From 2a5767d7576b1dc5da39b74f6e3e4983a45b7baf Mon Sep 17 00:00:00 2001 From: "Philip.Hazel" Date: Fri, 19 Dec 2014 09:55:25 +0000 Subject: [PATCH] File tidies for 10.00-RC2. --- ChangeLog | 5 +- NEWS | 2 +- configure.ac | 2 +- doc/html/pcre2_substring_copy_byname.html | 12 +- doc/html/pcre2_substring_copy_bynumber.html | 12 +- doc/html/pcre2_substring_get_byname.html | 14 +- doc/html/pcre2_substring_get_bynumber.html | 12 +- doc/html/pcre2api.html | 158 +++- doc/pcre2.txt | 958 +++++++++++--------- doc/pcre2_substring_copy_byname.3 | 6 +- doc/pcre2_substring_get_byname.3 | 4 +- doc/pcre2api.3 | 38 +- src/config.h.generic | 6 +- src/pcre2.h.generic | 54 +- src/pcre2_error.c | 2 +- src/pcre2_internal.h | 2 +- src/pcre2_intmodedep.h | 2 +- src/pcre2_substring.c | 42 +- src/pcre2test.c | 2 +- 19 files changed, 753 insertions(+), 580 deletions(-) diff --git a/ChangeLog b/ChangeLog index 8c641d1..f9dada4 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,7 +1,7 @@ Change Log for PCRE2 -------------------- -Version 10.00 28-November-2014 +Version 10.00 19-December-2014 ------------------------------ Version 10.00 is the first release of PCRE2, a revised API for the PCRE @@ -14,7 +14,8 @@ logged. In addition to the API changes, the following changes were made. They are either new functionality, or bug fixes and other noticeable changes of behaviour that were implemented after the code had been forked. -1. Unicode support is now enabled by default. +1. Unicode support is now enabled by default, but it can optionally be +disabled. 2. The test program, now called pcre2test, was re-specified and almost completely re-written. Its input is not compatible with input for pcretest. diff --git a/NEWS b/NEWS index a63cd2b..838e151 100644 --- a/NEWS +++ b/NEWS @@ -1,7 +1,7 @@ News about PCRE2 releases ------------------------- -Version 10.00 28-November-2014 +Version 10.00 19-December-2014 ------------------------------ Version 10.00 is the first release of PCRE2, a revised API for the PCRE diff --git a/configure.ac b/configure.ac index 6bdc1d0..e495c45 100644 --- a/configure.ac +++ b/configure.ac @@ -11,7 +11,7 @@ dnl be defined as -RC2, for example. For real releases, it should be empty. m4_define(pcre2_major, [10]) m4_define(pcre2_minor, [00]) m4_define(pcre2_prerelease, [-RC2]) -m4_define(pcre2_date, [2014-11-28]) +m4_define(pcre2_date, [2014-12-19]) # NOTE: The CMakeLists.txt file searches for the above variables in the first # 50 lines of this file. Please update that if the variables above are moved. diff --git a/doc/html/pcre2_substring_copy_byname.html b/doc/html/pcre2_substring_copy_byname.html index d83c446..fd01805 100644 --- a/doc/html/pcre2_substring_copy_byname.html +++ b/doc/html/pcre2_substring_copy_byname.html @@ -36,8 +36,16 @@ by name, into a given buffer. The arguments are: The bufflen variable is updated to contain the length of the extracted string, excluding the trailing zero. The yield of the function is zero for -success, PCRE2_ERROR_NOMEMORY if the buffer is too small, or -PCRE2_ERROR_NOSUBSTRING if the string name is invalid. +success or one of the following error numbers: +
+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that name
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      the buffer is not big enough
+
+If there is more than one group with the given name, the first one that is set +is returned. In this situation PCRE2_ERROR_UNSET means that no group with the +given name was set.

There is a complete description of the PCRE2 native API in the diff --git a/doc/html/pcre2_substring_copy_bynumber.html b/doc/html/pcre2_substring_copy_bynumber.html index 0afeecc..83e1a27 100644 --- a/doc/html/pcre2_substring_copy_bynumber.html +++ b/doc/html/pcre2_substring_copy_bynumber.html @@ -36,9 +36,15 @@ buffer. The arguments are: bufflen Length of buffer The bufflen variable is updated with the length of the extracted string, -excluding the terminating zero. The yield of the function is zero for success, -PCRE2_ERROR_NOMEMORY if the buffer was too small, or PCRE2_ERROR_NOSUBSTRING if -the string number is invalid. +excluding the terminating zero. The yield of the function is zero for success +or one of the following error numbers: +

+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that number
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      the buffer is too small
+
+

There is a complete description of the PCRE2 native API in the diff --git a/doc/html/pcre2_substring_get_byname.html b/doc/html/pcre2_substring_get_byname.html index 8d53eb9..a4b8771 100644 --- a/doc/html/pcre2_substring_get_byname.html +++ b/doc/html/pcre2_substring_get_byname.html @@ -37,9 +37,17 @@ newly acquired memory. The arguments are: The memory in which the substring is placed is obtained by calling the same memory allocation function that was used for the match data block. The convenience function pcre2_substring_free() can be used to free it when -it is no longer needed. The yield of the function is zero for success, -PCRE2_ERROR_NOMEMORY if sufficient memory could not be obtained, or -PCRE2_ERROR_NOSUBSTRING if the string name is invalid. +it is no longer needed. The yield of the function is zero for success or one of +the following error numbers: +

+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that name
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      memory could not be obtained
+
+If there is more than one group with the given name, the first one that is set +is returned. In this situation PCRE2_ERROR_UNSET means that no group with the +given name was set.

There is a complete description of the PCRE2 native API in the diff --git a/doc/html/pcre2_substring_get_bynumber.html b/doc/html/pcre2_substring_get_bynumber.html index 5c4ff7c..391bc82 100644 --- a/doc/html/pcre2_substring_get_bynumber.html +++ b/doc/html/pcre2_substring_get_bynumber.html @@ -37,9 +37,15 @@ into newly acquired memory. The arguments are: The memory in which the substring is placed is obtained by calling the same memory allocation function that was used for the match data block. The convenience function pcre2_substring_free() can be used to free it when -it is no longer needed. The yield of the function is zero for success, -PCRE2_ERROR_NOMEMORY if sufficient memory could not be obtained, or -PCRE2_ERROR_NOSUBSTRING if the string number is invalid. +it is no longer needed. The yield of the function is zero for success or one of +the following error numbers: +

+  PCRE2_ERROR_NOSUBSTRING   there are no groups of that number
+  PCRE2_ERROR_UNAVAILBLE    the ovector was too small for that group
+  PCRE2_ERROR_UNSET         the group did not participate in the match
+  PCRE2_ERROR_NOMEMORY      memory could not be obtained
+
+

There is a complete description of the PCRE2 native API in the diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index 9877b8a..b05d917 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -947,6 +947,14 @@ contains the compiled pattern and related data. The caller must free the memory by calling pcre2_code_free() when it is no longer needed.

+NOTE: When one of the matching functions is called, pointers to the compiled +pattern and the subject string are set in the match data block so that they can +be referenced by the extraction functions. After running a match, you must not +free a compiled pattern (or a subject string) until after all operations on the +match data block +have taken place. +

+

If the compile context argument ccontext is NULL, memory for the compiled pattern is obtained by calling malloc(). Otherwise, it is obtained from the same memory function that was used for the compile context. @@ -1690,7 +1698,7 @@ pattern with the JIT compiler does not alter the value returned by this option. void pcre2_match_data_free(pcre2_match_data *match_data);

-Information about successful and unsuccessful matches is placed in a match +Information about a successful or unsuccessful match is placed in a match data block, which is an opaque structure that is accessed by function calls. In particular, the match data block contains a vector of offsets into the subject string that define the matched part of the subject and any substrings that were @@ -1724,15 +1732,24 @@ pattern (custom or default).

A match data block can be used many times, with the same or different compiled -patterns. When it is no longer needed, it should be freed by calling -pcre2_match_data_free(). You can extract information from a match data -block after a match operation has finished, using functions that are described -in the sections on +patterns. You can extract information from a match data block after a match +operation has finished, using functions that are described in the sections on matched strings and other match data below.

+

+When one of the matching functions is called, pointers to the compiled pattern +and the subject string are set in the match data block so that they can be +referenced by the extraction functions. After running a match, you must not +free a compiled pattern or a subject string until after all operations on the +match data block (for that match) have 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

int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject, @@ -2034,8 +2051,14 @@ from a successful match is 1, indicating that just the first pair of offsets has been set.

-If a capturing subpattern is matched repeatedly within a single match -operation, it is the last portion of the string that it matched that is +If a pattern uses the \K escape sequence within a positive assertion, the +reported start of the match can be greater than the end of the match. For +example, if the pattern (?=ab\K) is matched against "ab", the start and end +offset values for the match are 2 and 0. +

+

+If a capturing subpattern group is matched repeatedly within a single match +operation, it is the last portion of the subject that it matched that is returned.

@@ -2234,25 +2257,34 @@ Captured substrings can be accessed directly by using the ovector as described above. For convenience, auxiliary functions are provided for extracting captured substrings as new, separate, zero-terminated strings. The functions in this -section identify substrings by number. The next section describes similar -functions for extracting substrings by name. A substring that contains a binary -zero is correctly extracted and has a further zero added on the end, but the -result is not, of course, a C string. +section identify substrings by number. The number zero refers to the entire +matched substring, with higher numbers referring to substrings captured by +parenthesized groups. The next section describes similar functions for +extracting captured substrings by name. A substring that contains a binary zero +is correctly extracted and has a further zero added on the end, but the result +is not, of course, a C string. +

+

+If a pattern uses the \K escape sequence within a positive assertion, the +reported start of the match can be greater than the end of the match. For +example, if the pattern (?=ab\K) is matched against "ab", the start and end +offset values for the match are 2 and 0. In this situation, calling these +functions with a zero substring number extracts a zero-length empty string.

You can find the length in code units of a captured substring without extracting it by calling pcre2_substring_length_bynumber(). The first argument is a pointer to the match data block, the second is the group number, -and the third is a pointer to a variable into which the length is placed. +and the third is a pointer to a variable into which the length is placed. If +you just want to know whether or not the substring has been captured, you can +pass the third argument as NULL.

-The pcre2_substring_copy_bynumber() function copies one string into a -supplied buffer, whereas pcre2_substring_get_bynumber() copies it into -new memory, obtained using the same memory allocation function that was used -for the match data block. The first two arguments of these functions are a -pointer to the match data block and a capturing group number. A group number of -zero extracts the substring that matched the entire pattern, and higher values -extract the captured substrings. +The pcre2_substring_copy_bynumber() function copies a captured substring +into a supplied buffer, whereas pcre2_substring_get_bynumber() copies it +into new memory, obtained using the same memory allocation function that was +used for the match data block. The first two arguments of these functions are a +pointer to the match data block and a capturing group number.

The final arguments of pcre2_substring_copy_bynumber() are a pointer to @@ -2268,8 +2300,9 @@ zero. When the substring is no longer needed, the memory should be freed by calling pcre2_substring_free().

-The return value from these functions is zero for success, or one of these -error codes: +The return value from all these functions is zero for success, or a negative +error code. If the pattern match failed, the match failure code is returned. +Other possible error codes are: 

   PCRE2_ERROR_NOMEMORY
@@ -2278,10 +2311,20 @@ attempt to get memory failed for pcre2_substring_get_bynumber(). 
   PCRE2_ERROR_NOSUBSTRING
-No substring with the given number was captured. This could be because there is -no capturing group of that number in the pattern, or because the group with -that number did not participate in the match, or because the ovector was too -small to capture that group. +There is no substring with that number in the pattern, that is, the number is +greater than the number of capturing parentheses. +
+  PCRE2_ERROR_UNAVAILABLE
+
+The substring number, though not greater than the number of captures in the +pattern, is greater than the number of slots in the ovector, so the substring +could not be captured. +
+  PCRE2_ERROR_UNSET
+
+The substring did not participate in the match. For example, if the pattern is +(abc)|(def) and the subject is "def", and the ovector contains at least two +capturing slots, substring number 1 is unset.


EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS

@@ -2316,7 +2359,7 @@ capturing subpattern number n+1 matches some part of the subject, but subpattern n has not been used at all, it returns an empty string. This can be distinguished from a genuine zero-length substring by inspecting the appropriate offset in the ovector, which contain PCRE2_UNSET for unset -substrings. +substrings, or by calling pcre2_substring_length_bynumber().


