Revision: 739
http://www.exim.org/viewvc/pcre2?view=rev&revision=739
Author: ph10
Date: 2017-04-11 12:47:25 +0100 (Tue, 11 Apr 2017)
Log Message:
-----------
Add explicit heap limiting options to pcre2_match(), with associated features
for listing, configuring, etc.
Modified Paths:
--------------
code/trunk/CMakeLists.txt
code/trunk/ChangeLog
code/trunk/Makefile.am
code/trunk/README
code/trunk/RunTest
code/trunk/config-cmake.h.in
code/trunk/configure.ac
code/trunk/doc/html/README.txt
code/trunk/doc/html/index.html
code/trunk/doc/html/pcre2_config.html
code/trunk/doc/html/pcre2_match.html
code/trunk/doc/html/pcre2_pattern_info.html
code/trunk/doc/html/pcre2api.html
code/trunk/doc/html/pcre2build.html
code/trunk/doc/html/pcre2grep.html
code/trunk/doc/html/pcre2pattern.html
code/trunk/doc/html/pcre2perform.html
code/trunk/doc/html/pcre2test.html
code/trunk/doc/index.html.src
code/trunk/doc/pcre2.txt
code/trunk/doc/pcre2_config.3
code/trunk/doc/pcre2_match.3
code/trunk/doc/pcre2_pattern_info.3
code/trunk/doc/pcre2api.3
code/trunk/doc/pcre2build.3
code/trunk/doc/pcre2grep.1
code/trunk/doc/pcre2grep.txt
code/trunk/doc/pcre2pattern.3
code/trunk/doc/pcre2perform.3
code/trunk/doc/pcre2test.1
code/trunk/doc/pcre2test.txt
code/trunk/src/config.h.in
code/trunk/src/pcre2.h
code/trunk/src/pcre2.h.in
code/trunk/src/pcre2_compile.c
code/trunk/src/pcre2_config.c
code/trunk/src/pcre2_context.c
code/trunk/src/pcre2_error.c
code/trunk/src/pcre2_internal.h
code/trunk/src/pcre2_intmodedep.h
code/trunk/src/pcre2_match.c
code/trunk/src/pcre2_pattern_info.c
code/trunk/src/pcre2grep.c
code/trunk/src/pcre2test.c
code/trunk/testdata/testoutput15
code/trunk/testdata/testoutput2
Added Paths:
-----------
code/trunk/doc/pcre2_set_heap_limit.3
Modified: code/trunk/CMakeLists.txt
===================================================================
--- code/trunk/CMakeLists.txt 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/CMakeLists.txt 2017-04-11 11:47:25 UTC (rev 739)
@@ -78,6 +78,7 @@
# fix by David Gaussmann
# 2016-10-07 PH added PCREGREP_MAX_BUFSIZE
# 2017-03-11 PH turned HEAP_MATCH_RECURSE into a NO-OP for 10.30
+# 2017-04-08 PH added HEAP_LIMIT
PROJECT(PCRE2 C)
@@ -143,6 +144,9 @@
SET(PCRE2_PARENS_NEST_LIMIT "250" CACHE STRING
"Default nested parentheses limit. See PARENS_NEST_LIMIT in config.h.in for details.")
+SET(PCRE2_HEAP_LIMIT "20000000" CACHE STRING
+ "Default limit on heap memory (kilobytes). See HEAP_LIMIT in config.h.in for details.")
+
SET(PCRE2_MATCH_LIMIT "10000000" CACHE STRING
"Default limit on internal looping. See MATCH_LIMIT in config.h.in for details.")
@@ -765,6 +769,7 @@
MESSAGE(STATUS " Rebuild char tables ............. : ${PCRE2_REBUILD_CHARTABLES}")
MESSAGE(STATUS " Internal link size .............. : ${PCRE2_LINK_SIZE}")
MESSAGE(STATUS " Parentheses nest limit .......... : ${PCRE2_PARENS_NEST_LIMIT}")
+ MESSAGE(STATUS " Heap limit ...................... : ${PCRE2_HEAP_LIMIT}")
MESSAGE(STATUS " Match limit ..................... : ${PCRE2_MATCH_LIMIT}")
MESSAGE(STATUS " Match depth limit ............... : ${PCRE2_MATCH_LIMIT_DEPTH}")
MESSAGE(STATUS " Build shared libs ............... : ${BUILD_SHARED_LIBS}")
Modified: code/trunk/ChangeLog
===================================================================
--- code/trunk/ChangeLog 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/ChangeLog 2017-04-11 11:47:25 UTC (rev 739)
@@ -121,7 +121,12 @@
branch. For example, /(?(DEFINE)...)^A/ and /(...){0}^B/ are now flagged as
anchored.
+22. Added an explicit limit on the amount of heap used by pcre2_match(), set by
+pcre2_set_heap_limit() or (*LIMIT_HEAP=xxx). Upgraded pcre2test to show the
+heap limit along with other pattern information, and to find the minimum when
+the find_limits modifier is set.
+
Version 10.23 14-February-2017
------------------------------
Modified: code/trunk/Makefile.am
===================================================================
--- code/trunk/Makefile.am 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/Makefile.am 2017-04-11 11:47:25 UTC (rev 739)
@@ -69,6 +69,7 @@
doc/html/pcre2_set_character_tables.html \
doc/html/pcre2_set_compile_recursion_guard.html \
doc/html/pcre2_set_depth_limit.html \
+ doc/html/pcre2_set_heap_limit.html \
doc/html/pcre2_set_match_limit.html \
doc/html/pcre2_set_max_pattern_length.html \
doc/html/pcre2_set_offset_limit.html \
@@ -152,6 +153,7 @@
doc/pcre2_set_character_tables.3 \
doc/pcre2_set_compile_recursion_guard.3 \
doc/pcre2_set_depth_limit.3 \
+ doc/pcre2_set_heap_limit.3 \
doc/pcre2_set_match_limit.3 \
doc/pcre2_set_max_pattern_length.3 \
doc/pcre2_set_offset_limit.3 \
Modified: code/trunk/README
===================================================================
--- code/trunk/README 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/README 2017-04-11 11:47:25 UTC (rev 739)
@@ -223,10 +223,10 @@
--with-parens-nest-limit=500
-. PCRE2 has a counter that can be set to limit the amount of resources it uses
- when matching a pattern. If the limit is exceeded during a match, the match
- fails. The default is ten million. You can change the default by setting, for
- example,
+. PCRE2 has a counter that can be set to limit the amount of computing resource
+ it uses when matching a pattern with the Perl-compatible matching function.
+ If the limit is exceeded during a match, the match fails. The default is ten
+ million. You can change the default by setting, for example,
--with-match-limit=500000
@@ -235,8 +235,8 @@
pcre2api man page (search for pcre2_set_match_limit).
. There is a separate counter that limits the depth of nested backtracking
- during a matching process, which in turn limits the amount of memory that is
- used. This also has a default of ten million, which is essentially
+ during a matching process, which indirectly limits the amount of heap memory
+ that is used. This also has a default of ten million, which is essentially
"unlimited". You can change the default by setting, for example,
--with-match-limit-depth=5000
@@ -243,6 +243,15 @@
There is more discussion in the pcre2api man page (search for
pcre2_set_depth_limit).
+
+. You can also set an explicit limit on the amount of heap memory used by
+ the pcre2_match() interpreter:
+
+ --with-heap-limit=500
+
+ The units are kilobytes. This limit does not apply when the JIT optimization
+ (which has its own memory control features) is used. There is more discussion
+ on the pcre2api man page (search for pcre2_set_heap_limit).
. In the 8-bit library, the default maximum compiled pattern size is around
64K bytes. You can increase this by adding --with-link-size=3 to the
@@ -865,4 +874,4 @@
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
-Last updated: 17 March 2017
+Last updated: 11 April 2017
Modified: code/trunk/RunTest
===================================================================
--- code/trunk/RunTest 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/RunTest 2017-04-11 11:47:25 UTC (rev 739)
@@ -489,7 +489,7 @@
for opt in "" $jitopt; do
$sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput2 testtry
if [ $? = 0 ] ; then
- $sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -63,-62,-2,-1,0,100,188,189,190,191 >>testtry
+ $sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -64,-62,-2,-1,0,100,188,189,190,191 >>testtry
checkresult $? 2 "$opt"
fi
done
Modified: code/trunk/config-cmake.h.in
===================================================================
--- code/trunk/config-cmake.h.in 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/config-cmake.h.in 2017-04-11 11:47:25 UTC (rev 739)
@@ -36,6 +36,7 @@
#cmakedefine NEVER_BACKSLASH_C 1
#define LINK_SIZE @PCRE2_LINK_SIZE@
+#define HEAP_LIMIT @PCRE2_HEAP_LIMIT@
#define MATCH_LIMIT @PCRE2_MATCH_LIMIT@
#define MATCH_LIMIT_DEPTH @PCRE2_MATCH_LIMIT_DEPTH@
#define NEWLINE_DEFAULT @NEWLINE_DEFAULT@
Modified: code/trunk/configure.ac
===================================================================
--- code/trunk/configure.ac 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/configure.ac 2017-04-11 11:47:25 UTC (rev 739)
@@ -263,6 +263,12 @@
[nested parentheses limit (default=250)]),
, with_parens_nest_limit=250)
+# Handle --with-heap-limit
+AC_ARG_WITH(heap-limit,
+ AS_HELP_STRING([--with-heap-limit=N],
+ [default limit on heap memory (kilobytes, default=20000000)]),
+ , with_heap_limit=20000000)
+
# Handle --with-match-limit=N
AC_ARG_WITH(match-limit,
AS_HELP_STRING([--with-match-limit=N],
@@ -285,7 +291,7 @@
AC_ARG_WITH(match-limit-recursion,,
, with_match_limit_recursion=UNSET)
-
+
# Handle --enable-valgrind
AC_ARG_ENABLE(valgrind,
AS_HELP_STRING([--enable-valgrind],
@@ -680,12 +686,12 @@
stack that is used while compiling a pattern.])
AC_DEFINE_UNQUOTED([MATCH_LIMIT], [$with_match_limit], [
- The value of MATCH_LIMIT determines the default number of times the internal
- match() function can record a backtrack position during a single matching
- attempt. There is a runtime interface for setting a different limit. The
- limit exists in order to catch runaway regular expressions that take for ever
- to determine that they do not match. The default is set very large so that it
- does not accidentally catch legitimate cases.])
+ The value of MATCH_LIMIT determines the default number of times the
+ pcre2_match() function can record a backtrack position during a single
+ matching attempt. There is a runtime interface for setting a different limit.
+ The limit exists in order to catch runaway regular expressions that take for
+ ever to determine that they do not match. The default is set very large so
+ that it does not accidentally catch legitimate cases.])
# --with-match-limit-recursion is an obsolete synonym for --with-match-limit-depth
@@ -694,7 +700,7 @@
WARNING: --with-match-limit-recursion is an obsolete option. Please use
--with-match-limit-depth in future. If both are set, --with-match-limit-depth
- will be used.
+ will be used. See also --with-heap-limit.
EOF
if test "$with_match_limit_depth" = "MATCH_LIMIT"; then
@@ -711,6 +717,10 @@
be less than the value of MATCH_LIMIT. The default is to use the same value
as MATCH_LIMIT. There is a runtime method for setting a different limit.])
+AC_DEFINE_UNQUOTED([HEAP_LIMIT], [$with_heap_limit], [
+ This limits the amount of memory that pcre2_match() may use while matching
+ a pattern. The value is in kilobytes.])
+
AC_DEFINE([MAX_NAME_SIZE], [32], [
This limit is parameterized just in case anybody ever wants to
change it. Care must be taken if it is increased, because it guards
@@ -971,6 +981,7 @@
Rebuild char tables ................ : ${enable_rebuild_chartables}
Internal link size ................. : ${with_link_size}
Nested parentheses limit ........... : ${with_parens_nest_limit}
+ Heap limit ......................... : ${with_heap_limit} kilobytes
Match limit ........................ : ${with_match_limit}
Match depth limit .................. : ${with_match_limit_depth}
Build shared libs .................. : ${enable_shared}
Modified: code/trunk/doc/html/README.txt
===================================================================
--- code/trunk/doc/html/README.txt 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/README.txt 2017-04-11 11:47:25 UTC (rev 739)
@@ -223,10 +223,10 @@
--with-parens-nest-limit=500
-. PCRE2 has a counter that can be set to limit the amount of resources it uses
- when matching a pattern. If the limit is exceeded during a match, the match
- fails. The default is ten million. You can change the default by setting, for
- example,
+. PCRE2 has a counter that can be set to limit the amount of computing resource
+ it uses when matching a pattern with the Perl-compatible matching function.
+ If the limit is exceeded during a match, the match fails. The default is ten
+ million. You can change the default by setting, for example,
--with-match-limit=500000
@@ -235,8 +235,8 @@
pcre2api man page (search for pcre2_set_match_limit).
. There is a separate counter that limits the depth of nested backtracking
- during a matching process, which in turn limits the amount of memory that is
- used. This also has a default of ten million, which is essentially
+ during a matching process, which indirectly limits the amount of heap memory
+ that is used. This also has a default of ten million, which is essentially
"unlimited". You can change the default by setting, for example,
--with-match-limit-depth=5000
@@ -243,6 +243,15 @@
There is more discussion in the pcre2api man page (search for
pcre2_set_depth_limit).
+
+. You can also set an explicit limit on the amount of heap memory used by
+ the pcre2_match() interpreter:
+
+ --with-heap-limit=500
+
+ The units are kilobytes. This limit does not apply when the JIT optimization
+ (which has its own memory control features) is used. There is more discussion
+ on the pcre2api man page (search for pcre2_set_heap_limit).
. In the 8-bit library, the default maximum compiled pattern size is around
64K bytes. You can increase this by adding --with-link-size=3 to the
@@ -865,4 +874,4 @@
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
-Last updated: 17 March 2017
+Last updated: 11 April 2017
Modified: code/trunk/doc/html/index.html
===================================================================
--- code/trunk/doc/html/index.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/index.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -213,6 +213,9 @@
<tr><td><a href="pcre2_set_depth_limit.html">pcre2_set_depth_limit</a></td>
<td> Set the match backtracking depth limit</td></tr>
+<tr><td><a href="pcre2_set_heap_limit.html">pcre2_set_heap_limit</a></td>
+ <td> Set the match backtracking heap limit</td></tr>
+
<tr><td><a href="pcre2_set_match_limit.html">pcre2_set_match_limit</a></td>
<td> Set the match limit</td></tr>
Modified: code/trunk/doc/html/pcre2_config.html
===================================================================
--- code/trunk/doc/html/pcre2_config.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/pcre2_config.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -45,6 +45,7 @@
PCRE2_CONFIG_BSR Indicates what \R matches by default:
PCRE2_BSR_UNICODE
PCRE2_BSR_ANYCRLF
+ PCRE2_CONFIG_HEAPLIMIT Default heap memory limit
PCRE2_CONFIG_DEPTHLIMIT Default backtracking depth limit
PCRE2_CONFIG_JIT Availability of just-in-time compiler support (1=yes 0=no)
PCRE2_CONFIG_JITTARGET Information (a string) about the target architecture for the JIT compiler
Modified: code/trunk/doc/html/pcre2_match.html
===================================================================
--- code/trunk/doc/html/pcre2_match.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/pcre2_match.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -44,6 +44,7 @@
<pre>
Set up a callout function
Set a matching offset limit
+ Change the heap memory limit
Change the backtracking match limit
Change the backtracking depth limit
Set custom memory management specifically for the match
Modified: code/trunk/doc/html/pcre2_pattern_info.html
===================================================================
--- code/trunk/doc/html/pcre2_pattern_info.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/pcre2_pattern_info.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -51,6 +51,7 @@
PCRE2_INFO_FRAMESIZE Size of backtracking frame
PCRE2_INFO_HASBACKSLASHC Return 1 if pattern contains \C
PCRE2_INFO_HASCRORLF Return 1 if explicit CR or LF matches exist in the pattern
+ PCRE2_INFO_HEAPLIMIT Heap memory limit if set, otherwise PCRE2_ERROR_UNSET
PCRE2_INFO_JCHANGED Return 1 if (?J) or (?-J) was used
PCRE2_INFO_JITSIZE Size of JIT compiled code, or 0
PCRE2_INFO_LASTCODETYPE Type of must-be-present information
Modified: code/trunk/doc/html/pcre2api.html
===================================================================
--- code/trunk/doc/html/pcre2api.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/pcre2api.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -182,6 +182,10 @@
<b> PCRE2_SIZE <i>value</i>);</b>
<br>
<br>
+<b>int pcre2_set_heap_limit(pcre2_match_context *<i>mcontext</i>,</b>
+<b> uint32_t <i>value</i>);</b>
+<br>
+<br>
<b>int pcre2_set_match_limit(pcre2_match_context *<i>mcontext</i>,</b>
<b> uint32_t <i>value</i>);</b>
<br>
@@ -793,6 +797,7 @@
<pre>
Set up a callout function
Set an offset limit for matching an unanchored pattern
+ Change the limit on the amount of heap used when matching
Change the backtracking match limit
Change the backtracking depth limit
Set custom memory management specifically for the match
@@ -851,14 +856,47 @@
start within the first line of the subject. If this is set with an offset
limit, a match must occur in the first line and also within the offset limit.
In other words, whichever limit comes first is used.
+<b>int pcre2_set_heap_limit(pcre2_match_context *<i>mcontext</i>,</b>
+<b> uint32_t <i>value</i>);</b>
+<br>
+<br>
+The <i>heap_limit</i> parameter specifies, in units of kilobytes, the maximum
+amount of heap memory that <b>pcre2_match()</b> may use to hold backtracking
+information when running an interpretive match. This limit does not apply to
+matching with the JIT optimization, which has its own memory control
+arrangements (see the
+<a href="pcre2jit.html"><b>pcre2jit</b></a>
+documentation for more details), nor does it apply to <b>pcre2_dfa_match()</b>.
+If the limit is reached, the negative error code PCRE2_ERROR_HEAPLIMIT is
+returned. The default limit is set when PCRE2 is built; the default default is
+very large and is essentially "unlimited".
+</P>
+<P>
+A value for the heap limit may also be supplied by an item at the start of a
+pattern of the form
+<pre>
+ (*LIMIT_HEAP=ddd)
+</pre>
+where ddd is a decimal number. However, such a setting is ignored unless ddd is
+less than the limit set by the caller of <b>pcre2_match()</b> or, if no such
+limit is set, less than the default.
+</P>
+<P>
+The <b>pcre2_match()</b> function starts out using a 20K vector on the system
+stack for recording backtracking points. The more nested backtracking points
+there are (that is, the deeper the search tree), the more memory is needed.
+Heap memory is used only if the initial vector is too small. If the heap limit
+is set to a value less than 21 (in particular, zero) no heap memory will be
+used. In this case, only patterns that do not have a lot of nested backtracking
+can be successfully processed.
<b>int pcre2_set_match_limit(pcre2_match_context *<i>mcontext</i>,</b>
<b> uint32_t <i>value</i>);</b>
<br>
<br>
The <i>match_limit</i> parameter provides a means of preventing PCRE2 from using
-up too many resources when processing patterns that are not going to match, but
-which have a very large number of possibilities in their search trees. The
-classic example is a pattern that uses nested unlimited repeats.
+up too many computing resources when processing patterns that are not going to
+match, but which have a very large number of possibilities in their search
+trees. The classic example is a pattern that uses nested unlimited repeats.
</P>
<P>
There is an internal counter in <b>pcre2_match()</b> that is incremented each
@@ -895,16 +933,20 @@
This parameter limits the depth of nested backtracking in <b>pcre2_match()</b>.
Each time a nested backtracking point is passed, a new memory "frame" is used
to remember the state of matching at that point. Thus, this parameter
-indirectly limits the amount of memory that is used in a match.
+indirectly limits the amount of memory that is used in a match. However,
+because the size of each memory "frame" depends on the number of capturing
+parentheses, the actual memory limit varies from pattern to pattern. This limit
+was more useful in versions before 10.30, where function recursion was used for
+backtracking.
</P>
<P>
-This limit is not relevant, and is ignored, when matching is done using JIT
-compiled code. However, it is supported by <b>pcre2_dfa_match()</b>, which uses
-it to limit the depth of internal recursive function calls that implement
-lookaround assertions and pattern recursions. This is, therefore, an indirect
-limit on the amount of system stack that is used. A recursive pattern such as
-/(.)(?1)/, when matched to a very long string using <b>pcre2_dfa_match()</b>,
-can use a great deal of stack.
+The depth limit is not relevant, and is ignored, when matching is done using
+JIT compiled code. However, it is supported by <b>pcre2_dfa_match()</b>, which
+uses it to limit the depth of internal recursive function calls that implement
+atomic groups, lookaround assertions, and pattern recursions. This is,
+therefore, an indirect limit on the amount of system stack that is used. A
+recursive pattern such as /(.)(?1)/, when matched to a very long string using
+<b>pcre2_dfa_match()</b>, can use a great deal of stack.
</P>
<P>
The default value for the depth limit can be set when PCRE2 is built; the
@@ -959,6 +1001,12 @@
and lookarounds in <b>pcre2_dfa_match()</b>. Further details are given with
<b>pcre2_set_depth_limit()</b> above.
<pre>
+ PCRE2_CONFIG_HEAPLIMIT
+</pre>
+The output is a uint32_t integer that gives, in kilobytes, the default limit
+for the amount of heap memory used by <b>pcre2_match()</b>. Further details are
+given with <b>pcre2_set_heap_limit()</b> above.
+<pre>
PCRE2_CONFIG_JIT
</pre>
The output is a uint32_t integer that is set to one if support for just-in-time
@@ -1787,6 +1835,13 @@
explicit match is either a literal CR or LF character, or \r or \n or one of
the equivalent hexadecimal or octal escape sequences.
<pre>
+ PCRE2_INFO_HEAPLIMIT
+</pre>
+If the pattern set a heap memory limit by including an item of the form
+(*LIMIT_HEAP=nnnn) at the start, the value is returned. The third argument
+should point to an unsigned 32-bit integer. If no such value has been set, the
+call to <b>pcre2_pattern_info()</b> returns the error PCRE2_ERROR_UNSET.
+<pre>
PCRE2_INFO_JCHANGED
</pre>
Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
@@ -2554,7 +2609,8 @@
</pre>
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.
+or custom) fails. Note that a different error, PCRE2_ERROR_HEAPLIMIT, is given
+if the amount of memory needed exceeds the heap limit.
<pre>
PCRE2_ERROR_NULL
</pre>
@@ -3271,7 +3327,7 @@
</P>
<br><a name="SEC42" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 04 April 2017
+Last updated: 11 April 2017
<br>
Copyright © 1997-2017 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2build.html
===================================================================
--- code/trunk/doc/html/pcre2build.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/pcre2build.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -265,17 +265,41 @@
(though the counting is done differently).
</P>
<P>
-In some environments it is desirable to limit the depth of nested backtracking
-in order to restrict the maximum amount of heap memory that is used. A second
-limit controls this; it defaults to the value that is set for
---with-match-limit. You can set a lower default limit by adding, for example,
+The <b>pcre2_match()</b> function starts out using a 20K vector on the system
+stack to record backtracking points. The more nested backtracking points there
+are (that is, the deeper the search tree), the more memory is needed. If the
+initial vector is not large enough, heap memory is used, up to a certain limit,
+which is specified in kilobytes. The limit can be changed at run time, as
+described in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+documentation. The default limit (in effect unlimited) is 20 million. You can
+change this by a setting such as
<pre>
+ --with-heap-limit=500
+</pre>
+which limits the amount of heap to 500 kilobytes. This limit applies only to
+interpretive matching in pcre2_match(). It does not apply when JIT (which has
+its own memory arrangements) is used, nor does it apply to
+<b>pcre2_dfa_match()</b>.
+</P>
+<P>
+You can also explicitly limit the depth of nested backtracking in the
+<b>pcre2_match()</b> interpreter. This limit defaults to the value that is set
+for --with-match-limit. You can set a lower default limit by adding, for
+example,
+<pre>
--with-match-limit_depth=10000
</pre>
-to the <b>configure</b> command. This value can also be overridden at run time.
-As well as applying to <b>pcre2_match()</b>, this limit also controls the depth
-of recursive function calls in <b>pcre2_dfa_match()</b>. These are used for
-lookaround assertions, atomic groups, and recursion within patterns.
+to the <b>configure</b> command. This value can be overridden at run time. This
+depth limit indirectly limits the amount of heap memory that is used, but
+because the size of each backtracking "frame" depends on the number of
+capturing parentheses in a pattern, the amount of heap that is used before the
+limit is reached varies from pattern to pattern. This limit was more useful in
+versions before 10.30, where function recursion was used for backtracking.
+However, as well as applying to <b>pcre2_match()</b>, this limit also controls
+the depth of recursive function calls in <b>pcre2_dfa_match()</b>. These are
+used for lookaround assertions, atomic groups, and recursion within patterns.
+The limit does not apply to JIT matching.
</P>
<br><a name="SEC12" href="#TOC1">CREATING CHARACTER TABLES AT BUILD TIME</a><br>
<P>
@@ -530,7 +554,7 @@
</P>
<br><a name="SEC25" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 31 March 2017
+Last updated: 10 April 2017
<br>
Copyright © 1997-2017 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2grep.html
===================================================================
--- code/trunk/doc/html/pcre2grep.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/pcre2grep.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -404,6 +404,10 @@
If a line number is also being output, it follows the file name.
</P>
<P>
+<b>--heap-limit</b>=<i>number</i>
+See <b>--match-limit</b> below.
+</P>
+<P>
<b>--help</b>
Output a help message, giving brief details of the command options and file
type support, and then exit. Anything else on the command line is
@@ -505,7 +509,7 @@
<b>--match-limit</b>=<i>number</i>
Processing some regular expression patterns may take a very long time to search
for all possible matching strings. Others may require a very large amount of
-memory. There are two options that set resource limits for matching.
+memory. There are three options that set resource limits for matching.
<br>
<br>
The <b>--match-limit</b> option provides a means of limiting computing resource
@@ -516,13 +520,24 @@
value set by <b>--match-limit</b> is reached, an error occurs.
<br>
<br>
+The <b>--heap-limit</b> option specifies, as a number of kilobytes, the amount
+of heap memory that may be used for matching. Heap memory is needed only if
+matching the pattern requires a significant number of nested backtracking
+points to be remembered. This parameter can be set to zero to forbid the use of
+heap memory altogether.
+<br>
+<br>
The <b>--depth-limit</b> option limits the depth of nested backtracking points,
-which in turn limits the amount of memory that is used. This limit is of use
-only if it is set smaller than <b>--match-limit</b>.
+which indirectly limits the amount of memory that is used. The amount of memory
+needed for each backtracking point depends on the number of capturing
+parentheses in the pattern, so the amount of memory that is used before this
+limit acts varies from pattern to pattern. This limit is of use only if it is
+set smaller than <b>--match-limit</b>.
<br>
<br>
There are no short forms for these options. The default settings are specified
-when the PCRE2 library is compiled, with the default default being 10 million.
+when the PCRE2 library is compiled, with the default defaults being very large
+and so effectively unlimited.
</P>
<P>
\fB--max-buffer-size=<i>number</i>
@@ -764,11 +779,12 @@
as in the GNU <b>grep</b> program. Any long option of the form
<b>--xxx-regexp</b> (GNU terminology) is also available as <b>--xxx-regex</b>
(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>--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.
+<b>--file-offsets</b>, <b>--heap-limit</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>--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
@@ -891,9 +907,9 @@
</P>
<P>
The <b>--match-limit</b> option of <b>pcre2grep</b> can be used to set the
-overall resource limit; there is a second option called <b>--depth-limit</b>
-that sets a limit on the amount of memory that is used (see the discussion of
-these options above).
+overall resource limit. There are also other limits that affect the amount of
+memory used during matching; see the discussion of <b>--heap-limit</b> and
+<b>--depth-limit</b> above.
</P>
<br><a name="SEC12" href="#TOC1">DIAGNOSTICS</a><br>
<P>
@@ -918,7 +934,7 @@
</P>
<br><a name="SEC15" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 06 April 2017
+Last updated: 11 April 2017
<br>
Copyright © 1997-2017 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2pattern.html
===================================================================
--- code/trunk/doc/html/pcre2pattern.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/pcre2pattern.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -170,14 +170,15 @@
<b>pcre2_jit_compile()</b> is ignored.
</P>
<br><b>
-Setting match and backtracking depth limits
+Setting match resource limits
</b><br>
<P>
The pcre2_match() function contains a counter that is incremented every time it
goes round its main loop. The caller of <b>pcre2_match()</b> can set a limit on
this counter, which therefore limits the amount of computing resource used for
-a match. The maximum depth of nested backtracking can also be limited, and this
-restricts the amount of heap memory that is used.
+a match. The maximum depth of nested backtracking can also be limited; this
+indirectly restricts the amount of heap memory that is used, but there is also
+an explicit memory limit that can be set.
</P>
<P>
These facilities are provided to catch runaway matches that are provoked by
@@ -186,6 +187,7 @@
these limits is reached, <b>pcre2_match()</b> gives an error return. The limits
can also be set by items at the start of the pattern of the form
<pre>
+ (*LIMIT_HEAP=d)
(*LIMIT_MATCH=d)
(*LIMIT_DEPTH=d)
</pre>
@@ -200,11 +202,13 @@
still recognized for backwards compatibility.
</P>
<P>
-The match limit is used (but in a different way) when JIT is being used, but it
-is not relevant, and is ignored, when matching with <b>pcre2_dfa_match()</b>.
-However, the depth limit is relevant for DFA matching, which uses function
-recursion for recursions within the pattern. In this case, the depth limit
-controls the amount of system stack that is used.
+The heap limit applies only when the <b>pcre2_match()</b> interpreter is used
+for matching. It does not apply to JIT or DFA matching. The match limit is used
+(but in a different way) when JIT is being used, but it is not relevant, and is
+ignored, when matching with <b>pcre2_dfa_match()</b>. The depth limit is ignored
+by JIT but is relevant for DFA matching, which uses function recursion for
+recursions within the pattern. In this case, the depth limit controls the
+amount of system stack that is used.
<a name="newlines"></a></P>
<br><b>
Newline conventions
@@ -3434,7 +3438,7 @@
</P>
<br><a name="SEC30" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 03 April 2017
+Last updated: 11 April 2017
<br>
Copyright © 1997-2017 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2perform.html
===================================================================
--- code/trunk/doc/html/pcre2perform.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/pcre2perform.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -83,11 +83,12 @@
uses very little system stack at run time. In earlier releases recursive
function calls could use a great deal of stack, and this could cause problems,
but this usage has been eliminated. Backtracking positions are now explicitly
-remembered in memory frames controlled by the code. An initial 10K vector of
-frames is allocated on the system stack (enough for about 50 frames for small
-patterns), but if this is insufficient, heap memory is used. Rewriting patterns
-to be time-efficient, as described below, may also reduce the memory
-requirements.
+remembered in memory frames controlled by the code. An initial 20K vector of
+frames is allocated on the system stack (enough for about 100 frames for small
+patterns), but if this is insufficient, heap memory is used. The amount of heap
+memory can be limited; if the limit is set to zero, only the initial stack
+vector is used. Rewriting patterns to be time-efficient, as described below,
+may also reduce the memory requirements.
</P>
<P>
In contrast to <b>pcre2_match()</b>, <b>pcre2_dfa_match()</b> does use recursive
@@ -243,7 +244,7 @@
</P>
<br><a name="SEC6" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 31 March 2017
+Last updated: 08 April 2017
<br>
Copyright © 1997-2017 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2test.html
===================================================================
--- code/trunk/doc/html/pcre2test.html 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/html/pcre2test.html 2017-04-11 11:47:25 UTC (rev 739)
@@ -235,6 +235,12 @@
compilation, each pattern is passed to the just-in-time compiler, if available.
</P>
<P>
+<b>-jitverify</b>
+Behave as if each pattern line has the <b>jitverify</b> modifier; after
+successful compilation, each pattern is passed to the just-in-time compiler, if
+available, and the use of JIT is verified.
+</P>
+<P>
\fB-pattern\fB <i>modifier-list</i>
Behave as if each pattern line contains the given modifiers.
</P>
@@ -1088,6 +1094,7 @@
get=<number or name> extract captured substring
getall extract all captured substrings
/g global global matching
+ heap_limit=<n> set a limit on heap memory
jitstack=<n> set size of JIT stack
mark show mark values
match_limit=<n> set a match limit
@@ -1330,11 +1337,11 @@
complicated patterns.
