From 4e61019ffebd4fc59994bec073b4d34f64093dc6 Mon Sep 17 00:00:00 2001 From: "Philip.Hazel" Date: Mon, 23 Mar 2015 15:52:08 +0000 Subject: [PATCH] Implement pcre2_callout_enumerate(). --- ChangeLog | 4 +- Makefile.am | 2 + doc/html/index.html | 3 + doc/html/pcre2_callout_enumerate.html | 62 ++++ doc/html/pcre2api.html | 117 +++++--- doc/html/pcre2callout.html | 148 +++++++-- doc/html/pcre2compat.html | 14 +- doc/html/pcre2pattern.html | 79 +++-- doc/html/pcre2syntax.html | 12 +- doc/html/pcre2test.html | 95 ++++-- doc/index.html.src | 3 + doc/pcre2.txt | 392 +++++++++++++++--------- doc/pcre2_callout_enumerate.3 | 50 ++++ doc/pcre2api.3 | 58 +++- doc/pcre2callout.3 | 66 ++++- doc/pcre2test.1 | 10 +- doc/pcre2test.txt | 412 ++++++++++++++------------ src/pcre2.h.in | 31 +- src/pcre2_pattern_info.c | 177 +++++++++++ src/pcre2test.c | 179 ++++++++--- testdata/testinput2 | 6 +- testdata/testoutput2 | 16 +- 22 files changed, 1403 insertions(+), 533 deletions(-) create mode 100644 doc/html/pcre2_callout_enumerate.html create mode 100644 doc/pcre2_callout_enumerate.3 diff --git a/ChangeLog b/ChangeLog index 4938a94..2edaed6 100644 --- a/ChangeLog +++ b/ChangeLog @@ -10,7 +10,9 @@ Version 10.20 xx-xx-2015 3. The invalid pattern (?(?C) has a missing assertion condition at the end. The pcre2_compile() function read past the end of the input before diagnosing an -error. +error. This bug was discovered by the LLVM fuzzer. + +4. Implemented pcre2_callout_enumerate(). Version 10.10 06-March-2015 diff --git a/Makefile.am b/Makefile.am index 2e4e79e..56f93db 100644 --- a/Makefile.am +++ b/Makefile.am @@ -24,6 +24,7 @@ dist_html_DATA = \ doc/html/index.html \ doc/html/pcre2-config.html \ doc/html/pcre2.html \ + doc/html/pcre2_callout_enumerate.html \ doc/html/pcre2_code_free.html \ doc/html/pcre2_compile.html \ doc/html/pcre2_compile_context_copy.html \ @@ -102,6 +103,7 @@ dist_html_DATA = \ dist_man_MANS = \ doc/pcre2-config.1 \ doc/pcre2.3 \ + doc/pcre2_callout_enumerate.3 \ doc/pcre2_code_free.3 \ doc/pcre2_compile.3 \ doc/pcre2_compile_context_copy.3 \ diff --git a/doc/html/index.html b/doc/html/index.html index ec12c6e..ae938fd 100644 --- a/doc/html/index.html +++ b/doc/html/index.html @@ -88,6 +88,9 @@ in the library. + + + diff --git a/doc/html/pcre2_callout_enumerate.html b/doc/html/pcre2_callout_enumerate.html new file mode 100644 index 0000000..8344ead --- /dev/null +++ b/doc/html/pcre2_callout_enumerate.html @@ -0,0 +1,62 @@ + + +pcre2_callout_enumerate specification + + +

pcre2_callout_enumerate man page

+

+Return to the PCRE2 index page. +

+

+This page is part of the PCRE2 HTML documentation. It was generated +automatically from the original man page. If there is any nonsense in it, +please consult the man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre2.h> +

+

+int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *callout_data); +

+
+DESCRIPTION +
+

+This function scans a compiled regular expression and calls the callback() +function for each callout within the pattern. The yield of the function is zero +for success and non-zero otherwise. The arguments are: +

+  code           Points to the compiled pattern
+  callback       The callback function
+  callout_data   User data that is passed to the callback  
+
+The callback() function is passed a pointer to a data block containing +the following fields: +
+  version                Block version number
+  pattern_position       Offset to next item in pattern
+  next_item_length       Length of next item in pattern
+  callout_number         Number for numbered callouts
+  callout_string_offset  Offset to string within pattern
+  callout_string_length  Length of callout string
+  callout_string         Points to callout string or is NULL
+
+The second argument is the callout data that was passed to +pcre2_callout_enumerate(). The callback() function must return zero +for success. Any other value causes the pattern scan to stop, with the value +being passed back as the result of pcre2_callout_enumerate(). +

+

+There is a complete description of the PCRE2 native API in the +pcre2api +page and a description of the POSIX API in the +pcre2posix +page. +

+Return to the PCRE2 index page. +

diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index 685826b..6fbf183 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -35,23 +35,24 @@ please consult the man page, in case the conversion went wrong.
  • JUST-IN-TIME (JIT) COMPILATION
  • LOCALE SUPPORT
  • INFORMATION ABOUT A COMPILED PATTERN -
  • SERIALIZATION AND PRECOMPILING -
  • THE MATCH DATA BLOCK -
  • MATCHING A PATTERN: THE TRADITIONAL FUNCTION -
  • NEWLINE HANDLING WHEN MATCHING -
  • HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS -
  • OTHER INFORMATION ABOUT A MATCH -
  • ERROR RETURNS FROM pcre2_match() -
  • EXTRACTING CAPTURED SUBSTRINGS BY NUMBER -
  • EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS -
  • EXTRACTING CAPTURED SUBSTRINGS BY NAME -
  • CREATING A NEW STRING WITH SUBSTITUTIONS -
  • DUPLICATE SUBPATTERN NAMES -
  • FINDING ALL POSSIBLE MATCHES AT ONE POSITION -
  • MATCHING A PATTERN: THE ALTERNATIVE FUNCTION -
  • SEE ALSO -
  • AUTHOR -
  • REVISION +
  • INFORMATION ABOUT A PATTERN'S CALLOUTS +
  • SERIALIZATION AND PRECOMPILING +
  • THE MATCH DATA BLOCK +
  • MATCHING A PATTERN: THE TRADITIONAL FUNCTION +
  • NEWLINE HANDLING WHEN MATCHING +
  • HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS +
  • OTHER INFORMATION ABOUT A MATCH +
  • ERROR RETURNS FROM pcre2_match() +
  • EXTRACTING CAPTURED SUBSTRINGS BY NUMBER +
  • EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS +
  • EXTRACTING CAPTURED SUBSTRINGS BY NAME +
  • CREATING A NEW STRING WITH SUBSTITUTIONS +
  • DUPLICATE SUBPATTERN NAMES +
  • FINDING ALL POSSIBLE MATCHES AT ONE POSITION +
  • MATCHING A PATTERN: THE ALTERNATIVE FUNCTION +
  • SEE ALSO +
  • AUTHOR +
  • REVISION

    #include <pcre2.h> @@ -291,6 +292,11 @@ document for an overview of all the PCRE2 documentation. int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where);

    +int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); +
    +
    int pcre2_config(uint32_t what, void *where);


    PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES
    @@ -1433,14 +1439,16 @@ can be processed in different locales. int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where);

    -The pcre2_pattern_info() function returns information about a compiled -pattern. The first argument is a pointer to the compiled pattern. The second -argument specifies which piece of information is required, and the third -argument is a pointer to a variable to receive the data. If the third argument -is NULL, the first argument is ignored, and the function returns the size in -bytes of the variable that is required for the information requested. -Otherwise, The yield of the function is zero for success, or one of the -following negative numbers: +The pcre2_pattern_info() function returns general information about a +compiled pattern. For information about callouts, see the +next section. +The first argument for pcre2_pattern_info() is a pointer to the compiled +pattern. The second argument specifies which piece of information is required, +and the third argument is a pointer to a variable to receive the data. If the +third argument is NULL, the first argument is ignored, and the function returns +the size in bytes of the variable that is required for the information +requested. Otherwise, The yield of the function is zero for success, or one of +the following negative numbers: 

       PCRE2_ERROR_NULL           the argument code was NULL
   PCRE2_ERROR_BADMAGIC       the "magic number" was not found
@@ -1719,8 +1727,27 @@ memory in which to place the compiled pattern may be slightly larger than the
 value returned by this option, because there are cases where the code that
 calculates the size has to over-estimate. Processing a pattern with the JIT
 compiler does not alter the value returned by this option.
+
    
+
    INFORMATION ABOUT A PATTERN'S CALLOUTS
    
+
    
+int pcre2_callout_enumerate(const pcre2_code *code,
+  int (*callback)(pcre2_callout_enumerate_block *, void *),
+  void *user_data);
+
    
+
    
+A script language that supports the use of string arguments in callouts might 
+like to scan all the callouts in a pattern before running the match. This can 
+be done by calling pcre2_callout_enumerate(). The first argument is a 
+pointer to a compiled pattern, the second points to a callback function, and
+the third is arbitrary user data. The callback function is called for every
+callout in the pattern in the order in which they appear. Its first argument is
+a pointer to a callout enumeration block, and its second argument is the
+user_data value that was passed to pcre2_callout_enumerate(). The 
+contents of the callout enumeration block are described in the
+pcre2callout
+documentation, which also gives further details about callouts.
 
    
-
    SERIALIZATION AND PRECOMPILING
    
+
    SERIALIZATION AND PRECOMPILING
    
 
    
 It is possible to save compiled patterns on disc or elsewhere, and reload them
 later, subject to a number of restrictions. The functions whose names begin
@@ -1729,7 +1756,7 @@ the
 pcre2serialize
 documentation.
 
    
-
    THE MATCH DATA BLOCK
    
+
    THE MATCH DATA BLOCK
    
 
    
 pcre2_match_data_create(uint32_t ovecsize,
   pcre2_general_context *gcontext);
@@ -1800,7 +1827,7 @@ match data block (for that match) have taken place.
 When a match data block itself is no longer needed, it should be freed by
 calling pcre2_match_data_free().
 
    
-
    MATCHING A PATTERN: THE TRADITIONAL FUNCTION
    
+
    MATCHING A PATTERN: THE TRADITIONAL FUNCTION
    
 
    
 int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject,
   PCRE2_SIZE length, PCRE2_SIZE startoffset,
@@ -2014,7 +2041,7 @@ examples, in the
 pcre2partial
 documentation.
 
    
-
    NEWLINE HANDLING WHEN MATCHING
    
+
    NEWLINE HANDLING WHEN MATCHING
    
 
    
 When PCRE2 is built, a default newline convention is set; this is usually the
 standard convention for the operating system. The default can be overridden in
@@ -2049,7 +2076,7 @@ LF in the characters that it matches.
 Notwithstanding the above, anomalous effects may still occur when CRLF is a
 valid newline sequence and explicit \r or \n escapes appear in the pattern.
 
    
-
    HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
    
+
    HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
    
 
    
 uint32_t pcre2_get_ovector_count(pcre2_match_data *match_data);
 
    
@@ -2151,7 +2178,7 @@ parentheses, no more than ovector[0] to ovector[2n+1] are set by
 pcre2_match(). The other elements retain whatever values they previously
 had.
 
    
-
    OTHER INFORMATION ABOUT A MATCH
    
+
    OTHER INFORMATION ABOUT A MATCH
    
 
    
 PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data);
 
    
@@ -2195,7 +2222,7 @@ the code unit offset of the invalid UTF character. Details are given in the
 pcre2unicode
 page.
 
    
-
    ERROR RETURNS FROM pcre2_match()
    
+
    ERROR RETURNS FROM pcre2_match()
    
 
    
 If pcre2_match() fails, it returns a negative number. This can be
 converted to a text string by calling pcre2_get_error_message(). Negative
@@ -2246,8 +2273,8 @@ of the subject.
   PCRE2_ERROR_CALLOUT
    This error is never generated by pcre2_match() itself. It is provided for -use by callout functions that want to cause pcre2_match() to return a -distinctive error code. See the +use by callout functions that want to cause pcre2_match() or +pcre2_callout_enumerate() to return a distinctive error code. See the pcre2callout documentation for details. 
    @@ -2304,7 +2331,7 @@ is attempted.
    The internal recursion limit was reached.

    -
    EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
    +
    EXTRACTING CAPTURED SUBSTRINGS BY NUMBER

    int pcre2_substring_length_bynumber(pcre2_match_data *match_data, uint32_t number, PCRE2_SIZE *length); @@ -2401,7 +2428,7 @@ The substring did not participate in the match. For example, if the pattern is (abc)|(def) and the subject is "def", and the ovector contains at least two capturing slots, substring number 1 is unset.

    -
    EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
    +
    EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS

    int pcre2_substring_list_get(pcre2_match_data *match_data, " PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr); @@ -2440,7 +2467,7 @@ can be distinguished from a genuine zero-length substring by inspecting the appropriate offset in the ovector, which contain PCRE2_UNSET for unset substrings, or by calling pcre2_substring_length_bynumber().

    -
    EXTRACTING CAPTURED SUBSTRINGS BY NAME
    +
    EXTRACTING CAPTURED SUBSTRINGS BY NAME

    int pcre2_substring_number_from_name(const pcre2_code *code, PCRE2_SPTR name); @@ -2500,7 +2527,7 @@ 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.

    -
    CREATING A NEW STRING WITH SUBSTITUTIONS
    +
    CREATING A NEW STRING WITH SUBSTITUTIONS

    int pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length, PCRE2_SIZE startoffset, @@ -2561,7 +2588,7 @@ straight back. PCRE2_ERROR_BADREPLACEMENT is returned for an invalid replacement string (unrecognized sequence following a dollar sign), and PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough.

    -
    DUPLICATE SUBPATTERN NAMES
    +
    DUPLICATE SUBPATTERN NAMES

    int pcre2_substring_nametable_scan(const pcre2_code *code, PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); @@ -2606,7 +2633,7 @@ The format of the name table is described above in the section entitled Given all the relevant entries for the name, you can extract each of their numbers, and hence the captured data.

    -
    FINDING ALL POSSIBLE MATCHES AT ONE POSITION
    +
    FINDING ALL POSSIBLE MATCHES AT ONE POSITION

    The traditional matching function uses a similar algorithm to Perl, which stops when it finds the first match at a given point in the subject. If you want to @@ -2624,7 +2651,7 @@ 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.