EXTRACTING CAPTURED SUBSTRINGS BY NAME

@@ -2350,14 +2393,22 @@ calling pcre2_substring_number_from_name(). The first argument is the compiled pattern, and the second is the name. The yield of the function is the subpattern number, PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of -that name. +that name. Given the number, you can extract the substring directly, or use one +of the functions described above.

-Given the number, you can extract the substring directly, or use one of the -functions described above. For convenience, there are also "byname" functions -that correspond to the "bynumber" functions, the only difference being that the -second argument is a name instead of a number. However, if PCRE2_DUPNAMES is -set and there are duplicate names, the behaviour may not be what you want. +For convenience, there are also "byname" functions that correspond to the +"bynumber" functions, the only difference being that the second argument is a +name instead of a number. If PCRE2_DUPNAMES is set and there are duplicate +names, these functions scan all the groups with the given name, and return the +first named string that is set. +

+

+If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is +returned. If all groups with the name have numbers that are greater than the +number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is returned. If there +is at least one group with a slot in the ovector, but no group is found to be +set, PCRE2_ERROR_UNSET is returned.

Warning: If the pattern uses the (?| feature to set up multiple @@ -2451,9 +2502,9 @@ documentation.

When duplicates are present, pcre2_substring_copy_byname() and pcre2_substring_get_byname() return the first substring corresponding to -the given name that is set. If none are set, PCRE2_ERROR_NOSUBSTRING is -returned. The pcre2_substring_number_from_name() function returns -the error PCRE2_ERROR_NOUNIQUESUBSTRING. +the given name that is set. Only if none are set is PCRE2_ERROR_UNSET is +returned. The pcre2_substring_number_from_name() function returns the +error PCRE2_ERROR_NOUNIQUESUBSTRING when there are duplicate names.

If you want to get full details of all captured substrings for a given name, @@ -2607,17 +2658,38 @@ is matched against the string the three matched strings are 

-  <something>
-  <something> <something else>
   <something> <something else> <something further>
+  <something> <something else>
+  <something>
On success, the yield of the function is a number greater than zero, which is the number of matched substrings. The offsets of the substrings are returned in -the ovector, and can be extracted in the same way as for pcre2_match(). -They are returned in reverse order of length; that is, the longest -matching string is given first. If there were too many matches to fit into -the ovector, the yield of the function is zero, and the vector is filled with -the longest matches. +the ovector, and can be extracted by number in the same way as for +pcre2_match(), but the numbers bear no relation to any capturing groups +that may exist in the pattern, because DFA matching does not support group +capture. +

+

+Calls to the convenience functions that extract substrings by name +return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used after a +DFA match. The convenience functions that extract substrings by number never +return PCRE2_ERROR_NOSUBSTRING, and the meanings of some other errors are +slightly different: +

+  PCRE2_ERROR_UNAVAILABLE
+
+The ovector is not big enough to include a slot for the given substring number. +
+  PCRE2_ERROR_UNSET
+
+There is a slot in the ovector for this substring, but there were insufficient +matches to fill it. +

+

+The matched strings are stored in the ovector in reverse order of length; that +is, the longest matching string is first. If there were too many matches to fit +into the ovector, the yield of the function is zero, and the vector is filled +with the longest matches.

NOTE: PCRE2's "auto-possessification" optimization usually applies to character @@ -2685,7 +2757,7 @@ Cambridge, England.