</P>
<br><b>
-Setting match and depth limits
+Setting heap, match, and depth limits
</b><br>
<P>
-The <b>match_limit</b> and <b>depth_limit</b> modifiers set the appropriate
-limits in the match context. These values are ignored when the
+The <b>heap_limit</b>, <b>match_limit</b>, and <b>depth_limit</b> modifiers set
+the appropriate limits in the match context. These values are ignored when the
<b>find_limits</b> modifier is specified.
</P>
<br><b>
@@ -1343,8 +1350,8 @@
<P>
If the <b>find_limits</b> modifier is present on a subject line, <b>pcre2test</b>
calls the relevant matching function several times, setting different values in
-the match context via <b>pcre2_set_match_limit()</b> or
-<b>pcre2_set_depth_limit()</b> until it finds the minimum values for each
+the match context via <b>pcre2_set_heap_limit(), \fBpcre2_set_match_limit()</b>,
+or <b>pcre2_set_depth_limit()</b> until it finds the minimum values for each
parameter that allows the match to complete without error.
</P>
<P>
@@ -1360,9 +1367,9 @@
</P>
<P>
For non-DFA matching, the minimum <i>depth_limit</i> number is a measure of how
-much memory for recording backtracking points is needed to complete the match
-attempt. In the case of DFA matching, <i>depth_limit</i> controls the depth of
-recursive calls of the internal function that is used for handling pattern
+much nested backtracking happens (that is, how deeply the pattern's tree is
+searched). In the case of DFA matching, <i>depth_limit</i> controls the depth of
+recursive calls of the internal function that is used for handling pattern
recursion, lookaround assertions, and atomic groups.
</P>
<br><b>
@@ -1800,7 +1807,7 @@
</P>
<br><a name="SEC21" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 04 April 2017
+Last updated: 11 April 2017
<br>
Copyright © 1997-2017 University of Cambridge.
<br>
Modified: code/trunk/doc/index.html.src
===================================================================
--- code/trunk/doc/index.html.src 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/index.html.src 2017-04-11 11:47:25 UTC (rev 739)
@@ -213,6 +213,9 @@
<tr><td><a href="pcre2_set_depth_limit.html">pcre2_set_depth_limit</a></td>
<td> Set the match backtracking depth limit</td></tr>
+<tr><td><a href="pcre2_set_heap_limit.html">pcre2_set_heap_limit</a></td>
+ <td> Set the match backtracking heap limit</td></tr>
+
<tr><td><a href="pcre2_set_match_limit.html">pcre2_set_match_limit</a></td>
<td> Set the match limit</td></tr>
Modified: code/trunk/doc/pcre2.txt
===================================================================
--- code/trunk/doc/pcre2.txt 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2.txt 2017-04-11 11:47:25 UTC (rev 739)
@@ -283,6 +283,9 @@
int pcre2_set_offset_limit(pcre2_match_context *mcontext,
PCRE2_SIZE value);
+ int pcre2_set_heap_limit(pcre2_match_context *mcontext,
+ uint32_t value);
+
int pcre2_set_match_limit(pcre2_match_context *mcontext,
uint32_t value);
@@ -840,6 +843,7 @@
Set up a callout function
Set an offset limit for matching an unanchored pattern
+ Change the limit on the amount of heap used when matching
Change the backtracking match limit
Change the backtracking depth limit
Set custom memory management specifically for the match
@@ -896,67 +900,101 @@
also within the offset limit. In other words, whichever limit comes
first is used.
+ int pcre2_set_heap_limit(pcre2_match_context *mcontext,
+ uint32_t value);
+
+ The heap_limit parameter specifies, in units of kilobytes, the maximum
+ amount of heap memory that pcre2_match() may use to hold backtracking
+ information when running an interpretive match. This limit does not
+ apply to matching with the JIT optimization, which has its own memory
+ control arrangements (see the pcre2jit documentation for more details),
+ nor does it apply to pcre2_dfa_match(). If the limit is reached, the
+ negative error code PCRE2_ERROR_HEAPLIMIT is returned. The default
+ limit is set when PCRE2 is built; the default default is very large and
+ is essentially "unlimited".
+
+ A value for the heap limit may also be supplied by an item at the start
+ of a pattern of the form
+
+ (*LIMIT_HEAP=ddd)
+
+ where ddd is a decimal number. However, such a setting is ignored
+ unless ddd is less than the limit set by the caller of pcre2_match()
+ or, if no such limit is set, less than the default.
+
+ The pcre2_match() function starts out using a 20K vector on the system
+ stack for recording backtracking points. The more nested backtracking
+ points there are (that is, the deeper the search tree), the more memory
+ is needed. Heap memory is used only if the initial vector is too
+ small. If the heap limit is set to a value less than 21 (in particular,
+ zero) no heap memory will be used. In this case, only patterns that do
+ not have a lot of nested backtracking can be successfully processed.
+
int pcre2_set_match_limit(pcre2_match_context *mcontext,
uint32_t value);
- The match_limit parameter provides a means of preventing PCRE2 from
- using up too many resources when processing patterns that are not going
- to match, but which have a very large number of possibilities in their
- search trees. The classic example is a pattern that uses nested unlim-
- ited repeats.
+ The match_limit parameter provides a means of preventing PCRE2 from
+ using up too many computing resources when processing patterns that are
+ not going to match, but which have a very large number of possibilities
+ in their search trees. The classic example is a pattern that uses
+ nested unlimited repeats.
- There is an internal counter in pcre2_match() that is incremented each
- time round its main matching loop. If this value reaches the match
+ There is an internal counter in pcre2_match() that is incremented each
+ time round its main matching loop. If this value reaches the match
limit, pcre2_match() returns the negative value PCRE2_ERROR_MATCHLIMIT.
- This has the effect of limiting the amount of backtracking that can
+ This has the effect of limiting the amount of backtracking that can
take place. For patterns that are not anchored, the count restarts from
- zero for each position in the subject string. This limit is not rele-
+ zero for each position in the subject string. This limit is not rele-
vant to pcre2_dfa_match(), which ignores it.
- When pcre2_match() is called with a pattern that was successfully pro-
+ When pcre2_match() is called with a pattern that was successfully pro-
cessed by pcre2_jit_compile(), the way in which matching is executed is
- entirely different. However, there is still the possibility of runaway
- matching that goes on for a very long time, and so the match_limit
- value is also used in this case (but in a different way) to limit how
+ entirely different. However, there is still the possibility of runaway
+ matching that goes on for a very long time, and so the match_limit
+ value is also used in this case (but in a different way) to limit how
long the matching can continue.
- The default value for the limit can be set when PCRE2 is built; the
- default default is 10 million, which handles all but the most extreme
- cases. A value for the match limit may also be supplied by an item at
+ The default value for the limit can be set when PCRE2 is built; the
+ default default is 10 million, which handles all but the most extreme
+ cases. A value for the match limit may also be supplied by an item at
the start of a pattern of the form
(*LIMIT_MATCH=ddd)
- where ddd is a decimal number. However, such a setting is ignored
- unless ddd is less than the limit set by the caller of pcre2_match()
+ where ddd is a decimal number. However, such a setting is ignored
+ unless ddd is less than the limit set by the caller of pcre2_match()
or, if no such limit is set, less than the default.
int pcre2_set_depth_limit(pcre2_match_context *mcontext,
uint32_t value);
- This parameter limits the depth of nested backtracking in
- pcre2_match(). Each time a nested backtracking point is passed, a new
+ This parameter limits the depth of nested backtracking in
+ pcre2_match(). Each time a nested backtracking point is passed, a new
memory "frame" is used to remember the state of matching at that point.
- Thus, this parameter indirectly limits the amount of memory that is
- used in a match.
+ Thus, this parameter indirectly limits the amount of memory that is
+ used in a match. However, because the size of each memory "frame"
+ depends on the number of capturing parentheses, the actual memory limit
+ varies from pattern to pattern. This limit was more useful in versions
+ before 10.30, where function recursion was used for backtracking.
- This limit is not relevant, and is ignored, when matching is done using
- JIT compiled code. However, it is supported by pcre2_dfa_match(), which
- uses it to limit the depth of internal recursive function calls that
- implement lookaround assertions and pattern recursions. This is, there-
- fore, an indirect limit on the amount of system stack that is used. A
- recursive pattern such as /(.)(?1)/, when matched to a very long string
- using pcre2_dfa_match(), can use a great deal of stack.
+ The depth limit is not relevant, and is ignored, when matching is done
+ using JIT compiled code. However, it is supported by pcre2_dfa_match(),
+ which uses it to limit the depth of internal recursive function calls
+ that implement atomic groups, lookaround assertions, and pattern recur-
+ sions. This is, therefore, an indirect limit on the amount of system
+ stack that is used. A recursive pattern such as /(.)(?1)/, when matched
+ to a very long string using pcre2_dfa_match(), can use a great deal of
+ stack.
- The default value for the depth limit can be set when PCRE2 is built;
- the default default is the same value as the default for the match
- limit. If the limit is exceeded, pcre2_match() or pcre2_dfa_match()
+ The default value for the depth limit can be set when PCRE2 is built;
+ the default default is the same value as the default for the match
+ limit. If the limit is exceeded, pcre2_match() or pcre2_dfa_match()
returns PCRE2_ERROR_DEPTHLIMIT. A value for the depth limit may also be
supplied by an item at the start of a pattern of the form
(*LIMIT_DEPTH=ddd)
- where ddd is a decimal number. However, such a setting is ignored
+ where ddd is a decimal number. However, such a setting is ignored
unless ddd is less than the limit set by the caller of pcre2_match() or
pcre2_dfa_match() or, if no such limit is set, less than the default.
@@ -965,82 +1003,88 @@
int pcre2_config(uint32_t what, void *where);
- The function pcre2_config() makes it possible for a PCRE2 client to
- discover which optional features have been compiled into the PCRE2
- library. The pcre2build documentation has more details about these
+ The function pcre2_config() makes it possible for a PCRE2 client to
+ discover which optional features have been compiled into the PCRE2
+ library. The pcre2build documentation has more details about these
optional features.
- The first argument for pcre2_config() specifies which information is
- required. The second argument is a pointer to memory into which the
- information is placed. If NULL is passed, the function returns the
- amount of memory that is needed for the requested information. For
- calls that return numerical values, the value is in bytes; when
- requesting these values, where should point to appropriately aligned
- memory. For calls that return strings, the required length is given in
+ The first argument for pcre2_config() specifies which information is
+ required. The second argument is a pointer to memory into which the
+ information is placed. If NULL is passed, the function returns the
+ amount of memory that is needed for the requested information. For
+ calls that return numerical values, the value is in bytes; when
+ requesting these values, where should point to appropriately aligned
+ memory. For calls that return strings, the required length is given in
code units, not counting the terminating zero.
- When requesting information, the returned value from pcre2_config() is
- non-negative on success, or the negative error code PCRE2_ERROR_BADOP-
- TION if the value in the first argument is not recognized. The follow-
+ When requesting information, the returned value from pcre2_config() is
+ non-negative on success, or the negative error code PCRE2_ERROR_BADOP-
+ TION if the value in the first argument is not recognized. The follow-
ing information is available:
PCRE2_CONFIG_BSR
- The output is a uint32_t integer whose value indicates what character
- sequences the \R escape sequence matches by default. A value of
+ The output is a uint32_t integer whose value indicates what character
+ sequences the \R escape sequence matches by default. A value of
PCRE2_BSR_UNICODE means that \R matches any Unicode line ending
- sequence; a value of PCRE2_BSR_ANYCRLF means that \R matches only CR,
+ sequence; a value of PCRE2_BSR_ANYCRLF means that \R matches only CR,
LF, or CRLF. The default can be overridden when a pattern is compiled.
PCRE2_CONFIG_DEPTHLIMIT
- The output is a uint32_t integer that gives the default limit for the
- depth of nested backtracking in pcre2_match() or the depth of nested
- recursions and lookarounds in pcre2_dfa_match(). Further details are
+ The output is a uint32_t integer that gives the default limit for the
+ depth of nested backtracking in pcre2_match() or the depth of nested
+ recursions and lookarounds in pcre2_dfa_match(). Further details are
given with pcre2_set_depth_limit() above.
+ PCRE2_CONFIG_HEAPLIMIT
+
+ The output is a uint32_t integer that gives, in kilobytes, the default
+ limit for the amount of heap memory used by pcre2_match(). Further
+ details are given with pcre2_set_heap_limit() above.
+
PCRE2_CONFIG_JIT
- The output is a uint32_t integer that is set to one if support for
+ The output is a uint32_t integer that is set to one if support for
just-in-time compiling is available; otherwise it is set to zero.
PCRE2_CONFIG_JITTARGET
- The where argument should point to a buffer that is at least 48 code
- units long. (The exact length required can be found by calling
- pcre2_config() with where set to NULL.) The buffer is filled with a
- string that contains the name of the architecture for which the JIT
- compiler is configured, for example "x86 32bit (little endian +
- unaligned)". If JIT support is not available, PCRE2_ERROR_BADOPTION is
- returned, otherwise the number of code units used is returned. This is
+ The where argument should point to a buffer that is at least 48 code
+ units long. (The exact length required can be found by calling
+ pcre2_config() with where set to NULL.) The buffer is filled with a
+ string that contains the name of the architecture for which the JIT
+ compiler is configured, for example "x86 32bit (little endian +
+ unaligned)". If JIT support is not available, PCRE2_ERROR_BADOPTION is
+ returned, otherwise the number of code units used is returned. This is
the length of the string, plus one unit for the terminating zero.
PCRE2_CONFIG_LINKSIZE
The output is a uint32_t integer that contains the number of bytes used
- for internal linkage in compiled regular expressions. When PCRE2 is
- configured, the value can be set to 2, 3, or 4, with the default being
- 2. This is the value that is returned by pcre2_config(). However, when
- the 16-bit library is compiled, a value of 3 is rounded up to 4, and
- when the 32-bit library is compiled, internal linkages always use 4
+ for internal linkage in compiled regular expressions. When PCRE2 is
+ configured, the value can be set to 2, 3, or 4, with the default being
+ 2. This is the value that is returned by pcre2_config(). However, when
+ the 16-bit library is compiled, a value of 3 is rounded up to 4, and
+ when the 32-bit library is compiled, internal linkages always use 4
bytes, so the configured value is not relevant.
The default value of 2 for the 8-bit and 16-bit libraries is sufficient
- for all but the most massive patterns, since it allows the size of the
+ for all but the most massive patterns, since it allows the size of the
compiled pattern to be up to 64K code units. Larger values allow larger
- regular expressions to be compiled by those two libraries, but at the
+ regular expressions to be compiled by those two libraries, but at the
expense of slower matching.
PCRE2_CONFIG_MATCHLIMIT
The output is a uint32_t integer that gives the default match limit for
- pcre2_match(). Further details are given with pcre2_set_match_limit()
+ pcre2_match(). Further details are given with pcre2_set_match_limit()
above.
PCRE2_CONFIG_NEWLINE
- The output is a uint32_t integer whose value specifies the default
- character sequence that is recognized as meaning "newline". The values
+ The output is a uint32_t integer whose value specifies the default
+ character sequence that is recognized as meaning "newline". The values
are:
PCRE2_NEWLINE_CR Carriage return (CR)
@@ -1049,17 +1093,17 @@
PCRE2_NEWLINE_ANY Any Unicode line ending
PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF
- The default should normally correspond to the standard sequence for
+ The default should normally correspond to the standard sequence for
your operating system.
PCRE2_CONFIG_PARENSLIMIT
- The output is a uint32_t integer that gives the maximum depth of nest-
+ The output is a uint32_t integer that gives the maximum depth of nest-
ing of parentheses (of any kind) in a pattern. This limit is imposed to
- cap the amount of system stack used when a pattern is compiled. It is
- specified when PCRE2 is built; the default is 250. This limit does not
- take into account the stack that may already be used by the calling
- application. For finer control over compilation stack usage, see
+ cap the amount of system stack used when a pattern is compiled. It is
+ specified when PCRE2 is built; the default is 250. This limit does not
+ take into account the stack that may already be used by the calling
+ application. For finer control over compilation stack usage, see
pcre2_set_compile_recursion_guard().
PCRE2_CONFIG_STACKRECURSE
@@ -1069,25 +1113,25 @@
PCRE2_CONFIG_UNICODE_VERSION
- The where argument should point to a buffer that is at least 24 code
- units long. (The exact length required can be found by calling
- pcre2_config() with where set to NULL.) If PCRE2 has been compiled
- without Unicode support, the buffer is filled with the text "Unicode
- not supported". Otherwise, the Unicode version string (for example,
- "8.0.0") is inserted. The number of code units used is returned. This
+ The where argument should point to a buffer that is at least 24 code
+ units long. (The exact length required can be found by calling
+ pcre2_config() with where set to NULL.) If PCRE2 has been compiled
+ without Unicode support, the buffer is filled with the text "Unicode
+ not supported". Otherwise, the Unicode version string (for example,
+ "8.0.0") is inserted. The number of code units used is returned. This
is the length of the string plus one unit for the terminating zero.
PCRE2_CONFIG_UNICODE
- The output is a uint32_t integer that is set to one if Unicode support
- is available; otherwise it is set to zero. Unicode support implies UTF
+ The output is a uint32_t integer that is set to one if Unicode support
+ is available; otherwise it is set to zero. Unicode support implies UTF
support.
PCRE2_CONFIG_VERSION
- The where argument should point to a buffer that is at least 24 code
- units long. (The exact length required can be found by calling
- pcre2_config() with where set to NULL.) The buffer is filled with the
+ The where argument should point to a buffer that is at least 24 code
+ units long. (The exact length required can be found by calling
+ pcre2_config() with where set to NULL.) The buffer is filled with the
PCRE2 version string, zero-terminated. The number of code units used is
returned. This is the length of the string plus one unit for the termi-
nating zero.
@@ -1105,90 +1149,90 @@
pcre2_code *pcre2_code_copy_with_tables(const pcre2_code *code);
- The pcre2_compile() function compiles a pattern into an internal form.
- The pattern is defined by a pointer to a string of code units and a
- length. If the pattern is zero-terminated, the length can be specified
- as PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of
- memory that contains the compiled pattern and related data, or NULL if
+ The pcre2_compile() function compiles a pattern into an internal form.
+ The pattern is defined by a pointer to a string of code units and a
+ length. If the pattern is zero-terminated, the length can be specified
+ as PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of
+ memory that contains the compiled pattern and related data, or NULL if
an error occurred.
- If the compile context argument ccontext is NULL, memory for the com-
- piled pattern is obtained by calling malloc(). Otherwise, it is
- obtained from the same memory function that was used for the compile
- context. The caller must free the memory by calling pcre2_code_free()
+ If the compile context argument ccontext is NULL, memory for the com-
+ piled pattern is obtained by calling malloc(). Otherwise, it is
+ obtained from the same memory function that was used for the compile
+ context. The caller must free the memory by calling pcre2_code_free()
when it is no longer needed.
The function pcre2_code_copy() makes a copy of the compiled code in new
- memory, using the same memory allocator as was used for the original.
- However, if the code has been processed by the JIT compiler (see
- below), the JIT information cannot be copied (because it is position-
+ memory, using the same memory allocator as was used for the original.
+ However, if the code has been processed by the JIT compiler (see
+ below), the JIT information cannot be copied (because it is position-
dependent). The new copy can initially be used only for non-JIT match-
ing, though it can be passed to pcre2_jit_compile() if required.
The pcre2_code_copy() function provides a way for individual threads in
- a multithreaded application to acquire a private copy of shared com-
- piled code. However, it does not make a copy of the character tables
- used by the compiled pattern; the new pattern code points to the same
- tables as the original code. (See "Locale Support" below for details
- of these character tables.) In many applications the same tables are
- used throughout, so this behaviour is appropriate. Nevertheless, there
+ a multithreaded application to acquire a private copy of shared com-
+ piled code. However, it does not make a copy of the character tables
+ used by the compiled pattern; the new pattern code points to the same
+ tables as the original code. (See "Locale Support" below for details
+ of these character tables.) In many applications the same tables are
+ used throughout, so this behaviour is appropriate. Nevertheless, there
are occasions when a copy of a compiled pattern and the relevant tables
- are needed. The pcre2_code_copy_with_tables() provides this facility.
- Copies of both the code and the tables are made, with the new code
- pointing to the new tables. The memory for the new tables is automati-
- cally freed when pcre2_code_free() is called for the new copy of the
+ are needed. The pcre2_code_copy_with_tables() provides this facility.
+ Copies of both the code and the tables are made, with the new code
+ pointing to the new tables. The memory for the new tables is automati-
+ cally freed when pcre2_code_free() is called for the new copy of the
compiled code.
- NOTE: When one of the matching functions is called, pointers to the
+ NOTE: When one of the matching functions is called, pointers to the
compiled pattern and the subject string are set in the match data block
- so that they can be referenced by the substring extraction functions.
- After running a match, you must not free a compiled pattern (or a sub-
- ject string) until after all operations on the match data block have
+ so that they can be referenced by the substring extraction functions.
+ After running a match, you must not free a compiled pattern (or a sub-
+ ject string) until after all operations on the match data block have
taken place.
- The options argument for pcre2_compile() contains various bit settings
- that affect the compilation. It should be zero if no options are
- required. The available options are described below. Some of them (in
- particular, those that are compatible with Perl, but some others as
- well) can also be set and unset from within the pattern (see the
+ The options argument for pcre2_compile() contains various bit settings
+ that affect the compilation. It should be zero if no options are
+ required. The available options are described below. Some of them (in
+ particular, those that are compatible with Perl, but some others as
+ well) can also be set and unset from within the pattern (see the
detailed description in the pcre2pattern documentation).
- 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, PCRE2_ENDANCHORED, and
- PCRE2_NO_UTF_CHECK options can be set at the time of matching as well
+ 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, 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;
@@ -1202,28 +1246,28 @@
&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-
@@ -1230,13 +1274,13 @@
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).
@@ -1243,55 +1287,55 @@
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.
@@ -1298,188 +1342,188 @@
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,
+ 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
- totally ignored except when escaped or inside a character class. How-
- ever, white space is not allowed within sequences such as (?> that
+ If this bit is set, most white space characters in the pattern are
+ totally ignored except when escaped or inside a character class. How-
+ ever, white space is not allowed within sequences such as (?> that
introduce various parenthesized subpatterns, nor within numerical quan-
- tifiers such as {1,3}. Ignorable white space is permitted between an
- item and a following quantifier and between a quantifier and a follow-
+ tifiers such as {1,3}. Ignorable white space is permitted between an
+ item and a following quantifier and between a quantifier and a follow-
ing + that indicates possessiveness.
- PCRE2_EXTENDED also causes characters between an unescaped # outside a
- character class and the next newline, inclusive, to be ignored, which
+ PCRE2_EXTENDED also causes characters between an unescaped # outside a
+ character class and the next newline, inclusive, to be ignored, which
makes it possible to include comments inside complicated patterns. Note
- that the end of this type of comment is a literal newline sequence in
+ that the end of this type of comment is a literal newline sequence in
the pattern; escape sequences that happen to represent a newline do not
- count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be
+ count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be
changed within a pattern by a (?x) option setting.
Which characters are interpreted as newlines can be specified by a set-
- ting in the compile context that is passed to pcre2_compile() or by a
- special sequence at the start of the pattern, as described in the sec-
- tion entitled "Newline conventions" in the pcre2pattern documentation.
+ ting in the compile context that is passed to pcre2_compile() or by a
+ special sequence at the start of the pattern, as described in the sec-
+ tion entitled "Newline conventions" in the pcre2pattern documentation.
A default is defined when PCRE2 is built.
PCRE2_FIRSTLINE
- If this option is set, an unanchored pattern is required to match
- before or at the first newline in the subject string, though the
- matched text may continue over the newline. See also PCRE2_USE_OFF-
- SET_LIMIT, which provides a more general limiting facility. If
- PCRE2_FIRSTLINE is set with an offset limit, a match must occur in the
- first line and also within the offset limit. In other words, whichever
+ If this option is set, an unanchored pattern is required to match
+ before or at the first newline in the subject string, though the
+ matched text may continue over the newline. See also PCRE2_USE_OFF-
+ SET_LIMIT, which provides a more general limiting facility. If
+ PCRE2_FIRSTLINE is set with an offset limit, a match must occur in the
+ first line and also within the offset limit. In other words, whichever
limit comes first is used.
PCRE2_MATCH_UNSET_BACKREF
- If this option is set, a back reference to an unset subpattern group
- matches an empty string (by default this causes the current matching
- alternative to fail). A pattern such as (\1)(a) succeeds when this
- option is set (assuming it can find an "a" in the subject), whereas it
- fails by default, for Perl compatibility. Setting this option makes
+ If this option is set, a back reference to an unset subpattern group
+ matches an empty string (by default this causes the current matching
+ alternative to fail). A pattern such as (\1)(a) succeeds when this
+ option is set (assuming it can find an "a" in the subject), whereas it
+ fails by default, for Perl compatibility. Setting this option makes
PCRE2 behave more like ECMAscript (aka JavaScript).
PCRE2_MULTILINE
- By default, for the purposes of matching "start of line" and "end of
- line", PCRE2 treats the subject string as consisting of a single line
- of characters, even if it actually contains newlines. The "start of
- line" metacharacter (^) matches only at the start of the string, and
- the "end of line" metacharacter ($) matches only at the end of the
+ By default, for the purposes of matching "start of line" and "end of
+ line", PCRE2 treats the subject string as consisting of a single line
+ of characters, even if it actually contains newlines. The "start of
+ line" metacharacter (^) matches only at the start of the string, and
+ the "end of line" metacharacter ($) matches only at the end of the
string, or before a terminating newline (except when PCRE2_DOL-
- LAR_ENDONLY is set). Note, however, that unless PCRE2_DOTALL is set,
+ LAR_ENDONLY is set). Note, however, that unless PCRE2_DOTALL is set,
the "any character" metacharacter (.) does not match at a newline. This
behaviour (for ^, $, and dot) is the same as Perl.
- When PCRE2_MULTILINE it is set, the "start of line" and "end of line"
- constructs match immediately following or immediately before internal
- newlines in the subject string, respectively, as well as at the very
- start and end. This is equivalent to Perl's /m option, and it can be
+ When PCRE2_MULTILINE it is set, the "start of line" and "end of line"
+ constructs match immediately following or immediately before internal
+ newlines in the subject string, respectively, as well as at the very
+ start and end. This is equivalent to Perl's /m option, and it can be
changed within a pattern by a (?m) option setting. Note that the "start
of line" metacharacter does not match after a newline at the end of the
- subject, for compatibility with Perl. However, you can change this by
- setting the PCRE2_ALT_CIRCUMFLEX option. If there are no newlines in a
- subject string, or no occurrences of ^ or $ in a pattern, setting
+ subject, for compatibility with Perl. However, you can change this by
+ setting the PCRE2_ALT_CIRCUMFLEX option. If there are no newlines in a
+ subject string, or no occurrences of ^ or $ in a pattern, setting
PCRE2_MULTILINE has no effect.
PCRE2_NEVER_BACKSLASH_C
- This option locks out the use of \C in the pattern that is being com-
- piled. This escape can cause unpredictable behaviour in UTF-8 or
- UTF-16 modes, because it may leave the current matching point in the
- middle of a multi-code-unit character. This option may be useful in
- applications that process patterns from external sources. Note that
+ This option locks out the use of \C in the pattern that is being com-
+ piled. This escape can cause unpredictable behaviour in UTF-8 or
+ UTF-16 modes, because it may leave the current matching point in the
+ middle of a multi-code-unit character. This option may be useful in
+ applications that process patterns from external sources. Note that
there is also a build-time option that permanently locks out the use of
\C.
PCRE2_NEVER_UCP
- This option locks out the use of Unicode properties for handling \B,
+ This option locks out the use of Unicode properties for handling \B,
\b, \D, \d, \S, \s, \W, \w, and some of the POSIX character classes, as
- described for the PCRE2_UCP option below. In particular, it prevents
- the creator of the pattern from enabling this facility by starting the
- pattern with (*UCP). This option may be useful in applications that
+ described for the PCRE2_UCP option below. In particular, it prevents
+ the creator of the pattern from enabling this facility by starting the
+ pattern with (*UCP). This option may be useful in applications that
process patterns from external sources. The option combination PCRE_UCP
and PCRE_NEVER_UCP causes an error.
PCRE2_NEVER_UTF
- This option locks out interpretation of the pattern as UTF-8, UTF-16,
+ This option locks out interpretation of the pattern as UTF-8, UTF-16,
or UTF-32, depending on which library is in use. In particular, it pre-
- vents the creator of the pattern from switching to UTF interpretation
- by starting the pattern with (*UTF). This option may be useful in
- applications that process patterns from external sources. The combina-
+ vents the creator of the pattern from switching to UTF interpretation
+ by starting the pattern with (*UTF). This option may be useful in
+ applications that process patterns from external sources. The combina-
tion of PCRE2_UTF and PCRE2_NEVER_UTF causes an error.
PCRE2_NO_AUTO_CAPTURE
If this option is set, it disables the use of numbered capturing paren-
- theses in the pattern. Any opening parenthesis that is not followed by
- ? behaves as if it were followed by ?: but named parentheses can still
- be used for capturing (and they acquire numbers in the usual way).
- There is no equivalent of this option in Perl. Note that, if this
- option is set, references to capturing groups (back references or
- recursion/subroutine calls) may only refer to named groups, though the
+ theses in the pattern. Any opening parenthesis that is not followed by
+ ? behaves as if it were followed by ?: but named parentheses can still
+ be used for capturing (and they acquire numbers in the usual way).
+ There is no equivalent of this option in Perl. Note that, if this
+ option is set, references to capturing groups (back references or
+ recursion/subroutine calls) may only refer to named groups, though the
reference can be by name or by number.
PCRE2_NO_AUTO_POSSESS
If this option is set, it disables "auto-possessification", which is an
- optimization that, for example, turns a+b into a++b in order to avoid
- backtracks into a+ that can never be successful. However, if callouts
- are in use, auto-possessification means that some callouts are never
+ optimization that, for example, turns a+b into a++b in order to avoid
+ backtracks into a+ that can never be successful. However, if callouts
+ are in use, auto-possessification means that some callouts are never
taken. You can set this option if you want the matching functions to do
- a full unoptimized search and run all the callouts, but it is mainly
+ a full unoptimized search and run all the callouts, but it is mainly
provided for testing purposes.
PCRE2_NO_DOTSTAR_ANCHOR
If this option is set, it disables an optimization that is applied when
- .* is the first significant item in a top-level branch of a pattern,
- and all the other branches also start with .* or with \A or \G or ^.
- The optimization is automatically disabled for .* if it is inside an
- atomic group or a capturing group that is the subject of a back refer-
- ence, or if the pattern contains (*PRUNE) or (*SKIP). When the opti-
- mization is not disabled, such a pattern is automatically anchored if
+ .* is the first significant item in a top-level branch of a pattern,
+ and all the other branches also start with .* or with \A or \G or ^.
+ The optimization is automatically disabled for .* if it is inside an
+ atomic group or a capturing group that is the subject of a back refer-
+ ence, or if the pattern contains (*PRUNE) or (*SKIP). When the opti-
+ mization is not disabled, such a pattern is automatically anchored if
PCRE2_DOTALL is set for all the .* items and PCRE2_MULTILINE is not set
- for any ^ items. Otherwise, the fact that any match must start either
- at the start of the subject or following a newline is remembered. Like
+ for any ^ items. Otherwise, the fact that any match must start either
+ at the start of the subject or following a newline is remembered. Like
other optimizations, this can cause callouts to be skipped.
PCRE2_NO_START_OPTIMIZE
- This is an option whose main effect is at matching time. It does not
+ This is an option whose main effect is at matching time. It does not
change what pcre2_compile() generates, but it does affect the output of
the JIT compiler.
- There are a number of optimizations that may occur at the start of a
- match, in order to speed up the process. For example, if it is known
- that an unanchored match must start with a specific character, the
- matching code searches the subject for that character, and fails imme-
- diately if it cannot find it, without actually running the main match-
- ing function. This means that a special item such as (*COMMIT) at the
- start of a pattern is not considered until after a suitable starting
- point for the match has been found. Also, when callouts or (*MARK)
- items are in use, these "start-up" optimizations can cause them to be
- skipped if the pattern is never actually used. The start-up optimiza-
- tions are in effect a pre-scan of the subject that takes place before
+ There are a number of optimizations that may occur at the start of a
+ match, in order to speed up the process. For example, if it is known
+ that an unanchored match must start with a specific character, the
+ matching code searches the subject for that character, and fails imme-
+ diately if it cannot find it, without actually running the main match-
+ ing function. This means that a special item such as (*COMMIT) at the
+ start of a pattern is not considered until after a suitable starting
+ point for the match has been found. Also, when callouts or (*MARK)
+ items are in use, these "start-up" optimizations can cause them to be
+ skipped if the pattern is never actually used. The start-up optimiza-
+ tions are in effect a pre-scan of the subject that takes place before
the pattern is run.