    -
    MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
    +
    MATCHING A PATTERN: THE ALTERNATIVE FUNCTION

    int pcre2_dfa_match(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length, PCRE2_SIZE startoffset, @@ -2819,13 +2846,13 @@ 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
    +
    SEE ALSO

    pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), pcre2partial(3), pcre2posix(3), pcre2sample(3), pcre2stack(3), pcre2unicode(3).

    -
    AUTHOR
    +
    AUTHOR

    Philip Hazel
    @@ -2834,9 +2861,9 @@ University Computing Service Cambridge, England.

    -
    REVISION
    +
    REVISION

    -Last updated: 23 January 2015 +Last updated: 23 March 2015
    Copyright © 1997-2015 University of Cambridge.
    diff --git a/doc/html/pcre2callout.html b/doc/html/pcre2callout.html index 93deba9..5815d00 100644 --- a/doc/html/pcre2callout.html +++ b/doc/html/pcre2callout.html @@ -17,9 +17,10 @@ please consult the man page, in case the conversion went wrong.

  • DESCRIPTION
  • MISSING CALLOUTS
  • THE CALLOUT INTERFACE -
  • RETURN VALUES -
  • AUTHOR -
  • REVISION +
  • RETURN VALUES FROM CALLOUTS +
  • CALLOUT ENUMERATION +
  • AUTHOR +
  • REVISION
    SYNOPSIS

    @@ -27,23 +28,32 @@ please consult the man page, in case the conversion went wrong.

    int (*pcre2_callout)(pcre2_callout_block *, void *); +
    +
    +int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data);


    DESCRIPTION

    PCRE2 provides a feature called "callout", which is a means of temporarily passing control to the caller of PCRE2 in the middle of pattern matching. The caller of PCRE2 provides an external function by putting its entry point in -a match context (see pcre2_set_callout()) in the +a match context (see pcre2_set_callout() in the pcre2api documentation).

    -Within a regular expression, (?C) indicates the points at which the external +Within a regular expression, (?C<arg>) indicates a point at which the external function is to be called. Different callout points can be identified by putting a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: +Alternatively, the argument may be a delimited string. The starting delimiter +must be one of ` ' " ^ % # $ { and the ending delimiter is the same as the +start, except for {, where the ending delimiter is }. If the ending delimiter +is needed within the string, it must be doubled. For example, this pattern has +two callout points: 

    -  (?C1)abc(?C2)def
+  (?C1)abc(?C"some ""arbitrary"" text")def
    If the PCRE2_AUTO_CALLOUT option bit is set when a pattern is compiled, PCRE2 automatically inserts callouts, all with number 255, before each item in the @@ -62,19 +72,18 @@ alternation bar. If the pattern contains a conditional group whose condition is an assertion, an automatic callout is inserted immediately before the condition. Such a callout may also be inserted explicitly, for example: 
    -  (?(?C9)(?=a)ab|de)
+  (?(?C9)(?=a)ab|de)  (?(?C%text%)(?!=d)ab|de)
    This applies only to assertion conditions (because they are themselves independent groups).

    -Automatic callouts can be used for tracking the progress of pattern matching. -The +Callouts can be useful for tracking the progress of pattern matching. The pcre2test -program has a pattern qualifier (/auto_callout) that sets automatic callouts; -when it is used, the output indicates how the pattern is being matched. This is -useful information when you are trying to optimize the performance of a -particular pattern. +program has a pattern qualifier (/auto_callout) that sets automatic callouts. +When any callouts are present, the output from pcre2test indicates how +the pattern is being matched. This is useful information when you are trying to +optimize the performance of a particular pattern.


    MISSING CALLOUTS

    @@ -185,7 +194,7 @@ You can disable these optimizations by passing the PCRE2_NO_START_OPTIMIZE option to pcre2_compile(), or by starting the pattern with (*NO_START_OPT). This slows down the matching process, but does ensure that callouts such as the example above are obeyed. -

    +


    THE CALLOUT INTERFACE

    During matching, when PCRE2 reaches a callout point, if an external function is @@ -209,16 +218,53 @@ documentation). The callout block structure contains the following fields: PCRE2_SIZE current_position; PCRE2_SIZE pattern_position; PCRE2_SIZE next_item_length; + PCRE2_SIZE callout_string_offset; + PCRE2_SIZE callout_string_length; + PCRE2_SPTR callout_string; The version field contains the version number of the block format. The -current version is 0. The version number will change in future if additional -fields are added, but the intention is never to remove any of the existing -fields. +current version is 1; the three callout string fields were added for this +version. If you are writing an application that might use an earlier release of +PCRE2, you should check the version number before accessing any of these +fields. The version number will increase in future if more fields are added, +but the intention is never to remove any of the existing fields. +

    +
    +Fields for numerical callouts +
    +

    +For a numerical callout, callout_string is NULL, and callout_number +contains the number of the callout, in the range 0-255. This is the number +that follows (?C for manual callouts; it is 255 for automatically generated +callouts. +

    +
    +Fields for string callouts +
    +

    +For callouts with string arguments, callout_number is always zero, and +callout_string points to the string that is contained within the compiled +pattern. Its length is given by callout_string_length. Duplicated ending +delimiters that were present in the original pattern string have been turned +into single characters, but there is no other processing of the callout string +argument. An additional code unit containing binary zero is present after the +string, but is not included in the length. The delimiter that was used to start +the string is also stored within the pattern, immediately before the string +itself. You can access this delimiter as callout_string[-1] if you need +it.

    -The callout_number field contains the number of the callout, as compiled -into the pattern (that is, the number after ?C for manual callouts, and 255 for -automatically generated callouts). +The callout_string_offset field is the code unit offset to the start of +the callout argument string within the original pattern string. This is +provided for the benefit of applications such as script languages that might +need to report errors in the callout string within the pattern. +

    +
    +Fields for all callouts +
    +

    +The remaining fields in the callout block are the same for both kinds of +callout.

    The offset_vector field is a pointer to the vector of capturing offsets @@ -259,8 +305,8 @@ substrings have been captured, the value of capture_last is 0. This is always the case for the DFA matching functions.

    -The pattern_position field contains the offset to the next item to be -matched in the pattern string. +The pattern_position field contains the offset in the pattern string to +the next item to be matched.

    The next_item_length field contains the length of the next item to be @@ -272,7 +318,9 @@ of the entire subpattern.

    The pattern_position and next_item_length fields are intended to help in distinguishing between different automatic callouts, which all have the -same callout number. However, they are set for all callouts. +same callout number. However, they are set for all callouts, and are used by +pcre2test to show the next item to be matched when displaying callout +information.

    In callouts from pcre2_match() the mark field contains a pointer to @@ -281,7 +329,7 @@ the zero-terminated name of the most recently passed (*MARK), (*PRUNE), or of (*PRUNE) or (*THEN) without a name do not obliterate a previous (*MARK). In callouts from the DFA matching function this field always contains NULL.

    -
    RETURN VALUES
    +
    RETURN VALUES FROM CALLOUTS

    The external callout function returns an integer to PCRE2. If the value is zero, matching proceeds as normal. If the value is greater than zero, matching @@ -296,7 +344,51 @@ values. In particular, PCRE2_ERROR_NOMATCH forces a standard "no match" failure. The error number PCRE2_ERROR_CALLOUT is reserved for use by callout functions; it will never be used by PCRE2 itself.

    -
    AUTHOR
    +
    CALLOUT ENUMERATION
    +

    +int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); +
    +
    +A script language that supports the use of string arguments in callouts might +like to scan all the callouts in a pattern before running the match. This can +be done by calling pcre2_callout_enumerate(). The first argument is a +pointer to a compiled pattern, the second points to a callback function, and +the third is arbitrary user data. The callback function is called for every +callout in the pattern in the order in which they appear. Its first argument is +a pointer to a callout enumeration block, and its second argument is the +user_data value that was passed to pcre2_callout_enumerate(). The +data block contains the following fields: +

    +  version                Block version number
+  pattern_position       Offset to next item in pattern
+  next_item_length       Length of next item in pattern
+  callout_number         Number for numbered callouts
+  callout_string_offset  Offset to string within pattern
+  callout_string_length  Length of callout string
+  callout_string         Points to callout string or is NULL
+
    +The version number is currently 0. It will increase if new fields are ever +added to the block. The remaining fields are the same as their namesakes in the +pcre2_callout block that is used for callouts during matching, as +described +above. +

    +

    +Note that the value of pattern_position is unique for each callout. +However, if a callout occurs inside a group that is quantified with a non-zero +minimum or a fixed maximum, the group is replicated inside the compiled +pattern. For example, a pattern such as /(a){2}/ is compiled as if it were +/(a)(a)/. This means that the callout will be enumerated more than once, but +with the same value for pattern_position in each case. +

    +

    +The callback function should normally return zero. If it returns a non-zero +value, scanning the pattern stops, and that value is returned from +pcre2_callout_enumerate(). +

    +
    AUTHOR

    Philip Hazel
    @@ -305,9 +397,9 @@ University Computing Service Cambridge, England.

    -
    REVISION
    +
    REVISION

    -Last updated: 02 January 2015 +Last updated: 23 March 2015
    Copyright © 1997-2015 University of Cambridge.
    diff --git a/doc/html/pcre2compat.html b/doc/html/pcre2compat.html index 2939a88..3b29e6f 100644 --- a/doc/html/pcre2compat.html +++ b/doc/html/pcre2compat.html @@ -83,11 +83,11 @@ the documentation for details.

    -8. Subpatterns that are called as subroutines (whether or not recursively) are -always treated as atomic groups in PCRE2. This is like Python, but unlike Perl. -Captured values that are set outside a subroutine call can be reference from -inside in PCRE2, but not in Perl. There is a discussion that explains these -differences in more detail in the +8. Subroutine calls (whether recursive or not) are treated as atomic groups. +Atomic recursion is like Python, but unlike Perl. Captured values that are set +outside a subroutine call can be referenced from inside in PCRE2, but not in +Perl. There is a discussion that explains these differences in more detail in +the section on recursion differences from Perl in the pcre2pattern @@ -214,9 +214,9 @@ Cambridge, England. REVISION

    -Last updated: 28 September 2014 +Last updated: 15 March 2015
    -Copyright © 1997-2014 University of Cambridge. +Copyright © 1997-2015 University of Cambridge.

    Return to the PCRE2 index page. diff --git a/doc/html/pcre2pattern.html b/doc/html/pcre2pattern.html index 4e7f87b..184ee25 100644 --- a/doc/html/pcre2pattern.html +++ b/doc/html/pcre2pattern.html @@ -2786,43 +2786,70 @@ same pair of parentheses when there is a repetition. PCRE2 provides a similar feature, but of course it cannot obey arbitrary Perl code. The feature is called "callout". The caller of PCRE2 provides an external function by putting its entry point in a match context using the function -pcre2_set_callout() and passing the context to pcre2_match() or -pcre2_dfa_match(). If no match context is passed, or if the callout entry -point is set to NULL, callouts are disabled. +pcre2_set_callout(), and then passing that context to pcre2_match() +or pcre2_dfa_match(). If no match context is passed, or if the callout +entry point is set to NULL, callouts are disabled.

    -Within a regular expression, (?C) indicates the points at which the external -function is to be called. If you want to identify different callout points, you -can put a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: +Within a regular expression, (?C<arg>) indicates a point at which the external +function is to be called. There are two kinds of callout: those with a +numerical argument and those with a string argument. (?C) on its own with no +argument is treated as (?C0). A numerical argument allows the application to +distinguish between different callouts. String arguments were added for release +10.20 to make it possible for script languages that use PCRE2 to embed short +scripts within patterns in a similar way to Perl. +

    +

    +During matching, when PCRE2 reaches a callout point, the external function is +called. It is provided with the number or string argument of the callout, the +position in the pattern, and one item of data that is also set in the match +block. The callout function may cause matching to proceed, to backtrack, or to +fail. +

    +

    +By default, PCRE2 implements a number of optimizations at matching time, and +one side-effect is that sometimes callouts are skipped. If you need all +possible callouts to happen, you need to set options that disable the relevant +optimizations. More details, including a complete description of the +programming interface to the callout function, are given in the +pcre2callout +documentation. +

    +
    +Callouts with numerical arguments +
    +

    +If you just want to have a means of identifying different callout points, put a +number less than 256 after the letter C. For example, this pattern has two +callout points: 

       (?C1)abc(?C2)def
    -If the PCRE2_AUTO_CALLOUT flag is passed to pcre2_compile(), callouts are -automatically installed before each item in the pattern. They are all numbered -255. If there is a conditional group in the pattern whose condition is an -assertion, an additional callout is inserted just before the condition. An -explicit callout may also be set at this position, as in this example: +If the PCRE2_AUTO_CALLOUT flag is passed to pcre2_compile(), numerical +callouts are automatically installed before each item in the pattern. They are +all numbered 255. If there is a conditional group in the pattern whose +condition is an assertion, an additional callout is inserted just before the +condition. An explicit callout may also be set at this position, as in this +example: 
       (?(?C9)(?=a)abc|def)
    Note that this applies only to assertion conditions, not to other types of condition.

    +
    +Callouts with string arguments +

    -During matching, when PCRE2 reaches a callout point, the external function is -called. It is provided with the number of the callout, the position in the -pattern, and one item of data that is also set in the match block. The callout -function may cause matching to proceed, to backtrack, or to fail. -

    -

    -By default, PCRE2 implements a number of optimizations at matching time, and -one side-effect is that sometimes callouts are skipped. If you need all -possible callouts to happen, you need to set options that disable the relevant -optimizations. More details, and a complete description of the interface to the -callout function, are given in the -pcre2callout -documentation. +A delimited string may be used instead of a number as a callout argument. The +starting delimiter must be one of ` ' " ^ % # $ { and the ending delimiter is +the same as the start, except for {, where the ending delimiter is }. If the +ending delimiter is needed within the string, it must be doubled. For +example: +

    +  (?C'ab ''c'' d')xyz(?C{any text})pqr
+
    +The doubling is removed before the string is passed to the callout function.


    BACKTRACKING CONTROL

    @@ -3258,7 +3285,7 @@ Cambridge, England.


