The options are:
<pre>
PCRE2_ANCHORED Match only at the first position
+ PCRE2_ENDANCHORED Pattern can match only at end of subject
PCRE2_NOTBOL Subject is not the beginning of a line
PCRE2_NOTEOL Subject is not the end of a line
PCRE2_NOTEMPTY An empty string is not a valid match
Modified: code/trunk/doc/html/pcre2_match.html
===================================================================
--- code/trunk/doc/html/pcre2_match.html 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/html/pcre2_match.html 2017-04-06 18:02:40 UTC (rev 734)
@@ -53,6 +53,7 @@
subject that is terminated by a binary zero code unit. The options are:
<pre>
PCRE2_ANCHORED Match only at the first position
+ PCRE2_ENDANCHORED Pattern can match only at end of subject
PCRE2_NOTBOL Subject string is not the beginning of a line
PCRE2_NOTEOL Subject string is not the end of a line
PCRE2_NOTEMPTY An empty string is not a valid match
Modified: code/trunk/doc/html/pcre2_substitute.html
===================================================================
--- code/trunk/doc/html/pcre2_substitute.html 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/html/pcre2_substitute.html 2017-04-06 18:02:40 UTC (rev 734)
@@ -64,6 +64,7 @@
zero-terminated strings. The options are:
<pre>
PCRE2_ANCHORED Match only at the first position
+ PCRE2_ENDANCHORED Pattern can match only at end of subject
PCRE2_NOTBOL Subject is not the beginning of a line
PCRE2_NOTEOL Subject is not the end of a line
PCRE2_NOTEMPTY An empty string is not a valid match
Modified: code/trunk/doc/html/pcre2api.html
===================================================================
--- code/trunk/doc/html/pcre2api.html 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/html/pcre2api.html 2017-04-06 18:02:40 UTC (rev 734)
@@ -1123,8 +1123,8 @@
<P>
For those options that can be different in different parts of the pattern, the
contents of the <i>options</i> argument specifies their settings at the start of
-compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK options can be set at
-the time of matching as well as at compile time.
+compilation. The PCRE2_ANCHORED, PCRE2_ENDANCHORED, and PCRE2_NO_UTF_CHECK
+options can be set at the time of matching as well as at compile time.
</P>
<P>
Other, less frequently required compile-time parameters (for example, the
@@ -1280,6 +1280,13 @@
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
documentation.
<pre>
+ PCRE2_ENDANCHORED
+</pre>
+If this bit is set, the end of any pattern match must be right at the end of
+the string being searched (the "subject string"). This effect can also be
+achieved by appropriate constructs in the pattern itself, which is the only way
+to do it in Perl.
+<pre>
PCRE2_EXTENDED
</pre>
If this bit is set, most white space characters in the pattern are totally
@@ -2141,16 +2148,16 @@
</b><br>
<P>
The unused bits of the <i>options</i> argument for <b>pcre2_match()</b> must be
-zero. The only bits that may be set are PCRE2_ANCHORED, 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.
+zero. The only bits that may be set are PCRE2_ANCHORED, 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.
</P>
<P>
-Setting PCRE2_ANCHORED at match time is not supported by the just-in-time (JIT)
-compiler. If it is set, JIT matching is disabled and the interpretive code in
-<b>pcre2_match()</b> is run. Apart from PCRE2_NO_JIT (obviously), the remaining
-options are supported for JIT matching.
+Setting PCRE2_ANCHORED or PCRE2_ENDANCHORED at match time is not supported by
+the just-in-time (JIT) compiler. If it is set, JIT matching is disabled and the
+interpretive code in <b>pcre2_match()</b> is run. Apart from PCRE2_NO_JIT
+(obviously), the remaining options are supported for JIT matching.
<pre>
PCRE2_ANCHORED
</pre>
@@ -2160,6 +2167,12 @@
matching time. Note that setting the option at match time disables JIT
matching.
<pre>
+ PCRE2_ENDANCHORED
+</pre>
+If the PCRE2_ENDANCHORED option is set, any string that <b>pcre2_match()</b>
+matches must be right at the end of the subject string. Note that setting the
+option at match time disables JIT matching.
+<pre>
PCRE2_NOTBOL
</pre>
This option specifies that first character of the subject string is not the
@@ -3100,11 +3113,11 @@
</b><br>
<P>
The unused bits of the <i>options</i> argument for <b>pcre2_dfa_match()</b> must
-be zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL,
-PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK,
-PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, PCRE2_DFA_SHORTEST, and
-PCRE2_DFA_RESTART. All but the last four of these are exactly the same as for
-<b>pcre2_match()</b>, so their description is not repeated here.
+be zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_ENDANCHORED,
+PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART,
+PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, PCRE2_DFA_SHORTEST,
+and PCRE2_DFA_RESTART. All but the last four of these are exactly the same as
+for <b>pcre2_match()</b>, so their description is not repeated here.
<pre>
PCRE2_PARTIAL_HARD
PCRE2_PARTIAL_SOFT
@@ -3258,7 +3271,7 @@
</P>
<br><a name="SEC42" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 01 April 2017
+Last updated: 04 April 2017
<br>
Copyright © 1997-2017 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2grep.html
===================================================================
--- code/trunk/doc/html/pcre2grep.html 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/html/pcre2grep.html 2017-04-06 18:02:40 UTC (rev 734)
@@ -22,7 +22,7 @@
<li><a name="TOC7" href="#SEC7">NEWLINES</a>
<li><a name="TOC8" href="#SEC8">OPTIONS COMPATIBILITY</a>
<li><a name="TOC9" href="#SEC9">OPTIONS WITH DATA</a>
-<li><a name="TOC10" href="#SEC10">CALLING EXTERNAL SCRIPTS</a>
+<li><a name="TOC10" href="#SEC10">USING PCRE2'S CALLOUT FACILITY</a>
<li><a name="TOC11" href="#SEC11">MATCHING ERRORS</a>
<li><a name="TOC12" href="#SEC12">DIAGNOSTICS</a>
<li><a name="TOC13" href="#SEC13">SEE ALSO</a>
@@ -384,8 +384,8 @@
offset from the start of the file and a length, separated by a comma. In this
mode, no context is shown. That is, the <b>-A</b>, <b>-B</b>, and <b>-C</b>
options are ignored. If there is more than one match in a line, each of them is
-shown separately. This option is mutually exclusive with <b>--line-offsets</b>
-and <b>--only-matching</b>.
+shown separately. This option is mutually exclusive with <b>--output</b>,
+<b>--line-offsets</b>, and <b>--only-matching</b>.
</P>
<P>
<b>-H</b>, <b>--with-filename</b>
@@ -491,7 +491,8 @@
offset and length are separated by a comma. In this mode, no context is shown.
That is, the <b>-A</b>, <b>-B</b>, and <b>-C</b> options are ignored. If there is
more than one match in a line, each of them is shown separately. This option is
-mutually exclusive with <b>--file-offsets</b> and <b>--only-matching</b>.
+mutually exclusive with <b>--output</b>, <b>--file-offsets</b>, and
+<b>--only-matching</b>.
</P>
<P>
<b>--locale</b>=<i>locale-name</i>
@@ -602,6 +603,36 @@
It should never be needed in normal use.
</P>
<P>
+<b>-O</b> <i>text</i>, <b>--output</b>=<i>text</i>
+When there is a match, instead of outputting the whole line that matched,
+output just the given text. This option is mutually exclusive with
+<b>--only-matching</b>, <b>--file-offsets</b>, and <b>--line-offsets</b>. Escape
+sequences starting with a dollar character may be used to insert the contents
+of the matched part of the line and/or captured substrings into the text.
+<br>
+<br>
+$<digits> or ${<digits>} is replaced by the captured
+substring of the given decimal number; zero substitutes the whole match. If
+the number is greater than the number of capturing substrings, or if the
+capture is unset, the replacement is empty.
+<br>
+<br>
+$a is replaced by bell; $b by backspace; $e by escape; $f by form feed; $n by
+newline; $r by carriage return; $t by tab; $v by vertical tab.
+<br>
+<br>
+$o<digits> is replaced by the character represented by the given octal
+number; up to three digits are processed.
+<br>
+<br>
+$x<digits> is replaced by the character represented by the given hexadecimal
+number; up to two digits are processed.
+<br>
+<br>
+Any other character is substituted by itself. In particular, $$ is replaced by
+a single dollar.
+</P>
+<P>
<b>-o</b>, <b>--only-matching</b>
Show only the part of the line that matched a pattern instead of the whole
line. In this mode, no context is shown. That is, the <b>-A</b>, <b>-B</b>, and
@@ -611,7 +642,7 @@
lines), no output is generated, but the return code is set appropriately. If
the matched portion of the line is empty, nothing is output unless the file
name or line number are being printed, in which case they are shown on an
-otherwise empty line. This option is mutually exclusive with
+otherwise empty line. This option is mutually exclusive with <b>--output</b>,
<b>--file-offsets</b> and <b>--line-offsets</b>.
</P>
<P>
@@ -621,7 +652,7 @@
equivalent to <b>-o</b> without a number. Because these options can be given
without an argument (see above), if an argument is present, it must be given in
the same shell item, for example, -o3 or --only-matching=2. The comments given
-for the non-argument case above also apply to this case. If the specified
+for the non-argument case above also apply to this option. If the specified
capturing parentheses do not exist in the pattern, or were not set in the
match, nothing is output unless the file name or line number are being output.
<br>
@@ -735,9 +766,9 @@
(PCRE2 terminology). However, the <b>--depth-limit</b>, <b>--file-list</b>,
<b>--file-offsets</b>, <b>--include-dir</b>, <b>--line-offsets</b>,
<b>--locale</b>, <b>--match-limit</b>, <b>-M</b>, <b>--multiline</b>, <b>-N</b>,
-<b>--newline</b>, <b>--om-separator</b>, <b>-u</b>, and <b>--utf-8</b> options are
-specific to <b>pcre2grep</b>, as is the use of the <b>--only-matching</b> option
-with a capturing parentheses number.