The PCRE2_NO_START_OPTIMIZE option disables the start-up optimizations,
- possibly causing performance to suffer, but ensuring that in cases
- where the result is "no match", the callouts do occur, and that items
+ possibly causing performance to suffer, but ensuring that in cases
+ where the result is "no match", the callouts do occur, and that items
such as (*COMMIT) and (*MARK) are considered at every possible starting
position in the subject string.
- Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching
+ Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching
operation. Consider the pattern
(*COMMIT)ABC
- When this is compiled, PCRE2 records the fact that a match must start
- with the character "A". Suppose the subject string is "DEFABC". The
- start-up optimization scans along the subject, finds "A" and runs the
- first match attempt from there. The (*COMMIT) item means that the pat-
- tern must match the current starting position, which in this case, it
- does. However, if the same match is run with PCRE2_NO_START_OPTIMIZE
- set, the initial scan along the subject string does not happen. The
- first match attempt is run starting from "D" and when this fails,
- (*COMMIT) prevents any further matches being tried, so the overall
+ When this is compiled, PCRE2 records the fact that a match must start
+ with the character "A". Suppose the subject string is "DEFABC". The
+ start-up optimization scans along the subject, finds "A" and runs the
+ first match attempt from there. The (*COMMIT) item means that the pat-
+ tern must match the current starting position, which in this case, it
+ does. However, if the same match is run with PCRE2_NO_START_OPTIMIZE
+ set, the initial scan along the subject string does not happen. The
+ first match attempt is run starting from "D" and when this fails,
+ (*COMMIT) prevents any further matches being tried, so the overall
result is "no match". There are also other start-up optimizations. For
example, a minimum length for the subject may be recorded. Consider the
pattern
@@ -1486,75 +1530,75 @@
(*MARK:A)(X|Y)
- The minimum length for a match is one character. If the subject is
+ The minimum length for a match is one character. If the subject is
"ABC", there will be attempts to match "ABC", "BC", and "C". An attempt
to match an empty string at the end of the subject does not take place,
- because PCRE2 knows that the subject is now too short, and so the
- (*MARK) is never encountered. In this case, the optimization does not
+ because PCRE2 knows that the subject is now too short, and so the
+ (*MARK) is never encountered. In this case, the optimization does not
affect the overall match result, which is still "no match", but it does
affect the auxiliary information that is returned.
PCRE2_NO_UTF_CHECK
- When PCRE2_UTF is set, the validity of the pattern as a UTF string is
- automatically checked. There are discussions about the validity of
- UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode
- document. If an invalid UTF sequence is found, pcre2_compile() returns
+ When PCRE2_UTF is set, the validity of the pattern as a UTF string is
+ automatically checked. There are discussions about the validity of
+ UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode
+ document. If an invalid UTF sequence is found, pcre2_compile() returns
a negative error code.
If you know that your pattern is valid, and you want to skip this check
- for performance reasons, you can set the PCRE2_NO_UTF_CHECK option.
- When it is set, the effect of passing an invalid UTF string as a pat-
- tern is undefined. It may cause your program to crash or loop. Note
- that this option can also be passed to pcre2_match() and
+ for performance reasons, you can set the PCRE2_NO_UTF_CHECK option.
+ When it is set, the effect of passing an invalid UTF string as a pat-
+ tern is undefined. It may cause your program to crash or loop. Note
+ that this option can also be passed to pcre2_match() and
pcre_dfa_match(), to suppress validity checking of the subject string.
PCRE2_UCP
This option changes the way PCRE2 processes \B, \b, \D, \d, \S, \s, \W,
- \w, and some of the POSIX character classes. By default, only ASCII
- characters are recognized, but if PCRE2_UCP is set, Unicode properties
- are used instead to classify characters. More details are given in the
+ \w, and some of the POSIX character classes. By default, only ASCII
+ characters are recognized, but if PCRE2_UCP is set, Unicode properties
+ are used instead to classify characters. More details are given in the
section on generic character types in the pcre2pattern page. If you set
- PCRE2_UCP, matching one of the items it affects takes much longer. The
- option is available only if PCRE2 has been compiled with Unicode sup-
+ PCRE2_UCP, matching one of the items it affects takes much longer. The
+ option is available only if PCRE2 has been compiled with Unicode sup-
port (which is the default).
PCRE2_UNGREEDY
- This option inverts the "greediness" of the quantifiers so that they
- are not greedy by default, but become greedy if followed by "?". It is
- not compatible with Perl. It can also be set by a (?U) option setting
+ This option inverts the "greediness" of the quantifiers so that they
+ are not greedy by default, but become greedy if followed by "?". It is
+ not compatible with Perl. It can also be set by a (?U) option setting
within the pattern.
PCRE2_USE_OFFSET_LIMIT
This option must be set for pcre2_compile() if pcre2_set_offset_limit()
- is going to be used to set a non-default offset limit in a match con-
- text for matches that use this pattern. An error is generated if an
- offset limit is set without this option. For more details, see the
- description of pcre2_set_offset_limit() in the section that describes
+ is going to be used to set a non-default offset limit in a match con-
+ text for matches that use this pattern. An error is generated if an
+ offset limit is set without this option. For more details, see the
+ description of pcre2_set_offset_limit() in the section that describes
match contexts. See also the PCRE2_FIRSTLINE option above.
PCRE2_UTF
- This option causes PCRE2 to regard both the pattern and the subject
- strings that are subsequently processed as strings of UTF characters
- instead of single-code-unit strings. It is available when PCRE2 is
- built to include Unicode support (which is the default). If Unicode
- support is not available, the use of this option provokes an error.
- Details of how this option changes the behaviour of PCRE2 are given in
+ This option causes PCRE2 to regard both the pattern and the subject
+ strings that are subsequently processed as strings of UTF characters
+ instead of single-code-unit strings. It is available when PCRE2 is
+ built to include Unicode support (which is the default). If Unicode
+ support is not available, the use of this option provokes an error.
+ Details of how this option changes the behaviour of PCRE2 are given in
the pcre2unicode page.
COMPILATION ERROR CODES
- There are nearly 100 positive error codes that pcre2_compile() may
- return (via errorcode) if it finds an error in the pattern. There are
- also some negative error codes that are used for invalid UTF strings.
+ There are nearly 100 positive error codes that pcre2_compile() may
+ return (via errorcode) if it finds an error in the pattern. There are
+ also some negative error codes that are used for invalid UTF strings.
These are the same as given by pcre2_match() and pcre2_dfa_match(), and
- are described in the pcre2unicode page. The pcre2_get_error_message()
- function (see "Obtaining a textual error message" below) can be called
+ are described in the pcre2unicode page. The pcre2_get_error_message()
+ function (see "Obtaining a textual error message" below) can be called
to obtain a textual error message from any error code.
@@ -1577,53 +1621,53 @@
void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack);
- These functions provide support for JIT compilation, which, if the
- just-in-time compiler is available, further processes a compiled pat-
+ These functions provide support for JIT compilation, which, if the
+ just-in-time compiler is available, further processes a compiled pat-
tern into machine code that executes much faster than the pcre2_match()
- interpretive matching function. Full details are given in the pcre2jit
+ interpretive matching function. Full details are given in the pcre2jit
documentation.
- JIT compilation is a heavyweight optimization. It can take some time
- for patterns to be analyzed, and for one-off matches and simple pat-
- terns the benefit of faster execution might be offset by a much slower
- compilation time. Most (but not all) patterns can be optimized by the
+ JIT compilation is a heavyweight optimization. It can take some time
+ for patterns to be analyzed, and for one-off matches and simple pat-
+ terns the benefit of faster execution might be offset by a much slower
+ compilation time. Most (but not all) patterns can be optimized by the
JIT compiler.
LOCALE SUPPORT
- PCRE2 handles caseless matching, and determines whether characters are
- letters, digits, or whatever, by reference to a set of tables, indexed
- by character code point. This applies only to characters whose code
- points are less than 256. By default, higher-valued code points never
- match escapes such as \w or \d. However, if PCRE2 is built with Uni-
+ PCRE2 handles caseless matching, and determines whether characters are
+ letters, digits, or whatever, by reference to a set of tables, indexed
+ by character code point. This applies only to characters whose code
+ points are less than 256. By default, higher-valued code points never
+ match escapes such as \w or \d. However, if PCRE2 is built with Uni-
code support, all characters can be tested with \p and \P, or, alterna-
- tively, the PCRE2_UCP option can be set when a pattern is compiled;
- this causes \w and friends to use Unicode property support instead of
+ tively, the PCRE2_UCP option can be set when a pattern is compiled;
+ this causes \w and friends to use Unicode property support instead of
the built-in tables.
- The use of locales with Unicode is discouraged. If you are handling
- characters with code points greater than 128, you should either use
+ The use of locales with Unicode is discouraged. If you are handling
+ characters with code points greater than 128, you should either use
Unicode support, or use locales, but not try to mix the two.
- PCRE2 contains an internal set of character tables that are used by
- default. These are sufficient for many applications. Normally, the
+ PCRE2 contains an internal set of character tables that are used by
+ default. These are sufficient for many applications. Normally, the
internal tables recognize only ASCII characters. However, when PCRE2 is
built, it is possible to cause the internal tables to be rebuilt in the
default "C" locale of the local system, which may cause them to be dif-
ferent.
- The internal tables can be overridden by tables supplied by the appli-
- cation that calls PCRE2. These may be created in a different locale
- from the default. As more and more applications change to using Uni-
+ The internal tables can be overridden by tables supplied by the appli-
+ cation that calls PCRE2. These may be created in a different locale
+ from the default. As more and more applications change to using Uni-
code, the need for this locale support is expected to die away.
- External tables are built by calling the pcre2_maketables() function,
- in the relevant locale. The result can be passed to pcre2_compile() as
- often as necessary, by creating a compile context and calling
- pcre2_set_character_tables() to set the tables pointer therein. For
- example, to build and use tables that are appropriate for the French
- locale (where accented characters with values greater than 128 are
+ External tables are built by calling the pcre2_maketables() function,
+ in the relevant locale. The result can be passed to pcre2_compile() as
+ often as necessary, by creating a compile context and calling
+ pcre2_set_character_tables() to set the tables pointer therein. For
+ example, to build and use tables that are appropriate for the French
+ locale (where accented characters with values greater than 128 are
treated as letters), the following code could be used:
setlocale(LC_CTYPE, "fr_FR");
@@ -1632,15 +1676,15 @@
pcre2_set_character_tables(ccontext, tables);
re = pcre2_compile(..., ccontext);
- The locale name "fr_FR" is used on Linux and other Unix-like systems;
- if you are using Windows, the name for the French locale is "french".
- It is the caller's responsibility to ensure that the memory containing
+ The locale name "fr_FR" is used on Linux and other Unix-like systems;
+ if you are using Windows, the name for the French locale is "french".
+ It is the caller's responsibility to ensure that the memory containing
the tables remains available for as long as it is needed.
The pointer that is passed (via the compile context) to pcre2_compile()
- is saved with the compiled pattern, and the same tables are used by
- pcre2_match() and pcre_dfa_match(). Thus, for any single pattern, com-
- pilation and matching both happen in the same locale, but different
+ is saved with the compiled pattern, and the same tables are used by
+ pcre2_match() and pcre_dfa_match(). Thus, for any single pattern, com-
+ pilation and matching both happen in the same locale, but different
patterns can be processed in different locales.
@@ -1648,13 +1692,13 @@
int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where);
- The pcre2_pattern_info() function returns general information about a
+ The pcre2_pattern_info() function returns general information about a
compiled pattern. For information about callouts, see the next section.
- The first argument for pcre2_pattern_info() is a pointer to the com-
+ The first argument for pcre2_pattern_info() is a pointer to the com-
piled pattern. The second argument specifies which piece of information
- is required, and the third argument is a pointer to a variable to
- receive the data. If the third argument is NULL, the first argument is
- ignored, and the function returns the size in bytes of the variable
+ is required, and the third argument is a pointer to a variable to
+ receive the data. If the third argument is NULL, the first argument is
+ ignored, and the function returns the size in bytes of the variable
that is required for the information requested. Otherwise, the yield of
the function is zero for success, or one of the following negative num-
bers:
@@ -1664,9 +1708,9 @@
PCRE2_ERROR_BADOPTION the value of what was invalid
PCRE2_ERROR_UNSET the requested field is not set
- The "magic number" is placed at the start of each compiled pattern as
- an simple check against passing an arbitrary memory pointer. Here is a
- typical call of pcre2_pattern_info(), to obtain the length of the com-
+ The "magic number" is placed at the start of each compiled pattern as
+ an simple check against passing an arbitrary memory pointer. Here is a
+ typical call of pcre2_pattern_info(), to obtain the length of the com-
piled pattern:
int rc;
@@ -1683,19 +1727,19 @@
PCRE2_INFO_ARGOPTIONS
Return a copy of the pattern's options. The third argument should point
- to a uint32_t variable. PCRE2_INFO_ARGOPTIONS returns exactly the
- options that were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOP-
- TIONS returns the compile options as modified by any top-level (*XXX)
+ to a uint32_t variable. PCRE2_INFO_ARGOPTIONS returns exactly the
+ options that were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOP-
+ TIONS returns the compile options as modified by any top-level (*XXX)
option settings such as (*UTF) at the start of the pattern itself.
- For example, if the pattern /(*UTF)abc/ is compiled with the
- PCRE2_EXTENDED option, the result for PCRE2_INFO_ALLOPTIONS is
- PCRE2_EXTENDED and PCRE2_UTF. Option settings such as (?i) that can
- change within a pattern do not affect the result of PCRE2_INFO_ALLOP-
+ For example, if the pattern /(*UTF)abc/ is compiled with the
+ PCRE2_EXTENDED option, the result for PCRE2_INFO_ALLOPTIONS is
+ PCRE2_EXTENDED and PCRE2_UTF. Option settings such as (?i) that can
+ change within a pattern do not affect the result of PCRE2_INFO_ALLOP-
TIONS, even if they appear right at the start of the pattern. (This was
different in some earlier releases.)
- A pattern compiled without PCRE2_ANCHORED is automatically anchored by
+ A pattern compiled without PCRE2_ANCHORED is automatically anchored by
PCRE2 if the first significant item in every top-level branch is one of
the following:
@@ -1704,7 +1748,7 @@
\G always
.* sometimes - see below
- When .* is the first significant item, anchoring is possible only when
+ When .* is the first significant item, anchoring is possible only when
all the following are true:
.* is not in an atomic group
@@ -1714,18 +1758,18 @@
Neither (*PRUNE) nor (*SKIP) appears in the pattern
PCRE2_NO_DOTSTAR_ANCHOR is not set
- For patterns that are auto-anchored, the PCRE2_ANCHORED bit is set in
+ For patterns that are auto-anchored, the PCRE2_ANCHORED bit is set in
the options returned for PCRE2_INFO_ALLOPTIONS.
PCRE2_INFO_BACKREFMAX
- Return the number of the highest back reference in the pattern. The
- third argument should point to an uint32_t variable. Named subpatterns
- acquire numbers as well as names, and these count towards the highest
- back reference. Back references such as \4 or \g{12} match the cap-
- tured characters of the given group, but in addition, the check that a
+ Return the number of the highest back reference in the pattern. The
+ third argument should point to an uint32_t variable. Named subpatterns
+ acquire numbers as well as names, and these count towards the highest
+ back reference. Back references such as \4 or \g{12} match the cap-
+ tured characters of the given group, but in addition, the check that a
capturing group is set in a conditional subpattern such as (?(3)a|b) is
- also a back reference. Zero is returned if there are no back refer-
+ also a back reference. Zero is returned if there are no back refer-
ences.
PCRE2_INFO_BSR
@@ -1732,52 +1776,52 @@
The output is a uint32_t whose value indicates what character sequences
the \R escape sequence matches. A value of PCRE2_BSR_UNICODE means that
- \R matches any Unicode line ending sequence; a value of PCRE2_BSR_ANY-
+ \R matches any Unicode line ending sequence; a value of PCRE2_BSR_ANY-
CRLF means that \R matches only CR, LF, or CRLF.
PCRE2_INFO_CAPTURECOUNT
- Return the highest capturing subpattern number in the pattern. In pat-
+ Return the highest capturing subpattern number in the pattern. In pat-
terns where (?| is not used, this is also the total number of capturing
subpatterns. The third argument should point to an uint32_t variable.
PCRE2_INFO_DEPTHLIMIT
- If the pattern set a backtracking depth limit by including an item of
- the form (*LIMIT_DEPTH=nnnn) at the start, the value is returned. The
- third argument should point to an unsigned 32-bit integer. If no such
- value has been set, the call to pcre2_pattern_info() returns the error
+ If the pattern set a backtracking depth limit by including an item of
+ the form (*LIMIT_DEPTH=nnnn) at the start, the value is returned. The
+ third argument should point to an unsigned 32-bit integer. If no such
+ value has been set, the call to pcre2_pattern_info() returns the error
PCRE2_ERROR_UNSET.
PCRE2_INFO_FIRSTBITMAP
- In the absence of a single first code unit for a non-anchored pattern,
- pcre2_compile() may construct a 256-bit table that defines a fixed set
- of values for the first code unit in any match. For example, a pattern
- that starts with [abc] results in a table with three bits set. When
- code unit values greater than 255 are supported, the flag bit for 255
- means "any code unit of value 255 or above". If such a table was con-
- structed, a pointer to it is returned. Otherwise NULL is returned. The
+ In the absence of a single first code unit for a non-anchored pattern,
+ pcre2_compile() may construct a 256-bit table that defines a fixed set
+ of values for the first code unit in any match. For example, a pattern
+ that starts with [abc] results in a table with three bits set. When
+ code unit values greater than 255 are supported, the flag bit for 255
+ means "any code unit of value 255 or above". If such a table was con-
+ structed, a pointer to it is returned. Otherwise NULL is returned. The
third argument should point to an const uint8_t * variable.
PCRE2_INFO_FIRSTCODETYPE
Return information about the first code unit of any matched string, for
- a non-anchored pattern. The third argument should point to an uint32_t
- variable. If there is a fixed first value, for example, the letter "c"
+ a non-anchored pattern. The third argument should point to an uint32_t
+ variable. If there is a fixed first value, for example, the letter "c"
from a pattern such as (cat|cow|coyote), 1 is returned, and the charac-
- ter value can be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is
- no fixed first value, but it is known that a match can occur only at
- the start of the subject or following a newline in the subject, 2 is
+ ter value can be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is
+ no fixed first value, but it is known that a match can occur only at
+ the start of the subject or following a newline in the subject, 2 is
returned. Otherwise, and for anchored patterns, 0 is returned.
PCRE2_INFO_FIRSTCODEUNIT
- Return the value of the first code unit of any matched string in the
+ Return the value of the first code unit of any matched string in the
situation where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0.
- The third argument should point to an uint32_t variable. In the 8-bit
- library, the value is always less than 256. In the 16-bit library the
- value can be up to 0xffff. In the 32-bit library in UTF-32 mode the
+ The third argument should point to an uint32_t variable. In the 8-bit
+ library, the value is always less than 256. In the 16-bit library the
+ value can be up to 0xffff. In the 32-bit library in UTF-32 mode the
value can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32
mode.
@@ -1784,94 +1828,102 @@
PCRE2_INFO_FRAMESIZE
Return the size (in bytes) of the data frames that are used to remember
- backtracking positions when the pattern is processed by pcre2_match()
- without the use of JIT. The third argument should point to an size_t
+ backtracking positions when the pattern is processed by pcre2_match()
+ without the use of JIT. The third argument should point to an size_t
variable. The frame size depends on the number of capturing parentheses
- in the pattern. Each additional capturing group adds two PCRE2_SIZE
+ in the pattern. Each additional capturing group adds two PCRE2_SIZE
variables.
PCRE2_INFO_HASBACKSLASHC
- Return 1 if the pattern contains any instances of \C, otherwise 0. The
+ Return 1 if the pattern contains any instances of \C, otherwise 0. The
third argument should point to an uint32_t variable.
PCRE2_INFO_HASCRORLF
- Return 1 if the pattern contains any explicit matches for CR or LF
+ Return 1 if the pattern contains any explicit matches for CR or LF
characters, otherwise 0. The third argument should point to an uint32_t
- variable. An explicit match is either a literal CR or LF character, or
- \r or \n or one of the equivalent hexadecimal or octal escape
+ variable. An explicit match is either a literal CR or LF character, or
+ \r or \n or one of the equivalent hexadecimal or octal escape
sequences.
+ PCRE2_INFO_HEAPLIMIT
+
+ If the pattern set a heap memory limit by including an item of the form
+ (*LIMIT_HEAP=nnnn) at the start, the value is returned. The third argu-
+ ment should point to an unsigned 32-bit integer. If no such value has
+ been set, the call to pcre2_pattern_info() returns the error
+ PCRE2_ERROR_UNSET.
+
PCRE2_INFO_JCHANGED
- Return 1 if the (?J) or (?-J) option setting is used in the pattern,
- otherwise 0. The third argument should point to an uint32_t variable.
- (?J) and (?-J) set and unset the local PCRE2_DUPNAMES option, respec-
+ Return 1 if the (?J) or (?-J) option setting is used in the pattern,
+ otherwise 0. The third argument should point to an uint32_t variable.
+ (?J) and (?-J) set and unset the local PCRE2_DUPNAMES option, respec-
tively.
PCRE2_INFO_JITSIZE
- If the compiled pattern was successfully processed by pcre2_jit_com-
- pile(), return the size of the JIT compiled code, otherwise return
+ If the compiled pattern was successfully processed by pcre2_jit_com-
+ pile(), return the size of the JIT compiled code, otherwise return
zero. The third argument should point to a size_t variable.
PCRE2_INFO_LASTCODETYPE
- Returns 1 if there is a rightmost literal code unit that must exist in
- any matched string, other than at its start. The third argument should
- point to an uint32_t variable. If there is no such value, 0 is
- returned. When 1 is returned, the code unit value itself can be
- retrieved using PCRE2_INFO_LASTCODEUNIT. For anchored patterns, a last
- literal value is recorded only if it follows something of variable
- length. For example, for the pattern /^a\d+z\d+/ the returned value is
- 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/
+ Returns 1 if there is a rightmost literal code unit that must exist in
+ any matched string, other than at its start. The third argument should
+ point to an uint32_t variable. If there is no such value, 0 is
+ returned. When 1 is returned, the code unit value itself can be
+ retrieved using PCRE2_INFO_LASTCODEUNIT. For anchored patterns, a last
+ literal value is recorded only if it follows something of variable
+ length. For example, for the pattern /^a\d+z\d+/ the returned value is
+ 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/
the returned value is 0.
PCRE2_INFO_LASTCODEUNIT
- Return the value of the rightmost literal data unit that must exist in
- any matched string, other than at its start, if such a value has been
- recorded. The third argument should point to an uint32_t variable. If
+ Return the value of the rightmost literal data unit that must exist in
+ any matched string, other than at its start, if such a value has been
+ recorded. The third argument should point to an uint32_t variable. If
there is no such value, 0 is returned.
PCRE2_INFO_MATCHEMPTY
- Return 1 if the pattern might match an empty string, otherwise 0. The
- third argument should point to an uint32_t variable. When a pattern
+ Return 1 if the pattern might match an empty string, otherwise 0. The
+ third argument should point to an uint32_t variable. When a pattern
contains recursive subroutine calls it is not always possible to deter-
- mine whether or not it can match an empty string. PCRE2 takes a cau-
+ mine whether or not it can match an empty string. PCRE2 takes a cau-
tious approach and returns 1 in such cases.
PCRE2_INFO_MATCHLIMIT
- If the pattern set a match limit by including an item of the form
- (*LIMIT_MATCH=nnnn) at the start, the value is returned. The third
- argument should point to an unsigned 32-bit integer. If no such value
- has been set, the call to pcre2_pattern_info() returns the error
+ If the pattern set a match limit by including an item of the form
+ (*LIMIT_MATCH=nnnn) at the start, the value is returned. The third
+ argument should point to an unsigned 32-bit integer. If no such value
+ has been set, the call to pcre2_pattern_info() returns the error
PCRE2_ERROR_UNSET.
PCRE2_INFO_MAXLOOKBEHIND
Return the number of characters (not code units) in the longest lookbe-
- hind assertion in the pattern. The third argument should point to an
- unsigned 32-bit integer. This information is useful when doing multi-
- segment matching using the partial matching facilities. Note that the
+ hind assertion in the pattern. The third argument should point to an
+ unsigned 32-bit integer. This information is useful when doing multi-
+ segment matching using the partial matching facilities. Note that the
simple assertions \b and \B require a one-character lookbehind. \A also
- registers a one-character lookbehind, though it does not actually
- inspect the previous character. This is to ensure that at least one
- character from the old segment is retained when a new segment is pro-
+ registers a one-character lookbehind, though it does not actually
+ inspect the previous character. This is to ensure that at least one
+ character from the old segment is retained when a new segment is pro-
cessed. Otherwise, if there are no lookbehinds in the pattern, \A might
match incorrectly at the start of a new segment.
PCRE2_INFO_MINLENGTH
- If a minimum length for matching subject strings was computed, its
- value is returned. Otherwise the returned value is 0. The value is a
- number of characters, which in UTF mode may be different from the num-
- ber of code units. The third argument should point to an uint32_t
- variable. The value is a lower bound to the length of any matching
- string. There may not be any strings of that length that do actually
+ If a minimum length for matching subject strings was computed, its
+ value is returned. Otherwise the returned value is 0. The value is a
+ number of characters, which in UTF mode may be different from the num-
+ ber of code units. The third argument should point to an uint32_t
+ variable. The value is a lower bound to the length of any matching
+ string. There may not be any strings of that length that do actually
match, but every string that does match is at least that long.
PCRE2_INFO_NAMECOUNT
@@ -1879,50 +1931,50 @@
PCRE2_INFO_NAMETABLE
PCRE2 supports the use of named as well as numbered capturing parenthe-
- ses. The names are just an additional way of identifying the parenthe-
+ ses. The names are just an additional way of identifying the parenthe-
ses, which still acquire numbers. Several convenience functions such as
- pcre2_substring_get_byname() are provided for extracting captured sub-
- strings by name. It is also possible to extract the data directly, by
- first converting the name to a number in order to access the correct
- pointers in the output vector (described with pcre2_match() below). To
- do the conversion, you need to use the name-to-number map, which is
+ pcre2_substring_get_byname() are provided for extracting captured sub-
+ strings by name. It is also possible to extract the data directly, by
+ first converting the name to a number in order to access the correct
+ pointers in the output vector (described with pcre2_match() below). To
+ do the conversion, you need to use the name-to-number map, which is
described by these three values.
- The map consists of a number of fixed-size entries. PCRE2_INFO_NAME-
- COUNT gives the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives
- the size of each entry in code units; both of these return a uint32_t
+ The map consists of a number of fixed-size entries. PCRE2_INFO_NAME-
+ COUNT gives the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives
+ the size of each entry in code units; both of these return a uint32_t
value. The entry size depends on the length of the longest name.
PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table.
- This is a PCRE2_SPTR pointer to a block of code units. In the 8-bit
- library, the first two bytes of each entry are the number of the cap-
+ This is a PCRE2_SPTR pointer to a block of code units. In the 8-bit
+ library, the first two bytes of each entry are the number of the cap-
turing parenthesis, most significant byte first. In the 16-bit library,
- the pointer points to 16-bit code units, the first of which contains
- the parenthesis number. In the 32-bit library, the pointer points to
- 32-bit code units, the first of which contains the parenthesis number.
+ the pointer points to 16-bit code units, the first of which contains
+ the parenthesis number. In the 32-bit library, the pointer points to
+ 32-bit code units, the first of which contains the parenthesis number.
The rest of the entry is the corresponding name, zero terminated.
- The names are in alphabetical order. If (?| is used to create multiple
- groups with the same number, as described in the section on duplicate
- subpattern numbers in the pcre2pattern page, the groups may be given
- the same name, but there is only one entry in the table. Different
+ The names are in alphabetical order. If (?| is used to create multiple
+ groups with the same number, as described in the section on duplicate
+ subpattern numbers in the pcre2pattern page, the groups may be given
+ the same name, but there is only one entry in the table. Different
names for groups of the same number are not permitted.
- Duplicate names for subpatterns with different numbers are permitted,
- but only if PCRE2_DUPNAMES is set. They appear in the table in the
- order in which they were found in the pattern. In the absence of (?|
- this is the order of increasing number; when (?| is used this is not
+ Duplicate names for subpatterns with different numbers are permitted,
+ but only if PCRE2_DUPNAMES is set. They appear in the table in the
+ order in which they were found in the pattern. In the absence of (?|
+ this is the order of increasing number; when (?| is used this is not
necessarily the case because later subpatterns may have lower numbers.
- As a simple example of the name/number table, consider the following
- pattern after compilation by the 8-bit library (assume PCRE2_EXTENDED
+ As a simple example of the name/number table, consider the following
+ pattern after compilation by the 8-bit library (assume PCRE2_EXTENDED
is set, so white space - including newlines - is ignored):
(?<date> (?<year>(\d\d)?\d\d) -
(?<month>\d\d) - (?<day>\d\d) )
- There are four named subpatterns, so the table has four entries, and
- each entry in the table is eight bytes long. The table is as follows,
+ There are four named subpatterns, so the table has four entries, and
+ each entry in the table is eight bytes long. The table is as follows,
with non-printing bytes shows in hexadecimal, and undefined bytes shown
as ??:
@@ -1931,8 +1983,8 @@
00 04 m o n t h 00
00 02 y e a r 00 ??
- When writing code to extract data from named subpatterns using the
- name-to-number map, remember that the length of the entries is likely
+ When writing code to extract data from named subpatterns using the
+ name-to-number map, remember that the length of the entries is likely
to be different for each compiled pattern.
PCRE2_INFO_NEWLINE
@@ -1950,14 +2002,14 @@
PCRE2_INFO_SIZE
- Return the size of the compiled pattern in bytes (for all three
- libraries). The third argument should point to a size_t variable. This
- value includes the size of the general data block that precedes the
- code units of the compiled pattern itself. The value that is used when
- pcre2_compile() is getting memory in which to place the compiled pat-
- tern may be slightly larger than the value returned by this option,
- because there are cases where the code that calculates the size has to
- over-estimate. Processing a pattern with the JIT compiler does not
+ Return the size of the compiled pattern in bytes (for all three
+ libraries). The third argument should point to a size_t variable. This
+ value includes the size of the general data block that precedes the
+ code units of the compiled pattern itself. The value that is used when
+ pcre2_compile() is getting memory in which to place the compiled pat-
+ tern may be slightly larger than the value returned by this option,
+ because there are cases where the code that calculates the size has to
+ over-estimate. Processing a pattern with the JIT compiler does not
alter the value returned by this option.
@@ -1968,22 +2020,22 @@
void *user_data);
A script language that supports the use of string arguments in callouts
- might like to scan all the callouts in a pattern before running the
+ might like to scan all the callouts in a pattern before running the
match. This can be done by calling pcre2_callout_enumerate(). The first
- argument is a pointer to a compiled pattern, the second points to a
- callback function, and the third is arbitrary user data. The callback
- function is called for every callout in the pattern in the order in
+ argument is a pointer to a compiled pattern, the second points to a
+ callback function, and the third is arbitrary user data. The callback
+ function is called for every callout in the pattern in the order in
which they appear. Its first argument is a pointer to a callout enumer-
- ation block, and its second argument is the user_data value that was
- passed to pcre2_callout_enumerate(). The contents of the callout enu-
- meration block are described in the pcre2callout documentation, which
+ ation block, and its second argument is the user_data value that was
+ passed to pcre2_callout_enumerate(). The contents of the callout enu-
+ meration block are described in the pcre2callout documentation, which
also gives further details about callouts.
SERIALIZATION AND PRECOMPILING
- It is possible to save compiled patterns on disc or elsewhere, and
- reload them later, subject to a number of restrictions. The functions
+ It is possible to save compiled patterns on disc or elsewhere, and
+ reload them later, subject to a number of restrictions. The functions
whose names begin with pcre2_serialize_ are used for this purpose. They
are described in the pcre2serialize documentation.
@@ -1998,56 +2050,56 @@
void pcre2_match_data_free(pcre2_match_data *match_data);
- Information about a successful or unsuccessful match is placed in a
- match data block, which is an opaque structure that is accessed by
- function calls. In particular, the match data block contains a vector
- of offsets into the subject string that define the matched part of the
- subject and any substrings that were captured. This is known as the
+ Information about a successful or unsuccessful match is placed in a
+ match data block, which is an opaque structure that is accessed by
+ function calls. In particular, the match data block contains a vector
+ of offsets into the subject string that define the matched part of the
+ subject and any substrings that were captured. This is known as the
ovector.