REVISION

-Last updated: 01 December 2014 +Last updated: 14 December 2014
Copyright © 1997-2014 University of Cambridge.
diff --git a/doc/pcre2.txt b/doc/pcre2.txt index b45aee9..b7a2f2f 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -995,43 +995,50 @@ COMPILING A PATTERN must free the memory by calling pcre2_code_free() when it is no longer needed. - If the compile context argument ccontext is NULL, memory for the com- - piled pattern is obtained by calling malloc(). Otherwise, it is - obtained from the same memory function that was used for the compile + NOTE: When one of the matching functions is called, pointers to the + compiled pattern and the subject string are set in the match data block + so that they can be referenced by the extraction functions. After run- + ning a match, you must not free a compiled pattern (or a subject + string) until after all operations on the match data block have taken + place. + + If the compile context argument ccontext is NULL, memory for the com- + piled pattern is obtained by calling malloc(). Otherwise, it is + obtained from the same memory function that was used for the compile context. The options argument contains various bit settings that affect the com- - pilation. It should be zero if no options are required. The available - options are described below. Some of them (in particular, those that - are compatible with Perl, but some others as well) can also be set and - unset from within the pattern (see the detailed description in the + pilation. It should be zero if no options are required. The available + options are described below. Some of them (in particular, those that + are compatible with Perl, but some others as well) can also be set and + unset from within the pattern (see the detailed description in the pcre2pattern documentation). - For those options that can be different in different parts of the pat- - tern, the contents of the options argument specifies their settings at - the start of compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK + For those options that can be different in different parts of the pat- + tern, the contents of the options argument specifies their settings at + the start of compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK options can be set at the time of matching as well as at compile time. - Other, less frequently required compile-time parameters (for example, + Other, less frequently required compile-time parameters (for example, the newline setting) can be provided in a compile context (as described above). If errorcode or erroroffset is NULL, pcre2_compile() returns NULL imme- - diately. Otherwise, if compilation of a pattern fails, pcre2_compile() + diately. Otherwise, if compilation of a pattern fails, pcre2_compile() returns NULL, having set these variables to an error code and an offset - (number of code units) within the pattern, respectively. The - pcre2_get_error_message() function provides a textual message for each + (number of code units) within the pattern, respectively. The + pcre2_get_error_message() function provides a textual message for each error code. Compilation errors are positive numbers, but UTF formatting errors are negative numbers. For an invalid UTF-8 or UTF-16 string, the offset is that of the first code unit of the failing character. - Some errors are not detected until the whole pattern has been scanned; - in these cases, the offset passed back is the length of the pattern. - Note that the offset is in code units, not characters, even in a UTF + Some errors are not detected until the whole pattern has been scanned; + in these cases, the offset passed back is the length of the pattern. + Note that the offset is in code units, not characters, even in a UTF mode. It may sometimes point into the middle of a UTF-8 or UTF-16 char- acter. - This code fragment shows a typical straightforward call to pcre2_com- + This code fragment shows a typical straightforward call to pcre2_com- pile(): pcre2_code *re; @@ -1045,158 +1052,158 @@ COMPILING A PATTERN &erroffset, /* for error offset */ NULL); /* no compile context */ - The following names for option bits are defined in the pcre2.h header + The following names for option bits are defined in the pcre2.h header file: PCRE2_ANCHORED If this bit is set, the pattern is forced to be "anchored", that is, it - is constrained to match only at the first matching point in the string - that is being searched (the "subject string"). This effect can also be - achieved by appropriate constructs in the pattern itself, which is the + is constrained to match only at the first matching point in the string + that is being searched (the "subject string"). This effect can also be + achieved by appropriate constructs in the pattern itself, which is the only way to do it in Perl. PCRE2_ALLOW_EMPTY_CLASS - By default, for compatibility with Perl, a closing square bracket that - immediately follows an opening one is treated as a data character for - the class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the + By default, for compatibility with Perl, a closing square bracket that + immediately follows an opening one is treated as a data character for + the class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the class, which therefore contains no characters and so can never match. PCRE2_ALT_BSUX - This option request alternative handling of three escape sequences, - which makes PCRE2's behaviour more like ECMAscript (aka JavaScript). + This option request alternative handling of three escape sequences, + which makes PCRE2's behaviour more like ECMAscript (aka JavaScript). When it is set: (1) \U matches an upper case "U" character; by default \U causes a com- pile time error (Perl uses \U to upper case subsequent characters). (2) \u matches a lower case "u" character unless it is followed by four - hexadecimal digits, in which case the hexadecimal number defines the - code point to match. By default, \u causes a compile time error (Perl + hexadecimal digits, in which case the hexadecimal number defines the + code point to match. By default, \u causes a compile time error (Perl uses it to upper case the following character). - (3) \x matches a lower case "x" character unless it is followed by two - hexadecimal digits, in which case the hexadecimal number defines the - code point to match. By default, as in Perl, a hexadecimal number is + (3) \x matches a lower case "x" character unless it is followed by two + hexadecimal digits, in which case the hexadecimal number defines the + code point to match. By default, as in Perl, a hexadecimal number is always expected after \x, but it may have zero, one, or two digits (so, for example, \xz matches a binary zero character followed by z). PCRE2_AUTO_CALLOUT - If this bit is set, pcre2_compile() automatically inserts callout + If this bit is set, pcre2_compile() automatically inserts callout items, all with number 255, before each pattern item. For discussion of the callout facility, see the pcre2callout documentation. PCRE2_CASELESS - If this bit is set, letters in the pattern match both upper and lower - case letters in the subject. It is equivalent to Perl's /i option, and + If this bit is set, letters in the pattern match both upper and lower + case letters in the subject. It is equivalent to Perl's /i option, and it can be changed within a pattern by a (?i) option setting. PCRE2_DOLLAR_ENDONLY - If this bit is set, a dollar metacharacter in the pattern matches only - at the end of the subject string. Without this option, a dollar also - matches immediately before a newline at the end of the string (but not - before any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored - if PCRE2_MULTILINE is set. There is no equivalent to this option in + If this bit is set, a dollar metacharacter in the pattern matches only + at the end of the subject string. Without this option, a dollar also + matches immediately before a newline at the end of the string (but not + before any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored + if PCRE2_MULTILINE is set. There is no equivalent to this option in Perl, and no way to set it within a pattern. PCRE2_DOTALL - If this bit is set, a dot metacharacter in the pattern matches any - character, including one that indicates a newline. However, it only + If this bit is set, a dot metacharacter in the pattern matches any + character, including one that indicates a newline. However, it only ever matches one character, even if newlines are coded as CRLF. Without this option, a dot does not match when the current position in the sub- - ject is at a newline. This option is equivalent to Perl's /s option, + ject is at a newline. This option is equivalent to Perl's /s option, and it can be changed within a pattern by a (?s) option setting. A neg- ative class such as [^a] always matches newline characters, independent of the setting of this option. PCRE2_DUPNAMES - If this bit is set, names used to identify capturing subpatterns need + If this bit is set, names used to identify capturing subpatterns need not be unique. This can be helpful for certain types of pattern when it - is known that only one instance of the named subpattern can ever be - matched. There are more details of named subpatterns below; see also + is known that only one instance of the named subpattern can ever be + matched. There are more details of named subpatterns below; see also the pcre2pattern documentation. PCRE2_EXTENDED - If this bit is set, most white space characters in the pattern are - totally ignored except when escaped or inside a character class. How- - ever, white space is not allowed within sequences such as (?> that + If this bit is set, most white space characters in the pattern are + totally ignored except when escaped or inside a character class. How- + ever, white space is not allowed within sequences such as (?> that introduce various parenthesized subpatterns, nor within numerical quan- - tifiers such as {1,3}. Ignorable white space is permitted between an - item and a following quantifier and between a quantifier and a follow- + tifiers such as {1,3}. Ignorable white space is permitted between an + item and a following quantifier and between a quantifier and a follow- ing + that indicates possessiveness. - PCRE2_EXTENDED also causes characters between an unescaped # outside a - character class and the next newline, inclusive, to be ignored, which + PCRE2_EXTENDED also causes characters between an unescaped # outside a + character class and the next newline, inclusive, to be ignored, which makes it possible to include comments inside complicated patterns. Note - that the end of this type of comment is a literal newline sequence in + that the end of this type of comment is a literal newline sequence in the pattern; escape sequences that happen to represent a newline do not - count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be + count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be changed within a pattern by a (?x) option setting. Which characters are interpreted as newlines can be specified by a set- - ting in the compile context that is passed to pcre2_compile() or by a - special sequence at the start of the pattern, as described in the sec- - tion entitled "Newline conventions" in the pcre2pattern documentation. + ting in the compile context that is passed to pcre2_compile() or by a + special sequence at the start of the pattern, as described in the sec- + tion entitled "Newline conventions" in the pcre2pattern documentation. A default is defined when PCRE2 is built. PCRE2_FIRSTLINE - If this option is set, an unanchored pattern is required to match - before or at the first newline in the subject string, though the + If this option is set, an unanchored pattern is required to match + before or at the first newline in the subject string, though the matched text may continue over the newline. PCRE2_MATCH_UNSET_BACKREF - If this option is set, a back reference to an unset subpattern group - matches an empty string (by default this causes the current matching - alternative to fail). A pattern such as (\1)(a) succeeds when this - option is set (assuming it can find an "a" in the subject), whereas it - fails by default, for Perl compatibility. Setting this option makes + If this option is set, a back reference to an unset subpattern group + matches an empty string (by default this causes the current matching + alternative to fail). A pattern such as (\1)(a) succeeds when this + option is set (assuming it can find an "a" in the subject), whereas it + fails by default, for Perl compatibility. Setting this option makes PCRE2 behave more like ECMAscript (aka JavaScript). PCRE2_MULTILINE - By default, for the purposes of matching "start of line" and "end of - line", PCRE2 treats the subject string as consisting of a single line - of characters, even if it actually contains newlines. The "start of - line" metacharacter (^) matches only at the start of the string, and - the "end of line" metacharacter ($) matches only at the end of the + By default, for the purposes of matching "start of line" and "end of + line", PCRE2 treats the subject string as consisting of a single line + of characters, even if it actually contains newlines. The "start of + line" metacharacter (^) matches only at the start of the string, and + the "end of line" metacharacter ($) matches only at the end of the string, or before a terminating newline (except when PCRE2_DOL- - LAR_ENDONLY is set). Note, however, that unless PCRE2_DOTALL is set, + LAR_ENDONLY is set). Note, however, that unless PCRE2_DOTALL is set, the "any character" metacharacter (.) does not match at a newline. This behaviour (for ^, $, and dot) is the same as Perl. - When PCRE2_MULTILINE it is set, the "start of line" and "end of line" - constructs match immediately following or immediately before internal - newlines in the subject string, respectively, as well as at the very - start and end. This is equivalent to Perl's /m option, and it can be + When PCRE2_MULTILINE it is set, the "start of line" and "end of line" + constructs match immediately following or immediately before internal + newlines in the subject string, respectively, as well as at the very + start and end. This is equivalent to Perl's /m option, and it can be changed within a pattern by a (?m) option setting. If there are no new- - lines in a subject string, or no occurrences of ^ or $ in a pattern, + lines in a subject string, or no occurrences of ^ or $ in a pattern, setting PCRE2_MULTILINE has no effect. PCRE2_NEVER_UCP - This option locks out the use of Unicode properties for handling \B, + This option locks out the use of Unicode properties for handling \B, \b, \D, \d, \S, \s, \W, \w, and some of the POSIX character classes, as - described for the PCRE2_UCP option below. In particular, it prevents - the creator of the pattern from enabling this facility by starting the - pattern with (*UCP). This may be useful in applications that process - patterns from external sources. The option combination PCRE_UCP and + described for the PCRE2_UCP option below. In particular, it prevents + the creator of the pattern from enabling this facility by starting the + pattern with (*UCP). This may be useful in applications that process + patterns from external sources. The option combination PCRE_UCP and PCRE_NEVER_UCP causes an error. PCRE2_NEVER_UTF - This option locks out interpretation of the pattern as UTF-8, UTF-16, + This option locks out interpretation of the pattern as UTF-8, UTF-16, or UTF-32, depending on which library is in use. In particular, it pre- - vents the creator of the pattern from switching to UTF interpretation + vents the creator of the pattern from switching to UTF interpretation by starting the pattern with (*UTF). This may be useful in applications that process patterns from external sources. The combination of PCRE2_UTF and PCRE2_NEVER_UTF causes an error. @@ -1204,124 +1211,124 @@ COMPILING A PATTERN PCRE2_NO_AUTO_CAPTURE If this option is set, it disables the use of numbered capturing paren- - theses in the pattern. Any opening parenthesis that is not followed by - ? behaves as if it were followed by ?: but named parentheses can still - be used for capturing (and they acquire numbers in the usual way). + theses in the pattern. Any opening parenthesis that is not followed by + ? behaves as if it were followed by ?: but named parentheses can still + be used for capturing (and they acquire numbers in the usual way). There is no equivalent of this option in Perl. PCRE2_NO_AUTO_POSSESS If this option is set, it disables "auto-possessification", which is an - optimization that, for example, turns a+b into a++b in order to avoid - backtracks into a+ that can never be successful. However, if callouts - are in use, auto-possessification means that some callouts are never + optimization that, for example, turns a+b into a++b in order to avoid + backtracks into a+ that can never be successful. However, if callouts + are in use, auto-possessification means that some callouts are never taken. You can set this option if you want the matching functions to do - a full unoptimized search and run all the callouts, but it is mainly + a full unoptimized search and run all the callouts, but it is mainly provided for testing purposes. PCRE2_NO_START_OPTIMIZE - This is an option whose main effect is at matching time. It does not + This is an option whose main effect is at matching time. It does not change what pcre2_compile() generates, but it does affect the output of the JIT compiler. - There are a number of optimizations that may occur at the start of a - match, in order to speed up the process. For example, if it is known - that an unanchored match must start with a specific character, the - matching code searches the subject for that character, and fails imme- - diately if it cannot find it, without actually running the main match- - ing function. This means that a special item such as (*COMMIT) at the - start of a pattern is not considered until after a suitable starting - point for the match has been found. Also, when callouts or (*MARK) - items are in use, these "start-up" optimizations can cause them to be - skipped if the pattern is never actually used. The start-up optimiza- - tions are in effect a pre-scan of the subject that takes place before + There are a number of optimizations that may occur at the start of a + match, in order to speed up the process. For example, if it is known + that an unanchored match must start with a specific character, the + matching code searches the subject for that character, and fails imme- + diately if it cannot find it, without actually running the main match- + ing function. This means that a special item such as (*COMMIT) at the + start of a pattern is not considered until after a suitable starting + point for the match has been found. Also, when callouts or (*MARK) + items are in use, these "start-up" optimizations can cause them to be + skipped if the pattern is never actually used. The start-up optimiza- + tions are in effect a pre-scan of the subject that takes place before the pattern is run. The PCRE2_NO_START_OPTIMIZE option disables the start-up optimizations, - possibly causing performance to suffer, but ensuring that in cases - where the result is "no match", the callouts do occur, and that items + possibly causing performance to suffer, but ensuring that in cases + where the result is "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK) are considered at every possible starting position in the subject string. - Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching + Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching operation. Consider the pattern (*COMMIT)ABC - When this is compiled, PCRE2 records the fact that a match must start - with the character "A". Suppose the subject string is "DEFABC". The - start-up optimization scans along the subject, finds "A" and runs the - first match attempt from there. The (*COMMIT) item means that the pat- - tern must match the current starting position, which in this case, it - does. However, if the same match is run with PCRE2_NO_START_OPTIMIZE - set, the initial scan along the subject string does not happen. The - first match attempt is run starting from "D" and when this fails, - (*COMMIT) prevents any further matches being tried, so the overall + When this is compiled, PCRE2 records the fact that a match must start + with the character "A". Suppose the subject string is "DEFABC". The + start-up optimization scans along the subject, finds "A" and runs the + first match attempt from there. The (*COMMIT) item means that the pat- + tern must match the current starting position, which in this case, it + does. However, if the same match is run with PCRE2_NO_START_OPTIMIZE + set, the initial scan along the subject string does not happen. The + first match attempt is run starting from "D" and when this fails, + (*COMMIT) prevents any further matches being tried, so the overall result is "no match". There are also other start-up optimizations. For example, a minimum length for the subject may be recorded. Consider the pattern (*MARK:A)(X|Y) - The minimum length for a match is one character. If the subject is + The minimum length for a match is one character. If the subject is "ABC", there will be attempts to match "ABC", "BC", and "C". An attempt to match an empty string at the end of the subject does not take place, - because PCRE2 knows that the subject is now too short, and so the - (*MARK) is never encountered. In this case, the optimization does not + because PCRE2 knows that the subject is now too short, and so the + (*MARK) is never encountered. In this case, the optimization does not affect the overall match result, which is still "no match", but it does affect the auxiliary information that is returned. PCRE2_NO_UTF_CHECK - When PCRE2_UTF is set, the validity of the pattern as a UTF string is - automatically checked. There are discussions about the validity of - UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode + When PCRE2_UTF is set, the validity of the pattern as a UTF string is + automatically checked. There are discussions about the validity of + UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode document. If an invalid UTF sequence is found, pcre2_compile() returns a negative error code. If you know that your pattern is valid, and you want to skip this check - for performance reasons, you can set the PCRE2_NO_UTF_CHECK option. - When it is set, the effect of passing an invalid UTF string as a pat- - tern is undefined. It may cause your program to crash or loop. Note - that this option can also be passed to pcre2_match() and + for performance reasons, you can set the PCRE2_NO_UTF_CHECK option. + When it is set, the effect of passing an invalid UTF string as a pat- + tern is undefined. It may cause your program to crash or loop. Note + that this option can also be passed to pcre2_match() and pcre_dfa_match(), to suppress validity checking of the subject string. PCRE2_UCP This option changes the way PCRE2 processes \B, \b, \D, \d, \S, \s, \W, - \w, and some of the POSIX character classes. By default, only ASCII - characters are recognized, but if PCRE2_UCP is set, Unicode properties - are used instead to classify characters. More details are given in the + \w, and some of the POSIX character classes. By default, only ASCII + characters are recognized, but if PCRE2_UCP is set, Unicode properties + are used instead to classify characters. More details are given in the section on generic character types in the pcre2pattern page. If you set - PCRE2_UCP, matching one of the items it affects takes much longer. The - option is available only if PCRE2 has been compiled with Unicode sup- + PCRE2_UCP, matching one of the items it affects takes much longer. The + option is available only if PCRE2 has been compiled with Unicode sup- port. PCRE2_UNGREEDY - This option inverts the "greediness" of the quantifiers so that they - are not greedy by default, but become greedy if followed by "?". It is - not compatible with Perl. It can also be set by a (?U) option setting + This option inverts the "greediness" of the quantifiers so that they + are not greedy by default, but become greedy if followed by "?". It is + not compatible with Perl. It can also be set by a (?U) option setting within the pattern. PCRE2_UTF - This option causes PCRE2 to regard both the pattern and the subject - strings that are subsequently processed as strings of UTF characters - instead of single-code-unit strings. It is available when PCRE2 is - built to include Unicode support (which is the default). If Unicode - support is not available, the use of this option provokes an error. - Details of how this option changes the behaviour of PCRE2 are given in + This option causes PCRE2 to regard both the pattern and the subject + strings that are subsequently processed as strings of UTF characters + instead of single-code-unit strings. It is available when PCRE2 is + built to include Unicode support (which is the default). If Unicode + support is not available, the use of this option provokes an error. + Details of how this option changes the behaviour of PCRE2 are given in the pcre2unicode page. COMPILATION ERROR CODES - There are over 80 positive error codes that pcre2_compile() may return + There are over 80 positive error codes that pcre2_compile() may return if it finds an error in the pattern. There are also some negative error - codes that are used for invalid UTF strings. These are the same as - given by pcre2_match() and pcre2_dfa_match(), and are described in the + codes that are used for invalid UTF strings. These are the same as + given by pcre2_match() and pcre2_dfa_match(), and are described in the pcre2unicode page. The pcre2_get_error_message() function can be called to obtain a textual error message from any error code. @@ -1345,53 +1352,53 @@ JUST-IN-TIME (JIT) COMPILATION void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack); - These functions provide support for JIT compilation, which, if the - just-in-time compiler is available, further processes a compiled pat- + These functions provide support for JIT compilation, which, if the + just-in-time compiler is available, further processes a compiled pat- tern into machine code that executes much faster than the pcre2_match() - interpretive matching function. Full details are given in the pcre2jit + interpretive matching function. Full details are given in the pcre2jit documentation. - JIT compilation is a heavyweight optimization. It can take some time - for patterns to be analyzed, and for one-off matches and simple pat- - terns the benefit of faster execution might be offset by a much slower - compilation time. Most, but not all patterns can be optimized by the + JIT compilation is a heavyweight optimization. It can take some time + for patterns to be analyzed, and for one-off matches and simple pat- + terns the benefit of faster execution might be offset by a much slower + compilation time. Most, but not all patterns can be optimized by the JIT compiler. LOCALE SUPPORT - PCRE2 handles caseless matching, and determines whether characters are - letters, digits, or whatever, by reference to a set of tables, indexed - by character code point. This applies only to characters whose code - points are less than 256. By default, higher-valued code points never - match escapes such as \w or \d. However, if PCRE2 is built with UTF - support, all characters can be tested with \p and \P, or, alterna- - tively, the PCRE2_UCP option can be set when a pattern is compiled; - this causes \w and friends to use Unicode property support instead of + PCRE2 handles caseless matching, and determines whether characters are + letters, digits, or whatever, by reference to a set of tables, indexed + by character code point. This applies only to characters whose code + points are less than 256. By default, higher-valued code points never + match escapes such as \w or \d. However, if PCRE2 is built with UTF + support, all characters can be tested with \p and \P, or, alterna- + tively, the PCRE2_UCP option can be set when a pattern is compiled; + this causes \w and friends to use Unicode property support instead of the built-in tables. - The use of locales with Unicode is discouraged. If you are handling - characters with code points greater than 128, you should either use + The use of locales with Unicode is discouraged. If you are handling + characters with code points greater than 128, you should either use Unicode support, or use locales, but not try to mix the two. - PCRE2 contains an internal set of character tables that are used by - default. These are sufficient for many applications. Normally, the + PCRE2 contains an internal set of character tables that are used by + default. These are sufficient for many applications. Normally, the internal tables recognize only ASCII characters. However, when PCRE2 is built, it is possible to cause the internal tables to be rebuilt in the default "C" locale of the local system, which may cause them to be dif- ferent. - The internal tables can be overridden by tables supplied by the appli- - cation that calls PCRE2. These may be created in a different locale - from the default. As more and more applications change to using Uni- + The internal tables can be overridden by tables supplied by the appli- + cation that calls PCRE2. These may be created in a different locale + from the default. As more and more applications change to using Uni- code, the need for this locale support is expected to die away. - External tables are built by calling the pcre2_maketables() function, - in the relevant locale. The result can be passed to pcre2_compile() as - often as necessary, by creating a compile context and calling - pcre2_set_character_tables() to set the tables pointer therein. For - example, to build and use tables that are appropriate for the French - locale (where accented characters with values greater than 128 are + External tables are built by calling the pcre2_maketables() function, + in the relevant locale. The result can be passed to pcre2_compile() as + often as necessary, by creating a compile context and calling + pcre2_set_character_tables() to set the tables pointer therein. For + example, to build and use tables that are appropriate for the French + locale (where accented characters with values greater than 128 are treated as letters), the following code could be used: setlocale(LC_CTYPE, "fr_FR"); @@ -1400,15 +1407,15 @@ LOCALE SUPPORT pcre2_set_character_tables(ccontext, tables); re = pcre2_compile(..., ccontext); - The locale name "fr_FR" is used on Linux and other Unix-like systems; - if you are using Windows, the name for the French locale is "french". - It is the caller's responsibility to ensure that the memory containing + The locale name "fr_FR" is used on Linux and other Unix-like systems; + if you are using Windows, the name for the French locale is "french". + It is the caller's responsibility to ensure that the memory containing the tables remains available for as long as it is needed. The pointer that is passed (via the compile context) to pcre2_compile() - is saved with the compiled pattern, and the same tables are used by - pcre2_match() and pcre_dfa_match(). Thus, for any single pattern, com- - pilation, and matching all happen in the same locale, but different + is saved with the compiled pattern, and the same tables are used by + pcre2_match() and pcre_dfa_match(). Thus, for any single pattern, com- + pilation, and matching all happen in the same locale, but different patterns can be processed in different locales. @@ -1416,13 +1423,13 @@ 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 + 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 + 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 @@ -1430,9 +1437,9 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_ERROR_BADOPTION the value of what was invalid PCRE2_ERROR_UNSET the requested field is not set - The "magic number" is placed at the start of each compiled pattern as - an simple check against passing an arbitrary memory pointer. Here is a - typical call of pcre2_pattern_info(), to obtain the length of the com- + The "magic number" is placed at the start of each compiled pattern as + an simple check against passing an arbitrary memory pointer. Here is a + typical call of pcre2_pattern_info(), to obtain the length of the com- piled pattern: int rc; @@ -1449,16 +1456,16 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_INFO_ARGOPTIONS Return a copy of the pattern's options. The third argument should point - to a uint32_t variable. PCRE2_INFO_ARGOPTIONS returns exactly the - options that were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOP- - TIONS returns the compile options as modified by any top-level option - settings at the start of the pattern itself. In other words, they are + to a uint32_t variable. PCRE2_INFO_ARGOPTIONS returns exactly the + options that were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOP- + TIONS returns the compile options as modified by any top-level option + settings at the start of the pattern itself. In other words, they are the options that will be in force when matching starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE2_EXTENDED - option, the result is PCRE2_CASELESS, PCRE2_MULTILINE, and + option, the result is PCRE2_CASELESS, PCRE2_MULTILINE, and PCRE2_EXTENDED. - A pattern is automatically anchored by PCRE2 if all of its top-level + A pattern is automatically anchored by PCRE2 if all of its top-level alternatives begin with one of the following: ^ unless PCRE2_MULTILINE is set @@ -1467,42 +1474,42 @@ INFORMATION ABOUT A COMPILED PATTERN .* if PCRE2_DOTALL is set and there are no back references to the subpattern in which .