diff options
| author | Philip Hazel <Philip.Hazel@gmail.com> | 2024-04-24 09:32:25 +0100 |
|---|---|---|
| committer | Philip Hazel <Philip.Hazel@gmail.com> | 2024-04-24 09:32:25 +0100 |
| commit | 05aafb2e308e5529e3fd5fed45bae253eebed75b (patch) | |
| tree | 3fbe040d5970fd525b061d1b383a863f507e49dd | |
| parent | 22cb0a659cbda66e3106e2a1627ca2546d509aad (diff) | |
| download | pcre-05aafb2e308e5529e3fd5fed45bae253eebed75b.tar.gz | |
Implement pcre2_set_max_pattern_compiled_length() and set this limit in the fuzzer
| -rw-r--r-- | ChangeLog | 5 | ||||
| -rw-r--r-- | Makefile.am | 2 | ||||
| -rw-r--r-- | doc/html/index.html | 5 | ||||
| -rw-r--r-- | doc/html/pcre2_set_max_pattern_compiled_length.html | 44 | ||||
| -rw-r--r-- | doc/html/pcre2api.html | 18 | ||||
| -rw-r--r-- | doc/html/pcre2test.html | 15 | ||||
| -rw-r--r-- | doc/index.html.src | 5 | ||||
| -rw-r--r-- | doc/pcre2.txt | 18 | ||||
| -rw-r--r-- | doc/pcre2_set_max_pattern_compiled_length.3 | 32 | ||||
| -rw-r--r-- | doc/pcre2api.3 | 19 | ||||
| -rw-r--r-- | doc/pcre2demo.3 | 2 | ||||
| -rw-r--r-- | doc/pcre2test.1 | 17 | ||||
| -rw-r--r-- | doc/pcre2test.txt | 685 | ||||
| -rw-r--r-- | src/pcre2.h.in | 3 | ||||
| -rw-r--r-- | src/pcre2_compile.c | 18 | ||||
| -rw-r--r-- | src/pcre2_context.c | 10 | ||||
| -rw-r--r-- | src/pcre2_error.c | 3 | ||||
| -rw-r--r-- | src/pcre2_fuzzsupport.c | 22 | ||||
| -rw-r--r-- | src/pcre2_intmodedep.h | 3 | ||||
| -rw-r--r-- | src/pcre2test.c | 25 | ||||
| -rw-r--r-- | testdata/testinput2 | 3 | ||||
| -rw-r--r-- | testdata/testoutput2 | 4 | ||||
| -rw-r--r-- | testdata/testoutput8-16-2 | 168 | ||||
| -rw-r--r-- | testdata/testoutput8-32-2 | 168 | ||||
| -rw-r--r-- | testdata/testoutput8-8-2 | 168 |
25 files changed, 929 insertions, 533 deletions
@@ -29,6 +29,8 @@ example pattern is: /(((?<=123?456456|ABC)))(?<=\2)/ (e) General code tidies. + (f) Limit the size of compiled patterns to 10MB (see 6 below). + 3. Increase the maximum length of a name for a group from 32 to 128 because there is a user for whom 32 is too small. @@ -38,6 +40,9 @@ return if either jitverify or info is specified/ 5. Some auxiliary files for building under OpenVMS that were contributed by Alexey Chupahin have been installed. +6. Added pcre2_set_max_pattern_compiled_length() to limit the size of compiled +patterns. + Version 10.43 16-February-2024 ------------------------------ diff --git a/Makefile.am b/Makefile.am index 7bf5327c..65d07119 100644 --- a/Makefile.am +++ b/Makefile.am @@ -82,6 +82,7 @@ dist_html_DATA = \ doc/html/pcre2_set_glob_separator.html \ doc/html/pcre2_set_heap_limit.html \ doc/html/pcre2_set_match_limit.html \ + doc/html/pcre2_set_max_pattern_compiled_length.html \ doc/html/pcre2_set_max_pattern_length.html \ doc/html/pcre2_set_max_varlookbehind.html \ doc/html/pcre2_set_offset_limit.html \ @@ -180,6 +181,7 @@ dist_man_MANS = \ doc/pcre2_set_glob_separator.3 \ doc/pcre2_set_heap_limit.3 \ doc/pcre2_set_match_limit.3 \ + doc/pcre2_set_max_pattern_compiled_length.3 \ doc/pcre2_set_max_pattern_length.3 \ doc/pcre2_set_max_varlookbehind.3 \ doc/pcre2_set_offset_limit.3 \ diff --git a/doc/html/index.html b/doc/html/index.html index f056fed9..e4dc7862 100644 --- a/doc/html/index.html +++ b/doc/html/index.html @@ -252,8 +252,11 @@ in the library. <tr><td><a href="pcre2_set_match_limit.html">pcre2_set_match_limit</a></td> <td> Set the match limit</td></tr> +<tr><td><a href="pcre2_set_max_pattern_compiled_length.html">pcre2_set_max_pattern_compiled_length</a></td> + <td> Set the maximum length of a compiled pattern</td></tr> + <tr><td><a href="pcre2_set_max_pattern_length.html">pcre2_set_max_pattern_length</a></td> - <td> Set the maximum length of pattern</td></tr> + <td> Set the maximum length of a pattern</td></tr> <tr><td><a href="pcre2_set_max_varlookbehind.html">pcre2_set_max_varlookbehind</a></td> <td> Set the maximum match length for a variable-length lookbehind</td></tr> diff --git a/doc/html/pcre2_set_max_pattern_compiled_length.html b/doc/html/pcre2_set_max_pattern_compiled_length.html new file mode 100644 index 00000000..ab570cf6 --- /dev/null +++ b/doc/html/pcre2_set_max_pattern_compiled_length.html @@ -0,0 +1,44 @@ +<html> +<head> +<title>pcre2_set_max_pattern_compiled_length specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre2_set_max_pattern_compiled_length man page</h1> +<p> +Return to the <a href="index.html">PCRE2 index page</a>. +</p> +<p> +This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre2.h></b> +</P> +<P> +<b>int pcre2_set_max_pattern_compiled_length(</b> +<b> pcre2_compile_context *<i>ccontext</i>, PCRE2_SIZE <i>value</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function sets, in a compile context, the maximum size (in bytes) for the +memory needed to hold the compiled version of a pattern that is compiled with +this context. The result is always zero. If a pattern that is passed to +<b>pcre2_compile()</b> with this context needs more memory, an error is +generated. The default is the largest number that a PCRE2_SIZE variable can +hold, which is effectively unlimited. +</P> +<P> +There is a complete description of the PCRE2 native API in the +<a href="pcre2api.html"><b>pcre2api</b></a> +page and a description of the POSIX API in the +<a href="pcre2posix.html"><b>pcre2posix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE2 index page</a>. +</p> diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index 23997d72..6b60ee9f 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -161,6 +161,10 @@ document for an overview of all the PCRE2 documentation. <b> PCRE2_SIZE <i>value</i>);</b> <br> <br> +<b>int pcre2_set_max_pattern_compiled_length(</b> +<b> pcre2_compile_context *<i>ccontext</i>, PCRE2_SIZE <i>value</i>);</b> +<br> +<br> <b>int pcre2_set_max_varlookbehind(pcre2_compile_contest *<i>ccontext</i>,</b> <b>" uint32_t <i>value</i>);</b> <br> @@ -874,6 +878,18 @@ external sources can limit their size. The default is the largest number that a PCRE2_SIZE variable can hold, which is effectively unlimited. <br> <br> +<b>int pcre2_set_max_pattern_compiled_length(</b> +<b> pcre2_compile_context *<i>ccontext</i>, PCRE2_SIZE <i>value</i>);</b> +<br> +<br> +This sets a maximum size, in bytes, for the memory needed to hold the compiled +version of a pattern that is compiled with this context. If the pattern needs +more memory, an error is generated. This facility is provided so that +applications that accept patterns from external sources can limit the amount of +memory they use. The default is the largest number that a PCRE2_SIZE variable +can hold, which is effectively unlimited. +<br> +<br> <b>int pcre2_set_max_varlookbehind(pcre2_compile_contest *<i>ccontext</i>,</b> <b>" uint32_t <i>value</i>);</b> <br> @@ -4161,7 +4177,7 @@ Cambridge, England. </P> <br><a name="SEC43" href="#TOC1">REVISION</a><br> <P> -Last updated: 27 January 2024 +Last updated: 24 April 2024 <br> Copyright © 1997-2024 University of Cambridge. <br> diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html index fdeed5fb..6cc3cc31 100644 --- a/doc/html/pcre2test.html +++ b/doc/html/pcre2test.html @@ -696,7 +696,9 @@ heavily used in the test files. jitfast use JIT fast path jitverify verify JIT use locale=<name> use this locale - max_pattern_length=<n> set maximum pattern length + max_pattern_compiled ) set maximum compiled pattern + _length=<n> ) length (bytes) + max_pattern_length=<n> set maximum pattern length (code units) max_varlookbehind=<n> set maximum variable lookbehind length memory show memory used newline=<type> set newline type @@ -1019,6 +1021,15 @@ The <b>max_pattern_length</b> modifier sets a limit, in code units, to the length of pattern that <b>pcre2_compile()</b> will accept. Breaching the limit causes a compilation error. The default is the largest number a PCRE2_SIZE variable can hold (essentially unlimited). +</P> +<br><b> +Limiting the size of a compiled pattern +</b><br> +<P> +The <b>max_pattern_compiled_length</b> modifier sets a limit, in bytes, to the +amount of memory used by a compiled pattern. Breaching the limit causes a +compilation error. The default is the largest number a PCRE2_SIZE variable can +hold (essentially unlimited). <a name="posixwrapper"></a></P> <br><b> Using the POSIX wrapper API @@ -2193,7 +2204,7 @@ Cambridge, England. </P> <br><a name="SEC21" href="#TOC1">REVISION</a><br> <P> -Last updated: 27 January 2024 +Last updated: 24 April 2024 <br> Copyright © 1997-2024 University of Cambridge. <br> diff --git a/doc/index.html.src b/doc/index.html.src index f056fed9..e4dc7862 100644 --- a/doc/index.html.src +++ b/doc/index.html.src @@ -252,8 +252,11 @@ in the library. <tr><td><a href="pcre2_set_match_limit.html">pcre2_set_match_limit</a></td> <td> Set the match limit</td></tr> +<tr><td><a href="pcre2_set_max_pattern_compiled_length.html">pcre2_set_max_pattern_compiled_length</a></td> + <td> Set the maximum length of a compiled pattern</td></tr> + <tr><td><a href="pcre2_set_max_pattern_length.html">pcre2_set_max_pattern_length</a></td> - <td> Set the maximum length of pattern</td></tr> + <td> Set the maximum length of a pattern</td></tr> <tr><td><a href="pcre2_set_max_varlookbehind.html">pcre2_set_max_varlookbehind</a></td> <td> Set the maximum match length for a variable-length lookbehind</td></tr> diff --git a/doc/pcre2.txt b/doc/pcre2.txt index 50794f4f..25779322 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -283,6 +283,9 @@ PCRE2 NATIVE API COMPILE CONTEXT FUNCTIONS int pcre2_set_max_pattern_length(pcre2_compile_context *ccontext, PCRE2_SIZE value); + int pcre2_set_max_pattern_compiled_length( + pcre2_compile_context *ccontext, PCRE2_SIZE value); + int pcre2_set_max_varlookbehind(pcre2_compile_contest *ccontext, uint32_t value); @@ -912,6 +915,17 @@ PCRE2 CONTEXTS largest number that a PCRE2_SIZE variable can hold, which is effec- tively unlimited. + int pcre2_set_max_pattern_compiled_length( + pcre2_compile_context *ccontext, PCRE2_SIZE value); + + This sets a maximum size, in bytes, for the memory needed to hold the + compiled version of a pattern that is compiled with this context. If + the pattern needs more memory, an error is generated. This facility is + provided so that applications that accept patterns from external + sources can limit the amount of memory they use. The default is the + largest number that a PCRE2_SIZE variable can hold, which is effec- + tively unlimited. + int pcre2_set_max_varlookbehind(pcre2_compile_contest *ccontext, uint32_t value); @@ -3998,11 +4012,11 @@ AUTHOR REVISION - Last updated: 27 January 2024 + Last updated: 24 April 2024 Copyright (c) 1997-2024 University of Cambridge. -PCRE2 10.43 27 January 2024 PCRE2API(3) +PCRE2 10.44 24 April 2024 PCRE2API(3) ------------------------------------------------------------------------------ diff --git a/doc/pcre2_set_max_pattern_compiled_length.3 b/doc/pcre2_set_max_pattern_compiled_length.3 new file mode 100644 index 00000000..472a7bbd --- /dev/null +++ b/doc/pcre2_set_max_pattern_compiled_length.3 @@ -0,0 +1,32 @@ +.TH PCRE2_SET_MAX_PATTERN_COMPILED_LENGTH 3 "24 April 2024" "PCRE2 10.44" +.SH NAME +PCRE2 - Perl-compatible regular expressions (revised API) +.SH SYNOPSIS +.rs +.sp +.B #include <pcre2.h> +.PP +.nf +.B int pcre2_set_max_pattern_compiled_length( +.B " pcre2_compile_context *\fIccontext\fP, PCRE2_SIZE \fIvalue\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function sets, in a compile context, the maximum size (in bytes) for the +memory needed to hold the compiled version of a pattern that is compiled with +this context. The result is always zero. If a pattern that is passed to +\fBpcre2_compile()\fP with this context needs more memory, an error is +generated. The default is the largest number that a PCRE2_SIZE variable can +hold, which is effectively unlimited. +.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. diff --git a/doc/pcre2api.3 b/doc/pcre2api.3 index 47990052..6028d626 100644 --- a/doc/pcre2api.3 +++ b/doc/pcre2api.3 @@ -1,4 +1,4 @@ -.TH PCRE2API 3 "27 January 2024" "PCRE2 10.43" +.TH PCRE2API 3 "24 April 2024" "PCRE2 10.44" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .sp @@ -101,6 +101,9 @@ document for an overview of all the PCRE2 documentation. .B int pcre2_set_max_pattern_length(pcre2_compile_context *\fIccontext\fP, .B " PCRE2_SIZE \fIvalue\fP);" .sp +.B int pcre2_set_max_pattern_compiled_length( +.B " pcre2_compile_context *\fIccontext\fP, PCRE2_SIZE \fIvalue\fP);" +.sp .B int pcre2_set_max_varlookbehind(pcre2_compile_contest *\fIccontext\fP, .B " uint32_t \fIvalue\fP); .sp @@ -805,6 +808,18 @@ external sources can limit their size. The default is the largest number that a PCRE2_SIZE variable can hold, which is effectively unlimited. .sp .nf +.B int pcre2_set_max_pattern_compiled_length( +.B " pcre2_compile_context *\fIccontext\fP, PCRE2_SIZE \fIvalue\fP);" +.fi +.sp +This sets a maximum size, in bytes, for the memory needed to hold the compiled +version of a pattern that is compiled with this context. If the pattern needs +more memory, an error is generated. This facility is provided so that +applications that accept patterns from external sources can limit the amount of +memory they use. The default is the largest number that a PCRE2_SIZE variable +can hold, which is effectively unlimited. +.sp +.nf .B int pcre2_set_max_varlookbehind(pcre2_compile_contest *\fIccontext\fP, .B " uint32_t \fIvalue\fP); .fi @@ -4167,6 +4182,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 27 January 2024 +Last updated: 24 April 2024 Copyright (c) 1997-2024 University of Cambridge. .fi diff --git a/doc/pcre2demo.3 b/doc/pcre2demo.3 index ad0f730d..23933b58 100644 --- a/doc/pcre2demo.3 +++ b/doc/pcre2demo.3 @@ -1,4 +1,4 @@ -.TH PCRE2DEMO 3 "16 April 2024" "PCRE2 10.43" +.TH PCRE2DEMO 3 "24 April 2024" "PCRE2 10.43" .\"AUTOMATICALLY GENERATED BY PrepareRelease - do not EDIT! .SH NAME PCRE2DEMO - A demonstration C program for PCRE2 diff --git a/doc/pcre2test.1 b/doc/pcre2test.1 index 5e6f36a6..c7df4183 100644 --- a/doc/pcre2test.1 +++ b/doc/pcre2test.1 @@ -1,4 +1,4 @@ -.TH PCRE2TEST 1 "27 January 2024" "PCRE 10.43" +.TH PCRE2TEST 1 "24 April 2024" "PCRE 10.44" .SH NAME pcre2test - a program for testing Perl-compatible regular expressions. .SH SYNOPSIS @@ -652,7 +652,9 @@ heavily used in the test files. jitfast use JIT fast path jitverify verify JIT use locale=<name> use this locale - max_pattern_length=<n> set maximum pattern length + max_pattern_compiled ) set maximum compiled pattern + _length=<n> ) length (bytes) + max_pattern_length=<n> set maximum pattern length (code units) max_varlookbehind=<n> set maximum variable lookbehind length memory show memory used newline=<type> set newline type @@ -976,6 +978,15 @@ causes a compilation error. The default is the largest number a PCRE2_SIZE variable can hold (essentially unlimited). . . +.SS "Limiting the size of a compiled pattern" +.rs +.sp +The \fBmax_pattern_compiled_length\fP modifier sets a limit, in bytes, to the +amount of memory used by a compiled pattern. Breaching the limit causes a +compilation error. The default is the largest number a PCRE2_SIZE variable can +hold (essentially unlimited). +. +. .