- Before calling pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match()
+ Before calling pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match()
you must create a match data block by calling one of the creation func-
- tions above. For pcre2_match_data_create(), the first argument is the
- number of pairs of offsets in the ovector. One pair of offsets is
+ tions above. For pcre2_match_data_create(), the first argument is the
+ number of pairs of offsets in the ovector. One pair of offsets is
required to identify the string that matched the whole pattern, with an
- additional pair for each captured substring. For example, a value of 4
- creates enough space to record the matched portion of the subject plus
- three captured substrings. A minimum of at least 1 pair is imposed by
+ additional pair for each captured substring. For example, a value of 4
+ creates enough space to record the matched portion of the subject plus
+ three captured substrings. A minimum of at least 1 pair is imposed by
pcre2_match_data_create(), so it is always possible to return the over-
all matched string.
The second argument of pcre2_match_data_create() is a pointer to a gen-
- eral context, which can specify custom memory management for obtaining
+ eral context, which can specify custom memory management for obtaining
the memory for the match data block. If you are not using custom memory
management, pass NULL, which causes malloc() to be used.
- For pcre2_match_data_create_from_pattern(), the first argument is a
+ For pcre2_match_data_create_from_pattern(), the first argument is a
pointer to a compiled pattern. The ovector is created to be exactly the
right size to hold all the substrings a pattern might capture. The sec-
- ond argument is again a pointer to a general context, but in this case
+ ond argument is again a pointer to a general context, but in this case
if NULL is passed, the memory is obtained using the same allocator that
was used for the compiled pattern (custom or default).
- A match data block can be used many times, with the same or different
- compiled patterns. You can extract information from a match data block
+ A match data block can be used many times, with the same or different
+ compiled patterns. You can extract information from a match data block
after a match operation has finished, using functions that are
- described in the sections on matched strings and other match data
+ described in the sections on matched strings and other match data
below.
- When a call of pcre2_match() fails, valid data is available in the
- match block only when the error is PCRE2_ERROR_NOMATCH,
- PCRE2_ERROR_PARTIAL, or one of the error codes for an invalid UTF
+ When a call of pcre2_match() fails, valid data is available in the
+ match block only when the error is PCRE2_ERROR_NOMATCH,
+ PCRE2_ERROR_PARTIAL, or one of the error codes for an invalid UTF
string. Exactly what is available depends on the error, and is detailed
below.
- When one of the matching functions is called, pointers to the compiled
- pattern and the subject string are set in the match data block so that
- they can be referenced by the extraction functions. After running a
- match, you must not free a compiled pattern or a subject string until
- after all operations on the match data block (for that match) have
+ When one of the matching functions is called, pointers to the compiled
+ pattern and the subject string are set in the match data block so that
+ they can be referenced by the extraction functions. After running a
+ match, you must not free a compiled pattern or a subject string until
+ after all operations on the match data block (for that match) have
taken place.
- When a match data block itself is no longer needed, it should be freed
+ When a match data block itself is no longer needed, it should be freed
by calling pcre2_match_data_free().
@@ -2058,15 +2110,15 @@
uint32_t options, pcre2_match_data *match_data,
pcre2_match_context *mcontext);
- The function pcre2_match() is called to match a subject string against
- a compiled pattern, which is passed in the code argument. You can call
+ The function pcre2_match() is called to match a subject string against
+ a compiled pattern, which is passed in the code argument. You can call
pcre2_match() with the same code argument as many times as you like, in
- order to find multiple matches in the subject string or to match dif-
+ order to find multiple matches in the subject string or to match dif-
ferent subject strings with the same pattern.
- This function is the main matching facility of the library, and it
- operates in a Perl-like manner. For specialist use there is also an
- alternative matching function, which is described below in the section
+ This function is the main matching facility of the library, and it
+ operates in a Perl-like manner. For specialist use there is also an
+ alternative matching function, which is described below in the section
about the pcre2_dfa_match() function.
Here is an example of a simple call to pcre2_match():
@@ -2081,7 +2133,7 @@
match_data, /* the match data block */
NULL); /* a match context; NULL means use defaults */
- If the subject string is zero-terminated, the length can be given as
+ If the subject string is zero-terminated, the length can be given as
PCRE2_ZERO_TERMINATED. A match context must be provided if certain less
common matching parameters are to be changed. For details, see the sec-
tion on the match context above.
@@ -2088,92 +2140,92 @@
The string to be matched by pcre2_match()
- The subject string is passed to pcre2_match() as a pointer in subject,
- a length in length, and a starting offset in startoffset. The length
- and offset are in code units, not characters. That is, they are in
- bytes for the 8-bit library, 16-bit code units for the 16-bit library,
- and 32-bit code units for the 32-bit library, whether or not UTF pro-
+ The subject string is passed to pcre2_match() as a pointer in subject,
+ a length in length, and a starting offset in startoffset. The length
+ and offset are in code units, not characters. That is, they are in
+ bytes for the 8-bit library, 16-bit code units for the 16-bit library,
+ and 32-bit code units for the 32-bit library, whether or not UTF pro-
cessing is enabled.
If startoffset is greater than the length of the subject, pcre2_match()
- returns PCRE2_ERROR_BADOFFSET. When the starting offset is zero, the
- search for a match starts at the beginning of the subject, and this is
+ returns PCRE2_ERROR_BADOFFSET. When the starting offset is zero, the
+ search for a match starts at the beginning of the subject, and this is
by far the most common case. In UTF-8 or UTF-16 mode, the starting off-
- set must point to the start of a character, or to the end of the sub-
- ject (in UTF-32 mode, one code unit equals one character, so all off-
- sets are valid). Like the pattern string, the subject may contain
+ set must point to the start of a character, or to the end of the sub-
+ ject (in UTF-32 mode, one code unit equals one character, so all off-
+ sets are valid). Like the pattern string, the subject may contain
binary zeroes.
- A non-zero starting offset is useful when searching for another match
- in the same subject by calling pcre2_match() again after a previous
- success. Setting startoffset differs from passing over a shortened
- string and setting PCRE2_NOTBOL in the case of a pattern that begins
+ A non-zero starting offset is useful when searching for another match
+ in the same subject by calling pcre2_match() again after a previous
+ success. Setting startoffset differs from passing over a shortened
+ string and setting PCRE2_NOTBOL in the case of a pattern that begins
with any kind of lookbehind. For example, consider the pattern
\Biss\B
- which finds occurrences of "iss" in the middle of words. (\B matches
- only if the current position in the subject is not a word boundary.)
+ which finds occurrences of "iss" in the middle of words. (\B matches
+ only if the current position in the subject is not a word boundary.)
When applied to the string "Mississipi" the first call to pcre2_match()
- finds the first occurrence. If pcre2_match() is called again with just
- the remainder of the subject, namely "issipi", it does not match,
+ finds the first occurrence. If pcre2_match() is called again with just
+ the remainder of the subject, namely "issipi", it does not match,
because \B is always false at the start of the subject, which is deemed
- to be a word boundary. However, if pcre2_match() is passed the entire
+ to be a word boundary. However, if pcre2_match() is passed the entire
string again, but with startoffset set to 4, it finds the second occur-
- rence of "iss" because it is able to look behind the starting point to
+ rence of "iss" because it is able to look behind the starting point to
discover that it is preceded by a letter.
- Finding all the matches in a subject is tricky when the pattern can
+ Finding all the matches in a subject is tricky when the pattern can
match an empty string. It is possible to emulate Perl's /g behaviour by
- first trying the match again at the same offset, with the
- PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED options, and then if that
- fails, advancing the starting offset and trying an ordinary match
- again. There is some code that demonstrates how to do this in the
- pcre2demo sample program. In the most general case, you have to check
- to see if the newline convention recognizes CRLF as a newline, and if
- so, and the current character is CR followed by LF, advance the start-
+ first trying the match again at the same offset, with the
+ PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED options, and then if that
+ fails, advancing the starting offset and trying an ordinary match
+ again. There is some code that demonstrates how to do this in the
+ pcre2demo sample program. In the most general case, you have to check
+ to see if the newline convention recognizes CRLF as a newline, and if
+ so, and the current character is CR followed by LF, advance the start-
ing offset by two characters instead of one.
- If a non-zero starting offset is passed when the pattern is anchored,
- an single attempt to match at the given offset is made. This can only
+ If a non-zero starting offset is passed when the pattern is anchored,
+ an single attempt to match at the given offset is made. This can only
succeed if the pattern does not require the match to be at the start of
- the subject. In other words, the anchoring must be the result of set-
- ting the PCRE2_ANCHORED option or the use of .* with PCRE2_DOTALL, not
+ the subject. In other words, the anchoring must be the result of set-
+ ting the PCRE2_ANCHORED option or the use of .* with PCRE2_DOTALL, not
by starting the pattern with ^ or \A.
Option bits for pcre2_match()
The unused bits of the options argument for pcre2_match() must be zero.
- The only bits that may be set are PCRE2_ANCHORED, PCRE2_ENDANCHORED,
- PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART,
- PCRE2_NO_JIT, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PAR-
+ 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 or PCRE2_ENDANCHORED at match time is not sup-
- ported by the just-in-time (JIT) compiler. If it is set, JIT matching
- is disabled and the interpretive code in pcre2_match() is run. Apart
- from PCRE2_NO_JIT (obviously), the remaining options are supported for
+ Setting PCRE2_ANCHORED or PCRE2_ENDANCHORED at match time is not sup-
+ ported by the just-in-time (JIT) compiler. If it is set, JIT matching
+ is disabled and the interpretive code in pcre2_match() is run. Apart
+ from PCRE2_NO_JIT (obviously), the remaining options are supported for
JIT matching.
PCRE2_ANCHORED
The PCRE2_ANCHORED option limits pcre2_match() to matching at the first
- matching position. If a pattern was compiled with PCRE2_ANCHORED, or
- turned out to be anchored by virtue of its contents, it cannot be made
- unachored at matching time. Note that setting the option at match time
+ matching position. If a pattern was compiled with PCRE2_ANCHORED, or
+ turned out to be anchored by virtue of its contents, it cannot be made
+ unachored at matching time. Note that setting the option at match time
disables JIT matching.
PCRE2_ENDANCHORED
- If the PCRE2_ENDANCHORED option is set, any string that pcre2_match()
- matches must be right at the end of the subject string. Note that set-
+ If the PCRE2_ENDANCHORED option is set, any string that pcre2_match()
+ matches must be right at the end of the subject string. Note that set-
ting the option at match time disables JIT matching.
PCRE2_NOTBOL
This option specifies that first character of the subject string is not
- the beginning of a line, so the circumflex metacharacter should not
- match before it. Setting this without having set PCRE2_MULTILINE at
+ the beginning of a line, so the circumflex metacharacter should not
+ match before it. Setting this without having set PCRE2_MULTILINE at
compile time causes circumflex never to match. This option affects only
the behaviour of the circumflex metacharacter. It does not affect \A.
@@ -2180,9 +2232,9 @@
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.
@@ -2189,79 +2241,79 @@
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.
@@ -2271,38 +2323,38 @@
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.
@@ -2313,81 +2365,81 @@
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.
@@ -2397,42 +2449,42 @@
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.
@@ -2439,14 +2491,14 @@
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
@@ -2455,20 +2507,20 @@
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
@@ -2482,15 +2534,15 @@
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
@@ -2499,14 +2551,14 @@
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
@@ -2515,9 +2567,11 @@
PCRE2_ERROR_NOMEMORY
- If a pattern contains many nested backtracking points, heap memory is
- used to remember them. This error is given when the memory allocation
- function (default or custom) fails.
+ If a pattern contains many nested backtracking points, heap memory is
+ used to remember them. This error is given when the memory allocation
+ function (default or custom) fails. Note that a different error,
+ PCRE2_ERROR_HEAPLIMIT, is given if the amount of memory needed exceeds
+ the heap limit.
PCRE2_ERROR_NULL
@@ -2525,12 +2579,12 @@
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.
@@ -2539,20 +2593,20 @@
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.
@@ -2571,39 +2625,39 @@
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
@@ -2612,25 +2666,25 @@
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
@@ -2641,8 +2695,8 @@
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.
@@ -2653,32 +2707,32 @@
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().
@@ -2698,39 +2752,39 @@
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.
@@ -2743,41 +2797,41 @@
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
@@ -2784,11 +2838,11 @@
$<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
@@ -2798,92 +2852,92 @@
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
@@ -2892,16 +2946,16 @@
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-
@@ -2908,25 +2962,25 @@
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).
@@ -2935,56 +2989,56 @@
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.
@@ -2996,26 +3050,26 @@
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():
@@ -3035,45 +3089,45 @@
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_ENDAN-
- CHORED, PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY,
+ 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
+ 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.
@@ -3081,8 +3135,8 @@
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
<.*>
@@ -3097,17 +3151,17 @@
<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
@@ -3117,64 +3171,64 @@
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).
@@ -3187,7 +3241,7 @@
REVISION
- Last updated: 04 April 2017
+ Last updated: 11 April 2017
Copyright (c) 1997-2017 University of Cambridge.
------------------------------------------------------------------------------
@@ -3427,19 +3481,40 @@
pcre2_dfa_match() matching function, but it does also limit JIT match-
ing (though the counting is done differently).
- In some environments it is desirable to limit the depth of nested back-
- tracking in order to restrict the maximum amount of heap memory that is
- used. A second limit controls this; it defaults to the value that is
- set for --with-match-limit. You can set a lower default limit by
- adding, for example,
+ The pcre2_match() function starts out using a 20K vector on the system
+ stack to record backtracking points. The more nested backtracking
+ points there are (that is, the deeper the search tree), the more memory
+ is needed. If the initial vector is not large enough, heap memory is
+ used, up to a certain limit, which is specified in kilobytes. The limit
+ can be changed at run time, as described in the pcre2api documentation.
+ The default limit (in effect unlimited) is 20 million. You can change
+ this by a setting such as
+ --with-heap-limit=500
+
+ which limits the amount of heap to 500 kilobytes. This limit applies
+ only to interpretive matching in pcre2_match(). It does not apply when
+ JIT (which has its own memory arrangements) is used, nor does it apply
+ to pcre2_dfa_match().
+
+ You can also explicitly limit the depth of nested backtracking in the
+ pcre2_match() interpreter. This limit defaults to the value that is set
+ for --with-match-limit. You can set a lower default limit by adding,
+ for example,
+
--with-match-limit_depth=10000
- to the configure command. This value can also be overridden at run
- time. As well as applying to pcre2_match(), this limit also controls
- the depth of recursive function calls in pcre2_dfa_match(). These are
- used for lookaround assertions, atomic groups, and recursion within
- patterns.
+ to the configure command. This value can be overridden at run time.
+ This depth limit indirectly limits the amount of heap memory that is
+ used, but because the size of each backtracking "frame" depends on the
+ number of capturing parentheses in a pattern, the amount of heap that
+ is used before the limit is reached varies from pattern to pattern.
+ This limit was more useful in versions before 10.30, where function
+ recursion was used for backtracking. However, as well as applying to
+ pcre2_match(), this limit also controls the depth of recursive function
+ calls in pcre2_dfa_match(). These are used for lookaround assertions,
+ atomic groups, and recursion within patterns. The limit does not apply
+ to JIT matching.
CREATING CHARACTER TABLES AT BUILD TIME
@@ -3446,24 +3521,24 @@
PCRE2 uses fixed tables for processing characters whose code points are
less than 256. By default, PCRE2 is built with a set of tables that are
- distributed in the file src/pcre2_chartables.c.dist. These tables are
+ distributed in the file src/pcre2_chartables.c.dist. These tables are
for ASCII codes only. If you add
--enable-rebuild-chartables
- to the configure command, the distributed tables are no longer used.
- Instead, a program called dftables is compiled and run. This outputs
+ to the configure command, the distributed tables are no longer used.
+ Instead, a program called dftables is compiled and run. This outputs
the source for new set of tables, created in the default locale of your
C run-time system. This method of replacing the tables does not work if
- you are cross compiling, because dftables is run on the local host. If
- you need to create alternative tables when cross compiling, you will
+ you are cross compiling, because dftables is run on the local host. If
+ you need to create alternative tables when cross compiling, you will
have to do so "by hand".
USING EBCDIC CODE
- PCRE2 assumes by default that it will run in an environment where the
- character code is ASCII or Unicode, which is a superset of ASCII. This
+ PCRE2 assumes by default that it will run in an environment where the
+ character code is ASCII or Unicode, which is a superset of ASCII. This
is the case for most computer operating systems. PCRE2 can, however, be
compiled to run in an 8-bit EBCDIC environment by adding
@@ -3470,21 +3545,21 @@
--enable-ebcdic --disable-unicode
to the configure command. This setting implies --enable-rebuild-charta-
- bles. You should only use it if you know that you are in an EBCDIC
+ bles. You should only use it if you know that you are in an EBCDIC
environment (for example, an IBM mainframe operating system).
- It is not possible to support both EBCDIC and UTF-8 codes in the same
- version of the library. Consequently, --enable-unicode and --enable-
+ It is not possible to support both EBCDIC and UTF-8 codes in the same
+ version of the library. Consequently, --enable-unicode and --enable-
ebcdic are mutually exclusive.
The EBCDIC character that corresponds to an ASCII LF is assumed to have
- the value 0x15 by default. However, in some EBCDIC environments, 0x25
+ the value 0x15 by default. However, in some EBCDIC environments, 0x25
is used. In such an environment you should use
--enable-ebcdic-nl25
as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR
- has the same value as in ASCII, namely, 0x0d. Whichever of 0x15 and
+ has the same value as in ASCII, namely, 0x0d. Whichever of 0x15 and
0x25 is not chosen as LF is made to correspond to the Unicode NEL char-
acter (which, in Unicode, is 0x85).
@@ -3497,15 +3572,15 @@
By default, on non-Windows systems, pcre2grep supports the use of call-
outs with string arguments within the patterns it is matching, in order
- to run external scripts. For details, see the pcre2grep documentation.
- This support can be disabled by adding --disable-pcre2grep-callout to
+ to run external scripts. For details, see the pcre2grep documentation.
+ This support can be disabled by adding --disable-pcre2grep-callout to
the configure command.
PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT
- By default, pcre2grep reads all files as plain text. You can build it
- so that it recognizes files whose names end in .gz or .bz2, and reads
+ By default, pcre2grep reads all files as plain text. You can build it
+ so that it recognizes files whose names end in .gz or .bz2, and reads
them with libz or libbz2, respectively, by adding one or both of
--enable-pcre2grep-libz
@@ -3512,19 +3587,19 @@
--enable-pcre2grep-libbz2
to the configure command. These options naturally require that the rel-
- evant libraries are installed on your system. Configuration will fail
+ evant libraries are installed on your system. Configuration will fail
if they are not.
PCRE2GREP BUFFER SIZE
- pcre2grep uses an internal buffer to hold a "window" on the file it is
+ pcre2grep uses an internal buffer to hold a "window" on the file it is
scanning, in order to be able to output "before" and "after" lines when
- it finds a match. The starting size of the buffer is controlled by a
- parameter whose default value is 20K. The buffer itself is three times
- this size, but because of the way it is used for holding "before"
- lines, the longest line that is guaranteed to be processable is the
- parameter size. If a longer line is encountered, pcre2grep automati-
+ it finds a match. The starting size of the buffer is controlled by a
+ parameter whose default value is 20K. The buffer itself is three times
+ this size, but because of the way it is used for holding "before"
+ lines, the longest line that is guaranteed to be processable is the
+ parameter size. If a longer line is encountered, pcre2grep automati-
cally expands the buffer, up to a specified maximum size, whose default
is 1M or the starting size, whichever is the larger. You can change the
default parameter values by adding, for example,
@@ -3532,8 +3607,8 @@
--with-pcre2grep-bufsize=51200
--with-pcre2grep-max-bufsize=2097152
- to the configure command. The caller of pcre2grep can override these
- values by using --buffer-size and --max-buffer-size on the command
+ to the configure command. The caller of pcre2grep can override these
+ values by using --buffer-size and --max-buffer-size on the command
line.
@@ -3544,19 +3619,19 @@
--enable-pcre2test-libreadline
--enable-pcre2test-libedit
- to the configure command, pcre2test is linked with the libreadline
+ to the configure command, pcre2test is linked with the libreadline
orlibedit library, respectively, and when its input is from a terminal,
- it reads it using the readline() function. This provides line-editing
- and history facilities. Note that libreadline is GPL-licensed, so if
- you distribute a binary of pcre2test linked in this way, there may be
+ it reads it using the readline() function. This provides line-editing
+ and history facilities. Note that libreadline is GPL-licensed, so if
+ you distribute a binary of pcre2test linked in this way, there may be
licensing issues. These can be avoided by linking instead with libedit,
which has a BSD licence.
- Setting --enable-pcre2test-libreadline causes the -lreadline option to
- be added to the pcre2test build. In many operating environments with a
- sytem-installed readline library this is sufficient. However, in some
+ Setting --enable-pcre2test-libreadline causes the -lreadline option to
+ be added to the pcre2test build. In many operating environments with a
+ sytem-installed readline library this is sufficient. However, in some
environments (e.g. if an unmodified distribution version of readline is
- in use), some extra configuration may be necessary. The INSTALL file
+ in use), some extra configuration may be necessary. The INSTALL file
for libreadline says this:
"Readline uses the termcap functions, but does not link with
@@ -3563,7 +3638,7 @@
the termcap or curses library itself, allowing applications
which link with readline the to choose an appropriate library."
- If your environment has not been set up so that an appropriate library
+ If your environment has not been set up so that an appropriate library
is automatically included, you may need to add something like
LIBS="-ncurses"
@@ -3577,7 +3652,7 @@
--enable-debug
- to the configure command, additional debugging code is included in the
+ to the configure command, additional debugging code is included in the
build. This feature is intended for use by the PCRE2 maintainers.
@@ -3587,15 +3662,15 @@
--enable-valgrind
- to the configure command, PCRE2 will use valgrind annotations to mark
- certain memory regions as unaddressable. This allows it to detect
- invalid memory accesses, and is mostly useful for debugging PCRE2
+ to the configure command, PCRE2 will use valgrind annotations to mark
+ certain memory regions as unaddressable. This allows it to detect
+ invalid memory accesses, and is mostly useful for debugging PCRE2
itself.
CODE COVERAGE REPORTING
- If your C compiler is gcc, you can build a version of PCRE2 that can
+ If your C compiler is gcc, you can build a version of PCRE2 that can
generate a code coverage report for its test suite. To enable this, you
must install lcov version 1.6 or above. Then specify
@@ -3604,7 +3679,7 @@
to the configure command and build PCRE2 in the usual way.
Note that using ccache (a caching C compiler) is incompatible with code
- coverage reporting. If you have configured ccache to run automatically
+ coverage reporting. If you have configured ccache to run automatically
on your system, you must set the environment variable
CCACHE_DISABLE=1
@@ -3611,13 +3686,13 @@
before running make to build PCRE2, so that ccache is not used.
- When --enable-coverage is used, the following addition targets are
+ When --enable-coverage is used, the following addition targets are
added to the Makefile:
make coverage
- This creates a fresh coverage report for the PCRE2 test suite. It is
- equivalent to running "make coverage-reset", "make coverage-baseline",
+ This creates a fresh coverage report for the PCRE2 test suite. It is
+ equivalent to running "make coverage-reset", "make coverage-baseline",
"make check", and then "make coverage-report".
make coverage-reset
@@ -3634,56 +3709,56 @@
make coverage-clean-report
- This removes the generated coverage report without cleaning the cover-
+ This removes the generated coverage report without cleaning the cover-
age data itself.
make coverage-clean-data
- This removes the captured coverage data without removing the coverage
+ This removes the captured coverage data without removing the coverage
files created at compile time (*.gcno).
make coverage-clean
- This cleans all coverage data including the generated coverage report.
- For more information about code coverage, see the gcov and lcov docu-
+ This cleans all coverage data including the generated coverage report.
+ For more information about code coverage, see the gcov and lcov docu-
mentation.
SUPPORT FOR FUZZERS
- There is a special option for use by people who want to run fuzzing
+ There is a special option for use by people who want to run fuzzing
tests on PCRE2:
--enable-fuzz-support
At present this applies only to the 8-bit library. If set, it causes an
- extra library called libpcre2-fuzzsupport.a to be built, but not
- installed. This contains a single function called LLVMFuzzerTestOneIn-
- put() whose arguments are a pointer to a string and the length of the
- string. When called, this function tries to compile the string as a
- pattern, and if that succeeds, to match it. This is done both with no
- options and with some random options bits that are generated from the
+ extra library called libpcre2-fuzzsupport.a to be built, but not
+ installed. This contains a single function called LLVMFuzzerTestOneIn-
+ put() whose arguments are a pointer to a string and the length of the
+ string. When called, this function tries to compile the string as a
+ pattern, and if that succeeds, to match it. This is done both with no
+ options and with some random options bits that are generated from the
string.
- Setting --enable-fuzz-support also causes a binary called pcre2fuz-
- zcheck to be created. This is normally run under valgrind or used when
+ Setting --enable-fuzz-support also causes a binary called pcre2fuz-
+ zcheck to be created. This is normally run under valgrind or used when
PCRE2 is compiled with address sanitizing enabled. It calls the fuzzing
- function and outputs information about it is doing. The input strings
- are specified by arguments: if an argument starts with "=" the rest of
- it is a literal input string. Otherwise, it is assumed to be a file
+ function and outputs information about it is doing. The input strings
+ are specified by arguments: if an argument starts with "=" the rest of
+ it is a literal input string. Otherwise, it is assumed to be a file
name, and the contents of the file are the test string.
OBSOLETE OPTION
- In versions of PCRE2 prior to 10.30, there were two ways of handling
- backtracking in the pcre2_match() function. The default was to use the
+ In versions of PCRE2 prior to 10.30, there were two ways of handling
+ backtracking in the pcre2_match() function. The default was to use the
system stack, but if
--disable-stack-for-recursion
- was set, memory on the heap was used. From release 10.30 onwards this
- has changed (the stack is no longer used) and this option now does
+ was set, memory on the heap was used. From release 10.30 onwards this
+ has changed (the stack is no longer used) and this option now does
nothing except give a warning.
@@ -3701,7 +3776,7 @@
REVISION
- Last updated: 31 March 2017
+ Last updated: 10 April 2017
Copyright (c) 1997-2017 University of Cambridge.
------------------------------------------------------------------------------
@@ -5522,41 +5597,44 @@
attempt by the application to apply the JIT optimization by calling
pcre2_jit_compile() is ignored.
- Setting match and backtracking depth limits
+ Setting match resource limits
The pcre2_match() function contains a counter that is incremented every
time it goes round its main loop. The caller of pcre2_match() can set a
limit on this counter, which therefore limits the amount of computing
resource used for a match. The maximum depth of nested backtracking can
- also be limited, and this restricts the amount of heap memory that is
- used.
+ also be limited; this indirectly restricts the amount of heap memory
+ that is used, but there is also an explicit memory limit that can be
+ set.
- These facilities are provided to catch runaway matches that are pro-
+ These facilities are provided to catch runaway matches that are pro-
voked by patterns with huge matching trees (a typical example is a pat-
- tern with nested unlimited repeats applied to a long string that does
+ tern with nested unlimited repeats applied to a long string that does
not match). When one of these limits is reached, pcre2_match() gives an
- error return. The limits can also be set by items at the start of the
+ error return. The limits can also be set by items at the start of the
pattern of the form
+ (*LIMIT_HEAP=d)
(*LIMIT_MATCH=d)
(*LIMIT_DEPTH=d)
where d is any number of decimal digits. However, the value of the set-
- ting must be less than the value set (or defaulted) by the caller of
- pcre2_match() for it to have any effect. In other words, the pattern
- writer can lower the limits set by the programmer, but not raise them.
- If there is more than one setting of one of these limits, the lower
+ ting must be less than the value set (or defaulted) by the caller of
+ pcre2_match() for it to have any effect. In other words, the pattern
+ writer can lower the limits set by the programmer, but not raise them.
+ If there is more than one setting of one of these limits, the lower
value is used.
- Prior to release 10.30, LIMIT_DEPTH was called LIMIT_RECURSION. This
+ Prior to release 10.30, LIMIT_DEPTH was called LIMIT_RECURSION. This
name is still recognized for backwards compatibility.
- The match limit is used (but in a different way) when JIT is being
- used, but it is not relevant, and is ignored, when matching with
- pcre2_dfa_match(). However, the depth limit is relevant for DFA match-
- ing, which uses function recursion for recursions within the pattern.
- In this case, the depth limit controls the amount of system stack that
- is used.
+ The heap limit applies only when the pcre2_match() interpreter is used
+ for matching. It does not apply to JIT or DFA matching. The match limit
+ is used (but in a different way) when JIT is being used, but it is not
+ relevant, and is ignored, when matching with pcre2_dfa_match(). The
+ depth limit is ignored by JIT but is relevant for DFA matching, which
+ uses function recursion for recursions within the pattern. In this
+ case, the depth limit controls the amount of system stack that is used.
Newline conventions
@@ -8480,7 +8558,7 @@
REVISION
- Last updated: 03 April 2017
+ Last updated: 11 April 2017
Copyright (c) 1997-2017 University of Cambridge.
------------------------------------------------------------------------------
@@ -8557,10 +8635,12 @@
sive function calls could use a great deal of stack, and this could
cause problems, but this usage has been eliminated. Backtracking posi-
tions are now explicitly remembered in memory frames controlled by the
- code. An initial 10K vector of frames is allocated on the system stack
- (enough for about 50 frames for small patterns), but if this is insuf-
- ficient, heap memory is used. Rewriting patterns to be time-efficient,
- as described below, may also reduce the memory requirements.
+ code. An initial 20K vector of frames is allocated on the system stack
+ (enough for about 100 frames for small patterns), but if this is insuf-
+ ficient, heap memory is used. The amount of heap memory can be limited;
+ if the limit is set to zero, only the initial stack vector is used.
+ Rewriting patterns to be time-efficient, as described below, may also
+ reduce the memory requirements.
In contrast to pcre2_match(), pcre2_dfa_match() does use recursive
function calls, but only for processing atomic groups, lookaround
@@ -8706,7 +8786,7 @@
REVISION
- Last updated: 31 March 2017
+ Last updated: 08 April 2017
Copyright (c) 1997-2017 University of Cambridge.
