From 1c41a5b8157f110cf60db69c0133b1b28a1eb177 Mon Sep 17 00:00:00 2001 From: Philip Hazel Date: Tue, 14 Dec 2021 15:52:24 +0000 Subject: [PATCH] Fix minor issues raised by Clang sanitize --- ChangeLog | 2 + doc/html/pcre2api.html | 14 +- doc/pcre2.txt | 413 +++++++++++++++++++++-------------------- doc/pcre2api.3 | 16 +- src/pcre2_compile.c | 140 +++++++------- src/pcre2_intmodedep.h | 2 +- src/pcre2_match.c | 5 +- src/pcre2_study.c | 4 +- src/pcre2_substitute.c | 14 +- src/pcre2test.c | 39 ++-- 10 files changed, 336 insertions(+), 313 deletions(-) diff --git a/ChangeLog b/ChangeLog index 45813a6..101688a 100644 --- a/ChangeLog +++ b/ChangeLog @@ -41,6 +41,8 @@ of applications treat NULL/0 in this way. 14. Added support for Bidi_Class and Bidi_Control Unicode properties. +15. Fix some minor issues raised by clang sanitize. + Version 10.39 29-October-2021 ----------------------------- diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index b7c0907..0a93d67 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -3440,12 +3440,12 @@ block may or may not have been changed. As well as the usual options for pcre2_match(), a number of additional options can be set in the options argument of pcre2_substitute(). One such option is PCRE2_SUBSTITUTE_MATCHED. When this is set, an external -match_data block must be provided, and it must have been used for an -external call to pcre2_match(). The data in the match_data block -(return code, offset vector) is used for the first substitution instead of -calling pcre2_match() from within pcre2_substitute(). This allows -an application to check for a match before choosing to substitute, without -having to repeat the match. +match_data block must be provided, and it must have already been used for +an external call to pcre2_match() with the same pattern and subject +arguments. The data in the match_data block (return code, offset vector) +is then used for the first substitution instead of calling pcre2_match() +from within pcre2_substitute(). This allows an application to check for a +match before choosing to substitute, without having to repeat the match.

The contents of the externally supplied match data block are not changed when @@ -4018,7 +4018,7 @@ Cambridge, England.


REVISION

-Last updated: 08 December 2021 +Last updated: 14 December 2021
Copyright © 1997-2021 University of Cambridge.
diff --git a/doc/pcre2.txt b/doc/pcre2.txt index f2b877d..e1e9c1a 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -3321,89 +3321,90 @@ CREATING A NEW STRING WITH SUBSTITUTIONS As well as the usual options for pcre2_match(), a number of additional options can be set in the options argument of pcre2_substitute(). One such option is PCRE2_SUBSTITUTE_MATCHED. When this is set, an external - match_data block must be provided, and it must have been used for an - external call to pcre2_match(). The data in the match_data block (re- - turn code, offset vector) is used for the first substitution instead of - calling pcre2_match() from within pcre2_substitute(). This allows an - application to check for a match before choosing to substitute, without - having to repeat the match. + match_data block must be provided, and it must have already been used + for an external call to pcre2_match() with the same pattern and subject + arguments. The data in the match_data block (return code, offset vec- + tor) is then used for the first substitution instead of calling + pcre2_match() from within pcre2_substitute(). This allows an applica- + tion to check for a match before choosing to substitute, without having + to repeat the match. - The contents of the externally supplied match data block are not - changed when PCRE2_SUBSTITUTE_MATCHED is set. If PCRE2_SUBSTI- - TUTE_GLOBAL is also set, pcre2_match() is called after the first sub- - stitution to check for further matches, but this is done using an in- - ternally obtained match data block, thus always leaving the external + The contents of the externally supplied match data block are not + changed when PCRE2_SUBSTITUTE_MATCHED is set. If PCRE2_SUBSTI- + TUTE_GLOBAL is also set, pcre2_match() is called after the first sub- + stitution to check for further matches, but this is done using an in- + ternally obtained match data block, thus always leaving the external block unchanged. - The code argument is not used for matching before the first substitu- - tion when PCRE2_SUBSTITUTE_MATCHED is set, but it must be provided, - even when PCRE2_SUBSTITUTE_GLOBAL is not set, because it contains in- + The code argument is not used for matching before the first substitu- + tion when PCRE2_SUBSTITUTE_MATCHED is set, but it must be provided, + even when PCRE2_SUBSTITUTE_GLOBAL is not set, because it contains in- formation such as the UTF setting and the number of capturing parenthe- ses in the pattern. - The default action of pcre2_substitute() is to return a copy of the + The default action of pcre2_substitute() is to return a copy of the subject string with matched substrings replaced. However, if PCRE2_SUB- - STITUTE_REPLACEMENT_ONLY is set, only the replacement substrings are + STITUTE_REPLACEMENT_ONLY is set, only the replacement substrings are returned. In the global case, multiple replacements are