+<b>--newline</b>, <b>--om-separator</b>, <b>--output</b>, <b>-u</b>, and
+<b>--utf-8</b> options are specific to <b>pcre2grep</b>, as is the use of the
+<b>--only-matching</b> option with a capturing parentheses number.
</P>
<P>
Although most of the common options work the same way, a few are different in
@@ -778,23 +809,30 @@
options does have data, it must be given in the first form, using an equals
character. Otherwise <b>pcre2grep</b> will assume that it has no data.
</P>
-<br><a name="SEC10" href="#TOC1">CALLING EXTERNAL SCRIPTS</a><br>
+<br><a name="SEC10" href="#TOC1">USING PCRE2'S CALLOUT FACILITY</a><br>
<P>
<b>pcre2grep</b> has, by default, support for calling external programs or
-scripts during matching by making use of PCRE2's callout facility. However,
-this support can be disabled when <b>pcre2grep</b> is built. You can find out
-whether your binary has support for callouts by running it with the <b>--help</b>
-option. If the support is not enabled, all callouts in patterns are ignored by
-<b>pcre2grep</b>.
+scripts or echoing specific strings during matching by making use of PCRE2's
+callout facility. However, this support can be disabled when <b>pcre2grep</b> is
+built. You can find out whether your binary has support for callouts by running
+it with the <b>--help</b> option. If the support is not enabled, all callouts in
+patterns are ignored by <b>pcre2grep</b>.
</P>
<P>
A callout in a PCRE2 pattern is of the form (?C<arg>) where the argument is
either a number or a quoted string (see the
<a href="pcre2callout.html"><b>pcre2callout</b></a>
-documentation for details). Numbered callouts are ignored by <b>pcre2grep</b>.
-String arguments are parsed as a list of substrings separated by pipe (vertical
-bar) characters. The first substring must be an executable name, with the
-following substrings specifying arguments:
+documentation for details). Numbered callouts are ignored by <b>pcre2grep</b>;
+only callouts with string arguments are useful.
+</P>
+<br><b>
+Calling external programs or scripts
+</b><br>
+<P>
+If the callout string does not start with a pipe (vertical bar) character, it
+is parsed into a list of substrings separated by pipe characters. The first
+substring must be an executable name, with the following substrings specifying
+arguments:
<pre>
executable_name|arg1|arg2|...
</pre>
@@ -828,6 +866,19 @@
the non-existence of the executable), a local matching failure occurs and the
matcher backtracks in the normal way.
</P>
+<br><b>
+Echoing a specific string
+</b><br>
+<P>
+If the callout string starts with a pipe (vertical bar) character, the rest of
+the string is written to the output, having been passed through the same escape
+processing as text from the --output option. This provides a simple echoing
+facility that avoids calling an external program or script. No terminator is
+added to the string, so if you want a newline, you must include it explicitly.
+Matching continues normally after the string is output. If you want to see only
+the callout output but not any output from an actual match, you should end the
+relevant pattern with (*FAIL).
+</P>
<br><a name="SEC11" href="#TOC1">MATCHING ERRORS</a><br>
<P>
It is possible to supply a regular expression that takes a very long time to
@@ -867,7 +918,7 @@
</P>
<br><a name="SEC15" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 31 March 2017
+Last updated: 06 April 2017
<br>
Copyright © 1997-2017 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2test.html
===================================================================
--- code/trunk/doc/html/pcre2test.html 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/html/pcre2test.html 2017-04-06 18:02:40 UTC (rev 734)
@@ -568,6 +568,7 @@
dollar_endonly set PCRE2_DOLLAR_ENDONLY
/s dotall set PCRE2_DOTALL
dupnames set PCRE2_DUPNAMES
+ endanchored set PCRE2_ENDANCHORED
/x extended set PCRE2_EXTENDED
firstline set PCRE2_FIRSTLINE
match_unset_backref set PCRE2_MATCH_UNSET_BACKREF
@@ -1039,6 +1040,7 @@
for a description of their effects.
<pre>
anchored set PCRE2_ANCHORED
+ endanchored set PCRE2_ENDANCHORED
dfa_restart set PCRE2_DFA_RESTART
dfa_shortest set PCRE2_DFA_SHORTEST
no_jit set PCRE2_NO_JIT
@@ -1798,7 +1800,7 @@
</P>
<br><a name="SEC21" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 25 March 2017
+Last updated: 04 April 2017
<br>
Copyright © 1997-2017 University of Cambridge.
<br>
Modified: code/trunk/doc/pcre2.txt
===================================================================
--- code/trunk/doc/pcre2.txt 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/pcre2.txt 2017-04-06 18:02:40 UTC (rev 734)
@@ -1155,39 +1155,40 @@
For those options that can be different in different parts of the pat-
tern, the contents of the options argument specifies their settings at
- the start of compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK
- options can be set at the time of matching as well as at compile time.
+ the start of compilation. The PCRE2_ANCHORED, PCRE2_ENDANCHORED, and
+ PCRE2_NO_UTF_CHECK options can be set at the time of matching as well
+ as at compile time.
- Other, less frequently required compile-time parameters (for example,
+ Other, less frequently required compile-time parameters (for example,
the newline setting) can be provided in a compile context (as described
above).
If errorcode or erroroffset is NULL, pcre2_compile() returns NULL imme-
- diately. Otherwise, the variables to which these point are set to an
- error code and an offset (number of code units) within the pattern,
- respectively, when pcre2_compile() returns NULL because a compilation
+ diately. Otherwise, the variables to which these point are set to an
+ error code and an offset (number of code units) within the pattern,
+ respectively, when pcre2_compile() returns NULL because a compilation
error has occurred. The values are not defined when compilation is suc-
cessful and pcre2_compile() returns a non-NULL value.
The value returned in erroroffset is an indication of where in the pat-
- tern the error occurred. It is not necessarily the furthest point in
- the pattern that was read. For example, after the error "lookbehind
+ tern the error occurred. It is not necessarily the furthest point in
+ the pattern that was read. For example, after the error "lookbehind
assertion is not fixed length", the error offset points to the start of
the failing assertion.
- The pcre2_get_error_message() function (see "Obtaining a textual error
- message" below) provides a textual message for each error code. Compi-
+ The pcre2_get_error_message() function (see "Obtaining a textual error
+ message" below) provides a textual message for each error code. Compi-
lation errors have positive error codes; UTF formatting error codes are
- negative. For an invalid UTF-8 or UTF-16 string, the offset is that of
+ negative. For an invalid UTF-8 or UTF-16 string, the offset is that of
the first code unit of the failing character.
- Some errors are not detected until the whole pattern has been scanned;
- in these cases, the offset passed back is the length of the pattern.
- Note that the offset is in code units, not characters, even in a UTF
+ Some errors are not detected until the whole pattern has been scanned;
+ in these cases, the offset passed back is the length of the pattern.
+ Note that the offset is in code units, not characters, even in a UTF
mode. It may sometimes point into the middle of a UTF-8 or UTF-16 char-
acter.
- This code fragment shows a typical straightforward call to pcre2_com-
+ This code fragment shows a typical straightforward call to pcre2_com-
pile():
pcre2_code *re;
@@ -1201,28 +1202,28 @@
&erroffset, /* for error offset */
NULL); /* no compile context */
- The following names for option bits are defined in the pcre2.h header
+ The following names for option bits are defined in the pcre2.h header
file:
PCRE2_ANCHORED
If this bit is set, the pattern is forced to be "anchored", that is, it
- is constrained to match only at the first matching point in the string
- that is being searched (the "subject string"). This effect can also be
- achieved by appropriate constructs in the pattern itself, which is the
+ is constrained to match only at the first matching point in the string
+ that is being searched (the "subject string"). This effect can also be
+ achieved by appropriate constructs in the pattern itself, which is the
only way to do it in Perl.
PCRE2_ALLOW_EMPTY_CLASS
- By default, for compatibility with Perl, a closing square bracket that
- immediately follows an opening one is treated as a data character for
- the class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the
+ By default, for compatibility with Perl, a closing square bracket that
+ immediately follows an opening one is treated as a data character for
+ the class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the
class, which therefore contains no characters and so can never match.
PCRE2_ALT_BSUX
- This option request alternative handling of three escape sequences,
- which makes PCRE2's behaviour more like ECMAscript (aka JavaScript).
+ This option request alternative handling of three escape sequences,
+ which makes PCRE2's behaviour more like ECMAscript (aka JavaScript).
When it is set:
(1) \U matches an upper case "U" character; by default \U causes a com-
@@ -1229,13 +1230,13 @@
pile time error (Perl uses \U to upper case subsequent characters).
(2) \u matches a lower case "u" character unless it is followed by four
- hexadecimal digits, in which case the hexadecimal number defines the
- code point to match. By default, \u causes a compile time error (Perl
+ hexadecimal digits, in which case the hexadecimal number defines the
+ code point to match. By default, \u causes a compile time error (Perl
uses it to upper case the following character).
- (3) \x matches a lower case "x" character unless it is followed by two
- hexadecimal digits, in which case the hexadecimal number defines the
- code point to match. By default, as in Perl, a hexadecimal number is
+ (3) \x matches a lower case "x" character unless it is followed by two
+ hexadecimal digits, in which case the hexadecimal number defines the
+ code point to match. By default, as in Perl, a hexadecimal number is
always expected after \x, but it may have zero, one, or two digits (so,
for example, \xz matches a binary zero character followed by z).