------------------------------------------------------------------------------
Modified: code/trunk/doc/pcre2_config.3
===================================================================
--- code/trunk/doc/pcre2_config.3 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2_config.3 2017-04-11 11:47:25 UTC (rev 739)
@@ -1,4 +1,4 @@
-.TH PCRE2_CONFIG 3 "24 March 2017" "PCRE2 10.30"
+.TH PCRE2_CONFIG 3 "11 April 2017" "PCRE2 10.30"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS
@@ -31,6 +31,7 @@
PCRE2_CONFIG_BSR Indicates what \eR matches by default:
PCRE2_BSR_UNICODE
PCRE2_BSR_ANYCRLF
+ PCRE2_CONFIG_HEAPLIMIT Default heap memory limit
PCRE2_CONFIG_DEPTHLIMIT Default backtracking depth limit
.\" JOIN
PCRE2_CONFIG_JIT Availability of just-in-time compiler
Modified: code/trunk/doc/pcre2_match.3
===================================================================
--- code/trunk/doc/pcre2_match.3 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2_match.3 2017-04-11 11:47:25 UTC (rev 739)
@@ -1,4 +1,4 @@
-.TH PCRE2_MATCH 3 "04 April 2017" "PCRE2 10.30"
+.TH PCRE2_MATCH 3 "11 April 2017" "PCRE2 10.30"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS
@@ -32,6 +32,7 @@
.sp
Set up a callout function
Set a matching offset limit
+ Change the heap memory limit
Change the backtracking match limit
Change the backtracking depth limit
Set custom memory management specifically for the match
Modified: code/trunk/doc/pcre2_pattern_info.3
===================================================================
--- code/trunk/doc/pcre2_pattern_info.3 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2_pattern_info.3 2017-04-11 11:47:25 UTC (rev 739)
@@ -1,4 +1,4 @@
-.TH PCRE2_PATTERN_INFO 3 "25 March 2017" "PCRE2 10.30"
+.TH PCRE2_PATTERN_INFO 3 "11 April 2017" "PCRE2 10.30"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS
@@ -43,6 +43,9 @@
.\" JOIN
PCRE2_INFO_HASCRORLF Return 1 if explicit CR or LF matches
exist in the pattern
+.\" JOIN
+ PCRE2_INFO_HEAPLIMIT Heap memory limit if set,
+ otherwise PCRE2_ERROR_UNSET
PCRE2_INFO_JCHANGED Return 1 if (?J) or (?-J) was used
PCRE2_INFO_JITSIZE Size of JIT compiled code, or 0
PCRE2_INFO_LASTCODETYPE Type of must-be-present information
Added: code/trunk/doc/pcre2_set_heap_limit.3
===================================================================
--- code/trunk/doc/pcre2_set_heap_limit.3 (rev 0)
+++ code/trunk/doc/pcre2_set_heap_limit.3 2017-04-11 11:47:25 UTC (rev 739)
@@ -0,0 +1,28 @@
+.TH PCRE2_SET_DEPTH_LIMIT 3 "11 April 2017" "PCRE2 10.30"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include <pcre2.h>
+.PP
+.nf
+.B int pcre2_set_heap_limit(pcre2_match_context *\fImcontext\fP,
+.B " uint32_t \fIvalue\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets the backtracking heap limit field in a match context. The
+result is always zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
Modified: code/trunk/doc/pcre2api.3
===================================================================
--- code/trunk/doc/pcre2api.3 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2api.3 2017-04-11 11:47:25 UTC (rev 739)
@@ -1,4 +1,4 @@
-.TH PCRE2API 3 "04 April 2017" "PCRE2 10.30"
+.TH PCRE2API 3 "11 April 2017" "PCRE2 10.30"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.sp
@@ -123,6 +123,9 @@
.B int pcre2_set_offset_limit(pcre2_match_context *\fImcontext\fP,
.B " PCRE2_SIZE \fIvalue\fP);"
.sp
+.B int pcre2_set_heap_limit(pcre2_match_context *\fImcontext\fP,
+.B " uint32_t \fIvalue\fP);"
+.sp
.B int pcre2_set_match_limit(pcre2_match_context *\fImcontext\fP,
.B " uint32_t \fIvalue\fP);"
.sp
@@ -753,6 +756,7 @@
.sp
Set up a callout function
Set an offset limit for matching an unanchored pattern
+ Change the limit on the amount of heap used when matching
Change the backtracking match limit
Change the backtracking depth limit
Set custom memory management specifically for the match
@@ -816,14 +820,49 @@
In other words, whichever limit comes first is used.
.sp
.nf
+.B int pcre2_set_heap_limit(pcre2_match_context *\fImcontext\fP,
+.B " uint32_t \fIvalue\fP);"
+.fi
+.sp
+The \fIheap_limit\fP parameter specifies, in units of kilobytes, the maximum
+amount of heap memory that \fBpcre2_match()\fP may use to hold backtracking
+information when running an interpretive match. This limit does not apply to
+matching with the JIT optimization, which has its own memory control
+arrangements (see the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation for more details), nor does it apply to \fBpcre2_dfa_match()\fP.
+If the limit is reached, the negative error code PCRE2_ERROR_HEAPLIMIT is
+returned. The default limit is set when PCRE2 is built; the default default is
+very large and is essentially "unlimited".
+.P
+A value for the heap limit may also be supplied by an item at the start of a
+pattern of the form
+.sp
+ (*LIMIT_HEAP=ddd)
+.sp
+where ddd is a decimal number. However, such a setting is ignored unless ddd is
+less than the limit set by the caller of \fBpcre2_match()\fP or, if no such
+limit is set, less than the default.
+.P
+The \fBpcre2_match()\fP function starts out using a 20K vector on the system
+stack for recording backtracking points. The more nested backtracking points
+there are (that is, the deeper the search tree), the more memory is needed.
+Heap memory is used only if the initial vector is too small. If the heap limit
+is set to a value less than 21 (in particular, zero) no heap memory will be
+used. In this case, only patterns that do not have a lot of nested backtracking
+can be successfully processed.
+.sp
+.nf
.B int pcre2_set_match_limit(pcre2_match_context *\fImcontext\fP,
.B " uint32_t \fIvalue\fP);"
.fi
.sp
The \fImatch_limit\fP parameter provides a means of preventing PCRE2 from using
-up too many resources when processing patterns that are not going to match, but
-which have a very large number of possibilities in their search trees. The
-classic example is a pattern that uses nested unlimited repeats.
+up too many computing resources when processing patterns that are not going to
+match, but which have a very large number of possibilities in their search
+trees. The classic example is a pattern that uses nested unlimited repeats.
.P
There is an internal counter in \fBpcre2_match()\fP that is incremented each
time round its main matching loop. If this value reaches the match limit,
@@ -859,15 +898,19 @@
This parameter limits the depth of nested backtracking in \fBpcre2_match()\fP.
Each time a nested backtracking point is passed, a new memory "frame" is used
to remember the state of matching at that point. Thus, this parameter
-indirectly limits the amount of memory that is used in a match.
+indirectly limits the amount of memory that is used in a match. However,
+because the size of each memory "frame" depends on the number of capturing
+parentheses, the actual memory limit varies from pattern to pattern. This limit
+was more useful in versions before 10.30, where function recursion was used for
+backtracking.
.P
-This limit is not relevant, and is ignored, when matching is done using JIT
-compiled code. However, it is supported by \fBpcre2_dfa_match()\fP, which uses
-it to limit the depth of internal recursive function calls that implement
-lookaround assertions and pattern recursions. This is, therefore, an indirect
-limit on the amount of system stack that is used. A recursive pattern such as
-/(.)(?1)/, when matched to a very long string using \fBpcre2_dfa_match()\fP,
-can use a great deal of stack.
+The depth limit is not relevant, and is ignored, when matching is done using
+JIT compiled code. However, it is supported by \fBpcre2_dfa_match()\fP, which
+uses it to limit the depth of internal recursive function calls that implement
+atomic groups, lookaround assertions, and pattern recursions. This is,
+therefore, an indirect limit on the amount of system stack that is used. A
+recursive pattern such as /(.)(?1)/, when matched to a very long string using
+\fBpcre2_dfa_match()\fP, can use a great deal of stack.
.P
The default value for the depth limit can be set when PCRE2 is built; the
default default is the same value as the default for the match limit. If the
@@ -922,6 +965,12 @@
and lookarounds in \fBpcre2_dfa_match()\fP. Further details are given with
\fBpcre2_set_depth_limit()\fP above.
.sp
+ PCRE2_CONFIG_HEAPLIMIT
+.sp
+The output is a uint32_t integer that gives, in kilobytes, the default limit
+for the amount of heap memory used by \fBpcre2_match()\fP. Further details are
+given with \fBpcre2_set_heap_limit()\fP above.
+.sp
PCRE2_CONFIG_JIT
.sp
The output is a uint32_t integer that is set to one if support for just-in-time
@@ -1785,6 +1834,13 @@
explicit match is either a literal CR or LF character, or \er or \en or one of
the equivalent hexadecimal or octal escape sequences.
.sp
+ PCRE2_INFO_HEAPLIMIT
+.sp
+If the pattern set a heap memory limit by including an item of the form
+(*LIMIT_HEAP=nnnn) at the start, the value is returned. The third argument
+should point to an unsigned 32-bit integer. If no such value has been set, the
+call to \fBpcre2_pattern_info()\fP returns the error PCRE2_ERROR_UNSET.
+.sp
PCRE2_INFO_JCHANGED
.sp
Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
@@ -2603,7 +2659,8 @@
.sp
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.
+or custom) fails. Note that a different error, PCRE2_ERROR_HEAPLIMIT, is given
+if the amount of memory needed exceeds the heap limit.
.sp
PCRE2_ERROR_NULL
.sp
@@ -3322,6 +3379,6 @@
.rs
.sp
.nf
-Last updated: 04 April 2017
+Last updated: 11 April 2017
Copyright (c) 1997-2017 University of Cambridge.
.fi
Modified: code/trunk/doc/pcre2build.3
===================================================================
--- code/trunk/doc/pcre2build.3 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2build.3 2017-04-11 11:47:25 UTC (rev 739)
@@ -1,4 +1,4 @@
-.TH PCRE2BUILD 3 "31 March 2017" "PCRE2 10.30"
+.TH PCRE2BUILD 3 "10 April 2017" "PCRE2 10.30"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.
@@ -260,17 +260,42 @@
\fBpcre2_dfa_match()\fP matching function, but it does also limit JIT matching
(though the counting is done differently).
.P
-In some environments it is desirable to limit the depth of nested backtracking
-in order to restrict the maximum amount of heap memory that is used. A second
-limit controls this; it defaults to the value that is set for
---with-match-limit. You can set a lower default limit by adding, for example,
+The \fBpcre2_match()\fP function starts out using a 20K vector on the system
+stack to record backtracking points. The more nested backtracking points there
+are (that is, the deeper the search tree), the more memory is needed. If the
+initial vector is not large enough, heap memory is used, up to a certain limit,
+which is specified in kilobytes. The limit can be changed at run time, as
+described in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+documentation. The default limit (in effect unlimited) is 20 million. You can
+change this by a setting such as
.sp
+ --with-heap-limit=500
+.sp
+which limits the amount of heap to 500 kilobytes. This limit applies only to
+interpretive matching in pcre2_match(). It does not apply when JIT (which has
+its own memory arrangements) is used, nor does it apply to
+\fBpcre2_dfa_match()\fP.
+.P
+You can also explicitly limit the depth of nested backtracking in the
+\fBpcre2_match()\fP interpreter. This limit defaults to the value that is set
+for --with-match-limit. You can set a lower default limit by adding, for
+example,
+.sp
--with-match-limit_depth=10000
.sp
-to the \fBconfigure\fP command. This value can also be overridden at run time.
-As well as applying to \fBpcre2_match()\fP, this limit also controls the depth
-of recursive function calls in \fBpcre2_dfa_match()\fP. These are used for
-lookaround assertions, atomic groups, and recursion within patterns.
+to the \fBconfigure\fP command. This value can be overridden at run time. This
+depth limit indirectly limits the amount of heap memory that is used, but
+because the size of each backtracking "frame" depends on the number of
+capturing parentheses in a pattern, the amount of heap that is used before the
+limit is reached varies from pattern to pattern. This limit was more useful in
+versions before 10.30, where function recursion was used for backtracking.
+However, as well as applying to \fBpcre2_match()\fP, this limit also controls
+the depth of recursive function calls in \fBpcre2_dfa_match()\fP. These are
+used for lookaround assertions, atomic groups, and recursion within patterns.
+The limit does not apply to JIT matching.
.
.
.SH "CREATING CHARACTER TABLES AT BUILD TIME"
@@ -547,6 +572,6 @@
.rs
.sp
.nf
-Last updated: 31 March 2017
+Last updated: 10 April 2017
Copyright (c) 1997-2017 University of Cambridge.
.fi
Modified: code/trunk/doc/pcre2grep.1
===================================================================
--- code/trunk/doc/pcre2grep.1 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2grep.1 2017-04-11 11:47:25 UTC (rev 739)
@@ -1,4 +1,4 @@
-.TH PCRE2GREP 1 "06 April 2017" "PCRE2 10.30"
+.TH PCRE2GREP 1 "11 April 2017" "PCRE2 10.30"
.SH NAME
pcre2grep - a grep with Perl-compatible regular expressions.
.SH SYNOPSIS
@@ -347,6 +347,9 @@
file name is followed by a colon; for context lines, a hyphen separator is used.
If a line number is also being output, it follows the file name.
.TP
+\fB--heap-limit\fP=\fInumber\fP
+See \fB--match-limit\fP below.
+.TP
\fB--help\fP
Output a help message, giving brief details of the command options and file
type support, and then exit. Anything else on the command line is
@@ -436,7 +439,7 @@
\fB--match-limit\fP=\fInumber\fP
Processing some regular expression patterns may take a very long time to search
for all possible matching strings. Others may require a very large amount of
-memory. There are two options that set resource limits for matching.
+memory. There are three options that set resource limits for matching.
.sp
The \fB--match-limit\fP option provides a means of limiting computing resource
usage when processing patterns that are not going to match, but which have a
@@ -445,12 +448,22 @@
counter that is incremented each time around its main processing loop. If the
value set by \fB--match-limit\fP is reached, an error occurs.
.sp
+The \fB--heap-limit\fP option specifies, as a number of kilobytes, the amount
+of heap memory that may be used for matching. Heap memory is needed only if
+matching the pattern requires a significant number of nested backtracking
+points to be remembered. This parameter can be set to zero to forbid the use of
+heap memory altogether.
+.sp
The \fB--depth-limit\fP option limits the depth of nested backtracking points,
-which in turn limits the amount of memory that is used. This limit is of use
-only if it is set smaller than \fB--match-limit\fP.
+which indirectly limits the amount of memory that is used. The amount of memory
+needed for each backtracking point depends on the number of capturing
+parentheses in the pattern, so the amount of memory that is used before this
+limit acts varies from pattern to pattern. This limit is of use only if it is
+set smaller than \fB--match-limit\fP.
.sp
There are no short forms for these options. The default settings are specified
-when the PCRE2 library is compiled, with the default default being 10 million.
+when the PCRE2 library is compiled, with the default defaults being very large
+and so effectively unlimited.
.TP
\fB--max-buffer-size=\fInumber\fP
This limits the expansion of the processing buffer, whose initial size can be
@@ -670,11 +683,12 @@
as in the GNU \fBgrep\fP program. Any long option of the form
\fB--xxx-regexp\fP (GNU terminology) is also available as \fB--xxx-regex\fP
(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--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.
+\fB--file-offsets\fP, \fB--heap-limit\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--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
@@ -799,9 +813,9 @@
there are more than 20 such errors, \fBpcre2grep\fP gives up.
.P
The \fB--match-limit\fP option of \fBpcre2grep\fP can be used to set the
-overall resource limit; there is a second option called \fB--depth-limit\fP
-that sets a limit on the amount of memory that is used (see the discussion of
-these options above).
+overall resource limit. There are also other limits that affect the amount of
+memory used during matching; see the discussion of \fB--heap-limit\fP and
+\fB--depth-limit\fP above.
.
.
.SH DIAGNOSTICS
@@ -834,6 +848,6 @@
.rs
.sp
.nf
-Last updated: 06 April 2017
+Last updated: 11 April 2017
Copyright (c) 1997-2017 University of Cambridge.
.fi
Modified: code/trunk/doc/pcre2grep.txt
===================================================================
--- code/trunk/doc/pcre2grep.txt 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2grep.txt 2017-04-11 11:47:25 UTC (rev 739)
@@ -383,6 +383,9 @@
colon; for context lines, a hyphen separator is used. If a
line number is also being output, it follows the file name.
+ --heap-limit=number
+ See --match-limit below.
+
--help Output a help message, giving brief details of the command
options and file type support, and then exit. Anything else
on the command line is ignored.
@@ -482,7 +485,7 @@
--match-limit=number
Processing some regular expression patterns may take a very
long time to search for all possible matching strings. Others
- may require a very large amount of memory. There are two
+ may require a very large amount of memory. There are three
options that set resource limits for matching.
The --match-limit option provides a means of limiting comput-
@@ -494,174 +497,185 @@
processing loop. If the value set by --match-limit is
reached, an error occurs.
- The --depth-limit option limits the depth of nested back-
- tracking points, which in turn limits the amount of memory
- that is used. This limit is of use only if it is set smaller
- than --match-limit.
+ The --heap-limit option specifies, as a number of kilobytes,
+ the amount of heap memory that may be used for matching. Heap
+ memory is needed only if matching the pattern requires a sig-
+ nificant number of nested backtracking points to be remem-
+ bered. This parameter can be set to zero to forbid the use of
+ heap memory altogether.
+ The --depth-limit option limits the depth of nested back-
+ tracking points, which indirectly limits the amount of memory
+ that is used. The amount of memory needed for each backtrack-
+ ing point depends on the number of capturing parentheses in
+ the pattern, so the amount of memory that is used before this
+ limit acts varies from pattern to pattern. This limit is of
+ use only if it is set smaller than --match-limit.
+
There are no short forms for these options. The default set-
tings are specified when the PCRE2 library is compiled, with
- the default default being 10 million.
+ the default defaults being very large and so effectively
+ unlimited.
--max-buffer-size=number
- This limits the expansion of the processing buffer, whose
- initial size can be set by --buffer-size. The maximum buffer
- size is silently forced to be no smaller than the starting
+ This limits the expansion of the processing buffer, whose
+ initial size can be set by --buffer-size. The maximum buffer
+ size is silently forced to be no smaller than the starting
buffer size.
-M, --multiline
- Allow patterns to match more than one line. When this option
+ Allow patterns to match more than one line. When this option
is set, the PCRE2 library is called in "multiline" mode. This
- allows a matched string to extend past the end of a line and
- continue on one or more subsequent lines. Patterns used with
+ allows a matched string to extend past the end of a line and
+ continue on one or more subsequent lines. Patterns used with
-M may usefully contain literal newline characters and inter-
- nal occurrences of ^ and $ characters. The output for a suc-
- cessful match may consist of more than one line. The first
- line is the line in which the match started, and the last
- line is the line in which the match ended. If the matched
- string ends with a newline sequence, the output ends at the
- end of that line. If -v is set, none of the lines in a
- multi-line match are output. Once a match has been handled,
- scanning restarts at the beginning of the line after the one
+ nal occurrences of ^ and $ characters. The output for a suc-
+ cessful match may consist of more than one line. The first
+ line is the line in which the match started, and the last
+ line is the line in which the match ended. If the matched
+ string ends with a newline sequence, the output ends at the
+ end of that line. If -v is set, none of the lines in a
+ multi-line match are output. Once a match has been handled,
+ scanning restarts at the beginning of the line after the one
in which the match ended.
- The newline sequence that separates multiple lines must be
- matched as part of the pattern. For example, to find the
- phrase "regular expression" in a file where "regular" might
- be at the end of a line and "expression" at the start of the
+ The newline sequence that separates multiple lines must be
+ matched as part of the pattern. For example, to find the
+ phrase "regular expression" in a file where "regular" might
+ be at the end of a line and "expression" at the start of the
next line, you could use this command:
pcre2grep -M 'regular\s+expression' <file>
- The \s escape sequence matches any white space character,
- including newlines, and is followed by + so as to match
- trailing white space on the first line as well as possibly
+ The \s escape sequence matches any white space character,
+ including newlines, and is followed by + so as to match
+ trailing white space on the first line as well as possibly
handling a two-character newline sequence.
- There is a limit to the number of lines that can be matched,
- imposed by the way that pcre2grep buffers the input file as
- it scans it. With a sufficiently large processing buffer,
+ There is a limit to the number of lines that can be matched,
+ imposed by the way that pcre2grep buffers the input file as
+ it scans it. With a sufficiently large processing buffer,
this should not be a problem, but the -M option does not work
when input is read line by line (see --line-buffered.)
-N newline-type, --newline=newline-type
- The PCRE2 library supports five different conventions for
- indicating the ends of lines. They are the single-character
- sequences CR (carriage return) and LF (linefeed), the two-
- character sequence CRLF, an "anycrlf" convention, which rec-
- ognizes any of the preceding three types, and an "any" con-
+ The PCRE2 library supports five different conventions for
+ indicating the ends of lines. They are the single-character
+ sequences CR (carriage return) and LF (linefeed), the two-
+ character sequence CRLF, an "anycrlf" convention, which rec-
+ ognizes any of the preceding three types, and an "any" con-
vention, in which any Unicode line ending sequence is assumed
- to end a line. The Unicode sequences are the three just men-
- tioned, plus VT (vertical tab, U+000B), FF (form feed,
- U+000C), NEL (next line, U+0085), LS (line separator,
+ to end a line. The Unicode sequences are the three just men-
+ tioned, plus VT (vertical tab, U+000B), FF (form feed,
+ U+000C), NEL (next line, U+0085), LS (line separator,
U+2028), and PS (paragraph separator, U+2029).
- When the PCRE2 library is built, a default line-ending
- sequence is specified. This is normally the standard
+ When the PCRE2 library is built, a default line-ending
+ sequence is specified. This is normally the standard
sequence for the operating system. Unless otherwise specified
- by this option, pcre2grep uses the library's default. The
+ by this option, pcre2grep uses the library's default. The
possible values for this option are CR, LF, CRLF, ANYCRLF, or
- ANY. This makes it possible to use pcre2grep to scan files
+ ANY. This makes it possible to use pcre2grep to scan files
that have come from other environments without having to mod-
- ify their line endings. If the data that is being scanned
- does not agree with the convention set by this option,
- pcre2grep may behave in strange ways. Note that this option
- does not apply to files specified by the -f, --exclude-from,
- or --include-from options, which are expected to use the
+ ify their line endings. If the data that is being scanned
+ does not agree with the convention set by this option,
+ pcre2grep may behave in strange ways. Note that this option
+ does not apply to files specified by the -f, --exclude-from,
+ or --include-from options, which are expected to use the
operating system's standard newline sequence.
-n, --line-number
Precede each output line by its line number in the file, fol-
- lowed by a colon for matching lines or a hyphen for context
+ lowed by a colon for matching lines or a hyphen for context
lines. If the file name is also being output, it precedes the
- line number. When the -M option causes a pattern to match
- more than one line, only the first is preceded by its line
+ line number. When the -M option causes a pattern to match
+ more than one line, only the first is preceded by its line
number. This option is forced if --line-offsets is used.
- --no-jit If the PCRE2 library is built with support for just-in-time
+ --no-jit If the PCRE2 library is built with support for just-in-time
compiling (which speeds up matching), pcre2grep automatically
makes use of this, unless it was explicitly disabled at build
- time. This option can be used to disable the use of JIT at
- run time. It is provided for testing and working round prob-
+ time. This option can be used to disable the use of JIT at
+ 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
+ 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
+ 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
+ $<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-
+ 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;
+ $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
+ $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
+ $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,
+ 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
- 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,
- on a separate line of output. If -o is combined with -v
- (invert the sense of the match to find non-matching lines),
- no output is generated, but the return code is set appropri-
- 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
+ of the whole line. 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,
+ on a separate line of output. If -o is combined with -v
+ (invert the sense of the match to find non-matching lines),
+ no output is generated, but the return code is set appropri-
+ 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 --output,
--file-offsets and --line-offsets.
-onumber, --only-matching=number
- Show only the part of the line that matched the capturing
+ Show only the part of the line that matched the capturing
parentheses of the given number. Up to 32 capturing parenthe-
ses are supported, and -o0 is equivalent to -o without a num-
- ber. 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.
+ ber. 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 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-
+ 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.
- If this option is given multiple times, multiple substrings
- are output for each match, in the order the options are
- given, and all on one line. For example, -o3 -o1 -o3 causes
- the substrings matched by capturing parentheses 3 and 1 and
- then 3 again to be output. By default, there is no separator
+ If this option is given multiple times, multiple substrings
+ are output for each match, in the order the options are
+ given, and all on one line. For example, -o3 -o1 -o3 causes
+ the substrings matched by capturing parentheses 3 and 1 and
+ then 3 again to be output. By default, there is no separator
(but see the next option).
--om-separator=text
- Specify a separating string for multiple occurrences of -o.
- The default is an empty string. Separating strings are never
+ Specify a separating string for multiple occurrences of -o.
+ The default is an empty string. Separating strings are never
coloured.
-q, --quiet
Work quietly, that is, display nothing except error messages.
- The exit status indicates whether or not any matches were
+ The exit status indicates whether or not any matches were
found.
-r, --recursive
- If any given path is a directory, recursively scan the files
- it contains, taking note of any --include and --exclude set-
- tings. By default, a directory is read as a normal file; in
- some operating systems this gives an immediate end-of-file.
- This option is a shorthand for setting the -d option to
+ If any given path is a directory, recursively scan the files
+ it contains, taking note of any --include and --exclude set-
+ tings. By default, a directory is read as a normal file; in
+ some operating systems this gives an immediate end-of-file.
+ This option is a shorthand for setting the -d option to
"recurse".
--recursion-limit=number
@@ -668,63 +682,63 @@
See --match-limit above.
-s, --no-messages
- Suppress error messages about non-existent or unreadable
- files. Such files are quietly skipped. However, the return
+ Suppress error messages about non-existent or unreadable
+ files. Such files are quietly skipped. However, the return
code is still 2, even if matches were found in other files.
-t, --total-count
- This option is useful when scanning more than one file. If
- used on its own, -t suppresses all output except for a grand
- total number of matching lines (or non-matching lines if -v
- is used) in all the files. If -t is used with -c, a grand
- total is output except when the previous output is just one
- line. In other words, it is not output when just one file's
- count is listed. If file names are being output, the grand
- total is preceded by "TOTAL:". Otherwise, it appears as just
- another number. The -t option is ignored when used with -L
- (list files without matches), because the grand total would
+ This option is useful when scanning more than one file. If
+ used on its own, -t suppresses all output except for a grand
+ total number of matching lines (or non-matching lines if -v
+ is used) in all the files. If -t is used with -c, a grand
+ total is output except when the previous output is just one
+ line. In other words, it is not output when just one file's
+ count is listed. If file names are being output, the grand
+ total is preceded by "TOTAL:". Otherwise, it appears as just
+ another number. The -t option is ignored when used with -L
+ (list files without matches), because the grand total would
always be zero.
-u, --utf-8
Operate in UTF-8 mode. This option is available only if PCRE2
has been compiled with UTF-8 support. All patterns (including
- those for any --exclude and --include options) and all sub-
- ject lines that are scanned must be valid strings of UTF-8
+ those for any --exclude and --include options) and all sub-
+ ject lines that are scanned must be valid strings of UTF-8
characters.
-V, --version
- Write the version numbers of pcre2grep and the PCRE2 library
- to the standard output and then exit. Anything else on the
+ Write the version numbers of pcre2grep and the PCRE2 library
+ to the standard output and then exit. Anything else on the
command line is ignored.
-v, --invert-match
- Invert the sense of the match, so that lines which do not
+ Invert the sense of the match, so that lines which do not
match any of the patterns are the ones that are found.
-w, --word-regex, --word-regexp
Force the patterns to match only whole words. This is equiva-
- lent to having \b at the start and end of the pattern. This
- option applies only to the patterns that are matched against
- the contents of files; it does not apply to patterns speci-
+ lent to having \b at the start and end of the pattern. This
+ option applies only to the patterns that are matched against
+ the contents of files; it does not apply to patterns speci-
fied by any of the --include or --exclude options.
-x, --line-regex, --line-regexp
- Force the patterns to be anchored (each must start matching
- at the beginning of a line) and in addition, require them to
- match entire lines. In multiline mode the match may be more
+ Force the patterns to be anchored (each must start matching
+ at the beginning of a line) and in addition, require them to
+ match entire lines. In multiline mode the match may be more
than one line. This is equivalent to having \A and \Z charac-
- ters at the start and end of each alternative top-level
+ ters at the start and end of each alternative top-level
branch in every pattern. This option applies only to the pat-
terns that are matched against the contents of files; it does
- not apply to patterns specified by any of the --include or
+ not apply to patterns specified by any of the --include or
--exclude options.
ENVIRONMENT VARIABLES
- The environment variables LC_ALL and LC_CTYPE are examined, in that
- order, for a locale. The first one that is set is used. This can be
- overridden by the --locale option. If no locale is set, the PCRE2
+ The environment variables LC_ALL and LC_CTYPE are examined, in that
+ order, for a locale. The first one that is set is used. This can be
+ overridden by the --locale option. If no locale is set, the PCRE2
library's default (usually the "C" locale) is used.
@@ -732,14 +746,14 @@
The -N (--newline) option allows pcre2grep to scan files with different
newline conventions from the default. Any parts of the input files that
- are written to the standard output are copied identically, with what-
- ever newline sequences they have in the input. However, the setting of
- this option does not affect the interpretation of files specified by
+ are written to the standard output are copied identically, with what-
+ ever newline sequences they have in the input. However, the setting of
+ this option does not affect the interpretation of files specified by
the -f, --exclude-from, or --include-from options, which are assumed to
- use the operating system's standard newline sequence, nor does it
- affect the way in which pcre2grep writes informational messages to the
+ use the operating system's standard newline sequence, nor does it
+ affect the way in which pcre2grep writes informational messages to the
standard error and output streams. For these it uses the string "\n" to
- indicate newlines, relying on the C I/O library to convert this to an
+ indicate newlines, relying on the C I/O library to convert this to an
appropriate sequence.
@@ -746,18 +760,18 @@
OPTIONS COMPATIBILITY
Many of the short and long forms of pcre2grep's options are the same as
- in the GNU grep program. Any long option of the form --xxx-regexp (GNU
+ in the GNU grep program. Any long option of the form --xxx-regexp (GNU
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, --output, -u, and --utf-8 options are specific to
- pcre2grep, as is the use of the --only-matching option with a capturing
- parentheses number.
+ ever, the --depth-limit, --file-list, --file-offsets, --heap-limit,
+ --include-dir, --line-offsets, --locale, --match-limit, -M, --multi-
+ line, -N, --newline, --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.
- Although most of the common options work the same way, a few are dif-
- ferent in pcre2grep. For example, the --include option's argument is a
- glob for GNU grep, but a regular expression for pcre2grep. If both the
- -c and -l options are given, GNU grep lists only file names, without
+ Although most of the common options work the same way, a few are dif-
+ ferent in pcre2grep. For example, the --include option's argument is a
+ glob for GNU grep, but a regular expression for pcre2grep. If both the
+ -c and -l options are given, GNU grep lists only file names, without
counts, but pcre2grep gives the counts as well.
@@ -764,7 +778,7 @@
OPTIONS WITH DATA
There are four different ways in which an option with data can be spec-
- ified. If a short form option is used, the data may follow immedi-
+ ified. If a short form option is used, the data may follow immedi-
ately, or (with one exception) in the next command line item. For exam-
ple:
@@ -771,60 +785,60 @@
-f/some/file
-f /some/file
- The exception is the -o option, which may appear with or without data.
- Because of this, if data is present, it must follow immediately in the
+ The exception is the -o option, which may appear with or without data.
+ Because of this, if data is present, it must follow immediately in the
same item, for example -o3.
- If a long form option is used, the data may appear in the same command
- line item, separated by an equals character, or (with two exceptions)
+ If a long form option is used, the data may appear in the same command
+ line item, separated by an equals character, or (with two exceptions)
it may appear in the next command line item. For example:
--file=/some/file
--file /some/file
- Note, however, that if you want to supply a file name beginning with ~
- as data in a shell command, and have the shell expand ~ to a home
+ Note, however, that if you want to supply a file name beginning with ~
+ as data in a shell command, and have the shell expand ~ to a home
directory, you must separate the file name from the option, because the
shell does not treat ~ specially unless it is at the start of an item.
- The exceptions to the above are the --colour (or --color) and --only-
- matching options, for which the data is optional. If one of these
- options does have data, it must be given in the first form, using an
+ The exceptions to the above are the --colour (or --color) and --only-
+ matching options, for which the data is optional. If one of these
+ options does have data, it must be given in the first form, using an
equals character. Otherwise pcre2grep will assume that it has no data.
USING PCRE2'S CALLOUT FACILITY
- pcre2grep has, by default, support for calling external programs or
- 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
+ pcre2grep has, by default, support for calling external programs or
+ 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;
+ 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;
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-
+ 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 \
@@ -840,49 +854,49 @@
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
+ 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-
+ 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
+ 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
- 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
- these options above).
+ The --match-limit option of pcre2grep can be used to set the overall
+ resource limit. There are also other limits that affect the amount of
+ memory used during matching; see the discussion of --heap-limit and
+ --depth-limit above.
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.
@@ -901,5 +915,5 @@
REVISION
- Last updated: 06 April 2017
+ Last updated: 11 April 2017
Copyright (c) 1997-2017 University of Cambridge.
Modified: code/trunk/doc/pcre2pattern.3
===================================================================
--- code/trunk/doc/pcre2pattern.3 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2pattern.3 2017-04-11 11:47:25 UTC (rev 739)
@@ -1,4 +1,4 @@
-.TH PCRE2PATTERN 3 "03 April 2017" "PCRE2 10.30"
+.TH PCRE2PATTERN 3 "11 April 2017" "PCRE2 10.30"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH "PCRE2 REGULAR EXPRESSION DETAILS"
@@ -138,14 +138,15 @@
\fBpcre2_jit_compile()\fP is ignored.
.
.
-.SS "Setting match and backtracking depth limits"
+.SS "Setting match resource limits"
.rs
.sp
The pcre2_match() function contains a counter that is incremented every time it
goes round its main loop. The caller of \fBpcre2_match()\fP can set a limit on
this counter, which therefore limits the amount of computing resource used for
-a match. The maximum depth of nested backtracking can also be limited, and this
-restricts the amount of heap memory that is used.