\" HTML <a name="posixwrapper"></a> .SS "Using the POSIX wrapper API" .rs @@ -2170,6 +2181,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 27 January 2024 +Last updated: 24 April 2024 Copyright (c) 1997-2024 University of Cambridge. .fi diff --git a/doc/pcre2test.txt b/doc/pcre2test.txt index d5750b48..ddb491d7 100644 --- a/doc/pcre2test.txt +++ b/doc/pcre2test.txt @@ -630,7 +630,9 @@ PATTERN MODIFIERS jitfast use JIT fast path jitverify verify JIT use locale=<name> use this locale - max_pattern_length=<n> set maximum pattern length + max_pattern_compiled ) set maximum compiled pattern + _length=<n> ) length (bytes) + max_pattern_length=<n> set maximum pattern length (code units) max_varlookbehind=<n> set maximum variable lookbehind length memory show memory used newline=<type> set newline type @@ -913,14 +915,21 @@ PATTERN MODIFIERS causes a compilation error. The default is the largest number a PCRE2_SIZE variable can hold (essentially unlimited). + Limiting the size of a compiled pattern + + The max_pattern_compiled_length modifier sets a limit, in bytes, to the + amount of memory used by a compiled pattern. Breaching the limit 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 @@ -930,42 +939,42 @@ PATTERN MODIFIERS 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 be- + The aftertext and allaftertext subject modifiers work as described be- low. All other modifiers are either ignored, with a warning message, or cause an error. - The pattern is passed to regcomp() as a zero-terminated string by de- + The pattern is passed to regcomp() as a zero-terminated string by de- fault, but if the use_length or hex modifiers are set, the REG_PEND ex- tension is used to pass it by length. 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, 2, or 3. 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 - behaviour with different character tables. The digit specifies the ta- + be passed to pcre2_compile(). This is used in the PCRE2 tests to check + behaviour with different character tables. The digit specifies the ta- bles as follows: 0 do not pass any special character tables @@ -976,15 +985,15 @@ PATTERN MODIFIERS In tables 2, some characters whose codes are greater than 128 are iden- tified as letters, digits, spaces, etc. Tables 3 can be used only after - a #loadtables command has loaded them from a binary file. Setting al- + a #loadtables command has loaded them from a binary file. Setting al- ternate character tables and a locale are mutually exclusive. Setting certain match controls The following modifiers are really subject modifiers, and are described - under "Subject Modifiers" below. However, they may be included in a - pattern's modifier list, in which case they are applied to every sub- - ject line that is processed with that pattern. These modifiers do not + under "Subject Modifiers" below. However, they may be included in a + pattern's modifier list, in which case they are applied to every sub- + ject line that is processed with that pattern. These modifiers do not affect the compilation process. aftertext show text after match @@ -1010,39 +1019,39 @@ PATTERN MODIFIERS 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. Specifying literal subject lines - If the subject_literal modifier is present on a pattern, all the sub- + If the subject_literal modifier is present on a pattern, all the sub- ject lines that it matches are taken as literal strings, with no inter- - pretation of backslashes. It is not possible to set subject modifiers - on such lines, but any that are set as defaults by a #subject command + pretation of backslashes. It is not possible to set subject modifiers + on such lines, but any that are set as defaults by a #subject command are recognized. 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 in- - compatible with compilation modifiers such as global that act at match + 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 in- + compatible 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 subsequent + warning message, except for replace, which causes an error. Note that + jitverify, which is allowed, does not carry through to any subsequent matching that uses a stacked pattern. Testing foreign pattern conversion - The experimental foreign pattern conversion functions in PCRE2 can be - tested by setting the convert modifier. Its argument is a colon-sepa- - rated list of options, which set the equivalent option for the + The experimental foreign pattern conversion functions in PCRE2 can be + tested by setting the convert modifier. Its argument is a colon-sepa- + rated list of options, which set the equivalent option for the pcre2_pattern_convert() function: glob PCRE2_CONVERT_GLOB @@ -1054,19 +1063,19 @@ PATTERN MODIFIERS The "unset" value is useful for turning off a default that has been set by a #pattern command. When one of these options is set, the input pat- - tern is passed to pcre2_pattern_convert(). If the conversion is suc- - cessful, the result is reflected in the output and then passed to + tern is passed to pcre2_pattern_convert(). If the conversion is suc- + cessful, the result is reflected in the output and then passed to pcre2_compile(). The normal utf and no_utf_check options, if set, cause - the PCRE2_CONVERT_UTF and PCRE2_CONVERT_NO_UTF_CHECK options to be + the PCRE2_CONVERT_UTF and PCRE2_CONVERT_NO_UTF_CHECK options to be passed to pcre2_pattern_convert(). By default, the conversion function is allowed to allocate a buffer for - its output. However, if the convert_length modifier is set to a value - greater than zero, pcre2test passes a buffer of the given length. This + its output. However, if the convert_length modifier is set to a value + greater than zero, pcre2test passes a buffer of the given length. This makes it possible to test the length check. - The convert_glob_escape and convert_glob_separator modifiers can be - used to specify the escape and separator characters for glob process- + The convert_glob_escape and convert_glob_separator modifiers can be + used to specify the escape and separator characters for glob process- ing, overriding the defaults, which are operating-system dependent. @@ -1077,7 +1086,7 @@ SUBJECT MODIFIERS 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 @@ -1094,35 +1103,35 @@ SUBJECT MODIFIERS 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 or posix_nosub modifier was present on the pattern, caus- + If the posix or posix_nosub modifier was present on the pattern, caus- ing the POSIX wrapper API to be used, the only option-setting modifiers that have any effect are notbol, notempty, and noteol, causing REG_NOT- - BOL, REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to + BOL, REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec(). The other modifiers are ignored, with a warning message. - There is one additional modifier that can be used with the POSIX wrap- + There is one additional modifier that can be used with the POSIX wrap- per. It is ignored (with a warning) if used for non-POSIX matching. posix_startend=<n>[:<m>] - This causes the subject string to be passed to regexec() using the - REG_STARTEND option, which uses offsets to specify which part of the - string is searched. If only one number is given, the end offset is - passed as the end of the subject string. For more detail of REG_STAR- - TEND, see the pcre2posix documentation. If the subject string contains - binary zeros (coded as escapes such as \x{00} because pcre2test does + This causes the subject string to be passed to regexec() using the + REG_STARTEND option, which uses offsets to specify which part of the + string is searched. If only one number is given, the end offset is + passed as the end of the subject string. For more detail of REG_STAR- + TEND, see the pcre2posix documentation. If the subject string contains + binary zeros (coded as escapes such as \x{00} because pcre2test does not support actual binary zeros in its input), you must use posix_star- tend to specify its length. 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 - is matched against that pattern, but can be overridden by modifiers on + 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, but can be overridden by modifiers on the subject. aftertext show text after match @@ -1175,29 +1184,29 @@ SUBJECT MODIFIERS 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, - for both full and partial matches. 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 look- - behind at the start of a match, or, for a complete match, a lookahead + The allusedtext modifier requests that all the text that was consulted + during a successful pattern match by the interpreter should be shown, + for both full and partial matches. 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 look- + behind at the start of a match, or, for a complete match, 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 indicated in the out- + follow the start and end of the actual match are indicated in the out- put by '<' or '>' characters underneath them. Here is an example: re> /(?<=pqr)abc(?=xyz)/ @@ -1208,16 +1217,16 @@ SUBJECT MODIFIERS Partial match: pqrabcxy <<< - The first, complete match shows that the matched string is "abc", with - the preceding and following strings "pqr" and "xyz" having been con- - sulted during the match (when processing the assertions). The partial + The first, complete match shows that the matched string is "abc", with + the preceding and following strings "pqr" and "xyz" having been con- + sulted during the match (when processing the assertions). The partial match can indicate only the preceding string. - 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 + is displayed from the starting character instead of from the match point, with circumflex characters under the earlier characters. For ex- ample: @@ -1226,7 +1235,7 @@ SUBJECT MODIFIERS 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 @@ -1234,104 +1243,104 @@ SUBJECT MODIFIERS 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) and does not apply when replace + 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) and does not apply when replace is specified; it is ignored, with a warning message, if present. Showing the entire ovector, for all outcomes The allvector modifier requests that the entire ovector be shown, what- ever the outcome of the match. Compare allcaptures, which shows only up - to the maximum number of capture groups for the pattern, and then only - for a successful complete non-DFA match. This modifier, which acts af- - ter any match result, and also for DFA matching, provides a means of - checking that there are no unexpected modifications to ovector fields. - Before each match attempt, the ovector is filled with a special value, - and if this is found in both elements of a capturing pair, "<un- - changed>" is output. After a successful match, this applies to all - groups after the maximum capture group for the pattern. In other cases - it applies to the entire ovector. After a partial match, the first two - elements are the only ones that should be set. After a DFA match, the - amount of ovector that is used depends on the number of matches that + to the maximum number of capture groups for the pattern, and then only + for a successful complete non-DFA match. This modifier, which acts af- + ter any match result, and also for DFA matching, provides a means of + checking that there are no unexpected modifications to ovector fields. + Before each match attempt, the ovector is filled with a special value, + and if this is found in both elements of a capturing pair, "<un- + changed>" is output. After a successful match, this applies to all + groups after the maximum capture group for the pattern. In other cases + it applies to the entire ovector. After a partial match, the first two + elements are the only ones that should be set. After a DFA match, the + amount of ovector that is used depends on the number of matches that were found. Testing pattern callouts - A callout function is supplied when pcre2test calls the library match- - ing functions, unless callout_none is specified. Its behaviour can be - controlled by various modifiers listed above whose names begin with - callout_. Details are given in the section entitled "Callouts" below. - Testing callouts from pcre2_substitute() is described separately in + A callout function is supplied when pcre2test calls the library match- + ing functions, unless callout_none is specified. Its behaviour can be + controlled by various modifiers listed above whose names begin with + callout_. Details are given in the section entitled "Callouts" below. + Testing callouts from pcre2_substitute() is described separately in "Testing the substitution function" below. 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 re- - tried. This imitates the way Perl handles such cases when using the /g - modifier or the split() function. Normally, the start offset is ad- - vanced by one character, but if the newline convention recognizes CRLF - as a newline, and the current character is CR followed by LF, an ad- + match fails, the start offset is advanced, and the normal match is re- + tried. This imitates the way Perl handles such cases when using the /g + modifier or the split() function. Normally, the start offset is ad- + vanced by one character, but if the newline convention recognizes CRLF + as a newline, and the current character is CR followed by LF, an ad- vance 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 capture group name or num- ber, 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 (or after one call of - pcre2_match() in the case of PCRE2_SUBSTITUTE_MATCHED). Note that re- - placement strings cannot contain commas, because a comma signifies the - end of a modifier. This is not thought to be an issue in a test pro- + If the replace modifier is set, the pcre2_substitute() function is + called instead of one of the matching functions (or after one call of + pcre2_match() in the case of PCRE2_SUBSTITUTE_MATCHED). Note that re- + placement strings cannot contain commas, because a comma signifies the + end of a modifier. This is not thought to be an issue in a test pro- gram. - Specifying a completely empty replacement string disables this modi- - fier. However, it is possible to specify an empty replacement by pro- - viding a buffer length, as described below, for an otherwise empty re- + Specifying a completely empty replacement string disables this modi- + fier. However, it is possible to specify an empty replacement by pro- + viding a buffer length, as described below, for an otherwise empty re- placement. - 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 @@ -1345,8 +1354,8 @@ SUBJECT MODIFIERS See the pcre2api documentation for details of these options. - 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 @@ -1355,12 +1364,12 @@ SUBJECT MODIFIERS =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 re- - placement 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 re- + placement string starting at the next character. Here is an example that tests the edge case: /abc/ @@ -1370,12 +1379,12 @@ SUBJECT MODIFIERS Failed: error -47: no more memory The default action of pcre2_substitute() is to return PCRE2_ER- - ROR_NOMEMORY when the output buffer is too small. However, if the - PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by using the substi- + ROR_NOMEMORY when the output buffer is too small. However, if the + PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by using the substi- tute_overflow_length modifier), pcre2_substitute() continues to go - through the motions of matching and substituting (but not doing any - callouts), in order to compute the size of buffer that is required. - When this happens, pcre2test shows the required buffer length (which + through the motions of matching and substituting (but not doing any + callouts), 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: @@ -1384,15 +1393,15 @@ SUBJECT MODIFIERS 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(). Testing substitute callouts If the substitute_callout modifier is set, a substitution callout func- - tion is set up. The null_context modifier must not be set, because the - address of the callout function is passed in a match context. When the - callout function is called (after each substitution), details of the + tion is set up. The null_context modifier must not be set, because the + address of the callout function is passed in a match context. When the + callout function is called (after each substitution), details of the input and output strings are output. For example: /abc/g,replace=<$0>,substitute_callout @@ -1401,19 +1410,19 @@ SUBJECT MODIFIERS 2(1) Old 6 9 "abc" New 8 13 "<abc>" 2: <abc>def<abc>pqr - The first number on each callout line is the count of matches. The + The first number on each callout line is the count of matches. The parenthesized number is the number of pairs that are set in the ovector - (that is, one more than the number of capturing groups that were set). + (that is, one more than the number of capturing groups that were set). Then are listed the offsets of the old substring, its contents, and the same for the replacement. - By default, the substitution callout function returns zero, which ac- - cepts the replacement and causes matching to continue if /g was used. - Two further modifiers can be used to test other return values. If sub- - stitute_skip is set to a value greater than zero the callout function - returns +1 for the match of that number, and similarly substitute_stop - returns -1. These cause the replacement to be rejected, and -1 causes - no further matching to take place. If either of them are set, substi- + By default, the substitution callout function returns zero, which ac- + cepts the replacement and causes matching to continue if /g was used. + Two further modifiers can be used to test other return values. If sub- + stitute_skip is set to a value greater than zero the callout function + returns +1 for the match of that number, and similarly substitute_stop + returns -1. These cause the replacement to be rejected, and -1 causes + no further matching to take place. If either of them are set, substi- tute_callout is assumed. For example: /abc/g,replace=<$0>,substitute_skip=1 @@ -1431,181 +1440,181 @@ SUBJECT MODIFIERS 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 - JIT optimization is not being used. The value is a number of kibibytes - (units of 1024 bytes). Setting zero reverts to the default of 32KiB. + 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 kibibytes + (units of 1024 bytes). Setting zero reverts to the default of 32KiB. Providing a stack that is larger than the default is necessary only for - very complicated patterns. If jitstack is set non-zero on a subject + very complicated patterns. If jitstack is set non-zero on a subject line it overrides any value that was set on the pattern. Setting heap, match, and depth limits - The heap_limit, match_limit, and depth_limit modifiers set the appro- - priate limits in the match context. These values are ignored when the + 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 or find_limits_noheap 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_heap_limit(), - pcre2_set_match_limit(), or pcre2_set_depth_limit() until it finds the - smallest value for each parameter that allows the match to complete + 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 + smallest value for each parameter that allows the match to complete without a "limit exceeded" error. The match itself may succeed or fail. An alternative modifier, find_limits_noheap, omits the heap limit. This - is used in the standard tests, because the minimum heap limit varies - between systems. If JIT is being used, only the match limit is rele- + is used in the standard tests, because the minimum heap limit varies + between systems. If JIT is being used, only the match limit is rele- vant, and the other two are automatically omitted. When using this modifier, the pattern should not contain any limit set- - tings such as (*LIMIT_MATCH=...) within it. If such a setting is + tings such as (*LIMIT_MATCH=...) within it. If such a setting is present and is lower than the minimum matching value, the minimum value - cannot be found because pcre2_set_match_limit() etc. are only able to + cannot be found because pcre2_set_match_limit() etc. are only able to reduce the value of an in-pattern limit; they cannot increase it. - For non-DFA matching, the minimum depth_limit number is a measure of + For non-DFA matching, the minimum depth_limit number is a measure of 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 + 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. For non-DFA matching, the match_limit number is a measure of the amount of backtracking that takes place, and learning the minimum value can be - instructive. For most simple matches, the number is quite small, but - for patterns with very large numbers of matching possibilities, it can - become large very quickly with increasing length of subject string. In - the case of DFA matching, match_limit controls the total number of + instructive. For most simple matches, the number is quite small, but + for patterns with very large numbers of matching possibilities, it can + become large very quickly with increasing length of subject string. In + the case of DFA matching, match_limit controls the total number of calls, both recursive and non-recursive, to the internal matching func- tion, thus controlling the overall amount of computing resource that is used. - For both kinds of matching, the heap_limit number, which is in - kibibytes (units of 1024 bytes), limits the amount of heap memory used + For both kinds of matching, the heap_limit number, which is in + kibibytes (units of 1024 bytes), limits the amount of heap memory used for matching. Showing MARK names The mark modifier causes the names from backtracking control verbs that - are returned from calls to pcre2_match() to be displayed. If a mark is - returned for a match, non-match, or partial match, pcre2test shows it. - For a match, it is on a line by itself, tagged with "MK:". Otherwise, + are returned from calls to pcre2_match() to be displayed. If a mark is + returned for a match, non-match, or partial match, pcre2test shows it. + For a match, it is on a line by itself, tagged with "MK:". Otherwise, it is added to the non-match message. Showing memory usage - The memory modifier causes pcre2test to log the sizes of all heap mem- - ory allocation and freeing calls that occur during a call to - pcre2_match() or pcre2_dfa_match(). In the latter case, heap memory is - used only when a match requires more internal workspace that the de- - fault allocation on the stack, so in many cases there will be no out- - put. No heap memory is allocated during matching with JIT. For this + The memory modifier causes pcre2test to log the sizes of all heap mem- + ory allocation and freeing calls that occur during a call to + pcre2_match() or pcre2_dfa_match(). In the latter case, heap memory is + used only when a match requires more internal workspace that the de- + fault allocation on the stack, so in many cases there will be no out- + put. No heap memory is allocated during matching with JIT. For this modifier to work, the null_context modifier must not be set on both the pattern and the subject, though it can be set on one or the other. Showing the heap frame overall vector size - The heapframes_size modifier is relevant for matches using + The heapframes_size modifier is relevant for matches using pcre2_match() without JIT. After a match has run (whether successful or - not) the size, in bytes, of the allocated heap frames vector that is - left attached to the match data block is shown. If the matching action - involved several calls to pcre2_match() (for example, global matching + not) the size, in bytes, of the allocated heap frames vector that is + left attached to the match data block is shown. If the matching action + involved several calls to pcre2_match() (for example, global matching or for timing) only the final value is shown. - This modifier is ignored, with a warning, for POSIX or DFA matching. + This modifier is ignored, with a warning, for POSIX or DFA matching. JIT matching does not use the heap frames vector, so the size is always - zero, unless there was a previous non-JIT match. Note that specifing a + zero, unless there was a previous non-JIT match. Note that specifing a size of zero for the output vector (see below) causes pcre2test to free its match data block (and associated heap frames vector) and allocate a new one. Setting a starting offset - The offset modifier sets an offset in the subject string at which + The offset modifier sets an offset in the subject string at which matching starts. Its value is a number of code units, not characters. Setting an offset limit - The offset_limit modifier sets a limit for unanchored matches. If a + The offset_limit modifier sets a limit for unanchored matches. If a match cannot be found starting at or before this offset in the subject, a "no match" return is given. The data value is a number of code units, - not characters. When this modifier is used, the use_offset_limit modi- + not characters. When this modifier is used, the use_offset_limit modi- fier must have been set for the pattern; if not, an error is generated. Setting the size of the output vector - The ovector modifier applies only to the subject line in which it ap- + The ovector modifier applies only to the subject line in which it ap- pears, though of course it can also be used to set a default in a #sub- - ject command. It specifies the number of pairs of offsets that are + ject command. It specifies the number of pairs of offsets that are available for storing matching information. The default is 15. - A value of zero is useful when testing the POSIX API because it causes + A value of zero is useful when testing the POSIX API because it causes regexec() to be called with a NULL capture vector. When not testing the - POSIX API, a value of zero is used to cause pcre2_match_data_cre- - ate_from_pattern() to be called, in order to create a new match block - of exactly the right size for the pattern. (It is not possible to cre- - ate a match block with a zero-length ovector; there is always at least + POSIX API, a value of zero is used to cause pcre2_match_data_cre- + ate_from_pattern() to be called, in order to create a new match block + of exactly the right size for the pattern. (It is not possible to cre- + ate a match block with a zero-length ovector; there is always at least one pair of offsets.) The old match data block is freed. Passing the subject as zero-terminated By default, the subject string is passed to a native API matching func- tion with its correct length. In order to test the facility for passing - a zero-terminated string, the zero_terminate modifier is provided. It - causes the length to be passed as PCRE2_ZERO_TERMINATED. When matching + a zero-terminated string, the zero_terminate modifier is provided. It + causes the length to be passed as PCRE2_ZERO_TERMINATED. When matching via the POSIX interface, this modifier is ignored, with a warning. - When testing pcre2_substitute(), this modifier also has the effect of + When testing pcre2_substitute(), this modifier also has the effect of passing the replacement string as zero-terminated. Passing a NULL context, subject, or replacement - Normally, pcre2test passes a context block to pcre2_match(), - pcre2_dfa_match(), pcre2_jit_match() or pcre2_substitute(). If the - null_context modifier is set, however, NULL is passed. This is for - testing that the matching and substitution functions behave correctly - in this case (they use default values). This modifier cannot be used - with the find_limits, find_limits_noheap, or substitute_callout modi- + Normally, pcre2test passes a context block to pcre2_match(), + pcre2_dfa_match(), pcre2_jit_match() or pcre2_substitute(). If the + null_context modifier is set, however, NULL is passed. This is for + testing that the matching and substitution functions behave correctly + in this case (they use default values). This modifier cannot be used + with the find_limits, find_limits_noheap, or substitute_callout modi- fiers. - Similarly, for testing purposes, if the null_subject or null_replace- - ment modifier is set, the subject or replacement string pointers are + Similarly, for testing purposes, if the null_subject or null_replace- + ment modifier is set, the subject or replacement string pointers are passed as NULL, respectively, to the relevant functions. THE ALTERNATIVE MATCHING FUNCTION - By default, pcre2test uses the standard PCRE2 matching function, + By default, pcre2test uses the standard PCRE2 matching function, pcre2_match() to match each subject line. PCRE2 also supports an alter- - native matching function, pcre2_dfa_match(), which operates in a dif- - ferent way, and has some restrictions. The differences between the two + native matching function, pcre2_dfa_match(), which operates in a dif- + ferent way, and has some restrictions. The differences between the two functions are described in the pcre2matching documentation. - If the dfa modifier is set, the alternative matching function is used. - This function finds all possible matches at a given point in the sub- - ject. If, however, the dfa_shortest modifier is set, processing stops - after the first match is found. This is always the shortest possible + If the dfa modifier is set, the alternative matching function is used. + This function finds all possible matches at a given point in the sub- + ject. If, however, the dfa_shortest modifier is set, processing stops + after the first match is found. This is always the shortest possible match. DEFAULT OUTPUT FROM pcre2test - This section describes the output when the normal matching function, + This section describes the output when the normal matching function, pcre2_match(), is being used. - When a match succeeds, pcre2test outputs the list of captured sub- - strings, starting with number 0 for the string that matched the whole + When a match succeeds, pcre2test outputs the list of captured sub- + strings, starting with number 0 for the string that matched the whole pattern. Otherwise, it outputs "No match" when the return is PCRE2_ER- - ROR_NOMATCH, or "Partial match:" followed by the partially matching - substring when the return is PCRE2_ERROR_PARTIAL. (Note that this is - the entire substring that was inspected during the partial match; it - may include characters before the actual match start if a lookbehind + ROR_NOMATCH, or "Partial match:" followed by the partially matching + substring when the return is PCRE2_ERROR_PARTIAL. (Note that this is + the entire substring that was inspected during the partial match; it + may include characters before the actual match start if a lookbehind assertion, \K, \b, or \B was involved.) For any other return, pcre2test outputs the PCRE2 negative error number - and a short descriptive phrase. If the error is a failed UTF string - check, the code unit offset of the start of the failing character is + and a short descriptive phrase. If the error is a failed UTF string + check, the code unit offset of the start of the failing character is also output. Here is an example of an interactive pcre2test run. $ pcre2test @@ -1621,8 +1630,8 @@ DEFAULT OUTPUT FROM pcre2test Unset capturing substrings that are not followed by one that is set are not shown by pcre2test unless the allcaptures modifier is specified. In the following example, there are two capturing substrings, but when the - first data line is matched, the second, unset substring is not shown. - An "internal" unset substring is shown as "<unset>", as for the second + first data line is matched, the second, unset substring is not shown. + An "internal" unset substring is shown as "<unset>", as for the second data line. re> /(a)|(b)/ @@ -1634,11 +1643,11 @@ DEFAULT OUTPUT FROM pcre2test 1: <unset> 2: b - If the strings contain any non-printing characters, they are output as - \xhh escapes if the value is less than 256 and UTF mode is not set. + If the strings contain any non-printing characters, they are output as + \xhh escapes if the value is less than 256 and UTF mode is not set. Otherwise they are output as \x{hh...