    REVISION

    -Last updated: 28 January 2015 +Last updated: 15 March 2015
    Copyright © 1997-2015 University of Cambridge.
    diff --git a/doc/html/pcre2syntax.html b/doc/html/pcre2syntax.html index 1b7237f..a0a1b99 100644 --- a/doc/html/pcre2syntax.html +++ b/doc/html/pcre2syntax.html @@ -535,9 +535,13 @@ pattern is not anchored.
    CALLOUTS

    -  (?C)      callout
-  (?Cn)     callout with data n
-
    + (?C) callout (assumed number 0) + (?Cn) callout with numerical data n + (?C"text") callout with string data + +The allowed string delimiters are ` ' " ^ % # $ (which are the same for the +start and the end), and the starting delimiter { matched with the ending +delimiter }. To encode the ending delimiter within the string, double it.


    SEE ALSO

    @@ -555,7 +559,7 @@ Cambridge, England.


    REVISION

    -Last updated: 26 January 2015 +Last updated: 15 March 2015
    Copyright © 1997-2015 University of Cambridge.
    diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html index 24b3052..aee6edc 100644 --- a/doc/html/pcre2test.html +++ b/doc/html/pcre2test.html @@ -90,11 +90,18 @@ names used in the libraries have a suffix _8, _16, or _32, as appropriate.

    Input to pcre2test is processed line by line, either by calling the C library's fgets() function, or via the libreadline library (see -below). In Unix-like environments, fgets() treats any bytes other than -newline as data characters. However, in some Windows environments character 26 -(hex 1A) causes an immediate end of file, and no further data is read. For -maximum portability, therefore, it is safest to avoid non-printing characters -in pcre2test input files. +below). The input is processed using using C's string functions, so must not +contain binary zeroes, even though in Unix-like environments, fgets() +treats any bytes other than newline as data characters. In some Windows +environments character 26 (hex 1A) causes an immediate end of file, and no +further data is read. +

    +

    +For maximum portability, therefore, it is safest to avoid non-printing +characters in pcre2test input files. There is a facility for specifying a +pattern's characters as hexadecimal pairs, thus making it possible to include +binary zeroes in a pattern for testing purposes. Subject lines are processed +for backslash escapes, which makes it possible to include any data value.


    COMMAND LINE OPTIONS

    @@ -499,6 +506,7 @@ about the pattern: 

           bsr=[anycrlf|unicode]     specify \R handling
   /B  bincode                   show binary code without lengths
+      callout_info              show callout information 
       debug                     same as info,fullbincode
       fullbincode               show binary code with lengths
   /I  info                      show info about compiled pattern
@@ -580,6 +588,12 @@ unit" is the last literal code unit that must be present in any match. This is
 not necessarily the last character. These lines are omitted if no starting or
 ending code units are recorded.
 
    
+
    
+The callout_info modifier requests information about all the callouts in 
+the pattern. A list of them is output at the end of any other information that 
+is requested. For each callout, either its number or string is given, followed 
+by the item that follows it in the pattern.
+
    
 
    
 Specifying a pattern in hex
 
    
@@ -907,12 +921,15 @@ set, the current captured groups are output when a callout occurs.
 The callout_fail modifier can be given one or two numbers. If there is
 only one number, 1 is returned instead of 0 when a callout of that number is
 reached. If two numbers are given, 1 is returned when callout <n> is reached
-for the <m>th time.
+for the <m>th time. Note that callouts with string arguments are always given
+the number zero. See "Callouts" below for a description of the output when a
+callout it taken.
 
    
 
    
 The callout_data modifier can be given an unsigned or a negative number.
-Any value other than zero is used as a return from pcre2test's callout
-function.
+This is set as the "user data" that is passed to the matching function, and
+passed back when the callout function is invoked. Any value other than zero is
+used as a return from pcre2test's callout function.
 
    
 
    
 Finding all matches in a string
@@ -1262,10 +1279,32 @@ documentation.
 
    CALLOUTS
    
 
    
 If the pattern contains any callout requests, pcre2test's callout
-function is called during matching. This works with both matching functions. By
-default, the called function displays the callout number, the start and current
-positions in the text at the callout time, and the next pattern item to be
-tested. For example:
+function is called during matching unless callout_none is specified.
+This works with both matching functions.
+
    
+
    
+The callout function in pcre2test returns zero (carry on matching) by
+default, but you can use a callout_fail modifier in a subject line (as
+described above) to change this and other parameters of the callout.
+
    
+
    
+Inserting callouts can be helpful when using pcre2test to check
+complicated regular expressions. For further information about callouts, see
+the
+pcre2callout
+documentation.
+
    
+
    
+The output for callouts with numerical arguments and those with string
+arguments is slightly different.
+
    
+
    
+Callouts with numerical arguments
+
    
+
    
+By default, the callout function displays the callout number, the start and
+current positions in the subject text at the callout time, and the next pattern
+item to be tested. For example:
 
       --->pqrabcdef
     0    ^  ^     \d
@@ -1308,17 +1347,27 @@ The mark changes between matching "a" and "b", but stays the same for the rest
 of the match, so nothing more is output. If, as a result of backtracking, the
 mark reverts to being unset, the text "<unset>" is output.
 
    
+
    
+Callouts with string arguments
+
    
 
    
-The callout function in pcre2test returns zero (carry on matching) by
-default, but you can use a callout_fail modifier in a subject line (as
-described above) to change this and other parameters of the callout.
-
    
-
    
-Inserting callouts can be helpful when using pcre2test to check
-complicated regular expressions. For further information about callouts, see
-the
-pcre2callout
-documentation.
+The output for a callout with a string argument is similar, except that instead
+of outputting a callout number before the position indicators, the callout
+string and its offset in the pattern string are output before the reflection of
+the subject string, and the subject string is reflected for each callout. For
+example:
+
    +    re> /^ab(?C'first')cd(?C"second")ef/
+  data> abcdefg
+  Callout (7): 'first'
+  --->abcdefg
+      ^ ^         c
+  Callout (20): "second"
+  --->abcdefg
+      ^   ^       e
+   0: abcdef
+
+
    
 
    
 
    NON-PRINTING CHARACTERS
    
 
    
@@ -1411,7 +1460,7 @@ Cambridge, England.
 
    
 
    REVISION
    
 
    
-Last updated: 23 January 2015
+Last updated: 22 March 2015
 
    
 Copyright © 1997-2015 University of Cambridge.
 