+a match. The maximum depth of nested backtracking can also be limited; this
+indirectly restricts the amount of heap memory that is used, but there is also
+an explicit memory limit that can be set.
.P
These facilities are provided to catch runaway matches that are provoked by
patterns with huge matching trees (a typical example is a pattern with nested
@@ -153,6 +154,7 @@
these limits is reached, \fBpcre2_match()\fP gives an error return. The limits
can also be set by items at the start of the pattern of the form
.sp
+ (*LIMIT_HEAP=d)
(*LIMIT_MATCH=d)
(*LIMIT_DEPTH=d)
.sp
@@ -165,11 +167,13 @@
Prior to release 10.30, LIMIT_DEPTH was called LIMIT_RECURSION. This name is
still recognized for backwards compatibility.
.P
-The match limit is used (but in a different way) when JIT is being used, but it
-is not relevant, and is ignored, when matching with \fBpcre2_dfa_match()\fP.
-However, the depth limit is relevant for DFA matching, which uses function
-recursion for recursions within the pattern. In this case, the depth limit
-controls the amount of system stack that is used.
+The heap limit applies only when the \fBpcre2_match()\fP interpreter is used
+for matching. It does not apply to JIT or DFA matching. The match limit is used
+(but in a different way) when JIT is being used, but it is not relevant, and is
+ignored, when matching with \fBpcre2_dfa_match()\fP. The depth limit is ignored
+by JIT but is relevant for DFA matching, which uses function recursion for
+recursions within the pattern. In this case, the depth limit controls the
+amount of system stack that is used.
.
.
.\" HTML <a name="newlines"></a>
@@ -3465,6 +3469,6 @@
.rs
.sp
.nf
-Last updated: 03 April 2017
+Last updated: 11 April 2017
Copyright (c) 1997-2017 University of Cambridge.
.fi
Modified: code/trunk/doc/pcre2perform.3
===================================================================
--- code/trunk/doc/pcre2perform.3 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2perform.3 2017-04-11 11:47:25 UTC (rev 739)
@@ -1,4 +1,4 @@
-.TH PCRE2PERFORM 3 "31 March 2017" "PCRE2 10.30"
+.TH PCRE2PERFORM 3 "08 April 2017" "PCRE2 10.30"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH "PCRE2 PERFORMANCE"
@@ -69,11 +69,12 @@
uses very little system stack at run time. In earlier releases recursive
function calls could use a great deal of stack, and this could cause problems,
but this usage has been eliminated. Backtracking positions are now explicitly
-remembered in memory frames controlled by the code. An initial 10K vector of
-frames is allocated on the system stack (enough for about 50 frames for small
-patterns), but if this is insufficient, heap memory is used. Rewriting patterns
-to be time-efficient, as described below, may also reduce the memory
-requirements.
+remembered in memory frames controlled by the code. An initial 20K vector of
+frames is allocated on the system stack (enough for about 100 frames for small
+patterns), but if this is insufficient, heap memory is used. The amount of heap
+memory can be limited; if the limit is set to zero, only the initial stack
+vector is used. Rewriting patterns to be time-efficient, as described below,
+may also reduce the memory requirements.
.P
In contrast to \fBpcre2_match()\fP, \fBpcre2_dfa_match()\fP does use recursive
function calls, but only for processing atomic groups, lookaround assertions,
@@ -231,6 +232,6 @@
.rs
.sp
.nf
-Last updated: 31 March 2017
+Last updated: 08 April 2017
Copyright (c) 1997-2017 University of Cambridge.
.fi
Modified: code/trunk/doc/pcre2test.1
===================================================================
--- code/trunk/doc/pcre2test.1 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2test.1 2017-04-11 11:47:25 UTC (rev 739)
@@ -1,4 +1,4 @@
-.TH PCRE2TEST 1 "08 April 2017" "PCRE 10.30"
+.TH PCRE2TEST 1 "11 April 2017" "PCRE 10.30"
.SH NAME
pcre2test - a program for testing Perl-compatible regular expressions.
.SH SYNOPSIS
@@ -1063,6 +1063,7 @@
get=<number or name> extract captured substring
getall extract all captured substrings
/g global global matching
+ heap_limit=<n> set a limit on heap memory
jitstack=<n> set size of JIT stack
mark show mark values
match_limit=<n> set a match limit
@@ -1293,11 +1294,11 @@
complicated patterns.
.
.
-.SS "Setting match and depth limits"
+.SS "Setting heap, match, and depth limits"
.rs
.sp
-The \fBmatch_limit\fP and \fBdepth_limit\fP modifiers set the appropriate
-limits in the match context. These values are ignored when the
+The \fBheap_limit\fP, \fBmatch_limit\fP, and \fBdepth_limit\fP modifiers set
+the appropriate limits in the match context. These values are ignored when the
\fBfind_limits\fP modifier is specified.
.
.
@@ -1306,8 +1307,8 @@
.sp
If the \fBfind_limits\fP modifier is present on a subject line, \fBpcre2test\fP
calls the relevant matching function several times, setting different values in
-the match context via \fBpcre2_set_match_limit()\fP or
-\fBpcre2_set_depth_limit()\fP until it finds the minimum values for each
+the match context via \fBpcre2_set_heap_limit(), \fBpcre2_set_match_limit()\fP,
+or \fBpcre2_set_depth_limit()\fP until it finds the minimum values for each
parameter that allows the match to complete without error.
.P
If JIT is being used, only the match limit is relevant. If DFA matching is
@@ -1320,9 +1321,9 @@
increasing length of subject string.
.P
For non-DFA matching, the minimum \fIdepth_limit\fP number is a measure of how
-much memory for recording backtracking points is needed to complete the match
-attempt. In the case of DFA matching, \fIdepth_limit\fP controls the depth of
-recursive calls of the internal function that is used for handling pattern
+much nested backtracking happens (that is, how deeply the pattern's tree is
+searched). In the case of DFA matching, \fIdepth_limit\fP controls the depth of
+recursive calls of the internal function that is used for handling pattern
recursion, lookaround assertions, and atomic groups.
.
.
@@ -1782,6 +1783,6 @@
.rs
.sp
.nf
-Last updated: 08 April 2017
+Last updated: 11 April 2017
Copyright (c) 1997-2017 University of Cambridge.
.fi
Modified: code/trunk/doc/pcre2test.txt
===================================================================
--- code/trunk/doc/pcre2test.txt 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/doc/pcre2test.txt 2017-04-11 11:47:25 UTC (rev 739)
@@ -185,6 +185,12 @@
successful compilation, each pattern is passed to the just-
in-time compiler, if available.
+ -jitverify
+ Behave as if each pattern line has the jitverify modifier;
+ after successful compilation, each pattern is passed to the
+ just-in-time compiler, if available, and the use of JIT is
+ verified.
+
-pattern modifier-list
Behave as if each pattern line contains the given modifiers.
@@ -191,25 +197,25 @@
-q Do not output the version number of pcre2test at the start of
execution.
- -S size On Unix-like systems, set the size of the run-time stack to
+ -S size On Unix-like systems, set the size of the run-time stack to
size megabytes.
-subject modifier-list
Behave as if each subject line contains the given modifiers.
- -t Run each compile and match many times with a timer, and out-
- put the resulting times per compile or match. When JIT is
- used, separate times are given for the initial compile and
- the JIT compile. You can control the number of iterations
- that are used for timing by following -t with a number (as a
- separate item on the command line). For example, "-t 1000"
+ -t Run each compile and match many times with a timer, and out-
+ put the resulting times per compile or match. When JIT is
+ used, separate times are given for the initial compile and
+ the JIT compile. You can control the number of iterations
+ that are used for timing by following -t with a number (as a
+ separate item on the command line). For example, "-t 1000"
iterates 1000 times. The default is to iterate 500,000 times.
-tm This is like -t except that it times only the matching phase,
not the compile phase.
- -T -TM These behave like -t and -tm, but in addition, at the end of
- a run, the total times for all compiles and matches are out-
+ -T -TM These behave like -t and -tm, but in addition, at the end of
+ a run, the total times for all compiles and matches are out-
put.
-version Output the PCRE2 version number and then exit.
@@ -217,139 +223,139 @@
DESCRIPTION
- If pcre2test is given two filename arguments, it reads from the first
+ If pcre2test is given two filename arguments, it reads from the first
and writes to the second. If the first name is "-", input is taken from
- the standard input. If pcre2test is given only one argument, it reads
+ the standard input. If pcre2test is given only one argument, it reads
from that file and writes to stdout. Otherwise, it reads from stdin and
writes to stdout.
- When pcre2test is built, a configuration option can specify that it
- should be linked with the libreadline or libedit library. When this is
- done, if the input is from a terminal, it is read using the readline()
+ When pcre2test is built, a configuration option can specify that it
+ should be linked with the libreadline or libedit library. When this is
+ done, if the input is from a terminal, it is read using the readline()
function. This provides line-editing and history facilities. The output
from the -help option states whether or not readline() will be used.
- The program handles any number of tests, each of which consists of a
- set of input lines. Each set starts with a regular expression pattern,
+ The program handles any number of tests, each of which consists of a
+ set of input lines. Each set starts with a regular expression pattern,
followed by any number of subject lines to be matched against that pat-
tern. In between sets of test data, command lines that begin with # may
appear. This file format, with some restrictions, can also be processed
- by the perltest.sh script that is distributed with PCRE2 as a means of
+ by the perltest.sh script that is distributed with PCRE2 as a means of
checking that the behaviour of PCRE2 and Perl is the same.
When the input is a terminal, pcre2test prompts for each line of input,
- using "re>" to prompt for regular expression patterns, and "data>" to
- prompt for subject lines. Command lines starting with # can be entered
+ using "re>" to prompt for regular expression patterns, and "data>" to
+ prompt for subject lines. Command lines starting with # can be entered
only in response to the "re>" prompt.
- Each subject line is matched separately and independently. If you want
+ Each subject line is matched separately and independently. If you want
to do multi-line matches, you have to use the \n escape sequence (or \r
- or \r\n, etc., depending on the newline setting) in a single line of
- input to encode the newline sequences. There is no limit on the length
- of subject lines; the input buffer is automatically extended if it is
- too small. There are replication features that makes it possible to
- generate long repetitive pattern or subject lines without having to
+ or \r\n, etc., depending on the newline setting) in a single line of
+ input to encode the newline sequences. There is no limit on the length
+ of subject lines; the input buffer is automatically extended if it is
+ too small. There are replication features that makes it possible to
+ generate long repetitive pattern or subject lines without having to
supply them explicitly.
- An empty line or the end of the file signals the end of the subject
- lines for a test, at which point a new pattern or command line is
+ An empty line or the end of the file signals the end of the subject
+ lines for a test, at which point a new pattern or command line is
expected if there is still input to be read.
COMMAND LINES
- In between sets of test data, a line that begins with # is interpreted
+ In between sets of test data, a line that begins with # is interpreted
as a command line. If the first character is followed by white space or
- an exclamation mark, the line is treated as a comment, and ignored.
+ an exclamation mark, the line is treated as a comment, and ignored.
Otherwise, the following commands are recognized:
#forbid_utf
- Subsequent patterns automatically have the PCRE2_NEVER_UTF and
- PCRE2_NEVER_UCP options set, which locks out the use of the PCRE2_UTF
- and PCRE2_UCP options and the use of (*UTF) and (*UCP) at the start of
- patterns. This command also forces an error if a subsequent pattern
- contains any occurrences of \P, \p, or \X, which are still supported
- when PCRE2_UTF is not set, but which require Unicode property support
+ Subsequent patterns automatically have the PCRE2_NEVER_UTF and
+ PCRE2_NEVER_UCP options set, which locks out the use of the PCRE2_UTF
+ and PCRE2_UCP options and the use of (*UTF) and (*UCP) at the start of
+ patterns. This command also forces an error if a subsequent pattern
+ contains any occurrences of \P, \p, or \X, which are still supported
+ when PCRE2_UTF is not set, but which require Unicode property support
to be included in the library.
- This is a trigger guard that is used in test files to ensure that UTF
- or Unicode property tests are not accidentally added to files that are
- used when Unicode support is not included in the library. Setting
- PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as a default can also be obtained
- by the use of #pattern; the difference is that #forbid_utf cannot be
- unset, and the automatic options are not displayed in pattern informa-
+ This is a trigger guard that is used in test files to ensure that UTF
+ or Unicode property tests are not accidentally added to files that are
+ used when Unicode support is not included in the library. Setting
+ PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as a default can also be obtained
+ by the use of #pattern; the difference is that #forbid_utf cannot be
+ unset, and the automatic options are not displayed in pattern informa-
tion, to avoid cluttering up test output.
#load <filename>
This command is used to load a set of precompiled patterns from a file,
- as described in the section entitled "Saving and restoring compiled
+ as described in the section entitled "Saving and restoring compiled
patterns" below.
#newline_default [<newline-list>]
- When PCRE2 is built, a default newline convention can be specified.
- This determines which characters and/or character pairs are recognized
+ When PCRE2 is built, a default newline convention can be specified.
+ This determines which characters and/or character pairs are recognized
as indicating a newline in a pattern or subject string. The default can
- be overridden when a pattern is compiled. The standard test files con-
- tain tests of various newline conventions, but the majority of the
- tests expect a single linefeed to be recognized as a newline by
+ be overridden when a pattern is compiled. The standard test files con-
+ tain tests of various newline conventions, but the majority of the
+ tests expect a single linefeed to be recognized as a newline by
default. Without special action the tests would fail when PCRE2 is com-
piled with either CR or CRLF as the default newline.
The #newline_default command specifies a list of newline types that are
- acceptable as the default. The types must be one of CR, LF, CRLF, ANY-
+ acceptable as the default. The types must be one of CR, LF, CRLF, ANY-
CRLF, or ANY (in upper or lower case), for example:
#newline_default LF Any anyCRLF
If the default newline is in the list, this command has no effect. Oth-
- erwise, except when testing the POSIX API, a newline modifier that
- specifies the first newline convention in the list (LF in the above
- example) is added to any pattern that does not already have a newline
+ erwise, except when testing the POSIX API, a newline modifier that
+ specifies the first newline convention in the list (LF in the above
+ example) is added to any pattern that does not already have a newline
modifier. If the newline list is empty, the feature is turned off. This
command is present in a number of the standard test input files.
- When the POSIX API is being tested there is no way to override the
- default newline convention, though it is possible to set the newline
- convention from within the pattern. A warning is given if the posix
+ When the POSIX API is being tested there is no way to override the
+ default newline convention, though it is possible to set the newline
+ convention from within the pattern. A warning is given if the posix
modifier is used when #newline_default would set a default for the non-
POSIX API.
#pattern <modifier-list>
- This command sets a default modifier list that applies to all subse-
+ This command sets a default modifier list that applies to all subse-
quent patterns. Modifiers on a pattern can change these settings.
#perltest
- The appearance of this line causes all subsequent modifier settings to
+ The appearance of this line causes all subsequent modifier settings to
be checked for compatibility with the perltest.sh script, which is used
- to confirm that Perl gives the same results as PCRE2. Also, apart from
- comment lines, none of the other command lines are permitted, because
- they and many of the modifiers are specific to pcre2test, and should
- not be used in test files that are also processed by perltest.sh. The
- #perltest command helps detect tests that are accidentally put in the
+ to confirm that Perl gives the same results as PCRE2. Also, apart from
+ comment lines, none of the other command lines are permitted, because
+ they and many of the modifiers are specific to pcre2test, and should
+ not be used in test files that are also processed by perltest.sh. The
+ #perltest command helps detect tests that are accidentally put in the
wrong file.
#pop [<modifiers>]
#popcopy [<modifiers>]
- These commands are used to manipulate the stack of compiled patterns,
- as described in the section entitled "Saving and restoring compiled
+ These commands are used to manipulate the stack of compiled patterns,
+ as described in the section entitled "Saving and restoring compiled
patterns" below.
#save <filename>
- This command is used to save a set of compiled patterns to a file, as
- described in the section entitled "Saving and restoring compiled pat-
+ This command is used to save a set of compiled patterns to a file, as
+ described in the section entitled "Saving and restoring compiled pat-
terns" below.
#subject <modifier-list>
- This command sets a default modifier list that applies to all subse-
- quent subject lines. Modifiers on a subject line can change these set-
+ This command sets a default modifier list that applies to all subse-
+ quent subject lines. Modifiers on a subject line can change these set-
tings.
@@ -357,58 +363,58 @@
Modifier lists are used with both pattern and subject lines. Items in a
list are separated by commas followed by optional white space. Trailing
- whitespace in a modifier list is ignored. Some modifiers may be given
- for both patterns and subject lines, whereas others are valid only for
+ whitespace in a modifier list is ignored. Some modifiers may be given
+ for both patterns and subject lines, whereas others are valid only for
one or the other. Each modifier has a long name, for example
- "anchored", and some of them must be followed by an equals sign and a
- value, for example, "offset=12". Values cannot contain comma charac-
- ters, but may contain spaces. Modifiers that do not take values may be
+ "anchored", and some of them must be followed by an equals sign and a
+ value, for example, "offset=12". Values cannot contain comma charac-
+ ters, but may contain spaces. Modifiers that do not take values may be
preceded by a minus sign to turn off a previous setting.
A few of the more common modifiers can also be specified as single let-
- ters, for example "i" for "caseless". In documentation, following the
+ ters, for example "i" for "caseless". In documentation, following the
Perl convention, these are written with a slash ("the /i modifier") for
- clarity. Abbreviated modifiers must all be concatenated in the first
- item of a modifier list. If the first item is not recognized as a long
- modifier name, it is interpreted as a sequence of these abbreviations.
+ clarity. Abbreviated modifiers must all be concatenated in the first
+ item of a modifier list. If the first item is not recognized as a long
+ modifier name, it is interpreted as a sequence of these abbreviations.
For example:
/abc/ig,newline=cr,jit=3
- This is a pattern line whose modifier list starts with two one-letter
- modifiers (/i and /g). The lower-case abbreviated modifiers are the
+ This is a pattern line whose modifier list starts with two one-letter
+ modifiers (/i and /g). The lower-case abbreviated modifiers are the
same as used in Perl.
PATTERN SYNTAX
- A pattern line must start with one of the following characters (common
+ A pattern line must start with one of the following characters (common
symbols, excluding pattern meta-characters):
/ ! " ' ` - = _ : ; , % & @ ~
- This is interpreted as the pattern's delimiter. A regular expression
- may be continued over several input lines, in which case the newline
+ This is interpreted as the pattern's delimiter. A regular expression
+ may be continued over several input lines, in which case the newline
characters are included within it. It is possible to include the delim-
iter within the pattern by escaping it with a backslash, for example
/abc\/def/
- If you do this, the escape and the delimiter form part of the pattern,
+ If you do this, the escape and the delimiter form part of the pattern,
but since the delimiters are all non-alphanumeric, this does not affect
- its interpretation. If the terminating delimiter is immediately fol-
+ its interpretation. If the terminating delimiter is immediately fol-
lowed by a backslash, for example,
/abc/\
- then a backslash is added to the end of the pattern. This is done to
- provide a way of testing the error condition that arises if a pattern
+ then a backslash is added to the end of the pattern. This is done to
+ provide a way of testing the error condition that arises if a pattern
finishes with a backslash, because
/abc\/
- is interpreted as the first line of a pattern that starts with "abc/",
- causing pcre2test to read the next line as a continuation of the regu-
+ is interpreted as the first line of a pattern that starts with "abc/",
+ causing pcre2test to read the next line as a continuation of the regu-
lar expression.
A pattern can be followed by a modifier list (details below).
@@ -416,7 +422,7 @@
SUBJECT LINE SYNTAX
- Before each subject line is passed to pcre2_match() or
+ Before each subject line is passed to pcre2_match() or
pcre2_dfa_match(), leading and trailing white space is removed, and the
line is scanned for backslash escapes. The following provide a means of
encoding non-printing characters in a visible way:
@@ -436,15 +442,15 @@
\x{hh...} hexadecimal character (any number of hex digits)
The use of \x{hh...} is not dependent on the use of the utf modifier on
- the pattern. It is recognized always. There may be any number of hexa-
- decimal digits inside the braces; invalid values provoke error mes-
+ the pattern. It is recognized always. There may be any number of hexa-
+ decimal digits inside the braces; invalid values provoke error mes-
sages.
- Note that \xhh specifies one byte rather than one character in UTF-8
- mode; this makes it possible to construct invalid UTF-8 sequences for
- testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8
- character in UTF-8 mode, generating more than one byte if the value is
- greater than 127. When testing the 8-bit library not in UTF-8 mode,
+ Note that \xhh specifies one byte rather than one character in UTF-8
+ mode; this makes it possible to construct invalid UTF-8 sequences for
+ testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8
+ character in UTF-8 mode, generating more than one byte if the value is
+ greater than 127. When testing the 8-bit library not in UTF-8 mode,
\x{hh} generates one byte for values less than 256, and causes an error
for greater values.
@@ -451,8 +457,8 @@
In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it
possible to construct invalid UTF-16 sequences for testing purposes.
- In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This
- makes it possible to construct invalid UTF-32 sequences for testing
+ In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This
+ makes it possible to construct invalid UTF-32 sequences for testing
purposes.
There is a special backslash sequence that specifies replication of one
@@ -460,45 +466,45 @@
\[<characters>]{<count>}
- This makes it possible to test long strings without having to provide
+ This makes it possible to test long strings without having to provide
them as part of the file. For example:
\[abc]{4}
- is converted to "abcabcabcabc". This feature does not support nesting.
+ is converted to "abcabcabcabc". This feature does not support nesting.
To include a closing square bracket in the characters, code it as \x5D.
- A backslash followed by an equals sign marks the end of the subject
+ A backslash followed by an equals sign marks the end of the subject
string and the start of a modifier list. For example:
abc\=notbol,notempty
- If the subject string is empty and \= is followed by whitespace, the
- line is treated as a comment line, and is not used for matching. For
+ If the subject string is empty and \= is followed by whitespace, the
+ line is treated as a comment line, and is not used for matching. For
example:
\= This is a comment.
abc\= This is an invalid modifier list.
- A backslash followed by any other non-alphanumeric character just
+ A backslash followed by any other non-alphanumeric character just
escapes that character. A backslash followed by anything else causes an
- error. However, if the very last character in the line is a backslash
- (and there is no modifier list), it is ignored. This gives a way of
- passing an empty line as data, since a real empty line terminates the
+ error. However, if the very last character in the line is a backslash
+ (and there is no modifier list), it is ignored. This gives a way of
+ passing an empty line as data, since a real empty line terminates the
data input.
PATTERN MODIFIERS
- There are several types of modifier that can appear in pattern lines.
+ There are several types of modifier that can appear in pattern lines.
Except where noted below, they may also be used in #pattern commands. A
- pattern's modifier list can add to or override default modifiers that
+ pattern's modifier list can add to or override default modifiers that
were set by a previous #pattern command.
Setting compilation options
- The following modifiers set options for pcre2_compile(). The most com-
- mon ones have single-letter abbreviations. See pcre2api for a descrip-
+ The following modifiers set options for pcre2_compile(). The most com-
+ mon ones have single-letter abbreviations. See pcre2api for a descrip-
tion of their effects.
allow_empty_class set PCRE2_ALLOW_EMPTY_CLASS
@@ -530,15 +536,15 @@
utf set PCRE2_UTF
As well as turning on the PCRE2_UTF option, the utf modifier causes all
- non-printing characters in output strings to be printed using the
- \x{hh...} notation. Otherwise, those less than 0x100 are output in hex
- without the curly brackets. Setting utf in 16-bit or 32-bit mode also
- causes pattern and subject strings to be translated to UTF-16 or
+ non-printing characters in output strings to be printed using the
+ \x{hh...} notation. Otherwise, those less than 0x100 are output in hex
+ without the curly brackets. Setting utf in 16-bit or 32-bit mode also
+ causes pattern and subject strings to be translated to UTF-16 or
UTF-32, respectively, before being passed to library functions.
Setting compilation controls
- The following modifiers affect the compilation process or request
+ The following modifiers affect the compilation process or request
information about the pattern:
bsr=[anycrlf|unicode] specify \R handling
@@ -571,34 +577,34 @@
Newline and \R handling
- The bsr modifier specifies what \R in a pattern should match. If it is
- set to "anycrlf", \R matches CR, LF, or CRLF only. If it is set to
- "unicode", \R matches any Unicode newline sequence. The default is
+ The bsr modifier specifies what \R in a pattern should match. If it is
+ set to "anycrlf", \R matches CR, LF, or CRLF only. If it is set to
+ "unicode", \R matches any Unicode newline sequence. The default is
specified when PCRE2 is built, with the default default being Unicode.
- The newline modifier specifies which characters are to be interpreted
+ The newline modifier specifies which characters are to be interpreted
as newlines, both in the pattern and in subject lines. The type must be
one of CR, LF, CRLF, ANYCRLF, or ANY (in upper or lower case).
Information about a pattern
- The debug modifier is a shorthand for info,fullbincode, requesting all
+ The debug modifier is a shorthand for info,fullbincode, requesting all
available information.
The bincode modifier causes a representation of the compiled code to be
- output after compilation. This information does not contain length and
+ output after compilation. This information does not contain length and
offset values, which ensures that the same output is generated for dif-
- ferent internal link sizes and different code unit widths. By using
- bincode, the same regression tests can be used in different environ-
+ ferent internal link sizes and different code unit widths. By using
+ bincode, the same regression tests can be used in different environ-
ments.
- The fullbincode modifier, by contrast, does include length and offset
- values. This is used in a few special tests that run only for specific
+ The fullbincode modifier, by contrast, does include length and offset
+ values. This is used in a few special tests that run only for specific
code unit widths and link sizes, and is also useful for one-off tests.
- The info modifier requests information about the compiled pattern
- (whether it is anchored, has a fixed first character, and so on). The
- information is obtained from the pcre2_pattern_info() function. Here
+ The info modifier requests information about the compiled pattern
+ (whether it is anchored, has a fixed first character, and so on). The
+ information is obtained from the pcre2_pattern_info() function. Here
are some typical examples:
re> /(?i)(^a|^b)/m,info
@@ -616,21 +622,21 @@
Last code unit = 'c' (caseless)
Subject length lower bound = 3
- "Compile options" are those specified by modifiers; "overall options"
- have added options that are taken or deduced from the pattern. If both
- sets of options are the same, just a single "options" line is output;
- if there are no options, the line is omitted. "First code unit" is
- where any match must start; if there is more than one they are listed
- as "starting code units". "Last code unit" is the last literal code
- unit that must be present in any match. This is not necessarily the
- last character. These lines are omitted if no starting or ending code
+ "Compile options" are those specified by modifiers; "overall options"
+ have added options that are taken or deduced from the pattern. If both
+ sets of options are the same, just a single "options" line is output;
+ if there are no options, the line is omitted. "First code unit" is
+ where any match must start; if there is more than one they are listed
+ as "starting code units". "Last code unit" is the last literal code
+ unit that must be present in any match. This is not necessarily the
+ last character. These lines are omitted if no starting or ending code
units are recorded.
- The framesize modifier shows the size, in bytes, of the storage frames
- used by pcre2_match() for handling backtracking. The size depends on
+ The framesize modifier shows the size, in bytes, of the storage frames
+ used by pcre2_match() for handling backtracking. The size depends on
the number of capturing parentheses in the pattern.
- The callout_info modifier requests information about all the callouts
+ The callout_info modifier requests information about all the callouts
in the pattern. A list of them is output at the end of any other infor-
mation that is requested. For each callout, either its number or string
is given, followed by the item that follows it in the pattern.
@@ -637,45 +643,45 @@
Passing a NULL context
- Normally, pcre2test passes a context block to pcre2_compile(). If the
- null_context modifier is set, however, NULL is passed. This is for
- testing that pcre2_compile() behaves correctly in this case (it uses
+ Normally, pcre2test passes a context block to pcre2_compile(). If the
+ null_context modifier is set, however, NULL is passed. This is for
+ testing that pcre2_compile() behaves correctly in this case (it uses
default values).
Specifying the pattern's length
By default, patterns are passed to the compiling functions as zero-ter-
- minated strings. When using the POSIX wrapper API, there is no other
- option. However, when using PCRE2's native API, patterns can be passed
- by length instead of being zero-terminated. The use_length modifier
- causes this to happen. Using a length happens automatically (whether
- or not use_length is set) when hex is set, because patterns specified
+ minated strings. When using the POSIX wrapper API, there is no other
+ option. However, when using PCRE2's native API, patterns can be passed
+ by length instead of being zero-terminated. The use_length modifier
+ causes this to happen. Using a length happens automatically (whether
+ or not use_length is set) when hex is set, because patterns specified
in hexadecimal may contain binary zeros.
Specifying pattern characters in hexadecimal
- The hex modifier specifies that the characters of the pattern, except
- for substrings enclosed in single or double quotes, are to be inter-
- preted as pairs of hexadecimal digits. This feature is provided as a
+ The hex modifier specifies that the characters of the pattern, except
+ for substrings enclosed in single or double quotes, are to be inter-
+ preted as pairs of hexadecimal digits. This feature is provided as a
way of creating patterns that contain binary zeros and other non-print-
- ing characters. White space is permitted between pairs of digits. For
+ ing characters. White space is permitted between pairs of digits. For
example, this pattern contains three characters:
/ab 32 59/hex
- Parts of such a pattern are taken literally if quoted. This pattern
- contains nine characters, only two of which are specified in hexadeci-
+ Parts of such a pattern are taken literally if quoted. This pattern
+ contains nine characters, only two of which are specified in hexadeci-
mal:
/ab "literal" 32/hex
- Either single or double quotes may be used. There is no way of includ-
- ing the delimiter within a substring. The hex and expand modifiers are
+ Either single or double quotes may be used. There is no way of includ-
+ ing the delimiter within a substring. The hex and expand modifiers are
mutually exclusive.
- The POSIX API cannot be used with patterns specified in hexadecimal
+ The POSIX API cannot be used with patterns specified in hexadecimal
because they may contain binary zeros, which conflicts with regcomp()'s
- requirement for a zero-terminated string. Such patterns are always
+ requirement for a zero-terminated string. Such patterns are always
passed to pcre2_compile() as a string with a length, not as zero-termi-
nated.
@@ -682,18 +688,18 @@
Specifying wide characters in 16-bit and 32-bit modes
In 16-bit and 32-bit modes, all input is automatically treated as UTF-8
- and translated to UTF-16 or UTF-32 when the utf modifier is set. For
+ and translated to UTF-16 or UTF-32 when the utf modifier is set. For
testing the 16-bit and 32-bit libraries in non-UTF mode, the utf8_input
- modifier can be used. It is mutually exclusive with utf. Input lines
+ modifier can be used. It is mutually exclusive with utf. Input lines
are interpreted as UTF-8 as a means of specifying wide characters. More
details are given in "Input encoding" above.
Generating long repetitive patterns
- Some tests use long patterns that are very repetitive. Instead of cre-
- ating a very long input line for such a pattern, you can use a special
- repetition feature, similar to the one described for subject lines
- above. If the expand modifier is present on a pattern, parts of the
+ Some tests use long patterns that are very repetitive. Instead of cre-
+ ating a very long input line for such a pattern, you can use a special
+ repetition feature, similar to the one described for subject lines
+ above. If the expand modifier is present on a pattern, parts of the
pattern that have the form
\[<characters>]{<count>}
@@ -700,34 +706,34 @@
are expanded before the pattern is passed to pcre2_compile(). For exam-
ple, \[AB]{6000} is expanded to "ABAB..." 6000 times. This construction
- cannot be nested. An initial "\[" sequence is recognized only if "]{"
- followed by decimal digits and "}" is found later in the pattern. If
+ cannot be nested. An initial "\[" sequence is recognized only if "]{"
+ followed by decimal digits and "}" is found later in the pattern. If
not, the characters remain in the pattern unaltered. The expand and hex
modifiers are mutually exclusive.
- If part of an expanded pattern looks like an expansion, but is really
+ If part of an expanded pattern looks like an expansion, but is really
part of the actual pattern, unwanted expansion can be avoided by giving
two values in the quantifier. For example, \[AB]{6000,6000} is not rec-
ognized as an expansion item.
- If the info modifier is set on an expanded pattern, the result of the
+ If the info modifier is set on an expanded pattern, the result of the
expansion is included in the information that is output.