@@ -1242,55 +1243,55 @@
PCRE2_ALT_CIRCUMFLEX
In multiline mode (when PCRE2_MULTILINE is set), the circumflex
- metacharacter matches at the start of the subject (unless PCRE2_NOTBOL
- is set), and also after any internal newline. However, it does not
+ metacharacter matches at the start of the subject (unless PCRE2_NOTBOL
+ is set), and also after any internal newline. However, it does not
match after a newline at the end of the subject, for compatibility with
- Perl. If you want a multiline circumflex also to match after a termi-
+ Perl. If you want a multiline circumflex also to match after a termi-
nating newline, you must set PCRE2_ALT_CIRCUMFLEX.
PCRE2_ALT_VERBNAMES
- By default, for compatibility with Perl, the name in any verb sequence
- such as (*MARK:NAME) is any sequence of characters that does not
- include a closing parenthesis. The name is not processed in any way,
- and it is not possible to include a closing parenthesis in the name.
- However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash
- processing is applied to verb names and only an unescaped closing
- parenthesis terminates the name. A closing parenthesis can be included
- in a name either as \) or between \Q and \E. If the PCRE2_EXTENDED
+ By default, for compatibility with Perl, the name in any verb sequence
+ such as (*MARK:NAME) is any sequence of characters that does not
+ include a closing parenthesis. The name is not processed in any way,
+ and it is not possible to include a closing parenthesis in the name.
+ However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash
+ processing is applied to verb names and only an unescaped closing
+ parenthesis terminates the name. A closing parenthesis can be included
+ in a name either as \) or between \Q and \E. If the PCRE2_EXTENDED
option is set, unescaped whitespace in verb names is skipped and #-com-
- ments are recognized in this mode, exactly as in the rest of the pat-
+ ments are recognized in this mode, exactly as in the rest of the pat-
tern.
PCRE2_AUTO_CALLOUT
- If this bit is set, pcre2_compile() automatically inserts callout
- items, all with number 255, before each pattern item, except immedi-
- ately before or after an explicit callout in the pattern. For discus-
+ If this bit is set, pcre2_compile() automatically inserts callout
+ items, all with number 255, before each pattern item, except immedi-
+ ately before or after an explicit callout in the pattern. For discus-
sion of the callout facility, see the pcre2callout documentation.
PCRE2_CASELESS
- If this bit is set, letters in the pattern match both upper and lower
- case letters in the subject. It is equivalent to Perl's /i option, and
+ If this bit is set, letters in the pattern match both upper and lower
+ case letters in the subject. It is equivalent to Perl's /i option, and
it can be changed within a pattern by a (?i) option setting.
PCRE2_DOLLAR_ENDONLY
- If this bit is set, a dollar metacharacter in the pattern matches only
- at the end of the subject string. Without this option, a dollar also
- matches immediately before a newline at the end of the string (but not
- before any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored
- if PCRE2_MULTILINE is set. There is no equivalent to this option in
+ If this bit is set, a dollar metacharacter in the pattern matches only
+ at the end of the subject string. Without this option, a dollar also
+ matches immediately before a newline at the end of the string (but not
+ before any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored
+ if PCRE2_MULTILINE is set. There is no equivalent to this option in
Perl, and no way to set it within a pattern.
PCRE2_DOTALL
- If this bit is set, a dot metacharacter in the pattern matches any
- character, including one that indicates a newline. However, it only
+ If this bit is set, a dot metacharacter in the pattern matches any
+ character, including one that indicates a newline. However, it only
ever matches one character, even if newlines are coded as CRLF. Without
this option, a dot does not match when the current position in the sub-
- ject is at a newline. This option is equivalent to Perl's /s option,
+ ject is at a newline. This option is equivalent to Perl's /s option,
and it can be changed within a pattern by a (?s) option setting. A neg-
ative class such as [^a] always matches newline characters, independent
of the setting of this option.
@@ -1297,12 +1298,19 @@
PCRE2_DUPNAMES
- If this bit is set, names used to identify capturing subpatterns need
+ 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
+ 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.
+ PCRE2_ENDANCHORED
+
+ If this bit is set, the end of any pattern match must be right at the
+ end of the string being searched (the "subject string"). This effect
+ can also be achieved by appropriate constructs in the pattern itself,
+ which is the only way to do it in Perl.
+
PCRE2_EXTENDED
If this bit is set, most white space characters in the pattern are
@@ -2136,29 +2144,36 @@
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_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.
+ The only bits that may be set are PCRE2_ANCHORED, PCRE2_ENDANCHORED,
+ PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART,
+ PCRE2_NO_JIT, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PAR-
+ TIAL_SOFT. Their action is described below.
- Setting PCRE2_ANCHORED at match time is not supported 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.
+ 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_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-
+ 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.
@@ -2165,9 +2180,9 @@
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.
@@ -2174,79 +2189,79 @@
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.
@@ -2256,38 +2271,38 @@
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.
@@ -2298,81 +2313,81 @@
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
+ 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
+ be captured. The pcre2_pattern_info() function can be used to find out
how many capturing subpatterns 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
+ 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 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
+ 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
+ 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-
+ 2 is not. When this happens, both values in the offset pairs corre-
sponding to unused subpatterns 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
+ 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-
+ 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
+ ond and third capturing subpatterns (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-
+ pcre2_match(). The other elements retain whatever values they previ-
ously had.
@@ -2382,42 +2397,42 @@
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 avail-
- able, and pcre2_get_mark() can be called. It returns a pointer to the
- zero-terminated name, which is within the compiled pattern. Otherwise
- NULL is returned. The length of the (*MARK) name (excluding the termi-
- nating zero) is stored in the code unit that preceeds the name. You
- should use this instead of relying on the terminating zero if the
+ After a successful match, a partial match (PCRE2_ERROR_PARTIAL), or a
+ failure to match (PCRE2_ERROR_NOMATCH), a (*MARK) name may be avail-
+ able, and pcre2_get_mark() can be called. It returns a pointer to the
+ zero-terminated name, which is within the compiled pattern. Otherwise
+ NULL is returned. The length of the (*MARK) name (excluding the termi-
+ nating zero) is stored in the code unit that preceeds the name. You
+ should use this instead of relying on the terminating zero if the
(*MARK) name might contain a binary zero.
After a successful match, the (*MARK) name that is returned is the last
- one encountered on the matching path through the pattern. After a "no
- match" or a partial match, the last encountered (*MARK) name is
+ one encountered on the matching path through the pattern. After a "no
+ match" or a partial match, the last encountered (*MARK) name is
returned. For example, consider this pattern:
^(*MARK:A)((*MARK:B)a|b)c
- When it matches "bc", the returned mark 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 mark 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
mark is B.
- 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.
@@ -2424,14 +2439,14 @@
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
@@ -2440,20 +2455,20 @@
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
@@ -2467,15 +2482,15 @@
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
@@ -2484,14 +2499,14 @@
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
@@ -2500,8 +2515,8 @@
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
+ 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.
PCRE2_ERROR_NULL
@@ -2510,12 +2525,12 @@
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-
+ 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
+ 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.
@@ -2524,20 +2539,20 @@
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.
@@ -2556,39 +2571,39 @@
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
+ 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 final arguments of pcre2_substring_copy_bynumber() are a pointer to
@@ -2597,25 +2612,25 @@
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
@@ -2626,8 +2641,8 @@
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.
@@ -2638,32 +2653,32 @@
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
+ 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-
+ PCRE2_UNSET for unset substrings, or by calling pcre2_sub-
string_length_bynumber().
@@ -2683,39 +2698,39 @@
void pcre2_substring_free(PCRE2_UCHAR *buffer);
- To extract a substring by name, you first have to find associated num-
+ To extract a substring by name, you first have to find associated num-
ber. For example, for this pattern:
(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
+ 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
+ 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
+ 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.
- 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
+ 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.
- 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
+ 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
causes an error at compile time.
@@ -2728,41 +2743,41 @@
PCRE2_SIZE rlength, PCRE2_UCHAR *outputbufferP,
PCRE2_SIZE *outlengthptr);
- This function calls pcre2_match() and then makes a copy of the subject
- string in outputbuffer, replacing the part that was matched with the
- replacement string, whose length is supplied in rlength. This can be
+ This function calls pcre2_match() and then makes a copy of the subject
+ string in outputbuffer, replacing the part that was matched with the
+ replacement string, whose length is supplied in rlength. This can be
given as PCRE2_ZERO_TERMINATED for a zero-terminated string. Matches in
- which a \K item in a lookahead in the pattern causes the match to end
+ 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.
- 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.
- 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 (*MARK) items
+ ify the insertion of characters from capturing groups or (*MARK) items
in the pattern. The following forms are always recognized:
$$ insert a dollar character
@@ -2769,11 +2784,11 @@
$<n> or ${<n>} insert the contents of group <n>
$*MARK or ${*MARK} insert the name of the last (*MARK) encountered
- 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+=".
The facility for inserting a (*MARK) name can be used to perform simple
@@ -2783,92 +2798,92 @@
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.
PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject
- string, replacing every matching substring. If this is not set, only
- the first matching substring is replaced. If any matched substring has
- zero length, after the substitution has happened, an attempt to find a
- non-empty match at the same position is performed. If this is not suc-
- cessful, the current position is advanced by one character except when
- CRLF is a valid newline sequence and the next two characters are CR,
+ string, replacing every matching substring. If this is not set, only
+ the first matching substring is replaced. If any matched substring has
+ zero length, after the substitution has happened, an attempt to find a
+ non-empty match at the same position is performed. If this is not suc-
+ cessful, the current position 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 current position 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
+ 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_UNSET_EMPTY causes unset capturing groups (including
+ PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capturing 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 not influence the extended
+ 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 not influence the extended
substitution syntax described below.
- PCRE2_SUBSTITUTE_EXTENDED causes extra processing to be applied to the
- replacement string. Without this option, only the dollar character is
- special, and only the group insertion forms listed above are valid.