* appears - For such patterns, the PCRE2_ANCHORED bit is set in the options + For such patterns, the PCRE2_ANCHORED bit is set in the options returned for PCRE2_INFO_ALLOPTIONS. PCRE2_INFO_BACKREFMAX - Return the number of the highest back reference in the pattern. The - third argument should point to an uint32_t variable. Zero is returned + Return the number of the highest back reference in the pattern. The + third argument should point to an uint32_t variable. Zero is returned if there are no back references. PCRE2_INFO_BSR The output is a uint32_t whose value indicates what character sequences the \R escape sequence matches. A value of PCRE2_BSR_UNICODE means that - \R matches any Unicode line ending sequence; a value of PCRE2_BSR_ANY- + \R matches any Unicode line ending sequence; a value of PCRE2_BSR_ANY- CRLF means that \R matches only CR, LF, or CRLF. PCRE2_INFO_CAPTURECOUNT - Return the number of capturing subpatterns in the pattern. The third + Return the number of capturing subpatterns in the pattern. The third argument should point to an uint32_t variable. PCRE2_INFO_FIRSTCODETYPE Return information about the first code unit of any matched string, for - a non-anchored pattern. The third argument should point to an uint32_t + a non-anchored pattern. The third argument should point to an uint32_t variable. - If there is a fixed first value, for example, the letter "c" from a - pattern such as (cat|cow|coyote), 1 is returned, and the character - value can be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is no + If there is a fixed first value, for example, the letter "c" from a + pattern such as (cat|cow|coyote), 1 is returned, and the character + value can be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is no fixed first value, and if either (a) the pattern was compiled with the PCRE2_MULTILINE option, and every branch starts with "^", or - (b) every branch of the pattern starts with ".*" and PCRE2_DOTALL is + (b) every branch of the pattern starts with ".*" and PCRE2_DOTALL is not set (if it were set, the pattern would be anchored), 2 is returned, indicating that the pattern matches only at the start of @@ -1511,99 +1518,99 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_INFO_FIRSTCODEUNIT - Return the value of the first code unit of any matched string in the + Return the value of the first code unit of any matched string in the situation where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0. - The third argument should point to an uint32_t variable. In the 8-bit - library, the value is always less than 256. In the 16-bit library the - value can be up to 0xffff. In the 32-bit library in UTF-32 mode the + The third argument should point to an uint32_t variable. In the 8-bit + library, the value is always less than 256. In the 16-bit library the + value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. PCRE2_INFO_FIRSTBITMAP - In the absence of a single first code unit for a non-anchored pattern, - pcre2_compile() may construct a 256-bit table that defines a fixed set - of values for the first code unit in any match. For example, a pattern - that starts with [abc] results in a table with three bits set. When - code unit values greater than 255 are supported, the flag bit for 255 - means "any code unit of value 255 or above". If such a table was con- - structed, a pointer to it is returned. Otherwise NULL is returned. The + In the absence of a single first code unit for a non-anchored pattern, + pcre2_compile() may construct a 256-bit table that defines a fixed set + of values for the first code unit in any match. For example, a pattern + that starts with [abc] results in a table with three bits set. When + code unit values greater than 255 are supported, the flag bit for 255 + means "any code unit of value 255 or above". If such a table was con- + structed, a pointer to it is returned. Otherwise NULL is returned. The third argument should point to an const uint8_t * variable. PCRE2_INFO_HASCRORLF - Return 1 if the pattern contains any explicit matches for CR or LF + Return 1 if the pattern contains any explicit matches for CR or LF characters, otherwise 0. The third argument should point to an uint32_t - variable. An explicit match is either a literal CR or LF character, or + variable. An explicit match is either a literal CR or LF character, or \r or \n. PCRE2_INFO_JCHANGED - Return 1 if the (?J) or (?-J) option setting is used in the pattern, - otherwise 0. The third argument should point to an uint32_t variable. - (?J) and (?-J) set and unset the local PCRE2_DUPNAMES option, respec- + Return 1 if the (?J) or (?-J) option setting is used in the pattern, + otherwise 0. The third argument should point to an uint32_t variable. + (?J) and (?-J) set and unset the local PCRE2_DUPNAMES option, respec- tively. PCRE2_INFO_JITSIZE - If the compiled pattern was successfully processed by pcre2_jit_com- - pile(), return the size of the JIT compiled code, otherwise return + If the compiled pattern was successfully processed by pcre2_jit_com- + pile(), return the size of the JIT compiled code, otherwise return zero. The third argument should point to a size_t variable. PCRE2_INFO_LASTCODETYPE - Returns 1 if there is a rightmost literal code unit that must exist in - any matched string, other than at its start. The third argument should - point to an uint32_t variable. If there is no such value, 0 is - returned. When 1 is returned, the code unit value itself can be + Returns 1 if there is a rightmost literal code unit that must exist in + any matched string, other than at its start. The third argument should + point to an uint32_t variable. If there is no such value, 0 is + returned. When 1 is returned, the code unit value itself can be retrieved using PCRE2_INFO_LASTCODEUNIT. For anchored patterns, a last literal value is recorded only if it fol- - lows something of variable length. For example, for the pattern - /^a\d+z\d+/ the returned value is 1 (with "z" returned from + lows something of variable length. For example, for the pattern + /^a\d+z\d+/ the returned value is 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ the returned value is 0. PCRE2_INFO_LASTCODEUNIT - Return the value of the rightmost literal data unit that must exist in - any matched string, other than at its start, if such a value has been - recorded. The third argument should point to an uint32_t variable. If + Return the value of the rightmost literal data unit that must exist in + any matched string, other than at its start, if such a value has been + recorded. The third argument should point to an uint32_t variable. If there is no such value, 0 is returned. PCRE2_INFO_MATCHEMPTY - Return 1 if the pattern can match an empty string, otherwise 0. The + Return 1 if the pattern can match an empty string, otherwise 0. The third argument should point to an uint32_t variable. PCRE2_INFO_MATCHLIMIT - If the pattern set a match limit by including an item of the form - (*LIMIT_MATCH=nnnn) at the start, the value is returned. The third - argument should point to an unsigned 32-bit integer. If no such value - has been set, the call to pcre2_pattern_info() returns the error + If the pattern set a match limit by including an item of the form + (*LIMIT_MATCH=nnnn) at the start, the value is returned. The third + argument should point to an unsigned 32-bit integer. If no such value + has been set, the call to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET. PCRE2_INFO_MAXLOOKBEHIND Return the number of characters (not code units) in the longest lookbe- - hind assertion in the pattern. The third argument should point to an - unsigned 32-bit integer. This information is useful when doing multi- - segment matching using the partial matching facilities. Note that the + hind assertion in the pattern. The third argument should point to an + unsigned 32-bit integer. This information is useful when doing multi- + segment matching using the partial matching facilities. Note that the simple assertions \b and \B require a one-character lookbehind. \A also - registers a one-character lookbehind, though it does not actually - inspect the previous character. This is to ensure that at least one - character from the old segment is retained when a new segment is pro- + registers a one-character lookbehind, though it does not actually + inspect the previous character. This is to ensure that at least one + character from the old segment is retained when a new segment is pro- cessed. Otherwise, if there are no lookbehinds in the pattern, \A might match incorrectly at the start of a new segment. PCRE2_INFO_MINLENGTH - If a minimum length for matching subject strings was computed, its - value is returned. Otherwise the returned value is 0. The value is a - number of characters, which in UTF mode may be different from the num- - ber of code units. The third argument should point to an uint32_t - variable. The value is a lower bound to the length of any matching - string. There may not be any strings of that length that do actually + If a minimum length for matching subject strings was computed, its + value is returned. Otherwise the returned value is 0. The value is a + number of characters, which in UTF mode may be different from the num- + ber of code units. The third argument should point to an uint32_t + variable. The value is a lower bound to the length of any matching + string. There may not be any strings of that length that do actually match, but every string that does match is at least that long. PCRE2_INFO_NAMECOUNT @@ -1611,50 +1618,50 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_INFO_NAMETABLE PCRE2 supports the use of named as well as numbered capturing parenthe- - ses. The names are just an additional way of identifying the parenthe- + ses. The names are just an additional way of identifying the parenthe- ses, which still acquire numbers. Several convenience functions such as - pcre2_substring_get_byname() are provided for extracting captured sub- - strings by name. It is also possible to extract the data directly, by - first converting the name to a number in order to access the correct - pointers in the output vector (described with pcre2_match() below). To - do the conversion, you need to use the name-to-number map, which is + pcre2_substring_get_byname() are provided for extracting captured sub- + strings by name. It is also possible to extract the data directly, by + first converting the name to a number in order to access the correct + pointers in the output vector (described with pcre2_match() below). To + do the conversion, you need to use the name-to-number map, which is described by these three values. - The map consists of a number of fixed-size entries. PCRE2_INFO_NAME- - COUNT gives the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives - the size of each entry in code units; both of these return a uint32_t + The map consists of a number of fixed-size entries. PCRE2_INFO_NAME- + COUNT gives the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives + the size of each entry in code units; both of these return a uint32_t value. The entry size depends on the length of the longest name. PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table. - This is a PCRE2_SPTR pointer to a block of code units. In the 8-bit - library, the first two bytes of each entry are the number of the cap- + This is a PCRE2_SPTR pointer to a block of code units. In the 8-bit + library, the first two bytes of each entry are the number of the cap- turing parenthesis, most significant byte first. In the 16-bit library, - the pointer points to 16-bit code units, the first of which contains - the parenthesis number. In the 32-bit library, the pointer points to - 32-bit code units, the first of which contains the parenthesis number. + the pointer points to 16-bit code units, the first of which contains + the parenthesis number. In the 32-bit library, the pointer points to + 32-bit code units, the first of which contains the parenthesis number. The rest of the entry is the corresponding name, zero terminated. - The names are in alphabetical order. If (?| is used to create multiple - groups with the same number, as described in the section on duplicate - subpattern numbers in the pcre2pattern page, the groups may be given - the same name, but there is only one entry in the table. Different + The names are in alphabetical order. If (?| is used to create multiple + groups with the same number, as described in the section on duplicate + subpattern numbers in the pcre2pattern page, the groups may be given + the same name, but there is only one entry in the table. Different names for groups of the same number are not permitted. - Duplicate names for subpatterns with different numbers are permitted, - but only if PCRE2_DUPNAMES is set. They appear in the table in the - order in which they were found in the pattern. In the absence of (?| - this is the order of increasing number; when (?| is used this is not + Duplicate names for subpatterns with different numbers are permitted, + but only if PCRE2_DUPNAMES is set. They appear in the table in the + order in which they were found in the pattern. In the absence of (?| + this is the order of increasing number; when (?| is used this is not necessarily the case because later subpatterns may have lower numbers. - As a simple example of the name/number table, consider the following - pattern after compilation by the 8-bit library (assume PCRE2_EXTENDED + As a simple example of the name/number table, consider the following + pattern after compilation by the 8-bit library (assume PCRE2_EXTENDED is set, so white space - including newlines - is ignored): (? (?(\d\d)?\d\d) - (?\d\d) - (?\d\d) ) - There are four named subpatterns, so the table has four entries, and - each entry in the table is eight bytes long. The table is as follows, + There are four named subpatterns, so the table has four entries, and + each entry in the table is eight bytes long. The table is as follows, with non-printing bytes shows in hexadecimal, and undefined bytes shown as ??: @@ -1663,8 +1670,8 @@ INFORMATION ABOUT A COMPILED PATTERN 00 04 m o n t h 00 00 02 y e a r 00 ?? - When writing code to extract data from named subpatterns using the - name-to-number map, remember that the length of the entries is likely + When writing code to extract data from named subpatterns using the + name-to-number map, remember that the length of the entries is likely to be different for each compiled pattern. PCRE2_INFO_NEWLINE @@ -1677,26 +1684,26 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_NEWLINE_ANY Any Unicode line ending PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF - This specifies the default character sequence that will be recognized + This specifies the default character sequence that will be recognized as meaning "newline" while matching. PCRE2_INFO_RECURSIONLIMIT - If the pattern set a recursion limit by including an item of the form - (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The third - argument should point to an unsigned 32-bit integer. If no such value - has been set, the call to pcre2_pattern_info() returns the error + If the pattern set a recursion limit by including an item of the form + (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The third + argument should point to an unsigned 32-bit integer. If no such value + has been set, the call to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET. PCRE2_INFO_SIZE - Return the size of the compiled pattern in bytes (for all three - libraries). The third argument should point to a size_t variable. This - value does not include the size of the pcre2_code structure that is + Return the size of the compiled pattern in bytes (for all three + libraries). The third argument should point to a size_t variable. This + value does not include the size of the pcre2_code structure that is returned by pcre_compile(). The value that is used when pcre2_compile() - is getting memory in which to place the compiled data is the value + is getting memory in which to place the compiled data is the value returned by this option plus the size of the pcre2_code structure. Pro- - cessing a pattern with the JIT compiler does not alter the value + cessing a pattern with the JIT compiler does not alter the value returned by this option. @@ -1710,42 +1717,51 @@ THE MATCH DATA BLOCK void pcre2_match_data_free(pcre2_match_data *match_data); - Information about successful and unsuccessful matches is placed in a - match data block, which is an opaque structure that is accessed by - function calls. In particular, the match data block contains a vector - of offsets into the subject string that define the matched part of the - subject and any substrings that were captured. This is know as the + Information about a successful or unsuccessful match is placed in a + match data block, which is an opaque structure that is accessed by + function calls. In particular, the match data block contains a vector + of offsets into the subject string that define the matched part of the + subject and any substrings that were captured. This is know as the