concatenated in - the output buffer. Substitution callouts (see below) can be used to + the output buffer. Substitution callouts (see below) can be used to separate them if necessary. - The outlengthptr argument of pcre2_substitute() must point to a vari- - able that contains the length, in code units, of the output buffer. If - the function is successful, the value is updated to contain the length - in code units of the new string, excluding the trailing zero that is + The outlengthptr argument of pcre2_substitute() must point to a vari- + able that contains the length, in code units, of the output buffer. If + the function is successful, the value is updated to contain the length + in code units of the new string, excluding the trailing zero that is automatically added. - If the function is not successful, the value set via outlengthptr de- - pends on the type of error. For syntax errors in the replacement + If the function is not successful, the value set via outlengthptr de- + pends on the type of error. For syntax errors in the replacement string, the value is the offset in the replacement string where the er- - ror was detected. For other errors, the value is PCRE2_UNSET by de- + ror was detected. For other errors, the value is PCRE2_UNSET by de- fault. This includes the case of the output buffer being too small, un- less PCRE2_SUBSTITUTE_OVERFLOW_LENGTH is set. - PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when the output + PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when the output buffer is too small. The default action is to return PCRE2_ERROR_NOMEM- - ORY immediately. If this option is set, however, pcre2_substitute() + ORY immediately. If this option is set, however, pcre2_substitute() continues to go through the motions of matching and substituting (with- - out, of course, writing anything) in order to compute the size of buf- - fer that is needed. This value is passed back via the outlengthptr - variable, with the result of the function still being PCRE2_ER- + out, of course, writing anything) in order to compute the size of buf- + fer that is needed. This value is passed back via the outlengthptr + variable, with the result of the function still being PCRE2_ER- ROR_NOMEMORY. - Passing a buffer size of zero is a permitted way of finding out how - much memory is needed for given substitution. However, this does mean + Passing a buffer size of zero is a permitted way of finding out how + much memory is needed for given substitution. However, this does mean that the entire operation is carried out twice. Depending on the appli- - cation, it may be more efficient to allocate a large buffer and free - the excess afterwards, instead of using PCRE2_SUBSTITUTE_OVER- + cation, it may be more efficient to allocate a large buffer and free + the excess afterwards, instead of using PCRE2_SUBSTITUTE_OVER- FLOW_LENGTH. - The replacement string, which is interpreted as a UTF string in UTF - mode, is checked for UTF validity unless PCRE2_NO_UTF_CHECK is set. An + The replacement string, which is interpreted as a UTF string in UTF + mode, is checked for UTF validity unless PCRE2_NO_UTF_CHECK is set. An invalid UTF replacement string causes an immediate return with the rel- evant UTF error code. - If PCRE2_SUBSTITUTE_LITERAL is set, the replacement string is not in- + If PCRE2_SUBSTITUTE_LITERAL is set, the replacement string is not in- terpreted in any way. By default, however, a dollar character is an es- - cape character that can specify the insertion of characters from cap- - ture groups and names from (*MARK) or other control verbs in the pat- + cape character that can specify the insertion of characters from cap- + ture groups and names from (*MARK) or other control verbs in the pat- tern. The following forms are always recognized: $$ insert a dollar character $ or ${} insert the contents of group $*MARK or ${*MARK} insert a control verb name - 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 + 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+=". - $*MARK inserts the name from the last encountered backtracking control - verb on the matching path that has a name. (*MARK) must always include - a name, but the other verbs need not. For example, in the case of + $*MARK inserts the name from the last encountered backtracking control + verb on the matching path that has a name. (*MARK) must always include + a name, but the other verbs need not. For example, in the case of (*MARK:A)(*PRUNE) the name inserted is "A", but for (*MARK:A)(*PRUNE:B) - the relevant name is "B". This facility can be used to perform simple + the relevant name is "B". This facility can be used to perform simple simultaneous substitutions, as this pcre2test example shows: /(*MARK:pear)apple|(*MARK:orange)lemon/g,replace=${*MARK} @@ -3411,15 +3412,15 @@ CREATING A NEW STRING WITH SUBSTITUTIONS 2: pear orange PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject - string, replacing every matching substring. If this option is not set, - only the first matching substring is replaced. The search for matches - takes place in the original subject string (that is, previous replace- - ments do not affect it). Iteration is implemented by advancing the - startoffset value