+ PCRE2_SUBSTITUTE_EXTENDED causes extra processing to be applied to the
+ replacement string. Without this option, only the dollar character is
+ special, and only the group insertion forms listed above are valid.
When PCRE2_SUBSTITUTE_EXTENDED is set, two things change:
- Firstly, backslash in a replacement string is interpreted as an escape
+ Firstly, backslash in a replacement string is interpreted as an escape
character. The usual forms such as \n or \x{ddd} can be used to specify
- particular character codes, and backslash followed by any non-alphanu-
- meric character quotes that character. Extended quoting can be coded
+ particular character codes, and backslash followed by any non-alphanu-
+ meric character quotes that character. Extended quoting can be coded
using \Q...\E, exactly as in pattern strings.
- There are also four escape sequences for forcing the case of inserted
- letters. The insertion mechanism has three states: no case forcing,
+ There are also four escape sequences for forcing the case of inserted
+ letters. The insertion mechanism has three states: no case forcing,
force upper case, and force lower case. The escape sequences change the
current state: \U and \L change to upper or lower case forcing, respec-
- tively, and \E (when not terminating a \Q quoted sequence) reverts to
- 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
+ tively, and \E (when not terminating a \Q quoted sequence) reverts to
+ 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-
ters within \Q...\E quoted sequences.
Note that case forcing sequences such as \U...\E do not nest. For exam-
- ple, the result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc"; the final
+ ple, the result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc"; the final
\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
+ 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:
${<n>:-<string>}
${<n>:+<string1>:<string2>}
- As before, <n> may be a group number or a name. The first form speci-
- fies a default value. If group <n> is set, its value is inserted; if
- not, <string> is expanded and the result inserted. The second form
- specifies strings that are expanded and inserted when group <n> is set
- or unset, respectively. The first form is just a convenient shorthand
+ As before, <n> may be a group number or a name. The first form speci-
+ fies a default value. If group <n> is set, its value is inserted; if
+ not, <string> is expanded and the result inserted. The second form
+ specifies strings that are expanded and inserted when group <n> is set
+ or unset, respectively. The first form is just a convenient shorthand
for
${<n>:+${<n>}:<string>}
- Backslash can be used to escape colons and closing curly brackets in
- the replacement strings. A change of the case forcing state within a
- replacement string remains in force afterwards, as shown in this
+ Backslash can be used to escape colons and closing curly brackets in
+ the replacement strings. A change of the case forcing state within a
+ replacement string remains in force afterwards, as shown in this
pcre2test example:
/(some)?(body)/substitute_extended,replace=${1:+\U:\L}HeLLo
@@ -2877,16 +2892,16 @@
somebody
1: HELLO
- The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended
- substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause
+ The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended
+ substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause
unknown groups in the extended syntax forms to be treated as unset.
- If successful, pcre2_substitute() returns the number of replacements
+ If successful, pcre2_substitute() returns the number of replacements
that were made. This may be zero if no matches were found, and is never
greater than 1 unless PCRE2_SUBSTITUTE_GLOBAL is set.
In the event of an error, a negative error code is returned. Except for
- PCRE2_ERROR_NOMATCH (which is never returned), errors from
+ PCRE2_ERROR_NOMATCH (which is never returned), errors from
pcre2_match() are passed straight back.
PCRE2_ERROR_NOSUBSTRING is returned for a non-existent substring inser-
@@ -2893,25 +2908,25 @@
tion, unless PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set.
PCRE2_ERROR_UNSET is returned for an unset substring insertion (includ-
- ing an unknown substring when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set)
+ ing an unknown substring when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set)
when the simple (non-extended) syntax is used and PCRE2_SUBSTI-
TUTE_UNSET_EMPTY is not set.
- PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big
+ PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big
enough. If the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set, the size
- of buffer that is needed is returned via outlengthptr. Note that this
+ of buffer that is needed is returned via outlengthptr. Note that this
does not happen by default.
- PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in
+ PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in
the replacement string, with more particular errors being
- PCRE2_ERROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REP-
- MISSING_BRACE (closing curly bracket not found), PCRE2_BADSUBSTITUTION
- (syntax error in extended group substitution), and PCRE2_BADSUBPATTERN
- (the pattern match ended before it started, which can happen if \K is
+ PCRE2_ERROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REP-
+ MISSING_BRACE (closing curly bracket not found), PCRE2_BADSUBSTITUTION
+ (syntax error in extended group substitution), and PCRE2_BADSUBPATTERN
+ (the pattern match ended before it started, which can happen if \K is
used in an assertion).
As for all PCRE2 errors, a text message that describes the error can be
- obtained by calling the pcre2_get_error_message() function (see
+ obtained by calling the pcre2_get_error_message() function (see
"Obtaining a textual error message" above).
@@ -2920,56 +2935,56 @@
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
+ 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.
Normally, patterns with duplicate names are such that in any one match,
- only one of the named subpatterns participates. An example is shown in
+ only one of the named subpatterns 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
- to the given name that is set. Only if none are set is
- PCRE2_ERROR_UNSET is returned. The pcre2_substring_number_from_name()
+ When duplicates are present, pcre2_substring_copy_byname() and
+ pcre2_substring_get_byname() return the first substring corresponding
+ to the given name that is set. Only if none are set is
+ PCRE2_ERROR_UNSET is returned. The pcre2_substring_number_from_name()
function returns the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are
duplicate names.
- If you want to get full details of all captured substrings for a given
- name, you must use the pcre2_substring_nametable_scan() function. The
- first argument is the compiled pattern, and the second is the name. If
- the third and fourth arguments are NULL, the function returns a group
+ If you want to get full details of all captured substrings for a given
+ name, you must use the pcre2_substring_nametable_scan() function. The
+ first argument is the compiled pattern, and the second is the name. If
+ the third and fourth arguments are NULL, the function returns a group
number for a unique name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise.
When the third and fourth arguments are not NULL, they must be pointers
- to variables that are updated by the function. After it has run, they
+ to variables that are updated by the function. After it has run, they
point to the first and last entries in the name-to-number table for the
- given name, and the function returns the length of each entry in code
- units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are
+ given name, and the function returns the length of each entry in code
+ units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are
no entries for the given name.
The format of the name table is described above in the section entitled
- Information about a pattern. Given all the relevant entries for the
- name, you can extract each of their numbers, and hence the captured
+ Information about a pattern. Given all the relevant entries for the
+ name, you can extract each of their numbers, and hence the captured
data.
FINDING ALL POSSIBLE MATCHES AT ONE POSITION
- The traditional matching function uses a similar algorithm to Perl,
- which stops when it finds the first match at a given point in the sub-
+ The traditional matching function uses a similar algorithm to Perl,
+ which stops when it finds the first match at a given point in the sub-
ject. If you want to find all possible matches, or the longest possible
- match at a given position, consider using the alternative matching
- function (see below) instead. If you cannot use the alternative func-
+ match at a given position, consider using the alternative matching
+ function (see below) instead. If you cannot use the alternative func-
tion, you can kludge it up by making use of the callout facility, which
is described in the pcre2callout documentation.
What you have to do is to insert a callout right at the end of the pat-
- tern. When your callout function is called, extract and save the cur-
- rent matched substring. Then return 1, which forces pcre2_match() to
- backtrack and try other alternatives. Ultimately, when it runs out of
+ tern. When your callout function is called, extract and save the cur-
+ rent matched substring. Then return 1, which forces pcre2_match() to
+ backtrack and try other alternatives. Ultimately, when it runs out of
matches, pcre2_match() will yield PCRE2_ERROR_NOMATCH.
@@ -2981,26 +2996,26 @@
pcre2_match_context *mcontext,
int *workspace, PCRE2_SIZE wscount);
- The function pcre2_dfa_match() is called to match a subject string
- against a compiled pattern, using a matching algorithm that scans the
+ The function pcre2_dfa_match() is called to match a subject string
+ against a compiled pattern, using a matching algorithm that scans the
subject string just once (not counting lookaround assertions), and does
- not backtrack. This has different characteristics to the normal algo-
- rithm, and is not compatible with Perl. Some of the features of PCRE2
- patterns are not supported. Nevertheless, there are times when this
- kind of matching can be useful. For a discussion of the two matching
+ not backtrack. This has different characteristics to the normal algo-
+ rithm, and is not compatible with Perl. Some of the features of PCRE2
+ patterns are not supported. Nevertheless, there are times when this
+ kind of matching can be useful. For a discussion of the two matching
algorithms, and a list of features that pcre2_dfa_match() does not sup-
port, see the pcre2matching documentation.
- The arguments for the pcre2_dfa_match() function are the same as for
+ The arguments for the pcre2_dfa_match() function are the same as for
pcre2_match(), plus two extras. The ovector within the match data block
is used in a different way, and this is described below. The other com-
- mon arguments are used in the same way as for pcre2_match(), so their
+ mon arguments are used in the same way as for pcre2_match(), so their
description is not repeated here.
- The two additional arguments provide workspace for the function. The
- workspace vector should contain at least 20 elements. It is used for
+ The two additional arguments provide workspace for the function. The
+ workspace vector should contain at least 20 elements. It is used for
keeping track of multiple paths through the pattern tree. More
- workspace is needed for patterns and subjects where there are a lot of
+ workspace is needed for patterns and subjects where there are a lot of
potential matches.
Here is an example of a simple call to pcre2_dfa_match():
@@ -3020,45 +3035,45 @@
Option bits for pcre_dfa_match()
- The unused bits of the options argument for pcre2_dfa_match() must be
- zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL,
- PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART,
- PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT,
- PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but the last four of
- these are exactly the same as for pcre2_match(), so their description
- is not repeated here.
+ The unused bits of the options argument for pcre2_dfa_match() must be
+ zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_ENDAN-
+ CHORED, PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY,
+ PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD,
+ PCRE2_PARTIAL_SOFT, PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but
+ the last four of these are exactly the same as for pcre2_match(), so
+ their description is not repeated here.