JIT compilation
- Just-in-time (JIT) compiling is a heavyweight optimization that can
- greatly speed up pattern matching. See the pcre2jit documentation for
- details. JIT compiling happens, optionally, after a pattern has been
- successfully compiled into an internal form. The JIT compiler converts
+ Just-in-time (JIT) compiling is a heavyweight optimization that can
+ greatly speed up pattern matching. See the pcre2jit documentation for
+ details. JIT compiling happens, optionally, after a pattern has been
+ successfully compiled into an internal form. The JIT compiler converts
this to optimized machine code. It needs to know whether the match-time
options PCRE2_PARTIAL_HARD and PCRE2_PARTIAL_SOFT are going to be used,
- because different code is generated for the different cases. See the
- partial modifier in "Subject Modifiers" below for details of how these
+ because different code is generated for the different cases. See the
+ partial modifier in "Subject Modifiers" below for details of how these
options are specified for each match attempt.
- JIT compilation is requested by the /jit pattern modifier, which may
+ JIT compilation is requested by the /jit pattern modifier, which may
optionally be followed by an equals sign and a number in the range 0 to
- 7. The three bits that make up the number specify which of the three
+ 7. The three bits that make up the number specify which of the three
JIT operating modes are to be compiled:
1 compile JIT code for non-partial matching
@@ -744,31 +750,31 @@
6 soft and hard partial matching only
7 all three modes
- If no number is given, 7 is assumed. The phrase "partial matching"
+ If no number is given, 7 is assumed. The phrase "partial matching"
means a call to pcre2_match() with either the PCRE2_PARTIAL_SOFT or the
- PCRE2_PARTIAL_HARD option set. Note that such a call may return a com-
+ PCRE2_PARTIAL_HARD option set. Note that such a call may return a com-
plete match; the options enable the possibility of a partial match, but
- do not require it. Note also that if you request JIT compilation only
- for partial matching (for example, /jit=2) but do not set the partial
- modifier on a subject line, that match will not use JIT code because
+ do not require it. Note also that if you request JIT compilation only
+ for partial matching (for example, /jit=2) but do not set the partial
+ modifier on a subject line, that match will not use JIT code because
none was compiled for non-partial matching.
- If JIT compilation is successful, the compiled JIT code will automati-
- cally be used when an appropriate type of match is run, except when
- incompatible run-time options are specified. For more details, see the
- pcre2jit documentation. See also the jitstack modifier below for a way
+ If JIT compilation is successful, the compiled JIT code will automati-
+ cally be used when an appropriate type of match is run, except when
+ incompatible run-time options are specified. For more details, see the
+ pcre2jit documentation. See also the jitstack modifier below for a way
of setting the size of the JIT stack.
- If the jitfast modifier is specified, matching is done using the JIT
- "fast path" interface, pcre2_jit_match(), which skips some of the san-
- ity checks that are done by pcre2_match(), and of course does not work
- when JIT is not supported. If jitfast is specified without jit, jit=7
+ If the jitfast modifier is specified, matching is done using the JIT
+ "fast path" interface, pcre2_jit_match(), which skips some of the san-
+ ity checks that are done by pcre2_match(), and of course does not work
+ when JIT is not supported. If jitfast is specified without jit, jit=7
is assumed.
- If the jitverify modifier is specified, information about the compiled
- pattern shows whether JIT compilation was or was not successful. If
- jitverify is specified without jit, jit=7 is assumed. If JIT compila-
- tion is successful when jitverify is set, the text "(JIT)" is added to
+ If the jitverify modifier is specified, information about the compiled
+ pattern shows whether JIT compilation was or was not successful. If
+ jitverify is specified without jit, jit=7 is assumed. If JIT compila-
+ tion is successful when jitverify is set, the text "(JIT)" is added to
the first output line after a match or non match when JIT-compiled code
was actually used in the match.
@@ -779,19 +785,19 @@
/pattern/locale=fr_FR
The given locale is set, pcre2_maketables() is called to build a set of
- character tables for the locale, and this is then passed to pcre2_com-
- pile() when compiling the regular expression. The same tables are used
- when matching the following subject lines. The locale modifier applies
+ character tables for the locale, and this is then passed to pcre2_com-
+ pile() when compiling the regular expression. The same tables are used
+ when matching the following subject lines. The locale modifier applies
only to the pattern on which it appears, but can be given in a #pattern
- command if a default is needed. Setting a locale and alternate charac-
+ command if a default is needed. Setting a locale and alternate charac-
ter tables are mutually exclusive.
Showing pattern memory
The memory modifier causes the size in bytes of the memory used to hold
- the compiled pattern to be output. This does not include the size of
- the pcre2_code block; it is just the actual compiled data. If the pat-
- tern is subsequently passed to the JIT compiler, the size of the JIT
+ the compiled pattern to be output. This does not include the size of
+ the pcre2_code block; it is just the actual compiled data. If the pat-
+ tern is subsequently passed to the JIT compiler, the size of the JIT
compiled code is also output. Here is an example:
re> /a(b)c/jit,memory
@@ -801,27 +807,27 @@
Limiting nested parentheses
- The parens_nest_limit modifier sets a limit on the depth of nested
- parentheses in a pattern. Breaching the limit causes a compilation
- error. The default for the library is set when PCRE2 is built, but
- pcre2test sets its own default of 220, which is required for running
+ The parens_nest_limit modifier sets a limit on the depth of nested
+ parentheses in a pattern. Breaching the limit causes a compilation
+ error. The default for the library is set when PCRE2 is built, but
+ pcre2test sets its own default of 220, which is required for running
the standard test suite.
Limiting the pattern length
- The max_pattern_length modifier sets a limit, in code units, to the
+ The max_pattern_length modifier sets a limit, in code units, to the
length of pattern that pcre2_compile() will accept. Breaching the limit
- causes a compilation error. The default is the largest number a
+ causes a compilation error. The default is the largest number a
PCRE2_SIZE variable can hold (essentially unlimited).
Using the POSIX wrapper API
- The /posix and posix_nosub modifiers cause pcre2test to call PCRE2 via
- the POSIX wrapper API rather than its native API. When posix_nosub is
- used, the POSIX option REG_NOSUB is passed to regcomp(). The POSIX
- wrapper supports only the 8-bit library. Note that it does not imply
+ The /posix and posix_nosub modifiers cause pcre2test to call PCRE2 via
+ the POSIX wrapper API rather than its native API. When posix_nosub is
+ used, the POSIX option REG_NOSUB is passed to regcomp(). The POSIX
+ wrapper supports only the 8-bit library. Note that it does not imply
POSIX matching semantics; for more detail see the pcre2posix documenta-
- tion. The following pattern modifiers set options for the regcomp()
+ tion. The following pattern modifiers set options for the regcomp()
function:
caseless REG_ICASE
@@ -831,35 +837,35 @@
ucp REG_UCP ) the POSIX standard
utf REG_UTF8 )
- The regerror_buffsize modifier specifies a size for the error buffer
- that is passed to regerror() in the event of a compilation error. For
+ The regerror_buffsize modifier specifies a size for the error buffer
+ that is passed to regerror() in the event of a compilation error. For
example:
/abc/posix,regerror_buffsize=20
- This provides a means of testing the behaviour of regerror() when the
- buffer is too small for the error message. If this modifier has not
+ This provides a means of testing the behaviour of regerror() when the
+ buffer is too small for the error message. If this modifier has not
been set, a large buffer is used.
- The aftertext and allaftertext subject modifiers work as described
- below. All other modifiers are either ignored, with a warning message,
+ The aftertext and allaftertext subject modifiers work as described
+ below. All other modifiers are either ignored, with a warning message,
or cause an error.
Testing the stack guard feature
- The stackguard modifier is used to test the use of pcre2_set_com-
- pile_recursion_guard(), a function that is provided to enable stack
- availability to be checked during compilation (see the pcre2api docu-
- mentation for details). If the number specified by the modifier is
+ The stackguard modifier is used to test the use of pcre2_set_com-
+ pile_recursion_guard(), a function that is provided to enable stack
+ availability to be checked during compilation (see the pcre2api docu-
+ mentation for details). If the number specified by the modifier is
greater than zero, pcre2_set_compile_recursion_guard() is called to set
- up callback from pcre2_compile() to a local function. The argument it
- receives is the current nesting parenthesis depth; if this is greater
+ up callback from pcre2_compile() to a local function. The argument it
+ receives is the current nesting parenthesis depth; if this is greater
than the value given by the modifier, non-zero is returned, causing the
compilation to be aborted.
Using alternative character tables
- The value specified for the tables modifier must be one of the digits
+ The value specified for the tables modifier must be one of the digits
0, 1, or 2. It causes a specific set of built-in character tables to be
passed to pcre2_compile(). This is used in the PCRE2 tests to check be-
haviour with different character tables. The digit specifies the tables
@@ -870,15 +876,15 @@
pcre2_chartables.c.dist
2 a set of tables defining ISO 8859 characters
- In table 2, some characters whose codes are greater than 128 are iden-
- tified as letters, digits, spaces, etc. Setting alternate character
+ In table 2, some characters whose codes are greater than 128 are iden-
+ tified as letters, digits, spaces, etc. Setting alternate character
tables and a locale are mutually exclusive.
Setting certain match controls
The following modifiers are really subject modifiers, and are described
- below. However, they may be included in a pattern's modifier list, in
- which case they are applied to every subject line that is processed
+ below. However, they may be included in a pattern's modifier list, in
+ which case they are applied to every subject line that is processed
with that pattern. They may not appear in #pattern commands. These mod-
ifiers do not affect the compilation process.
@@ -895,24 +901,24 @@
substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET
substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY
- These modifiers may not appear in a #pattern command. If you want them
+ These modifiers may not appear in a #pattern command. If you want them
as defaults, set them in a #subject command.
Saving a compiled pattern
- When a pattern with the push modifier is successfully compiled, it is
- pushed onto a stack of compiled patterns, and pcre2test expects the
- next line to contain a new pattern (or a command) instead of a subject
+ When a pattern with the push modifier is successfully compiled, it is
+ pushed onto a stack of compiled patterns, and pcre2test expects the
+ next line to contain a new pattern (or a command) instead of a subject
line. This facility is used when saving compiled patterns to a file, as
- described in the section entitled "Saving and restoring compiled pat-
- terns" below. If pushcopy is used instead of push, a copy of the com-
- piled pattern is stacked, leaving the original as current, ready to
- match the following input lines. This provides a way of testing the
- pcre2_code_copy() function. The push and pushcopy modifiers are
- incompatible with compilation modifiers such as global that act at
- match time. Any that are specified are ignored (for the stacked copy),
+ described in the section entitled "Saving and restoring compiled pat-
+ terns" below. If pushcopy is used instead of push, a copy of the com-
+ piled pattern is stacked, leaving the original as current, ready to
+ match the following input lines. This provides a way of testing the
+ pcre2_code_copy() function. The push and pushcopy modifiers are
+ incompatible with compilation modifiers such as global that act at
+ match time. Any that are specified are ignored (for the stacked copy),
with a warning message, except for replace, which causes an error. Note
- that jitverify, which is allowed, does not carry through to any subse-
+ that jitverify, which is allowed, does not carry through to any subse-
quent matching that uses a stacked pattern.
@@ -923,7 +929,7 @@
Setting match options
- The following modifiers set options for pcre2_match() or
+ The following modifiers set options for pcre2_match() or
pcre2_dfa_match(). See pcreapi for a description of their effects.
anchored set PCRE2_ANCHORED
@@ -939,20 +945,20 @@
partial_hard (or ph) set PCRE2_PARTIAL_HARD
partial_soft (or ps) set PCRE2_PARTIAL_SOFT
- The partial matching modifiers are provided with abbreviations because
+ The partial matching modifiers are provided with abbreviations because
they appear frequently in tests.
- If the posix modifier was present on the pattern, causing the POSIX
+ If the posix modifier was present on the pattern, causing the POSIX
wrapper API to be used, the only option-setting modifiers that have any
- effect are notbol, notempty, and noteol, causing REG_NOTBOL,
- REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec().
+ effect are notbol, notempty, and noteol, causing REG_NOTBOL,
+ REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec().
The other modifiers are ignored, with a warning message.
Setting match controls
- The following modifiers affect the matching process or request addi-
- tional information. Some of them may also be specified on a pattern
- line (see above), in which case they apply to every subject line that
+ The following modifiers affect the matching process or request addi-
+ tional information. Some of them may also be specified on a pattern
+ line (see above), in which case they apply to every subject line that
is matched against that pattern.
aftertext show text after match
@@ -972,6 +978,7 @@
get=<number or name> extract captured substring
getall extract all captured substrings
/g global global matching
+ heap_limit=<n> set a limit on heap memory
jitstack=<n> set size of JIT stack
mark show mark values
match_limit=<n> set a match limit
@@ -991,29 +998,29 @@
zero_terminate pass the subject as zero-terminated
The effects of these modifiers are described in the following sections.
- When matching via the POSIX wrapper API, the aftertext, allaftertext,
- and ovector subject modifiers work as described below. All other modi-
+ When matching via the POSIX wrapper API, the aftertext, allaftertext,
+ and ovector subject modifiers work as described below. All other modi-
fiers are either ignored, with a warning message, or cause an error.
Showing more text
- The aftertext modifier requests that as well as outputting the part of
+ The aftertext modifier requests that as well as outputting the part of
the subject string that matched the entire pattern, pcre2test should in
addition output the remainder of the subject string. This is useful for
tests where the subject contains multiple copies of the same substring.
- The allaftertext modifier requests the same action for captured sub-
+ The allaftertext modifier requests the same action for captured sub-
strings as well as the main matched substring. In each case the remain-
der is output on the following line with a plus character following the
capture number.
- The allusedtext modifier requests that all the text that was consulted
- during a successful pattern match by the interpreter should be shown.
- This feature is not supported for JIT matching, and if requested with
- JIT it is ignored (with a warning message). Setting this modifier
+ The allusedtext modifier requests that all the text that was consulted
+ during a successful pattern match by the interpreter should be shown.
+ This feature is not supported for JIT matching, and if requested with
+ JIT it is ignored (with a warning message). Setting this modifier
affects the output if there is a lookbehind at the start of a match, or
- a lookahead at the end, or if \K is used in the pattern. Characters
- that precede or follow the start and end of the actual match are indi-
- cated in the output by '<' or '>' characters underneath them. Here is
+ a lookahead at the end, or if \K is used in the pattern. Characters
+ that precede or follow the start and end of the actual match are indi-
+ cated in the output by '<' or '>' characters underneath them. Here is
an example:
re> /(?<=pqr)abc(?=xyz)/
@@ -1021,16 +1028,16 @@
0: pqrabcxyz
<<< >>>
- This shows that the matched string is "abc", with the preceding and
- following strings "pqr" and "xyz" having been consulted during the
+ This shows that the matched string is "abc", with the preceding and
+ following strings "pqr" and "xyz" having been consulted during the
match (when processing the assertions).
- The startchar modifier requests that the starting character for the
- match be indicated, if it is different to the start of the matched
+ The startchar modifier requests that the starting character for the
+ match be indicated, if it is different to the start of the matched
string. The only time when this occurs is when \K has been processed as
part of the match. In this situation, the output for the matched string
- is displayed from the starting character instead of from the match
- point, with circumflex characters under the earlier characters. For
+ is displayed from the starting character instead of from the match
+ point, with circumflex characters under the earlier characters. For
example:
re> /abc\Kxyz/
@@ -1038,7 +1045,7 @@
0: abcxyz
^^^
- Unlike allusedtext, the startchar modifier can be used with JIT. How-
+ Unlike allusedtext, the startchar modifier can be used with JIT. How-
ever, these two modifiers are mutually exclusive.
Showing the value of all capture groups
@@ -1046,98 +1053,98 @@
The allcaptures modifier requests that the values of all potential cap-
tured parentheses be output after a match. By default, only those up to
the highest one actually used in the match are output (corresponding to
- the return code from pcre2_match()). Groups that did not take part in
- the match are output as "<unset>". This modifier is not relevant for
- DFA matching (which does no capturing); it is ignored, with a warning
+ the return code from pcre2_match()). Groups that did not take part in
+ the match are output as "<unset>". This modifier is not relevant for
+ DFA matching (which does no capturing); it is ignored, with a warning
message, if present.
Testing callouts
- A callout function is supplied when pcre2test calls the library match-
- ing functions, unless callout_none is specified. If callout_capture is
- set, the current captured groups are output when a callout occurs. The
+ A callout function is supplied when pcre2test calls the library match-
+ ing functions, unless callout_none is specified. If callout_capture is
+ set, the current captured groups are output when a callout occurs. The
default return from the callout function is zero, which allows matching
to continue.
- The callout_fail modifier can be given one or two numbers. If there is
- only one number, 1 is returned instead of 0 (causing matching to back-
- track) when a callout of that number is reached. If two numbers
- (<n>:<m>) are given, 1 is returned when callout <n> is reached and
- there have been at least <m> callouts. The callout_error modifier is
- similar, except that PCRE2_ERROR_CALLOUT is returned, causing the
- entire matching process to be aborted. If both these modifiers are set
+ The callout_fail modifier can be given one or two numbers. If there is
+ only one number, 1 is returned instead of 0 (causing matching to back-
+ track) when a callout of that number is reached. If two numbers
+ (<n>:<m>) are given, 1 is returned when callout <n> is reached and
+ there have been at least <m> callouts. The callout_error modifier is
+ similar, except that PCRE2_ERROR_CALLOUT is returned, causing the
+ entire matching process to be aborted. If both these modifiers are set
for the same callout number, callout_error takes precedence.
- Note that callouts with string arguments are always given the number
+ Note that callouts with string arguments are always given the number
zero. See "Callouts" below for a description of the output when a call-
out it taken.
- The callout_data modifier can be given an unsigned or a negative num-
- ber. This is set as the "user data" that is passed to the matching
- function, and passed back when the callout function is invoked. Any
- value other than zero is used as a return from pcre2test's callout
+ The callout_data modifier can be given an unsigned or a negative num-
+ ber. This is set as the "user data" that is passed to the matching
+ function, and passed back when the callout function is invoked. Any
+ value other than zero is used as a return from pcre2test's callout
function.
Finding all matches in a string
Searching for all possible matches within a subject can be requested by
- the global or altglobal modifier. After finding a match, the matching
- function is called again to search the remainder of the subject. The
- difference between global and altglobal is that the former uses the
- start_offset argument to pcre2_match() or pcre2_dfa_match() to start
- searching at a new point within the entire string (which is what Perl
+ the global or altglobal modifier. After finding a match, the matching
+ function is called again to search the remainder of the subject. The
+ difference between global and altglobal is that the former uses the
+ start_offset argument to pcre2_match() or pcre2_dfa_match() to start
+ searching at a new point within the entire string (which is what Perl
does), whereas the latter passes over a shortened subject. This makes a
difference to the matching process if the pattern begins with a lookbe-
hind assertion (including \b or \B).
- If an empty string is matched, the next match is done with the
+ If an empty string is matched, the next match is done with the
PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set, in order to search
for another, non-empty, match at the same point in the subject. If this
- match fails, the start offset is advanced, and the normal match is
- retried. This imitates the way Perl handles such cases when using the
- /g modifier or the split() function. Normally, the start offset is
- advanced by one character, but if the newline convention recognizes
- CRLF as a newline, and the current character is CR followed by LF, an
+ match fails, the start offset is advanced, and the normal match is
+ retried. This imitates the way Perl handles such cases when using the
+ /g modifier or the split() function. Normally, the start offset is
+ advanced by one character, but if the newline convention recognizes
+ CRLF as a newline, and the current character is CR followed by LF, an
advance of two characters occurs.
Testing substring extraction functions
- The copy and get modifiers can be used to test the pcre2_sub-
+ The copy and get modifiers can be used to test the pcre2_sub-
string_copy_xxx() and pcre2_substring_get_xxx() functions. They can be
- given more than once, and each can specify a group name or number, for
+ given more than once, and each can specify a group name or number, for
example:
abcd\=copy=1,copy=3,get=G1
- If the #subject command is used to set default copy and/or get lists,
- these can be unset by specifying a negative number to cancel all num-
+ If the #subject command is used to set default copy and/or get lists,
+ these can be unset by specifying a negative number to cancel all num-
bered groups and an empty name to cancel all named groups.
- The getall modifier tests pcre2_substring_list_get(), which extracts
+ The getall modifier tests pcre2_substring_list_get(), which extracts
all captured substrings.
- If the subject line is successfully matched, the substrings extracted
- by the convenience functions are output with C, G, or L after the
- string number instead of a colon. This is in addition to the normal
- full list. The string length (that is, the return from the extraction
+ If the subject line is successfully matched, the substrings extracted
+ by the convenience functions are output with C, G, or L after the
+ string number instead of a colon. This is in addition to the normal
+ full list. The string length (that is, the return from the extraction
function) is given in parentheses after each substring, followed by the
name when the extraction was by name.
Testing the substitution function
- If the replace modifier is set, the pcre2_substitute() function is
- called instead of one of the matching functions. Note that replacement
- strings cannot contain commas, because a comma signifies the end of a
+ If the replace modifier is set, the pcre2_substitute() function is
+ called instead of one of the matching functions. Note that replacement
+ strings cannot contain commas, because a comma signifies the end of a
modifier. This is not thought to be an issue in a test program.
- Unlike subject strings, pcre2test does not process replacement strings
- for escape sequences. In UTF mode, a replacement string is checked to
- see if it is a valid UTF-8 string. If so, it is correctly converted to
- a UTF string of the appropriate code unit width. If it is not a valid
- UTF-8 string, the individual code units are copied directly. This pro-
+ Unlike subject strings, pcre2test does not process replacement strings
+ for escape sequences. In UTF mode, a replacement string is checked to
+ see if it is a valid UTF-8 string. If so, it is correctly converted to
+ a UTF string of the appropriate code unit width. If it is not a valid
+ UTF-8 string, the individual code units are copied directly. This pro-
vides a means of passing an invalid UTF-8 string for testing purposes.
- The following modifiers set options (in additional to the normal match
+ The following modifiers set options (in additional to the normal match
options) for pcre2_substitute():
global PCRE2_SUBSTITUTE_GLOBAL
@@ -1147,8 +1154,8 @@
substitute_unset_empty PCRE2_SUBSTITUTE_UNSET_EMPTY
- After a successful substitution, the modified string is output, pre-
- ceded by the number of replacements. This may be zero if there were no
+ After a successful substitution, the modified string is output, pre-
+ ceded by the number of replacements. This may be zero if there were no
matches. Here is a simple example of a substitution test:
/abc/replace=xxx
@@ -1157,12 +1164,12 @@
=abc=abc=\=global
2: =xxx=xxx=
- Subject and replacement strings should be kept relatively short (fewer
- than 256 characters) for substitution tests, as fixed-size buffers are
- used. To make it easy to test for buffer overflow, if the replacement
- string starts with a number in square brackets, that number is passed
- to pcre2_substitute() as the size of the output buffer, with the
- replacement string starting at the next character. Here is an example
+ Subject and replacement strings should be kept relatively short (fewer
+ than 256 characters) for substitution tests, as fixed-size buffers are
+ used. To make it easy to test for buffer overflow, if the replacement
+ string starts with a number in square brackets, that number is passed
+ to pcre2_substitute() as the size of the output buffer, with the
+ replacement string starting at the next character. Here is an example
that tests the edge case:
/abc/
@@ -1171,11 +1178,11 @@
123abc123\=replace=[9]XYZ
Failed: error -47: no more memory
- The default action of pcre2_substitute() is to return
- PCRE2_ERROR_NOMEMORY when the output buffer is too small. However, if
- the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by using the sub-
- stitute_overflow_length modifier), pcre2_substitute() continues to go
- through the motions of matching and substituting, in order to compute
+ The default action of pcre2_substitute() is to return
+ PCRE2_ERROR_NOMEMORY when the output buffer is too small. However, if
+ the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by using the sub-
+ stitute_overflow_length modifier), pcre2_substitute() continues to go
+ through the motions of matching and substituting, in order to compute
the size of buffer that is required. When this happens, pcre2test shows
the required buffer length (which includes space for the trailing zero)
as part of the error message. For example:
@@ -1185,30 +1192,31 @@
Failed: error -47: no more memory: 10 code units are needed
A replacement string is ignored with POSIX and DFA matching. Specifying
- partial matching provokes an error return ("bad option value") from
+ partial matching provokes an error return ("bad option value") from
pcre2_substitute().
Setting the JIT stack size
- The jitstack modifier provides a way of setting the maximum stack size
- that is used by the just-in-time optimization code. It is ignored if
+ The jitstack modifier provides a way of setting the maximum stack size
+ that is used by the just-in-time optimization code. It is ignored if
JIT optimization is not being used. The value is a number of kilobytes.
Providing a stack that is larger than the default 32K is necessary only
for very complicated patterns.
- Setting match and depth limits
+ Setting heap, match, and depth limits
- The match_limit and depth_limit modifiers set the appropriate limits in
- the match context. These values are ignored when the find_limits modi-
- fier is specified.
+ The heap_limit, match_limit, and depth_limit modifiers set the appro-
+ priate limits in the match context. These values are ignored when the
+ find_limits modifier is specified.
Finding minimum limits
- If the find_limits modifier is present on a subject line, pcre2test
- calls the relevant matching function several times, setting different
- values in the match context via pcre2_set_match_limit() or
- pcre2_set_depth_limit() until it finds the minimum values for each
- parameter that allows the match to complete without error.
+ If the find_limits modifier is present on a subject line, pcre2test
+ calls the relevant matching function several times, setting different
+ values in the match context via pcre2_set_heap_limit(),
+ pcre2_set_match_limit(), or pcre2_set_depth_limit() until it finds the
+ minimum values for each parameter that allows the match to complete
+ without error.
If JIT is being used, only the match limit is relevant. If DFA matching
is being used, only the depth limit is relevant.
@@ -1220,8 +1228,8 @@
quickly with increasing length of subject string.
For non-DFA matching, the minimum depth_limit number is a measure of
- how much memory for recording backtracking points is needed to complete
- the match attempt. In the case of DFA matching, depth_limit controls
+ how much nested backtracking happens (that is, how deeply the pattern's
+ tree is searched). In the case of DFA matching, depth_limit controls
the depth of recursive calls of the internal function that is used for
handling pattern recursion, lookaround assertions, and atomic groups.
@@ -1632,5 +1640,5 @@
REVISION
- Last updated: 04 April 2017
+ Last updated: 11 April 2017
Copyright (c) 1997-2017 University of Cambridge.
Modified: code/trunk/src/config.h.in
===================================================================
--- code/trunk/src/config.h.in 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/config.h.in 2017-04-11 11:47:25 UTC (rev 739)
@@ -132,6 +132,10 @@
/* Define to 1 if you have the <zlib.h> header file. */
#undef HAVE_ZLIB_H
+/* This limits the amount of memory that pcre2_match() may use while matching
+ a pattern. The value is in kilobytes. */
+#undef HEAP_LIMIT
+
/* The value of LINK_SIZE determines the number of bytes used to store links
as offsets within the compiled regex. The default is 2, which allows for
compiled patterns up to 64K long. This covers the vast majority of cases.