} escapes. See below for the defi- - nition of non-printing characters. If the aftertext modifier is set, - the output for substring 0 is followed by the rest of the subject + nition of non-printing characters. If the aftertext modifier is set, + the output for substring 0 is followed by the rest of the subject string, identified by "0+" like this: re> /cat/aftertext @@ -1658,8 +1667,8 @@ DEFAULT OUTPUT FROM pcre2test 0: ipp 1: pp - "No match" is output only if the first match attempt fails. Here is an - example of a failure message (the offset 4 that is specified by the + "No match" is output only if the first match attempt fails. Here is an + example of a failure message (the offset 4 that is specified by the offset modifier is past the end of the subject string): re> /xyz/ @@ -1667,7 +1676,7 @@ DEFAULT OUTPUT FROM pcre2test Error -24 (bad offset value) Note that whereas patterns can be continued over several lines (a plain - ">" prompt is used for continuations), subject lines may not. However + ">" prompt is used for continuations), subject lines may not. However newlines can be included in a subject by means of the \n escape (or \r, \r\n, etc., depending on the newline sequence setting). @@ -1675,7 +1684,7 @@ DEFAULT OUTPUT FROM pcre2test OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION When the alternative matching function, pcre2_dfa_match(), is used, the - output consists of a list of all the matches that start at the first + output consists of a list of all the matches that start at the first point in the subject where there is at least one match. For example: re> /(tang|tangerine|tan)/ @@ -1684,11 +1693,11 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION 1: tang 2: tan - Using the normal matching function on this data finds only "tang". The - longest matching string is always given first (and numbered zero). Af- - ter a PCRE2_ERROR_PARTIAL return, the output is "Partial match:", fol- + Using the normal matching function on this data finds only "tang". The + longest matching string is always given first (and numbered zero). Af- + ter a PCRE2_ERROR_PARTIAL return, the output is "Partial match:", fol- lowed by the partially matching substring. Note that this is the entire - substring that was inspected during the partial match; it may include + substring that was inspected during the partial match; it may include characters before the actual match start if a lookbehind assertion, \b, or \B was involved. (\K is not supported for DFA matching.) @@ -1704,16 +1713,16 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION 1: tan 0: tan - The alternative matching function does not support substring capture, - so the modifiers that are concerned with captured substrings are not + The alternative matching function does not support substring capture, + so the modifiers that are concerned with captured substrings are not relevant. RESTARTING AFTER A PARTIAL MATCH - When the alternative matching function has given the PCRE2_ERROR_PAR- + When the alternative matching function has given the PCRE2_ERROR_PAR- TIAL return, indicating that the subject partially matched the pattern, - you can restart the match with additional subject data by means of the + you can restart the match with additional subject data by means of the dfa_restart modifier. For example: re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ @@ -1722,37 +1731,37 @@ RESTARTING AFTER A PARTIAL MATCH data> n05\=dfa,dfa_restart 0: n05 - For further information about partial matching, see the pcre2partial + For further information about partial matching, see the pcre2partial documentation. CALLOUTS If the pattern contains any callout requests, pcre2test's callout func- - tion is called during matching unless callout_none is specified. This + tion is called during matching unless callout_none is specified. This works with both matching functions, and with JIT, though there are some - differences in behaviour. The output for callouts with numerical argu- + differences in behaviour. The output for callouts with numerical argu- ments and those with string arguments is slightly different. Callouts with numerical arguments By default, the callout function displays the callout number, the start - and current positions in the subject text at the callout time, and the + and current positions in the subject text at the callout time, and the next pattern item to be tested. For example: --->pqrabcdef 0 ^ ^ \d - This output indicates that callout number 0 occurred for a match at- - tempt starting at the fourth character of the subject string, when the - pointer was at the seventh character, and when the next pattern item - was \d. Just one circumflex is output if the start and current posi- + This output indicates that callout number 0 occurred for a match at- + tempt starting at the fourth character of the subject string, when the + pointer was at the seventh character, and when the next pattern item + was \d. Just one circumflex is output if the start and current posi- tions are the same, or if the current position precedes the start posi- tion, which can happen if the callout is in a lookbehind assertion. Callouts numbered 255 are assumed to be automatic callouts, inserted as a result of the auto_callout pattern modifier. In this case, instead of - showing the callout number, the offset in the pattern, preceded by a + showing the callout number, the offset in the pattern, preceded by a plus, is output. For example: re> /\d?[A-E]\*/auto_callout @@ -1779,17 +1788,17 @@ CALLOUTS +12 ^ ^ 0: abc - The mark changes between matching "a" and "b", but stays the same for - the rest of the match, so nothing more is output. If, as a result of - backtracking, the mark reverts to being unset, the text "<unset>" is + The mark changes between matching "a" and "b", but stays the same for + the rest of the match, so nothing more is output. If, as a result of + backtracking, the mark reverts to being unset, the text "<unset>" is output. Callouts with string arguments The output for a callout with a string argument is similar, except that - instead of outputting a callout number before the position indicators, - the callout string and its offset in the pattern string are output be- - fore the reflection of the subject string, and the subject string is + instead of outputting a callout number before the position indicators, + the callout string and its offset in the pattern string are output be- + fore the reflection of the subject string, and the subject string is reflected for each callout. For example: re> /^ab(?C'first')cd(?C"second")ef/ @@ -1805,26 +1814,26 @@ CALLOUTS Callout modifiers - The callout function in pcre2test returns zero (carry on matching) by - default, but you can use a callout_fail modifier in a subject line to + The callout function in pcre2test returns zero (carry on matching) by + default, but you can use a callout_fail modifier in a subject line to change this and other parameters of the callout (see below). If the callout_capture modifier is set, the current captured groups are output when a callout occurs. This is useful only for non-DFA matching, - as pcre2_dfa_match() does not support capturing, so no captures are + as pcre2_dfa_match() does not support capturing, so no captures are ever shown. The normal callout output, showing the callout number or pattern offset - (as described above) is suppressed if the callout_no_where modifier is + (as described above) is suppressed if the callout_no_where modifier is set. - When using the interpretive matching function pcre2_match() without - JIT, setting the callout_extra modifier causes additional output from - pcre2test's callout function to be generated. For the first callout in - a match attempt at a new starting position in the subject, "New match - attempt" is output. If there has been a backtrack since the last call- + When using the interpretive matching function pcre2_match() without + JIT, setting the callout_extra modifier causes additional output from + pcre2test's callout function to be generated. For the first callout in + a match attempt at a new starting position in the subject, "New match + attempt" is output. If there has been a backtrack since the last call- out (or start of matching if this is the first callout), "Backtrack" is - output, followed by "No other matching paths" if the backtrack ended + output, followed by "No other matching paths" if the backtrack ended the previous match attempt. For example: re> /(a+)b/auto_callout,no_start_optimize,no_auto_possess @@ -1861,86 +1870,86 @@ CALLOUTS +1 ^ a+ No match - Notice that various optimizations must be turned off if you want all - possible matching paths to be scanned. If no_start_optimize is not - used, there is an immediate "no match", without any callouts, because - the starting optimization fails to find "b" in the subject, which it - knows must be present for any match. If no_auto_possess is not used, - the "a+" item is turned into "a++", which reduces the number of back- + Notice that various optimizations must be turned off if you want all + possible matching paths to be scanned. If no_start_optimize is not + used, there is an immediate "no match", without any callouts, because + the starting optimization fails to find "b" in the subject, which it + knows must be present for any match. If no_auto_possess is not used, + the "a+" item is turned into "a++", which reduces the number of back- tracks. - The callout_extra modifier has no effect if used with the DFA matching + The callout_extra modifier has no effect if used with the DFA matching function, or with JIT. Return values from callouts - The default return from the callout function is zero, which allows + 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 (caus- ing matching to backtrack) 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 + 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, caus- - ing 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 + ing 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 zero. - 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. Inserting callouts can be helpful when using pcre2test to check compli- - cated regular expressions. For further information about callouts, see + cated regular expressions. For further information about callouts, see the pcre2callout documentation. NON-PRINTING CHARACTERS When pcre2test is outputting text in the compiled version of a pattern, - bytes other than 32-126 are always treated as non-printing characters + bytes other than 32-126 are always treated as non-printing characters and are therefore shown as hex escapes. - When pcre2test is outputting text that is a matched part of a subject - string, it behaves in the same way, unless a different locale has been - set for the pattern (using the locale modifier). In this case, the is- + When pcre2test is outputting text that is a matched part of a subject + string, it behaves in the same way, unless a different locale has been + set for the pattern (using the locale modifier). In this case, the is- print() function is used to distinguish printing and non-printing char- acters. SAVING AND RESTORING COMPILED PATTERNS - It is possible to save compiled patterns on disc or elsewhere, and re- - load them later, subject to a number of restrictions. JIT data cannot - be saved. The host on which the patterns are reloaded must be running + It is possible to save compiled patterns on disc or elsewhere, and re- + load them later, subject to a number of restrictions. JIT data cannot + be saved. The host on which the patterns are reloaded must be running the same version of PCRE2, with the same code unit width, and must also - have the same endianness, pointer width and PCRE2_SIZE type. Before - compiled patterns can be saved they must be serialized, that is, con- - verted to a stream of bytes. A single byte stream may contain any num- - ber of compiled patterns, but they must all use the same character ta- - bles. A single copy of the tables is included in the byte stream (its + have the same endianness, pointer width and PCRE2_SIZE type. Before + compiled patterns can be saved they must be serialized, that is, con- + verted to a stream of bytes. A single byte stream may contain any num- + ber of compiled patterns, but they must all use the same character ta- + bles. A single copy of the tables is included in the byte stream (its size is 1088 bytes). - The functions whose names begin with pcre2_serialize_ are used for se- - rializing and de-serializing. They are described in the pcre2serialize - documentation. In this section we describe the features of pcre2test + The functions whose names begin with pcre2_serialize_ are used for se- + rializing and de-serializing. They are described in the pcre2serialize + documentation. In this section we describe the features of pcre2test that can be used to test these functions. - Note that "serialization" in PCRE2 does not convert compiled patterns - to an abstract format like Java or .NET. It just makes a reloadable + Note that "serialization" in PCRE2 does not convert compiled patterns + to an abstract format like Java or .NET. It just makes a reloadable byte code stream. Hence the restrictions on reloading mentioned above. - In pcre2test, when a pattern with push modifier is successfully com- - piled, it is pushed onto a stack of compiled patterns, and pcre2test - expects the next line to contain a new pattern (or command) instead of + In pcre2test, when a pattern with push modifier is successfully com- + piled, it is pushed onto a stack of compiled patterns, and pcre2test + expects the next line to contain a new pattern (or command) instead of a subject line. By contrast, the pushcopy modifier causes a copy of the - compiled pattern to be stacked, leaving the original available for im- - mediate matching. By using push and/or pushcopy, a number of patterns - can be compiled and retained. These modifiers are incompatible with + compiled pattern to be stacked, leaving the original available for im- + mediate matching. By using push and/or pushcopy, a number of patterns + can be compiled and retained. These modifiers are incompatible with posix, and control modifiers that act at match time are ignored (with a - message) for the stacked patterns. The jitverify modifier applies only + message) for the stacked patterns. The jitverify modifier applies only at compile time. The command @@ -1948,21 +1957,21 @@ SAVING AND RESTORING COMPILED PATTERNS #save <filename> causes all the stacked patterns to be serialized and the result written - to the named file. Afterwards, all the stacked patterns are freed. The + to the named file. Afterwards, all the stacked patterns are freed. The command #load <filename> - reads the data in the file, and then arranges for it to be de-serial- - ized, with the resulting compiled patterns added to the pattern stack. - The pattern on the top of the stack can be retrieved by the #pop com- - mand, which must be followed by lines of subjects that are to be - matched with the pattern, terminated as usual by an empty line or end - of file. This command may be followed by a modifier list containing - only control modifiers that act after a pattern has been compiled. In - particular, hex, posix, posix_nosub, push, and pushcopy are not al- - lowed, nor are any option-setting modifiers. The JIT modifiers are, - however permitted. Here is an example that saves and reloads two pat- + reads the data in the file, and then arranges for it to be de-serial- + ized, with the resulting compiled patterns added to the pattern stack. + The pattern on the top of the stack can be retrieved by the #pop com- + mand, which must be followed by lines of subjects that are to be + matched with the pattern, terminated as usual by an empty line or end + of file. This command may be followed by a modifier list containing + only control modifiers that act after a pattern has been compiled. In + particular, hex, posix, posix_nosub, push, and pushcopy are not al- + lowed, nor are any option-setting modifiers. The JIT modifiers are, + however permitted. Here is an example that saves and reloads two pat- terns. /abc/push @@ -1975,10 +1984,10 @@ SAVING AND RESTORING COMPILED PATTERNS #pop jit,bincode abc - If jitverify is used with #pop, it does not automatically imply jit, + If jitverify is used with #pop, it does not automatically imply jit, which is different behaviour from when it is used on a pattern. - The #popcopy command is analogous to the pushcopy modifier in that it + The #popcopy command is analogous to the pushcopy modifier in that it makes current a copy of the topmost stack pattern, leaving the original still on the stack. @@ -1998,8 +2007,8 @@ AUTHOR REVISION - Last updated: 27 January 2024 + Last updated: 24 April 2024 Copyright (c) 1997-2024 University of Cambridge. -PCRE 10.43 27 January 2024 PCRE2TEST(1) +PCRE 10.44 24 April 2024 PCRE2TEST(1) diff --git a/src/pcre2.h.in b/src/pcre2.h.in index 1e7e5eb1..b43534b0 100644 --- a/src/pcre2.h.in +++ b/src/pcre2.h.in @@ -604,6 +604,8 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \ pcre2_set_max_pattern_length(pcre2_compile_context *, PCRE2_SIZE); \ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \ + pcre2_set_max_pattern_compiled_length(pcre2_compile_context *, PCRE2_SIZE); \ +PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \ pcre2_set_max_varlookbehind(pcre2_compile_context *, uint32_t); \ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \ pcre2_set_newline(pcre2_compile_context *, uint32_t); \ @@ -901,6 +903,7 @@ pcre2_compile are called by application code. */ #define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_) #define pcre2_set_max_varlookbehind PCRE2_SUFFIX(pcre2_set_max_varlookbehind_) #define pcre2_set_max_pattern_length PCRE2_SUFFIX(pcre2_set_max_pattern_length_) +#define pcre2_set_max_pattern_compiled_length PCRE2_SUFFIX(pcre2_set_max_pattern_compiled_length_) #define pcre2_set_newline PCRE2_SUFFIX(pcre2_set_newline_) #define pcre2_set_parens_nest_limit PCRE2_SUFFIX(pcre2_set_parens_nest_limit_) #define pcre2_set_offset_limit PCRE2_SUFFIX(pcre2_set_offset_limit_) diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c index ecf56da1..8e6787ab 100644 --- a/src/pcre2_compile.c +++ b/src/pcre2_compile.c @@ -808,7 +808,8 @@ enum { ERR0 = COMPILE_ERROR_BASE, ERR61, ERR62, ERR63, ERR64, ERR65, ERR66, ERR67, ERR68, ERR69, ERR70, ERR71, ERR72, ERR73, ERR74, ERR75, ERR76, ERR77, ERR78, ERR79, ERR80, ERR81, ERR82, ERR83, ERR84, ERR85, ERR86, ERR87, ERR88, ERR89, ERR90, - ERR91, ERR92, ERR93, ERR94, ERR95, ERR96, ERR97, ERR98, ERR99, ERR100 }; + ERR91, ERR92, ERR93, ERR94, ERR95, ERR96, ERR97, ERR98, ERR99, ERR100, + ERR101 }; /* This is a table of start-of-pattern options such as (*UTF) and settings such as (*LIMIT_MATCH=nnnn) and (*CRLF). For completeness and backward @@ -10602,14 +10603,21 @@ if (length > MAX_PATTERN_SIZE) goto HAD_CB_ERROR; } -/* Compute the size of, and then get and initialize, the data block for storing -the compiled pattern and names table. Integer overflow should no longer be -possible because nowadays we limit the maximum value of cb.names_found and -cb.name_entry_size. */ +/* Compute the size of, then, if not too large, get and initialize the data +block for storing the compiled pattern and names table. Integer overflow should +no longer be possible because nowadays we limit the maximum value of +cb.names_found and cb.name_entry_size. */ re_blocksize = sizeof(pcre2_real_code) + CU2BYTES(length + (PCRE2_SIZE)cb.names_found * (PCRE2_SIZE)cb.name_entry_size); + +if (re_blocksize > ccontext->max_pattern_compiled_length) + { + errorcode = ERR101; + goto HAD_CB_ERROR; + } + re = (pcre2_real_code *) ccontext->memctl.malloc(re_blocksize, ccontext->memctl.memory_data); if (re == NULL) diff --git a/src/pcre2_context.c b/src/pcre2_context.c index 0bc2ea0b..9edbd1b2 100644 --- a/src/pcre2_context.c +++ b/src/pcre2_context.c @@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel Original API code Copyright (c) 1997-2012 University of Cambridge - New API code Copyright (c) 2016-2023 University of Cambridge + New API code Copyright (c) 2016-2024 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -136,6 +136,7 @@ const pcre2_compile_context PRIV(default_compile_context) = { NULL, /* Stack guard data */ PRIV(default_tables), /* Character tables */ PCRE2_UNSET, /* Max pattern length */ + PCRE2_UNSET, /* Max pattern compiled length */ BSR_DEFAULT, /* Backslash R default */ NEWLINE_DEFAULT, /* Newline convention */ PARENS_NEST_LIMIT, /* As it says */ @@ -353,6 +354,13 @@ return 0; } PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION +pcre2_set_max_pattern_compiled_length(pcre2_compile_context *ccontext, PCRE2_SIZE length) +{ +ccontext->max_pattern_compiled_length = length; +return 0; +} + +PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION pcre2_set_newline(pcre2_compile_context *ccontext, uint32_t newline) { switch(newline) diff --git a/src/pcre2_error.c b/src/pcre2_error.c index 1569f631..7fa997aa 100644 --- a/src/pcre2_error.c +++ b/src/pcre2_error.c @@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel Original API code Copyright (c) 1997-2012 University of Cambridge - New API code Copyright (c) 2016-2023 University of Cambridge + New API code Copyright (c) 2016-2024 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -189,6 +189,7 @@ static const unsigned char compile_error_texts[] = "\\K is not allowed in lookarounds (but see PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK)\0" /* 100 */ "branch too long in variable-length lookbehind assertion\0" + "compiled pattern would be longer than the limit set by the application\0" ; /* Match-time and UTF error texts are in the same format. */ diff --git a/src/pcre2_fuzzsupport.c b/src/pcre2_fuzzsupport.c index ae207fa5..806df0f6 100644 --- a/src/pcre2_fuzzsupport.c +++ b/src/pcre2_fuzzsupport.c @@ -8,7 +8,7 @@ rather than a file name. This allows easy testing of short strings. Written by Philip Hazel, October 2016 Updated February 2024 (Addison Crump added 16-bit/32-bit and JIT support) -Further updates March 2024 by PH +Further updates March/April 2024 by PH ***************************************************************************/ #include <errno.h> @@ -275,6 +275,7 @@ pcre2_match_data *match_data = NULL; #ifdef SUPPORT_JIT pcre2_match_data *match_data_jit = NULL; #endif +pcre2_compile_context *compile_context = NULL; pcre2_match_context *match_context = NULL; size_t match_size; int dfa_workspace[DFA_WORKSPACE_COUNT]; @@ -394,6 +395,19 @@ in large trees taking too much time. */ match_size = (size > MAX_MATCH_SIZE)? MAX_MATCH_SIZE : size; +/* Create a compile context, and set a limit on the size of the compiled +pattern. This stops the fuzzer using vast amounts of memory. */ + +compile_context = pcre2_compile_context_create(NULL); +if (compile_context == NULL) + { +#ifdef STANDALONE + fprintf(stderr, "** Failed to create compile context block\n"); +#endif + abort(); + } +pcre2_set_max_pattern_compiled_length(compile_context, 10*1024*1024); + /* Ensure that all undefined option bits are zero (waste of time trying them) and also that PCRE2_NO_UTF_CHECK is unset, as there is no guarantee that the input is valid UTF. Also unset PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as there is @@ -435,7 +449,7 @@ for (int i = 0; i < 2; i++) #endif code = pcre2_compile((PCRE2_SPTR)wdata, (PCRE2_SIZE)size, compile_options, - &errorcode, &erroroffset, NULL); + &errorcode, &erroroffset, compile_context); /* Compilation succeeded */ @@ -670,13 +684,15 @@ with the interpreter. */ compile_options = PCRE2_NEVER_BACKSLASH_C; /* For second time */ } +/* Tidy up before exiting */ + if (match_data != NULL) pcre2_match_data_free(match_data); #ifdef SUPPORT_JIT if (match_data_jit != NULL) pcre2_match_data_free(match_data_jit); free(newwdata); #endif if (match_context != NULL) pcre2_match_context_free(match_context); - +if (compile_context != NULL) pcre2_compile_context_free(compile_context); return 0; } diff --git a/src/pcre2_intmodedep.h b/src/pcre2_intmodedep.h index 5fcddce5..fd9245a4 100644 --- a/src/pcre2_intmodedep.h +++ b/src/pcre2_intmodedep.h @@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel Original API code Copyright (c) 1997-2012 University of Cambridge - New API code Copyright (c) 2016-2023 University of Cambridge + New API code Copyright (c) 2016-2024 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -568,6 +568,7 @@ typedef struct pcre2_real_compile_context { void *stack_guard_data; const uint8_t *tables; PCRE2_SIZE max_pattern_length; + PCRE2_SIZE max_pattern_compiled_length; uint16_t bsr_convention; uint16_t newline_convention; uint32_t parens_nest_limit; diff --git a/src/pcre2test.c b/src/pcre2test.c index bd972e1b..37903451 100644 --- a/src/pcre2test.c +++ b/src/pcre2test.c @@ -719,6 +719,7 @@ static modstruct modlist[] = { { "match_line", MOD_CTC, MOD_OPT, PCRE2_EXTRA_MATCH_LINE, CO(extra_options) }, { "match_unset_backref", MOD_PAT, MOD_OPT, PCRE2_MATCH_UNSET_BACKREF, PO(options) }, { "match_word", MOD_CTC, MOD_OPT, PCRE2_EXTRA_MATCH_WORD, CO(extra_options) }, + { "max_pattern_compiled_length", MOD_CTC, MOD_SIZ, 0, CO(max_pattern_compiled_length) }, { "max_pattern_length", MOD_CTC, MOD_SIZ, 0, CO(max_pattern_length) }, { "max_varlookbehind", MOD_CTC, MOD_INT, 0, CO(max_varlookbehind) }, { "memory", MOD_PD, MOD_CTL, CTL_MEMORY, PD(control) }, @@ -1428,6 +1429,14 @@ are supported. */ else \ pcre2_set_match_limit_32(G(a,32),b) +#define PCRE2_SET_MAX_PATTERN_COMPILED_LENGTH(a,b) \ + if (test_mode == PCRE8_MODE) \ + pcre2_set_max_pattern_compiled_length_8(G(a,8),b); \ + else if (test_mode == PCRE16_MODE) \ + pcre2_set_max_pattern_compiled_length_16(G(a,16),b); \ + else \ + pcre2_set_max_pattern_compiled_length_32(G(a,32),b) + #define PCRE2_SET_MAX_PATTERN_LENGTH(a,b) \ if (test_mode == PCRE8_MODE) \ pcre2_set_max_pattern_length_8(G(a,8),b); \ @@ -1934,6 +1943,12 @@ the three different cases. */ else \ G(pcre2_set_match_limit_,BITTWO)(G(a,BITTWO),b) +#define PCRE2_SET_MAX_PATTERN_COMPILED_LENGTH(a,b) \ + if (test_mode == G(G(PCRE,BITONE),_MODE)) \ + G(pcre2_set_max_pattern_compiled_length_,BITONE)(G(a,BITONE),b); \ + else \ + G(pcre2_set_max_pattern_compiled_length_,BITTWO)(G(a,BITTWO),b) + #define PCRE2_SET_MAX_PATTERN_LENGTH(a,b) \ if (test_mode == G(G(PCRE,BITONE),_MODE)) \ G(pcre2_set_max_pattern_length_,BITONE)(G(a,BITONE),b); \ @@ -2166,6 +2181,7 @@ the three different cases. */ #define PCRE2_SET_GLOB_SEPARATOR(r,a,b) r = pcre2_set_glob_separator_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_COMPILED_LENGTH(a,b) pcre2_set_max_pattern_compiled_length_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_MAX_VARLOOKBEHIND(a,b) pcre2_set_max_varlookbehind_8(G(a,8),b) #define PCRE2_SET_OFFSET_LIMIT(a,b) pcre2_set_offset_limit_8(G(a,8),b) @@ -4404,14 +4420,15 @@ if (test_mode == PCRE32_MODE) cblock_size = sizeof(pcre2_real_code_32); /* The uint32_t variables are cast before multiplying to stop code analyzers grumbling about potential overflow. */ -fprintf(outfile, "Memory allocation (code space): %" SIZ_FORM "\n", size - +fprintf(outfile, "Memory allocation - compiled block : %" SIZ_FORM "\n", size); +fprintf(outfile, "Memory allocation - code portion : %" SIZ_FORM "\n", size - (PCRE2_SIZE)name_count * (PCRE2_SIZE)name_entry_size * (PCRE2_SIZE)code_unit_size - cblock_size); if (pat_patctl.jit != 0) { (void)pattern_info(PCRE2_INFO_JITSIZE, &size, FALSE); - fprintf(outfile, "Memory allocation (JIT code): %" SIZ_FORM "\n", size); + fprintf(outfile, "Memory allocation - JIT code : %" SIZ_FORM "\n", size); } } @@ -5644,6 +5661,8 @@ if ((pat_patctl.control & CTL_POSIX) != 0) if (local_newline_default != 0) prmsg(&msg, "#newline_default"); if (FLD(pat_context, max_pattern_length) != PCRE2_UNSET) prmsg(&msg, "max_pattern_length"); + if (FLD(pat_context, max_pattern_compiled_length) != PCRE2_UNSET) + prmsg(&msg, "max_pattern_compiled_length"); if (FLD(pat_context, parens_nest_limit) != PARENS_NEST_DEFAULT) prmsg(&msg, "parens_nest_limit"); @@ -9409,11 +9428,11 @@ max_oveccount = DEFAULT_OVECCOUNT; #define CONTEXTTESTS \ (void)G(pcre2_set_compile_extra_options_,BITS)(G(pat_context,BITS), 0); \ (void)G(pcre2_set_max_pattern_length_,BITS)(G(pat_context,BITS), 0); \ + (void)G(pcre2_set_max_pattern_compiled_length_,BITS)(G(pat_context,BITS), 0); \ (void)G(pcre2_set_max_varlookbehind_,BITS)(G(pat_context,BITS), 0); \ (void)G(pcre2_set_offset_limit_,BITS)(G(dat_context,BITS), 0); \ (void)G(pcre2_get_match_data_size_,BITS)(G(match_data,BITS)) - /* Call the appropriate functions for the current mode, and exercise some functions that are not otherwise called. */ diff --git a/testdata/testinput2 b/testdata/testinput2 index 412d58b4..b90489ae 100644 --- a/testdata/testinput2 +++ b/testdata/testinput2 @@ -4694,6 +4694,9 @@ B)x/alt_verbnames,mark /abcdef/hex,max_pattern_length=3 +# Test compiled length limit +/(abcdefg){10}/max_pattern_compiled_length=100 + # These patterns used to take a long time to compile "(.*) diff --git a/testdata/testoutput2 b/testdata/testoutput2 index 0116727a..83756686 100644 --- a/testdata/testoutput2 +++ b/testdata/testoutput2 @@ -14952,6 +14952,10 @@ Failed: error 188 at offset 0: pattern string is longer than the limit set by th /abcdef/hex,max_pattern_length=3 +# Test compiled length limit +/(abcdefg){10}/max_pattern_compiled_length=100 +Failed: error 201 at offset 13: compiled pattern would be longer than the limit set by the application + # These patterns used to take a long time to compile "(.*) diff --git a/testdata/testoutput8-16-2 b/testdata/testoutput8-16-2 index 49b1022c..bcb9e177 100644 --- a/testdata/testoutput8-16-2 +++ b/testdata/testoutput8-16-2 @@ -10,7 +10,8 @@ #pattern fullbincode,memory /((?i)b)/ -Memory allocation (code space): 24 +Memory allocation - compiled block : 160 +Memory allocation - code portion : 24 ------------------------------------------------------------------ 0 9 Bra 2 5 CBra 1 @@ -21,7 +22,8 @@ Memory allocation (code space): 24 ------------------------------------------------------------------ /(?s)(.*X|^B)/ -Memory allocation (code space): 38 +Memory allocation - compiled block : 174 +Memory allocation - code portion : 38 ------------------------------------------------------------------ 0 16 Bra 2 7 CBra 1 @@ -36,7 +38,8 @@ Memory allocation (code space): 38 ------------------------------------------------------------------ /(?s:.*X|^B)/ -Memory allocation (code space): 36 +Memory allocation - compiled block : 172 +Memory allocation - code portion : 36 ------------------------------------------------------------------ 0 15 Bra 2 6 Bra @@ -51,7 +54,8 @@ Memory allocation (code space): 36 ------------------------------------------------------------------ /^[[:alnum:]]/ -Memory allocation (code space): 46 +Memory allocation - compiled block : 182 +Memory allocation - code portion : 46 ------------------------------------------------------------------ 0 20 Bra 2 ^ @@ -61,7 +65,8 @@ Memory allocation (code space): 46 ------------------------------------------------------------------ /#/Ix -Memory allocation (code space): 10 +Memory allocation - compiled block : 146 +Memory allocation - code portion : 10 ------------------------------------------------------------------ 0 2 Bra 2 2 Ket @@ -73,7 +78,8 @@ Options: extended Subject length lower bound = 0 /a#/Ix -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 a @@ -86,7 +92,8 @@ First code unit = 'a' Subject length lower bound = 1 /x?+/ -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 x?