    
diff --git a/doc/index.html.src b/doc/index.html.src
index ec12c6e..ae938fd 100644
--- a/doc/index.html.src
+++ b/doc/index.html.src
@@ -88,6 +88,9 @@ in the library.
    • pcre2_callout_enumerate  Enumerate callouts in a compiled pattern
    pcre2_code_free   Free a compiled pattern
    + + + diff --git a/doc/pcre2.txt b/doc/pcre2.txt index 80d841b..09f32b5 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -158,8 +158,8 @@ REVISION Last updated: 18 November 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2API(3) Library Functions Manual PCRE2API(3) @@ -367,6 +367,10 @@ PCRE2 NATIVE API AUXILIARY FUNCTIONS int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where); + int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); + int pcre2_config(uint32_t what, void *where); @@ -1452,14 +1456,16 @@ INFORMATION ABOUT A COMPILED PATTERN int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where); - The pcre2_pattern_info() function returns information about a compiled - pattern. The first argument is a pointer to the compiled pattern. The - second argument specifies which piece of information is required, and - the third argument is a pointer to a variable to receive the data. If - the third argument is NULL, the first argument is ignored, and the - function returns the size in bytes of the variable that is required for - the information requested. Otherwise, The yield of the function is - zero for success, or one of the following negative numbers: + The pcre2_pattern_info() function returns general information about a + compiled pattern. For information about callouts, see the next section. + The first argument for pcre2_pattern_info() is a pointer to the com- + piled pattern. The second argument specifies which piece of information + is required, and the third argument is a pointer to a variable to + receive the data. If the third argument is NULL, the first argument is + ignored, and the function returns the size in bytes of the variable + that is required for the information requested. Otherwise, The yield of + the function is zero for success, or one of the following negative num- + bers: PCRE2_ERROR_NULL the argument code was NULL PCRE2_ERROR_BADMAGIC the "magic number" was not found @@ -1744,6 +1750,25 @@ INFORMATION ABOUT A COMPILED PATTERN alter the value returned by this option. +INFORMATION ABOUT A PATTERN'S CALLOUTS + + int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); + + A script language that supports the use of string arguments in callouts + might like to scan all the callouts in a pattern before running the + match. This can be done by calling pcre2_callout_enumerate(). The first + argument is a pointer to a compiled pattern, the second points to a + callback function, and the third is arbitrary user data. The callback + function is called for every callout in the pattern in the order in + which they appear. Its first argument is a pointer to a callout enumer- + ation block, and its second argument is the user_data value that was + passed to pcre2_callout_enumerate(). The contents of the callout enu- + meration block are described in the pcre2callout documentation, which + also gives further details about callouts. + + SERIALIZATION AND PRECOMPILING It is possible to save compiled patterns on disc or elsewhere, and @@ -2221,9 +2246,9 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_CALLOUT This error is never generated by pcre2_match() itself. It is provided - for use by callout functions that want to cause pcre2_match() to return - a distinctive error code. See the pcre2callout documentation for - details. + for use by callout functions that want to cause pcre2_match() or + pcre2_callout_enumerate() to return a distinctive error code. See the + pcre2callout documentation for details. PCRE2_ERROR_INTERNAL @@ -2771,11 +2796,11 @@ AUTHOR REVISION - Last updated: 23 January 2015 + Last updated: 23 March 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2BUILD(3) Library Functions Manual PCRE2BUILD(3) @@ -3235,8 +3260,8 @@ REVISION Last updated: 26 January 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2CALLOUT(3) Library Functions Manual PCRE2CALLOUT(3) @@ -3250,22 +3275,30 @@ SYNOPSIS int (*pcre2_callout)(pcre2_callout_block *, void *); + int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); + DESCRIPTION PCRE2 provides a feature called "callout", which is a means of tempo- rarily passing control to the caller of PCRE2 in the middle of pattern matching. The caller of PCRE2 provides an external function by putting - its entry point in a match context (see pcre2_set_callout()) in the + its entry point in a match context (see pcre2_set_callout() in the pcre2api documentation). - Within a regular expression, (?C) indicates the points at which the + Within a regular expression, (?C) indicates a point at which the external function is to be called. Different callout points can be identified by putting a number less than 256 after the letter C. The - default value is zero. For example, this pattern has two callout + default value is zero. Alternatively, the argument may be a delimited + string. The starting delimiter must be one of ` ' " ^ % # $ { and the + ending delimiter is the same as the start, except for {, where the end- + ing delimiter is }. If the ending delimiter is needed within the + string, it must be doubled. For example, this pattern has two callout points: - (?C1)abc(?C2)def + (?C1)abc(?C"some ""arbitrary"" text")def If the PCRE2_AUTO_CALLOUT option bit is set when a pattern is compiled, PCRE2 automatically inserts callouts, all with number 255, before each @@ -3284,29 +3317,30 @@ DESCRIPTION before the condition. Such a callout may also be inserted explicitly, for example: - (?(?C9)(?=a)ab|de) + (?(?C9)(?=a)ab|de) (?(?C%text%)(?!=d)ab|de) This applies only to assertion conditions (because they are themselves independent groups). - Automatic callouts can be used for tracking the progress of pattern - matching. The pcre2test program has a pattern qualifier (/auto_call- - out) that sets automatic callouts; when it is used, the output indi- - cates how the pattern is being matched. This is useful information when - you are trying to optimize the performance of a particular pattern. + Callouts can be useful for tracking the progress of pattern matching. + The pcre2test program has a pattern qualifier (/auto_callout) that sets + automatic callouts. When any callouts are present, the output from + pcre2test indicates how the pattern is being matched. This is useful + information when you are trying to optimize the performance of a par- + ticular pattern. MISSING CALLOUTS - You should be aware that, because of optimizations in the way PCRE2 + You should be aware that, because of optimizations in the way PCRE2 compiles and matches patterns, callouts sometimes do not happen exactly as you might expect. Auto-possessification At compile time, PCRE2 "auto-possessifies" repeated items when it knows - that what follows cannot be part of the repeat. For example, a+[bc] is - compiled as if it were a++[bc]. The pcre2test output when this pattern + that what follows cannot be part of the repeat. For example, a+[bc] is + compiled as if it were a++[bc]. The pcre2test output when this pattern is compiled with PCRE2_ANCHORED and PCRE2_AUTO_CALLOUT and then applied to the string "aaaa" is: @@ -3315,10 +3349,10 @@ MISSING CALLOUTS +2 ^ ^ [bc] No match - This indicates that when matching [bc] fails, there is no backtracking - into a+ and therefore the callouts that would be taken for the back- - tracks do not occur. You can disable the auto-possessify feature by - passing PCRE2_NO_AUTO_POSSESS to pcre2_compile(), or starting the pat- + This indicates that when matching [bc] fails, there is no backtracking + into a+ and therefore the callouts that would be taken for the back- + tracks do not occur. You can disable the auto-possessify feature by + passing PCRE2_NO_AUTO_POSSESS to pcre2_compile(), or starting the pat- tern with (*NO_AUTO_POSSESS). In this case, the output changes to this: --->aaaa @@ -3335,16 +3369,16 @@ MISSING CALLOUTS Automatic .* anchoring By default, an optimization is applied when .* is the first significant - item in a pattern. If PCRE2_DOTALL is set, so that the dot can match - any character, the pattern is automatically anchored. If PCRE2_DOTALL - is not set, a match can start only after an internal newline or at the - beginning of the subject, and pcre2_compile() remembers this. This - optimization is disabled, however, if .* is in an atomic group or if - there is a back reference to the capturing group in which it appears. - It is also disabled if the pattern contains (*PRUNE) or (*SKIP). How- + item in a pattern. If PCRE2_DOTALL is set, so that the dot can match + any character, the pattern is automatically anchored. If PCRE2_DOTALL + is not set, a match can start only after an internal newline or at the + beginning of the subject, and pcre2_compile() remembers this. This + optimization is disabled, however, if .* is in an atomic group or if + there is a back reference to the capturing group in which it appears. + It is also disabled if the pattern contains (*PRUNE) or (*SKIP). How- ever, the presence of callouts does not affect it. - For example, if the pattern .*\d is compiled with PCRE2_AUTO_CALLOUT + For example, if the pattern .*\d is compiled with PCRE2_AUTO_CALLOUT and applied to the string "aa", the pcre2test output is: --->aa @@ -3354,10 +3388,10 @@ MISSING CALLOUTS +2 ^ \d No match - This shows that all match attempts start at the beginning of the sub- - ject. In other words, the pattern is anchored. You can disable this - optimization by passing PCRE2_NO_DOTSTAR_ANCHOR to pcre2_compile(), or - starting the pattern with (*NO_DOTSTAR_ANCHOR). In this case, the out- + This shows that all match attempts start at the beginning of the sub- + ject. In other words, the pattern is anchored. You can disable this + optimization by passing PCRE2_NO_DOTSTAR_ANCHOR to pcre2_compile(), or + starting the pattern with (*NO_DOTSTAR_ANCHOR). In this case, the out- put changes to: --->aa @@ -3370,43 +3404,43 @@ MISSING CALLOUTS +2 ^ \d No match - This shows more match attempts, starting at the second subject charac- - ter. Another optimization, described in the next section, means that + This shows more match attempts, starting at the second subject charac- + ter. Another optimization, described in the next section, means that there is no subsequent attempt to match with an empty subject. - If a pattern has more than one top-level branch, automatic anchoring + If a pattern has more than one top-level branch, automatic anchoring occurs if all branches are anchorable. Other optimizations - Other optimizations that provide fast "no match" results also affect + Other optimizations that provide fast "no match" results also affect callouts. For example, if the pattern is ab(?C4)cd - PCRE2 knows that any matching string must contain the letter "d". If - the subject string is "abyz", the lack of "d" means that matching - doesn't ever start, and the callout is never reached. However, with + PCRE2 knows that any matching string must contain the letter "d". If + the subject string is "abyz", the lack of "d" means that matching + doesn't ever start, and the callout is never reached. However, with "abyd", though the result is still no match, the callout is obeyed. - PCRE2 also knows the minimum length of a matching string, and will - immediately give a "no match" return without actually running a match - if the subject is not long enough, or, for unanchored patterns, if it + PCRE2 also knows the minimum length of a matching string, and will + immediately give a "no match" return without actually running a match + if the subject is not long enough, or, for unanchored patterns, if it has been scanned far enough. You can disable these optimizations by passing the PCRE2_NO_START_OPTI- - MIZE option to pcre2_compile(), or by starting the pattern with - (*NO_START_OPT). This slows down the matching process, but does ensure + MIZE option to pcre2_compile(), or by starting the pattern with + (*NO_START_OPT). This slows down the matching process, but does ensure that callouts such as the example above are obeyed. THE CALLOUT INTERFACE - During matching, when PCRE2 reaches a callout point, if an external - function is set in the match context, it is called. This applies to - both normal and DFA matching. The first argument to the callout func- - tion is a pointer to a pcre2_callout block. The second argument is the - void * callout data that was supplied when the callout was set up by + During matching, when PCRE2 reaches a callout point, if an external + function is set in the match context, it is called. This applies to + both normal and DFA matching. The first argument to the callout func- + tion is a pointer to a pcre2_callout block. The second argument is the + void * callout data that was supplied when the callout was set up by calling pcre2_set_callout() (see the pcre2api documentation). The call- out block structure contains the following fields: @@ -3422,15 +3456,47 @@ THE CALLOUT INTERFACE PCRE2_SIZE current_position; PCRE2_SIZE pattern_position; PCRE2_SIZE next_item_length; + PCRE2_SIZE callout_string_offset; + PCRE2_SIZE callout_string_length; + PCRE2_SPTR callout_string; - The version field contains the version number of the block format. The - current version is 0. The version number will change in future if addi- - tional fields are added, but the intention is never to remove any of - the existing fields. + The version field contains the version number of the block format. The + current version is 1; the three callout string fields were added for + this version. If you are writing an application that might use an ear- + lier release of PCRE2, you should check the version number before + accessing any of these fields. The version number will increase in + future if more fields are added, but the intention is never to remove + any of the existing fields. - The callout_number field contains the number of the callout, as com- - piled into the pattern (that is, the number after ?C for manual call- - outs, and 255 for automatically generated callouts). + Fields for numerical callouts + + For a numerical callout, callout_string is NULL, and callout_number + contains the number of the callout, in the range 0-255. This is the + number that follows (?C for manual callouts; it is 255 for automati- + cally generated callouts. + + Fields for string callouts + + For callouts with string arguments, callout_number is always zero, and + callout_string points to the string that is contained within the com- + piled pattern. Its length is given by callout_string_length. Duplicated + ending delimiters that were present in the original pattern string have + been turned into single characters, but there is no other processing of + the callout string argument. An additional code unit containing binary + zero is present after the string, but is not included in the length. + The delimiter that was used to start the string is also stored within + the pattern, immediately before the string itself. You can access this + delimiter as callout_string[-1] if you need it. + + The callout_string_offset field is the code unit offset to the start of + the callout argument string within the original pattern string. This is + provided for the benefit of applications such as script languages that + might need to report errors in the callout string within the pattern. + + Fields for all callouts + + The remaining fields in the callout block are the same for both kinds + of callout. The offset_vector field is a pointer to the vector of capturing offsets (the "ovector") that was passed to the matching function in the match @@ -3464,8 +3530,8 @@ THE CALLOUT INTERFACE substrings. If no substrings have been captured, the value of cap- ture_last is 0. This is always the case for the DFA matching functions. - The pattern_position field contains the offset to the next item to be - matched in the pattern string. + The pattern_position field contains the offset in the pattern string to + the next item to be matched. The next_item_length field contains the length of the next item to be matched in the pattern string. When the callout immediately precedes an @@ -3475,7 +3541,9 @@ THE CALLOUT INTERFACE The pattern_position and next_item_length fields are intended to help in distinguishing between different automatic callouts, which all have - the same callout number. However, they are set for all callouts. + the same callout number. However, they are set for all callouts, and + are used by pcre2test to show the next item to be matched when display- + ing callout information. In callouts from pcre2_match() the mark field contains a pointer to the zero-terminated name of the most recently passed (*MARK), (*PRUNE), or @@ -3485,7 +3553,7 @@ THE CALLOUT INTERFACE