ovector. - Before calling pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match() + Before calling pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match() you must create a match data block by calling one of the creation func- - tions above. For pcre2_match_data_create(), the first argument is the - number of pairs of offsets in the ovector. One pair of offsets is - required to identify the string that matched the whole pattern, with - another pair for each captured substring. For example, a value of 4 - creates enough space to record the matched portion of the subject plus - three captured substrings. A minimum of at least 1 pair is imposed by + tions above. For pcre2_match_data_create(), the first argument is the + number of pairs of offsets in the ovector. One pair of offsets is + required to identify the string that matched the whole pattern, with + another pair for each captured substring. For example, a value of 4 + creates enough space to record the matched portion of the subject plus + three captured substrings. A minimum of at least 1 pair is imposed by pcre2_match_data_create(), so it is always possible to return the over- all matched string. The second argument of pcre2_match_data_create() is a pointer to a gen- - eral context, which can specify custom memory management for obtaining + eral context, which can specify custom memory management for obtaining the memory for the match data block. If you are not using custom memory management, pass NULL, which causes malloc() to be used. - For pcre2_match_data_create_from_pattern(), the first argument is a + For pcre2_match_data_create_from_pattern(), the first argument is a pointer to a compiled pattern. The ovector is created to be exactly the right size to hold all the substrings a pattern might capture. The sec- - ond argument is again a pointer to a general context, but in this case + ond argument is again a pointer to a general context, but in this case if NULL is passed, the memory is obtained using the same allocator that was used for the compiled pattern (custom or default). - A match data block can be used many times, with the same or different - compiled patterns. When it is no longer needed, it should be freed by - calling pcre2_match_data_free(). You can extract information from a - match data block after a match operation has finished, using functions - that are described in the sections on matched strings and other match - data below. + A match data block can be used many times, with the same or different + compiled patterns. You can extract information from a match data block + after a match operation has finished, using functions that are + described in the sections on matched strings and other match data + below. + + When one of the matching functions is called, pointers to the compiled + pattern and the subject string are set in the match data block so that + they can be referenced by the extraction functions. After running a + match, you must not free a compiled pattern or a subject string until + after all operations on the match data block (for that match) have + 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 @@ -2017,39 +2033,44 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS subpatterns, the return value from a successful match is 1, indicating that just the first pair of offsets has been set. - If a capturing subpattern is matched repeatedly within a single match - operation, it is the last portion of the string that it matched that is - returned. + If a pattern uses the \K escape sequence within a positive assertion, + the reported start of the match can be greater than the end of the + match. For example, if the pattern (?=ab\K) is matched against "ab", + the start and end offset values for the match are 2 and 0. + + If a capturing subpattern group is matched repeatedly within a single + match operation, it is the last portion of the subject that it matched + that is returned. If the ovector is too small to hold all the captured substring offsets, - as much as possible is filled in, and the function returns a value of - zero. If captured substrings are not of interest, pcre2_match() may be + as much as possible is filled in, and the function returns a value of + zero. If captured substrings are not of interest, pcre2_match() may be called with a match data block whose ovector is of minimum length (that is, one pair). However, if the pattern contains back references and the ovector is not big enough to remember the related substrings, PCRE2 has - to get additional memory for use during matching. Thus it is usually + to get additional memory for use during matching. Thus it is usually advisable to set up a match data block containing an ovector of reason- able size. - It is possible for capturing subpattern number n+1 to match some part + It is possible for capturing subpattern number n+1 to match some part of the subject when subpattern n has not been used at all. For example, - if the string "abc" is matched against the pattern (a|(z))(bc) the + if the string "abc" is matched against the pattern (a|(z))(bc) the return from the function is 4, and subpatterns 1 and 3 are matched, but - 2 is not. When this happens, both values in the offset pairs corre- + 2 is not. When this happens, both values in the offset pairs corre- sponding to unused subpatterns are set to PCRE2_UNSET. - Offset values that correspond to unused subpatterns at the end of the - expression are also set to PCRE2_UNSET. For example, if the string + Offset values that correspond to unused subpatterns at the end of the + expression are also set to PCRE2_UNSET. For example, if the string "abc" is matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 - are not matched. The return from the function is 2, because the high- + are not matched. The return from the function is 2, because the high- est used capturing subpattern number is 1. The offsets for for the sec- - ond and third capturing subpatterns (assuming the vector is large + ond and third capturing subpatterns (assuming the vector is large enough, of course) are set to PCRE2_UNSET. Elements in the ovector that do not correspond to capturing parentheses in the pattern are never changed. That is, if a pattern contains n cap- turing parentheses, no more than ovector[0] to ovector[2n+1] are set by - pcre2_match(). The other elements retain whatever values they previ- + pcre2_match(). The other elements retain whatever values they previ- ously had. @@ -2059,36 +2080,36 @@ OTHER INFORMATION ABOUT A MATCH PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data); - As well as the offsets in the ovector, other information about a match - is retained in the match data block and can be retrieved by the above + As well as the offsets in the ovector, other information about a match + is retained in the match data block and can be retrieved by the above functions. - When a (*MARK) name is to be passed back, pcre2_get_mark() returns a - pointer to the zero-terminated name, which is within the compiled pat- - tern. Otherwise NULL is returned. A (*MARK) name may be available - after a failed match or a partial match, as well as after a successful + When a (*MARK) name is to be passed back, pcre2_get_mark() returns a + pointer to the zero-terminated name, which is within the compiled pat- + tern. Otherwise NULL is returned. A (*MARK) name may be available + after a failed match or a partial match, as well as after a successful one. - The code unit offset of the character at which a successful match - started is returned by pcre2_get_startchar(). For a non-partial match, - this can be different to the value of ovector[0] if the pattern con- - tains the \K escape sequence. After a partial match, however, this - value is always the same as ovector[0] because \K does not affect the + The code unit offset of the character at which a successful match + started is returned by pcre2_get_startchar(). For a non-partial match, + this can be different to the value of ovector[0] if the pattern con- + tains the \K escape sequence. After a partial match, however, this + value is always the same as ovector[0] because \K does not affect the result of a partial match. The startchar field is also used to return the offset of an invalid UTF - character when UTF checking fails. Details are given in the pcre2uni- + character when UTF checking fails. Details are given in the pcre2uni- code page. ERROR RETURNS FROM pcre2_match() - If pcre2_match() fails, it returns a negative number. This can be con- - verted to a text string by calling pcre2_get_error_message(). Negative - error codes are also returned by other functions, and are documented + If pcre2_match() fails, it returns a negative number. This can be con- + verted to a text string by calling pcre2_get_error_message(). Negative + error codes are also returned by other functions, and are documented with them. The codes are given names in the header file. If UTF check- ing is in force and an invalid UTF subject string is detected, one of a - number of UTF-specific negative error codes is returned. Details are + number of UTF-specific negative error codes is returned. Details are given in the pcre2unicode page. The following are the other errors that may be returned by pcre2_match(): @@ -2098,19 +2119,19 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_PARTIAL - The subject string did not match, but it did match partially. See the + The subject string did not match, but it did match partially. See the pcre2partial documentation for details of partial matching. PCRE2_ERROR_BADMAGIC PCRE2 stores a 4-byte "magic number" at the start of the compiled code, - to catch the case when it is passed a junk pointer. This is the error + to catch the case when it is passed a junk pointer. This is the error that is returned when the magic number is not present. PCRE2_ERROR_BADMODE - This error is given when a pattern that was compiled by the 8-bit - library is passed to a 16-bit or 32-bit library function, or vice + This error is given when a pattern that was compiled by the 8-bit + library is passed to a 16-bit or 32-bit library function, or vice versa. PCRE2_ERROR_BADOFFSET @@ -2124,35 +2145,35 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_BADUTFOFFSET The UTF code unit sequence that was passed as a subject was checked and - found to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the - value of startoffset did not point to the beginning of a UTF character + found to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the + value of startoffset did not point to the beginning of a UTF character or the end of the subject. PCRE2_ERROR_CALLOUT - This error is never generated by pcre2_match() itself. It is provided + 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 + a distinctive error code. See the pcre2callout documentation for details. PCRE2_ERROR_INTERNAL - An unexpected internal error has occurred. This error could be caused + An unexpected internal error has occurred. This error could be caused by a bug in PCRE2 or by overwriting of the compiled pattern. PCRE2_ERROR_JIT_BADOPTION - This error is returned when a pattern that was successfully studied - using JIT is being matched, but the matching mode (partial or complete - match) does not correspond to any JIT compilation mode. When the JIT - fast path function is used, this error may be also given for invalid + This error is returned when a pattern that was successfully studied + using JIT is being matched, but the matching mode (partial or complete + match) does not correspond to any JIT compilation mode. When the JIT + fast path function is used, this error may be also given for invalid options. See the pcre2jit documentation for more details. PCRE2_ERROR_JIT_STACKLIMIT - This error is returned when a pattern that was successfully studied - using JIT is being matched, but the memory available for the just-in- - time processing stack is not large enough. See the pcre2jit documenta- + This error is returned when a pattern that was successfully studied + using JIT is being matched, but the memory available for the just-in- + time processing stack is not large enough. See the pcre2jit documenta- tion for more details. PCRE2_ERROR_MATCHLIMIT @@ -2161,10 +2182,10 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_NOMEMORY - If a pattern contains back references, but the ovector is not big - enough to remember the referenced substrings, PCRE2 gets a block of + If a pattern contains back references, but the ovector is not big + enough to remember the referenced substrings, PCRE2 gets a block of memory at the start of matching to use for this purpose. There are some - other special cases where extra memory is needed during matching. This + other special cases where extra memory is needed during matching. This error is given when memory cannot be obtained. PCRE2_ERROR_NULL @@ -2173,12 +2194,12 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_RECURSELOOP - This error is returned when pcre2_match() detects a recursion loop - within the pattern. Specifically, it means that either the whole pat- + This error is returned when pcre2_match() detects a recursion loop + within the pattern. Specifically, it means that either the whole pat- tern or a subpattern has been called recursively for the second time at - the same position in the subject string. Some simple patterns that - might do this are detected and faulted at compile time, but more com- - plicated cases, in particular mutual recursions between two different + the same position in the subject string. Some simple patterns that + might do this are detected and faulted at compile time, but more com- + plicated cases, in particular mutual recursions between two different subpatterns, cannot be detected until matching is attempted. PCRE2_ERROR_RECURSIONLIMIT @@ -2201,28 +2222,37 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER void pcre2_substring_free(PCRE2_UCHAR *buffer); - Captured substrings can be accessed directly by using the ovector as + Captured substrings can be accessed directly by using the ovector as described above. For convenience, auxiliary functions are provided for - extracting captured substrings as new, separate, zero-terminated - strings. The functions in this section identify substrings by number. - The next section describes similar functions for extracting substrings - by name. A substring that contains a binary zero is correctly extracted - and has a further zero added on the end, but the result is not, of - course, a C string. + extracting captured substrings as new, separate, zero-terminated + strings. The functions in this section identify substrings by number. + The number zero refers to the entire matched substring, with higher + numbers referring to substrings captured by parenthesized groups. The + next section describes similar functions for extracting captured sub- + strings by name. A substring that contains a binary zero is correctly + extracted and has a further zero added on the end, but the result is + not, of course, a C string. + + If a pattern uses the \K escape sequence within a positive assertion, + the reported start of the match can be greater than the end of the + match. For example, if the pattern (?