+ @@ -95,7 +102,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /x++/ -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 x++ @@ -104,7 +112,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /x{1,3}+/ -Memory allocation (code space): 20 +Memory allocation - compiled block : 156 +Memory allocation - code portion : 20 ------------------------------------------------------------------ 0 7 Bra 2 x @@ -114,7 +123,8 @@ Memory allocation (code space): 20 ------------------------------------------------------------------ /(x)*+/ -Memory allocation (code space): 26 +Memory allocation - compiled block : 162 +Memory allocation - code portion : 26 ------------------------------------------------------------------ 0 10 Bra 2 Braposzero @@ -126,7 +136,8 @@ Memory allocation (code space): 26 ------------------------------------------------------------------ /^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/ -Memory allocation (code space): 142 +Memory allocation - compiled block : 278 +Memory allocation - code portion : 142 ------------------------------------------------------------------ 0 68 Bra 2 ^ @@ -149,7 +160,8 @@ Memory allocation (code space): 142 ------------------------------------------------------------------ "8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b" -Memory allocation (code space): 1648 +Memory allocation - compiled block : 1784 +Memory allocation - code portion : 1648 ------------------------------------------------------------------ 0 821 Bra 2 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X @@ -159,7 +171,8 @@ Memory allocation (code space): 1648 ------------------------------------------------------------------ "\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b" -Memory allocation (code space): 1628 +Memory allocation - compiled block : 1764 +Memory allocation - code portion : 1628 ------------------------------------------------------------------ 0 811 Bra 2 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X @@ -169,7 +182,8 @@ Memory allocation (code space): 1628 ------------------------------------------------------------------ /(a(?1)b)/ -Memory allocation (code space): 32 +Memory allocation - compiled block : 168 +Memory allocation - code portion : 32 ------------------------------------------------------------------ 0 13 Bra 2 9 CBra 1 @@ -182,7 +196,8 @@ Memory allocation (code space): 32 ------------------------------------------------------------------ /(a(?1)+b)/ -Memory allocation (code space): 40 +Memory allocation - compiled block : 176 +Memory allocation - code portion : 40 ------------------------------------------------------------------ 0 17 Bra 2 13 CBra 1 @@ -197,7 +212,8 @@ Memory allocation (code space): 40 ------------------------------------------------------------------ /a(?P<name1>b|c)d(?P<longername2>e)/ -Memory allocation (code space): 54 +Memory allocation - compiled block : 242 +Memory allocation - code portion : 54 ------------------------------------------------------------------ 0 24 Bra 2 a @@ -215,7 +231,8 @@ Memory allocation (code space): 54 ------------------------------------------------------------------ /(?:a(?P<c>c(?P<d>d)))(?P<a>a)/ -Memory allocation (code space): 64 +Memory allocation - compiled block : 218 +Memory allocation - code portion : 64 ------------------------------------------------------------------ 0 29 Bra 2 18 Bra @@ -235,7 +252,8 @@ Memory allocation (code space): 64 ------------------------------------------------------------------ /(?P<a>a)...(?P=a)bbb(?P>a)d/ -Memory allocation (code space): 54 +Memory allocation - compiled block : 196 +Memory allocation - code portion : 54 ------------------------------------------------------------------ 0 24 Bra 2 5 CBra 1 @@ -253,7 +271,8 @@ Memory allocation (code space): 54 ------------------------------------------------------------------ /abc(?C255)de(?C)f/ -Memory allocation (code space): 50 +Memory allocation - compiled block : 186 +Memory allocation - code portion : 50 ------------------------------------------------------------------ 0 22 Bra 2 abc @@ -266,7 +285,8 @@ Memory allocation (code space): 50 ------------------------------------------------------------------ /abcde/auto_callout -Memory allocation (code space): 78 +Memory allocation - compiled block : 214 +Memory allocation - code portion : 78 ------------------------------------------------------------------ 0 36 Bra 2 Callout 255 0 1 @@ -285,7 +305,8 @@ Memory allocation (code space): 78 ------------------------------------------------------------------ /\x{100}/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 \x{100} @@ -294,7 +315,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /\x{1000}/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 \x{1000} @@ -303,7 +325,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /\x{10000}/utf -Memory allocation (code space): 16 +Memory allocation - compiled block : 152 +Memory allocation - code portion : 16 ------------------------------------------------------------------ 0 5 Bra 2 \x{10000} @@ -312,7 +335,8 @@ Memory allocation (code space): 16 ------------------------------------------------------------------ /\x{100000}/utf -Memory allocation (code space): 16 +Memory allocation - compiled block : 152 +Memory allocation - code portion : 16 ------------------------------------------------------------------ 0 5 Bra 2 \x{100000} @@ -321,7 +345,8 @@ Memory allocation (code space): 16 ------------------------------------------------------------------ /\x{10ffff}/utf -Memory allocation (code space): 16 +Memory allocation - compiled block : 152 +Memory allocation - code portion : 16 ------------------------------------------------------------------ 0 5 Bra 2 \x{10ffff} @@ -333,7 +358,8 @@ Memory allocation (code space): 16 Failed: error 134 at offset 9: character code point value in \x{} or \o{} is too large /[\x{ff}]/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 \x{ff} @@ -342,7 +368,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /[\x{100}]/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 \x{100} @@ -351,7 +378,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /\x80/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 \x{80} @@ -360,7 +388,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /\xff/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 \x{ff} @@ -369,7 +398,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /\x{0041}\x{2262}\x{0391}\x{002e}/I,utf -Memory allocation (code space): 26 +Memory allocation - compiled block : 162 +Memory allocation - code portion : 26 ------------------------------------------------------------------ 0 10 Bra 2 A\x{2262}\x{391}. @@ -383,7 +413,8 @@ Last code unit = '.' Subject length lower bound = 4 /\x{D55c}\x{ad6d}\x{C5B4}/I,utf -Memory allocation (code space): 22 +Memory allocation - compiled block : 158 +Memory allocation - code portion : 22 ------------------------------------------------------------------ 0 8 Bra 2 \x{d55c}\x{ad6d}\x{c5b4} @@ -397,7 +428,8 @@ Last code unit = \x{c5b4} Subject length lower bound = 3 /\x{65e5}\x{672c}\x{8a9e}/I,utf -Memory allocation (code space): 22 +Memory allocation - compiled block : 158 +Memory allocation - code portion : 22 ------------------------------------------------------------------ 0 8 Bra 2 \x{65e5}\x{672c}\x{8a9e} @@ -411,7 +443,8 @@ Last code unit = \x{8a9e} Subject length lower bound = 3 /[\x{100}]/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 \x{100} @@ -420,7 +453,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /[Z\x{100}]/utf -Memory allocation (code space): 54 +Memory allocation - compiled block : 190 +Memory allocation - code portion : 54 ------------------------------------------------------------------ 0 24 Bra 2 [Z\x{100}] @@ -429,7 +463,8 @@ Memory allocation (code space): 54 ------------------------------------------------------------------ /^[\x{100}\E-\Q\E\x{150}]/utf -Memory allocation (code space): 26 +Memory allocation - compiled block : 162 +Memory allocation - code portion : 26 ------------------------------------------------------------------ 0 10 Bra 2 ^ @@ -439,7 +474,8 @@ Memory allocation (code space): 26 ------------------------------------------------------------------ /^[\QĀ\E-\QŐ\E]/utf -Memory allocation (code space): 26 +Memory allocation - compiled block : 162 +Memory allocation - code portion : 26 ------------------------------------------------------------------ 0 10 Bra 2 ^ @@ -452,7 +488,8 @@ Memory allocation (code space): 26 Failed: error 106 at offset 13: missing terminating ] for character class /[\p{L}]/ -Memory allocation (code space): 24 +Memory allocation - compiled block : 160 +Memory allocation - code portion : 24 ------------------------------------------------------------------ 0 9 Bra 2 [\p{L}] @@ -461,7 +498,8 @@ Memory allocation (code space): 24 ------------------------------------------------------------------ /[\p{^L}]/ -Memory allocation (code space): 24 +Memory allocation - compiled block : 160 +Memory allocation - code portion : 24 ------------------------------------------------------------------ 0 9 Bra 2 [\P{L}] @@ -470,7 +508,8 @@ Memory allocation (code space): 24 ------------------------------------------------------------------ /[\P{L}]/ -Memory allocation (code space): 24 +Memory allocation - compiled block : 160 +Memory allocation - code portion : 24 ------------------------------------------------------------------ 0 9 Bra 2 [\P{L}] @@ -479,7 +518,8 @@ Memory allocation (code space): 24 ------------------------------------------------------------------ /[\P{^L}]/ -Memory allocation (code space): 24 +Memory allocation - compiled block : 160 +Memory allocation - code portion : 24 ------------------------------------------------------------------ 0 9 Bra 2 [\p{L}] @@ -488,7 +528,8 @@ Memory allocation (code space): 24 ------------------------------------------------------------------ /[abc\p{L}\x{0660}]/utf -Memory allocation (code space): 60 +Memory allocation - compiled block : 196 +Memory allocation - code portion : 60 ------------------------------------------------------------------ 0 27 Bra 2 [a-c\p{L}\x{660}] @@ -497,7 +538,8 @@ Memory allocation (code space): 60 ------------------------------------------------------------------ /[\p{Nd}]/utf -Memory allocation (code space): 24 +Memory allocation - compiled block : 160 +Memory allocation - code portion : 24 ------------------------------------------------------------------ 0 9 Bra 2 [\p{Nd}] @@ -506,7 +548,8 @@ Memory allocation (code space): 24 ------------------------------------------------------------------ /[\p{Nd}+-]+/utf -Memory allocation (code space): 58 +Memory allocation - compiled block : 194 +Memory allocation - code portion : 58 ------------------------------------------------------------------ 0 26 Bra 2 [+\-\p{Nd}]++ @@ -515,7 +558,8 @@ Memory allocation (code space): 58 ------------------------------------------------------------------ /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/i,utf -Memory allocation (code space): 32 +Memory allocation - compiled block : 168 +Memory allocation - code portion : 32 ------------------------------------------------------------------ 0 13 Bra 2 /i A\x{391}\x{10427}\x{ff3a}\x{1fb0} @@ -524,7 +568,8 @@ Memory allocation (code space): 32 ------------------------------------------------------------------ /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/utf -Memory allocation (code space): 32 +Memory allocation - compiled block : 168 +Memory allocation - code portion : 32 ------------------------------------------------------------------ 0 13 Bra 2 A\x{391}\x{10427}\x{ff3a}\x{1fb0} @@ -533,7 +578,8 @@ Memory allocation (code space): 32 ------------------------------------------------------------------ /[\x{105}-\x{109}]/i,utf -Memory allocation (code space): 24 +Memory allocation - compiled block : 160 +Memory allocation - code portion : 24 ------------------------------------------------------------------ 0 9 Bra 2 [\x{104}-\x{109}] @@ -542,7 +588,8 @@ Memory allocation (code space): 24 ------------------------------------------------------------------ /( ( (?(1)0|) )* )/x -Memory allocation (code space): 52 +Memory allocation - compiled block : 188 +Memory allocation - code portion : 52 ------------------------------------------------------------------ 0 23 Bra 2 19 CBra 1 @@ -560,7 +607,8 @@ Memory allocation (code space): 52 ------------------------------------------------------------------ /( (?(1)0|)* )/x -Memory allocation (code space): 42 +Memory allocation - compiled block : 178 +Memory allocation - code portion : 42 ------------------------------------------------------------------ 0 18 Bra 2 14 CBra 1 @@ -576,7 +624,8 @@ Memory allocation (code space): 42 ------------------------------------------------------------------ /[a]/ -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 a @@ -585,7 +634,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /[a]/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 a @@ -594,7 +644,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /[\xaa]/ -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 \x{aa} @@ -603,7 +654,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /[\xaa]/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 \x{aa} @@ -612,7 +664,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /[^a]/ -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 [^a] @@ -621,7 +674,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /[^a]/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 [^a] @@ -630,7 +684,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /[^\xaa]/ -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 [^\x{aa}] @@ -639,7 +694,8 @@ Memory allocation (code space): 14 ------------------------------------------------------------------ /[^\xaa]/utf -Memory allocation (code space): 14 +Memory allocation - compiled block : 150 +Memory allocation - code portion : 14 ------------------------------------------------------------------ 0 4 Bra 2 [^\x{aa}] diff --git a/testdata/testoutput8-32-2 b/testdata/testoutput8-32-2 index 91d96c94..d76f3aaa 100644 --- a/testdata/testoutput8-32-2 +++ b/testdata/testoutput8-32-2 @@ -10,7 +10,8 @@ #pattern fullbincode,memory /((?i)b)/ -Memory allocation (code space): 48 +Memory allocation - compiled block : 184 +Memory allocation - code portion : 48 ------------------------------------------------------------------ 0 9 Bra 2 5 CBra 1 @@ -21,7 +22,8 @@ Memory allocation (code space): 48 ------------------------------------------------------------------ /(?s)(.*X|^B)/ -Memory allocation (code space): 76 +Memory allocation - compiled block : 212 +Memory allocation - code portion : 76 ------------------------------------------------------------------ 0 16 Bra 2 7 CBra 1 @@ -36,7 +38,8 @@ Memory allocation (code space): 76 ------------------------------------------------------------------ /(?s:.*X|^B)/ -Memory allocation (code space): 72 +Memory allocation - compiled block : 208 +Memory allocation - code portion : 72 ------------------------------------------------------------------ 0 15 Bra 2 6 Bra @@ -51,7 +54,8 @@ Memory allocation (code space): 72 ------------------------------------------------------------------ /^[[:alnum:]]/ -Memory allocation (code space): 60 +Memory allocation - compiled block : 196 +Memory allocation - code portion : 60 ------------------------------------------------------------------ 0 12 Bra 2 ^ @@ -61,7 +65,8 @@ Memory allocation (code space): 60 ------------------------------------------------------------------ /#/Ix -Memory allocation (code space): 20 +Memory allocation - compiled block : 156 +Memory allocation - code portion : 20 ------------------------------------------------------------------ 0 2 Bra 2 2 Ket @@ -73,7 +78,8 @@ Options: extended Subject length lower bound = 0 /a#/Ix -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 a @@ -86,7 +92,8 @@ First code unit = 'a' Subject length lower bound = 1 /x?+/ -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 x?