PCRE2_PARTIAL_HARD
PCRE2_PARTIAL_SOFT
- These have the same general effect as they do for pcre2_match(), but
- the details are slightly different. When PCRE2_PARTIAL_HARD is set for
- pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the
+ These have the same general effect as they do for pcre2_match(), but
+ the details are slightly different. When PCRE2_PARTIAL_HARD is set for
+ pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the
subject is reached and there is still at least one matching possibility
that requires additional characters. This happens even if some complete
- matches have already been found. When PCRE2_PARTIAL_SOFT is set, the
- return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL
- if the end of the subject is reached, there have been no complete
+ matches have already been found. When PCRE2_PARTIAL_SOFT is set, the
+ return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL
+ if the end of the subject is reached, there have been no complete
matches, but there is still at least one matching possibility. The por-
- tion of the string that was inspected when the longest partial match
+ tion of the string that was inspected when the longest partial match
was found is set as the first matching string in both cases. There is a
- more detailed discussion of partial and multi-segment matching, with
+ more detailed discussion of partial and multi-segment matching, with
examples, in the pcre2partial documentation.
PCRE2_DFA_SHORTEST
- Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to
+ Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to
stop as soon as it has found one match. Because of the way the alterna-
- tive algorithm works, this is necessarily the shortest possible match
+ tive algorithm works, this is necessarily the shortest possible match
at the first possible matching point in the subject string.
PCRE2_DFA_RESTART
- When pcre2_dfa_match() returns a partial match, it is possible to call
+ When pcre2_dfa_match() returns a partial match, it is possible to call
it again, with additional subject characters, and have it continue with
the same match. The PCRE2_DFA_RESTART option requests this action; when
- it is set, the workspace and wscount options must reference the same
- vector as before because data about the match so far is left in them
+ it is set, the workspace and wscount options must reference the same
+ vector as before because data about the match so far is left in them
after a partial match. There is more discussion of this facility in the
pcre2partial documentation.
@@ -3066,8 +3081,8 @@
When pcre2_dfa_match() succeeds, it may have matched more than one sub-
string in the subject. Note, however, that all the matches from one run
- of the function start at the same point in the subject. The shorter
- matches are all initial substrings of the longer matches. For example,
+ of the function start at the same point in the subject. The shorter
+ matches are all initial substrings of the longer matches. For example,
if the pattern
<.*>
@@ -3082,17 +3097,17 @@
<something> <something else>
<something>
- On success, the yield of the function is a number greater than zero,
- 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-
+ On success, the yield of the function is a number greater than zero,
+ 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.
- Calls to the convenience functions that extract substrings by name
- return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used
+ Calls to the convenience functions that extract substrings by name
+ return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used
after a DFA match. The convenience functions that extract substrings by
- number never return PCRE2_ERROR_NOSUBSTRING, and the meanings of some
+ number never return PCRE2_ERROR_NOSUBSTRING, and the meanings of some
other errors are slightly different:
PCRE2_ERROR_UNAVAILABLE
@@ -3102,64 +3117,64 @@
PCRE2_ERROR_UNSET
- There is a slot in the ovector for this substring, but there were
+ There is a slot in the ovector for this substring, but there were
insufficient matches to fill it.
- The matched strings are stored in the ovector in reverse order of
- length; that is, the longest matching string is first. If there were
- too many matches to fit into the ovector, the yield of the function is
+ The matched strings are stored in the ovector in reverse order of
+ length; that is, the longest matching string is first. If there were
+ too many matches to fit into the ovector, the yield of the function is
zero, and the vector is filled with the longest matches.
- NOTE: PCRE2's "auto-possessification" optimization usually applies to
- character repeats at the end of a pattern (as well as internally). For
- example, the pattern "a\d+" is compiled as if it were "a\d++". For DFA
- matching, this means that only one possible match is found. If you
- really do want multiple matches in such cases, either use an ungreedy
- repeat auch as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when
+ NOTE: PCRE2's "auto-possessification" optimization usually applies to
+ character repeats at the end of a pattern (as well as internally). For
+ example, the pattern "a\d+" is compiled as if it were "a\d++". For DFA
+ matching, this means that only one possible match is found. If you
+ really do want multiple matches in such cases, either use an ungreedy
+ repeat auch as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when
compiling.
Error returns from pcre2_dfa_match()
The pcre2_dfa_match() function returns a negative number when it fails.
- Many of the errors are the same as for pcre2_match(), as described
+ Many of the errors are the same as for pcre2_match(), as described
above. There are in addition the following errors that are specific to
pcre2_dfa_match():
PCRE2_ERROR_DFA_UITEM
- This return is given if pcre2_dfa_match() encounters an item in the
- pattern that it does not support, for instance, the use of \C in a UTF
+ This return is given if pcre2_dfa_match() encounters an item in the
+ pattern that it does not support, for instance, the use of \C in a UTF
mode or a back reference.
PCRE2_ERROR_DFA_UCOND
- This return is given if pcre2_dfa_match() encounters a condition item
- that uses a back reference for the condition, or a test for recursion
+ This return is given if pcre2_dfa_match() encounters a condition item
+ that uses a back reference for the condition, or a test for recursion
in a specific group. These are not supported.
PCRE2_ERROR_DFA_WSSIZE
- This return is given if pcre2_dfa_match() runs out of space in the
+ This return is given if pcre2_dfa_match() runs out of space in the
workspace vector.
PCRE2_ERROR_DFA_RECURSE
- When a recursive subpattern is processed, the matching function calls
+ 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
+ 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).
@@ -3172,7 +3187,7 @@
REVISION
- Last updated: 01 April 2017
+ Last updated: 04 April 2017
Copyright (c) 1997-2017 University of Cambridge.
------------------------------------------------------------------------------
Modified: code/trunk/doc/pcre2grep.1
===================================================================
--- code/trunk/doc/pcre2grep.1 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/pcre2grep.1 2017-04-06 18:02:40 UTC (rev 734)
@@ -1,4 +1,4 @@
-.TH PCRE2GREP 1 "31 March 2017" "PCRE2 10.30"
+.TH PCRE2GREP 1 "06 April 2017" "PCRE2 10.30"
.SH NAME
pcre2grep - a grep with Perl-compatible regular expressions.
.SH SYNOPSIS
@@ -330,8 +330,8 @@
offset from the start of the file and a length, separated by a comma. In this
mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP
options are ignored. If there is more than one match in a line, each of them is
-shown separately. This option is mutually exclusive with \fB--line-offsets\fP
-and \fB--only-matching\fP.
+shown separately. This option is mutually exclusive with \fB--output\fP,
+\fB--line-offsets\fP, and \fB--only-matching\fP.
.TP
\fB-H\fP, \fB--with-filename\fP
Force the inclusion of the file name at the start of output lines when
@@ -424,7 +424,8 @@
offset and length are separated by a comma. In this mode, no context is shown.
That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP options are ignored. If there is
more than one match in a line, each of them is shown separately. This option is
-mutually exclusive with \fB--file-offsets\fP and \fB--only-matching\fP.
+mutually exclusive with \fB--output\fP, \fB--file-offsets\fP, and
+\fB--only-matching\fP.
.TP
\fB--locale\fP=\fIlocale-name\fP
This option specifies a locale to be used for pattern matching. It overrides
@@ -521,6 +522,30 @@
use of JIT at run time. It is provided for testing and working round problems.
It should never be needed in normal use.
.TP
+\fB-O\fP \fItext\fP, \fB--output\fP=\fItext\fP
+When there is a match, instead of outputting the whole line that matched,
+output just the given text. This option is mutually exclusive with
+\fB--only-matching\fP, \fB--file-offsets\fP, and \fB--line-offsets\fP. Escape
+sequences starting with a dollar character may be used to insert the contents
+of the matched part of the line and/or captured substrings into the text.
+.sp
+$<digits> or ${<digits>} is replaced by the captured
+substring of the given decimal number; zero substitutes the whole match. If
+the number is greater than the number of capturing substrings, or if the
+capture is unset, the replacement is empty.
+.sp
+$a is replaced by bell; $b by backspace; $e by escape; $f by form feed; $n by
+newline; $r by carriage return; $t by tab; $v by vertical tab.
+.sp
+$o<digits> is replaced by the character represented by the given octal
+number; up to three digits are processed.
+.sp
+$x<digits> is replaced by the character represented by the given hexadecimal
+number; up to two digits are processed.
+.sp
+Any other character is substituted by itself. In particular, $$ is replaced by
+a single dollar.
+.TP
\fB-o\fP, \fB--only-matching\fP
Show only the part of the line that matched a pattern instead of the whole
line. In this mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and
@@ -530,7 +555,7 @@
lines), no output is generated, but the return code is set appropriately. If
the matched portion of the line is empty, nothing is output unless the file
name or line number are being printed, in which case they are shown on an
-otherwise empty line. This option is mutually exclusive with
+otherwise empty line. This option is mutually exclusive with \fB--output\fP,
\fB--file-offsets\fP and \fB--line-offsets\fP.
.TP
\fB-o\fP\fInumber\fP, \fB--only-matching\fP=\fInumber\fP
@@ -539,7 +564,7 @@
equivalent to \fB-o\fP without a number. Because these options can be given
without an argument (see above), if an argument is present, it must be given in
the same shell item, for example, -o3 or --only-matching=2. The comments given
-for the non-argument case above also apply to this case. If the specified
+for the non-argument case above also apply to this option. If the specified
capturing parentheses do not exist in the pattern, or were not set in the
match, nothing is output unless the file name or line number are being output.
