From 08e3107cbe3ffecc4f9da363adc23a012f84bd11 Mon Sep 17 00:00:00 2001 From: "Philip.Hazel" Date: Mon, 3 Nov 2014 17:13:00 +0000 Subject: [PATCH] Changed jit_stack_alloc to jit_stack_create. --- Makefile.am | 4 +- RunGrepTest | 6 +- doc/html/README.txt | 9 +- doc/html/index.html | 8 +- doc/html/pcre2_get_startchar.html | 8 +- doc/html/pcre2_jit_free_unused_memory.html | 5 +- doc/html/pcre2_jit_match.html | 2 +- doc/html/pcre2_jit_stack_assign.html | 4 +- ...alloc.html => pcre2_jit_stack_create.html} | 6 +- doc/html/pcre2_jit_stack_free.html | 2 +- .../pcre2_substring_number_from_name.html | 11 +- doc/html/pcre2api.html | 22 +- doc/html/pcre2jit.html | 69 +-- doc/html/pcre2test.html | 77 +++- doc/index.html.src | 6 +- doc/pcre2.txt | 347 ++++++++------- doc/pcre2_jit_free_unused_memory.3 | 6 +- doc/pcre2_jit_match.3 | 4 +- doc/pcre2_jit_stack_assign.3 | 6 +- ...stack_alloc.3 => pcre2_jit_stack_create.3} | 4 +- doc/pcre2_jit_stack_free.3 | 2 +- doc/pcre2_substring_number_from_name.3 | 2 +- doc/pcre2api.3 | 14 +- doc/pcre2jit.3 | 16 +- doc/pcre2test.1 | 30 +- doc/pcre2test.txt | 412 ++++++++++-------- perltest.sh | 24 +- src/pcre2.h.generic | 231 +++++----- src/pcre2.h.in | 4 +- src/pcre2_compile.c | 6 +- src/pcre2_error.c | 2 +- src/pcre2_jit_misc.c | 2 +- src/pcre2_jit_test.c | 6 +- src/pcre2_substring.c | 2 +- src/pcre2grep.c | 2 +- src/pcre2test.c | 52 +-- testdata/testoutput16 | 5 + 37 files changed, 753 insertions(+), 665 deletions(-) rename doc/html/{pcre2_jit_stack_alloc.html => pcre2_jit_stack_create.html} (90%) rename doc/{pcre2_jit_stack_alloc.3 => pcre2_jit_stack_create.3} (88%) diff --git a/Makefile.am b/Makefile.am index 71798e0..4a2fa2e 100644 --- a/Makefile.am +++ b/Makefile.am @@ -42,8 +42,8 @@ dist_html_DATA = \ doc/html/pcre2_jit_compile.html \ doc/html/pcre2_jit_free_unused_memory.html \ doc/html/pcre2_jit_match.html \ - doc/html/pcre2_jit_stack_alloc.html \ doc/html/pcre2_jit_stack_assign.html \ + doc/html/pcre2_jit_stack_create.html \ doc/html/pcre2_jit_stack_free.html \ doc/html/pcre2_maketables.html \ doc/html/pcre2_match.html \ @@ -113,8 +113,8 @@ dist_man_MANS = \ doc/pcre2_jit_compile.3 \ doc/pcre2_jit_free_unused_memory.3 \ doc/pcre2_jit_match.3 \ - doc/pcre2_jit_stack_alloc.3 \ doc/pcre2_jit_stack_assign.3 \ + doc/pcre2_jit_stack_create.3 \ doc/pcre2_jit_stack_free.3 \ doc/pcre2_maketables.3 \ doc/pcre2_match.3 \ diff --git a/RunGrepTest b/RunGrepTest index 719311f..6d26d87 100755 --- a/RunGrepTest +++ b/RunGrepTest @@ -82,8 +82,8 @@ checkspecial() exit 1 fi } - -# ------ Normal tests ------ + +# ------ Normal tests ------ echo "Testing pcre2grep main features" @@ -585,7 +585,7 @@ $cf $srcdir/testdata/grepoutputN testtrygrep if [ $? != 0 ] ; then exit 1; fi -# Finally, some tests to exercise code that is not tested above, just to be +# Finally, some tests to exercise code that is not tested above, just to be # sure that it runs OK. Doing this improves the coverage statistics. The output # is not checked. diff --git a/doc/html/README.txt b/doc/html/README.txt index d765b21..293c00a 100644 --- a/doc/html/README.txt +++ b/doc/html/README.txt @@ -574,7 +574,7 @@ a list of tests. The first two tests can always be run, as they expect only plain text strings (not UTF) and make no use of Unicode properties. The first test file can be fed -directly into the perltest.pl script to check that Perl gives the same results. +directly into the perltest.sh script to check that Perl gives the same results. The only difference you should see is in the first few lines, where the Perl version is given instead of the PCRE2 version. The second set of tests check auxiliary functions, error detection, and run-time flags that are specific to @@ -609,7 +609,7 @@ of the French locale have been encountered. The test passes if its output matches any one of them. The fourth and fifth tests check UTF and Unicode property support, the fourth -being compatible with the perltest.pl script, and the fifth checking +being compatible with the perltest.sh script, and the fifth checking PCRE2-specific things. The sixth and seventh tests check the pcre2_dfa_match() alternative matching @@ -781,7 +781,6 @@ The distribution should contain the files listed below. doc/html/* HTML documentation doc/pcre2.txt plain text version of the man pages doc/pcre2test.txt plain text documentation of test program - doc/perltest.txt plain text documentation of Perl test program install-sh a shell script for installing files libpcre2-8.pc.in template for libpcre2-8.pc for pkg-config libpcre2-16.pc.in template for libpcre2-16.pc for pkg-config @@ -791,7 +790,7 @@ The distribution should contain the files listed below. missing ) common stub for a few missing GNU programs while ) installing, generated by automake mkinstalldirs script for making install directories - perltest.pl Perl test program + perltest.sh Script for running a Perl test program pcre2-config.in source of script which retains PCRE2 information pcre2_jit_test.c test program for the JIT compiler testdata/testinput* test data for main library tests @@ -829,4 +828,4 @@ The distribution should contain the files listed below. Philip Hazel Email local part: ph10 Email domain: cam.ac.uk -Last updated: 27 October 2014 +Last updated: 25 October 2014 diff --git a/doc/html/index.html b/doc/html/index.html index 865c895..13eeef6 100644 --- a/doc/html/index.html +++ b/doc/html/index.html @@ -140,12 +140,12 @@ in the library. pcre2_jit_match   Fast path interface to JIT matching -pcre2_jit_stack_alloc -   Create a stack for JIT matching - pcre2_jit_stack_assign   Assign stack for JIT matching +pcre2_jit_stack_create +   Create a stack for JIT matching + pcre2_jit_stack_free   Free a JIT matching stack @@ -162,7 +162,7 @@ in the library. pcre2_match_context_create   Create a match context -pcre2_match_contest_free +pcre2_match_context_free   Free a match context pcre2_match_data_create diff --git a/doc/html/pcre2_get_startchar.html b/doc/html/pcre2_get_startchar.html index c9d0dfa..d2c28b2 100644 --- a/doc/html/pcre2_get_startchar.html +++ b/doc/html/pcre2_get_startchar.html @@ -27,9 +27,11 @@ DESCRIPTION

After a successful call of pcre2_match() that was passed the match block that is this function's argument, this function returns the code unit offset of -the character at which the successful match started. This can be different to -the value of ovector[0] if the pattern contains the \K escape sequence. -Note, however, that \K has no effect for a partial match. +the character at which the successful match started. For a non-partial match, +this can be different to the value of ovector[0] if the pattern contains +the \K escape sequence. After a partial match, however, this value is always +the same as ovector[0] because \K does not affect the result of a +partial match.

There is a complete description of the PCRE2 native API in the diff --git a/doc/html/pcre2_jit_free_unused_memory.html b/doc/html/pcre2_jit_free_unused_memory.html index cdd5b39..8b59b8e 100644 --- a/doc/html/pcre2_jit_free_unused_memory.html +++ b/doc/html/pcre2_jit_free_unused_memory.html @@ -27,7 +27,10 @@ DESCRIPTION

This function frees unused JIT executable memory. The argument is a general context, for custom memory management, or NULL for standard memory management. -FIXME: more detail needed. +JIT memory allocation retains some memory in order to improve future JIT +compilation speed. In low memory conditions, +\fBpcre2_jit_free_unused_memory()\fB can be used to cause this memory to be +freed.

There is a complete description of the PCRE2 native API in the diff --git a/doc/html/pcre2_jit_match.html b/doc/html/pcre2_jit_match.html index d8658f1..ab58854 100644 --- a/doc/html/pcre2_jit_match.html +++ b/doc/html/pcre2_jit_match.html @@ -36,7 +36,7 @@ Its arguments are exactly the same as for pcre2_match() plus one additional argument that must either point to a JIT stack or be NULL. In the latter case, if a callback function has been set up by -pcre2_jit_stack_alloc(), it is called. Otherwise the system stack is +pcre2_jit_stack_create(), it is called. Otherwise the system stack is used.

diff --git a/doc/html/pcre2_jit_stack_assign.html b/doc/html/pcre2_jit_stack_assign.html index cbe9340..95e81b3 100644 --- a/doc/html/pcre2_jit_stack_assign.html +++ b/doc/html/pcre2_jit_stack_assign.html @@ -42,13 +42,13 @@ block on the machine stack is used.

If callback is NULL and callback_data is not NULL, callback_data must be a valid JIT stack, the result of calling -pcre2_jit_stack_alloc(). +pcre2_jit_stack_create().

If callback not NULL, it is called with callback_data as an argument at the start of matching, in order to set up a JIT stack. If the result is NULL, the internal 32K stack is used; otherwise the return value must -be a valid JIT stack, the result of calling pcre2_jit_stack_alloc(). +be a valid JIT stack, the result of calling pcre2_jit_stack_create().

You may safely assign the same JIT stack to multiple patterns, as long as they diff --git a/doc/html/pcre2_jit_stack_alloc.html b/doc/html/pcre2_jit_stack_create.html similarity index 90% rename from doc/html/pcre2_jit_stack_alloc.html rename to doc/html/pcre2_jit_stack_create.html index d630d49..cf31af6 100644 --- a/doc/html/pcre2_jit_stack_alloc.html +++ b/doc/html/pcre2_jit_stack_create.html @@ -1,9 +1,9 @@ -pcre2_jit_stack_alloc specification +pcre2_jit_stack_create specification -

pcre2_jit_stack_alloc man page

+

pcre2_jit_stack_create man page

Return to the PCRE2 index page.

@@ -19,7 +19,7 @@ SYNOPSIS #include <pcre2.h>

-pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *gcontext, +pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *gcontext, PCRE2_SIZE startsize, PCRE2_SIZE maxsize);


diff --git a/doc/html/pcre2_jit_stack_free.html b/doc/html/pcre2_jit_stack_free.html index c6b488d..21ac276 100644 --- a/doc/html/pcre2_jit_stack_free.html +++ b/doc/html/pcre2_jit_stack_free.html @@ -26,7 +26,7 @@ DESCRIPTION

This function is used to free a JIT stack that was created by -pcre2_jit_stack_alloc() when it is no longer needed. For more details, +pcre2_jit_stack_create() when it is no longer needed. For more details, see the pcre2jit page. diff --git a/doc/html/pcre2_substring_number_from_name.html b/doc/html/pcre2_substring_number_from_name.html index 92ac91d..160fbda 100644 --- a/doc/html/pcre2_substring_number_from_name.html +++ b/doc/html/pcre2_substring_number_from_name.html @@ -27,16 +27,17 @@ DESCRIPTION

This convenience function finds the number of a named substring capturing -parenthesis in a compiled pattern. Its arguments are: +parenthesis in a compiled pattern, provided that it is a unique name. The +function arguments are: 

   code    Compiled regular expression
   name    Name whose number is required
The yield of the function is the number of the parenthesis if the name is -found, or PCRE2_ERROR_NOSUBSTRING otherwise. When duplicate names are allowed -(PCRE2_DUPNAMES is set), it is not defined which of the numbers is returned. -You can obtain the complete list by calling -pcre2_substring_nametable_scan(). +found, or PCRE2_ERROR_NOSUBSTRING if it is not found. When duplicate names are +allowed (PCRE2_DUPNAMES is set), if the name is not unique, +PCRE2_ERROR_NOUNIQUESUBSTRING is returned. You can obtain the list of numbers +with the same name by calling pcre2_substring_nametable_scan().

There is a complete description of the PCRE2 native API in the diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index 016fd4a..4545948 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -236,7 +236,7 @@ document for an overview of all the PCRE2 documentation. void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);

-pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *gcontext, +pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *gcontext, PCRE2_SIZE startsize, PCRE2_SIZE maxsize);

@@ -363,7 +363,7 @@ support is not available.

More complicated programs might need to make use of the specialist functions -pcre2_jit_stack_alloc(), pcre2_jit_stack_free(), and +pcre2_jit_stack_create(), pcre2_jit_stack_free(), and pcre2_jit_stack_assign() in order to control the JIT code's memory usage.

@@ -1272,7 +1272,7 @@ textual error message from any error code. void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);

-pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *gcontext, +pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *gcontext, PCRE2_SIZE startsize, PCRE2_SIZE maxsize);

@@ -2050,10 +2050,11 @@ Otherwise NULL is returned. A (*MARK) name may be available after a failed match or a partial match, as well as after a successful one.

-The offset of the character at which the successful match started is -returned by pcre2_get_startchar(). This can be different to the value of -ovector[0] if the pattern contains the \K escape sequence. Note, -however, that \K has no effect for a partial match. +The code unit offset of the character at which a successful match started is +returned by pcre2_get_startchar(). For a non-partial match, this can be +different to the value of ovector[0] if the pattern contains the \K +escape sequence. After a partial match, however, this value is always the same +as ovector[0] because \K does not affect the result of a partial match.


Error return values from pcre2_match() @@ -2302,8 +2303,9 @@ the number of the subpattern called "xxx" is 2. If the name is known to be unique (PCRE2_DUPNAMES was not set), you can find the number from the name by calling pcre2_substring_number_from_name(). The first argument is the compiled pattern, and the second is the name. The yield of the function is the -subpattern number, or PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that -name. +subpattern number, PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that +name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of +that name.

Given the number, you can extract the substring directly, or use one of the @@ -2577,7 +2579,7 @@ Cambridge CB2 3QH, England.


REVISION

-Last updated: 16 October 2014 +Last updated: 03 November 2014
Copyright © 1997-2014 University of Cambridge.
diff --git a/doc/html/pcre2jit.html b/doc/html/pcre2jit.html index 0699990..fcd7cb6 100644 --- a/doc/html/pcre2jit.html +++ b/doc/html/pcre2jit.html @@ -20,17 +20,15 @@ please consult the man page, in case the conversion went wrong.

  • RETURN VALUES FROM JIT MATCHING
  • CONTROLLING THE JIT STACK
  • JIT STACK FAQ -
  • EXAMPLE CODE -
  • JIT FAST PATH API -
  • SEE ALSO -
  • AUTHOR -
  • REVISION +
  • FREEING JIT SPECULATIVE MEMORY +
  • EXAMPLE CODE +
  • JIT FAST PATH API +
  • SEE ALSO +
  • AUTHOR +
  • REVISION
    PCRE2 JUST-IN-TIME COMPILER SUPPORT

    -FIXME: This needs checking over once JIT support is implemented. -

    -

    Just-in-time compiling is a heavyweight optimization that can greatly speed up pattern matching. However, it comes at the cost of extra processing before the match is performed. Therefore, it is of most benefit when the same pattern is @@ -79,9 +77,12 @@ second is a set of option bits, which must include at least one of PCRE2_JIT_COMPLETE, PCRE2_JIT_PARTIAL_HARD, or PCRE2_JIT_PARTIAL_SOFT.

    -The returned value from pcre2_jit_compile() is zero on success, or a -negative error code. In particular, PCRE2_ERROR_JIT_BADOPTION is returned if -JIT is not supported or if an unknown options bit is set. +If JIT support is not available, a call to pcre2_jit_comple() does +nothing and returns PCRE2_ERROR_JIT_BADOPTION. Otherwise, the compiled pattern +is passed to the JIT compiler, which turns it into machine code that executes +much faster than the normal interpretive code, but yields exactly the same +results. The returned value from pcre2_jit_compile() is zero on success, +or a negative error code.

    PCRE2_JIT_COMPLETE requests the JIT compiler to generate code for complete @@ -100,12 +101,6 @@ described in the section entitled below.

    -If JIT support is not available, a call to pcre2_jit_comple() does -nothing and returns FIXME. Otherwise, the compiled pattern is passed to the JIT -compiler, which turns it into machine code that executes much faster than the -normal interpretive code, but yields exactly the same results. -

    -

    There are some pcre2_match() options that are not supported by JIT, and there are also some pattern items that JIT cannot handle. Details are given below. In both cases, matching automatically falls back to the interpretive @@ -166,7 +161,7 @@ about the use of JIT stacks in the section entitled below.