for each search, which is always passed the entire + string, replacing every matching substring. If this option is not set, + only the first matching substring is replaced. The search for matches + takes place in the original subject string (that is, previous replace- + ments do not affect it). Iteration is implemented by advancing the + startoffset value for each search, which is always passed the entire subject string. If an offset limit is set in the match context, search- ing stops when that limit is reached. - You can restrict the effect of a global substitution to a portion of + You can restrict the effect of a global substitution to a portion of the subject string by setting either or both of startoffset and an off- set limit. Here is a pcre2test example: @@ -3427,73 +3428,73 @@ CREATING A NEW STRING WITH SUBSTITUTIONS ABC ABC ABC ABC\=offset=3,offset_limit=12 2: ABC A!C A!C ABC - When continuing with global substitutions after matching a substring + When continuing with global substitutions after matching a substring with zero length, an attempt to find a non-empty match at the same off- set is performed. If this is not successful, the offset is advanced by one character except when CRLF is a valid newline sequence and the next - two characters are CR, LF. In this case, the offset is advanced by two + two characters are CR, LF. In this case, the offset is advanced by two characters. PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capture groups that do not appear in the pattern to be treated as unset groups. This option - should be used with care, because it means that a typo in a group name + should be used with care, because it means that a typo in a group name or number no longer causes the PCRE2_ERROR_NOSUBSTRING error. PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capture groups (including un- - known groups when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) to be treated - as empty strings when inserted as described above. If this option is + known groups when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) to be treated + as empty strings when inserted as described above. If this option is not set, an attempt to insert an unset group causes the PCRE2_ERROR_UN- - SET error. This option does not influence the extended substitution + SET error. This option does not influence the extended substitution syntax described below. - PCRE2_SUBSTITUTE_EXTENDED causes extra processing to be applied to the - replacement string. Without this option, only the dollar character is - special, and only the group insertion forms listed above are valid. + PCRE2_SUBSTITUTE_EXTENDED causes extra processing to be applied to the + replacement string. Without this option, only the dollar character is + special, and only the group insertion forms listed above are valid. When PCRE2_SUBSTITUTE_EXTENDED is set, two things change: - Firstly, backslash in a replacement string is interpreted as an escape + Firstly, backslash in a replacement string is interpreted as an escape character. The usual forms such as \n or \x{ddd} can be used to specify - particular character codes, and backslash followed by any non-alphanu- - meric character quotes that character. Extended quoting can be coded + particular character codes, and backslash followed by any non-alphanu- + meric character quotes that character. Extended quoting can be coded using \Q...\E, exactly as in pattern strings. - There are also four escape sequences for forcing the case of inserted - letters. The insertion mechanism has three states: no case forcing, + There are also four escape sequences for forcing the case of inserted + letters. The insertion mechanism has three states: no case forcing, force upper case, and force lower case. The escape sequences change the current state: \U and \L change to upper or lower case forcing, respec- - tively, and \E (when not terminating a \Q quoted sequence) reverts to - no case forcing. The sequences \u and \l force the next character (if - it is a letter) to upper or lower case, respectively, and then the + tively, and \E (when not terminating a \Q quoted sequence) reverts to + no case forcing. The sequences \u and \l force the next character (if + it is a letter) to upper or lower case, respectively, and then the state automatically reverts to no case forcing. Case forcing applies to - all inserted characters, including those from capture groups and let- - ters within \Q...\E quoted sequences. If either PCRE2_UTF or PCRE2_UCP - was set when the pattern was compiled, Unicode properties are used for + all inserted characters, including those from capture groups and let- + ters within \Q...\E quoted sequences. If either PCRE2_UTF or PCRE2_UCP + was set when the pattern was compiled, Unicode properties are used for case forcing characters whose code points are greater than 127. Note that case forcing sequences such as \U...