.sp
@@ -647,9 +672,9 @@
(PCRE2 terminology). However, the \fB--depth-limit\fP, \fB--file-list\fP,
\fB--file-offsets\fP, \fB--include-dir\fP, \fB--line-offsets\fP,
\fB--locale\fP, \fB--match-limit\fP, \fB-M\fP, \fB--multiline\fP, \fB-N\fP,
-\fB--newline\fP, \fB--om-separator\fP, \fB-u\fP, and \fB--utf-8\fP options are
-specific to \fBpcre2grep\fP, as is the use of the \fB--only-matching\fP option
-with a capturing parentheses number.
+\fB--newline\fP, \fB--om-separator\fP, \fB--output\fP, \fB-u\fP, and
+\fB--utf-8\fP options are specific to \fBpcre2grep\fP, as is the use of the
+\fB--only-matching\fP option with a capturing parentheses number.
.P
Although most of the common options work the same way, a few are different in
\fBpcre2grep\fP. For example, the \fB--include\fP option's argument is a glob
@@ -690,15 +715,15 @@
character. Otherwise \fBpcre2grep\fP will assume that it has no data.
.
.
-.SH "CALLING EXTERNAL SCRIPTS"
+.SH "USING PCRE2'S CALLOUT FACILITY"
.rs
.sp
\fBpcre2grep\fP has, by default, support for calling external programs or
-scripts during matching by making use of PCRE2's callout facility. However,
-this support can be disabled when \fBpcre2grep\fP is built. You can find out
-whether your binary has support for callouts by running it with the \fB--help\fP
-option. If the support is not enabled, all callouts in patterns are ignored by
-\fBpcre2grep\fP.
+scripts or echoing specific strings during matching by making use of PCRE2's
+callout facility. However, this support can be disabled when \fBpcre2grep\fP is
+built. You can find out whether your binary has support for callouts by running
+it with the \fB--help\fP option. If the support is not enabled, all callouts in
+patterns are ignored by \fBpcre2grep\fP.
.P
A callout in a PCRE2 pattern is of the form (?C<arg>) where the argument is
either a number or a quoted string (see the
@@ -705,11 +730,18 @@
.\" HREF
\fBpcre2callout\fP
.\"
-documentation for details). Numbered callouts are ignored by \fBpcre2grep\fP.
-String arguments are parsed as a list of substrings separated by pipe (vertical
-bar) characters. The first substring must be an executable name, with the
-following substrings specifying arguments:
+documentation for details). Numbered callouts are ignored by \fBpcre2grep\fP;
+only callouts with string arguments are useful.
+.
+.
+.SS "Calling external programs or scripts"
+.rs
.sp
+If the callout string does not start with a pipe (vertical bar) character, it
+is parsed into a list of substrings separated by pipe characters. The first
+substring must be an executable name, with the following substrings specifying
+arguments:
+.sp
executable_name|arg1|arg2|...
.sp
Any substring (including the executable name) may contain escape sequences
@@ -742,6 +774,19 @@
matcher backtracks in the normal way.
.
.
+.SS "Echoing a specific string"
+.rs
+.sp
+If the callout string starts with a pipe (vertical bar) character, the rest of
+the string is written to the output, having been passed through the same escape
+processing as text from the --output option. This provides a simple echoing
+facility that avoids calling an external program or script. No terminator is
+added to the string, so if you want a newline, you must include it explicitly.
+Matching continues normally after the string is output. If you want to see only
+the callout output but not any output from an actual match, you should end the
+relevant pattern with (*FAIL).
+.
+.
.SH "MATCHING ERRORS"
.rs
.sp
@@ -789,6 +834,6 @@
.rs
.sp
.nf
-Last updated: 31 March 2017
+Last updated: 06 April 2017
Copyright (c) 1997-2017 University of Cambridge.
.fi
Modified: code/trunk/doc/pcre2grep.txt
===================================================================
--- code/trunk/doc/pcre2grep.txt 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/pcre2grep.txt 2017-04-06 18:02:40 UTC (rev 734)
@@ -363,8 +363,8 @@
length, separated by a comma. In this mode, no context is
shown. That is, the -A, -B, and -C options are ignored. If
there is more than one match in a line, each of them is shown
- separately. This option is mutually exclusive with --line-
- offsets and --only-matching.
+ separately. This option is mutually exclusive with --output,
+ --line-offsets, and --only-matching.
-H, --with-filename
Force the inclusion of the file name at the start of output
@@ -469,8 +469,8 @@
separated by a comma. In this mode, no context is shown.
That is, the -A, -B, and -C options are ignored. If there is
more than one match in a line, each of them is shown sepa-
- rately. This option is mutually exclusive with --file-offsets
- and --only-matching.
+ rately. This option is mutually exclusive with --output,
+ --file-offsets, and --only-matching.
--locale=locale-name
This option specifies a locale to be used for pattern match-
@@ -585,6 +585,33 @@
run time. It is provided for testing and working round prob-
lems. It should never be needed in normal use.
+ -O text, --output=text
+ When there is a match, instead of outputting the whole line
+ that matched, output just the given text. This option is
+ mutually exclusive with --only-matching, --file-offsets, and
+ --line-offsets. Escape sequences starting with a dollar char-
+ acter may be used to insert the contents of the matched part
+ of the line and/or captured substrings into the text.
+
+ $<digits> or ${<digits>} is replaced by the captured sub-
+ string of the given decimal number; zero substitutes the
+ whole match. If the number is greater than the number of cap-
+ turing substrings, or if the capture is unset, the replace-
+ ment is empty.
+
+ $a is replaced by bell; $b by backspace; $e by escape; $f by
+ form feed; $n by newline; $r by carriage return; $t by tab;
+ $v by vertical tab.
+
+ $o<digits> is replaced by the character represented by the
+ given octal number; up to three digits are processed.
+
+ $x<digits> is replaced by the character represented by the
+ given hexadecimal number; up to two digits are processed.
+
+ Any other character is substituted by itself. In particular,
+ $$ is replaced by a single dollar.
+
-o, --only-matching
Show only the part of the line that matched a pattern instead
of the whole line. In this mode, no context is shown. That
@@ -596,8 +623,8 @@
ately. If the matched portion of the line is empty, nothing
is output unless the file name or line number are being
printed, in which case they are shown on an otherwise empty
- line. This option is mutually exclusive with --file-offsets
- and --line-offsets.
+ line. This option is mutually exclusive with --output,
+ --file-offsets and --line-offsets.
-onumber, --only-matching=number
Show only the part of the line that matched the capturing
@@ -607,7 +634,7 @@
(see above), if an argument is present, it must be given in
the same shell item, for example, -o3 or --only-matching=2.
The comments given for the non-argument case above also apply
- to this case. If the specified capturing parentheses do not
+ to this option. If the specified capturing parentheses do not
exist in the pattern, or were not set in the match, nothing
is output unless the file name or line number are being out-
put.
@@ -723,7 +750,7 @@
terminology) is also available as --xxx-regex (PCRE2 terminology). How-
ever, the --depth-limit, --file-list, --file-offsets, --include-dir,
--line-offsets, --locale, --match-limit, -M, --multiline, -N, --new-
- line, --om-separator, -u, and --utf-8 options are specific to
+ line, --om-separator, --output, -u, and --utf-8 options are specific to
pcre2grep, as is the use of the --only-matching option with a capturing
parentheses number.
@@ -766,33 +793,38 @@
equals character. Otherwise pcre2grep will assume that it has no data.
-CALLING EXTERNAL SCRIPTS
+USING PCRE2'S CALLOUT FACILITY
pcre2grep has, by default, support for calling external programs or
- scripts during matching by making use of PCRE2's callout facility. How-
- ever, this support can be disabled when pcre2grep is built. You can
- find out whether your binary has support for callouts by running it
- with the --help option. If the support is not enabled, all callouts in
- patterns are ignored by pcre2grep.
+ scripts or echoing specific strings during matching by making use of
+ PCRE2's callout facility. However, this support can be disabled when
+ pcre2grep is built. You can find out whether your binary has support
+ for callouts by running it with the --help option. If the support is
+ not enabled, all callouts in patterns are ignored by pcre2grep.
A callout in a PCRE2 pattern is of the form (?C<arg>) where the argu-
ment is either a number or a quoted string (see the pcre2callout docu-
- mentation for details). Numbered callouts are ignored by pcre2grep.
- String arguments are parsed as a list of substrings separated by pipe
- (vertical bar) characters. The first substring must be an executable
- name, with the following substrings specifying arguments:
+ mentation for details). Numbered callouts are ignored by pcre2grep;
+ only callouts with string arguments are useful.
+ Calling external programs or scripts
+
+ If the callout string does not start with a pipe (vertical bar) charac-
+ ter, it is parsed into a list of substrings separated by pipe charac-
+ ters. The first substring must be an executable name, with the follow-
+ ing substrings specifying arguments:
+
executable_name|arg1|arg2|...
- Any substring (including the executable name) may contain escape
- sequences started by a dollar character: $<digits> or ${<digits>} is
- replaced by the captured substring of the given decimal number, which
- must be greater than zero. If the number is greater than the number of
- capturing substrings, or if the capture is unset, the replacement is
+ Any substring (including the executable name) may contain escape
+ sequences started by a dollar character: $<digits> or ${<digits>} is
+ replaced by the captured substring of the given decimal number, which
+ must be greater than zero. If the number is greater than the number of
+ capturing substrings, or if the capture is unset, the replacement is
empty.
- Any other character is substituted by itself. In particular, $$ is
- replaced by a single dollar and $| is replaced by a pipe character.
+ Any other character is substituted by itself. In particular, $$ is
+ replaced by a single dollar and $| is replaced by a pipe character.