    -The pcre2_jit_stack_alloc() function creates a JIT stack. Its arguments +The pcre2_jit_stack_create() function creates a JIT stack. Its arguments are a general context (for memory allocation functions, or NULL for standard memory allocation), a starting size and a maximum size, and it returns a pointer to an opaque structure of type pcre2_jit_stack, or NULL if there @@ -195,14 +190,14 @@ the other two options: on the machine stack is used. (2) If callback is NULL and data is not NULL, data must be - a valid JIT stack, the result of calling pcre2_jit_stack_alloc(). + a valid JIT stack, the result of calling pcre2_jit_stack_create(). (3) If callback is not NULL, it must point to a function that is called with data as an argument at the start of matching, in order to set up a JIT stack. If the return from the callback function is NULL, the internal 32K stack is used; otherwise the return value must be a valid JIT stack, the result of calling - pcre2_jit_stack_alloc(). + pcre2_jit_stack_create(). A callback function is obeyed whenever JIT code is about to be run; it is not obeyed when pcre2_match() is called with options that are incompatible @@ -231,7 +226,7 @@ This is a suggestion for how a multithreaded program that needs to set up non-default JIT stacks might operate: 

       During thread initalization
-    thread_local_var = pcre2_jit_stack_alloc(...)
+    thread_local_var = pcre2_jit_stack_create(...)
 
   During thread exit
     pcre2_jit_stack_free(thread_local_var)
@@ -323,7 +318,19 @@ stack handling?
 No, thanks to Windows. If POSIX threads were used everywhere, we could throw
 out this complicated API.
 
    
-
    EXAMPLE CODE
    
+
    FREEING JIT SPECULATIVE MEMORY
    
+
    
+void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);
+
    
+
    
+The JIT executable allocator does not free all memory when it is possible.
+It expects new allocations, and keeps some free memory around to improve
+allocation speed. However, in low memory conditions, it might be better to free
+all possible memory. You can cause this to happen by calling
+pcre2_jit_free_unused_memory(). Its argument is a general context, for custom
+memory management, or NULL for standard memory management.
+
    
+
    EXAMPLE CODE
    
 
    
 This is a single-threaded example that specifies a JIT stack without using a
 callback.
@@ -338,7 +345,7 @@ callback.
   /* Check for errors */
   rc = pcre2_jit_compile(re, PCRE2_JIT_COMPLETE);
   /* Check for errors */
-  jit_stack = pcre2_jit_stack_alloc(NULL, 32*1024, 512*1024);
+  jit_stack = pcre2_jit_stack_create(NULL, 32*1024, 512*1024);
   /* Check for error (NULL) */
   pcre2_jit_stack_assign(re, NULL, jit_stack);
   match_data = pcre2_match_data_create(re, 10);
@@ -349,7 +356,7 @@ callback.

    -
    JIT FAST PATH API
    +
    JIT FAST PATH API

    Because the API described above falls back to interpreted matching when JIT is not available, it is convenient for programs that are written for general use @@ -364,11 +371,11 @@ processed by pcre2_jit_compile()). The fast path function is called pcre2_jit_match(), and it takes exactly the same arguments as pcre2_match(), plus one additional argument that must either point to a JIT stack or be NULL. In the latter case, if a callback -function has been set up by pcre2_jit_stack_alloc(), it is called. +function has been set up by pcre2_jit_stack_assign(), it is called. Otherwise the system stack is used. The return values are the same as for pcre2_match(), plus PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial -or complete) is requested that was not compiled. Unsupported option bits are -ignored. +or complete) is requested that was not compiled. Unsupported option bits (for +example, PCRE2_ANCHORED) are ignored.

    When you call pcre2_match(), as well as testing for invalid options, a @@ -382,11 +389,11 @@ invalid data is passed, the result is undefined. Bypassing the sanity checks and the pcre2_match() wrapping can give speedups of more than 10%.

    -
    SEE ALSO
    +
    SEE ALSO

    pcre2api(3)

    -
    AUTHOR
    +
    AUTHOR

    Philip Hazel (FAQ by Zoltan Herczeg)
    @@ -395,9 +402,9 @@ University Computing Service Cambridge CB2 3QH, England.

    -
    REVISION
    +
    REVISION

    -Last updated: 21 October 2014 +Last updated: 03 November 2014
    Copyright © 1997-2014 University of Cambridge.
    diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html index 0609a41..527a609 100644 --- a/doc/html/pcre2test.html +++ b/doc/html/pcre2test.html @@ -223,10 +223,12 @@ Output the PCRE2 version number and then exit.
    DESCRIPTION

    If pcre2test is given two filename arguments, it reads from the first and -writes to the second. If it is given only one filename argument, it reads from +writes to the second. If the first name is "-", input is taken from the +standard input. If pcre2test is given only one argument, it reads from that file and writes to stdout. Otherwise, it reads from stdin and writes to -stdout, and prompts for each line of input, using "re>" to prompt for regular -expression patterns, and "data>" to prompt for subject lines. +stdout. When the input is a terminal, it prompts for each line of input, using +"re>" to prompt for regular expression patterns, and "data>" to prompt for +subject lines.

    When pcre2test is built, a configuration option can specify that it @@ -476,6 +478,7 @@ about the pattern: /I info show info about compiled pattern hex pattern is coded in hexadecimal jit[=<number>] use JIT + jitfast use JIT fast path jitverify verify JIT use locale=<name> use this locale memory show memory used @@ -573,6 +576,13 @@ documentation. See also the jitstack modifier below for a way of setting the size of the JIT stack.

    +If the jitfast modifier is specified, matching is done using the JIT +"fast path" interface (\fBpcre2_jit_match()), which skips some of the sanity +checks that are done by pcre2_match(), and of course does not work when +JIT is not supported. If jitfast is specified without jit, jit=7 is +assumed. +

    +

    If the jitverify modifier is specified, information about the compiled pattern shows whether JIT compilation was or was not successful. If jitverify is specified without jit, jit=7 is assumed. If JIT @@ -612,6 +622,9 @@ Limiting nested parentheses

    The parens_nest_limit modifier sets a limit on the depth of nested parentheses in a pattern. Breaching the limit causes a compilation error. +The default for the library is set when PCRE2 is built, but pcre2test +sets its own default of 220, which is required for running the standard test +suite.


    Using the POSIX wrapper API @@ -675,12 +688,13 @@ However, they may be included in a pattern's modifier list, in which case they are applied to every subject line that is processed with that pattern. They do not affect the compilation process. 
    -      aftertext                 show text after match
-      allaftertext              show text after captures
-      allcaptures               show all captures
-      allusedtext               show all consulted text
-  /g  global                    global matching
-      mark                      show mark values
+      aftertext           show text after match
+      allaftertext        show text after captures
+      allcaptures         show all captures
+      allusedtext         show all consulted text
+  /g  global              global matching
+      mark                show mark values
+      startchar           show starting character when relevant
    These modifiers may not appear in a #pattern command. If you want them as defaults, set them in a #subject command. @@ -751,6 +765,7 @@ pattern. offset=<n> set starting offset ovector=<n> set size of output vector recursion_limit=<n> set a recursion limit + startchar show startchar when relevant The effects of these modifiers are described in the following sections. FIXME: Give more examples. @@ -777,14 +792,30 @@ there is a lookbehind at the start of a match, or a lookahead at the end, or if of the actual match are indicated in the output by '<' or '>' characters underneath them. Here is an example: 
    -  /(?<=pqr)abc(?=xyz)/
-      123pqrabcxyz456\=allusedtext
+    re> /(?<=pqr)abc(?=xyz)/
+  data> 123pqrabcxyz456\=allusedtext
    0: pqrabcxyz
       <<<   >>>
    This shows that the matched string is "abc", with the preceding and following strings "pqr" and "xyz" also consulted during the match.

    +

    +The startchar modifier requests that the starting character for the match +be indicated, if it is different to the start of the matched string. The only +time when this occurs is when \K has been processed as part of the match. In +this situation, the output for the matched string is displayed from the +starting character instead of from the match point, with circumflex characters +under the earlier characters. For example: +

    +    re> /abc\Kxyz/
+  data> abcxyz\=startchar
+   0: abcxyz
+      ^^^
+
    +Unlike allusedtext, the startchar modifier can be used with JIT. +However, these two modifiers are mutually exclusive. +


    Showing the value of all capture groups
    @@ -870,8 +901,9 @@ 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. Providing a stack that is larger than the -default 32K is necessary only for very complicated patterns. +optimization is not being used. The value is a number of kilobytes. Providing a +stack that is larger than the default 32K is necessary only for very +complicated patterns.


    Setting match and recursion limits @@ -939,11 +971,13 @@ appears, though of course it can also be used to set a default in a available for storing matching information. The default is 15.

    -At least one pair of offsets is always created by -pcre2_match_data_create(), for matching with PCRE2's native API, so a -value of 0 is the same as 1. However a value of 0 is useful when testing the -POSIX API because it causes regexec() to be called with a NULL capture -vector. +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_create_from_pattern to be called, in order to create a +match block of exactly the right size for the pattern. (It is not possible to +create a match block with a zero-length ovector; there is always one pair of +offsets.)


    THE ALTERNATIVE MATCHING FUNCTION

    @@ -1175,10 +1209,9 @@ characters.


    SEE ALSO

    -pcre2(3), pcre16(3), pcre32(3), pcre2api(3), -pcre2callout(3), +pcre2(3), pcre2api(3), pcre2callout(3), pcre2jit, pcre2matching(3), pcre2partial(d), -pcre2pattern(3), pcre2precompile(3). +pcre2pattern(3).


    AUTHOR

    @@ -1191,7 +1224,7 @@ Cambridge CB2 3QH, England.