+ @@ -95,7 +102,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /x++/ -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 x++ @@ -104,7 +112,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /x{1,3}+/ -Memory allocation (code space): 40 +Memory allocation - compiled block : 176 +Memory allocation - code portion : 40 ------------------------------------------------------------------ 0 7 Bra 2 x @@ -114,7 +123,8 @@ Memory allocation (code space): 40 ------------------------------------------------------------------ /(x)*+/ -Memory allocation (code space): 52 +Memory allocation - compiled block : 188 +Memory allocation - code portion : 52 ------------------------------------------------------------------ 0 10 Bra 2 Braposzero @@ -126,7 +136,8 @@ Memory allocation (code space): 52 ------------------------------------------------------------------ /^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/ -Memory allocation (code space): 220 +Memory allocation - compiled block : 356 +Memory allocation - code portion : 220 ------------------------------------------------------------------ 0 52 Bra 2 ^ @@ -149,7 +160,8 @@ Memory allocation (code space): 220 ------------------------------------------------------------------ "8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b" -Memory allocation (code space): 3296 +Memory allocation - compiled block : 3432 +Memory allocation - code portion : 3296 ------------------------------------------------------------------ 0 821 Bra 2 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X @@ -159,7 +171,8 @@ Memory allocation (code space): 3296 ------------------------------------------------------------------ "\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b" -Memory allocation (code space): 3256 +Memory allocation - compiled block : 3392 +Memory allocation - code portion : 3256 ------------------------------------------------------------------ 0 811 Bra 2 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X @@ -169,7 +182,8 @@ Memory allocation (code space): 3256 ------------------------------------------------------------------ /(a(?1)b)/ -Memory allocation (code space): 64 +Memory allocation - compiled block : 200 +Memory allocation - code portion : 64 ------------------------------------------------------------------ 0 13 Bra 2 9 CBra 1 @@ -182,7 +196,8 @@ Memory allocation (code space): 64 ------------------------------------------------------------------ /(a(?1)+b)/ -Memory allocation (code space): 80 +Memory allocation - compiled block : 216 +Memory allocation - code portion : 80 ------------------------------------------------------------------ 0 17 Bra 2 13 CBra 1 @@ -197,7 +212,8 @@ Memory allocation (code space): 80 ------------------------------------------------------------------ /a(?P<name1>b|c)d(?P<longername2>e)/ -Memory allocation (code space): 108 +Memory allocation - compiled block : 348 +Memory allocation - code portion : 108 ------------------------------------------------------------------ 0 24 Bra 2 a @@ -215,7 +231,8 @@ Memory allocation (code space): 108 ------------------------------------------------------------------ /(?:a(?P<c>c(?P<d>d)))(?P<a>a)/ -Memory allocation (code space): 128 +Memory allocation - compiled block : 300 +Memory allocation - code portion : 128 ------------------------------------------------------------------ 0 29 Bra 2 18 Bra @@ -235,7 +252,8 @@ Memory allocation (code space): 128 ------------------------------------------------------------------ /(?P<a>a)...(?P=a)bbb(?P>a)d/ -Memory allocation (code space): 108 +Memory allocation - compiled block : 256 +Memory allocation - code portion : 108 ------------------------------------------------------------------ 0 24 Bra 2 5 CBra 1 @@ -253,7 +271,8 @@ Memory allocation (code space): 108 ------------------------------------------------------------------ /abc(?C255)de(?C)f/ -Memory allocation (code space): 100 +Memory allocation - compiled block : 236 +Memory allocation - code portion : 100 ------------------------------------------------------------------ 0 22 Bra 2 abc @@ -266,7 +285,8 @@ Memory allocation (code space): 100 ------------------------------------------------------------------ /abcde/auto_callout -Memory allocation (code space): 156 +Memory allocation - compiled block : 292 +Memory allocation - code portion : 156 ------------------------------------------------------------------ 0 36 Bra 2 Callout 255 0 1 @@ -285,7 +305,8 @@ Memory allocation (code space): 156 ------------------------------------------------------------------ /\x{100}/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{100} @@ -294,7 +315,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /\x{1000}/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{1000} @@ -303,7 +325,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /\x{10000}/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{10000} @@ -312,7 +335,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /\x{100000}/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{100000} @@ -321,7 +345,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /\x{10ffff}/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{10ffff} @@ -333,7 +358,8 @@ Memory allocation (code space): 28 Failed: error 134 at offset 9: character code point value in \x{} or \o{} is too large /[\x{ff}]/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{ff} @@ -342,7 +368,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /[\x{100}]/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{100} @@ -351,7 +378,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /\x80/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{80} @@ -360,7 +388,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /\xff/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{ff} @@ -369,7 +398,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /\x{0041}\x{2262}\x{0391}\x{002e}/I,utf -Memory allocation (code space): 52 +Memory allocation - compiled block : 188 +Memory allocation - code portion : 52 ------------------------------------------------------------------ 0 10 Bra 2 A\x{2262}\x{391}. @@ -383,7 +413,8 @@ Last code unit = '.' Subject length lower bound = 4 /\x{D55c}\x{ad6d}\x{C5B4}/I,utf -Memory allocation (code space): 44 +Memory allocation - compiled block : 180 +Memory allocation - code portion : 44 ------------------------------------------------------------------ 0 8 Bra 2 \x{d55c}\x{ad6d}\x{c5b4} @@ -397,7 +428,8 @@ Last code unit = \x{c5b4} Subject length lower bound = 3 /\x{65e5}\x{672c}\x{8a9e}/I,utf -Memory allocation (code space): 44 +Memory allocation - compiled block : 180 +Memory allocation - code portion : 44 ------------------------------------------------------------------ 0 8 Bra 2 \x{65e5}\x{672c}\x{8a9e} @@ -411,7 +443,8 @@ Last code unit = \x{8a9e} Subject length lower bound = 3 /[\x{100}]/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{100} @@ -420,7 +453,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /[Z\x{100}]/utf -Memory allocation (code space): 76 +Memory allocation - compiled block : 212 +Memory allocation - code portion : 76 ------------------------------------------------------------------ 0 16 Bra 2 [Z\x{100}] @@ -429,7 +463,8 @@ Memory allocation (code space): 76 ------------------------------------------------------------------ /^[\x{100}\E-\Q\E\x{150}]/utf -Memory allocation (code space): 52 +Memory allocation - compiled block : 188 +Memory allocation - code portion : 52 ------------------------------------------------------------------ 0 10 Bra 2 ^ @@ -439,7 +474,8 @@ Memory allocation (code space): 52 ------------------------------------------------------------------ /^[\QĀ\E-\QŐ\E]/utf -Memory allocation (code space): 52 +Memory allocation - compiled block : 188 +Memory allocation - code portion : 52 ------------------------------------------------------------------ 0 10 Bra 2 ^ @@ -452,7 +488,8 @@ Memory allocation (code space): 52 Failed: error 106 at offset 13: missing terminating ] for character class /[\p{L}]/ -Memory allocation (code space): 48 +Memory allocation - compiled block : 184 +Memory allocation - code portion : 48 ------------------------------------------------------------------ 0 9 Bra 2 [\p{L}] @@ -461,7 +498,8 @@ Memory allocation (code space): 48 ------------------------------------------------------------------ /[\p{^L}]/ -Memory allocation (code space): 48 +Memory allocation - compiled block : 184 +Memory allocation - code portion : 48 ------------------------------------------------------------------ 0 9 Bra 2 [\P{L}] @@ -470,7 +508,8 @@ Memory allocation (code space): 48 ------------------------------------------------------------------ /[\P{L}]/ -Memory allocation (code space): 48 +Memory allocation - compiled block : 184 +Memory allocation - code portion : 48 ------------------------------------------------------------------ 0 9 Bra 2 [\P{L}] @@ -479,7 +518,8 @@ Memory allocation (code space): 48 ------------------------------------------------------------------ /[\P{^L}]/ -Memory allocation (code space): 48 +Memory allocation - compiled block : 184 +Memory allocation - code portion : 48 ------------------------------------------------------------------ 0 9 Bra 2 [\p{L}] @@ -488,7 +528,8 @@ Memory allocation (code space): 48 ------------------------------------------------------------------ /[abc\p{L}\x{0660}]/utf -Memory allocation (code space): 88 +Memory allocation - compiled block : 224 +Memory allocation - code portion : 88 ------------------------------------------------------------------ 0 19 Bra 2 [a-c\p{L}\x{660}] @@ -497,7 +538,8 @@ Memory allocation (code space): 88 ------------------------------------------------------------------ /[\p{Nd}]/utf -Memory allocation (code space): 48 +Memory allocation - compiled block : 184 +Memory allocation - code portion : 48 ------------------------------------------------------------------ 0 9 Bra 2 [\p{Nd}] @@ -506,7 +548,8 @@ Memory allocation (code space): 48 ------------------------------------------------------------------ /[\p{Nd}+-]+/utf -Memory allocation (code space): 84 +Memory allocation - compiled block : 220 +Memory allocation - code portion : 84 ------------------------------------------------------------------ 0 18 Bra 2 [+\-\p{Nd}]++ @@ -515,7 +558,8 @@ Memory allocation (code space): 84 ------------------------------------------------------------------ /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/i,utf -Memory allocation (code space): 60 +Memory allocation - compiled block : 196 +Memory allocation - code portion : 60 ------------------------------------------------------------------ 0 12 Bra 2 /i A\x{391}\x{10427}\x{ff3a}\x{1fb0} @@ -524,7 +568,8 @@ Memory allocation (code space): 60 ------------------------------------------------------------------ /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/utf -Memory allocation (code space): 60 +Memory allocation - compiled block : 196 +Memory allocation - code portion : 60 ------------------------------------------------------------------ 0 12 Bra 2 A\x{391}\x{10427}\x{ff3a}\x{1fb0} @@ -533,7 +578,8 @@ Memory allocation (code space): 60 ------------------------------------------------------------------ /[\x{105}-\x{109}]/i,utf -Memory allocation (code space): 48 +Memory allocation - compiled block : 184 +Memory allocation - code portion : 48 ------------------------------------------------------------------ 0 9 Bra 2 [\x{104}-\x{109}] @@ -542,7 +588,8 @@ Memory allocation (code space): 48 ------------------------------------------------------------------ /( ( (?(1)0|) )* )/x -Memory allocation (code space): 104 +Memory allocation - compiled block : 240 +Memory allocation - code portion : 104 ------------------------------------------------------------------ 0 23 Bra 2 19 CBra 1 @@ -560,7 +607,8 @@ Memory allocation (code space): 104 ------------------------------------------------------------------ /( (?(1)0|)* )/x -Memory allocation (code space): 84 +Memory allocation - compiled block : 220 +Memory allocation - code portion : 84 ------------------------------------------------------------------ 0 18 Bra 2 14 CBra 1 @@ -576,7 +624,8 @@ Memory allocation (code space): 84 ------------------------------------------------------------------ /[a]/ -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 a @@ -585,7 +634,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /[a]/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 a @@ -594,7 +644,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /[\xaa]/ -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{aa} @@ -603,7 +654,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /[\xaa]/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 \x{aa} @@ -612,7 +664,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /[^a]/ -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 [^a] @@ -621,7 +674,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /[^a]/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 [^a] @@ -630,7 +684,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /[^\xaa]/ -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 [^\x{aa}] @@ -639,7 +694,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /[^\xaa]/utf -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 4 Bra 2 [^\x{aa}] diff --git a/testdata/testoutput8-8-2 b/testdata/testoutput8-8-2 index e9568e53..f3811d95 100644 --- a/testdata/testoutput8-8-2 +++ b/testdata/testoutput8-8-2 @@ -10,7 +10,8 @@ #pattern fullbincode,memory /((?i)b)/ -Memory allocation (code space): 17 +Memory allocation - compiled block : 153 +Memory allocation - code portion : 17 ------------------------------------------------------------------ 0 13 Bra 3 7 CBra 1 @@ -21,7 +22,8 @@ Memory allocation (code space): 17 ------------------------------------------------------------------ /(?s)(.*X|^B)/ -Memory allocation (code space): 25 +Memory allocation - compiled block : 161 +Memory allocation - code portion : 25 ------------------------------------------------------------------ 0 21 Bra 3 9 CBra 1 @@ -36,7 +38,8 @@ Memory allocation (code space): 25 ------------------------------------------------------------------ /(?s:.*X|^B)/ -Memory allocation (code space): 23 +Memory allocation - compiled block : 159 +Memory allocation - code portion : 23 ------------------------------------------------------------------ 0 19 Bra 3 7 Bra @@ -51,7 +54,8 @@ Memory allocation (code space): 23 ------------------------------------------------------------------ /^[[:alnum:]]/ -Memory allocation (code space): 41 +Memory allocation - compiled block : 177 +Memory allocation - code portion : 41 ------------------------------------------------------------------ 0 37 Bra 3 ^ @@ -61,7 +65,8 @@ Memory allocation (code space): 41 ------------------------------------------------------------------ /#/Ix -Memory allocation (code space): 7 +Memory allocation - compiled block : 143 +Memory allocation - code portion : 7 ------------------------------------------------------------------ 0 3 Bra 3 3 Ket @@ -73,7 +78,8 @@ Options: extended Subject length lower bound = 0 /a#/Ix -Memory allocation (code space): 9 +Memory allocation - compiled block : 145 +Memory allocation - code portion : 9 ------------------------------------------------------------------ 0 5 Bra 3 a @@ -86,7 +92,8 @@ First code unit = 'a' Subject length lower bound = 1 /x?+/ -Memory allocation (code space): 9 +Memory allocation - compiled block : 145 +Memory allocation - code portion : 9 ------------------------------------------------------------------ 0 5 Bra 3 x?