always contains NULL. -RETURN VALUES +RETURN VALUES FROM CALLOUTS The external callout function returns an integer to PCRE2. If the value is zero, matching proceeds as normal. If the value is greater than @@ -3501,6 +3569,49 @@ RETURN VALUES itself. +CALLOUT ENUMERATION + + int pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), + void *user_data); + + A script language that supports the use of string arguments in callouts + might like to scan all the callouts in a pattern before running the + match. This can be done by calling pcre2_callout_enumerate(). The first + argument is a pointer to a compiled pattern, the second points to a + callback function, and the third is arbitrary user data. The callback + function is called for every callout in the pattern in the order in + which they appear. Its first argument is a pointer to a callout enumer- + ation block, and its second argument is the user_data value that was + passed to pcre2_callout_enumerate(). The data block contains the fol- + lowing fields: + + version Block version number + pattern_position Offset to next item in pattern + next_item_length Length of next item in pattern + callout_number Number for numbered callouts + callout_string_offset Offset to string within pattern + callout_string_length Length of callout string + callout_string Points to callout string or is NULL + + The version number is currently 0. It will increase if new fields are + ever added to the block. The remaining fields are the same as their + namesakes in the pcre2_callout block that is used for callouts during + matching, as described above. + + Note that the value of pattern_position is unique for each callout. + However, if a callout occurs inside a group that is quantified with a + non-zero minimum or a fixed maximum, the group is replicated inside the + compiled pattern. For example, a pattern such as /(a){2}/ is compiled + as if it were /(a)(a)/. This means that the callout will be enumerated + more than once, but with the same value for pattern_position in each + case. + + The callback function should normally return zero. If it returns a non- + zero value, scanning the pattern stops, and that value is returned from + pcre2_callout_enumerate(). + + AUTHOR Philip Hazel @@ -3510,11 +3621,11 @@ AUTHOR REVISION - Last updated: 02 January 2015 + Last updated: 23 March 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2COMPAT(3) Library Functions Manual PCRE2COMPAT(3) @@ -3585,104 +3696,103 @@ DIFFERENCES BETWEEN PCRE2 AND PERL during pattern matching. See the pcre2callout documentation for details. - 8. Subpatterns that are called as subroutines (whether or not recur- - sively) are always treated as atomic groups in PCRE2. This is like - Python, but unlike Perl. Captured values that are set outside a sub- - routine call can be reference from inside in PCRE2, but not in Perl. - There is a discussion that explains these differences in more detail in - the section on recursion differences from Perl in the pcre2pattern - page. + 8. Subroutine calls (whether recursive or not) are treated as atomic + groups. Atomic recursion is like Python, but unlike Perl. Captured + values that are set outside a subroutine call can be referenced from + inside in PCRE2, but not in Perl. There is a discussion that explains + these differences in more detail in the section on recursion differ- + ences from Perl in the pcre2pattern page. - 9. If any of the backtracking control verbs are used in a subpattern - that is called as a subroutine (whether or not recursively), their - effect is confined to that subpattern; it does not extend to the sur- - rounding pattern. This is not always the case in Perl. In particular, - if (*THEN) is present in a group that is called as a subroutine, its + 9. If any of the backtracking control verbs are used in a subpattern + that is called as a subroutine (whether or not recursively), their + effect is confined to that subpattern; it does not extend to the sur- + rounding pattern. This is not always the case in Perl. In particular, + if (*THEN) is present in a group that is called as a subroutine, its action is limited to that group, even if the group does not contain any - | characters. Note that such subpatterns are processed as anchored at + | characters. Note that such subpatterns are processed as anchored at the point where they are tested. - 10. If a pattern contains more than one backtracking control verb, the - first one that is backtracked onto acts. For example, in the pattern - A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but a failure + 10. If a pattern contains more than one backtracking control verb, the + first one that is backtracked onto acts. For example, in the pattern + A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but a failure in C triggers (*PRUNE). Perl's behaviour is more complex; in many cases it is the same as PCRE2, but there are examples where it differs. - 11. Most backtracking verbs in assertions have their normal actions. + 11. Most backtracking verbs in assertions have their normal actions. They are not confined to the assertion. - 12. There are some differences that are concerned with the settings of - captured strings when part of a pattern is repeated. For example, - matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 + 12. There are some differences that are concerned with the settings of + captured strings when part of a pattern is repeated. For example, + matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE2 it is set to "b". 13. PCRE2's handling of duplicate subpattern numbers and duplicate sub- pattern names is not as general as Perl's. This is a consequence of the - fact the PCRE2 works internally just with numbers, using an external - table to translate between numbers and names. In particular, a pattern - such as (?|(?A)|(?A)|(? +.PP +.nf +.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP, +.B " int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *)," +.B " void *\fIcallout_data\fP);" +.fi +. +.SH DESCRIPTION +.rs +.sp +This function scans a compiled regular expression and calls the \fIcallback()\fP +function for each callout within the pattern. The yield of the function is zero +for success and non-zero otherwise. The arguments are: +.sp + \fIcode\fP Points to the compiled pattern + \fIcallback\fP The callback function + \fIcallout_data\fP User data that is passed to the callback +.sp +The \fIcallback()\fP function is passed a pointer to a data block containing +the following fields: +.sp + \fIversion\fP Block version number + \fIpattern_position\fP Offset to next item in pattern + \fInext_item_length\fP Length of next item in pattern + \fIcallout_number\fP Number for numbered callouts + \fIcallout_string_offset\fP Offset to string within pattern + \fIcallout_string_length\fP Length of callout string + \fIcallout_string\fP Points to callout string or is NULL +.sp +The second argument is the callout data that was passed to +\fBpcre2_callout_enumerate()\fP. The \fBcallback()\fP function must return zero +for success. Any other value causes the pattern scan to stop, with the value +being passed back as the result of \fBpcre2_callout_enumerate()\fP. +.P +There is a complete description of the PCRE2 native API in the +.\" HREF +\fBpcre2api\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcre2posix\fP +.\" +page. diff --git a/doc/pcre2api.3 b/doc/pcre2api.3 index ad60e3c..39a849b 100644 --- a/doc/pcre2api.3 +++ b/doc/pcre2api.3 @@ -1,4 +1,4 @@ -.TH PCRE2API 3 "23 January 2015" "PCRE2 10.10" +.TH PCRE2API 3 "23 March 2015" "PCRE2 10.20" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .sp @@ -234,6 +234,10 @@ document for an overview of all the PCRE2 documentation. .sp .B int pcre2_pattern_info(const pcre2 *\fIcode\fP, uint32_t \fIwhat\fP, void *\fIwhere\fP); .sp +.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP, +.B " int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *)," +.B " void *\fIuser_data\fP);" +.sp .B int pcre2_config(uint32_t \fIwhat\fP, void *\fIwhere\fP); .fi . @@ -1427,14 +1431,19 @@ can be processed in different locales. .B int pcre2_pattern_info(const pcre2 *\fIcode\fP, uint32_t \fIwhat\fP, void *\fIwhere\fP); .fi .P -The \fBpcre2_pattern_info()\fP function returns information about a compiled -pattern. The first argument is a pointer to the compiled pattern. The second -argument specifies which piece of information is required, and the third -argument is a pointer to a variable to receive the data. If the third argument -is NULL, the first argument is ignored, and the function returns the size in -bytes of the variable that is required for the information requested. -Otherwise, The yield of the function is zero for success, or one of the -following negative numbers: +The \fBpcre2_pattern_info()\fP function returns general information about a +compiled pattern. For information about callouts, see the +.\" HTML +.\" +next section. +.\" +The first argument for \fBpcre2_pattern_info()\fP is a pointer to the compiled +pattern. The second argument specifies which piece of information is required, +and the third argument is a pointer to a variable to receive the data. If the +third argument is NULL, the first argument is ignored, and the function returns +the size in bytes of the variable that is required for the information +requested. Otherwise, The yield of the function is zero for success, or one of +the following negative numbers: .sp PCRE2_ERROR_NULL the argument \fIcode\fP was NULL PCRE2_ERROR_BADMAGIC the "magic number" was not found @@ -1716,6 +1725,31 @@ calculates the size has to over-estimate. Processing a pattern with the JIT compiler does not alter the value returned by this option. . . +.\" HTML +.SH "INFORMATION ABOUT A PATTERN'S CALLOUTS" +.rs +.sp +.nf +.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP, +.B " int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *)," +.B " void *\fIuser_data\fP);" +.fi +.sp +A script language that supports the use of string arguments in callouts might +like to scan all the callouts in a pattern before running the match. This can +be done by calling \fBpcre2_callout_enumerate()\fP. The first argument is a +pointer to a compiled pattern, the second points to a callback function, and +the third is arbitrary user data. The callback function is called for every +callout in the pattern in the order in which they appear. Its first argument is +a pointer to a callout enumeration block, and its second argument is the +\fIuser_data\fP value that was passed to \fBpcre2_callout_enumerate()\fP. The +contents of the callout enumeration block are described in the +.\" HREF +\fBpcre2callout\fP +.\" +documentation, which also gives further details about callouts. +. +. .SH "SERIALIZATION AND PRECOMPILING" .rs .sp @@ -2275,8 +2309,8 @@ of the subject. PCRE2_ERROR_CALLOUT .sp This error is never generated by \fBpcre2_match()\fP itself. It is provided for -use by callout functions that want to cause \fBpcre2_match()\fP to return a -distinctive error code. See the +use by callout functions that want to cause \fBpcre2_match()\fP or +\fBpcre2_callout_enumerate()\fP to return a distinctive error code. See the .\" HREF \fBpcre2callout\fP .\" @@ -2885,6 +2919,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 23 January 2015 +Last updated: 23 March 2015 Copyright (c) 1997-2015 University of Cambridge. .fi diff --git a/doc/pcre2callout.3 b/doc/pcre2callout.3 index 41ca8ab..8b3f338 100644 --- a/doc/pcre2callout.3 +++ b/doc/pcre2callout.3 @@ -1,4 +1,4 @@ -.TH PCRE2CALLOUT 3 "16 March 2015" "PCRE2 10.20" +.TH PCRE2CALLOUT 3 "23 March 2015" "PCRE2 10.20" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH SYNOPSIS @@ -7,7 +7,13 @@ PCRE2 - Perl-compatible regular expressions (revised API) .B #include .PP .SM +.nf .B int (*pcre2_callout)(pcre2_callout_block *, void *); +.sp +.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP, +.B " int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *)," +.B " void *\fIuser_data\fP);" +.fi . .SH DESCRIPTION .rs @@ -170,6 +176,7 @@ option to \fBpcre2_compile()\fP, or by starting the pattern with callouts such as the example above are obeyed. . . +.\" HTML .SH "THE CALLOUT INTERFACE" .rs .sp @@ -199,7 +206,6 @@ documentation). The callout block structure contains the following fields: PCRE2_SIZE \fIcallout_string_offset\fP; PCRE2_SIZE \fIcallout_string_length\fP; PCRE2_SPTR \fIcallout_string\fP; - .sp The \fIversion\fP field contains the version number of the block format. The current version is 1; the three callout string fields were added for this @@ -276,8 +282,8 @@ outside the recursion, as do the values of all captured substrings. If no substrings have been captured, the value of \fIcapture_last\fP is 0. This is always the case for the DFA matching functions. .P -The \fIpattern_position\fP field contains the offset to the next item to be -matched in the pattern string. +The \fIpattern_position\fP field contains the offset in the pattern string to +the next item to be matched. .P The \fInext_item_length\fP field contains the length of the next item to be matched in the pattern string. When the callout immediately precedes an @@ -298,7 +304,7 @@ of (*PRUNE) or (*THEN) without a name do not obliterate a previous (*MARK). In callouts from the DFA matching function this field always contains NULL. . . -.SH "RETURN VALUES" +.SH "RETURN VALUES FROM CALLOUTS" .rs .sp The external callout function returns an integer to PCRE2. If the value is @@ -314,6 +320,54 @@ failure. The error number PCRE2_ERROR_CALLOUT is reserved for use by callout functions; it will never be used by PCRE2 itself. . . +.SH "CALLOUT ENUMERATION" +.rs +.sp +.nf +.B int pcre2_callout_enumerate(const pcre2_code *\fIcode\fP, +.B " int (*\fIcallback\fP)(pcre2_callout_enumerate_block *, void *)," +.B " void *\fIuser_data\fP);" +.fi +.sp +A script language that supports the use of string arguments in callouts might +like to scan all the callouts in a pattern before running the match. This can +be done by calling \fBpcre2_callout_enumerate()\fP. The first argument is a +pointer to a compiled pattern, the second points to a callback function, and +the third is arbitrary user data. The callback function is called for every +callout in the pattern in the order in which they appear. Its first argument is +a pointer to a callout enumeration block, and its second argument is the +\fIuser_data\fP value that was passed to \fBpcre2_callout_enumerate()\fP. The +data block contains the following fields: +.sp + \fIversion\fP Block version number + \fIpattern_position\fP Offset to next item in pattern + \fInext_item_length\fP Length of next item in pattern + \fIcallout_number\fP Number for numbered callouts + \fIcallout_string_offset\fP Offset to string within pattern + \fIcallout_string_length\fP Length of callout string + \fIcallout_string\fP Points to callout string or is NULL +.sp +The version number is currently 0. It will increase if new fields are ever +added to the block. The remaining fields are the same as their namesakes in the +\fBpcre2_callout\fP block that is used for callouts during matching, as +described +.\" HTML +.\" +above. +.