=ab\K) is matched against "ab", + the start and end offset values for the match are 2 and 0. In this sit- + uation, calling these functions with a zero substring number extracts a + zero-length empty string. You can find the length in code units of a captured substring without extracting it by calling pcre2_substring_length_bynumber(). The first argument is a pointer to the match data block, the second is the group number, and the third is a pointer to a variable into which the length - is placed. + is placed. If you just want to know whether or not the substring has + been captured, you can pass the third argument as NULL. - The pcre2_substring_copy_bynumber() function copies one string into a - supplied buffer, whereas pcre2_substring_get_bynumber() copies it into - new memory, obtained using the same memory allocation function that was - used for the match data block. The first two arguments of these func- - tions are a pointer to the match data block and a capturing group num- - ber. A group number of zero extracts the substring that matched the - entire pattern, and higher values extract the captured substrings. + The pcre2_substring_copy_bynumber() function copies a captured sub- + string into a supplied buffer, whereas pcre2_substring_get_bynumber() + copies it into new memory, obtained using the same memory allocation + function that was used for the match data block. The first two argu- + ments of these functions are a pointer to the match data block and a + capturing group number. The final arguments of pcre2_substring_copy_bynumber() are a pointer to the buffer and a pointer to a variable that contains its length in code @@ -2235,20 +2265,31 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER terminating zero. When the substring is no longer needed, the memory should be freed by calling pcre2_substring_free(). - The return value from these functions is zero for success, or one of - these error codes: + The return value from all these functions is zero for success, or a + negative error code. If the pattern match failed, the match failure + code is returned. Other possible error codes are: PCRE2_ERROR_NOMEMORY - The buffer was too small for pcre2_substring_copy_bynumber(), or the + The buffer was too small for pcre2_substring_copy_bynumber(), or the attempt to get memory failed for pcre2_substring_get_bynumber(). PCRE2_ERROR_NOSUBSTRING - No substring with the given number was captured. This could be because - there is no capturing group of that number in the pattern, or because - the group with that number did not participate in the match, or because - the ovector was too small to capture that group. + There is no substring with that number in the pattern, that is, the + number is greater than the number of capturing parentheses. + + PCRE2_ERROR_UNAVAILABLE + + The substring number, though not greater than the number of captures in + the pattern, is greater than the number of slots in the ovector, so the + substring could not be captured. + + PCRE2_ERROR_UNSET + + The substring did not participate in the match. For example, if the + pattern is (abc)|(def) and the subject is "def", and the ovector con- + tains at least two capturing slots, substring number 1 is unset. EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS @@ -2258,29 +2299,30 @@ EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS void pcre2_substring_list_free(PCRE2_SPTR *list); - The pcre2_substring_list_get() function extracts all available sub- - strings and builds a list of pointers to them. It also (optionally) - builds a second list that contains their lengths (in code units), + The pcre2_substring_list_get() function extracts all available sub- + strings and builds a list of pointers to them. It also (optionally) + builds a second list that contains their lengths (in code units), excluding a terminating zero that is added to each of them. All this is done in a single block of memory that is obtained using the same memory allocation function that was used to get the match data block. - The address of the memory block is returned via listptr, which is also + The address of the memory block is returned via listptr, which is also the start of the list of string pointers. The end of the list is marked - by a NULL pointer. The address of the list of lengths is returned via - lengthsptr. If your strings do not contain binary zeros and you do not + by a NULL pointer. The address of the list of lengths is returned via + lengthsptr. If your strings do not contain binary zeros and you do not therefore need the lengths, you may supply NULL as the lengthsptr argu- - ment to disable the creation of a list of lengths. The yield of the - function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the mem- - ory block could not be obtained. When the list is no longer needed, it + ment to disable the creation of a list of lengths. The yield of the + function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the mem- + ory block could not be obtained. When the list is no longer needed, it should be freed by calling pcre2_substring_list_free(). If this function encounters a substring that is unset, which can happen - when capturing subpattern number n+1 matches some part of the subject, - but subpattern n has not been used at all, it returns an empty string. - This can be distinguished from a genuine zero-length substring by + when capturing subpattern number n+1 matches some part of the subject, + but subpattern n has not been used at all, it returns an empty string. + This can be distinguished from a genuine zero-length substring by inspecting the appropriate offset in the ovector, which contain - PCRE2_UNSET for unset substrings. + PCRE2_UNSET for unset substrings, or by calling pcre2_sub- + string_length_bynumber(). EXTRACTING CAPTURED SUBSTRINGS BY NAME @@ -2310,21 +2352,28 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME ment is the compiled pattern, and the second is the name. The yield of the function is the subpattern number, PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if - there is more than one subpattern of that name. + there is more than one subpattern of that name. Given the number, you + can extract the substring directly, or use one of the functions + described above. - Given the number, you can extract the substring directly, or use one of - the functions described above. For convenience, there are also "byname" - functions that correspond to the "bynumber" functions, the only differ- - ence being that the second argument is a name instead of a number. How- - ever, if PCRE2_DUPNAMES is set and there are duplicate names, the be- - haviour may not be what you want. + For convenience, there are also "byname" functions that correspond to + the "bynumber" functions, the only difference being that the second + argument is a name instead of a number. If PCRE2_DUPNAMES is set and + there are duplicate names, these functions scan all the groups with the + given name, and return the first named string that is set. + + If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is + returned. If all groups with the name have numbers that are greater + than the number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is + returned. If there is at least one group with a slot in the ovector, + but no group is found to be set, PCRE2_ERROR_UNSET is returned. Warning: If the pattern uses the (?| feature to set up multiple subpat- - terns with the same number, as described in the section on duplicate - subpattern numbers in the pcre2pattern page, you cannot use names to - distinguish the different subpatterns, because names are not included - in the compiled code. The matching process uses only numbers. For this - reason, the use of different names for subpatterns of the same number + terns with the same number, as described in the section on duplicate + subpattern numbers in the pcre2pattern page, you cannot use names to + distinguish the different subpatterns, because names are not included + in the compiled code. The matching process uses only numbers. For this + reason, the use of different names for subpatterns of the same number causes an error at compile time. @@ -2336,53 +2385,53 @@ CREATING A NEW STRING WITH SUBSTITUTIONS pcre2_match_context *mcontext, PCRE2_SPTR replacementzfP, PCRE2_SIZE rlength, PCRE2_UCHAR *outputbufferP, PCRE2_SIZE *outlengthptr); - This function calls pcre2_match() and then makes a copy of the subject - string in outputbuffer, replacing the part that was matched with the - replacement string, whose length is supplied in rlength. This can be + This function calls pcre2_match() and then makes a copy of the subject + string in outputbuffer, replacing the part that was matched with the + replacement string, whose length is supplied in rlength. This can be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. - In the replacement string, which is interpreted as a UTF string in UTF - mode, and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK + In the replacement string, which is interpreted as a UTF string in UTF + mode, and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK option is set, a dollar character is an escape character that can spec- - ify the insertion of characters from capturing groups in the pattern. + ify the insertion of characters from capturing groups in the pattern. The following forms are recognized: $$ insert a dollar character $ insert the contents of group ${} insert the contents of group - Either a group number or a group name can be given for . Curly - brackets are required only if the following character would be inter- + Either a group number or a group name can be given for . Curly + brackets are required only if the following character would be inter- preted as part of the number or name. The number may be zero to include - the entire matched string. For example, if the pattern a(b)c is - matched with "=abc=" and the replacement string "+$1$0$1+", the result - is "=+babcb+=". Group insertion is done by calling pcre2_copy_byname() + the entire matched string. For example, if the pattern a(b)c is + matched with "=abc=" and the replacement string "+$1$0$1+", the result + is "=+babcb+=". Group insertion is done by calling pcre2_copy_byname() or pcre2_copy_bynumber() as appropriate. - The first seven arguments of pcre2_substitute() are the same as for + The first seven arguments of pcre2_substitute() are the same as for pcre2_match(), except that the partial matching options are not permit- - ted, and match_data may be passed as NULL, in which case a match data - block is obtained and freed within this function, using memory manage- - ment functions from the match context, if provided, or else those that + ted, and match_data may be passed as NULL, in which case a match data + block is obtained and freed within this function, using memory manage- + ment functions from the match context, if provided, or else those that were used to allocate memory for the compiled code. - There is one additional option, PCRE2_SUBSTITUTE_GLOBAL, which causes + There is one additional option, PCRE2_SUBSTITUTE_GLOBAL, which causes the function to iterate over the subject string, replacing every match- ing substring. If this is not set, only the first matching substring is replaced. - The outlengthptr argument must point to a variable that contains the - length, in code units, of the output buffer. It is updated to contain + The outlengthptr argument must point to a variable that contains the + length, in code units, of the output buffer. It is updated to contain the length of the new string, excluding the trailing zero that is auto- matically added. - The function returns the number of replacements that were made. This - may be zero if no matches were found, and is never greater than 1 + The function returns the number of replacements that were made. This + may be zero if no matches were found, and is never greater than 1 unless PCRE2_SUBSTITUTE_GLOBAL is set. In the event of an error, a neg- - ative error code is returned. Except for PCRE2_ERROR_NOMATCH (which is + ative error code is returned. Except for PCRE2_ERROR_NOMATCH (which is never returned), any errors from pcre2_match() or the substring copying functions are passed straight back. PCRE2_ERROR_BADREPLACEMENT is - returned for an invalid replacement string (unrecognized sequence fol- + returned for an invalid replacement string (unrecognized sequence fol- lowing a dollar sign), and PCRE2_ERROR_NOMEMORY is returned if the out- put buffer is not big enough. @@ -2392,21 +2441,22 @@ DUPLICATE SUBPATTERN NAMES int pcre2_substring_nametable_scan(const pcre2_code *code, PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); - When a pattern is compiled with the PCRE2_DUPNAMES option, names for - subpatterns are not required to be unique. Duplicate names are always - allowed for subpatterns with the same number, created by using the (?| - feature. Indeed, if such subpatterns are named, they are required to + When a pattern is compiled with the PCRE2_DUPNAMES option, names for + subpatterns are not required to be unique. Duplicate names are always + allowed for subpatterns with the same number, created by using the (?| + feature. Indeed, if such subpatterns are named, they are required to use the same names. Normally, patterns with duplicate names are such that in any one match, - only one of the named subpatterns participates. An example is shown in + only one of the named subpatterns participates. An example is shown in the pcre2pattern documentation. - When duplicates are present, pcre2_substring_copy_byname() and - pcre2_substring_get_byname() return the first substring corresponding - to the given name that is set. If none are set, PCRE2_ERROR_NOSUBSTRING - is returned. The pcre2_substring_number_from_name() function returns - the error PCRE2_ERROR_NOUNIQUESUBSTRING. + When duplicates are present, pcre2_substring_copy_byname() and + pcre2_substring_get_byname() return the first substring corresponding + to the given name that is set. Only if none are set is + PCRE2_ERROR_UNSET is returned. The pcre2_substring_number_from_name() + function returns the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are + duplicate names. If you want to get full details of all captured substrings for a given name, you must use the pcre2_substring_nametable_scan() function. The @@ -2549,17 +2599,37 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION the three matched strings are - - + + On success, the yield of the function is a number greater than zero, which is the number of matched substrings. The offsets of the sub- - strings are returned in the ovector, and can be extracted in the same - way as for pcre2_match(). They are returned in reverse order of - length; that is, the longest matching string is given first. If there - were too many matches to fit into the ovector, the yield of the func- - tion is zero, and the vector is filled with the longest matches. + strings are returned in the ovector, and can be extracted by number in + the same way as for pcre2_match(), but the numbers bear no relation to + any capturing groups that may exist in the pattern, because DFA match- + ing does not support group capture. + + Calls to the convenience functions that extract substrings by name + return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used + after a DFA match. The convenience functions that extract substrings by + number never return PCRE2_ERROR_NOSUBSTRING, and the meanings of some + other errors are slightly different: + + PCRE2_ERROR_UNAVAILABLE + + The ovector is not big enough to include a slot for the given substring + number. + + PCRE2_ERROR_UNSET + + There is a slot in the ovector for this substring, but there were + insufficient matches to fill it. + + The matched strings are stored in the ovector in reverse order of + length; that is, the longest matching string is first. If there were + too many matches to fit into the ovector, the yield of the function is + zero, and the vector is filled with the longest matches. NOTE: PCRE2's "auto-possessification" optimization usually applies to character repeats at the end of a pattern (as well as internally). For @@ -2624,7 +2694,7 @@ AUTHOR REVISION - Last updated: 01 December 2014 + Last updated: 14 December 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ diff --git a/doc/pcre2_substring_copy_byname.3 b/doc/pcre2_substring_copy_byname.3 index 5c8d075..d2af63b 100644 --- a/doc/pcre2_substring_copy_byname.3 +++ b/doc/pcre2_substring_copy_byname.3 @@ -29,10 +29,10 @@ success or one of the following error numbers: PCRE2_ERROR_NOSUBSTRING there are no groups of that name PCRE2_ERROR_UNAVAILBLE the ovector was too small for that group PCRE2_ERROR_UNSET the group did not participate in the match - PCRE2_ERROR_NOMEMORY the buffer is not big enough + PCRE2_ERROR_NOMEMORY the buffer is not big enough .sp -If there is more than one group with the given name, the first one that is set -is returned. In this situation PCRE2_ERROR_UNSET means that no group with the +If there is more than one group with the given name, the first one that is set +is returned. In this situation PCRE2_ERROR_UNSET means that no group with the given name was set. .P There is a complete description of the PCRE2 native API in the diff --git a/doc/pcre2_substring_get_byname.3 b/doc/pcre2_substring_get_byname.3 index bb4b911..6c3f7d5 100644 --- a/doc/pcre2_substring_get_byname.3 +++ b/doc/pcre2_substring_get_byname.3 @@ -33,8 +33,8 @@ the following error numbers: PCRE2_ERROR_UNSET the group did not participate in the match PCRE2_ERROR_NOMEMORY memory could not be obtained .sp -If there is more than one group with the given name, the first one that is set -is returned. In this situation PCRE2_ERROR_UNSET means that no group with the +If there is more than one group with the given name, the first one that is set +is returned. In this situation PCRE2_ERROR_UNSET means that no group with the given name was set. .P There is a complete description of the PCRE2 native API in the diff --git a/doc/pcre2api.3 b/doc/pcre2api.3 index bd1108d..bc5b640 100644 --- a/doc/pcre2api.3 +++ b/doc/pcre2api.3 @@ -927,7 +927,7 @@ be referenced by the extraction functions. After running a match, you must not free a compiled pattern (or a subject string) until after all operations on the .\" HTML .\" -match data block +match data block .\" have taken place. .P @@ -2070,9 +2070,9 @@ returned value is 3. If there are no capturing subpatterns, the return value from a successful match is 1, indicating that just the first pair of offsets has been set. .P -If a pattern uses the \eK escape sequence within a positive assertion, the -reported start of the match can be greater than the end of the match. For -example, if the pattern (?