    REVISION

    -Last updated: 11 October 2014 +Last updated: 02 November 2014
    Copyright © 1997-2014 University of Cambridge.
    diff --git a/doc/index.html.src b/doc/index.html.src index 738199a..355cf34 100644 --- a/doc/index.html.src +++ b/doc/index.html.src @@ -140,12 +140,12 @@ in the library. pcre2_jit_match   Fast path interface to JIT matching -pcre2_jit_stack_alloc -   Create a stack for JIT matching - pcre2_jit_stack_assign   Assign stack for JIT matching +pcre2_jit_stack_create +   Create a stack for JIT matching + pcre2_jit_stack_free   Free a JIT matching stack diff --git a/doc/pcre2.txt b/doc/pcre2.txt index 806e3ab..796bfcc 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -324,7 +324,7 @@ PCRE2 NATIVE API JIT FUNCTIONS void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext); - pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *gcontext, + pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *gcontext, PCRE2_SIZE startsize, PCRE2_SIZE maxsize); void pcre2_jit_stack_assign(const pcre2_code *code, @@ -437,7 +437,7 @@ PCRE2 API OVERVIEW support is not available. More complicated programs might need to make use of the specialist - functions pcre2_jit_stack_alloc(), pcre2_jit_stack_free(), and + functions pcre2_jit_stack_create(), pcre2_jit_stack_free(), and pcre2_jit_stack_assign() in order to control the JIT code's memory usage. @@ -1303,7 +1303,7 @@ JUST-IN-TIME (JIT) COMPILATION void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext); - pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *gcontext, + pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *gcontext, PCRE2_SIZE startsize, PCRE2_SIZE maxsize); void pcre2_jit_stack_assign(const pcre2_code *code, @@ -2034,10 +2034,12 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS after a failed match or a partial match, as well as after a successful one. - The offset of the character at which the successful match started is - returned by pcre2_get_startchar(). This can be different to the value - of ovector[0] if the pattern contains the \K escape sequence. Note, - however, that \K has no effect for a partial match. + The code unit offset of the character at which a successful match + started is returned by pcre2_get_startchar(). For a non-partial match, + this can be different to the value of ovector[0] if the pattern con- + tains the \K escape sequence. After a partial match, however, this + value is always the same as ovector[0] because \K does not affect the + result of a partial match. Error return values from pcre2_match() @@ -2266,23 +2268,24 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME be unique (PCRE2_DUPNAMES was not set), you can find the number from the name by calling pcre2_substring_number_from_name(). The first argu- ment is the compiled pattern, and the second is the name. The yield of - the function is the subpattern number, or PCRE2_ERROR_NOSUBSTRING if - there is no subpattern of that name. + the function is the subpattern number, PCRE2_ERROR_NOSUBSTRING if there + is no subpattern of that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if + there is more than one subpattern of that name. Given the number, you can extract the substring directly, or use one of the functions described in the previous section. For convenience, there - are also "byname" functions that correspond to the "bynumber" func- - tions, the only difference being that the second argument is a name - instead of a number. However, if PCRE2_DUPNAMES is set and there are - duplicate names, the behaviour may not be what you want (see the next + are also "byname" functions that correspond to the "bynumber" func- + tions, the only difference being that the second argument is a name + instead of a number. However, if PCRE2_DUPNAMES is set and there are + duplicate names, the behaviour may not be what you want (see the next section). Warning: If the pattern uses the (?| feature to set up multiple subpat- - terns with the same number, as described in the section on duplicate - subpattern numbers in the pcre2pattern page, you cannot use names to - distinguish the different subpatterns, because names are not included - in the compiled code. The matching process uses only numbers. For this - reason, the use of different names for subpatterns of the same number + terns with the same number, as described in the section on duplicate + subpattern numbers in the pcre2pattern page, you cannot use names to + distinguish the different subpatterns, because names are not included + in the compiled code. The matching process uses only numbers. For this + reason, the use of different names for subpatterns of the same number causes an error at compile time. @@ -2291,54 +2294,54 @@ DUPLICATE SUBPATTERN NAMES int pcre2_substring_nametable_scan(const pcre2_code *code, PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); - When a pattern is compiled with the PCRE2_DUPNAMES option, names for - subpatterns are not required to be unique. Duplicate names are always - allowed for subpatterns with the same number, created by using the (?| - feature. Indeed, if such subpatterns are named, they are required to + When a pattern is compiled with the PCRE2_DUPNAMES option, names for + subpatterns are not required to be unique. Duplicate names are always + allowed for subpatterns with the same number, created by using the (?| + feature. Indeed, if such subpatterns are named, they are required to use the same names. Normally, patterns with duplicate names are such that in any one match, - only one of the named subpatterns participates. An example is shown in + only one of the named subpatterns participates. An example is shown in the pcre2pattern documentation. - When duplicates are present, pcre2_substring_copy_byname() and - pcre2_substring_get_byname() return the first substring corresponding + When duplicates are present, pcre2_substring_copy_byname() and + pcre2_substring_get_byname() return the first substring corresponding to the given name that is set. If none are set, PCRE2_ERROR_NOSUBSTRING - is returned. The pcre2_substring_number_from_name() function returns - one of the numbers that are associated with the name, but it is not + is returned. The pcre2_substring_number_from_name() function returns + one of the numbers that are associated with the name, but it is not defined which it is. - If you want to get full details of all captured substrings for a given - name, you must use the pcre2_substring_nametable_scan() function. The - first argument is the compiled pattern, and the second is the name. If - the third and fourth arguments are NULL, the function returns a group + If you want to get full details of all captured substrings for a given + name, you must use the pcre2_substring_nametable_scan() function. The + first argument is the compiled pattern, and the second is the name. If + the third and fourth arguments are NULL, the function returns a group number (it is not defined which). Otherwise, the third and fourth argu- - ments must be pointers to variables that are updated by the function. + ments must be pointers to variables that are updated by the function. After it has run, they point to the first and last entries in the name- to-number table for the given name, and the function returns the length - of each entry. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if + of each entry. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name. The format of the name table is described above in the section entitled - Information about a pattern above. Given all the relevant entries for + Information about a pattern above. Given all the relevant entries for the name, you can extract each of their numbers, and hence the captured data. FINDING ALL POSSIBLE MATCHES - The traditional matching function uses a similar algorithm to Perl, + The traditional matching function uses a similar algorithm to Perl, which stops when it finds the first match, starting at a given point in - the subject. If you want to find all possible matches, or the longest - possible match at a given position, consider using the alternative - matching function (see below) instead. If you cannot use the alterna- + the subject. If you want to find all possible matches, or the longest + possible match at a given position, consider using the alternative + matching function (see below) instead. If you cannot use the alterna- tive function, you can kludge it up by making use of the callout facil- ity, which is described in the pcre2callout documentation. What you have to do is to insert a callout right at the end of the pat- - tern. When your callout function is called, extract and save the cur- - rent matched substring. Then return 1, which forces pcre2_match() to - backtrack and try other alternatives. Ultimately, when it runs out of + tern. When your callout function is called, extract and save the cur- + rent matched substring. Then return 1, which forces pcre2_match() to + backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre2_match() will yield PCRE2_ERROR_NOMATCH. @@ -2350,26 +2353,26 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION pcre2_match_context *mcontext, int *workspace, PCRE2_SIZE wscount); - The function pcre2_dfa_match() is called to match a subject string - against a compiled pattern, using a matching algorithm that scans the - subject string just once, and does not backtrack. This has different - characteristics to the normal algorithm, and is not compatible with - Perl. Some of the features of PCRE2 patterns are not supported. Never- - theless, there are times when this kind of matching can be useful. For - a discussion of the two matching algorithms, and a list of features + The function pcre2_dfa_match() is called to match a subject string + against a compiled pattern, using a matching algorithm that scans the + subject string just once, and does not backtrack. This has different + characteristics to the normal algorithm, and is not compatible with + Perl. Some of the features of PCRE2 patterns are not supported. Never- + theless, there are times when this kind of matching can be useful. For + a discussion of the two matching algorithms, and a list of features that pcre2_dfa_match() does not support, see the pcre2matching documen- tation. - The arguments for the pcre2_dfa_match() function are the same as for + The arguments for the pcre2_dfa_match() function are the same as for pcre2_match(), plus two extras. The ovector within the match data block is used in a different way, and this is described below. The other com- - mon arguments are used in the same way as for pcre2_match(), so their + mon arguments are used in the same way as for pcre2_match(), so their description is not repeated here. - The two additional arguments provide workspace for the function. The - workspace vector should contain at least 20 elements. It is used for + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for keeping track of multiple paths through the pattern tree. More - workspace is needed for patterns and subjects where there are a lot of + workspace is needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre2_dfa_match(): @@ -2389,45 +2392,45 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION Option bits for pcre_dfa_match() - The unused bits of the options argument for pcre2_dfa_match() must be - zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, + The unused bits of the options argument for pcre2_dfa_match() must be + zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, - PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but the last four of - these are exactly the same as for pcre2_match(), so their description + PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but the last four of + these are exactly the same as for pcre2_match(), so their description is not repeated here. PCRE2_PARTIAL_HARD PCRE2_PARTIAL_SOFT - These have the same general effect as they do for pcre2_match(), but - the details are slightly different. When PCRE2_PARTIAL_HARD is set for - pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the + These have the same general effect as they do for pcre2_match(), but + the details are slightly different. When PCRE2_PARTIAL_HARD is set for + pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the subject is reached and there is still at least one matching possibility that requires additional characters. This happens even if some complete - matches have already been found. When PCRE2_PARTIAL_SOFT is set, the - return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL - if the end of the subject is reached, there have been no complete + matches have already been found. When PCRE2_PARTIAL_SOFT is set, the + return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL + if the end of the subject is reached, there have been no complete matches, but there is still at least one matching possibility. The por- - tion of the string that was inspected when the longest partial match + tion of the string that was inspected when the longest partial match was found is set as the first matching string in both cases. There is a - more detailed discussion of partial and multi-segment matching, with + more detailed discussion of partial and multi-segment matching, with examples, in the pcre2partial documentation. PCRE2_DFA_SHORTEST - Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to + Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to stop as soon as it has found one match. Because of the way the alterna- - tive algorithm works, this is necessarily the shortest possible match + tive algorithm works, this is necessarily the shortest possible match at the first possible matching point in the subject string. PCRE2_DFA_RESTART - When pcre2_dfa_match() returns a partial match, it is possible to call + When pcre2_dfa_match() returns a partial match, it is possible to call it again, with additional subject characters, and have it continue with the same match. The PCRE2_DFA_RESTART option requests this action; when - it is set, the workspace and wscount options must reference the same - vector as before because data about the match so far is left in them + it is set, the workspace and wscount options must reference the same + vector as before because data about the match so far is left in them after a partial match. There is more discussion of this facility in the pcre2partial documentation. @@ -2435,8 +2438,8 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION When pcre2_dfa_match() succeeds, it may have matched more than one sub- string in the subject. Note, however, that all the matches from one run - of the function start at the same point in the subject. The shorter - matches are all initial substrings of the longer matches. For example, + of the function start at the same point in the subject. The shorter + matches are all initial substrings of the longer matches. For example, if the pattern <.*> @@ -2451,66 +2454,66 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The offsets of the sub- - strings are returned in the ovector, and can be extracted in the same - way as for pcre2_match(). They are returned in reverse order of - length; that is, the longest matching string is given first. If there - were too many matches to fit into the ovector, the yield of the func- + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The offsets of the sub- + strings are returned in the ovector, and can be extracted in the same + way as for pcre2_match(). They are returned in reverse order of + length; that is, the longest matching string is given first. If there + were too many matches to fit into the ovector, the yield of the func- tion is zero, and the vector is filled with the longest matches. - NOTE: PCRE2's "auto-possessification" optimization usually applies to - character repeats at the end of a pattern (as well as internally). For - example, the pattern "a\d+" is compiled as if it were "a\d++" because - there is no point in backtracking into the repeated digits. For DFA - matching, this means that only one possible match is found. If you - really do want multiple matches in such cases, either use an ungreedy - repeat ("a\d+?") or set the PCRE2_NO_AUTO_POSSESS option when compil- + NOTE: PCRE2's "auto-possessification" optimization usually applies to + character repeats at the end of a pattern (as well as internally). For + example, the pattern "a\d+" is compiled as if it were "a\d++" because + there is no point in backtracking into the repeated digits. For DFA + matching, this means that only one possible match is found. If you + really do want multiple matches in such cases, either use an ungreedy + repeat ("a\d+?") or set the PCRE2_NO_AUTO_POSSESS option when compil- ing. Error returns from pcre2_dfa_match() The pcre2_dfa_match() function returns a negative number when it fails. - Many of the errors are the same as for pcre2_match(), as described + Many of the errors are the same as for pcre2_match(), as described above. There are in addition the following errors that are specific to pcre2_dfa_match(): PCRE2_ERROR_DFA_UITEM - This return is given if pcre2_dfa_match() encounters an item in the + This return is given if pcre2_dfa_match() encounters an item in the pattern that it does not support, for instance, the use of \C or a back reference. PCRE2_ERROR_DFA_UCOND - This return is given if pcre2_dfa_match() encounters a condition item - that uses a back reference for the condition, or a test for recursion + This return is given if pcre2_dfa_match() encounters a condition item + that uses a back reference for the condition, or a test for recursion in a specific group. These are not supported. PCRE2_ERROR_DFA_WSSIZE - This return is given if pcre2_dfa_match() runs out of space in the + This return is given if pcre2_dfa_match() runs out of space in the workspace vector. PCRE2_ERROR_DFA_RECURSE - When a recursive subpattern is processed, the matching function calls + When a recursive subpattern is processed, the matching function calls itself recursively, using private memory for the ovector and workspace. - This error is given if the internal ovector is not large enough. This + This error is given if the internal ovector is not large enough. This should be extremely rare, as a vector of size 1000 is used. PCRE2_ERROR_DFA_BADRESTART - When pcre2_dfa_match() is called with the pcre2_dfa_RESTART option, - some plausibility checks are made on the contents of the workspace, - which should contain data about the previous partial match. If any of + When pcre2_dfa_match() is called with the pcre2_dfa_RESTART option, + some plausibility checks are made on the contents of the workspace, + which should contain data about the previous partial match. If any of these checks fail, this error is given. SEE ALSO - pcre2build(3), pcre2libs(3), pcre2callout(3), pcre2matching(3), - pcre2partial(3), pcre2posix(3), pcre2demo(3), pcre2sample(3), + pcre2build(3), pcre2libs(3), pcre2callout(3), pcre2matching(3), + pcre2partial(3), pcre2posix(3), pcre2demo(3), pcre2sample(3), pcre2stack(3). @@ -2523,7 +2526,7 @@ AUTHOR REVISION - Last updated: 16 October 2014 + Last updated: 03 November 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ @@ -3411,8 +3414,6 @@ NAME PCRE2 JUST-IN-TIME COMPILER SUPPORT - FIXME: This needs checking over once JIT support is implemented. - Just-in-time compiling is a heavyweight optimization that can greatly speed up pattern matching. However, it comes at the cost of extra pro- cessing before the match is performed. Therefore, it is of most benefit @@ -3462,100 +3463,97 @@ SIMPLE USE OF JIT second is a set of option bits, which must include at least one of PCRE2_JIT_COMPLETE, PCRE2_JIT_PARTIAL_HARD, or PCRE2_JIT_PARTIAL_SOFT. - The returned value from pcre2_jit_compile() is zero on success, or a - negative error code. In particular, PCRE2_ERROR_JIT_BADOPTION is - returned if JIT is not supported or if an unknown options bit is set. + If JIT support is not available, a call to pcre2_jit_comple() does + nothing and returns PCRE2_ERROR_JIT_BADOPTION. Otherwise, the compiled + pattern is passed to the JIT compiler, which turns it into machine code + that executes much faster than the normal interpretive code, but yields + exactly the same results. The returned value from pcre2_jit_compile() + is zero on success, or a negative error code. - PCRE2_JIT_COMPLETE requests the JIT compiler to generate code for com- - plete matches. If you want to run partial matches using the PCRE2_PAR- - TIAL_HARD or PCRE2_PARTIAL_SOFT options of pcre2_match(), you should - set one or both of the other options as well as, or instead of + PCRE2_JIT_COMPLETE requests the JIT compiler to generate code for com- + plete matches. If you want to run partial matches using the PCRE2_PAR- + TIAL_HARD or PCRE2_PARTIAL_SOFT options of pcre2_match(), you should + set one or both of the other options as well as, or instead of PCRE2_JIT_COMPLETE. The JIT compiler generates different optimized code - for each of the three modes (normal, soft partial, hard partial). When - pcre2_match() is called, the appropriate code is run if it is avail- + for each of the three modes (normal, soft partial, hard partial). When + pcre2_match() is called, the appropriate code is run if it is avail- able. Otherwise, the pattern is matched using interpretive code. - In some circumstances you may need to call additional functions. These - are described in the section entitled "Controlling the JIT stack" + In some circumstances you may need to call additional functions. These + are described in the section entitled "Controlling the JIT stack" below. - If JIT support is not available, a call to pcre2_jit_comple() does - nothing and returns FIXME. Otherwise, the compiled pattern is passed to - the JIT compiler, which turns it into machine code that executes much - faster than the normal interpretive code, but yields exactly the same - results. - There are some pcre2_match() options that are not supported by JIT, and - there are also some pattern items that JIT cannot handle. Details are - given below. In both cases, matching automatically falls back to the - interpretive code. If you want to know whether JIT was actually used - for a particular match, you should arrange for a JIT callback function - to be set up as described in the section entitled "Controlling the JIT - stack" below, even if you do not need to supply a non-default JIT + there are also some pattern items that JIT cannot handle. Details are + given below. In both cases, matching automatically falls back to the + interpretive code. If you want to know whether JIT was actually used + for a particular match, you should arrange for a JIT callback function + to be set up as described in the section entitled "Controlling the JIT + stack" below, even if you do not need to supply a non-default JIT stack. Such a callback function is called whenever JIT code is about to - be obeyed. If the match-time options are not right for JIT execution, + be obeyed. If the match-time options are not right for JIT execution, the callback function is not obeyed. - If the JIT compiler finds an unsupported item, no JIT data is gener- - ated. You can find out if JIT matching is available after compiling a + If the JIT compiler finds an unsupported item, no JIT data is gener- + ated. You can find out if JIT matching is available after compiling a pattern by calling pcre2_pattern_info() with the PCRE2_INFO_JIT option. - A result of 1 means that JIT compilation was successful. A result of 0 - means that JIT support is not available, or the pattern was not pro- + A result of 1 means that JIT compilation was successful. A result of 0 + means that JIT support is not available, or the pattern was not pro- cessed by pcre2_jit_compile(), or the JIT compiler was not able to han- dle the pattern. UNSUPPORTED OPTIONS AND PATTERN ITEMS - The pcre2_match() options that are supported for JIT matching are - PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, + The pcre2_match() options that are supported for JIT matching are + PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. The PCRE2_ANCHORED option is not supported at match time. - The only unsupported pattern items are \C (match a single data unit) - when running in a UTF mode, and a callout immediately before an asser- + The only unsupported pattern items are \C (match a single data unit) + when running in a UTF mode, and a callout immediately before an asser- tion condition in a conditional group. RETURN VALUES FROM JIT MATCHING When a pattern is matched using JIT matching, the return values are the - same as those given by the interpretive pcre2_match() code, with the - addition of one new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means - that the memory used for the JIT stack was insufficient. See "Control- + same as those given by the interpretive pcre2_match() code, with the + addition of one new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means + that the memory used for the JIT stack was insufficient. See "Control- ling the JIT stack" below for a discussion of JIT stack usage. - The error code PCRE2_ERROR_MATCHLIMIT is returned by the JIT code if - searching a very large pattern tree goes on for too long, as it is in - the same circumstance when JIT is not used, but the details of exactly - what is counted are not the same. The PCRE2_ERROR_RECURSIONLIMIT error + The error code PCRE2_ERROR_MATCHLIMIT is returned by the JIT code if + searching a very large pattern tree goes on for too long, as it is in + the same circumstance when JIT is not used, but the details of exactly + what is counted are not the same. The PCRE2_ERROR_RECURSIONLIMIT error code is never returned when JIT matching is used. CONTROLLING THE JIT STACK When the compiled JIT code runs, it needs a block of memory to use as a - stack. By default, it uses 32K on the machine stack. However, some - large or complicated patterns need more than this. The error - PCRE2_ERROR_JIT_STACKLIMIT is given when there is not enough stack. - Three functions are provided for managing blocks of memory for use as - JIT stacks. There is further discussion about the use of JIT stacks in + stack. By default, it uses 32K on the machine stack. However, some + large or complicated patterns need more than this. The error + PCRE2_ERROR_JIT_STACKLIMIT is given when there is not enough stack. + Three functions are provided for managing blocks of memory for use as + JIT stacks. There is further discussion about the use of JIT stacks in the section entitled "JIT stack FAQ" below. - The pcre2_jit_stack_alloc() function creates a JIT stack. Its arguments - are a general context (for memory allocation functions, or NULL for - standard memory allocation), a starting size and a maximum size, and it - returns a pointer to an opaque structure of type pcre2_jit_stack, or - NULL if there is an error. The pcre2_jit_stack_free() function is used - to free a stack that is no longer needed. (For the technically minded: - the address space is allocated by mmap or VirtualAlloc.) FIXME Is this - right? + The pcre2_jit_stack_create() function creates a JIT stack. Its argu- + ments are a general context (for memory allocation functions, or NULL + for standard memory allocation), a starting size and a maximum size, + and it returns a pointer to an opaque structure of type + pcre2_jit_stack, or NULL if there is an error. The + pcre2_jit_stack_free() function is used to free a stack that is no + longer needed. (For the technically minded: the address space is allo- + cated by mmap or VirtualAlloc.) FIXME Is this right? - JIT uses far less memory for recursion than the interpretive code, and - a maximum stack size of 512K to 1M should be more than enough for any + JIT uses far less memory for recursion than the interpretive code, and + a maximum stack size of 512K to 1M should be more than enough for any pattern. - The pcre2_jit_stack_assign() function specifies which stack JIT code + The pcre2_jit_stack_assign() function specifies which stack JIT code should use. Its arguments are as follows: pcre2_code *code @@ -3563,21 +3561,22 @@ CONTROLLING THE JIT STACK void *data The code argument is a pointer to a compiled pattern, after it has been - processed by pcre2_jit_compile(). There are three cases for the values + processed by pcre2_jit_compile(). There are three cases for the values of the other two options: (1) If callback is NULL and data is NULL, an internal 32K block on the machine stack is used. (2) If callback is NULL and data is not NULL, data must be - a valid JIT stack, the result of calling pcre2_jit_stack_alloc(). + a valid JIT stack, the result of calling pcre2_jit_stack_cre- + ate(). (3) If callback is not NULL, it must point to a function that is called with data as an argument at the start of matching, in order to set up a JIT stack. If the return from the callback function is NULL, the internal 32K stack is used; otherwise the return value must be a valid JIT stack, the result of calling - pcre2_jit_stack_alloc(). + pcre2_jit_stack_create(). A callback function is obeyed whenever JIT code is about to be run; it is not obeyed when pcre2_match() is called with options that are incom- @@ -3605,7 +3604,7 @@ CONTROLLING THE JIT STACK up non-default JIT stacks might operate: During thread initalization - thread_local_var = pcre2_jit_stack_alloc(...) + thread_local_var = pcre2_jit_stack_create(...) During thread exit pcre2_jit_stack_free(thread_local_var) @@ -3687,6 +3686,19 @@ JIT STACK FAQ throw out this complicated API. +FREEING JIT SPECULATIVE MEMORY + + void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext); + + The JIT executable allocator does not free all memory when it is possi- + ble. It expects new allocations, and keeps some free memory around to + improve allocation speed. However, in low memory conditions, it might + be better to free all possible memory. You can cause this to happen by + calling pcre2_jit_free_unused_memory(). Its argument is a general con- + text, for custom memory management, or NULL for standard memory manage- + ment. + + EXAMPLE CODE This is a single-threaded example that specifies a JIT stack without @@ -3702,7 +3714,7 @@ EXAMPLE CODE /* Check for errors */ rc = pcre2_jit_compile(re, PCRE2_JIT_COMPLETE); /* Check for errors */ - jit_stack = pcre2_jit_stack_alloc(NULL, 32*1024, 512*1024); + jit_stack = pcre2_jit_stack_create(NULL, 32*1024, 512*1024); /* Check for error (NULL) */ pcre2_jit_stack_assign(re, NULL, jit_stack); match_data = pcre2_match_data_create(re, 10); @@ -3727,19 +3739,20 @@ JIT FAST PATH API exactly the same arguments as pcre2_match(), plus one additional argu- ment that must either point to a JIT stack or be NULL. In the latter case, if a callback function has been set up by - pcre2_jit_stack_alloc(), it is called. Otherwise the system stack is + pcre2_jit_stack_assign(), it is called. Otherwise the system stack is used. The return values are the same as for pcre2_match(), plus PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial or complete) is - requested that was not compiled. Unsupported option bits are ignored. + requested that was not compiled. Unsupported option bits (for example, + PCRE2_ANCHORED) are ignored. - When you call pcre2_match(), as well as testing for invalid options, a + When you call pcre2_match(), as well as testing for invalid options, a number of other sanity checks are performed on the arguments. For exam- ple, if the subject pointer is NULL, an immediate error is given. Also, - unless PCRE2_NO_UTF_CHECK is set, a UTF subject string is tested for - validity. In the interests of speed, these checks do not happen on the + unless PCRE2_NO_UTF_CHECK is set, a UTF subject string is tested for + validity. In the interests of speed, these checks do not happen on the JIT fast path, and if invalid data is passed, the result is undefined. - Bypassing the sanity checks and the pcre2_match() wrapping can give + Bypassing the sanity checks and the pcre2_match() wrapping can give speedups of more than 10%. @@ -3757,7 +3770,7 @@ AUTHOR REVISION - Last updated: 21 October 2014 + Last updated: 03 November 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ diff --git a/doc/pcre2_jit_free_unused_memory.3 b/doc/pcre2_jit_free_unused_memory.3 index 1a5c0e7..bf050c8 100644 --- a/doc/pcre2_jit_free_unused_memory.3 +++ b/doc/pcre2_jit_free_unused_memory.3 @@ -15,9 +15,9 @@ PCRE2 - Perl-compatible regular expressions (revised API) .sp This function frees unused JIT executable memory. The argument is a general context, for custom memory management, or NULL for standard memory management. -JIT memory allocation retains some memory in order to improve future JIT -compilation speed. In low memory conditions, -\fBpcre2_jit_free_unused_memory()\fB can be used to cause this memory to be +JIT memory allocation retains some memory in order to improve future JIT +compilation speed. In low memory conditions, +\fBpcre2_jit_free_unused_memory()\fB can be used to cause this memory to be freed. .P There is a complete description of the PCRE2 native API in the diff --git a/doc/pcre2_jit_match.3 b/doc/pcre2_jit_match.3 index 09c5d42..03b543c 100644 --- a/doc/pcre2_jit_match.3 +++ b/doc/pcre2_jit_match.3 @@ -1,4 +1,4 @@ -.TH PCRE2_JIT_MATCH 3 "21 October 2014" "PCRE2 10.0" +.TH PCRE2_JIT_MATCH 3 "03 November 2014" "PCRE2 10.0" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH SYNOPSIS @@ -26,7 +26,7 @@ Its arguments are exactly the same as for .\" plus one additional argument that must either point to a JIT stack or be NULL. In the latter case, if a callback function has been set up by -\fBpcre2_jit_stack_alloc()\fP, it is called. Otherwise the system stack is +\fBpcre2_jit_stack_create()\fP, it is called. Otherwise the system stack is used. .P The supported options are PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, diff --git a/doc/pcre2_jit_stack_assign.3 b/doc/pcre2_jit_stack_assign.3 index 0a3e1b8..5097c7e 100644 --- a/doc/pcre2_jit_stack_assign.3 +++ b/doc/pcre2_jit_stack_assign.3 @@ -1,4 +1,4 @@ -.TH PCRE2_JIT_STACK_ASSIGN 3 "21 October 2014" "PCRE2 10.0" +.TH PCRE2_JIT_STACK_ASSIGN 3 "03 November 2014" "PCRE2 10.0" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH SYNOPSIS @@ -27,12 +27,12 @@ block on the machine stack is used. .P If \fIcallback\fP is NULL and \fIcallback_data\fP is not NULL, \fIcallback_data\fP must be a valid JIT stack, the result of calling -\fBpcre2_jit_stack_alloc()\fP. +\fBpcre2_jit_stack_create()\fP. .P If \fIcallback\fP not NULL, it is called with \fIcallback_data\fP as an argument at the start of matching, in order to set up a JIT stack. If the result is NULL, the internal 32K stack is used; otherwise the return value must -be a valid JIT stack, the result of calling \fBpcre2_jit_stack_alloc()\fP. +be a valid JIT stack, the result of calling \fBpcre2_jit_stack_create()\fP. .P You may safely assign the same JIT stack to multiple patterns, as long as they are all matched in the same thread. In a multithread application, each thread diff --git a/doc/pcre2_jit_stack_alloc.3 b/doc/pcre2_jit_stack_create.3 similarity index 88% rename from doc/pcre2_jit_stack_alloc.3 rename to doc/pcre2_jit_stack_create.3 index dc35dea..b9d6756 100644 --- a/doc/pcre2_jit_stack_alloc.3 +++ b/doc/pcre2_jit_stack_create.3 @@ -1,4 +1,4 @@ -.TH PCRE2_JIT_STACK_ALLOC 3 "21 October 2014" "PCRE2 10.00" +.TH PCRE2_JIT_STACK_CREATE 3 "03 November 2014" "PCRE2 10.00" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH SYNOPSIS @@ -7,7 +7,7 @@ PCRE2 - Perl-compatible regular expressions (revised API) .B #include .PP .nf -.B pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *\fIgcontext\fP, +.B pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *\fIgcontext\fP, .B " PCRE2_SIZE \fIstartsize\fP, PCRE2_SIZE \fImaxsize\fP);" .fi . diff --git a/doc/pcre2_jit_stack_free.3 b/doc/pcre2_jit_stack_free.3 index 4e4a61d..bfa4f79 100644 --- a/doc/pcre2_jit_stack_free.3 +++ b/doc/pcre2_jit_stack_free.3 @@ -13,7 +13,7 @@ PCRE2 - Perl-compatible regular expressions (revised API) .rs .sp This function is used to free a JIT stack that was created by -\fBpcre2_jit_stack_alloc()\fP when it is no longer needed. For more details, +\fBpcre2_jit_stack_create()\fP when it is no longer needed. For more details, see the .