\" +.P +Note that the value of \fIpattern_position\fP is unique for each callout. +However, if a callout occurs inside a group that is quantified with a non-zero +minimum or a fixed maximum, the group is replicated inside the compiled +pattern. For example, a pattern such as /(a){2}/ is compiled as if it were +/(a)(a)/. This means that the callout will be enumerated more than once, but +with the same value for \fIpattern_position\fP in each case. +.P +The callback function should normally return zero. If it returns a non-zero +value, scanning the pattern stops, and that value is returned from +\fBpcre2_callout_enumerate()\fP. +. +. .SH AUTHOR .rs .sp @@ -328,6 +382,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 16 March 2015 +Last updated: 23 March 2015 Copyright (c) 1997-2015 University of Cambridge. .fi diff --git a/doc/pcre2test.1 b/doc/pcre2test.1 index e5b3462..eb2b04a 100644 --- a/doc/pcre2test.1 +++ b/doc/pcre2test.1 @@ -1,4 +1,4 @@ -.TH PCRE2TEST 1 "16 March 2015" "PCRE 10.20" +.TH PCRE2TEST 1 "22 March 2015" "PCRE 10.20" .SH NAME pcre2test - a program for testing Perl-compatible regular expressions. .SH SYNOPSIS @@ -473,6 +473,7 @@ about the pattern: .sp bsr=[anycrlf|unicode] specify \eR handling /B bincode show binary code without lengths + callout_info show callout information debug same as info,fullbincode fullbincode show binary code with lengths /I info show info about compiled pattern @@ -549,6 +550,11 @@ if there is more than one they are listed as "starting code units". "Last code unit" is the last literal code unit that must be present in any match. This is not necessarily the last character. These lines are omitted if no starting or ending code units are recorded. +.P +The \fBcallout_info\fP modifier requests information about all the callouts in +the pattern. A list of them is output at the end of any other information that +is requested. For each callout, either its number or string is given, followed +by the item that follows it in the pattern. . . .SS "Specifying a pattern in hex" @@ -1437,6 +1443,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 16 March 2015 +Last updated: 22 March 2015 Copyright (c) 1997-2015 University of Cambridge. .fi diff --git a/doc/pcre2test.txt b/doc/pcre2test.txt index b459c58..1a59b36 100644 --- a/doc/pcre2test.txt +++ b/doc/pcre2test.txt @@ -59,41 +59,48 @@ INPUT ENCODING Input to pcre2test is processed line by line, either by calling the C library's fgets() function, or via the libreadline library (see below). - In Unix-like environments, fgets() treats any bytes other than newline - as data characters. However, in some Windows environments character 26 - (hex 1A) causes an immediate end of file, and no further data is read. - For maximum portability, therefore, it is safest to avoid non-printing - characters in pcre2test input files. + The input is processed using using C's string functions, so must not + contain binary zeroes, even though in Unix-like environments, fgets() + treats any bytes other than newline as data characters. In some Windows + environments character 26 (hex 1A) causes an immediate end of file, and + no further data is read. + + For maximum portability, therefore, it is safest to avoid non-printing + characters in pcre2test input files. There is a facility for specifying + a pattern's characters as hexadecimal pairs, thus making it possible to + include binary zeroes in a pattern for testing purposes. Subject lines + are processed for backslash escapes, which makes it possible to include + any data value. COMMAND LINE OPTIONS -8 If the 8-bit library has been built, this option causes it to - be used (this is the default). If the 8-bit library has not + be used (this is the default). If the 8-bit library has not been built, this option causes an error. - -16 If the 16-bit library has been built, this option causes it - to be used. If only the 16-bit library has been built, this - is the default. If the 16-bit library has not been built, + -16 If the 16-bit library has been built, this option causes it + to be used. If only the 16-bit library has been built, this + is the default. If the 16-bit library has not been built, this option causes an error. - -32 If the 32-bit library has been built, this option causes it - to be used. If only the 32-bit library has been built, this - is the default. If the 32-bit library has not been built, + -32 If the 32-bit library has been built, this option causes it + to be used. If only the 32-bit library has been built, this + is the default. If the 32-bit library has not been built, this option causes an error. - -b Behave as if each pattern has the /fullbincode modifier; the + -b Behave as if each pattern has the /fullbincode modifier; the full internal binary form of the pattern is output after com- pilation. - -C Output the version number of the PCRE2 library, and all - available information about the optional features that are - included, and then exit with zero exit code. All other + -C Output the version number of the PCRE2 library, and all + available information about the optional features that are + included, and then exit with zero exit code. All other options are ignored. - -C option Output information about a specific build-time option, then - exit. This functionality is intended for use in scripts such - as RunTest. The following options output the value and set + -C option Output information about a specific build-time option, then + exit. This functionality is intended for use in scripts such + as RunTest. The following options output the value and set the exit code as indicated: ebcdic-nl the code for LF (= NL) in an EBCDIC environment: @@ -109,7 +116,7 @@ COMMAND LINE OPTIONS ANYCRLF or ANY exit code is always 0 - The following options output 1 for true or 0 for false, and + The following options output 1 for true or 0 for false, and set the exit code to the same value: ebcdic compiled for an EBCDIC environment @@ -119,15 +126,15 @@ COMMAND LINE OPTIONS pcre2-8 the 8-bit library was built unicode Unicode support is available - If an unknown option is given, an error message is output; + If an unknown option is given, an error message is output; the exit code is 0. - -d Behave as if each pattern has the debug modifier; the inter- + -d Behave as if each pattern has the debug modifier; the inter- nal form and information about the compiled pattern is output after compilation; -d is equivalent to -b -i. -dfa Behave as if each subject line has the dfa modifier; matching - is done using the pcre2_dfa_match() function instead of the + is done using the pcre2_dfa_match() function instead of the default pcre2_match(). -help Output a brief summary these options and then exit. @@ -135,8 +142,8 @@ COMMAND LINE OPTIONS -i Behave as if each pattern has the /info modifier; information about the compiled pattern is given after compilation. - -jit Behave as if each pattern line has the jit modifier; after - successful compilation, each pattern is passed to the just- + -jit Behave as if each pattern line has the jit modifier; after + successful compilation, each pattern is passed to the just- in-time compiler, if available. -pattern modifier-list @@ -145,25 +152,25 @@ COMMAND LINE OPTIONS -q Do not output the version number of pcre2test at the start of execution. - -S size On Unix-like systems, set the size of the run-time stack to + -S size On Unix-like systems, set the size of the run-time stack to size megabytes. -subject modifier-list Behave as if each subject line contains the given modifiers. - -t Run each compile and match many times with a timer, and out- - put the resulting times per compile or match. When JIT is - used, separate times are given for the initial compile and - the JIT compile. You can control the number of iterations - that are used for timing by following -t with a number (as a - separate item on the command line). For example, "-t 1000" + -t Run each compile and match many times with a timer, and out- + put the resulting times per compile or match. When JIT is + used, separate times are given for the initial compile and + the JIT compile. You can control the number of iterations + that are used for timing by following -t with a number (as a + separate item on the command line). For example, "-t 1000" iterates 1000 times. The default is to iterate 500,000 times. -tm This is like -t except that it times only the matching phase, not the compile phase. - -T -TM These behave like -t and -tm, but in addition, at the end of - a run, the total times for all compiles and matches are out- + -T -TM These behave like -t and -tm, but in addition, at the end of + a run, the total times for all compiles and matches are out- put. -version Output the PCRE2 version number and then exit. @@ -171,158 +178,158 @@ COMMAND LINE OPTIONS DESCRIPTION - If pcre2test is given two filename arguments, it reads from the first + If pcre2test is given two filename arguments, it reads from the first and writes to the second. If the first name is "-", input is taken from - the standard input. If pcre2test is given only one argument, it reads + the standard input. If pcre2test is given only one argument, it reads from that file and writes to stdout. Otherwise, it reads from stdin and writes to stdout. - When pcre2test is built, a configuration option can specify that it - should be linked with the libreadline or libedit library. When this is - done, if the input is from a terminal, it is read using the readline() + When pcre2test is built, a configuration option can specify that it + should be linked with the libreadline or libedit library. When this is + done, if the input is from a terminal, it is read using the readline() function. This provides line-editing and history facilities. The output from the -help option states whether or not readline() will be used. - The program handles any number of tests, each of which consists of a - set of input lines. Each set starts with a regular expression pattern, + The program handles any number of tests, each of which consists of a + set of input lines. Each set starts with a regular expression pattern, followed by any number of subject lines to be matched against that pat- tern. In between sets of test data, command lines that begin with # may appear. This file format, with some restrictions, can also be processed - by the perltest.sh script that is distributed with PCRE2 as a means of + by the perltest.sh script that is distributed with PCRE2 as a means of checking that the behaviour of PCRE2 and Perl is the same. When the input is a terminal, pcre2test prompts for each line of input, - using "re>" to prompt for regular expression patterns, and "data>" to - prompt for subject lines. Command lines starting with # can be entered + using "re>" to prompt for regular expression patterns, and "data>" to + prompt for subject lines. Command lines starting with # can be entered only in response to the "re>" prompt. - Each subject line is matched separately and independently. If you want + Each subject line is matched separately and independently. If you want to do multi-line matches, you have to use the \n escape sequence (or \r - or \r\n, etc., depending on the newline setting) in a single line of - input to encode the newline sequences. There is no limit on the length - of subject lines; the input buffer is automatically extended if it is - too small. There 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 # is interpreted + In between sets of test data, a line that begins with # is interpreted as a command line. If the first character is followed by white space or - an exclamation mark, the line is treated as a comment, and ignored. + an exclamation mark, the line is treated as a comment, and ignored. Otherwise, the following commands are recognized: #forbid_utf - Subsequent patterns automatically have the PCRE2_NEVER_UTF and + 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 + property features. This is a trigger guard that is used in test files to ensure that UTF or Unicode property tests are not accidentally added - to files that are used when Unicode support is not included in the - library. 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 + to files that are used when Unicode 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. #load This command is used to load a set of precompiled patterns from a file, - as described in the section entitled "Saving and restoring compiled + as described in the section entitled "Saving and restoring compiled patterns" below. #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.sh script, which is used - to confirm that Perl gives the same results as PCRE2. Also, apart from - comment lines, none of the other command lines are permitted, because - they and many of the modifiers are specific to pcre2test, and should - not be used in test files that are also processed by perltest.sh. The - #perltest command helps detect tests that are accidentally put in the + to confirm that Perl gives the same results as PCRE2. Also, apart from + comment lines, none of the other command lines are permitted, because + they and many of the modifiers are specific to pcre2test, and should + not be used in test files that are also processed by perltest.sh. The + #perltest command helps detect tests that are accidentally put in the wrong file. #pop [] - This command is used to manipulate the stack of compiled patterns, as - described in the section entitled "Saving and restoring compiled pat- + This command is used to manipulate the stack of compiled patterns, as + described in the section entitled "Saving and restoring compiled pat- terns" below. #save - This command is used to save a set of compiled patterns to a file, as - described in the section entitled "Saving and restoring compiled pat- + This command is used to save a set of compiled patterns to a file, as + described in the section entitled "Saving and restoring compiled pat- terns" below. #subject - 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 setting. A few of the more common modifiers can also be specified as single let- - ters, for example "i" for "caseless". In documentation, following the + ters, for example "i" for "caseless". In documentation, following the Perl convention, these are written with a slash ("the /i modifier") for - clarity. Abbreviated modifiers must all be concatenated in the first - item of a modifier list. If the first item is not recognized as a long - modifier name, it is interpreted as a sequence of these abbreviations. + clarity. Abbreviated modifiers must all be concatenated in the first + item of a modifier list. If the first item is not recognized as a long + modifier name, it is interpreted as a sequence of these abbreviations. For example: /abc/ig,newline=cr,jit=3 - This is a pattern line whose modifier list starts with two one-letter - modifiers (/i and /g). The lower-case abbreviated modifiers are the + This is a pattern line whose modifier list starts with two one-letter + modifiers (/i and /g). The lower-case abbreviated modifiers are the same as used in Perl. PATTERN SYNTAX - A pattern line must start with one of the following characters (common + A pattern line must start with one of the following characters (common symbols, excluding pattern meta-characters): / ! " ' ` - = _ : ; , % & @ ~ - This is interpreted as the pattern's delimiter. A regular expression - may be continued over several input lines, in which case the newline + This is interpreted as the pattern's delimiter. A regular expression + may be continued over several input lines, in which case the newline characters are included within it. It is possible to include the delim- iter within the pattern by escaping it with a backslash, for example /abc\/def/ - If you do this, the escape and the delimiter form part of the pattern, + If you do this, the escape and the delimiter form part of the pattern, but since the delimiters are all non-alphanumeric, this does not affect - its interpretation. If the terminating delimiter is immediately fol- + its interpretation. If the terminating delimiter is immediately fol- lowed by a backslash, for example, /abc/\ - then a backslash is added to the end of the pattern. This is done to - provide a way of testing the error condition that arises if a pattern + then a backslash is added to the end of the pattern. This is done to + provide a way of testing the error condition that arises if a pattern finishes with a backslash, because /abc\/ - is interpreted as the first line of a pattern that starts with "abc/", - causing pcre2test to read the next line as a continuation of the regu- + is interpreted as the first line of a pattern that starts with "abc/", + causing pcre2test to read the next line as a continuation of the regu- lar expression. A pattern can be followed by a modifier list (details below). @@ -330,7 +337,7 @@ 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: @@ -350,23 +357,23 @@ 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 @@ -374,38 +381,38 @@ 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 marks the end of the subject + A backslash followed by an equals sign marks the end of the subject string and the start of a modifier list. For example: abc\=notbol,notempty - 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 @@ -432,17 +439,18 @@ 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 /B bincode show binary code without lengths + callout_info show callout information debug same as info,fullbincode fullbincode show binary code with lengths /I info show info about compiled pattern @@ -463,34 +471,34 @@ 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 in subject lines. The type must be one of CR, LF, CRLF, ANYCRLF, or ANY (in upper or lower case). Information about a pattern - The debug modifier is a shorthand for info,fullbincode, requesting all + The debug modifier is a shorthand for info,fullbincode, requesting all available information. The bincode modifier causes a representation of the compiled code to be - output after compilation. This information does not contain length and + output after compilation. This information does not contain length and offset values, which ensures that the same output is generated for dif- - ferent internal link sizes and different code unit widths. By using - bincode, the same regression tests can be used in different environ- + ferent internal link sizes and different code unit widths. By using + bincode, the same regression tests can be used in different environ- ments. - The fullbincode modifier, by contrast, does include length and offset - values. This is used in a few special tests that run only for specific + The fullbincode