+ @@ -95,7 +102,8 @@ Memory allocation (code space): 9 ------------------------------------------------------------------ /x++/ -Memory allocation (code space): 9 +Memory allocation - compiled block : 145 +Memory allocation - code portion : 9 ------------------------------------------------------------------ 0 5 Bra 3 x++ @@ -104,7 +112,8 @@ Memory allocation (code space): 9 ------------------------------------------------------------------ /x{1,3}+/ -Memory allocation (code space): 13 +Memory allocation - compiled block : 149 +Memory allocation - code portion : 13 ------------------------------------------------------------------ 0 9 Bra 3 x @@ -114,7 +123,8 @@ Memory allocation (code space): 13 ------------------------------------------------------------------ /(x)*+/ -Memory allocation (code space): 18 +Memory allocation - compiled block : 154 +Memory allocation - code portion : 18 ------------------------------------------------------------------ 0 14 Bra 3 Braposzero @@ -126,7 +136,8 @@ Memory allocation (code space): 18 ------------------------------------------------------------------ /^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/ -Memory allocation (code space): 120 +Memory allocation - compiled block : 256 +Memory allocation - code portion : 120 ------------------------------------------------------------------ 0 116 Bra 3 ^ @@ -149,7 +160,8 @@ Memory allocation (code space): 120 ------------------------------------------------------------------ "8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b" -Memory allocation (code space): 826 +Memory allocation - compiled block : 962 +Memory allocation - code portion : 826 ------------------------------------------------------------------ 0 822 Bra 3 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X @@ -159,7 +171,8 @@ Memory allocation (code space): 826 ------------------------------------------------------------------ "\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b" -Memory allocation (code space): 816 +Memory allocation - compiled block : 952 +Memory allocation - code portion : 816 ------------------------------------------------------------------ 0 812 Bra 3 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X @@ -169,7 +182,8 @@ Memory allocation (code space): 816 ------------------------------------------------------------------ /(a(?1)b)/ -Memory allocation (code space): 22 +Memory allocation - compiled block : 158 +Memory allocation - code portion : 22 ------------------------------------------------------------------ 0 18 Bra 3 12 CBra 1 @@ -182,7 +196,8 @@ Memory allocation (code space): 22 ------------------------------------------------------------------ /(a(?1)+b)/ -Memory allocation (code space): 28 +Memory allocation - compiled block : 164 +Memory allocation - code portion : 28 ------------------------------------------------------------------ 0 24 Bra 3 18 CBra 1 @@ -197,7 +212,8 @@ Memory allocation (code space): 28 ------------------------------------------------------------------ /a(?P<name1>b|c)d(?P<longername2>e)/ -Memory allocation (code space): 36 +Memory allocation - compiled block : 200 +Memory allocation - code portion : 36 ------------------------------------------------------------------ 0 32 Bra 3 a @@ -215,7 +231,8 @@ Memory allocation (code space): 36 ------------------------------------------------------------------ /(?:a(?P<c>c(?P<d>d)))(?P<a>a)/ -Memory allocation (code space): 45 +Memory allocation - compiled block : 193 +Memory allocation - code portion : 45 ------------------------------------------------------------------ 0 41 Bra 3 25 Bra @@ -235,7 +252,8 @@ Memory allocation (code space): 45 ------------------------------------------------------------------ /(?P<a>a)...(?P=a)bbb(?P>a)d/ -Memory allocation (code space): 34 +Memory allocation - compiled block : 174 +Memory allocation - code portion : 34 ------------------------------------------------------------------ 0 30 Bra 3 7 CBra 1 @@ -253,7 +271,8 @@ Memory allocation (code space): 34 ------------------------------------------------------------------ /abc(?C255)de(?C)f/ -Memory allocation (code space): 31 +Memory allocation - compiled block : 167 +Memory allocation - code portion : 31 ------------------------------------------------------------------ 0 27 Bra 3 abc @@ -266,7 +285,8 @@ Memory allocation (code space): 31 ------------------------------------------------------------------ /abcde/auto_callout -Memory allocation (code space): 53 +Memory allocation - compiled block : 189 +Memory allocation - code portion : 53 ------------------------------------------------------------------ 0 49 Bra 3 Callout 255 0 1 @@ -285,7 +305,8 @@ Memory allocation (code space): 53 ------------------------------------------------------------------ /\x{100}/utf -Memory allocation (code space): 10 +Memory allocation - compiled block : 146 +Memory allocation - code portion : 10 ------------------------------------------------------------------ 0 6 Bra 3 \x{100} @@ -294,7 +315,8 @@ Memory allocation (code space): 10 ------------------------------------------------------------------ /\x{1000}/utf -Memory allocation (code space): 11 +Memory allocation - compiled block : 147 +Memory allocation - code portion : 11 ------------------------------------------------------------------ 0 7 Bra 3 \x{1000} @@ -303,7 +325,8 @@ Memory allocation (code space): 11 ------------------------------------------------------------------ /\x{10000}/utf -Memory allocation (code space): 12 +Memory allocation - compiled block : 148 +Memory allocation - code portion : 12 ------------------------------------------------------------------ 0 8 Bra 3 \x{10000} @@ -312,7 +335,8 @@ Memory allocation (code space): 12 ------------------------------------------------------------------ /\x{100000}/utf -Memory allocation (code space): 12 +Memory allocation - compiled block : 148 +Memory allocation - code portion : 12 ------------------------------------------------------------------ 0 8 Bra 3 \x{100000} @@ -321,7 +345,8 @@ Memory allocation (code space): 12 ------------------------------------------------------------------ /\x{10ffff}/utf -Memory allocation (code space): 12 +Memory allocation - compiled block : 148 +Memory allocation - code portion : 12 ------------------------------------------------------------------ 0 8 Bra 3 \x{10ffff} @@ -333,7 +358,8 @@ Memory allocation (code space): 12 Failed: error 134 at offset 9: character code point value in \x{} or \o{} is too large /[\x{ff}]/utf -Memory allocation (code space): 10 +Memory allocation - compiled block : 146 +Memory allocation - code portion : 10 ------------------------------------------------------------------ 0 6 Bra 3 \x{ff} @@ -342,7 +368,8 @@ Memory allocation (code space): 10 ------------------------------------------------------------------ /[\x{100}]/utf -Memory allocation (code space): 10 +Memory allocation - compiled block : 146 +Memory allocation - code portion : 10 ------------------------------------------------------------------ 0 6 Bra 3 \x{100} @@ -351,7 +378,8 @@ Memory allocation (code space): 10 ------------------------------------------------------------------ /\x80/utf -Memory allocation (code space): 10 +Memory allocation - compiled block : 146 +Memory allocation - code portion : 10 ------------------------------------------------------------------ 0 6 Bra 3 \x{80} @@ -360,7 +388,8 @@ Memory allocation (code space): 10 ------------------------------------------------------------------ /\xff/utf -Memory allocation (code space): 10 +Memory allocation - compiled block : 146 +Memory allocation - code portion : 10 ------------------------------------------------------------------ 0 6 Bra 3 \x{ff} @@ -369,7 +398,8 @@ Memory allocation (code space): 10 ------------------------------------------------------------------ /\x{0041}\x{2262}\x{0391}\x{002e}/I,utf -Memory allocation (code space): 18 +Memory allocation - compiled block : 154 +Memory allocation - code portion : 18 ------------------------------------------------------------------ 0 14 Bra 3 A\x{2262}\x{391}. @@ -383,7 +413,8 @@ Last code unit = '.' Subject length lower bound = 4 /\x{D55c}\x{ad6d}\x{C5B4}/I,utf -Memory allocation (code space): 19 +Memory allocation - compiled block : 155 +Memory allocation - code portion : 19 ------------------------------------------------------------------ 0 15 Bra 3 \x{d55c}\x{ad6d}\x{c5b4} @@ -397,7 +428,8 @@ Last code unit = \xb4 Subject length lower bound = 3 /\x{65e5}\x{672c}\x{8a9e}/I,utf -Memory allocation (code space): 19 +Memory allocation - compiled block : 155 +Memory allocation - code portion : 19 ------------------------------------------------------------------ 0 15 Bra 3 \x{65e5}\x{672c}\x{8a9e} @@ -411,7 +443,8 @@ Last code unit = \x9e Subject length lower bound = 3 /[\x{100}]/utf -Memory allocation (code space): 10 +Memory allocation - compiled block : 146 +Memory allocation - code portion : 10 ------------------------------------------------------------------ 0 6 Bra 3 \x{100} @@ -420,7 +453,8 @@ Memory allocation (code space): 10 ------------------------------------------------------------------ /[Z\x{100}]/utf -Memory allocation (code space): 47 +Memory allocation - compiled block : 183 +Memory allocation - code portion : 47 ------------------------------------------------------------------ 0 43 Bra 3 [Z\x{100}] @@ -429,7 +463,8 @@ Memory allocation (code space): 47 ------------------------------------------------------------------ /^[\x{100}\E-\Q\E\x{150}]/utf -Memory allocation (code space): 18 +Memory allocation - compiled block : 154 +Memory allocation - code portion : 18 ------------------------------------------------------------------ 0 14 Bra 3 ^ @@ -439,7 +474,8 @@ Memory allocation (code space): 18 ------------------------------------------------------------------ /^[\QĀ\E-\QŐ\E]/utf -Memory allocation (code space): 18 +Memory allocation - compiled block : 154 +Memory allocation - code portion : 18 ------------------------------------------------------------------ 0 14 Bra 3 ^ @@ -452,7 +488,8 @@ Memory allocation (code space): 18 Failed: error 106 at offset 15: missing terminating ] for character class /[\p{L}]/ -Memory allocation (code space): 15 +Memory allocation - compiled block : 151 +Memory allocation - code portion : 15 ------------------------------------------------------------------ 0 11 Bra 3 [\p{L}] @@ -461,7 +498,8 @@ Memory allocation (code space): 15 ------------------------------------------------------------------ /[\p{^L}]/ -Memory allocation (code space): 15 +Memory allocation - compiled block : 151 +Memory allocation - code portion : 15 ------------------------------------------------------------------ 0 11 Bra 3 [\P{L}] @@ -470,7 +508,8 @@ Memory allocation (code space): 15 ------------------------------------------------------------------ /[\P{L}]/ -Memory allocation (code space): 15 +Memory allocation - compiled block : 151 +Memory allocation - code portion : 15 ------------------------------------------------------------------ 0 11 Bra 3 [\P{L}] @@ -479,7 +518,8 @@ Memory allocation (code space): 15 ------------------------------------------------------------------ /[\P{^L}]/ -Memory allocation (code space): 15 +Memory allocation - compiled block : 151 +Memory allocation - code portion : 15 ------------------------------------------------------------------ 0 11 Bra 3 [\p{L}] @@ -488,7 +528,8 @@ Memory allocation (code space): 15 ------------------------------------------------------------------ /[abc\p{L}\x{0660}]/utf -Memory allocation (code space): 50 +Memory allocation - compiled block : 186 +Memory allocation - code portion : 50 ------------------------------------------------------------------ 0 46 Bra 3 [a-c\p{L}\x{660}] @@ -497,7 +538,8 @@ Memory allocation (code space): 50 ------------------------------------------------------------------ /[\p{Nd}]/utf -Memory allocation (code space): 15 +Memory allocation - compiled block : 151 +Memory allocation - code portion : 15 ------------------------------------------------------------------ 0 11 Bra 3 [\p{Nd}] @@ -506,7 +548,8 @@ Memory allocation (code space): 15 ------------------------------------------------------------------ /[\p{Nd}+-]+/utf -Memory allocation (code space): 48 +Memory allocation - compiled block : 184 +Memory allocation - code portion : 48 ------------------------------------------------------------------ 0 44 Bra 3 [+\-\p{Nd}]++ @@ -515,7 +558,8 @@ Memory allocation (code space): 48 ------------------------------------------------------------------ /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/i,utf -Memory allocation (code space): 25 +Memory allocation - compiled block : 161 +Memory allocation - code portion : 25 ------------------------------------------------------------------ 0 21 Bra 3 /i A\x{391}\x{10427}\x{ff3a}\x{1fb0} @@ -524,7 +568,8 @@ Memory allocation (code space): 25 ------------------------------------------------------------------ /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/utf -Memory allocation (code space): 25 +Memory allocation - compiled block : 161 +Memory allocation - code portion : 25 ------------------------------------------------------------------ 0 21 Bra 3 A\x{391}\x{10427}\x{ff3a}\x{1fb0} @@ -533,7 +578,8 @@ Memory allocation (code space): 25 ------------------------------------------------------------------ /[\x{105}-\x{109}]/i,utf -Memory allocation (code space): 17 +Memory allocation - compiled block : 153 +Memory allocation - code portion : 17 ------------------------------------------------------------------ 0 13 Bra 3 [\x{104}-\x{109}] @@ -542,7 +588,8 @@ Memory allocation (code space): 17 ------------------------------------------------------------------ /( ( (?(1)0|) )* )/x -Memory allocation (code space): 38 +Memory allocation - compiled block : 174 +Memory allocation - code portion : 38 ------------------------------------------------------------------ 0 34 Bra 3 28 CBra 1 @@ -560,7 +607,8 @@ Memory allocation (code space): 38 ------------------------------------------------------------------ /( (?(1)0|)* )/x -Memory allocation (code space): 30 +Memory allocation - compiled block : 166 +Memory allocation - code portion : 30 ------------------------------------------------------------------ 0 26 Bra 3 20 CBra 1 @@ -576,7 +624,8 @@ Memory allocation (code space): 30 ------------------------------------------------------------------ /[a]/ -Memory allocation (code space): 9 +Memory allocation - compiled block : 145 +Memory allocation - code portion : 9 ------------------------------------------------------------------ 0 5 Bra 3 a @@ -585,7 +634,8 @@ Memory allocation (code space): 9 ------------------------------------------------------------------ /[a]/utf -Memory allocation (code space): 9 +Memory allocation - compiled block : 145 +Memory allocation - code portion : 9 ------------------------------------------------------------------ 0 5 Bra 3 a @@ -594,7 +644,8 @@ Memory allocation (code space): 9 ------------------------------------------------------------------ /[\xaa]/ -Memory allocation (code space): 9 +Memory allocation - compiled block : 145 +Memory allocation - code portion : 9 ------------------------------------------------------------------ 0 5 Bra 3 \x{aa} @@ -603,7 +654,8 @@ Memory allocation (code space): 9 ------------------------------------------------------------------ /[\xaa]/utf -Memory allocation (code space): 10 +Memory allocation - compiled block : 146 +Memory allocation - code portion : 10 ------------------------------------------------------------------ 0 6 Bra 3 \x{aa} @@ -612,7 +664,8 @@ Memory allocation (code space): 10 ------------------------------------------------------------------ /[^a]/ -Memory allocation (code space): 9 +Memory allocation - compiled block : 145 +Memory allocation - code portion : 9 ------------------------------------------------------------------ 0 5 Bra 3 [^a] @@ -621,7 +674,8 @@ Memory allocation (code space): 9 ------------------------------------------------------------------ /[^a]/utf -Memory allocation (code space): 9 +Memory allocation - compiled block : 145 +Memory allocation - code portion : 9 ------------------------------------------------------------------ 0 5 Bra 3 [^a] @@ -630,7 +684,8 @@ Memory allocation (code space): 9 ------------------------------------------------------------------ /[^\xaa]/ -Memory allocation (code space): 9 +Memory allocation - compiled block : 145 +Memory allocation - code portion : 9 ------------------------------------------------------------------ 0 5 Bra 3 [^\x{aa}] @@ -639,7 +694,8 @@ Memory allocation (code space): 9 ------------------------------------------------------------------ /[^\xaa]/utf -Memory allocation (code space): 10 +Memory allocation - compiled block : 146 +Memory allocation - code portion : 10 ------------------------------------------------------------------ 0 6 Bra 3 [^\x{aa}] |