\E do not nest. For exam- - ple, the result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc"; the final - \E has no effect. Note also that the PCRE2_ALT_BSUX and PCRE2_EX- + ple, the result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc"; the final + \E has no effect. Note also that the PCRE2_ALT_BSUX and PCRE2_EX- TRA_ALT_BSUX options do not apply to replacement strings. - The second effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more - flexibility to capture group substitution. The syntax is similar to + The second effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more + flexibility to capture group substitution. The syntax is similar to that used by Bash: ${:-} ${:+:} - As before, may be a group number or a name. The first form speci- - fies a default value. If group is set, its value is inserted; if - not, is expanded and the result inserted. The second form - specifies strings that are expanded and inserted when group is set - or unset, respectively. The first form is just a convenient shorthand + As before, may be a group number or a name. The first form speci- + fies a default value. If group is set, its value is inserted; if + not, is expanded and the result inserted. The second form + specifies strings that are expanded and inserted when group is set + or unset, respectively. The first form is just a convenient shorthand for ${:+${}:} - Backslash can be used to escape colons and closing curly brackets in - the replacement strings. A change of the case forcing state within a - replacement string remains in force afterwards, as shown in this + Backslash can be used to escape colons and closing curly brackets in + the replacement strings. A change of the case forcing state within a + replacement string remains in force afterwards, as shown in this pcre2test example: /(some)?(body)/substitute_extended,replace=${1:+\U:\L}HeLLo @@ -3502,8 +3503,8 @@ CREATING A NEW STRING WITH SUBSTITUTIONS somebody 1: HELLO - The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended - substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause un- + The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended + substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause un- known groups in the extended syntax forms to be treated as unset. If PCRE2_SUBSTITUTE_LITERAL is set, PCRE2_SUBSTITUTE_UNKNOWN_UNSET, @@ -3512,39 +3513,39 @@ CREATING A NEW STRING WITH SUBSTITUTIONS Substitution errors - In the event of an error, pcre2_substitute() returns a negative error - code. Except for PCRE2_ERROR_NOMATCH (which is never returned), errors + In the event of an error, pcre2_substitute() returns a negative error + code. Except for PCRE2_ERROR_NOMATCH (which is never returned), errors from pcre2_match() are passed straight back. PCRE2_ERROR_NOSUBSTRING is returned for a non-existent substring inser- tion, unless PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set. PCRE2_ERROR_UNSET is returned for an unset substring insertion (includ- - ing an unknown substring when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) - when the simple (non-extended) syntax is used and PCRE2_SUBSTITUTE_UN- + ing an unknown substring when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) + when the simple (non-extended) syntax is used and PCRE2_SUBSTITUTE_UN- SET_EMPTY is not set. - PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big + PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough. If the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set, the size - of buffer that is needed is returned via outlengthptr. Note that this + of buffer that is needed is returned via outlengthptr. Note that this does not happen by default. PCRE2_ERROR_NULL is returned if PCRE2_SUBSTITUTE_MATCHED is set but the - match_data argument is NULL or if the subject or replacement arguments - are NULL. For backward compatibility reasons an exception is made for + match_data argument is NULL or if the subject or replacement arguments + are NULL. For backward compatibility reasons an exception is made for the replacement argument if the rlength argument is also 0. - PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in - the replacement string, with more particular errors being PCRE2_ER- + PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in + the replacement string, with more particular errors being PCRE2_ER- ROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REPMISSINGBRACE - (closing curly bracket not found), PCRE2_ERROR_BADSUBSTITUTION (syntax - error in extended group substitution), and PCRE2_ERROR_BADSUBSPATTERN + (closing curly bracket not found), PCRE2_ERROR_BADSUBSTITUTION (syntax + error in extended group substitution), and PCRE2_ERROR_BADSUBSPATTERN (the pattern match ended before it started or the match started earlier - than the current position in the subject, which can happen if \K is + than the current position in the subject, which can happen if \K is used in an assertion). As for all PCRE2 errors, a text message that describes the error can be - obtained by calling the pcre2_get_error_message() function (see "Ob- + obtained by calling the pcre2_get_error_message() function (see "Ob- taining a textual error message" above). Substitution callouts @@ -3553,15 +3554,15 @@ CREATING A NEW STRING WITH SUBSTITUTIONS int (*callout_function)(pcre2_substitute_callout_block *, void *), void *callout_data); - The pcre2_set_substitution_callout() function can be used to specify a - callout function for pcre2_substitute(). This information is passed in + The