Here is an example:
echo -e "abcde\n12345" | pcre2grep \
@@ -808,29 +840,41 @@
The parameters for the execv() system call that is used to run the pro-
gram or script are zero-terminated strings. This means that binary zero
- characters in the callout argument will cause premature termination of
- their substrings, and therefore should not be present. Any syntax
- errors in the string (for example, a dollar not followed by another
- character) cause the callout to be ignored. If running the program
+ characters in the callout argument will cause premature termination of
+ their substrings, and therefore should not be present. Any syntax
+ errors in the string (for example, a dollar not followed by another
+ character) cause the callout to be ignored. If running the program
fails for any reason (including the non-existence of the executable), a
- local matching failure occurs and the matcher backtracks in the normal
+ local matching failure occurs and the matcher backtracks in the normal
way.
+ Echoing a specific string
+ If the callout string starts with a pipe (vertical bar) character, the
+ rest of the string is written to the output, having been passed through
+ the same escape processing as text from the --output option. This pro-
+ vides a simple echoing facility that avoids calling an external program
+ or script. No terminator is added to the string, so if you want a new-
+ line, you must include it explicitly. Matching continues normally
+ after the string is output. If you want to see only the callout output
+ but not any output from an actual match, you should end the relevant
+ pattern with (*FAIL).
+
+
MATCHING ERRORS
- It is possible to supply a regular expression that takes a very long
- time to fail to match certain lines. Such patterns normally involve
- nested indefinite repeats, for example: (a+)*\d when matched against a
- line of a's with no final digit. The PCRE2 matching function has a
- resource limit that causes it to abort in these circumstances. If this
- happens, pcre2grep outputs an error message and the line that caused
- the problem to the standard error stream. If there are more than 20
+ It is possible to supply a regular expression that takes a very long
+ time to fail to match certain lines. Such patterns normally involve
+ nested indefinite repeats, for example: (a+)*\d when matched against a
+ line of a's with no final digit. The PCRE2 matching function has a
+ resource limit that causes it to abort in these circumstances. If this
+ happens, pcre2grep outputs an error message and the line that caused
+ the problem to the standard error stream. If there are more than 20
such errors, pcre2grep gives up.
- The --match-limit option of pcre2grep can be used to set the overall
+ The --match-limit option of pcre2grep can be used to set the overall
resource limit; there is a second option called --depth-limit that sets
- a limit on the amount of memory that is used (see the discussion of
+ a limit on the amount of memory that is used (see the discussion of
these options above).
@@ -837,8 +881,8 @@
DIAGNOSTICS
Exit status is 0 if any matches were found, 1 if no matches were found,
- and 2 for syntax errors, overlong lines, non-existent or inaccessible
- files (even if matches were found in other files) or too many matching
+ and 2 for syntax errors, overlong lines, non-existent or inaccessible
+ files (even if matches were found in other files) or too many matching
errors. Using the -s option to suppress error messages about inaccessi-
ble files does not affect the return code.
@@ -857,5 +901,5 @@
REVISION
- Last updated: 31 March 2017
+ Last updated: 06 April 2017
Copyright (c) 1997-2017 University of Cambridge.
Modified: code/trunk/doc/pcre2test.txt
===================================================================
--- code/trunk/doc/pcre2test.txt 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/doc/pcre2test.txt 2017-04-06 18:02:40 UTC (rev 734)
@@ -511,6 +511,7 @@
dollar_endonly set PCRE2_DOLLAR_ENDONLY
/s dotall set PCRE2_DOTALL
dupnames set PCRE2_DUPNAMES
+ endanchored set PCRE2_ENDANCHORED
/x extended set PCRE2_EXTENDED
firstline set PCRE2_FIRSTLINE
match_unset_backref set PCRE2_MATCH_UNSET_BACKREF
@@ -926,6 +927,7 @@
pcre2_dfa_match(). See pcreapi for a description of their effects.
anchored set PCRE2_ANCHORED
+ endanchored set PCRE2_ENDANCHORED
dfa_restart set PCRE2_DFA_RESTART
dfa_shortest set PCRE2_DFA_SHORTEST
no_jit set PCRE2_NO_JIT
@@ -1630,5 +1632,5 @@
REVISION
- Last updated: 25 March 2017
+ Last updated: 04 April 2017
Copyright (c) 1997-2017 University of Cambridge.
Modified: code/trunk/src/pcre2grep.c
===================================================================
--- code/trunk/src/pcre2grep.c 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/src/pcre2grep.c 2017-04-06 18:02:40 UTC (rev 734)
@@ -175,8 +175,9 @@
static const char *DEE_option = NULL;
static const char *locale = NULL;
static const char *newline_arg = NULL;
-static const char *om_separator = "";
+static const char *om_separator = NULL;
static const char *stdin_name = "(standard input)";
+static const char *output_text = NULL;
static char *main_buffer = NULL;
@@ -196,6 +197,7 @@
#else
static int dee_action = dee_READ;
#endif
+
static int DEE_action = DEE_READ;
static int error_count = 0;
static int filenames = FN_DEFAULT;
@@ -233,7 +235,6 @@
static BOOL omit_zero_count = FALSE;
static BOOL resource_error = FALSE;
static BOOL quiet = FALSE;
-static BOOL show_only_matching = FALSE;
static BOOL show_total_count = FALSE;
static BOOL silent = FALSE;
static BOOL utf = FALSE;
@@ -247,6 +248,7 @@
static omstr *only_matching = NULL;
static omstr *only_matching_last = NULL;
+static int only_matching_count;
/* Structure for holding the two variables that describe a number chain. */
@@ -406,6 +408,7 @@
#else
{ OP_NODATA, N_NOJIT, NULL, "no-jit", "ignored: this pcre2grep does not support JIT" },
#endif
+ { OP_STRING, 'O', &output_text, "output=text", "show only this text (possibly expanded)" },
{ OP_OP_NUMBERS, 'o', &only_matching_data, "only-matching=n", "show only the part of the line that matched" },
{ OP_STRING, N_OM_SEPARATOR, &om_separator, "om-separator=text", "set separator for multiple -o output" },
{ OP_NODATA, 'q', NULL, "quiet", "suppress output, just set return code" },
@@ -793,7 +796,7 @@
/************* Print optionally coloured match Unix-style and z/OS **********/
static void
-print_match(const char* buf, int length)
+print_match(const void *buf, int length)
{
if (length == 0) return;
if (do_colour) fprintf(stdout, "%c[%sm", 0x1b, colour_string);
@@ -942,7 +945,7 @@
static WORD match_colour;
static void
-print_match(const char* buf, int length)
+print_match(const void *buf, int length)
{
if (length == 0) return;
if (do_colour)
@@ -1001,7 +1004,7 @@
/************* Print optionally coloured match when we can't do it **********/
static void
-print_match(const char* buf, int length)
+print_match(const void *buf, int length)
{
if (length == 0) return;
FWRITE(buf, 1, length, stdout);
@@ -1658,6 +1661,277 @@
}
+/*************************************************
+* Check output text for errors *
+*************************************************/
+
+static BOOL
+syntax_check_output_text(PCRE2_SPTR string, BOOL callout)
+{
+PCRE2_SPTR begin = string;
+for (; *string != 0; string++)
+ {
+ if (*string == '$')
+ {
+ PCRE2_SIZE capture_id = 0;
+ BOOL brace = FALSE;
+
+ string++;
+
+ /* Syntax error: a character must be present after $. */
+ if (*string == 0)
+ {
+ if (!callout)
+ fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
+ (int)(string - begin), "no character after $");
+ return FALSE;
+ }
+
+ if (*string == '{')
+ {
+ /* Must be a decimal number in braces, e.g: {5} or {38} */
+ string++;
+
+ brace = TRUE;
+ }
+
+ if ((*string >= '1' && *string <= '9') || (!callout && *string == '0'))
+ {
+ do
+ {
+ /* Maximum capture id is 65535. */
+ if (capture_id <= 65535)
+ capture_id = capture_id * 10 + (*string - '0');
+
+ string++;
+ }
+ while (*string >= '0' && *string <= '9');
+
+ if (brace)
+ {
+ /* Syntax error: closing brace is missing. */
+ if (*string != '}')
+ {
+ if (!callout)
+ fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
+ (int)(string - begin), "missing closing brace");
+ return FALSE;
+ }
+ }
+ else
+ {
+ /* To negate the effect of the for. */
+ string--;
+ }
+ }
+ else if (brace)
+ {
+ /* Syntax error: a decimal number required. */
+ if (!callout)
+ fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
+ (int)(string - begin), "decimal number expected");
+ return FALSE;
+ }
+ else if (*string == 'o')
+ {
+ string++;
+
+ if (*string < '0' || *string > '7')
+ {
+ /* Syntax error: an octal number required. */
+ if (!callout)
+ fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
+ (int)(string - begin), "octal number expected");
+ return FALSE;
+ }
+ }
+ else if (*string == 'x')
+ {
+ string++;
+
+ if (!isxdigit((unsigned char)*string))
+ {
+ /* Syntax error: a hexdecimal number required. */
+ if (!callout)
+ fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
+ (int)(string - begin), "hexadecimal number expected");
+ return FALSE;
+ }
+ }
+ }
+ }
+
+ return TRUE;
+}
+
+
+/*************************************************
+* Display output text *
+*************************************************/
+
+/* Display the output text, which is assumed to have already been syntax
+checked. Output may contain escape sequences started by the dollar sign. The
+escape sequences are substituted as follows:
+
+ $<digits> or ${<digits>} is replaced by the captured substring of the given
+ decimal number; zero will substitute the whole match. If the number is
+ greater than the number of capturing substrings, or if the capture is unset,
+ the replacement is empty.
+
+ $a is replaced by bell.
+ $b is replaced by backspace.
+ $e is replaced by escape.
+ $f is replaced by form feed.
+ $n is replaced by newline.
+ $r is replaced by carriage return.
+ $t is replaced by tab.
+ $v is replaced by vertical tab.
+
+ $o<digits> is replaced by the character represented by the given octal
+ number; up to three digits are processed.