=ab\eK) is matched against "ab", the start and end +If a pattern uses the \eK escape sequence within a positive assertion, the +reported start of the match can be greater than the end of the match. For +example, if the pattern (?=ab\eK) is matched against "ab", the start and end offset values for the match are 2 and 0. .P If a capturing subpattern group is matched repeatedly within a single match @@ -2297,17 +2297,17 @@ extracting captured substrings by name. A substring that contains a binary zero is correctly extracted and has a further zero added on the end, but the result is not, of course, a C string. .P -If a pattern uses the \eK escape sequence within a positive assertion, the -reported start of the match can be greater than the end of the match. For -example, if the pattern (?=ab\eK) is matched against "ab", the start and end -offset values for the match are 2 and 0. In this situation, calling these +If a pattern uses the \eK escape sequence within a positive assertion, the +reported start of the match can be greater than the end of the match. For +example, if the pattern (?=ab\eK) is matched against "ab", the start and end +offset values for the match are 2 and 0. In this situation, calling these functions with a zero substring number extracts a zero-length empty string. .P You can find the length in code units of a captured substring without extracting it by calling \fBpcre2_substring_length_bynumber()\fP. The first argument is a pointer to the match data block, the second is the group number, -and the third is a pointer to a variable into which the length is placed. If -you just want to know whether or not the substring has been captured, you can +and the third is a pointer to a variable into which the length is placed. If +you just want to know whether or not the substring has been captured, you can pass the third argument as NULL. .P The \fBpcre2_substring_copy_bynumber()\fP function copies a captured substring @@ -2338,13 +2338,13 @@ attempt to get memory failed for \fBpcre2_substring_get_bynumber()\fP. .sp PCRE2_ERROR_NOSUBSTRING .sp -There is no substring with that number in the pattern, that is, the number is +There is no substring with that number in the pattern, that is, the number is greater than the number of capturing parentheses. .sp PCRE2_ERROR_UNAVAILABLE .sp -The substring number, though not greater than the number of captures in the -pattern, is greater than the number of slots in the ovector, so the substring +The substring number, though not greater than the number of captures in the +pattern, is greater than the number of slots in the ovector, so the substring could not be captured. .sp PCRE2_ERROR_UNSET @@ -2429,10 +2429,10 @@ name instead of a number. If PCRE2_DUPNAMES is set and there are duplicate names, these functions scan all the groups with the given name, and return the first named string that is set. .P -If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is -returned. If all groups with the name have numbers that are greater than the -number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is returned. If there -is at least one group with a slot in the ovector, but no group is found to be +If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is +returned. If all groups with the name have numbers that are greater than the +number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is returned. If there +is at least one group with a slot in the ovector, but no group is found to be set, PCRE2_ERROR_UNSET is returned. .P \fBWarning:\fP If the pattern uses the (?| feature to set up multiple @@ -2706,7 +2706,7 @@ the number of matched substrings. The offsets of the substrings are returned in the ovector, and can be extracted by number in the same way as for \fBpcre2_match()\fP, but the numbers bear no relation to any capturing groups that may exist in the pattern, because DFA matching does not support group -capture. +capture. .P Calls to the convenience functions that extract substrings by name return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used after a @@ -2720,7 +2720,7 @@ The ovector is not big enough to include a slot for the given substring number. .sp PCRE2_ERROR_UNSET .sp -There is a slot in the ovector for this substring, but there were insufficient +There is a slot in the ovector for this substring, but there were insufficient matches to fill it. .P The matched strings are stored in the ovector in reverse order of length; that diff --git a/src/config.h.generic b/src/config.h.generic index a90c2de..5fb75f1 100644 --- a/src/config.h.generic +++ b/src/config.h.generic @@ -201,7 +201,7 @@ sure both macros are undefined; an emulation function will then be used. */ #define PACKAGE_NAME "PCRE2" /* Define to the full name and version of this package. */ -#define PACKAGE_STRING "PCRE2 10.00-RC1" +#define PACKAGE_STRING "PCRE2 10.00-RC2" /* Define to the one symbol short name of this package. */ #define PACKAGE_TARNAME "pcre2" @@ -210,7 +210,7 @@ sure both macros are undefined; an emulation function will then be used. */ #define PACKAGE_URL "" /* Define to the version of this package. */ -#define PACKAGE_VERSION "10.00-RC1" +#define PACKAGE_VERSION "10.00-RC2" /* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested parentheses (of any kind) in a pattern. This limits the amount of system @@ -288,7 +288,7 @@ sure both macros are undefined; an emulation function will then be used. */ /* #undef SUPPORT_VALGRIND */ /* Version number of package */ -#define VERSION "10.00-RC1" +#define VERSION "10.00-RC2" /* Define to empty if `const' does not conform to ANSI C. */ /* #undef const */ diff --git a/src/pcre2.h.generic b/src/pcre2.h.generic index 3fef2e9..514cf63 100644 --- a/src/pcre2.h.generic +++ b/src/pcre2.h.generic @@ -43,8 +43,8 @@ POSSIBILITY OF SUCH DAMAGE. #define PCRE2_MAJOR 10 #define PCRE2_MINOR 00 -#define PCRE2_PRERELEASE -RC1 -#define PCRE2_DATE 2014-11-28 +#define PCRE2_PRERELEASE -RC2 +#define PCRE2_DATE 2014-12-19 /* When an application links to a PCRE DLL in Windows, the symbols that are imported have to be identified as such. When building PCRE2, the appropriate @@ -80,20 +80,20 @@ uint8_t, UCHAR_MAX, etc are defined. */ extern "C" { #endif -/* The following options can be passed to pcre2_compile(), pcre2_match(), or -pcre2_dfa_match(). PCRE2_NO_UTF_CHECK affects only the function to which it is -passed. Put these bits at the most significant end of the options word so +/* The following option bits can be passed to pcre2_compile(), pcre2_match(), +or pcre2_dfa_match(). PCRE2_NO_UTF_CHECK affects only the function to which it +is passed. Put these bits at the most significant end of the options word so others can be added next to them */ #define PCRE2_ANCHORED 0x80000000u #define PCRE2_NO_UTF_CHECK 0x40000000u -/* Other options that can be passed to pcre2_compile(). They may affect -compilation, JIT compilation, and/or interpretive execution. The following tags -indicate which: +/* The following option bits can be passed only to pcre2_compile(). However, +they may affect compilation, JIT compilation, and/or interpretive execution. +The following tags indicate which: -C alters what is compiled -J alters what JIT compiles +C alters what is compiled by pcre2_compile() +J alters what is compiled by pcre2_jit_compile() M is inspected during pcre2_match() execution D is inspected during pcre2_dfa_match() execution */ @@ -212,19 +212,21 @@ context functions. */ #define PCRE2_ERROR_DFA_BADRESTART (-38) #define PCRE2_ERROR_DFA_RECURSE (-39) #define PCRE2_ERROR_DFA_UCOND (-40) -#define PCRE2_ERROR_DFA_UITEM (-41) -#define PCRE2_ERROR_DFA_WSSIZE (-42) -#define PCRE2_ERROR_INTERNAL (-43) -#define PCRE2_ERROR_JIT_BADOPTION (-44) -#define PCRE2_ERROR_JIT_STACKLIMIT (-45) -#define PCRE2_ERROR_MATCHLIMIT (-46) -#define PCRE2_ERROR_NOMEMORY (-47) -#define PCRE2_ERROR_NOSUBSTRING (-48) -#define PCRE2_ERROR_NOUNIQUESUBSTRING (-49) -#define PCRE2_ERROR_NULL (-50) -#define PCRE2_ERROR_RECURSELOOP (-51) -#define PCRE2_ERROR_RECURSIONLIMIT (-52) -#define PCRE2_ERROR_UNSET (-53) +#define PCRE2_ERROR_DFA_UFUNC (-41) +#define PCRE2_ERROR_DFA_UITEM (-42) +#define PCRE2_ERROR_DFA_WSSIZE (-43) +#define PCRE2_ERROR_INTERNAL (-44) +#define PCRE2_ERROR_JIT_BADOPTION (-45) +#define PCRE2_ERROR_JIT_STACKLIMIT (-46) +#define PCRE2_ERROR_MATCHLIMIT (-47) +#define PCRE2_ERROR_NOMEMORY (-48) +#define PCRE2_ERROR_NOSUBSTRING (-49) +#define PCRE2_ERROR_NOUNIQUESUBSTRING (-50) +#define PCRE2_ERROR_NULL (-51) +#define PCRE2_ERROR_RECURSELOOP (-52) +#define PCRE2_ERROR_RECURSIONLIMIT (-53) +#define PCRE2_ERROR_UNAVAILABLE (-54) +#define PCRE2_ERROR_UNSET (-55) /* Request types for pcre2_pattern_info() */ @@ -434,16 +436,16 @@ PCRE2_EXP_DECL PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *); PCRE2_EXP_DECL int pcre2_substring_copy_byname(pcre2_match_data *, \ PCRE2_SPTR, PCRE2_UCHAR *, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_copy_bynumber(pcre2_match_data *, \ - unsigned int, PCRE2_UCHAR *, PCRE2_SIZE *); \ + uint32_t, PCRE2_UCHAR *, PCRE2_SIZE *); \ PCRE2_EXP_DECL void pcre2_substring_free(PCRE2_UCHAR *); \ PCRE2_EXP_DECL int pcre2_substring_get_byname(pcre2_match_data *, \ PCRE2_SPTR, PCRE2_UCHAR **, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_get_bynumber(pcre2_match_data *, \ - unsigned int, PCRE2_UCHAR **, PCRE2_SIZE *); \ + uint32_t, PCRE2_UCHAR **, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_length_byname(pcre2_match_data *, \ PCRE2_SPTR, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_length_bynumber(pcre2_match_data *, \ - unsigned int, PCRE2_SIZE *); \ + uint32_t, PCRE2_SIZE *); \ PCRE2_EXP_DECL int pcre2_substring_nametable_scan(const pcre2_code *, \ PCRE2_SPTR, PCRE2_SPTR *, PCRE2_SPTR *); \ PCRE2_EXP_DECL int pcre2_substring_number_from_name(\ diff --git a/src/pcre2_error.c b/src/pcre2_error.c index ce72fda..dd152d3 100644 --- a/src/pcre2_error.c +++ b/src/pcre2_error.c @@ -228,7 +228,7 @@ static const char match_error_texts[] = "NULL argument passed\0" "nested recursion at the same subject position\0" "recursion limit exceeded\0" - "requested value is not available\0" + "requested value is not available\0" "requested value is not set\0" ; diff --git a/src/pcre2_internal.h b/src/pcre2_internal.h index c8696bf..cbddecc 100644 --- a/src/pcre2_internal.h +++ b/src/pcre2_internal.h @@ -530,7 +530,7 @@ bytes in a code unit in that mode. */ enum { PCRE2_MATCHEDBY_INTERPRETER, /* pcre2_match() */ PCRE2_MATCHEDBY_DFA_INTERPRETER, /* pcre2_dfa_match() */ - PCRE2_MATCHEDBY_JIT }; /* pcre2_jit_match() */ + PCRE2_MATCHEDBY_JIT }; /* pcre2_jit_match() */ /* Magic number to provide a small check against being handed junk. */ diff --git a/src/pcre2_intmodedep.h b/src/pcre2_intmodedep.h index eb713cb..44acb89 100644 --- a/src/pcre2_intmodedep.h +++ b/src/pcre2_intmodedep.h @@ -620,7 +620,7 @@ typedef struct pcre2_real_match_data { PCRE2_SIZE leftchar; /* Offset to leftmost code unit */ PCRE2_SIZE rightchar; /* Offset to rightmost code unit */ PCRE2_SIZE startchar; /* Offset to starting code unit */ - uint16_t matchedby; /* Type of match (normal, JIT, DFA) */ + uint16_t matchedby; /* Type of match (normal, JIT, DFA) */ uint16_t oveccount; /* Number of pairs */ int rc; /* The return code from the match */ PCRE2_SIZE ovector[1]; /* The first field */ diff --git a/src/pcre2_substring.c b/src/pcre2_substring.c index 5299def..209e50a 100644 --- a/src/pcre2_substring.c +++ b/src/pcre2_substring.c @@ -65,7 +65,7 @@ Returns: if successful: zero if not successful, a negative error code: (1) an error from nametable_scan() (2) an error from copy_bynumber() - (3) PCRE2_ERROR_UNAVAILABLE: no group is in ovector + (3) PCRE2_ERROR_UNAVAILABLE: no group is in ovector (4) PCRE2_ERROR_UNSET: all named groups in ovector are unset */ @@ -88,8 +88,8 @@ for (entry = first; entry <= last; entry += entrysize) { if (match_data->ovector[n*2] != PCRE2_UNSET) return pcre2_substring_copy_bynumber(match_data, n, buffer, sizeptr); - failrc = PCRE2_ERROR_UNSET; - } + failrc = PCRE2_ERROR_UNSET; + } } return failrc; } @@ -114,7 +114,7 @@ Returns: if successful: 0 PCRE2_ERROR_NOMEMORY: buffer too small PCRE2_ERROR_NOSUBSTRING: no such substring PCRE2_ERROR_UNAVAILABLE: ovector too small - PCRE2_ERROR_UNSET: substring is not set + PCRE2_ERROR_UNSET: substring is not set */ PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION @@ -126,7 +126,7 @@ PCRE2_SIZE size; rc = pcre2_substring_length_bynumber(match_data, stringnumber, &size); if (rc < 0) return rc; if (size + 1 > *sizeptr) return PCRE2_ERROR_NOMEMORY; -memcpy(buffer, match_data->subject + match_data->ovector[stringnumber*2], +memcpy(buffer, match_data->subject + match_data->ovector[stringnumber*2], CU2BYTES(size)); buffer[size] = 0; *sizeptr = size; @@ -152,8 +152,8 @@ Arguments: Returns: if successful: zero if not successful, a negative value: (1) an error from nametable_scan() - (2) an error from get_bynumber() - (3) PCRE2_ERROR_UNAVAILABLE: no group is in ovector + (2) an error from get_bynumber() + (3) PCRE2_ERROR_UNAVAILABLE: no group is in ovector (4) PCRE2_ERROR_UNSET: all named groups in ovector are unset */ @@ -177,7 +177,7 @@ for (entry = first; entry <= last; entry += entrysize) if (match_data->ovector[n*2] != PCRE2_UNSET) return pcre2_substring_get_bynumber(match_data, n, stringptr, sizeptr); failrc = PCRE2_ERROR_UNSET; - } + } } return failrc; } @@ -202,7 +202,7 @@ Returns: if successful: 0 PCRE2_ERROR_NOMEMORY: failed to get memory PCRE2_ERROR_NOSUBSTRING: no such substring PCRE2_ERROR_UNAVAILABLE: ovector too small - PCRE2_ERROR_UNSET: substring is not set + PCRE2_ERROR_UNSET: substring is not set */ PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION @@ -218,7 +218,7 @@ yield = PRIV(memctl_malloc)(sizeof(pcre2_memctl) + (size + 1)*PCRE2_CODE_UNIT_WIDTH, (pcre2_memctl *)match_data); if (yield == NULL) return PCRE2_ERROR_NOMEMORY; yield = (PCRE2_UCHAR *)(((char *)yield) + sizeof(pcre2_memctl)); -memcpy(yield, match_data->subject + match_data->ovector[stringnumber*2], +memcpy(yield, match_data->subject + match_data->ovector[stringnumber*2], CU2BYTES(size)); yield[size] = 0; *stringptr = yield; @@ -281,7 +281,7 @@ for (entry = first; entry <= last; entry += entrysize) if (match_data->ovector[n*2] != PCRE2_UNSET) return pcre2_substring_length_bynumber(match_data, n, sizeptr); failrc = PCRE2_ERROR_UNSET; - } + } } return failrc; } @@ -292,8 +292,8 @@ return failrc; * Get length of a numbered substring * *************************************************/ -/* This function returns the length of a captured substring. If the start is -beyond the end (which can happen when \K is used in an assertion), it sets the +/* This function returns the length of a captured substring. If the start is +beyond the end (which can happen when \K is used in an assertion), it sets the length to zero. Arguments: @@ -305,7 +305,7 @@ Returns: if successful: 0 if not successful, a negative error code: PCRE2_ERROR_NOSUBSTRING: no such substring PCRE2_ERROR_UNAVAILABLE: ovector is too small - PCRE2_ERROR_UNSET: substring is not set + PCRE2_ERROR_UNSET: substring is not set */ PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION @@ -317,9 +317,9 @@ PCRE2_SIZE left, right; if ((count = match_data->rc) < 0) return count; /* Match failed */ if (match_data->matchedby != PCRE2_MATCHEDBY_DFA_INTERPRETER) { - if (stringnumber > match_data->code->top_bracket) + if (stringnumber > match_data->code->top_bracket) return PCRE2_ERROR_NOSUBSTRING; - if (stringnumber >= match_data->oveccount) + if (stringnumber >= match_data->oveccount) return PCRE2_ERROR_UNAVAILABLE; if (match_data->ovector[stringnumber*2] == PCRE2_UNSET) return PCRE2_ERROR_UNSET; @@ -328,11 +328,11 @@ else /* Matched using pcre2_dfa_match() */ { if (stringnumber >= match_data->oveccount) return PCRE2_ERROR_UNAVAILABLE; if (count != 0 && stringnumber >= (uint32_t)count) return PCRE2_ERROR_UNSET; - } + } left = match_data->ovector[stringnumber*2]; right = match_data->ovector[stringnumber*2+1]; if (sizeptr != NULL) *sizeptr = (left > right)? 0 : right - left; -return 0; +return 0; } @@ -382,8 +382,8 @@ for (i = 0; i < count2; i += 2) { size += sizeof(PCRE2_UCHAR *) + CU2BYTES(1); if (ovector[i+1] > ovector[i]) size += CU2BYTES(ovector[i+1] - ovector[i]); - } - + } + memp = PRIV(memctl_malloc)(size, (pcre2_memctl *)match_data); if (memp == NULL) return PCRE2_ERROR_NOMEMORY; @@ -489,7 +489,7 @@ while (top > bot) if (PRIV(strcmp)(stringname, (last + entrysize + IMM2_SIZE)) != 0) break; last += entrysize; } - if (firstptr == NULL) return (first == last)? + if (firstptr == NULL) return (first == last)? (int)GET2(entry, 0) : PCRE2_ERROR_NOUNIQUESUBSTRING; *firstptr = first; *lastptr = last; diff --git a/src/pcre2test.c b/src/pcre2test.c index 95cdbb8..7de394b 100644 --- a/src/pcre2test.c +++ b/src/pcre2test.c @@ -4142,7 +4142,7 @@ if (callout_capture) for (i = 0; i < cb->capture_top * 2; i += 2) { fprintf(f, "%2d: ", i/2); - if (cb->offset_vector[i] == PCRE2_UNSET) + if (cb->offset_vector[i] == PCRE2_UNSET) fprintf(f, ""); else {