\" HREF \fBpcre2jit\fP diff --git a/doc/pcre2_substring_number_from_name.3 b/doc/pcre2_substring_number_from_name.3 index 12a9d3d..b077b1d 100644 --- a/doc/pcre2_substring_number_from_name.3 +++ b/doc/pcre2_substring_number_from_name.3 @@ -15,7 +15,7 @@ PCRE2 - Perl-compatible regular expressions (revised API) .rs .sp This convenience function finds the number of a named substring capturing -parenthesis in a compiled pattern, provided that it is a unique name. The +parenthesis in a compiled pattern, provided that it is a unique name. The function arguments are: .sp \fIcode\fP Compiled regular expression diff --git a/doc/pcre2api.3 b/doc/pcre2api.3 index 8c3e39d..e05a60f 100644 --- a/doc/pcre2api.3 +++ b/doc/pcre2api.3 @@ -1,4 +1,4 @@ -.TH PCRE2API 3 "29 October 2014" "PCRE2 10.00" +.TH PCRE2API 3 "03 November 2014" "PCRE2 10.00" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .sp @@ -182,7 +182,7 @@ document for an overview of all the PCRE2 documentation. .sp .B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP); .sp -.B pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *\fIgcontext\fP, +.B pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *\fIgcontext\fP, .B " PCRE2_SIZE \fIstartsize\fP, PCRE2_SIZE \fImaxsize\fP);" .sp .B void pcre2_jit_stack_assign(const pcre2_code *\fIcode\fP, @@ -308,7 +308,7 @@ successfully compiled by \fBpcre2_compile()\fP. This does nothing if JIT support is not available. .P More complicated programs might need to make use of the specialist functions -\fBpcre2_jit_stack_alloc()\fP, \fBpcre2_jit_stack_free()\fP, and +\fBpcre2_jit_stack_create()\fP, \fBpcre2_jit_stack_free()\fP, and \fBpcre2_jit_stack_assign()\fP in order to control the JIT code's memory usage. .P JIT matching is automatically used by \fBpcre2_match()\fP if it is available. @@ -1265,7 +1265,7 @@ textual error message from any error code. .sp .B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP); .sp -.B pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *\fIgcontext\fP, +.B pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *\fIgcontext\fP, .B " PCRE2_SIZE \fIstartsize\fP, PCRE2_SIZE \fImaxsize\fP);" .sp .B void pcre2_jit_stack_assign(const pcre2_code *\fIcode\fP, @@ -2072,7 +2072,7 @@ match or a partial match, as well as after a successful one. The code unit offset of the character at which a successful match started is returned by \fBpcre2_get_startchar()\fP. For a non-partial match, this can be different to the value of \fIovector[0]\fP if the pattern contains the \eK -escape sequence. After a partial match, however, this value is always the same +escape sequence. After a partial match, however, this value is always the same as \fIovector[0]\fP because \eK does not affect the result of a partial match. . . @@ -2333,7 +2333,7 @@ unique (PCRE2_DUPNAMES was not set), you can find the number from the name by calling \fBpcre2_substring_number_from_name()\fP. The first argument is the compiled pattern, and the second is the name. The yield of the function is the subpattern number, PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that -name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of +name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of that name. .P Given the number, you can extract the substring directly, or use one of the @@ -2631,6 +2631,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 29 October 2014 +Last updated: 03 November 2014 Copyright (c) 1997-2014 University of Cambridge. .fi diff --git a/doc/pcre2jit.3 b/doc/pcre2jit.3 index 6b2ada0..bc06f1e 100644 --- a/doc/pcre2jit.3 +++ b/doc/pcre2jit.3 @@ -1,4 +1,4 @@ -.TH PCRE2JIT 3 "02 November 2014" "PCRE2 10.00" +.TH PCRE2JIT 3 "03 November 2014" "PCRE2 10.00" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH "PCRE2 JUST-IN-TIME COMPILER SUPPORT" @@ -149,7 +149,7 @@ about the use of JIT stacks in the section entitled .\" below. .P -The \fBpcre2_jit_stack_alloc()\fP function creates a JIT stack. Its arguments +The \fBpcre2_jit_stack_create()\fP function creates a JIT stack. Its arguments are a general context (for memory allocation functions, or NULL for standard memory allocation), a starting size and a maximum size, and it returns a pointer to an opaque structure of type \fBpcre2_jit_stack\fP, or NULL if there @@ -176,14 +176,14 @@ the other two options: on the machine stack is used. .sp (2) If \fIcallback\fP is NULL and \fIdata\fP is not NULL, \fIdata\fP must be - a valid JIT stack, the result of calling \fBpcre2_jit_stack_alloc()\fP. + a valid JIT stack, the result of calling \fBpcre2_jit_stack_create()\fP. .sp (3) If \fIcallback\fP is not NULL, it must point to a function that is called with \fIdata\fP as an argument at the start of matching, in order to set up a JIT stack. If the return from the callback function is NULL, the internal 32K stack is used; otherwise the return value must be a valid JIT stack, the result of calling - \fBpcre2_jit_stack_alloc()\fP. + \fBpcre2_jit_stack_create()\fP. .sp A callback function is obeyed whenever JIT code is about to be run; it is not obeyed when \fBpcre2_match()\fP is called with options that are incompatible @@ -209,7 +209,7 @@ This is a suggestion for how a multithreaded program that needs to set up non-default JIT stacks might operate: .sp During thread initalization - thread_local_var = pcre2_jit_stack_alloc(...) + thread_local_var = pcre2_jit_stack_create(...) .sp During thread exit pcre2_jit_stack_free(thread_local_var) @@ -323,7 +323,7 @@ callback. /* Check for errors */ rc = pcre2_jit_compile(re, PCRE2_JIT_COMPLETE); /* Check for errors */ - jit_stack = pcre2_jit_stack_alloc(NULL, 32*1024, 512*1024); + jit_stack = pcre2_jit_stack_create(NULL, 32*1024, 512*1024); /* Check for error (NULL) */ pcre2_jit_stack_assign(re, NULL, jit_stack); match_data = pcre2_match_data_create(re, 10); @@ -352,7 +352,7 @@ must either point to a JIT stack or be NULL. In the latter case, if a callback function has been set up by \fBpcre2_jit_stack_assign()\fP, it is called. Otherwise the system stack is used. The return values are the same as for \fBpcre2_match()\fP, plus PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial -or complete) is requested that was not compiled. Unsupported option bits (for +or complete) is requested that was not compiled. Unsupported option bits (for example, PCRE2_ANCHORED) are ignored. .P When you call \fBpcre2_match()\fP, as well as testing for invalid options, a @@ -386,6 +386,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 02 November 2014 +Last updated: 03 November 2014 Copyright (c) 1997-2014 University of Cambridge. .fi diff --git a/doc/pcre2test.1 b/doc/pcre2test.1 index 3977c1e..8434bc4 100644 --- a/doc/pcre2test.1 +++ b/doc/pcre2test.1 @@ -437,7 +437,7 @@ about the pattern: /I info show info about compiled pattern hex pattern is coded in hexadecimal jit[=] use JIT - jitfast use JIT fast path + jitfast use JIT fast path jitverify verify JIT use locale= use this locale memory show memory used @@ -577,8 +577,8 @@ also output. .sp The \fBparens_nest_limit\fP modifier sets a limit on the depth of nested parentheses in a pattern. Breaching the limit causes a compilation error. -The default for the library is set when PCRE2 is built, but \fBpcre2test\fP -sets its own default of 220, which is required for running the standard test +The default for the library is set when PCRE2 is built, but \fBpcre2test\fP +sets its own default of 220, which is required for running the standard test suite. . . @@ -651,7 +651,7 @@ not affect the compilation process. allusedtext show all consulted text /g global global matching mark show mark values - startchar show starting character when relevant + startchar show starting character when relevant .sp These modifiers may not appear in a \fB#pattern\fP command. If you want them as defaults, set them in a \fB#subject\fP command. @@ -725,7 +725,7 @@ pattern. offset= set starting offset ovector= set size of output vector recursion_limit= set a recursion limit - startchar show startchar when relevant + startchar show startchar when relevant .sp The effects of these modifiers are described in the following sections. FIXME: Give more examples. @@ -759,17 +759,17 @@ underneath them. Here is an example: This shows that the matched string is "abc", with the preceding and following strings "pqr" and "xyz" also consulted during the match. .P -The \fBstartchar\fP 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 \eK has been processed as part of the match. In -this situation, the output for the matched string is displayed from the -starting character instead of from the match point, with circumflex characters +The \fBstartchar\fP 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 \eK has been processed as part of the match. In +this situation, the output for the matched string is displayed from the +starting character instead of from the match point, with circumflex characters under the earlier characters. For example: .sp re> /abc\eKxyz/ data> abcxyz\e=startchar 0: abcxyz - ^^^ + ^^^ .sp Unlike \fBallusedtext\fP, the \fBstartchar\fP modifier can be used with JIT. However, these two modifiers are mutually exclusive. @@ -856,7 +856,7 @@ The \fBjitstack\fP modifier provides a way of setting the maximum stack size that is used by the just-in-time optimization code. It is ignored if JIT optimization is not being used. The value is a number of kilobytes. Providing a stack that is larger than the default 32K is necessary only for very -complicated patterns. +complicated patterns. . . .SS "Setting match and recursion limits" @@ -925,9 +925,9 @@ available for storing matching information. The default is 15. A value of zero is useful when testing the POSIX API because it causes \fBregexec()\fP to be called with a NULL capture vector. When not testing the POSIX API, a value of zero is used to cause -\fBpcre2_match_data_create_from_pattern\fP to be called, in order to create a -match block of exactly the right size for the pattern. (It is not possible to -create a match block with a zero-length ovector; there is always one pair of +\fBpcre2_match_data_create_from_pattern\fP to be called, in order to create a +match block of exactly the right size for the pattern. (It is not possible to +create a match block with a zero-length ovector; there is always one pair of offsets.) . . diff --git a/doc/pcre2test.txt b/doc/pcre2test.txt index 5da745a..0172c49 100644 --- a/doc/pcre2test.txt +++ b/doc/pcre2test.txt @@ -169,137 +169,138 @@ COMMAND LINE OPTIONS DESCRIPTION If pcre2test is given two filename arguments, it reads from the first - and writes to the second. If it is given only one filename argument, it - reads from that file and writes to stdout. Otherwise, it reads from - stdin and writes to stdout, and prompts for each line of input, using - "re>" to prompt for regular expression patterns, and "data>" to prompt - for subject lines. + and writes to the second. If the first name is "-", input is taken from + the standard input. If pcre2test is given only one argument, it reads + from that file and writes to stdout. Otherwise, it reads from stdin and + writes to stdout. When the input is a terminal, it prompts for each + line of input, using "re>" to prompt for regular expression patterns, + and "data>" to prompt for subject lines. - When pcre2test is built, a configuration option can specify that it - should be linked with the libreadline or libedit library. When this is - done, if the input is from a terminal, it is read using the readline() + When pcre2test is built, a configuration option can specify that it + should be linked with the libreadline or libedit library. When this is + done, if the input is from a terminal, it is read using the readline() function. This provides line-editing and history facilities. The output from the -help option states whether or not readline() will be used. - The program handles any number of tests, each of which consists of a - set of input lines. Each set starts with a regular expression pattern, + The program handles any number of tests, each of which consists of a + set of input lines. Each set starts with a regular expression pattern, followed by any number of subject lines to be matched against that pat- - tern. In between sets of test data, command lines that begin with a - hash (#) character may appear. This file format, with some restric- + tern. In between sets of test data, command lines that begin with a + hash (#) character may appear. This file format, with some restric- tions, can also be processed by the perltest.pl script that is distrib- - uted with PCRE2 as a means of checking that the behaviour of PCRE2 and + uted with PCRE2 as a means of checking that the behaviour of PCRE2 and Perl is the same. - Each subject line is matched separately and independently. If you want + Each subject line is matched separately and independently. If you want to do multi-line matches, you have to use the \n escape sequence (or \r - or \r\n, etc., depending on the newline setting) in a single line of - input to encode the newline sequences. There is no limit on the length - of subject lines; the input buffer is automatically extended if it is - too small. There is a replication feature that makes it possible to + or \r\n, etc., depending on the newline setting) in a single line of + input to encode the newline sequences. There is no limit on the length + of subject lines; the input buffer is automatically extended if it is + too small. There is a replication feature that makes it possible to generate long subject lines without having to supply them explicitly. - An empty line or the end of the file signals the end of the subject - lines for a test, at which point a new pattern or command line is + An empty line or the end of the file signals the end of the subject + lines for a test, at which point a new pattern or command line is expected if there is still input to be read. COMMAND LINES - In between sets of test data, a line that begins with a hash (#) char- - acter is interpreted as a command line. If the first character is fol- - lowed by white space or an exclamation mark, the line is treated as a - comment, and ignored. Otherwise, the following commands are recog- + In between sets of test data, a line that begins with a hash (#) char- + acter is interpreted as a command line. If the first character is fol- + lowed by white space or an exclamation mark, the line is treated as a + comment, and ignored. Otherwise, the following commands are recog- nized: #forbid_utf - Subsequent patterns automatically have the PCRE2_NEVER_UTF and + Subsequent patterns automatically have the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP options set, which locks out the use of UTF and Unicode - property features. This is a trigger guard that is used in test files - to ensure that UTF/Unicode tests are not accidentally added to files - that are used when UTF support is not included in the library. This - effect can also be obtained by the use of #pattern; the difference is - that #forbid_utf cannot be unset, and the automatic options are not + property features. This is a trigger guard that is used in test files + to ensure that UTF/Unicode tests are not accidentally added to files + that are used when UTF support is not included in the library. This + effect can also be obtained by the use of #pattern; the difference is + that #forbid_utf cannot be unset, and the automatic options are not displayed in pattern information, to avoid cluttering up test output. #pattern - This command sets a default modifier list that applies to all subse- + This command sets a default modifier list that applies to all subse- quent patterns. Modifiers on a pattern can change these settings. #perltest - The appearance of this line causes all subsequent modifier settings to + The appearance of this line causes all subsequent modifier settings to be checked for compatibility with the perltest.pl script, which is used - to confirm that Perl gives the same results as PCRE2. Also, apart from - comment lines, none of the other command lines are permitted, because - they and many of the modifiers are specific to pcre2test, and should - not be used in test files that are also processed by perltest.pl. The - #perltest command helps detect tests that are accidentally put in the + to confirm that Perl gives the same results as PCRE2. Also, apart from + comment lines, none of the other command lines are permitted, because + they and many of the modifiers are specific to pcre2test, and should + not be used in test files that are also processed by perltest.pl. The + #perltest command helps detect tests that are accidentally put in the wrong file. #subject - This command sets a default modifier list that applies to all subse- - quent subject lines. Modifiers on a subject line can change these set- + This command sets a default modifier list that applies to all subse- + quent subject lines. Modifiers on a subject line can change these set- tings. MODIFIER SYNTAX Modifier lists are used with both pattern and subject lines. Items in a - list are separated by commas and optional white space. Some modifiers - may be given for both patterns and subject lines, whereas others are - valid for one or the other only. Each modifier has a long name, for + list are separated by commas and optional white space. Some modifiers + may be given for both patterns and subject lines, whereas others are + valid for one or the other only. Each modifier has a long name, for example "anchored", and some of them must be followed by an equals sign and a value, for example, "offset=12". Modifiers that do not take val- ues may be preceded by a minus sign to turn off a previous default set- ting. A few of the more common modifiers can also be specified as single let- - ters, for example "i" for "caseless". In documentation, following the + ters, for example "i" for "caseless". In documentation, following the Perl convention, these are written with a slash ("the /i modifier") for - clarity. Abbreviated modifiers must all be concatenated in the first - item of a modifier list. If the first item is not recognized as a long - modifier name, it is interpreted as a sequence of these abbreviations. + clarity. Abbreviated modifiers must all be concatenated in the first + item of a modifier list. If the first item is not recognized as a long + modifier name, it is interpreted as a sequence of these abbreviations. For example: /abc/ig,newline=cr,jit=3 - This is a pattern line whose modifier list starts with two one-letter - modifiers (/i and /g). The lower-case abbreviated modifiers are the + This is a pattern line whose modifier list starts with two one-letter + modifiers (/i and /g). The lower-case abbreviated modifiers are the same as used in Perl. PATTERN SYNTAX - A pattern line must start with one of the following characters (common + A pattern line must start with one of the following characters (common symbols, excluding pattern meta-characters): / ! " ' ` - = _ : ; , % & @ ~ - This is interpreted as the pattern's delimiter. A regular expression - may be continued over several input lines, in which case the newline + This is interpreted as the pattern's delimiter. A regular expression + may be continued over several input lines, in which case the newline characters are included within it. It is possible to include the delim- iter within the pattern by escaping it with a backslash, for example /abc\/def/ - If you do this, the escape and the delimiter form part of the pattern, + If you do this, the escape and the delimiter form part of the pattern, but since the delimiters are all non-alphanumeric, this does not affect - its interpretation. If the terminating delimiter is immediately fol- + its interpretation. If the terminating delimiter is immediately fol- lowed by a backslash, for example, /abc/\ - then a backslash is added to the end of the pattern. This is done to - provide a way of testing the error condition that arises if a pattern + then a backslash is added to the end of the pattern. This is done to + provide a way of testing the error condition that arises if a pattern finishes with a backslash, because /abc\/ - is interpreted as the first line of a pattern that starts with "abc/", - causing pcre2test to read the next line as a continuation of the regu- + is interpreted as the first line of a pattern that starts with "abc/", + causing pcre2test to read the next line as a continuation of the regu- lar expression. A pattern can be followed by a modifier list (details below). @@ -307,7 +308,7 @@ PATTERN SYNTAX SUBJECT LINE SYNTAX - Before each subject line is passed to pcre2_match() or + Before each subject line is passed to pcre2_match() or pcre2_dfa_match(), leading and trailing white space is removed, and the line is scanned for backslash escapes. The following provide a means of encoding non-printing characters in a visible way: @@ -327,23 +328,23 @@ SUBJECT LINE SYNTAX \x{hh...