+
+ $x<digits> is replaced by the character represented by the given hexadecimal
+ number; up to two digits are processed.
+
+ Any other character is substituted by itself. E.g: $$ is replaced by a single
+ dollar.
+
+Arguments:
+ string: the output text
+ callout: TRUE for the builtin callout, FALSE for --output
+ subject the start of the subject
+ ovector: capture offsets
+ capture_top: number of captures
+
+Returns: TRUE if something was output, other than newline
+ FALSE if nothing was output, or newline was last output
+*/
+
+static BOOL
+display_output_text(PCRE2_SPTR string, BOOL callout, PCRE2_SPTR subject,
+ PCRE2_SIZE *ovector, PCRE2_SIZE capture_top)
+{
+BOOL printed = FALSE;
+
+for (; *string != 0; string++)
+ {
+ int ch = EOF;
+ if (*string == '$')
+ {
+ PCRE2_SIZE capture_id = 0;
+ BOOL brace = FALSE;
+
+ string++;
+
+ if (*string == '{')
+ {
+ /* Must be a decimal number in braces, e.g: {5} or {38} */
+ string++;
+
+ brace = TRUE;
+ }
+
+ if ((*string >= '1' && *string <= '9') || (!callout && *string == '0'))
+ {
+ do
+ {
+ /* Maximum capture id is 65535. */
+ if (capture_id <= 65535)
+ capture_id = capture_id * 10 + (*string - '0');
+
+ string++;
+ }
+ while (*string >= '0' && *string <= '9');
+
+ if (!brace)
+ {
+ /* To negate the effect of the for. */
+ string--;
+ }
+
+ if (capture_id < capture_top)
+ {
+ PCRE2_SIZE capturesize;
+ capture_id *= 2;
+
+ capturesize = ovector[capture_id + 1] - ovector[capture_id];
+ if (capturesize > 0)
+ {
+ print_match(subject + ovector[capture_id], capturesize);
+ printed = TRUE;
+ }
+ }
+ }
+ else if (*string == 'a') ch = '\a';
+ else if (*string == 'b') ch = '\b';
+#ifndef EBCDIC
+ else if (*string == 'e') ch = '\033';
+#else
+ else if (*string == 'e') ch = '\047';
+#endif
+ else if (*string == 'f') ch = '\f';
+ else if (*string == 'r') ch = '\r';
+ else if (*string == 't') ch = '\t';
+ else if (*string == 'v') ch = '\v';
+ else if (*string == 'n')
+ {
+ fprintf(stdout, STDOUT_NL);
+ printed = FALSE;
+ }
+ else if (*string == 'o')
+ {
+ string++;
+
+ ch = *string - '0';
+ if (string[1] >= '0' && string[1] <= '7')
+ {
+ string++;
+ ch = ch * 8 + (*string - '0');
+ }
+ if (string[1] >= '0' && string[1] <= '7')
+ {
+ string++;
+ ch = ch * 8 + (*string - '0');
+ }
+ }
+ else if (*string == 'x')
+ {
+ string++;
+
+ if (*string >= '0' && *string <= '9')
+ ch = *string - '0';
+ else
+ ch = (*string | 0x20) - 'a' + 10;
+ if (isxdigit((unsigned char)string[1]))
+ {
+ string++;
+ ch *= 16;
+ if (*string >= '0' && *string <= '9')
+ ch += *string - '0';
+ else
+ ch += (*string | 0x20) - 'a' + 10;
+ }
+ }
+ else
+ {
+ ch = *string;
+ }
+ }
+ else
+ {
+ ch = *string;
+ }
+ if (ch != EOF)
+ {
+ fprintf(stdout, "%c", ch);
+ printed = TRUE;
+ }
+ }
+
+return printed;
+}
+
+
#ifdef SUPPORT_PCRE2GREP_CALLOUT
/*************************************************
@@ -1683,6 +1957,10 @@
Any other character is substituted by itself. E.g: $$ is replaced by a single
dollar or $| replaced by a pipe character.
+Alternatively, if string starts with pipe, the remainder is taken as an output
+string, same as --output. In this case, --om-separator is used to separate each
+callout, defaulting to newline.
+
Example:
echo -e "abcde\n12345" | pcre2grep \
@@ -1725,6 +2003,16 @@
/* Only callout with strings are supported. */
if (string == NULL || length == 0) return 0;
+/* If there's no command, output the remainder directly. */
+
+if (*string == '|')
+ {
+ string++;
+ if (!syntax_check_output_text(string, TRUE)) return 0;
+ (void)display_output_text(string, TRUE, subject, ovector, capture_top);
+ return 0;
+ }
+
/* Checking syntax and compute the number of string fragments. Callout strings
are ignored in case of a syntax error. */
@@ -2174,8 +2462,8 @@
}
#endif
- /* We come back here after a match when show_only_matching is set, in order
- to find any further matches in the same line. This applies to
+ /* We come back here after a match when only_matching_count is non-zero, in
+ order to find any further matches in the same line. This applies to
--only-matching, --file-offsets, and --line-offsets. */
ONLY_MATCHING_RESTART:
@@ -2229,13 +2517,13 @@
/* The --only-matching option prints just the substring that matched,
and/or one or more captured portions of it, as long as these strings are
not empty. The --file-offsets and --line-offsets options output offsets for
- the matching substring (all three set show_only_matching). None of these
- mutually exclusive options prints any context. Afterwards, adjust the start
- and then jump back to look for further matches in the same line. If we are
- in invert mode, however, nothing is printed and we do not restart - this
- could still be useful because the return code is set. */
+ the matching substring (all three set only_matching_count non-zero). None
+ of these mutually exclusive options prints any context. Afterwards, adjust
+ the start and then jump back to look for further matches in the same line.
+ If we are in invert mode, however, nothing is printed and we do not restart
+ - this could still be useful because the return code is set. */
- else if (show_only_matching)
+ else if (only_matching_count != 0)
{
if (!invert)
{
@@ -2257,6 +2545,16 @@
(int)(filepos + matchptr + offsets[0] - ptr),
(int)(offsets[1] - offsets[0]));
+ /* Handle --output (which has already been syntax checked) */
+
+ else if (output_text != NULL)
+ {
+ if (display_output_text((PCRE2_SPTR)output_text, FALSE,
+ (PCRE2_SPTR)matchptr, offsets, mrc) || printname != NULL ||
+ number)
+ fprintf(stdout, STDOUT_NL);
+ }
+
/* Handle --only-matching, which may occur many times */
else
@@ -2272,7 +2570,8 @@
int plen = offsets[2*n + 1] - offsets[2*n];
if (plen > 0)
{
- if (printed) fprintf(stdout, "%s", om_separator);
+ if (printed && om_separator != NULL)
+ fprintf(stdout, "%s", om_separator);
print_match(matchptr + offsets[n*2], plen);
printed = TRUE;
}
@@ -2557,7 +2856,7 @@
/* End of file; print final "after" lines if wanted; do_after_lines sets
hyphenpending if it prints something. */
-if (!show_only_matching && !(count_only|show_total_count))
+if (only_matching_count == 0 && !(count_only|show_total_count))
{
do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname);
hyphenpending |= endhyphenpending;
@@ -3518,26 +3817,31 @@
if (before_context == 0) before_context = both_context;
}
-/* Only one of --only-matching, --file-offsets, or --line-offsets is permitted.
-However, all three set show_only_matching because they display, each in their
-own way, only the data that has matched. */
+/* Only one of --only-matching, --output, --file-offsets, or --line-offsets is
+permitted. They display, each in their own way, only the data that has matched.
+*/
-if ((only_matching != NULL && (file_offsets || line_offsets)) ||
- (file_offsets && line_offsets))
+only_matching_count = (only_matching != NULL) + (output_text != NULL) +
+ file_offsets + line_offsets;
+
+if (only_matching_count > 1)
{
- fprintf(stderr, "pcre2grep: Cannot mix --only-matching, --file-offsets "
- "and/or --line-offsets\n");
+ fprintf(stderr, "pcre2grep: Cannot mix --only-matching, --output, "
+ "--file-offsets and/or --line-offsets\n");
pcre2grep_exit(usage(2));
}
+/* Check the text supplied to --output for errors. */
+
+if (output_text != NULL &&
+ !syntax_check_output_text((PCRE2_SPTR)output_text, FALSE))
+ goto EXIT2;
+
/* Put limits into the match data block. */
if (match_limit > 0) pcre2_set_match_limit(match_context, match_limit);
if (depth_limit > 0) pcre2_set_depth_limit(match_context, depth_limit);
-if (only_matching != NULL || file_offsets || line_offsets)
- show_only_matching = TRUE;
-
/* If a locale has not been provided as an option, see if the LC_CTYPE or
LC_ALL environment variable is set, and if so, use it. */
@@ -3827,6 +4131,14 @@
else if (frc == 0 && rc == 1) rc = 0;
}
+#ifdef SUPPORT_PCRE2GREP_CALLOUT
+/* If separating builtin echo callouts by implicit newline, add one more for
+the final item. */
+
+if (om_separator != NULL && strcmp(om_separator, STDOUT_NL) == 0)
+ fprintf(stdout, STDOUT_NL);
+#endif
+
/* Show the total number of matches if requested, but not if only one file's
count was printed. */
Modified: code/trunk/testdata/grepoutput
===================================================================
(Binary files differ)
Modified: code/trunk/testdata/grepoutputC
===================================================================
--- code/trunk/testdata/grepoutputC 2017-04-05 15:40:06 UTC (rev 733)
+++ code/trunk/testdata/grepoutputC 2017-04-06 18:02:40 UTC (rev 734)
@@ -6,3 +6,9 @@
Arg1: [ t] [ t]
The quick brown
This time it jumps and jumps and jumps.
+0:T
+The quick brown
+0:T
+This time it jumps and jumps and jumps.
+T
+T