modifier, by contrast, does include length and offset + values. This is used in a few special tests that run only for specific code unit widths and link sizes, and is also useful for one-off tests. - The info modifier requests information about the compiled pattern - (whether it is anchored, has a fixed first character, and so on). The - information is obtained from the pcre2_pattern_info() function. Here + The info modifier requests information about the compiled pattern + (whether it is anchored, has a fixed first character, and so on). The + information is obtained from the pcre2_pattern_info() function. Here are some typical examples: re> /(?i)(^a|^b)/m,info @@ -508,16 +516,21 @@ PATTERN MODIFIERS Last code unit = 'c' (caseless) Subject length lower bound = 3 - "Compile options" are those specified by modifiers; "overall options" - have added options that are taken or deduced from the pattern. If both - sets of options are the same, just a single "options" line is output; - if there are no options, the line is omitted. "First code unit" is - where any match must start; if there is more than one they are listed - as "starting code units". "Last code unit" is the last literal code - unit that must be present in any match. This is not necessarily the - last character. These lines are omitted if no starting or ending code + "Compile options" are those specified by modifiers; "overall options" + have added options that are taken or deduced from the pattern. If both + sets of options are the same, just a single "options" line is output; + if there are no options, the line is omitted. "First code unit" is + where any match must start; if there is more than one they are listed + as "starting code units". "Last code unit" is the last literal code + unit that must be present in any match. This is not necessarily the + last character. These lines are omitted if no starting or ending code units are recorded. + The callout_info modifier requests information about all the callouts + in the pattern. A list of them is output at the end of any other infor- + mation that is requested. For each callout, either its number or string + is given, followed by the item that follows it in the pattern. + Specifying a pattern in hex The hex modifier specifies that the characters of the pattern are to be @@ -808,11 +821,15 @@ SUBJECT MODIFIERS The callout_fail modifier can be given one or two numbers. If there is only one number, 1 is returned instead of 0 when a callout of that num- ber is reached. If two numbers are given, 1 is returned when callout - is reached for the th time. + is reached for the th time. Note that callouts with string argu- + ments are always given the number zero. See "Callouts" below for a + description of the output when a callout it taken. The callout_data modifier can be given an unsigned or a negative num- - ber. Any value other than zero is used as a return from pcre2test's - callout function. + ber. This is set as the "user data" that is passed to the matching + function, and passed back when the callout function is invoked. Any + value other than zero is used as a return from pcre2test's callout + function. Finding all matches in a string @@ -1136,22 +1153,37 @@ RESTARTING AFTER A PARTIAL MATCH CALLOUTS If the pattern contains any callout requests, pcre2test's callout func- - tion is called during matching. This works with both matching func- - tions. By default, the called function displays the callout number, the - start and current positions in the text at the callout time, and the + tion is called during matching unless callout_none is specified. This + works with both matching functions. + + The callout function in pcre2test returns zero (carry on matching) by + default, but you can use a callout_fail modifier in a subject line (as + described above) to change this and other parameters of the callout. + + Inserting callouts can be helpful when using pcre2test to check compli- + cated regular expressions. For further information about callouts, see + the pcre2callout documentation. + + The output for callouts with numerical arguments and those with string + arguments is slightly different. + + Callouts with numerical arguments + + By default, the callout function displays the callout number, the start + and current positions in the subject text at the callout time, and the next pattern item to be tested. For example: --->pqrabcdef 0 ^ ^ \d - This output indicates that callout number 0 occurred for a match - attempt starting at the fourth character of the subject string, when - the pointer was at the seventh character, and when the next pattern - item was \d. Just one circumflex is output if the start and current + This output indicates that callout number 0 occurred for a match + attempt starting at the fourth character of the subject string, when + the pointer was at the seventh character, and when the next pattern + item was \d. Just one circumflex is output if the start and current positions are the same. Callouts numbered 255 are assumed to be automatic callouts, inserted as - a result of the /auto_callout pattern modifier. In this case, instead + a result of the /auto_callout pattern modifier. In this case, instead of showing the callout number, the offset in the pattern, preceded by a plus, is output. For example: @@ -1165,7 +1197,7 @@ CALLOUTS 0: E* If a pattern contains (*MARK) items, an additional line is output when- - ever a change of latest mark is passed to the callout function. For + ever a change of latest mark is passed to the callout function. For example: re> /a(*MARK:X)bc/auto_callout @@ -1179,76 +1211,86 @@ CALLOUTS +12 ^ ^ 0: abc - The mark changes between matching "a" and "b", but stays the same for - the rest of the match, so nothing more is output. If, as a result of - backtracking, the mark reverts to being unset, the text "" is + The mark changes between matching "a" and "b", but stays the same for + the rest of the match, so nothing more is output. If, as a result of + backtracking, the mark reverts to being unset, the text "" is output. - The callout function in pcre2test returns zero (carry on matching) by - default, but you can use a callout_fail modifier in a subject line (as - described above) to change this and other parameters of the callout. + Callouts with string arguments - Inserting callouts can be helpful when using pcre2test to check compli- - cated regular expressions. For further information about callouts, see - the pcre2callout documentation. + The output for a callout with a string argument is similar, except that + instead of outputting a callout number before the position indicators, + the callout string and its offset in the pattern string are output + before the reflection of the subject string, and the subject string is + reflected for each callout. For example: + + re> /^ab(?C'first')cd(?C"second")ef/ + data> abcdefg + Callout (7): 'first' + --->abcdefg + ^ ^ c + Callout (20): "second" + --->abcdefg + ^ ^ e + 0: abcdef NON-PRINTING CHARACTERS When pcre2test is outputting text in the compiled version of a pattern, - bytes other than 32-126 are always treated as non-printing characters + bytes other than 32-126 are always treated as non-printing characters and are therefore shown as hex escapes. - When pcre2test is outputting text that is a matched part of a subject - string, it behaves in the same way, unless a different locale has been - set for the pattern (using the /locale modifier). In this case, the - isprint() function is used to distinguish printing and non-printing + When pcre2test is outputting text that is a matched part of a subject + string, it behaves in the same way, unless a different locale has been + set for the pattern (using the /locale modifier). In this case, the + isprint() function is used to distinguish printing and non-printing characters. SAVING AND RESTORING COMPILED PATTERNS - It is possible to save compiled patterns on disc or elsewhere, and + It is possible to save compiled patterns on disc or elsewhere, and reload them later, subject to a number of restrictions. JIT data cannot - be saved. The host on which the patterns are reloaded must be running + be saved. The host on which the patterns are reloaded must be running the same version of PCRE2, with the same code unit width, and must also - have the same endianness, pointer width and PCRE2_SIZE type. Before - compiled patterns can be saved they must be serialized, that is, con- - verted to a stream of bytes. A single byte stream may contain any num- - ber of compiled patterns, but they must all use the same character + have the same endianness, pointer width and PCRE2_SIZE type. Before + compiled patterns can be saved they must be serialized, that is, con- + verted to a stream of bytes. A single byte stream may contain any num- + ber of compiled patterns, but they must all use the same character tables. A single copy of the tables is included in the byte stream (its size is 1088 bytes). - The functions whose names begin with pcre2_serialize_ are used for - serializing and de-serializing. They are described in the pcre2serial- + The functions whose names begin with pcre2_serialize_ are used for + serializing and de-serializing. They are described in the pcre2serial- ize documentation. In this section we describe the features of pcre2test that can be used to test these functions. - When a pattern with push modifier is successfully compiled, it is - pushed onto a stack of compiled patterns, and pcre2test expects the - next line to contain a new pattern (or command) instead of a subject + When a pattern with push modifier is successfully compiled, it is + pushed onto a stack of compiled patterns, and pcre2test expects the + next line to contain a new pattern (or command) instead of a subject line. By this means, a number of patterns can be compiled and retained. - The push modifier is incompatible with posix, and control modifiers + The push modifier is incompatible with posix, and control modifiers that act at match time are ignored (with a message). The jitverify mod- ifier applies only at compile time. The command #save causes all the stacked patterns to be serialized and the result written - to the named file. Afterwards, all the stacked patterns are freed. The + to the named file. Afterwards, all the stacked patterns are freed. The command #load - reads the data in the file, and then arranges for it to be de-serial- - ized, with the resulting compiled patterns added to the pattern stack. - The pattern on the top of the stack can be retrieved by the #pop com- - mand, which must be followed by lines of subjects that are to be - matched with the pattern, terminated as usual by an empty line or end - of file. This command may be followed by a modifier list containing - only control modifiers that act after a pattern has been compiled. In - particular, hex, posix, and push are not allowed, nor are any option- - setting modifiers. The JIT modifiers are, however permitted. Here is + reads the data in the file, and then arranges for it to be de-serial- + ized, with the resulting compiled patterns added to the pattern stack. + The pattern on the top of the stack can be retrieved by the #pop com- + mand, which must be followed by lines of subjects that are to be + matched with the pattern, terminated as usual by an empty line or end + of file. This command may be followed by a modifier list containing + only control modifiers that act after a pattern has been compiled. In + particular, hex, posix, and push are not allowed, nor are any option- + setting modifiers. The JIT modifiers are, however permitted. Here is an example that saves and reloads two patterns. /abc/push @@ -1261,7 +1303,7 @@ SAVING AND RESTORING COMPILED PATTERNS #pop jit,bincode abc - If jitverify is used with #pop, it does not automatically imply jit, + If jitverify is used with #pop, it does not automatically imply jit, which is different behaviour from when it is used on a pattern. @@ -1280,5 +1322,5 @@ AUTHOR REVISION - Last updated: 23 January 2015 + Last updated: 22 March 2015 Copyright (c) 1997-2015 University of Cambridge. diff --git a/src/pcre2.h.in b/src/pcre2.h.in index d73cdda..79f4d25 100644 --- a/src/pcre2.h.in +++ b/src/pcre2.h.in @@ -342,7 +342,19 @@ typedef struct pcre2_callout_block { \ PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \ PCRE2_SPTR callout_string; /* String compiled into pattern */ \ /* ------------------------------------------------------------------ */ \ -} pcre2_callout_block; +} pcre2_callout_block; \ +\ +typedef struct pcre2_callout_enumerate_block { \ + uint32_t version; /* Identifies version of block */ \ + /* ------------------------ Version 0 ------------------------------- */ \ + PCRE2_SIZE pattern_position; /* Offset to next item in the pattern */ \ + PCRE2_SIZE next_item_length; /* Length of next item in the pattern */ \ + uint32_t callout_number; /* Number compiled into pattern */ \ + PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \ + PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \ + PCRE2_SPTR callout_string; /* String compiled into pattern */ \ + /* ------------------------------------------------------------------ */ \ +} pcre2_callout_enumerate_block; /* List the generic forms of all other functions in macros, which will be @@ -410,6 +422,9 @@ PCRE2_EXP_DECL void pcre2_code_free(pcre2_code *); #define PCRE2_PATTERN_INFO_FUNCTIONS \ PCRE2_EXP_DECL int pcre2_pattern_info(const pcre2_code *, uint32_t, \ + void *); \ +PCRE2_EXP_DECL int pcre2_callout_enumerate(const pcre2_code *, \ + int (*)(pcre2_callout_enumerate_block *, void *), \ void *); @@ -538,15 +553,17 @@ pcre2_compile are called by application code. */ /* Data blocks */ -#define pcre2_callout_block PCRE2_SUFFIX(pcre2_callout_block_) -#define pcre2_general_context PCRE2_SUFFIX(pcre2_general_context_) -#define pcre2_compile_context PCRE2_SUFFIX(pcre2_compile_context_) -#define pcre2_match_context PCRE2_SUFFIX(pcre2_match_context_) -#define pcre2_match_data PCRE2_SUFFIX(pcre2_match_data_) +#define pcre2_callout_block PCRE2_SUFFIX(pcre2_callout_block_) +#define pcre2_callout_enumerate_block PCRE2_SUFFIX(pcre2_callout_enumerate_block_) +#define pcre2_general_context PCRE2_SUFFIX(pcre2_general_context_) +#define pcre2_compile_context PCRE2_SUFFIX(pcre2_compile_context_) +#define pcre2_match_context PCRE2_SUFFIX(pcre2_match_context_) +#define pcre2_match_data PCRE2_SUFFIX(pcre2_match_data_) /* Functions: the complete list in alphabetical order */ +#define pcre2_callout_enumerate PCRE2_SUFFIX(pcre2_callout_enumerate_) #define pcre2_code_free PCRE2_SUFFIX(pcre2_code_free_) #define pcre2_compile PCRE2_SUFFIX(pcre2_compile_) #define pcre2_compile_context_copy PCRE2_SUFFIX(pcre2_compile_context_copy_) @@ -554,7 +571,6 @@ pcre2_compile are called by application code. */ #define pcre2_compile_context_free PCRE2_SUFFIX(pcre2_compile_context_free_) #define pcre2_config PCRE2_SUFFIX(pcre2_config_) #define pcre2_dfa_match PCRE2_SUFFIX(pcre2_dfa_match_) -#define pcre2_match PCRE2_SUFFIX(pcre2_match_) #define pcre2_general_context_copy PCRE2_SUFFIX(pcre2_general_context_copy_) #define pcre2_general_context_create PCRE2_SUFFIX(pcre2_general_context_create_) #define pcre2_general_context_free PCRE2_SUFFIX(pcre2_general_context_free_) @@ -570,6 +586,7 @@ pcre2_compile are called by application code. */ #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 PCRE2_SUFFIX(pcre2_match_) #define pcre2_match_context_copy PCRE2_SUFFIX(pcre2_match_context_copy_) #define pcre2_match_context_create PCRE2_SUFFIX(pcre2_match_context_create_) #define pcre2_match_context_free PCRE2_SUFFIX(pcre2_match_context_free_) diff --git a/src/pcre2_pattern_info.c b/src/pcre2_pattern_info.c index b743a11..9ac01ec 100644 --- a/src/pcre2_pattern_info.c +++ b/src/pcre2_pattern_info.c @@ -225,4 +225,181 @@ switch(what) return 0; } + + +/************************************************* +* Callout enumerator * +*************************************************/ + +/* +Arguments: + code points to compiled code + callback function called for each callout block + callout_data user data passed to the callback + +Returns: 0 when successfully completed + < 0 on local error + != 0 for callback error +*/ + +PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION +pcre2_callout_enumerate(const pcre2_code *code, + int (*callback)(pcre2_callout_enumerate_block *, void *), void *callout_data) +{ +pcre2_real_code *re = (pcre2_real_code *)code; +pcre2_callout_enumerate_block cb; +PCRE2_SPTR cc; +#ifdef SUPPORT_UNICODE +BOOL utf = (re->overall_options & PCRE2_UTF) != 0; +#endif + +if (re == NULL) return PCRE2_ERROR_NULL; + +/* Check that the first field in the block is the magic number. If it is not, +return with PCRE2_ERROR_BADMAGIC. */ + +if (re->magic_number != MAGIC_NUMBER) return PCRE2_ERROR_BADMAGIC; + +/* Check that this pattern was compiled in the correct bit mode */ + +if ((re->flags & (PCRE2_CODE_UNIT_WIDTH/8)) == 0) return PCRE2_ERROR_BADMODE; + +cb.version = 0; +cc = (PCRE2_SPTR)((uint8_t *)re + sizeof(pcre2_real_code)) + + re->name_count * re->name_entry_size; + +while (TRUE) + { + int rc; + switch (*cc) + { + case OP_END: + return 0; + + case OP_CHAR: + case OP_CHARI: + case OP_NOT: + case OP_NOTI: + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + case OP_UPTO: + case OP_MINUPTO: + case OP_EXACT: + case OP_POSSTAR: + case OP_POSPLUS: + case OP_POSQUERY: + case OP_POSUPTO: + case OP_STARI: + case OP_MINSTARI: + case OP_PLUSI: + case OP_MINPLUSI: + case OP_QUERYI: + case OP_MINQUERYI: + case OP_UPTOI: + case OP_MINUPTOI: + case OP_EXACTI: + case OP_POSSTARI: + case OP_POSPLUSI: + case OP_POSQUERYI: + case OP_POSUPTOI: + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + case OP_NOTEXACT: + case OP_NOTPOSSTAR: + case OP_NOTPOSPLUS: + case OP_NOTPOSQUERY: + case OP_NOTPOSUPTO: + case OP_NOTSTARI: + case OP_NOTMINSTARI: + case OP_NOTPLUSI: + case OP_NOTMINPLUSI: + case OP_NOTQUERYI: + case OP_NOTMINQUERYI: + case OP_NOTUPTOI: + case OP_NOTMINUPTOI: + case OP_NOTEXACTI: + case OP_NOTPOSSTARI: + case OP_NOTPOSPLUSI: + case OP_NOTPOSQUERYI: + case OP_NOTPOSUPTOI: + cc += PRIV(OP_lengths)[*cc]; +#ifdef SUPPORT_UNICODE + if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); +#endif + break; + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEEXACT: + case OP_TYPEPOSSTAR: + case OP_TYPEPOSPLUS: + case OP_TYPEPOSQUERY: + case OP_TYPEPOSUPTO: + cc += PRIV(OP_lengths)[*cc]; +#ifdef SUPPORT_UNICODE + if (cc[-1] == OP_PROP || cc[-1] == OP_NOTPROP) cc += 2; +#endif + break; + +#if defined SUPPORT_UNICODE || PCRE2_CODE_UNIT_WIDTH != 8 + case OP_XCLASS: + cc += GET(cc, 1); + break; +#endif + + case OP_MARK: + case OP_PRUNE_ARG: + case OP_SKIP_ARG: + case OP_THEN_ARG: + cc += PRIV(OP_lengths)[*cc] + cc[1]; + break; + + case OP_CALLOUT: + cb.pattern_position = GET(cc, 1); + cb.next_item_length = GET(cc, 1 + LINK_SIZE); + cb.callout_number = cc[1 + 2*LINK_SIZE]; + cb.callout_string_offset = 0; + cb.callout_string_length = 0; + cb.callout_string = NULL; + rc = callback(&cb, callout_data); + if (rc != 0) return rc; + cc += PRIV(OP_lengths)[*cc]; + break; + + case OP_CALLOUT_STR: + cb.pattern_position = GET(cc, 1); + cb.next_item_length = GET(cc, 1 + LINK_SIZE); + cb.callout_number = 0; + cb.callout_string_offset = GET(cc, 1 + 3*LINK_SIZE); + cb.callout_string_length = + GET(cc, 1 + 2*LINK_SIZE) - (1 + 4*LINK_SIZE) - 2; + cb.callout_string = cc + (1 + 4*LINK_SIZE) + 1; + rc = callback(&cb, callout_data); + if (rc != 0) return rc; + cc += GET(cc, 1 + 2*LINK_SIZE); + break; + + default: + cc += PRIV(OP_lengths)[*cc]; + break; + } + } +} + /* End of pcre2_pattern_info.c */ diff --git a/src/pcre2test.c b/src/pcre2test.c index ee2d904..f64be14 100644 --- a/src/pcre2test.c +++ b/src/pcre2test.c @@ -382,28 +382,29 @@ either on a pattern or a data line, so they must all be distinct. */ #define CTL_ALTGLOBAL 0x00000010u #define CTL_BINCODE 0x00000020u #define CTL_CALLOUT_CAPTURE 0x00000040u -#define CTL_CALLOUT_NONE 0x00000080u -#define CTL_DFA 0x00000100u -#define CTL_FINDLIMITS 0x00000200u -#define CTL_FULLBINCODE 0x00000400u -#define CTL_GETALL 0x00000800u -#define CTL_GLOBAL 0x00001000u -#define CTL_HEXPAT 0x00002000u -#define CTL_INFO 0x00004000u -#define CTL_JITFAST 0x00008000u -#define CTL_JITVERIFY 0x00010000u -#define CTL_MARK 0x00020000u -#define CTL_MEMORY 0x00040000u -#define CTL_POSIX 0x00080000u -#define CTL_PUSH 0x00100000u -#define CTL_STARTCHAR 0x00200000u -#define CTL_ZERO_TERMINATE 0x00400000u +#define CTL_CALLOUT_INFO 0x00000080u +#define CTL_CALLOUT_NONE 0x00000100u +#define CTL_DFA 0x00000200u +#define CTL_FINDLIMITS 0x00000400u +#define CTL_FULLBINCODE 0x00000800u +#define CTL_GETALL 0x00001000u +#define CTL_GLOBAL 0x00002000u +#define CTL_HEXPAT 0x00004000u +#define CTL_INFO 0x00008000u +#define CTL_JITFAST 0x00010000u +#define CTL_JITVERIFY 0x00020000u +#define CTL_MARK 0x00040000u +#define CTL_MEMORY 0x00080000u +#define CTL_POSIX 0x00100000u +#define CTL_PUSH 0x00200000u +#define CTL_STARTCHAR 0x00400000u +#define CTL_ZERO_TERMINATE 0x00800000u #define CTL_BSR_SET 0x80000000u /* This is informational */ #define CTL_NL_SET 0x40000000u /* This is informational */ #define CTL_DEBUG (CTL_FULLBINCODE|CTL_INFO) /* For setting */ -#define CTL_ANYINFO (CTL_DEBUG|CTL_BINCODE) /* For testing */ +#define CTL_ANYINFO (CTL_DEBUG|CTL_BINCODE|CTL_CALLOUT_INFO) #define CTL_ANYGLOB (CTL_ALTGLOBAL|CTL_GLOBAL) /* These are all the controls that may be set either on a pattern or on a @@ -431,7 +432,7 @@ typedef struct patctl { /* Structure for pattern modifiers. */ uint32_t jit; uint32_t stackguard_test; uint32_t tables_id; - uint8_t locale[LOCALESIZE]; + uint8_t locale[LOCALESIZE]; } patctl; #define MAXCPYGET 10 @@ -494,6 +495,7 @@ static modstruct modlist[] = { { "callout_capture", MOD_DAT, MOD_CTL, CTL_CALLOUT_CAPTURE, DO(control) }, { "callout_data", MOD_DAT, MOD_INS, 0, DO(callout_data) }, { "callout_fail", MOD_DAT, MOD_IN2, 0, DO(cfail) }, + { "callout_info", MOD_PAT, MOD_CTL, CTL_CALLOUT_INFO, PO(control) }, { "callout_none", MOD_DAT, MOD_CTL, CTL_CALLOUT_NONE, DO(control) }, { "caseless", MOD_PATP, MOD_OPT, PCRE2_CASELESS, PO(options) }, { "copy", MOD_DAT, MOD_NN, DO(copy_numbers), DO(copy_names) }, @@ -578,8 +580,8 @@ static modstruct modlist[] = { /* Control bits that are not ignored with 'push'. */ #define PUSH_SUPPORTED_COMPILE_CONTROLS ( \ - CTL_BINCODE|CTL_FULLBINCODE|CTL_HEXPAT|CTL_INFO|CTL_JITVERIFY| \ - CTL_MEMORY|CTL_PUSH|CTL_BSR_SET|CTL_NL_SET) + CTL_BINCODE|CTL_CALLOUT_INFO|CTL_FULLBINCODE|CTL_HEXPAT|CTL_INFO| \ + CTL_JITVERIFY|CTL_MEMORY|CTL_PUSH|CTL_BSR_SET|CTL_NL_SET) /* Controls that apply only at compile time with 'push'. */ @@ -841,6 +843,17 @@ are supported. */ else \ (void)pchars8((PCRE2_SPTR8)(p)+offset, len, utf, f) +#define PCRE2_CALLOUT_ENUMERATE(a,b,c) \ + if (test_mode == PCRE8_MODE) \ + a = pcre2_callout_enumerate_8(compiled_code8, \ + (int (*)(struct pcre2_callout_enumerate_block_8 *, void *))b,c); \ + else if (test_mode == PCRE16_MODE) \ + a = pcre2_callout_enumerate_16(compiled_code16, \ + (int(*)(struct pcre2_callout_enumerate_block_16 *, void *))b,c); \ + else \ + a = pcre2_callout_enumerate_32(compiled_code32, \ + (int (*)(struct pcre2_callout_enumerate_block_32 *, void *))b,c) + #define PCRE2_COMPILE(a,b,c,d,e,f,g) \ if (test_mode == PCRE8_MODE) \ G(a,8) = pcre2_compile_8(G(b,8),c,d,e,f,G(g,8)); \ @@ -1268,6 +1281,14 @@ the three different cases. */ else \ (void)G(pchars,BITTWO)((G(PCRE2_SPTR,BITTWO))(p)+offset, len, utf, f) +#define PCRE2_CALLOUT_ENUMERATE(a,b,c) \ + if (test_mode == G(G(PCRE,BITONE),_MODE)) \ + a = G(pcre2_callout_enumerate,BITONE)(G(compiled_code,BITONE), \ + (int (*)(struct G(pcre2_callout_enumerate_block_,BITONE) *, void *))b,c); \ + else \ + a = G(pcre2_callout_enumerate,BITTWO)(G(compiled_code,BITTWO), \ + (int (*)(struct G(pcre2_callout_enumerate_block_,BITTWO) *, void *))b,c) + #define PCRE2_COMPILE(a,b,c,d,e,f,g) \ if (test_mode == G(G(PCRE,BITONE),_MODE)) \ G(a,BITONE) = G(pcre2_compile_,BITONE)(G(b,BITONE),c,d,e,f,G(g,BITONE)); \ @@ -1588,6 +1609,9 @@ the three different cases. */ lv = pchars8((PCRE2_SPTR8)(p)+offset, len, utf, f) #define PCHARSV(p, offset, len, utf, f) \ (void)pchars8((PCRE2_SPTR8)(p)+offset, len, utf, f) +#define PCRE2_CALLOUT_ENUMERATE(a,b,c) \ + a = pcre2_callout_enumerate_8(compiled_code8, \ + (int (*)(struct pcre2_callout_enumerate_block_8 *, void *))b,c) #define PCRE2_COMPILE(a,b,c,d,e,f,g) \ G(a,8) = pcre2_compile_8(G(b,8),c,d,e,f,G(g,8)) #define PCRE2_DFA_MATCH(a,b,c,d,e,f,g,h,i,j) \ @@ -1676,6 +1700,9 @@ the three different cases. */ lv = pchars16((PCRE2_SPTR16)(p)+offset, len, utf, f) #define PCHARSV(p, offset, len, utf, f) \ (void)pchars16((PCRE2_SPTR16)(p)+offset, len, utf, f) +#define PCRE2_CALLOUT_ENUMERATE(a,b,c) \ + a = pcre2_callout_enumerate_16(compiled_code16, \ + (int (*)(struct pcre2_callout_enumerate_block_16 *, void *))b,c) #define PCRE2_COMPILE(a,b,c,d,e,f,g) \ G(a,16) = pcre2_compile_16(G(b,16),c,d,e,f,G(g,16)) #define PCRE2_DFA_MATCH(a,b,c,d,e,f,g,h,i,j) \ @@ -1764,6 +1791,9 @@ the three different cases. */ lv = pchars32((PCRE2_SPTR32)(p)+offset, len, utf, f) #define PCHARSV(p, offset, len, utf, f) \ (void)pchars32((PCRE2_SPTR32)(p)+offset, len, utf, f) +#define PCRE2_CALLOUT_ENUMERATE(a,b,c) \ + a = pcre2_callout_enumerate_32(compiled_code32, \ + (int (*)(struct pcre2_callout_enumerate_block_32 *, void *))b,c) #define PCRE2_COMPILE(a,b,c,d,e,f,g) \ G(a,32) = pcre2_compile_32(G(b,32),c,d,e,f,G(g,32)) #define PCRE2_DFA_MATCH(a,b,c,d,e,f,g,h,i,j) \ @@ -3381,7 +3411,7 @@ Returns: nothing static void show_controls(uint32_t controls, const char *before) { -fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", +fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", before, ((controls & CTL_AFTERTEXT) != 0)? " aftertext" : "", ((controls & CTL_ALLAFTERTEXT) != 0)? " allaftertext" : "", @@ -3390,6 +3420,7 @@ fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", ((controls & CTL_ALTGLOBAL) != 0)? " altglobal" : "", ((controls & CTL_BINCODE) != 0)? " bincode" : "", ((controls & CTL_CALLOUT_CAPTURE) != 0)? " callout_capture" : "", + ((controls & CTL_CALLOUT_INFO) != 0)? " callout_info" : "", ((controls & CTL_CALLOUT_NONE) != 0)? " callout_none" : "", ((controls & CTL_DFA) != 0)? " dfa" : "", ((controls & CTL_FINDLIMITS) != 0)? " find_limits" : "", @@ -3517,6 +3548,56 @@ if (pat_patctl.jit != 0) +/************************************************* +* Callback function for callout enumeration * +*************************************************/ + +/* The only differences in the callout emumeration block for different code +unit widths are that the pointers to the subject, the most recent MARK, and a +callout argument string point to strings of the appropriate width. Casts can be +used to deal with this. + +Argument: + cb pointer to enumerate block + callout_data user data + +Returns: 0 +*/ + +static int callout_callback(pcre2_callout_enumerate_block_8 *cb, + void *callout_data) +{ +uint32_t i; +BOOL utf = (FLD(compiled_code, overall_options) & PCRE2_UTF) != 0; + +(void)callout_data; /* Not currently displayed */ + +fprintf(outfile, "Callout "); +if (cb->callout_string != NULL) + { + uint32_t delimiter = CODE_UNIT(cb->callout_string, -1); + fprintf(outfile, "%c", delimiter); + PCHARSV(cb->callout_string, 0, + cb->callout_string_length, utf, outfile); + for (i = 0; callout_start_delims[i] != 0; i++) + if (delimiter == callout_start_delims[i]) + { + delimiter = callout_end_delims[i]; + break; + } + fprintf(outfile, "%c ", delimiter); + } +else fprintf(outfile, "%d ", cb->callout_number); + +fprintf(outfile, "%.*s\n", + (int)((cb->next_item_length == 0)? 1 : cb->next_item_length), + pbuffer8 + cb->pattern_position); + +return 0; +} + + + /************************************************* * Show information about a pattern * *************************************************/ @@ -3789,6 +3870,24 @@ if ((pat_patctl.control & CTL_INFO) != 0) } } +if ((pat_patctl.control & CTL_CALLOUT_INFO) != 0) + { + int errorcode; + PCRE2_CALLOUT_ENUMERATE(errorcode, callout_callback, 0); + if (errorcode != 0) + { + int len; + fprintf(outfile, "Callout enumerate failed: error %d: ", errorcode); + if (errorcode < 0) + { + PCRE2_GET_ERROR_MESSAGE(len, errorcode, pbuffer); + PCHARSV(CASTVAR(void *, pbuffer), 0, len, FALSE, outfile); + } + fprintf(outfile, "\n"); + return PR_SKIP; + } + } + return PR_OK; } @@ -4534,37 +4633,37 @@ uint32_t i, pre_start, post_start, subject_length; BOOL utf = (FLD(compiled_code, overall_options) & PCRE2_UTF) != 0; BOOL callout_capture = (dat_datctl.control & CTL_CALLOUT_CAPTURE) != 0; -/* This FILE is used for echoing the subject. This is done only once in simple +/* This FILE is used for echoing the subject. This is done only once in simple cases. */ -FILE *f = (first_callout || callout_capture || cb->callout_string != NULL)? +FILE *f = (first_callout || callout_capture || cb->callout_string != NULL)? outfile : NULL; -/* For a callout with a string argument, show the string first because there +/* For a callout with a string argument, show the string first because there isn't a tidy way to fit it in the rest of the data. */ if (cb->callout_string != NULL) { - uint32_t delimiter = CODE_UNIT(cb->callout_string, -1); - fprintf(outfile, "Callout (%lu): %c", + uint32_t delimiter = CODE_UNIT(cb->callout_string, -1); + fprintf(outfile, "Callout (%lu): %c", (unsigned long int)cb->callout_string_offset, delimiter); PCHARSV(cb->callout_string, 0, cb->callout_string_length, utf, outfile); for (i = 0; callout_start_delims[i] != 0; i++) if (delimiter == callout_start_delims[i]) - { - delimiter = callout_end_delims[i]; + { + delimiter = callout_end_delims[i]; break; - } - fprintf(outfile, "%c", delimiter); + } + fprintf(outfile, "%c", delimiter); if (!callout_capture) fprintf(outfile, "\n"); - } - -/* Show captured strings if required */ + } + +/* Show captured strings if required */ if (callout_capture) { - if (cb->callout_string == NULL) + if (cb->callout_string == NULL) fprintf(outfile, "Callout %d:", cb->callout_number); fprintf(outfile, " last capture = %d\n", cb->capture_last); for (i = 0; i < cb->capture_top * 2; i += 2) @@ -4580,7 +4679,7 @@ if (callout_capture) fprintf(outfile, "\n"); } } - + /* Re-print the subject in canonical form, the first time or if giving full datails. On subsequent calls in the same match, we use pchars just to find the printed lengths of the substrings. */ @@ -4599,8 +4698,8 @@ PCHARSV(cb->subject, cb->current_position, if (f != NULL) fprintf(f, "\n"); -/* For automatic callouts, show the pattern offset. Otherwise, for a numerical -callout whose number has not already been shown with captured strings, show the +/* For automatic callouts, show the pattern offset. Otherwise, for a numerical +callout whose number has not already been shown with captured strings, show the number here. A callout with a string argument has been displayed above. */ if (cb->callout_number == 255) @@ -4608,13 +4707,13 @@ if (cb->callout_number == 255) fprintf(outfile, "%+3d ", (int)cb->pattern_position); if (cb->pattern_position > 99) fprintf(outfile, "\n "); } -else +else { if (callout_capture || cb->callout_string != NULL) fprintf(outfile, " "); else fprintf(outfile, "%3d ", cb->callout_number); } - -/* Now show position indicators */ + +/* Now show position indicators */ for (i = 0; i < pre_start; i++) fprintf(outfile, " "); fprintf(outfile, "^"); diff --git a/testdata/testinput2 b/testdata/testinput2 index 9adfd4b..9f2be9e 100644 --- a/testdata/testinput2 +++ b/testdata/testinput2 @@ -4206,11 +4206,11 @@ a random value. /Ix /^a(b)c(?C{AB})def/B abcdef\=callout_capture -/(?C`a``b`)(?C'a''b')(?C"a""b")(?C^a^^b^)(?C%a%%b%)(?C#a##b#)(?C$a$$b$)(?C{a}}b})/B +/(?C`a``b`)(?C'a''b')(?C"a""b")(?C^a^^b^)(?C%a%%b%)(?C#a##b#)(?C$a$$b$)(?C{a}}b})/B,callout_info /(?:a(?C`code`)){3}/B -/^(?(?C25)(?=abc)abcd|xyz)/B +/^(?(?C25)(?=abc)abcd|xyz)/B,callout_info abcdefg xyz123 @@ -4226,7 +4226,7 @@ a random value. /Ix # Binary zero in callout string # a ( ? C ' x z ' ) b -/ 61 28 3f 43 27 78 00 7a 27 29 62/hex +/ 61 28 3f 43 27 78 00 7a 27 29 62/hex,callout_info abcdefgh # End of testinput2 diff --git a/testdata/testoutput2 b/testdata/testoutput2 index 02415e9..e1544f8 100644 --- a/testdata/testoutput2 +++ b/testdata/testoutput2 @@ -14060,7 +14060,7 @@ Callout (10): {AB} last capture = 1 0: abcdef 1: b -/(?C`a``b`)(?C'a''b')(?C"a""b")(?C^a^^b^)(?C%a%%b%)(?C#a##b#)(?C$a$$b$)(?C{a}}b})/B +/(?C`a``b`)(?C'a''b')(?C"a""b")(?C^a^^b^)(?C%a%%b%)(?C#a##b#)(?C$a$$b$)(?C{a}}b})/B,callout_info ------------------------------------------------------------------ Bra CalloutStr `a`b` 4 10 0 @@ -14074,6 +14074,14 @@ Callout (10): {AB} last capture = 1 Ket End ------------------------------------------------------------------ +Callout `a`b` ( +Callout 'a'b' ( +Callout "a"b" ( +Callout ^a^b^ ( +Callout %a%b% ( +Callout #a#b# ( +Callout $a$b$ ( +Callout {a}b} /(?:a(?C`code`)){3}/B ------------------------------------------------------------------ @@ -14094,7 +14102,7 @@ Callout (10): {AB} last capture = 1 End ------------------------------------------------------------------ -/^(?(?C25)(?=abc)abcd|xyz)/B +/^(?(?C25)(?=abc)abcd|xyz)/B,callout_info ------------------------------------------------------------------ Bra ^ @@ -14110,6 +14118,7 @@ Callout (10): {AB} last capture = 1 Ket End ------------------------------------------------------------------ +Callout 25 (?=abc) abcdefg --->abcdefg 25 ^ (?=abc) @@ -14171,7 +14180,8 @@ Callout (8): `code` # Binary zero in callout string # a ( ? C ' x z ' ) b -/ 61 28 3f 43 27 78 00 7a 27 29 62/hex +/ 61 28 3f 43 27 78 00 7a 27 29 62/hex,callout_info +Callout 'x\x00z' b abcdefgh Callout (5): 'x\x00z' --->abcdefgh
    pcre2_callout_enumerate  Enumerate callouts in a compiled pattern
    pcre2_code_free   Free a compiled pattern