} hexadecimal character (any number of hex digits) The use of \x{hh...} is not dependent on the use of the utf modifier on - the pattern. It is recognized always. There may be any number of hexa- - decimal digits inside the braces; invalid values provoke error mes- + the pattern. It is recognized always. There may be any number of hexa- + decimal digits inside the braces; invalid values provoke error mes- sages. - Note that \xhh specifies one byte rather than one character in UTF-8 - mode; this makes it possible to construct invalid UTF-8 sequences for - testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8 - character in UTF-8 mode, generating more than one byte if the value is - greater than 127. When testing the 8-bit library not in UTF-8 mode, + Note that \xhh specifies one byte rather than one character in UTF-8 + mode; this makes it possible to construct invalid UTF-8 sequences for + testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8 + character in UTF-8 mode, generating more than one byte if the value is + greater than 127. When testing the 8-bit library not in UTF-8 mode, \x{hh} generates one byte for values less than 256, and causes an error for greater values. In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it possible to construct invalid UTF-16 sequences for testing purposes. - In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This - makes it possible to construct invalid UTF-32 sequences for testing + In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This + makes it possible to construct invalid UTF-32 sequences for testing purposes. There is a special backslash sequence that specifies replication of one @@ -351,38 +352,38 @@ SUBJECT LINE SYNTAX \[]{} - This makes it possible to test long strings without having to provide + This makes it possible to test long strings without having to provide them as part of the file. For example: \[abc]{4} - is converted to "abcabcabcabc". This feature does not support nesting. + is converted to "abcabcabcabc". This feature does not support nesting. To include a closing square bracket in the characters, code it as \x5D. - A backslash followed by an equals sign marke the end of the subject + A backslash followed by an equals sign marke the end of the subject string and the start of a modifier list. For example: abc\=notbol,notempty - A backslash followed by any other non-alphanumeric character just + A backslash followed by any other non-alphanumeric character just escapes that character. A backslash followed by anything else causes an - error. However, if the very last character in the line is a backslash - (and there is no modifier list), it is ignored. This gives a way of - passing an empty line as data, since a real empty line terminates the + error. However, if the very last character in the line is a backslash + (and there is no modifier list), it is ignored. This gives a way of + passing an empty line as data, since a real empty line terminates the data input. PATTERN MODIFIERS There are three types of modifier that can appear in pattern lines, two - of which may also be used in a #pattern command. A pattern's modifier + of which may also be used in a #pattern command. A pattern's modifier list can add to or override default modifiers that were set by a previ- ous #pattern command. Setting compilation options - The following modifiers set options for pcre2_compile(). The most com- - mon ones have single-letter abbreviations. See pcreapi for a descrip- + The following modifiers set options for pcre2_compile(). The most com- + mon ones have single-letter abbreviations. See pcreapi for a descrip- tion of their effects. allow_empty_class set PCRE2_ALLOW_EMPTY_CLASS @@ -408,13 +409,13 @@ PATTERN MODIFIERS utf set PCRE2_UTF As well as turning on the PCRE2_UTF option, the utf modifier causes all - non-printing characters in output strings to be printed using the - \x{hh...} notation. Otherwise, those less than 0x100 are output in hex + non-printing characters in output strings to be printed using the + \x{hh...} notation. Otherwise, those less than 0x100 are output in hex without the curly brackets. Setting compilation controls - The following modifiers affect the compilation process or request + The following modifiers affect the compilation process or request information about the pattern: bsr=[anycrlf|unicode] specify \R handling @@ -424,6 +425,7 @@ PATTERN MODIFIERS /I info show info about compiled pattern hex pattern is coded in hexadecimal jit[=] use JIT + jitfast use JIT fast path jitverify verify JIT use locale= use this locale memory show memory used @@ -440,55 +442,55 @@ PATTERN MODIFIERS Newline and \R handling - The bsr modifier specifies what \R in a pattern should match. If it is - set to "anycrlf", \R matches CR, LF, or CRLF only. If it is set to - "unicode", \R matches any Unicode newline sequence. The default is + The bsr modifier specifies what \R in a pattern should match. If it is + set to "anycrlf", \R matches CR, LF, or CRLF only. If it is set to + "unicode", \R matches any Unicode newline sequence. The default is specified when PCRE2 is built, with the default default being Unicode. - The newline modifier specifies which characters are to be interpreted + The newline modifier specifies which characters are to be interpreted as newlines, both in the pattern and (by default) in subject lines. The type must be one of CR, LF, CRLF, ANYCRLF, or ANY. Information about a pattern - The debug modifier is a shorthand for info,fullbincode, requesting all + The debug modifier is a shorthand for info,fullbincode, requesting all available information. The bincode modifier causes a representation of the compiled code to be - output after compilation. This information does not contain length and + output after compilation. This information does not contain length and offset values, which ensures that the same output is generated for dif- - ferent internal link sizes and different code unit widths. By using - bincode, the same regression tests can be used in different environ- + ferent internal link sizes and different code unit widths. By using + bincode, the same regression tests can be used in different environ- ments. - The fullbincode modifier, by contrast, does include length and offset + The fullbincode modifier, by contrast, does include length and offset values. This is used in a few special tests and is also useful for one- off tests. - The info modifier requests information about the compiled pattern - (whether it is anchored, has a fixed first character, and so on). The + The info modifier requests information about the compiled pattern + (whether it is anchored, has a fixed first character, and so on). The information is obtained from the pcre2_pattern_info() function. Specifying a pattern in hex The hex modifier specifies that the characters of the pattern are to be - interpreted as pairs of hexadecimal digits. White space is permitted + interpreted as pairs of hexadecimal digits. White space is permitted between pairs. For example: /ab 32 59/hex - This feature is provided as a way of creating patterns that contain + This feature is provided as a way of creating patterns that contain binary zero characters. When hex is set, it implies use_length. Using the pattern's length - By default, pcre2test passes patterns as zero-terminated strings to - pcre2_compile(), giving the length as -1. If use_length is set, the + By default, pcre2test passes patterns as zero-terminated strings to + pcre2_compile(), giving the length as -1. If use_length is set, the length of the pattern is passed. This is implied if hex is set. JIT compilation - The /jit modifier may optionally be followed by and equals sign and a + The /jit modifier may optionally be followed by and equals sign and a number in the range 0 to 7: 0 disable JIT @@ -499,17 +501,23 @@ PATTERN MODIFIERS 6 use JIT for soft and hard partial match 7 all three modes - If no number is given, 7 is assumed. If JIT compilation is successful, - the compiled JIT code will automatically be used when pcre2_match() is - run for the appropriate type of match, except when incompatible run- + If no number is given, 7 is assumed. If JIT compilation is successful, + the compiled JIT code will automatically be used when pcre2_match() is + run for the appropriate type of match, except when incompatible run- time options are specified. For more details, see the pcre2jit documen- - tation. See also the jitstack modifier below for a way of setting the + tation. See also the jitstack modifier below for a way of setting the size of the JIT stack. - If the jitverify modifier is specified, information about the compiled - pattern shows whether JIT compilation was or was not successful. If - jitverify is specified without jit, jit=7 is assumed. If JIT compila- - tion is successful when jitverify is set, the text "(JIT)" is added to + If the jitfast modifier is specified, matching is done using the JIT + "fast path" interface (pcre2_jit_match()), which skips some of the san- + ity checks that are done by pcre2_match(), and of course does not work + when JIT is not supported. If jitfast is specified without jit, jit=7 + is assumed. + + If the jitverify modifier is specified, information about the compiled + pattern shows whether JIT compilation was or was not successful. If + jitverify is specified without jit, jit=7 is assumed. If JIT compila- + tion is successful when jitverify is set, the text "(JIT)" is added to the first output line after a match or non match when JIT-compiled code was actually used. @@ -520,31 +528,33 @@ PATTERN MODIFIERS /pattern/locale=fr_FR The given locale is set, pcre2_maketables() is called to build a set of - character tables for the locale, and this is then passed to pcre2_com- - pile() when compiling the regular expression. The same tables are used + character tables for the locale, and this is then passed to pcre2_com- + pile() when compiling the regular expression. The same tables are used when matching the following subject lines. The /locale modifier applies only to the pattern on which it appears, but can be given in a #pattern - command if a default is needed. Setting a locale and alternate charac- + command if a default is needed. Setting a locale and alternate charac- ter tables are mutually exclusive. Showing pattern memory - The /memory modifier causes the size in bytes of the memory block used - to hold the compiled pattern to be output. This does not include the - size of the pcre2_code block; it is just the actual compiled data. If + The /memory modifier causes the size in bytes of the memory block used + to hold the compiled pattern to be output. This does not include the + size of the pcre2_code block; it is just the actual compiled data. If the pattern is subsequently passed to the JIT compiler, the size of the JIT compiled code is also output. Limiting nested parentheses - The parens_nest_limit modifier sets a limit on the depth of nested - parentheses in a pattern. Breaching the limit causes a compilation - error. + The parens_nest_limit modifier sets a limit on the depth of nested + parentheses in a pattern. Breaching the limit causes a compilation + error. The default for the library is set when PCRE2 is built, but + pcre2test sets its own default of 220, which is required for running + the standard test suite. Using the POSIX wrapper API - The /posix modifier causes pcre2test to call PCRE2 via the POSIX wrap- - per API rather than its native API. This supports only the 8-bit + The /posix modifier causes pcre2test to call PCRE2 via the POSIX wrap- + per API rather than its native API. This supports only the 8-bit library. When the POSIX API is being used, the following pattern modi- fiers set options for the regcomp() function: @@ -556,25 +566,25 @@ PATTERN MODIFIERS ucp REG_UCP ) the POSIX standard utf REG_UTF8 ) - The aftertext and allaftertext subject modifiers work as described + The aftertext and allaftertext subject modifiers work as described below. All other modifiers cause an error. Testing the stack guard feature - The /stackguard modifier is used to test the use of pcre2_set_com- - pile_recursion_guard(), a function that is provided to enable stack - availability to be checked during compilation (see the pcre2api docu- - mentation for details). If the number specified by the modifier is + The /stackguard modifier is used to test the use of pcre2_set_com- + pile_recursion_guard(), a function that is provided to enable stack + availability to be checked during compilation (see the pcre2api docu- + mentation for details). If the number specified by the modifier is greater than zero, pcre2_set_compile_recursion_guard() is called to set - up callback from pcre2_compile() to a local function. The argument it - is passed is the current nesting parenthesis depth; if this is greater + up callback from pcre2_compile() to a local function. The argument it + is passed 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 /tables modifier must be followed by a single digit. It causes a - specific set of built-in character tables to be passed to pcre2_com- + The /tables modifier must be followed by a single digit. It causes a + specific set of built-in character tables to be passed to pcre2_com- pile(). This is used in the PCRE2 tests to check behaviour with differ- ent character tables. The digit specifies the tables as follows: @@ -583,25 +593,26 @@ PATTERN MODIFIERS pcre2_chartables.c.dist 2 a set of tables defining ISO 8859 characters - In table 2, some characters whose codes are greater than 128 are iden- - tified as letters, digits, spaces, etc. Setting alternate character + In table 2, some characters whose codes are greater than 128 are iden- + tified as letters, digits, spaces, etc. Setting alternate character tables and a locale are mutually exclusive. Setting certain match controls The following modifiers are really subject modifiers, and are described - below. However, they may be included in a pattern's modifier list, in - which case they are applied to every subject line that is processed + below. However, they may be included in a pattern's modifier list, in + which case they are applied to every subject line that is processed with that pattern. They do not affect the compilation process. - aftertext show text after match - allaftertext show text after captures - allcaptures show all captures - allusedtext show all consulted text - /g global global matching - mark show mark values + aftertext show text after match + allaftertext show text after captures + allcaptures show all captures + allusedtext show all consulted text + /g global global matching + mark show mark values + startchar show starting character when relevant - 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. @@ -612,7 +623,7 @@ 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 @@ -626,20 +637,20 @@ 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 modifier was present on the pattern, causing the POSIX + If the /posix modifier was present on the pattern, causing the POSIX wrapper API to be used, the only option-setting modifiers that have any - effect are notbol, notempty, and noteol, causing REG_NOTBOL, - REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec(). + effect are notbol, notempty, and noteol, causing REG_NOTBOL, + REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec(). Any other modifiers cause an error. Setting match controls - The following modifiers affect the matching process or request addi- - tional information. Some of them may also be specified on a pattern - line (see above), in which case they apply to every subject line that + The following modifiers affect the matching process or request addi- + tional information. Some of them may also be specified on a pattern + line (see above), in which case they apply to every subject line that is matched against that pattern. aftertext show text after match @@ -664,39 +675,56 @@ SUBJECT MODIFIERS offset= set starting offset ovector= set size of output vector recursion_limit= set a recursion limit + startchar show startchar when relevant The effects of these modifiers are described in the following sections. FIXME: Give more examples. Showing more text - The aftertext modifier requests that as well as outputting the sub- - 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 substrings - as well as the main matched substring. In each case the remainder is - output on the following line with a plus character following the cap- + The aftertext modifier requests that as well as outputting the sub- + 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 substrings + as well as the main matched substring. In each case the remainder is + output on the following line with a plus character following the cap- ture number. - The allusedtext modifier requests that all the text that was consulted - during a successful pattern match by the interpreter should be shown. - This feature is not supported for JIT matching, and if requested with - JIT it is ignored (with a warning message). Setting this modifier + The allusedtext modifier requests that all the text that was consulted + during a successful pattern match by the interpreter should be shown. + This feature is not supported for JIT matching, and if requested with + JIT it is ignored (with a warning message). Setting this modifier affects the output if there is a lookbehind at the start of a match, or - a lookahead at the end, or if \K is used in the pattern. Characters - that precede or follow the start and end of the actual match are indi- - cated in the output by '<' or '>' characters underneath them. Here is + a lookahead at the end, or if \K is used in the pattern. Characters + that precede or follow the start and end of the actual match are indi- + cated in the output by '<' or '>' characters underneath them. Here is an example: - /(?<=pqr)abc(?=xyz)/ - 123pqrabcxyz456\=allusedtext + re> /(?<=pqr)abc(?