@@ -143,7 +147,7 @@
#undef LT_OBJDIR
/* The value of MATCH_LIMIT determines the default number of times the
- internal match() function can record a backtrack position during a single
+ pcre2_match() function can record a backtrack position during a single
matching attempt. There is a runtime interface for setting a different
limit. The limit exists in order to catch runaway regular expressions that
take for ever to determine that they do not match. The default is set very
Modified: code/trunk/src/pcre2.h
===================================================================
--- code/trunk/src/pcre2.h 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2.h 2017-04-11 11:47:25 UTC (rev 739)
@@ -268,6 +268,7 @@
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
#define PCRE2_ERROR_BADSERIALIZEDDATA (-62)
+#define PCRE2_ERROR_HEAPLIMIT (-63)
/* Request types for pcre2_pattern_info() */
@@ -297,6 +298,7 @@
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
#define PCRE2_INFO_FRAMESIZE 24
+#define PCRE2_INFO_HEAPLIMIT 25
/* Request types for pcre2_config(). */
@@ -313,6 +315,7 @@
#define PCRE2_CONFIG_UNICODE 9
#define PCRE2_CONFIG_UNICODE_VERSION 10
#define PCRE2_CONFIG_VERSION 11
+#define PCRE2_CONFIG_HEAPLIMIT 12
/* Types for code units in patterns and subject strings. */
@@ -453,6 +456,8 @@
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_depth_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+ pcre2_set_heap_limit(pcre2_match_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_match_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_offset_limit(pcre2_match_context *, PCRE2_SIZE); \
@@ -676,6 +681,7 @@
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_depth_limit PCRE2_SUFFIX(pcre2_set_depth_limit_)
+#define pcre2_set_heap_limit PCRE2_SUFFIX(pcre2_set_heap_limit_)
#define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_)
#define pcre2_set_max_pattern_length PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
#define pcre2_set_newline PCRE2_SUFFIX(pcre2_set_newline_)
Modified: code/trunk/src/pcre2.h.in
===================================================================
--- code/trunk/src/pcre2.h.in 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2.h.in 2017-04-11 11:47:25 UTC (rev 739)
@@ -268,6 +268,7 @@
#define PCRE2_ERROR_BADSUBSPATTERN (-60)
#define PCRE2_ERROR_TOOMANYREPLACE (-61)
#define PCRE2_ERROR_BADSERIALIZEDDATA (-62)
+#define PCRE2_ERROR_HEAPLIMIT (-63)
/* Request types for pcre2_pattern_info() */
@@ -297,6 +298,7 @@
#define PCRE2_INFO_SIZE 22
#define PCRE2_INFO_HASBACKSLASHC 23
#define PCRE2_INFO_FRAMESIZE 24
+#define PCRE2_INFO_HEAPLIMIT 25
/* Request types for pcre2_config(). */
@@ -313,6 +315,7 @@
#define PCRE2_CONFIG_UNICODE 9
#define PCRE2_CONFIG_UNICODE_VERSION 10
#define PCRE2_CONFIG_VERSION 11
+#define PCRE2_CONFIG_HEAPLIMIT 12
/* Types for code units in patterns and subject strings. */
@@ -453,6 +456,8 @@
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_depth_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+ pcre2_set_heap_limit(pcre2_match_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_match_limit(pcre2_match_context *, uint32_t); \
PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
pcre2_set_offset_limit(pcre2_match_context *, PCRE2_SIZE); \
@@ -676,6 +681,7 @@
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
#define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
#define pcre2_set_depth_limit PCRE2_SUFFIX(pcre2_set_depth_limit_)
+#define pcre2_set_heap_limit PCRE2_SUFFIX(pcre2_set_heap_limit_)
#define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_)
#define pcre2_set_max_pattern_length PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
#define pcre2_set_newline PCRE2_SUFFIX(pcre2_set_newline_)
Modified: code/trunk/src/pcre2_compile.c
===================================================================
--- code/trunk/src/pcre2_compile.c 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2_compile.c 2017-04-11 11:47:25 UTC (rev 739)
@@ -727,6 +727,7 @@
PSO_FLG, /* Value is a flag bit */
PSO_NL, /* Value is a newline type */
PSO_BSR, /* Value is a \R type */
+ PSO_LIMH, /* Read integer value for heap limit */
PSO_LIMM, /* Read integer value for match limit */
PSO_LIMD }; /* Read integer value for depth limit */
@@ -749,6 +750,7 @@
{ (uint8_t *)STRING_NO_DOTSTAR_ANCHOR_RIGHTPAR, 18, PSO_OPT, PCRE2_NO_DOTSTAR_ANCHOR },
{ (uint8_t *)STRING_NO_JIT_RIGHTPAR, 7, PSO_FLG, PCRE2_NOJIT },
{ (uint8_t *)STRING_NO_START_OPT_RIGHTPAR, 13, PSO_OPT, PCRE2_NO_START_OPTIMIZE },
+ { (uint8_t *)STRING_LIMIT_HEAP_EQ, 11, PSO_LIMH, 0 },
{ (uint8_t *)STRING_LIMIT_MATCH_EQ, 12, PSO_LIMM, 0 },
{ (uint8_t *)STRING_LIMIT_DEPTH_EQ, 12, PSO_LIMD, 0 },
{ (uint8_t *)STRING_LIMIT_RECURSION_EQ, 16, PSO_LIMD, 0 },
@@ -8853,6 +8855,7 @@
uint32_t setflags = 0; /* NL and BSR set flags */
uint32_t skipatstart; /* When checking (*UTF) etc */
+uint32_t limit_heap = UINT32_MAX;
uint32_t limit_match = UINT32_MAX; /* Unset match limits */
uint32_t limit_depth = UINT32_MAX;
@@ -9026,6 +9029,7 @@
case PSO_LIMM:
case PSO_LIMD:
+ case PSO_LIMH:
c = 0;
pp = skipatstart;
if (!IS_DIGIT(ptr[pp]))
@@ -9045,7 +9049,8 @@
ptr += pp;
goto HAD_EARLY_ERROR;
}
- if (p->type == PSO_LIMM) limit_match = c;
+ if (p->type == PSO_LIMH) limit_heap = c;
+ else if (p->type == PSO_LIMM) limit_match = c;
else limit_depth = c;
skipatstart += pp - skipatstart;
break;
@@ -9288,6 +9293,7 @@
re->compile_options = options;
re->overall_options = cb.external_options;
re->flags = PCRE2_CODE_UNIT_WIDTH/8 | cb.external_flags | setflags;
+re->limit_heap = limit_heap;
re->limit_match = limit_match;
re->limit_depth = limit_depth;
re->first_codeunit = 0;
Modified: code/trunk/src/pcre2_config.c
===================================================================
--- code/trunk/src/pcre2_config.c 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2_config.c 2017-04-11 11:47:25 UTC (rev 739)
@@ -84,6 +84,7 @@
return PCRE2_ERROR_BADOPTION;
case PCRE2_CONFIG_BSR:
+ case PCRE2_CONFIG_HEAPLIMIT:
case PCRE2_CONFIG_JIT:
case PCRE2_CONFIG_LINKSIZE:
case PCRE2_CONFIG_MATCHLIMIT:
@@ -116,6 +117,10 @@
#endif
break;
+ case PCRE2_CONFIG_HEAPLIMIT:
+ *((uint32_t *)where) = HEAP_LIMIT;
+ break;
+
case PCRE2_CONFIG_JIT:
#ifdef SUPPORT_JIT
*((uint32_t *)where) = 1;
Modified: code/trunk/src/pcre2_context.c
===================================================================
--- code/trunk/src/pcre2_context.c 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2_context.c 2017-04-11 11:47:25 UTC (rev 739)
@@ -168,6 +168,7 @@
NULL,
NULL,
PCRE2_UNSET, /* Offset limit */
+ HEAP_LIMIT,
MATCH_LIMIT,
MATCH_LIMIT_DEPTH };
@@ -347,6 +348,13 @@
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
+pcre2_set_heap_limit(pcre2_match_context *mcontext, uint32_t limit)
+{
+mcontext->heap_limit = limit;
+return 0;
+}
+
+PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_set_match_limit(pcre2_match_context *mcontext, uint32_t limit)
{
mcontext->match_limit = limit;
Modified: code/trunk/src/pcre2_error.c
===================================================================
--- code/trunk/src/pcre2_error.c 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2_error.c 2017-04-11 11:47:25 UTC (rev 739)
@@ -256,6 +256,7 @@
"match with end before start is not supported\0"
"too many replacements (more than INT_MAX)\0"
"bad serialized data\0"
+ "heap limit exceeded\0"
;
Modified: code/trunk/src/pcre2_internal.h
===================================================================
--- code/trunk/src/pcre2_internal.h 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2_internal.h 2017-04-11 11:47:25 UTC (rev 739)
@@ -240,6 +240,16 @@
#define COMPILE_ERROR_BASE 100
+/* The initial frames vector for remembering backtracking points in
+pcre2_match() is allocated on the system stack, of this size (bytes). The size
+must be a multiple of sizeof(PCRE2_SPTR) in all environments, so making it a
+multiple of 8 is best. Typical frame sizes are a few hundred bytes (it depends
+on the number of capturing parentheses) so 20K handles quite a few frames. A
+larger vector on the heap is obtained for patterns that need more frames. The
+maximum size of this can be limited. */
+
+#define START_FRAMES_SIZE 20480
+
/* Define the default BSR convention. */
#ifdef BSR_ANYCRLF
@@ -922,6 +932,7 @@
#define STRING_NO_START_OPT_RIGHTPAR "NO_START_OPT)"
#define STRING_NOTEMPTY_RIGHTPAR "NOTEMPTY)"
#define STRING_NOTEMPTY_ATSTART_RIGHTPAR "NOTEMPTY_ATSTART)"
+#define STRING_LIMIT_HEAP_EQ "LIMIT_HEAP="
#define STRING_LIMIT_MATCH_EQ "LIMIT_MATCH="
#define STRING_LIMIT_DEPTH_EQ "LIMIT_DEPTH="
#define STRING_LIMIT_RECURSION_EQ "LIMIT_RECURSION="
@@ -1196,6 +1207,7 @@
#define STRING_NO_START_OPT_RIGHTPAR STR_N STR_O STR_UNDERSCORE STR_S STR_T STR_A STR_R STR_T STR_UNDERSCORE STR_O STR_P STR_T STR_RIGHT_PARENTHESIS
#define STRING_NOTEMPTY_RIGHTPAR STR_N STR_O STR_T STR_E STR_M STR_P STR_T STR_Y STR_RIGHT_PARENTHESIS
#define STRING_NOTEMPTY_ATSTART_RIGHTPAR STR_N STR_O STR_T STR_E STR_M STR_P STR_T STR_Y STR_UNDERSCORE STR_A STR_T STR_S STR_T STR_A STR_R STR_T STR_RIGHT_PARENTHESIS
+#define STRING_LIMIT_HEAP_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_H STR_E STR_A STR_P STR_EQUALS_SIGN
#define STRING_LIMIT_MATCH_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_M STR_A STR_T STR_C STR_H STR_EQUALS_SIGN
#define STRING_LIMIT_DEPTH_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_D STR_E STR_P STR_T STR_H STR_EQUALS_SIGN
#define STRING_LIMIT_RECURSION_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_R STR_E STR_C STR_U STR_R STR_S STR_I STR_O STR_N STR_EQUALS_SIGN
Modified: code/trunk/src/pcre2_intmodedep.h
===================================================================
--- code/trunk/src/pcre2_intmodedep.h 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2_intmodedep.h 2017-04-11 11:47:25 UTC (rev 739)
@@ -585,6 +585,7 @@
int (*callout)(pcre2_callout_block *, void *);
void *callout_data;
PCRE2_SIZE offset_limit;
+ uint32_t heap_limit;
uint32_t match_limit;
uint32_t depth_limit;
} pcre2_real_match_context;
@@ -614,6 +615,7 @@
uint32_t compile_options; /* Options passed to pcre2_compile() */
uint32_t overall_options; /* Options after processing the pattern */
uint32_t flags; /* Various state flags */
+ uint32_t limit_heap; /* Limit set in the pattern */
uint32_t limit_match; /* Limit set in the pattern */
uint32_t limit_depth; /* Limit set in the pattern */
uint32_t first_codeunit; /* Starting code unit */
@@ -808,9 +810,10 @@
heapframe *match_frames; /* Points to vector of frames */
heapframe *match_frames_top; /* Points after the end of the vector */
heapframe *stack_frames; /* The original vector on the stack */
- uint32_t match_call_count; /* Number of times a new frame is created */
+ PCRE2_SIZE heap_limit; /* As it says */
uint32_t match_limit; /* As it says */
uint32_t match_limit_depth; /* As it says */
+ uint32_t match_call_count; /* Number of times a new frame is created */
BOOL hitend; /* Hit the end of the subject at some point */
BOOL hasthen; /* Pattern contains (*THEN) */
const uint8_t *lcc; /* Points to lower casing table */
Modified: code/trunk/src/pcre2_match.c
===================================================================
--- code/trunk/src/pcre2_match.c 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2_match.c 2017-04-11 11:47:25 UTC (rev 739)
@@ -64,15 +64,6 @@
#define RECURSE_UNSET 0xffffffffu /* Bigger than max group number */
-/* The initial frames vector for remembering backtracking points is allocated
-on the system stack, of this size (bytes). The size must be a multiple of
-sizeof(PCRE2_SPTR) in all environments, so making it a multiple of 8 is best.
-Typical frame sizes are a few hundred bytes (it depends on the number of
-capturing parentheses) so 10K handles quite a few frames. A larger vector on
-the heap is obtained for patterns that need more frames. */
-
-#define START_FRAMES_SIZE 10240
-
/* Masks for identifying the public options that are permitted at match time. */
#define PUBLIC_MATCH_OPTIONS \
@@ -618,14 +609,22 @@
MATCH_RECURSE:
/* Set up a new backtracking frame. If the vector is full, get a new one
-on the heap, doubling the size. */
+on the heap, doubling the size, but constrained by the heap limit. */
N = (heapframe *)((char *)F + frame_size);
if (N >= mb->match_frames_top)
{
PCRE2_SIZE newsize = mb->frame_vector_size * 2;
- heapframe *new = mb->memctl.malloc(newsize, mb->memctl.memory_data);
+ heapframe *new;
+ if ((newsize / 1024) > mb->heap_limit)
+ {
+ PCRE2_SIZE maxsize = ((mb->heap_limit * 1024)/frame_size) * frame_size;
+ if (mb->frame_vector_size == maxsize) return PCRE2_ERROR_HEAPLIMIT;
+ newsize = maxsize;
+ }
+
+ new = mb->memctl.malloc(newsize, mb->memctl.memory_data);
if (new == NULL) return PCRE2_ERROR_NOMEMORY;
memcpy(new, mb->match_frames, mb->frame_vector_size);
@@ -802,13 +801,13 @@
Fstart_match == mb->start_subject + mb->start_offset)))
RRETURN(MATCH_NOMATCH);
- /* Also fail if PCRE2_ENDANCHORED is set and the end of the match is not
+ /* Also fail if PCRE2_ENDANCHORED is set and the end of the match is not
the end of the subject. */
-
+
if (Feptr < mb->end_subject &&
((mb->moptions | mb->poptions) & PCRE2_ENDANCHORED) != 0)
- RRETURN(MATCH_NOMATCH);
-
+ RRETURN(MATCH_NOMATCH);
+
/* We have a successful match of the whole pattern. Record the result and
then do a direct return from the function. If there is space in the offset
vector, set any pairs that follow the highest-numbered captured string but
@@ -6093,13 +6092,13 @@
utf = (re->overall_options & PCRE2_UTF) != 0;
mb->partial = ((options & PCRE2_PARTIAL_HARD) != 0)? 2 :
((options & PCRE2_PARTIAL_SOFT) != 0)? 1 : 0;
-
-/* Partial matching and PCRE2_ENDANCHORED are currently not allowed at the same
-time. */
-
-if (mb->partial != 0 &&
+
+/* Partial matching and PCRE2_ENDANCHORED are currently not allowed at the same
+time. */
+
+if (mb->partial != 0 &&
((re->overall_options | options) & PCRE2_ENDANCHORED) != 0)
- return PCRE2_ERROR_BADOPTION;
+ return PCRE2_ERROR_BADOPTION;
/* Check a UTF string for validity if required. For 8-bit and 16-bit strings,
we must also check that a starting offset does not point into the middle of a
@@ -6266,9 +6265,22 @@
frame_size = sizeof(heapframe) + ((re->top_bracket - 1) * 2 * sizeof(PCRE2_SIZE));
+/* Limits set in the pattern override the match context only if they are
+smaller. */
+
+mb->heap_limit = (mcontext->heap_limit < re->limit_heap)?
+ mcontext->heap_limit : re->limit_heap;
+
+mb->match_limit = (mcontext->match_limit < re->limit_match)?
+ mcontext->match_limit : re->limit_match;
+
+mb->match_limit_depth = (mcontext->depth_limit < re->limit_depth)?
+ mcontext->depth_limit : re->limit_depth;
+
/* If a pattern has very many capturing parentheses, the frame size may be very
large. Ensure that there are at least 10 available frames by getting an initial
-vector on the heap if necessary. */
+vector on the heap if necessary, except when the heap limit prevents this. Get
+fewer if possible. (The heap limit is in kilobytes.) */
if (frame_size <= START_FRAMES_SIZE/10)
{
@@ -6278,6 +6290,11 @@
else
{
mb->frame_vector_size = frame_size * 10;
+ if ((mb->frame_vector_size / 1024) > mb->heap_limit)
+ {
+ if (frame_size > mb->heap_limit * 1024) return PCRE2_ERROR_HEAPLIMIT;
+ mb->frame_vector_size = ((mb->heap_limit * 1024)/frame_size) * frame_size;
+ }
mb->match_frames = mb->memctl.malloc(mb->frame_vector_size,
mb->memctl.memory_data);
if (mb->match_frames == NULL) return PCRE2_ERROR_NOMEMORY;
@@ -6292,14 +6309,6 @@
memset((char *)(mb->match_frames) + offsetof(heapframe, ovector), 0xff,
re->top_bracket * 2 * sizeof(PCRE2_SIZE));
-/* Limits set in the pattern override the match context only if they are
-smaller. */
-
-mb->match_limit = (mcontext->match_limit < re->limit_match)?
- mcontext->match_limit : re->limit_match;
-mb->match_limit_depth = (mcontext->depth_limit < re->limit_depth)?
- mcontext->depth_limit : re->limit_depth;
-
/* Pointers to the individual character tables */
mb->lcc = re->tables + lcc_offset;
Modified: code/trunk/src/pcre2_pattern_info.c
===================================================================
--- code/trunk/src/pcre2_pattern_info.c 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2_pattern_info.c 2017-04-11 11:47:25 UTC (rev 739)
@@ -80,6 +80,7 @@
case PCRE2_INFO_FIRSTCODEUNIT:
case PCRE2_INFO_HASBACKSLASHC:
case PCRE2_INFO_HASCRORLF:
+ case PCRE2_INFO_HEAPLIMIT:
case PCRE2_INFO_JCHANGED:
case PCRE2_INFO_LASTCODETYPE:
case PCRE2_INFO_LASTCODEUNIT:
@@ -171,6 +172,11 @@
*((uint32_t *)where) = (re->flags & PCRE2_HASCRORLF) != 0;
break;
+ case PCRE2_INFO_HEAPLIMIT:
+ *((uint32_t *)where) = re->limit_heap;
+ if (re->limit_heap == UINT32_MAX) return PCRE2_ERROR_UNSET;
+ break;
+
case PCRE2_INFO_JCHANGED:
*((uint32_t *)where) = (re->flags & PCRE2_JCHANGED) != 0;
break;
Modified: code/trunk/src/pcre2grep.c
===================================================================
--- code/trunk/src/pcre2grep.c 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2grep.c 2017-04-11 11:47:25 UTC (rev 739)
@@ -212,6 +212,7 @@
static uint32_t pcre2_options = 0;
static uint32_t process_options = 0;
+static PCRE2_SIZE heap_limit = PCRE2_UNSET;
static uint32_t match_limit = 0;
static uint32_t depth_limit = 0;
@@ -330,7 +331,7 @@
/* Structure for options and list of them */
-enum { OP_NODATA, OP_STRING, OP_OP_STRING, OP_NUMBER, OP_U32NUMBER,
+enum { OP_NODATA, OP_STRING, OP_OP_STRING, OP_NUMBER, OP_U32NUMBER, OP_SIZE,
OP_OP_NUMBER, OP_OP_NUMBERS, OP_PATLIST, OP_FILELIST, OP_BINFILES };
typedef struct option_item {
@@ -356,16 +357,17 @@
#define N_LOFFSETS (-10)
#define N_FOFFSETS (-11)
#define N_LBUFFER (-12)
-#define N_M_LIMIT (-13)
-#define N_M_LIMIT_DEP (-14)
-#define N_BUFSIZE (-15)
-#define N_NOJIT (-16)
-#define N_FILE_LIST (-17)
-#define N_BINARY_FILES (-18)
-#define N_EXCLUDE_FROM (-19)
-#define N_INCLUDE_FROM (-20)
-#define N_OM_SEPARATOR (-21)
-#define N_MAX_BUFSIZE (-22)
+#define N_H_LIMIT (-13)
+#define N_M_LIMIT (-14)
+#define N_M_LIMIT_DEP (-15)
+#define N_BUFSIZE (-16)
+#define N_NOJIT (-17)
+#define N_FILE_LIST (-18)
+#define N_BINARY_FILES (-19)
+#define N_EXCLUDE_FROM (-20)
+#define N_INCLUDE_FROM (-21)
+#define N_OM_SEPARATOR (-22)
+#define N_MAX_BUFSIZE (-23)
static option_item optionlist[] = {
{ OP_NODATA, N_NULL, NULL, "", "terminate options" },
@@ -397,6 +399,7 @@
{ OP_NODATA, N_LBUFFER, NULL, "line-buffered", "use line buffering" },
{ OP_NODATA, N_LOFFSETS, NULL, "line-offsets", "output line numbers and offsets, not text" },
{ OP_STRING, N_LOCALE, &locale, "locale=locale", "use the named locale" },
+ { OP_SIZE, N_H_LIMIT, &heap_limit, "heap-limit=number", "set PCRE2 heap limit option (kilobytes)" },
{ OP_U32NUMBER, N_M_LIMIT, &match_limit, "match-limit=number", "set PCRE2 match limit option" },
{ OP_U32NUMBER, N_M_LIMIT_DEP, &depth_limit, "depth-limit=number", "set PCRE2 depth limit option" },
{ OP_U32NUMBER, N_M_LIMIT_DEP, &depth_limit, "recursion-limit=number", "obsolete synonym for depth-limit" },
@@ -525,9 +528,9 @@
{
if (resource_error)
{
- fprintf(stderr, "pcre2grep: Error %d, %d or %d means that a resource limit "
- "was exceeded.\n", PCRE2_ERROR_JIT_STACKLIMIT, PCRE2_ERROR_MATCHLIMIT,
- PCRE2_ERROR_DEPTHLIMIT);
+ fprintf(stderr, "pcre2grep: Error %d, %d, %d or %d means that a resource "
+ "limit was exceeded.\n", PCRE2_ERROR_JIT_STACKLIMIT, PCRE2_ERROR_MATCHLIMIT,
+ PCRE2_ERROR_DEPTHLIMIT, PCRE2_ERROR_HEAPLIMIT);
fprintf(stderr, "pcre2grep: Check your regex for nested unlimited loops.\n");
}
exit(rc);
@@ -1647,7 +1650,7 @@
FWRITE(matchptr, 1, slen, stderr); /* In case binary zero included */
fprintf(stderr, "\n\n");
if (*mrc == PCRE2_ERROR_MATCHLIMIT || *mrc == PCRE2_ERROR_DEPTHLIMIT ||
- *mrc == PCRE2_ERROR_JIT_STACKLIMIT)
+ *mrc == PCRE2_ERROR_HEAPLIMIT || *mrc == PCRE2_ERROR_JIT_STACKLIMIT)
resource_error = TRUE;
if (error_count++ > 20)
{
@@ -3796,7 +3799,7 @@
/* Otherwise, deal with a single string or numeric data value. */
else if (op->type != OP_NUMBER && op->type != OP_U32NUMBER &&
- op->type != OP_OP_NUMBER)
+ op->type != OP_OP_NUMBER && op->type != OP_SIZE)
{
*((char **)op->dataptr) = option_data;
}
@@ -3804,6 +3807,7 @@
{
unsigned long int n = decode_number(option_data, op, longop);
if (op->type == OP_U32NUMBER) *((uint32_t *)op->dataptr) = n;
+ else if (op->type == OP_SIZE) *((PCRE2_SIZE *)op->dataptr) = n;
else *((int *)op->dataptr) = n;
}
}
@@ -3839,6 +3843,7 @@
/* Put limits into the match data block. */
+if (heap_limit != PCRE2_UNSET) pcre2_set_heap_limit(match_context, heap_limit);
if (match_limit > 0) pcre2_set_match_limit(match_context, match_limit);
if (depth_limit > 0) pcre2_set_depth_limit(match_context, depth_limit);
Modified: code/trunk/src/pcre2test.c
===================================================================
--- code/trunk/src/pcre2test.c 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/src/pcre2test.c 2017-04-11 11:47:25 UTC (rev 739)
@@ -588,6 +588,7 @@
{ "get", MOD_DAT, MOD_NN, DO(get_numbers), DO(get_names) },
{ "getall", MOD_DAT, MOD_CTL, CTL_GETALL, DO(control) },
{ "global", MOD_PNDP, MOD_CTL, CTL_GLOBAL, PO(control) },
+ { "heap_limit", MOD_CTM, MOD_INT, 0, MO(heap_limit) },
{ "hex", MOD_PAT, MOD_CTL, CTL_HEXPAT, PO(control) },
{ "info", MOD_PAT, MOD_CTL, CTL_INFO, PO(control) },
{ "jit", MOD_PAT, MOD_IND, 7, PO(jit) },
@@ -1207,6 +1208,14 @@
else \
pcre2_set_depth_limit_32(G(a,32),b)
+#define PCRE2_SET_HEAP_LIMIT(a,b) \
+ if (test_mode == PCRE8_MODE) \
+ pcre2_set_heap_limit_8(G(a,8),b); \
+ else if (test_mode == PCRE16_MODE) \
+ pcre2_set_heap_limit_16(G(a,16),b); \
+ else \
+ pcre2_set_heap_limit_32(G(a,32),b)
+
#define PCRE2_SET_MATCH_LIMIT(a,b) \
if (test_mode == PCRE8_MODE) \
pcre2_set_match_limit_8(G(a,8),b); \
@@ -1643,6 +1652,12 @@
else \
G(pcre2_set_depth_limit_,BITTWO)(G(a,BITTWO),b)
+#define PCRE2_SET_HEAP_LIMIT(a,b) \
+ if (test_mode == G(G(PCRE,BITONE),_MODE)) \
+ G(pcre2_set_heap_limit_,BITONE)(G(a,BITONE),b); \
+ else \
+ G(pcre2_set_heap_limit_,BITTWO)(G(a,BITTWO),b)
+
#define PCRE2_SET_MATCH_LIMIT(a,b) \
if (test_mode == G(G(PCRE,BITONE),_MODE)) \
G(pcre2_set_match_limit_,BITONE)(G(a,BITONE),b); \
@@ -1856,6 +1871,7 @@
#define PCRE2_SET_COMPILE_RECURSION_GUARD(a,b,c) \
pcre2_set_compile_recursion_guard_8(G(a,8),b,c)
#define PCRE2_SET_DEPTH_LIMIT(a,b) pcre2_set_depth_limit_8(G(a,8),b)
+#define PCRE2_SET_HEAP_LIMIT(a,b) pcre2_set_heap_limit_8(G(a,8),b)
#define PCRE2_SET_MATCH_LIMIT(a,b) pcre2_set_match_limit_8(G(a,8),b)
#define PCRE2_SET_MAX_PATTERN_LENGTH(a,b) pcre2_set_max_pattern_length_8(G(a,8),b)
#define PCRE2_SET_OFFSET_LIMIT(a,b) pcre2_set_offset_limit_8(G(a,8),b)
@@ -1952,6 +1968,7 @@
#define PCRE2_SET_COMPILE_RECURSION_GUARD(a,b,c) \
pcre2_set_compile_recursion_guard_16(G(a,16),b,c)
#define PCRE2_SET_DEPTH_LIMIT(a,b) pcre2_set_depth_limit_16(G(a,16),b)
+#define PCRE2_SET_HEAP_LIMIT(a,b) pcre2_set_heap_limit_16(G(a,16),b)
#define PCRE2_SET_MATCH_LIMIT(a,b) pcre2_set_match_limit_16(G(a,16),b)
#define PCRE2_SET_MAX_PATTERN_LENGTH(a,b) pcre2_set_max_pattern_length_16(G(a,16),b)
#define PCRE2_SET_OFFSET_LIMIT(a,b) pcre2_set_offset_limit_16(G(a,16),b)
@@ -2048,6 +2065,7 @@
#define PCRE2_SET_COMPILE_RECURSION_GUARD(a,b,c) \
pcre2_set_compile_recursion_guard_32(G(a,32),b,c)
#define PCRE2_SET_DEPTH_LIMIT(a,b) pcre2_set_depth_limit_32(G(a,32),b)
+#define PCRE2_SET_HEAP_LIMIT(a,b) pcre2_set_heap_limit_32(G(a,32),b)
#define PCRE2_SET_MATCH_LIMIT(a,b) pcre2_set_match_limit_32(G(a,32),b)
#define PCRE2_SET_MAX_PATTERN_LENGTH(a,b) pcre2_set_max_pattern_length_32(G(a,32),b)
#define PCRE2_SET_OFFSET_LIMIT(a,b) pcre2_set_offset_limit_32(G(a,32),b)
@@ -4040,14 +4058,28 @@
{
void *nametable;
uint8_t *start_bits;
- BOOL match_limit_set, depth_limit_set;
+ BOOL heap_limit_set, match_limit_set, depth_limit_set;
uint32_t backrefmax, bsr_convention, capture_count, first_ctype, first_cunit,
hasbackslashc, hascrorlf, jchanged, last_ctype, last_cunit, match_empty,
- match_limit, minlength, nameentrysize, namecount, newline_convention,
- depth_limit;
+ depth_limit, heap_limit, match_limit, minlength, nameentrysize, namecount,
+ newline_convention;
/* These info requests may return PCRE2_ERROR_UNSET. */
+ switch(pattern_info(PCRE2_INFO_HEAPLIMIT, &heap_limit, TRUE))
+ {
+ case 0:
+ heap_limit_set = TRUE;
+ break;
+
+ case PCRE2_ERROR_UNSET:
+ heap_limit_set = FALSE;
+ break;
+
+ default:
+ return PR_ABEND;
+ }
+
switch(pattern_info(PCRE2_INFO_MATCHLIMIT, &match_limit, TRUE))
{
case 0:
@@ -4106,6 +4138,9 @@
if (maxlookbehind > 0)
fprintf(outfile, "Max lookbehind = %d\n", maxlookbehind);
+ if (heap_limit_set)
+ fprintf(outfile, "Heap limit = %u\n", heap_limit);
+
if (match_limit_set)
fprintf(outfile, "Match limit = %u\n", match_limit);
@@ -5353,11 +5388,16 @@
PCRE2_SET_MATCH_LIMIT(dat_context, max);
PCRE2_SET_DEPTH_LIMIT(dat_context, max);
+PCRE2_SET_HEAP_LIMIT(dat_context, max);
for (;;)
{
- if (errnumber == PCRE2_ERROR_MATCHLIMIT)
+ if (errnumber == PCRE2_ERROR_HEAPLIMIT)
{
+ PCRE2_SET_HEAP_LIMIT(dat_context, mid);
+ }
+ else if (errnumber == PCRE2_ERROR_MATCHLIMIT)
+ {
PCRE2_SET_MATCH_LIMIT(dat_context, mid);
}
else
@@ -5393,13 +5433,23 @@
capcount == PCRE2_ERROR_NOMATCH ||
capcount == PCRE2_ERROR_PARTIAL)
{
+ /* If we've not hit the error with a heap limit less than the size of the
+ initial stack frame vector, the heap is not being used, so the minimum
+ limit is zero; there's no need to go on. The other limits are always
+ greater than zero. */
+
+ if (errnumber == PCRE2_ERROR_HEAPLIMIT && mid < START_FRAMES_SIZE/1024)
+ {
+ fprintf(outfile, "Minimum %s limit = 0\n", msg);
+ break;
+ }
if (mid == min + 1)
{
fprintf(outfile, "Minimum %s limit = %d\n", msg, mid);
break;
- }
- max = mid;
- mid = (min + mid)/2;
+ }
+ max = mid;
+ mid = (min + max)/2;
}
else break; /* Some other error */
}
@@ -6662,20 +6712,32 @@
(double)CLOCKS_PER_SEC);
}
- /* Find the match and depth limits if requested. The match limit is not
- relevant for DFA matching and the depth limit is not relevant for JIT. */
+ /* Find the heap, match and depth limits if requested. The match and heap
+ limits are not relevant for DFA matching and the depth limit is not relevant
+ for JIT. */
if ((dat_datctl.control & CTL_FINDLIMITS) != 0)
{
if ((dat_datctl.control & CTL_DFA) == 0)
+ {
+ if (FLD(compiled_code, executable_jit) == NULL ||
+ (dat_datctl.options & PCRE2_NO_JIT) != 0)
+ {
+ capcount = check_match_limit(pp, arg_ulen, PCRE2_ERROR_HEAPLIMIT,
+ "heap");
+ }
capcount = check_match_limit(pp, arg_ulen, PCRE2_ERROR_MATCHLIMIT,
"match");
+ }
else capcount = 0;
+
if (FLD(compiled_code, executable_jit) == NULL ||
(dat_datctl.options & PCRE2_NO_JIT) != 0 ||
(dat_datctl.control & CTL_DFA) != 0)
+ {
capcount = check_match_limit(pp, arg_ulen, PCRE2_ERROR_DEPTHLIMIT,
"depth");
+ }
}
/* Otherwise just run a single match, setting up a callout if required (the
@@ -7402,6 +7464,8 @@
printf(" Internal link size = %d\n", optval);
(void)PCRE2_CONFIG(PCRE2_CONFIG_PARENSLIMIT, &optval);
printf(" Parentheses nest limit = %d\n", optval);
+(void)PCRE2_CONFIG(PCRE2_CONFIG_HEAPLIMIT, &optval);
+printf(" Default heap limit = %d\n", optval);
(void)PCRE2_CONFIG(PCRE2_CONFIG_MATCHLIMIT, &optval);
printf(" Default match limit = %d\n", optval);
(void)PCRE2_CONFIG(PCRE2_CONFIG_DEPTHLIMIT, &optval);
Modified: code/trunk/testdata/testoutput15
===================================================================
--- code/trunk/testdata/testoutput15 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/testdata/testoutput15 2017-04-11 11:47:25 UTC (rev 739)
@@ -12,11 +12,13 @@
Last code unit = 'z'
Subject length lower bound = 2
aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\=find_limits
+Minimum heap limit = 0
Minimum match limit = 7
Minimum depth limit = 7
0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazz
1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
aaaaaaaaaaaaaz\=find_limits
+Minimum heap limit = 0
Minimum match limit = 20481
Minimum depth limit = 30
No match
@@ -26,6 +28,7 @@
May match empty string
Subject length lower bound = 0
/* this is a C style comment */\=find_limits
+Minimum heap limit = 0
Minimum match limit = 64
Minimum depth limit = 7
0: /* this is a C style comment */
@@ -33,10 +36,12 @@
/^(?>a)++/
aa\=find_limits
+Minimum heap limit = 0
Minimum match limit = 5
Minimum depth limit = 3
0: aa
aaaaaaaaa\=find_limits
+Minimum heap limit = 0
Minimum match limit = 12
Minimum depth limit = 3
0: aaaaaaaaa
@@ -43,11 +48,13 @@
/(a)(?1)++/
aa\=find_limits
+Minimum heap limit = 0
Minimum match limit = 7
Minimum depth limit = 5
0: aa
1: a
aaaaaaaaa\=find_limits
+Minimum heap limit = 0
Minimum match limit = 21
Minimum depth limit = 5
0: aaaaaaaaa
@@ -55,6 +62,7 @@
/a(?:.)*?a/ims
abbbbbbbbbbbbbbbbbbbbba\=find_limits
+Minimum heap limit = 0
Minimum match limit = 24
Minimum depth limit = 3
0: abbbbbbbbbbbbbbbbbbbbba
@@ -61,6 +69,7 @@
/a(?:.(*THEN))*?a/ims
abbbbbbbbbbbbbbbbbbbbba\=find_limits
+Minimum heap limit = 0
Minimum match limit = 66
Minimum depth limit = 45
0: abbbbbbbbbbbbbbbbbbbbba
@@ -67,6 +76,7 @@
/a(?:.(*THEN:ABC))*?a/ims
abbbbbbbbbbbbbbbbbbbbba\=find_limits
+Minimum heap limit = 0
Minimum match limit = 66
Minimum depth limit = 45
0: abbbbbbbbbbbbbbbbbbbbba
@@ -73,6 +83,7 @@
/^(?>a+)(?>b+)(?>c+)(?>d+)(?>e+)/
aabbccddee\=find_limits
+Minimum heap limit = 0
Minimum match limit = 7
Minimum depth limit = 7
0: aabbccddee
@@ -79,6 +90,7 @@
/^(?>(a+))(?>(b+))(?>(c+))(?>(d+))(?>(e+))/
aabbccddee\=find_limits
+Minimum heap limit = 0
Minimum match limit = 12
Minimum depth limit = 12
0: aabbccddee
@@ -90,6 +102,7 @@
/^(?>(a+))(?>b+)(?>(c+))(?>d+)(?>(e+))/
aabbccddee\=find_limits
+Minimum heap limit = 0
Minimum match limit = 10
Minimum depth limit = 10
0: aabbccddee
Modified: code/trunk/testdata/testoutput2
===================================================================
--- code/trunk/testdata/testoutput2 2017-04-08 15:35:27 UTC (rev 738)
+++ code/trunk/testdata/testoutput2 2017-04-11 11:47:25 UTC (rev 739)
@@ -15609,7 +15609,7 @@
Subject length lower bound = 4
# End of testinput2
-Error -63: PCRE2_ERROR_BADDATA (unknown error number)
+Error -64: PCRE2_ERROR_BADDATA (unknown error number)
Error -62: bad serialized data
Error -2: partial match
Error -1: no match