=xyz)/ + data> 123pqrabcxyz456\=allusedtext 0: pqrabcxyz <<< >>> - This shows that the matched string is "abc", with the preceding and + This shows that the matched string is "abc", with the preceding and following strings "pqr" and "xyz" also consulted during the match. + The startchar modifier requests that the starting character for the + match be indicated, if it is different to the start of the matched + string. The only time when this occurs is when \K has been processed as + part of the match. In this situation, the output for the matched string + is displayed from the starting character instead of from the match + point, with circumflex characters under the earlier characters. For + example: + + re> /abc\Kxyz/ + data> abcxyz\=startchar + 0: abcxyz + ^^^ + + 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 The allcaptures modifier requests that the values of all potential cap- @@ -768,66 +796,70 @@ SUBJECT MODIFIERS 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. Providing a stack that is larger - than the default 32K is necessary only for very complicated patterns. + JIT optimization is not being used. The value is a number of kilobytes. + Providing a stack that is larger than the default 32K is necessary only + for very complicated patterns. Setting match and recursion limits - The match_limit and recursion_limit modifiers set the appropriate lim- + The match_limit and recursion_limit modifiers set the appropriate lim- its in the match context. These values are ignored when the find_limits modifier is specified. Finding minimum limits - If the find_limits modifier is present, pcre2test calls pcre2_match() - several times, setting different values in the match context via - pcre2_set_match_limit() and pcre2_set_recursion_limit() until it finds - the minimum values for each parameter that allow pcre2_match() to com- + If the find_limits modifier is present, pcre2test calls pcre2_match() + several times, setting different values in the match context via + pcre2_set_match_limit() and pcre2_set_recursion_limit() until it finds + the minimum values for each parameter that allow pcre2_match() to com- plete without error. If JIT is being used, only the match limit is relevant. If DFA matching - is being used, neither limit is relevant, and this modifier is ignored + is being used, neither limit is relevant, and this modifier is ignored (with a warning message). - 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. The - match_limit_recursion number is a measure of how much stack (or, if - PCRE2 is compiled with NO_RECURSE, how much heap) memory is needed to + 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. The + match_limit_recursion number is a measure of how much stack (or, if + PCRE2 is compiled with NO_RECURSE, how much heap) memory is needed to complete the match attempt. 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 all memory allocation and + The memory modifier causes pcre2test to log all memory allocation and freeing calls that occur during a match operation. 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 the size of the output vector - The ovector modifier applies only to the subject line in which it - appears, though of course it can also be used to set a default in a - #subject command. It specifies the number of pairs of offsets that are + The ovector modifier applies only to the subject line in which it + appears, though of course it can also be used to set a default in a + #subject command. It specifies the number of pairs of offsets that are available for storing matching information. The default is 15. - At least one pair of offsets is always created by pcre2_match_data_cre- - ate(), for matching with PCRE2's native API, so a value of 0 is the - same as 1. However a value of 0 is useful when testing the POSIX API - because it causes regexec() to be called with a NULL capture vector. + 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 match block of + exactly the right size for the pattern. (It is not possible to create a + match block with a zero-length ovector; there is always one pair of + offsets.) THE ALTERNATIVE MATCHING FUNCTION @@ -1058,8 +1090,8 @@ NON-PRINTING CHARACTERS SEE ALSO - pcre2(3), pcre16(3), pcre32(3), pcre2api(3), pcre2callout(3), pcre2jit, - pcre2matching(3), pcre2partial(d), pcre2pattern(3), pcre2precompile(3). + pcre2(3), pcre2api(3), pcre2callout(3), pcre2jit, pcre2matching(3), + pcre2partial(d), pcre2pattern(3). AUTHOR @@ -1071,5 +1103,5 @@ AUTHOR REVISION - Last updated: 11 October 2014 + Last updated: 02 November 2014 Copyright (c) 1997-2014 University of Cambridge. diff --git a/perltest.sh b/perltest.sh index e45486a..51bf9b2 100755 --- a/perltest.sh +++ b/perltest.sh @@ -8,7 +8,7 @@ # # The desired effect is achieved by making this a shell script that passes the # Perl script to Perl through a pipe. If the first argument is "-utf8", a -# suitable prefix is set up. +# suitable prefix is set up. # # The remaining arguments, if any, are passed to Perl. They are an input file # and an output file. If there is one argument, the output is written to @@ -20,7 +20,7 @@ perl=perl prefix='' if [ $# > 0 -a "$1" = "-utf8" ] ; then prefix="use utf8; require Encode;" - shift + shift fi @@ -28,23 +28,23 @@ fi # can be given identical input, except that input patterns can be followed only # by Perl's lower case modifiers and certain other pcre2test modifiers that are # either handled or ignored: -# +# # aftertext interpreted as "print $' afterwards" # afteralltext ignored # dupnames ignored (Perl always allows) # mark ignored # no_auto_possess ignored -# no_start_optimize ignored -# ucp sets Perl's /u modifier -# utf invoke UTF-8 functionality -# +# no_start_optimize ignored +# ucp sets Perl's /u modifier +# utf invoke UTF-8 functionality +# # The data lines must not have any pcre2test modifiers. They are processed as # Perl double-quoted strings, so if they contain " $ or @ characters, these # have to be escaped. For this reason, all such characters in the # Perl-compatible testinput1 and testinput4 files are escaped so that they can # be used for perltest as well as for pcre2test. The output from this script # should be same as from pcre2test, apart from the initial identifying banner. -# +# # The other testinput files are not suitable for feeding to perltest.sh, # because they make use of the special modifiers that pcre2test uses for # testing features of PCRE2. Some of these files also contain malformed regular @@ -90,11 +90,11 @@ if (@ARGV > 0) $infile = "INFILE"; $interact = 0; } -else - { +else + { open(INFILE, " 1) @@ -291,5 +291,5 @@ for (;;) PERLEND ) | $perl - $@ - + # End diff --git a/src/pcre2.h.generic b/src/pcre2.h.generic index 3d7c9fd..724bb33 100644 --- a/src/pcre2.h.generic +++ b/src/pcre2.h.generic @@ -86,8 +86,7 @@ passed. Put these bits at the most significant end of the options word so others can be added next to them */ #define PCRE2_ANCHORED 0x80000000u -#define PCRE2_NO_START_OPTIMIZE 0x40000000u -#define PCRE2_NO_UTF_CHECK 0x20000000u +#define PCRE2_NO_UTF_CHECK 0x40000000u /* Other options that can be passed to pcre2_compile(). They may affect compilation, JIT compilation, and/or interpretive execution. The following tags @@ -95,7 +94,7 @@ indicate which: C alters what is compiled J alters what JIT compiles -E is inspected during pcre2_match() execution +M is inspected during pcre2_match() execution D is inspected during pcre2_dfa_match() execution */ @@ -103,24 +102,25 @@ D is inspected during pcre2_dfa_match() execution #define PCRE2_ALT_BSUX 0x00000002u /* C */ #define PCRE2_AUTO_CALLOUT 0x00000004u /* C */ #define PCRE2_CASELESS 0x00000008u /* C */ -#define PCRE2_DOLLAR_ENDONLY 0x00000010u /* J E D */ +#define PCRE2_DOLLAR_ENDONLY 0x00000010u /* J M D */ #define PCRE2_DOTALL 0x00000020u /* C */ #define PCRE2_DUPNAMES 0x00000040u /* C */ #define PCRE2_EXTENDED 0x00000080u /* C */ -#define PCRE2_FIRSTLINE 0x00000100u /* J E D */ -#define PCRE2_MATCH_UNSET_BACKREF 0x00000200u /* C J E */ +#define PCRE2_FIRSTLINE 0x00000100u /* J M D */ +#define PCRE2_MATCH_UNSET_BACKREF 0x00000200u /* C J M */ #define PCRE2_MULTILINE 0x00000400u /* C */ #define PCRE2_NEVER_UCP 0x00000800u /* C */ #define PCRE2_NEVER_UTF 0x00001000u /* C */ #define PCRE2_NO_AUTO_CAPTURE 0x00002000u /* C */ #define PCRE2_NO_AUTO_POSSESS 0x00004000u /* C */ -#define PCRE2_UCP 0x00008000u /* C J E D */ -#define PCRE2_UNGREEDY 0x00010000u /* C */ -#define PCRE2_UTF 0x00020000u /* C J E D */ +#define PCRE2_NO_START_OPTIMIZE 0x00008000u /* J M D */ +#define PCRE2_UCP 0x00010000u /* C J M D */ +#define PCRE2_UNGREEDY 0x00020000u /* C */ +#define PCRE2_UTF 0x00040000u /* C J M D */ /* These are for pcre2_jit_compile(). */ -#define PCRE2_JIT 0x00000001u /* For full matching */ +#define PCRE2_JIT_COMPLETE 0x00000001u /* For full matching */ #define PCRE2_JIT_PARTIAL_SOFT 0x00000002u #define PCRE2_JIT_PARTIAL_HARD 0x00000004u @@ -130,8 +130,8 @@ functions, so take care not to define synonyms by mistake. */ #define PCRE2_NOTBOL 0x00000001u #define PCRE2_NOTEOL 0x00000002u -#define PCRE2_NOTEMPTY 0x00000004u -#define PCRE2_NOTEMPTY_ATSTART 0x00000008u +#define PCRE2_NOTEMPTY 0x00000004u /* ) These two must be kept */ +#define PCRE2_NOTEMPTY_ATSTART 0x00000008u /* ) adjacent to each other. */ #define PCRE2_PARTIAL_SOFT 0x00000010u #define PCRE2_PARTIAL_HARD 0x00000020u @@ -140,9 +140,9 @@ functions, so take care not to define synonyms by mistake. */ #define PCRE2_DFA_RESTART 0x00000040u #define PCRE2_DFA_SHORTEST 0x00000080u -/* Newline and \R settings, for use in the compile and match contexts. The -newline values must be kept in step with values set in config.h and both sets -must all be greater than zero. */ +/* Newline and \R settings, for use in compile contexts. The newline values +must be kept in step with values set in config.h and both sets must all be +greater than zero. */ #define PCRE2_NEWLINE_CR 1 #define PCRE2_NEWLINE_LF 2 @@ -193,32 +193,33 @@ must all be greater than zero. */ #define PCRE2_ERROR_UTF32_ERR1 (-27) #define PCRE2_ERROR_UTF32_ERR2 (-28) -/* Error codes for pcre2[_dfa]_match() */ +/* Error codes for pcre2[_dfa]_match(), substring extraction functions, and +context functions. */ -#define PCRE2_ERROR_BADCOUNT (-29) -#define PCRE2_ERROR_BADENDIANNESS (-30) -#define PCRE2_ERROR_BADLENGTH (-31) -#define PCRE2_ERROR_BADMAGIC (-32) -#define PCRE2_ERROR_BADMODE (-33) -#define PCRE2_ERROR_BADOFFSET (-34) -#define PCRE2_ERROR_BADOPTION (-35) -#define PCRE2_ERROR_BADUTFOFFSET (-36) -#define PCRE2_ERROR_CALLOUT (-37) /* Never used by PCRE2 itself */ -#define PCRE2_ERROR_DFA_BADRESTART (-38) -#define PCRE2_ERROR_DFA_RECURSE (-39) -#define PCRE2_ERROR_DFA_UCOND (-40) -#define PCRE2_ERROR_DFA_UITEM (-41) -#define PCRE2_ERROR_DFA_UMLIMIT (-42) -#define PCRE2_ERROR_DFA_WSSIZE (-43) -#define PCRE2_ERROR_INTERNAL (-44) -#define PCRE2_ERROR_JIT_BADOPTION (-45) -#define PCRE2_ERROR_JIT_STACKLIMIT (-46) -#define PCRE2_ERROR_MATCHLIMIT (-47) -#define PCRE2_ERROR_NOMEMORY (-48) -#define PCRE2_ERROR_NOSUBSTRING (-49) -#define PCRE2_ERROR_NULL (-50) -#define PCRE2_ERROR_RECURSELOOP (-51) -#define PCRE2_ERROR_RECURSIONLIMIT (-52) +#define PCRE2_ERROR_BADDATA (-29) +#define PCRE2_ERROR_BADLENGTH (-30) +#define PCRE2_ERROR_BADMAGIC (-31) +#define PCRE2_ERROR_BADMODE (-32) +#define PCRE2_ERROR_BADOFFSET (-33) +#define PCRE2_ERROR_BADOPTION (-34) +#define PCRE2_ERROR_BADUTFOFFSET (-35) +#define PCRE2_ERROR_CALLOUT (-36) /* Never used by PCRE2 itself */ +#define PCRE2_ERROR_DFA_BADRESTART (-37) +#define PCRE2_ERROR_DFA_RECURSE (-38) +#define PCRE2_ERROR_DFA_UCOND (-39) +#define PCRE2_ERROR_DFA_UITEM (-40) +#define PCRE2_ERROR_DFA_WSSIZE (-41) +#define PCRE2_ERROR_INTERNAL (-42) +#define PCRE2_ERROR_JIT_BADOPTION (-43) +#define PCRE2_ERROR_JIT_STACKLIMIT (-44) +#define PCRE2_ERROR_MATCHLIMIT (-45) +#define PCRE2_ERROR_NOMEMORY (-46) +#define PCRE2_ERROR_NOSUBSTRING (-47) +#define PCRE2_ERROR_NOUNIQUESUBSTRING (-48) +#define PCRE2_ERROR_NULL (-49) +#define PCRE2_ERROR_RECURSELOOP (-50) +#define PCRE2_ERROR_RECURSIONLIMIT (-51) +#define PCRE2_ERROR_UNSET (-52) /* Request types for pcre2_pattern_info() */ @@ -257,8 +258,8 @@ must all be greater than zero. */ #define PCRE2_CONFIG_PARENSLIMIT 7 #define PCRE2_CONFIG_RECURSIONLIMIT 5 #define PCRE2_CONFIG_STACKRECURSE 8 -#define PCRE2_CONFIG_UNICODE_VERSION 9 -#define PCRE2_CONFIG_UTF 10 +#define PCRE2_CONFIG_UNICODE 9 +#define PCRE2_CONFIG_UNICODE_VERSION 10 #define PCRE2_CONFIG_VERSION 11 /* Types for code units in patterns and subject strings. */ @@ -271,12 +272,14 @@ typedef const PCRE2_UCHAR8 *PCRE2_SPTR8; typedef const PCRE2_UCHAR16 *PCRE2_SPTR16; typedef const PCRE2_UCHAR32 *PCRE2_SPTR32; -/* Offsets in the pattern (for errors) and in the subject (after a match) are -unsigned 32-bit numbers. We also define a value to indicate "unset" in the -offset vector (ovector). */ +/* The PCRE2_SIZE type is used for all string lengths and offsets in PCRE2, +including pattern offsets for errors and subject offsets after a match. We +define special values to indicate zero-terminated strings and unset offsets in +the offset vector (ovector). */ -#define PCRE2_OFFSET PCRE2_UCHAR32 -#define PCRE2_UNSET (~(PCRE2_OFFSET)0) +#define PCRE2_SIZE size_t +#define PCRE2_ZERO_TERMINATED (~(PCRE2_SIZE)0) +#define PCRE2_UNSET (~(PCRE2_SIZE)0) /* Generic types for opaque structures and JIT callback functions. These declarations are defined in a macro that is expanded for each width later. */ @@ -311,22 +314,20 @@ versions are generated from this macro below. */ #define PCRE2_STRUCTURE_LIST \ typedef struct pcre2_callout_block { \ - int version; /* Identifies version of block */ \ + uint32_t version; /* Identifies version of block */ \ /* ------------------------ Version 0 ------------------------------- */ \ uint32_t callout_number; /* Number compiled into pattern */ \ - PCRE2_OFFSET *offset_vector; /* The offset vector */ \ - PCRE2_SPTR subject; /* The subject being matched */ \ - size_t subject_length; /* The length of the subject */ \ - PCRE2_OFFSET start_match; /* Offset to start of this match attempt */ \ - PCRE2_OFFSET current_position; /* Where we currently are in the subject */ \ uint32_t capture_top; /* Max current capture */ \ uint32_t capture_last; /* Most recently closed capture */ \ void *callout_data; /* Data passed in with the call */ \ - /* ------------------- Added for Version 1 -------------------------- */ \ - PCRE2_OFFSET pattern_position; /* Offset to next item in the pattern */ \ - PCRE2_OFFSET next_item_length; /* Length of next item in the pattern */ \ - /* ------------------- Added for Version 2 -------------------------- */ \ - PCRE2_SPTR mark; /* Pointer to current mark or NULL */ \ + PCRE2_SIZE *offset_vector; /* The offset vector */ \ + PCRE2_SPTR mark; /* Pointer to current mark or NULL */ \ + PCRE2_SPTR subject; /* The subject being matched */ \ + PCRE2_SIZE subject_length; /* The length of the subject */ \ + PCRE2_SIZE start_match; /* Offset to start of this match attempt */ \ + PCRE2_SIZE current_position; /* Where we currently are in the subject */ \ + PCRE2_SIZE pattern_position; /* Offset to next item in the pattern */ \ + PCRE2_SIZE next_item_length; /* Length of next item in the pattern */ \ /* ------------------------------------------------------------------ */ \ } pcre2_callout_block; @@ -336,7 +337,7 @@ expanded for each width below. Start with functions that give general information. */ #define PCRE2_GENERAL_INFO_FUNCTIONS \ -PCRE2_EXP_DECL int pcre2_config(int, void *, size_t); +PCRE2_EXP_DECL int pcre2_config(uint32_t, void *); /* Functions for manipulating contexts. */ @@ -346,7 +347,7 @@ PCRE2_EXP_DECL \ pcre2_general_context *pcre2_general_context_copy(pcre2_general_context *); \ PCRE2_EXP_DECL \ pcre2_general_context *pcre2_general_context_create( \ - void *(*)(size_t, void *), \ + void *(*)(PCRE2_SIZE, void *), \ void (*)(void *, void *), void *); \ PCRE2_EXP_DECL void pcre2_general_context_free(pcre2_general_context *); @@ -356,12 +357,10 @@ PCRE2_EXP_DECL \ PCRE2_EXP_DECL \ pcre2_compile_context *pcre2_compile_context_create(pcre2_general_context *);\ PCRE2_EXP_DECL void pcre2_compile_context_free(pcre2_compile_context *); \ -PCRE2_EXP_DECL int pcre2_set_bsr_compile(pcre2_compile_context *, \ - uint32_t); \ +PCRE2_EXP_DECL int pcre2_set_bsr(pcre2_compile_context *, uint32_t); \ PCRE2_EXP_DECL int pcre2_set_character_tables(pcre2_compile_context *, \ const unsigned char *); \ -PCRE2_EXP_DECL int pcre2_set_newline_compile(pcre2_compile_context *, \ - uint32_t); \ +PCRE2_EXP_DECL int pcre2_set_newline(pcre2_compile_context *, uint32_t); \ PCRE2_EXP_DECL int pcre2_set_parens_nest_limit(pcre2_compile_context *, \ uint32_t); \ PCRE2_EXP_DECL int pcre2_set_compile_recursion_guard(\ @@ -373,18 +372,14 @@ PCRE2_EXP_DECL \ PCRE2_EXP_DECL \ pcre2_match_context *pcre2_match_context_create(pcre2_general_context *); \ PCRE2_EXP_DECL void pcre2_match_context_free(pcre2_match_context *); \ -PCRE2_EXP_DECL int pcre2_set_bsr_match(pcre2_match_context *, \ - uint32_t); \ PCRE2_EXP_DECL int pcre2_set_callout(pcre2_match_context *, \ int (*)(pcre2_callout_block *), void *); \ PCRE2_EXP_DECL int pcre2_set_match_limit(pcre2_match_context *, \ uint32_t); \ -PCRE2_EXP_DECL int pcre2_set_newline_match(pcre2_match_context *, \ - uint32_t); \ PCRE2_EXP_DECL int pcre2_set_recursion_limit(pcre2_match_context *, \ uint32_t); \ PCRE2_EXP_DECL int pcre2_set_recursion_memory_management( \ - pcre2_match_context *, void *(*)(size_t, void *), \ + pcre2_match_context *, void *(*)(PCRE2_SIZE, void *), \ void (*)(void *, void *), void *); @@ -392,8 +387,8 @@ PCRE2_EXP_DECL int pcre2_set_recursion_memory_management( \ #define PCRE2_COMPILE_FUNCTIONS \ PCRE2_EXP_DECL \ - pcre2_code *pcre2_compile(PCRE2_SPTR, int, uint32_t, \ - int *, PCRE2_OFFSET *, pcre2_compile_context *); \ + pcre2_code *pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, \ + int *, PCRE2_SIZE *, pcre2_compile_context *); \ PCRE2_EXP_DECL void pcre2_code_free(pcre2_code *); @@ -408,65 +403,62 @@ PCRE2_EXP_DECL int pcre2_pattern_info(const pcre2_code *, uint32_t, \ #define PCRE2_MATCH_FUNCTIONS \ PCRE2_EXP_DECL \ - pcre2_match_data *pcre2_match_data_create(uint32_t, \ - pcre2_general_context *); \ + pcre2_match_data *pcre2_match_data_create(uint32_t, \ + pcre2_general_context *); \ PCRE2_EXP_DECL \ - pcre2_match_data *pcre2_match_data_create_from_pattern(pcre2_code *, \ - pcre2_general_context *); \ -PCRE2_EXP_DECL int pcre2_dfa_match(const pcre2_code *, \ - PCRE2_SPTR, int, PCRE2_OFFSET, uint32_t, \ - pcre2_match_data *, pcre2_match_context *, int *, \ - size_t); \ -PCRE2_EXP_DECL int pcre2_match(const pcre2_code *, \ - PCRE2_SPTR, int, PCRE2_OFFSET, uint32_t, \ - pcre2_match_data *, pcre2_match_context *); \ -PCRE2_EXP_DECL void pcre2_match_data_free(pcre2_match_data *); \ -PCRE2_EXP_DECL PCRE2_OFFSET pcre2_get_leftchar(pcre2_match_data *); \ -PCRE2_EXP_DECL PCRE2_SPTR pcre2_get_mark(pcre2_match_data *); \ -PCRE2_EXP_DECL uint32_t pcre2_get_ovector_count(pcre2_match_data *); \ -PCRE2_EXP_DECL PCRE2_OFFSET *pcre2_get_ovector_pointer(pcre2_match_data *); \ -PCRE2_EXP_DECL PCRE2_OFFSET pcre2_get_rightchar(pcre2_match_data *); \ -PCRE2_EXP_DECL PCRE2_OFFSET pcre2_get_startchar(pcre2_match_data *); + pcre2_match_data *pcre2_match_data_create_from_pattern(pcre2_code *, \ + pcre2_general_context *); \ +PCRE2_EXP_DECL int pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, \ + PCRE2_SIZE, PCRE2_SIZE, uint32_t, \ + pcre2_match_data *, pcre2_match_context *, int *, \ + PCRE2_SIZE); \ +PCRE2_EXP_DECL int pcre2_match(const pcre2_code *, \ + PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \ + pcre2_match_data *, pcre2_match_context *); \ +PCRE2_EXP_DECL void pcre2_match_data_free(pcre2_match_data *); \ +PCRE2_EXP_DECL PCRE2_SPTR pcre2_get_mark(pcre2_match_data *); \ +PCRE2_EXP_DECL uint32_t pcre2_get_ovector_count(pcre2_match_data *); \ +PCRE2_EXP_DECL PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *); \ +PCRE2_EXP_DECL PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *); /* Convenience functions for handling matched substrings. */ #define PCRE2_SUBSTRING_FUNCTIONS \ PCRE2_EXP_DECL int pcre2_substring_copy_byname(pcre2_match_data *, \ - PCRE2_SPTR, PCRE2_UCHAR *, size_t); \ + PCRE2_SPTR, PCRE2_UCHAR *, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_copy_bynumber(pcre2_match_data *, \ - int, PCRE2_UCHAR *, size_t); \ + unsigned int, PCRE2_UCHAR *, PCRE2_SIZE *); \ PCRE2_EXP_DECL void pcre2_substring_free(PCRE2_UCHAR *); \ PCRE2_EXP_DECL int pcre2_substring_get_byname(pcre2_match_data *, \ - PCRE2_SPTR, PCRE2_UCHAR **); \ + PCRE2_SPTR, PCRE2_UCHAR **, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_get_bynumber(pcre2_match_data *, \ - int, PCRE2_UCHAR **); \ + unsigned int, PCRE2_UCHAR **, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_length_byname(pcre2_match_data *, \ - PCRE2_SPTR); \ + PCRE2_SPTR, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_length_bynumber(pcre2_match_data *, \ - int); \ + unsigned int, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_nametable_scan(const pcre2_code *, \ PCRE2_SPTR, PCRE2_SPTR *, PCRE2_SPTR *); \ PCRE2_EXP_DECL int pcre2_substring_number_from_name(\ const pcre2_code *, PCRE2_SPTR); \ PCRE2_EXP_DECL void pcre2_substring_list_free(PCRE2_SPTR *); \ PCRE2_EXP_DECL int pcre2_substring_list_get(pcre2_match_data *, \ - PCRE2_UCHAR ***, size_t **); + PCRE2_UCHAR ***, PCRE2_SIZE **); /* Functions for JIT processing */ #define PCRE2_JIT_FUNCTIONS \ -PCRE2_EXP_DECL int pcre2_jit_compile(pcre2_code *, uint32_t, \ - pcre2_match_context *); \ +PCRE2_EXP_DECL int pcre2_jit_compile(pcre2_code *, uint32_t); \ PCRE2_EXP_DECL int pcre2_jit_match(const pcre2_code *, \ - PCRE2_SPTR, int, PCRE2_OFFSET, uint32_t, \ + PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, uint32_t, \ pcre2_match_data *, pcre2_match_context *, \ pcre2_jit_stack *); \ PCRE2_EXP_DECL void pcre2_jit_free_unused_memory(pcre2_general_context *);\ PCRE2_EXP_DECL \ - pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *, \ - size_t, size_t); \ + pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *, \ + PCRE2_SIZE, PCRE2_SIZE); \ PCRE2_EXP_DECL void pcre2_jit_stack_assign(const pcre2_code *, \ pcre2_jit_callback, void *); \ PCRE2_EXP_DECL void pcre2_jit_stack_free(pcre2_jit_stack *); @@ -475,7 +467,7 @@ PCRE2_EXP_DECL void pcre2_jit_stack_free(pcre2_jit_stack *); /* Other miscellaneous functions. */ #define PCRE2_OTHER_FUNCTIONS \ -PCRE2_EXP_DECL int pcre2_get_error_message(int, PCRE2_UCHAR *, size_t); \ +PCRE2_EXP_DECL int pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \ PCRE2_EXP_DECL \ const uint8_t *pcre2_maketables(pcre2_general_context *); \ @@ -532,17 +524,15 @@ pcre2_compile are called by application code. */ #define pcre2_general_context_create PCRE2_SUFFIX(pcre2_general_context_create_) #define pcre2_general_context_free PCRE2_SUFFIX(pcre2_general_context_free_) #define pcre2_get_error_message PCRE2_SUFFIX(pcre2_get_error_message_) -#define pcre2_get_leftchar PCRE2_SUFFIX(pcre2_get_leftchar_) #define pcre2_get_mark PCRE2_SUFFIX(pcre2_get_mark_) #define pcre2_get_ovector_pointer PCRE2_SUFFIX(pcre2_get_ovector_pointer_) #define pcre2_get_ovector_count PCRE2_SUFFIX(pcre2_get_ovector_count_) -#define pcre2_get_rightchar PCRE2_SUFFIX(pcre2_get_rightchar_) #define pcre2_get_startchar PCRE2_SUFFIX(pcre2_get_startchar_) #define pcre2_jit_compile PCRE2_SUFFIX(pcre2_jit_compile_) #define pcre2_jit_match PCRE2_SUFFIX(pcre2_jit_match_) #define pcre2_jit_free_unused_memory PCRE2_SUFFIX(pcre2_jit_free_unused_memory_) -#define pcre2_jit_stack_alloc PCRE2_SUFFIX(pcre2_jit_stack_alloc_) #define pcre2_jit_stack_assign PCRE2_SUFFIX(pcre2_jit_stack_assign_) +#define pcre2_jit_stack_create PCRE2_SUFFIX(pcre2_jit_stack_create_) #define pcre2_jit_stack_free PCRE2_SUFFIX(pcre2_jit_stack_free_) #define pcre2_maketables PCRE2_SUFFIX(pcre2_maketables_) #define pcre2_match_context_copy PCRE2_SUFFIX(pcre2_match_context_copy_) @@ -552,14 +542,12 @@ pcre2_compile are called by application code. */ #define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_) #define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_) #define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_) -#define pcre2_set_bsr_compile PCRE2_SUFFIX(pcre2_set_bsr_compile_) -#define pcre2_set_bsr_match PCRE2_SUFFIX(pcre2_set_bsr_match_) +#define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_) #define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_) #define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_) #define pcre2_set_compile_recursion_guard PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_) #define pcre2_set_match_limit PCRE2_SUFFIX(pcre2_set_match_limit_) -#define pcre2_set_newline_compile PCRE2_SUFFIX(pcre2_set_newline_compile_) -#define pcre2_set_newline_match PCRE2_SUFFIX(pcre2_set_newline_match_) +#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_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_) #define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_) @@ -621,24 +609,27 @@ PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS #undef PCRE2_OTHER_FUNCTIONS #undef PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS -/* Re-define PCRE2_SUFFIX to use the external width value, if defined. -Otherwise, undefine the other macros and make PCRE2_SUFFIX a no-op, to reduce -confusion. */ +/* PCRE2_CODE_UNIT_WIDTH must be defined. If it is 8, 16, or 32, redefine +PCRE2_SUFFIX to use it. If it is 0, undefine the other macros and make +PCRE2_SUFFIX a no-op. Otherwise, generate an error. */ #undef PCRE2_SUFFIX -#ifdef PCRE2_CODE_UNIT_WIDTH -#if PCRE2_CODE_UNIT_WIDTH != 8 && \ - PCRE2_CODE_UNIT_WIDTH != 16 && \ - PCRE2_CODE_UNIT_WIDTH != 32 -#error PCRE2_CODE_UNIT_WIDTH must be 8, 16, or 32 -#endif +#ifndef PCRE2_CODE_UNIT_WIDTH +#error PCRE2_CODE_UNIT_WIDTH must be defined before including pcre2.h. +#error Use 8, 16, or 32; or 0 for a multi-width application. +#else /* PCRE2_CODE_UNIT_WIDTH is defined */ +#if PCRE2_CODE_UNIT_WIDTH == 8 || \ + PCRE2_CODE_UNIT_WIDTH == 16 || \ + PCRE2_CODE_UNIT_WIDTH == 32 #define PCRE2_SUFFIX(a) PCRE2_GLUE(a, PCRE2_CODE_UNIT_WIDTH) -#else +#elif PCRE2_CODE_UNIT_WIDTH == 0 #undef PCRE2_JOIN #undef PCRE2_GLUE #define PCRE2_SUFFIX(a) a +#else +#error PCRE2_CODE_UNIT_WIDTH must be 0, 8, 16, or 32. #endif - +#endif /* PCRE2_CODE_UNIT_WIDTH is defined */ #ifdef __cplusplus } /* extern "C" */ diff --git a/src/pcre2.h.in b/src/pcre2.h.in index bbbf469..3fd32d9 100644 --- a/src/pcre2.h.in +++ b/src/pcre2.h.in @@ -457,7 +457,7 @@ PCRE2_EXP_DECL int pcre2_jit_match(const pcre2_code *, \ pcre2_jit_stack *); \ PCRE2_EXP_DECL void pcre2_jit_free_unused_memory(pcre2_general_context *);\ PCRE2_EXP_DECL \ - pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *, \ + pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *, \ PCRE2_SIZE, PCRE2_SIZE); \ PCRE2_EXP_DECL void pcre2_jit_stack_assign(const pcre2_code *, \ pcre2_jit_callback, void *); \ @@ -531,8 +531,8 @@ pcre2_compile are called by application code. */ #define pcre2_jit_compile PCRE2_SUFFIX(pcre2_jit_compile_) #define pcre2_jit_match PCRE2_SUFFIX(pcre2_jit_match_) #define pcre2_jit_free_unused_memory PCRE2_SUFFIX(pcre2_jit_free_unused_memory_) -#define pcre2_jit_stack_alloc PCRE2_SUFFIX(pcre2_jit_stack_alloc_) #define pcre2_jit_stack_assign PCRE2_SUFFIX(pcre2_jit_stack_assign_) +#define pcre2_jit_stack_create PCRE2_SUFFIX(pcre2_jit_stack_create_) #define pcre2_jit_stack_free PCRE2_SUFFIX(pcre2_jit_stack_free_) #define pcre2_maketables PCRE2_SUFFIX(pcre2_maketables_) #define pcre2_match_context_copy PCRE2_SUFFIX(pcre2_match_context_copy_) diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c index c0dbe8a..b85cd5a 100644 --- a/src/pcre2_compile.c +++ b/src/pcre2_compile.c @@ -304,8 +304,8 @@ static const short int escapes[] = { #else /* This is the "abnormal" table for EBCDIC systems without UTF-8 support. -It runs from 'a' to '9'. For some minimal testing of EBCDIC features, the code -is sometimes compiled on an ASCII system. In this case, we must not use CHAR_a +It runs from 'a' to '9'. For some minimal testing of EBCDIC features, the code +is sometimes compiled on an ASCII system. In this case, we must not use CHAR_a because it is defined as 'a', which of course picks up the ASCII value. */ #if 'a' == 0x81 /* Check for a real EBCDIC environment */ @@ -7786,7 +7786,7 @@ if (cb.hwm > cb.start_workspace) NULL to indicate that forward references have been filled in. */ if (cb.workspace_size > COMPILE_WORK_SIZE) - ccontext->memctl.free((void *)cb.start_workspace, + ccontext->memctl.free((void *)cb.start_workspace, ccontext->memctl.memory_data); cb.start_workspace = NULL; diff --git a/src/pcre2_error.c b/src/pcre2_error.c index d1a253d..45b25cd 100644 --- a/src/pcre2_error.c +++ b/src/pcre2_error.c @@ -221,7 +221,7 @@ static const char match_error_texts[] = "match limit exceeded\0" "no more memory\0" "unknown or unset substring\0" - "non-unique substring name\0" + "non-unique substring name\0" "NULL argument passed\0" /* 50 */ "nested recursion at the same subject position\0" diff --git a/src/pcre2_jit_misc.c b/src/pcre2_jit_misc.c index 2b6da8b..41c2d4c 100644 --- a/src/pcre2_jit_misc.c +++ b/src/pcre2_jit_misc.c @@ -97,7 +97,7 @@ sljit_free_unused_memory_exec(); *************************************************/ PCRE2_EXP_DEFN pcre2_jit_stack * PCRE2_CALL_CONVENTION -pcre2_jit_stack_alloc(pcre2_general_context *gcontext, size_t startsize, +pcre2_jit_stack_create(pcre2_general_context *gcontext, size_t startsize, size_t maxsize) { #ifndef SUPPORT_JIT diff --git a/src/pcre2_jit_test.c b/src/pcre2_jit_test.c index 54dba24..68e822c 100644 --- a/src/pcre2_jit_test.c +++ b/src/pcre2_jit_test.c @@ -854,7 +854,7 @@ static pcre2_jit_stack_8 *stack8; static pcre2_jit_stack_8 *getstack8(void) { if (!stack8) - stack8 = pcre2_jit_stack_alloc_8(NULL, 1, 1024 * 1024); + stack8 = pcre2_jit_stack_create_8(NULL, 1, 1024 * 1024); return stack8; } @@ -877,7 +877,7 @@ static pcre2_jit_stack_16 *stack16; static pcre2_jit_stack_16 *getstack16(void) { if (!stack16) - stack16 = pcre2_jit_stack_alloc_16(NULL, 1, 1024 * 1024); + stack16 = pcre2_jit_stack_create_16(NULL, 1, 1024 * 1024); return stack16; } @@ -900,7 +900,7 @@ static pcre2_jit_stack_32 *stack32; static pcre2_jit_stack_32 *getstack32(void) { if (!stack32) - stack32 = pcre2_jit_stack_alloc_32(NULL, 1, 1024 * 1024); + stack32 = pcre2_jit_stack_create_32(NULL, 1, 1024 * 1024); return stack32; } diff --git a/src/pcre2_substring.c b/src/pcre2_substring.c index 3faecd0..c4d67c1 100644 --- a/src/pcre2_substring.c +++ b/src/pcre2_substring.c @@ -446,7 +446,7 @@ while (top > bot) if (PRIV(strcmp)(stringname, (last + entrysize + IMM2_SIZE)) != 0) break; last += entrysize; } - if (firstptr == NULL) + if (firstptr == NULL) return (first == last)? (int)GET2(entry, 0) : PCRE2_ERROR_NOUNIQUESUBSTRING; *firstptr = first; *lastptr = last; diff --git a/src/pcre2grep.c b/src/pcre2grep.c index ee374de..72259e8 100644 --- a/src/pcre2grep.c +++ b/src/pcre2grep.c @@ -3115,7 +3115,7 @@ for (fn = pattern_files; fn != NULL; fn = fn->next) #ifdef SUPPORT_PCRE2GREP_JIT if (use_jit) - jit_stack = pcre2_jit_stack_alloc(NULL, 32*1024, 1024*1024); + jit_stack = pcre2_jit_stack_create(NULL, 32*1024, 1024*1024); #endif for (j = 1, cp = patterns; cp != NULL; j++, cp = cp->next) diff --git a/src/pcre2test.c b/src/pcre2test.c index 0c971c7..3850efd 100644 --- a/src/pcre2test.c +++ b/src/pcre2test.c @@ -88,7 +88,7 @@ that first, falling back to readline/readline.h. */ #endif #endif -/* Put the test for interactive input into a macro so that it can be changed if +/* Put the test for interactive input into a macro so that it can be changed if required for different environments. */ #define INTERACTIVE(f) isatty(fileno(f)) @@ -822,13 +822,13 @@ are supported. */ a = pcre2_jit_match_32(G(b,32),(PCRE2_SPTR32)c,d,e,f,G(g,32),G(h,32), \ (pcre2_jit_stack_32 *)i) -#define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ +#define PCRE2_JIT_STACK_CREATE(a,b,c,d) \ if (test_mode == PCRE8_MODE) \ - a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_8(b,c,d); \ + a = (PCRE2_JIT_STACK *)pcre2_jit_stack_create_8(b,c,d); \ else if (test_mode == PCRE16_MODE) \ - a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_16(b,c,d); \ + a = (PCRE2_JIT_STACK *)pcre2_jit_stack_create_16(b,c,d); \ else \ - a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_32(b,c,d); + a = (PCRE2_JIT_STACK *)pcre2_jit_stack_create_32(b,c,d); #define PCRE2_JIT_STACK_ASSIGN(a,b,c) \ if (test_mode == PCRE8_MODE) \ @@ -1200,11 +1200,11 @@ the three different cases. */ a = G(pcre2_jit_match_,BITTWO)(G(b,BITTWO),(G(PCRE2_SPTR,BITTWO))c,d,e,f, \ G(g,BITTWO),G(h,BITTWO),(G(pcre2_jit_stack_,BITTWO) *)i) -#define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ +#define PCRE2_JIT_STACK_CREATE(a,b,c,d) \ if (test_mode == G(G(PCRE,BITONE),_MODE)) \ - a = (PCRE2_JIT_STACK *)G(pcre2_jit_stack_alloc_,BITONE)(b,c,d); \ + a = (PCRE2_JIT_STACK *)G(pcre2_jit_stack_create_,BITONE)(b,c,d); \ else \ - a = (PCRE2_JIT_STACK *)G(pcre2_jit_stack_alloc_,BITTWO)(b,c,d); \ + a = (PCRE2_JIT_STACK *)G(pcre2_jit_stack_create_,BITTWO)(b,c,d); \ #define PCRE2_JIT_STACK_ASSIGN(a,b,c) \ if (test_mode == G(G(PCRE,BITONE),_MODE)) \ @@ -1447,8 +1447,8 @@ the three different cases. */ #define PCRE2_JIT_MATCH(a,b,c,d,e,f,g,h,(pcre2_jit_stack_8 *)i) \ a = pcre2_jit_match_8(G(b,8),(PCRE2_SPTR8)c,d,e,f,G(g,8),G(h,8), \ (pcre2_jit_stack_8 *)i) -#define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ - a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_8(b,c,d); +#define PCRE2_JIT_STACK_CREATE(a,b,c,d) \ + a = (PCRE2_JIT_STACK *)pcre2_jit_stack_create_8(b,c,d); #define PCRE2_JIT_STACK_ASSIGN(a,b,c) \ pcre2_jit_stack_assign_8(G(a,8),(pcre2_jit_callback_8)b,c); #define PCRE2_JIT_STACK_FREE(a) pcre2_jit_stack_free_8((pcre2_jit_stack_8 *)a); @@ -1526,8 +1526,8 @@ the three different cases. */ #define PCRE2_JIT_MATCH(a,b,c,d,e,f,g,h,i) \ a = pcre2_jit_match_16(G(b,16),(PCRE2_SPTR16)c,d,e,f,G(g,16),G(h,16), \ (pcre2_jit_stack_16 *)i) -#define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ - a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_16(b,c,d); +#define PCRE2_JIT_STACK_CREATE(a,b,c,d) \ + a = (PCRE2_JIT_STACK *)pcre2_jit_stack_create_16(b,c,d); #define PCRE2_JIT_STACK_ASSIGN(a,b,c) \ pcre2_jit_stack_assign_16(G(a,16),(pcre2_jit_callback_16)b,c); #define PCRE2_JIT_STACK_FREE(a) pcre2_jit_stack_free_16((pcre2_jit_stack_16 *)a); @@ -1605,8 +1605,8 @@ the three different cases. */ #define PCRE2_JIT_MATCH(a,b,c,d,e,f,g,h,i) \ a = pcre2_jit_match_32(G(b,32),(PCRE2_SPTR32)c,d,e,f,G(g,32),G(h,32), \ (pcre2_jit_stack_32 *)i) -#define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ - a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_32(b,c,d); +#define PCRE2_JIT_STACK_CREATE(a,b,c,d) \ + a = (PCRE2_JIT_STACK *)pcre2_jit_stack_create_32(b,c,d); #define PCRE2_JIT_STACK_ASSIGN(a,b,c) \ pcre2_jit_stack_assign_32(G(a,32),(pcre2_jit_callback_32)b,c); #define PCRE2_JIT_STACK_FREE(a) pcre2_jit_stack_free_32((pcre2_jit_stack_32 *)a); @@ -3681,7 +3681,7 @@ if (!decode_modifiers(p, CTX_PAT, &pat_patctl, NULL)) return PR_SKIP; /* Assume full JIT compile for jitverify and/or jitfast if nothing else was specified. */ -if (pat_patctl.jit == 0 && +if (pat_patctl.jit == 0 && (pat_patctl.control & (CTL_JITVERIFY|CTL_JITFAST)) != 0) pat_patctl.jit = 7; utf = (pat_patctl.options & PCRE2_UTF) != 0; @@ -3996,7 +3996,7 @@ for (;;) if ((pat_patctl.control & CTL_JITFAST) != 0) PCRE2_JIT_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, dat_datctl.options, match_data, dat_context, jit_stack); - else + else PCRE2_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, dat_datctl.options, match_data, dat_context); @@ -4637,7 +4637,7 @@ if (dat_datctl.jitstack != 0) if (dat_datctl.jitstack != jit_stack_size) { PCRE2_JIT_STACK_FREE(jit_stack); - PCRE2_JIT_STACK_ALLOC(jit_stack, NULL, 1, dat_datctl.jitstack * 1024); + PCRE2_JIT_STACK_CREATE(jit_stack, NULL, 1, dat_datctl.jitstack * 1024); jit_stack_size = dat_datctl.jitstack; } PCRE2_JIT_STACK_ASSIGN(compiled_code, jit_callback, jit_stack); @@ -4690,10 +4690,10 @@ for (gmatched = 0;; gmatched++) PCRE2_SIZE ovecsave[2]; ovector = FLD(match_data, ovector); - + /* When matching is via pcre2_match(), we will detect the use of JIT via the stack callback function. */ - + jit_was_used = (pat_patctl.control & CTL_JITFAST) != 0; /* After the first time round a global loop, save the current ovector[0,1] so @@ -4722,7 +4722,7 @@ for (gmatched = 0;; gmatched++) } if (dfa_workspace == NULL) dfa_workspace = (int *)malloc(DFA_WS_DIMENSION*sizeof(int)); - start_time = clock(); + start_time = clock(); for (i = 0; i < timeitm; i++) { PCRE2_DFA_MATCH(capcount, compiled_code, pp, ulen, @@ -4730,7 +4730,7 @@ for (gmatched = 0;; gmatched++) dat_context, dfa_workspace, DFA_WS_DIMENSION); } } - + else if ((pat_patctl.control & CTL_JITFAST) != 0) { start_time = clock(); @@ -4740,9 +4740,9 @@ for (gmatched = 0;; gmatched++) dat_datctl.offset, dat_datctl.options | g_notempty, match_data, dat_context, jit_stack); } - } - - else + } + + else { start_time = clock(); for (i = 0; i < timeitm; i++) @@ -4751,7 +4751,7 @@ for (gmatched = 0;; gmatched++) dat_datctl.offset, dat_datctl.options | g_notempty, match_data, dat_context); } - } + } total_match_time += (time_taken = clock() - start_time); fprintf(outfile, "Match time %.4f milliseconds\n", (((double)time_taken * 1000.0) / (double)timeitm) / @@ -4809,7 +4809,7 @@ for (gmatched = 0;; gmatched++) if ((pat_patctl.control & CTL_JITFAST) != 0) PCRE2_JIT_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, dat_datctl.options | g_notempty, match_data, dat_context, jit_stack); - else + else PCRE2_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, dat_datctl.options | g_notempty, match_data, dat_context); if (capcount == 0) diff --git a/testdata/testoutput16 b/testdata/testoutput16 index 1631e9e..ec9ba59 100644 --- a/testdata/testoutput16 +++ b/testdata/testoutput16 @@ -245,6 +245,11 @@ Minimum match limit = 6 0: aabbccddee (JIT) 1: aa 2: cc + 3: ee + aabbccddee\=jitstack=1 + 0: aabbccddee (JIT) + 1: aa + 2: cc 3: ee /(a+)*zz/