pcre2_set_substitution_callout() function can be used to specify a + callout function for pcre2_substitute(). This information is passed in a match context. The callout function is called after each substitution has been processed, but it can cause the replacement not to happen. The - callout function is not called for simulated substitutions that happen + callout function is not called for simulated substitutions that happen as a result of the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option. The first argument of the callout function is a pointer to a substitute - callout block structure, which contains the following fields, not nec- + callout block structure, which contains the following fields, not nec- essarily in this order: uint32_t version; @@ -3572,34 +3573,34 @@ CREATING A NEW STRING WITH SUBSTITUTIONS uint32_t oveccount; PCRE2_SIZE output_offsets[2]; - The version field contains the version number of the block format. The - current version is 0. The version number will increase in future if - more fields are added, but the intention is never to remove any of the + The version field contains the version number of the block format. The + current version is 0. The version number will increase in future if + more fields are added, but the intention is never to remove any of the existing fields. The subscount field is the number of the current match. It is 1 for the first callout, 2 for the second, and so on. The input and output point- ers are copies of the values passed to pcre2_substitute(). - The ovector field points to the ovector, which contains the result of + The ovector field points to the ovector, which contains the result of the most recent match. The oveccount field contains the number of pairs that are set in the ovector, and is always greater than zero. - The output_offsets vector contains the offsets of the replacement in - the output string. This has already been processed for dollar and (if + The output_offsets vector contains the offsets of the replacement in + the output string. This has already been processed for dollar and (if requested) backslash substitutions as described above. - The second argument of the callout function is the value passed as - callout_data when the function was registered. The value returned by + The second argument of the callout function is the value passed as + callout_data when the function was registered. The value returned by the callout function is interpreted as follows: - If the value is zero, the replacement is accepted, and, if PCRE2_SUB- - STITUTE_GLOBAL is set, processing continues with a search for the next - match. If the value is not zero, the current replacement is not ac- - cepted. If the value is greater than zero, processing continues when - PCRE2_SUBSTITUTE_GLOBAL is set. Otherwise (the value is less than zero - or PCRE2_SUBSTITUTE_GLOBAL is not set), the the rest of the input is - copied to the output and the call to pcre2_substitute() exits, return- + If the value is zero, the replacement is accepted, and, if PCRE2_SUB- + STITUTE_GLOBAL is set, processing continues with a search for the next + match. If the value is not zero, the current replacement is not ac- + cepted. If the value is greater than zero, processing continues when + PCRE2_SUBSTITUTE_GLOBAL is set. Otherwise (the value is less than zero + or PCRE2_SUBSTITUTE_GLOBAL is not set), the the rest of the input is + copied to the output and the call to pcre2_substitute() exits, return- ing the number of matches so far. @@ -3608,56 +3609,56 @@ DUPLICATE CAPTURE GROUP 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 - capture groups are not required to be unique. Duplicate names are al- - ways allowed for groups with the same number, created by using the (?| + When a pattern is compiled with the PCRE2_DUPNAMES option, names for + capture groups are not required to be unique. Duplicate names are al- + ways allowed for groups with the same number, created by using the (?| feature. Indeed, if such groups are named, they are required to use the same names. - Normally, patterns that use duplicate names are such that in any one - match, only one of each set of identically-named groups participates. + Normally, patterns that use duplicate names are such that in any one + match, only one of each set of identically-named groups participates. An example is shown in the pcre2pattern documentation. - When duplicates are present, pcre2_substring_copy_byname() and - pcre2_substring_get_byname() return the first substring corresponding - to the given name that is set. Only if none are set is PCRE2_ERROR_UN- - SET is returned. The pcre2_substring_number_from_name() function re- - turns the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are duplicate + 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_UN- + SET is returned. The pcre2_substring_number_from_name() function re- + turns the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are duplicate names. - If you want to get full details of all captured substrings for a given - name, you must use the pcre2_substring_nametable_scan() function. The - first argument is the compiled pattern, and the second is the name. If - the third and fourth arguments are NULL, the function returns a group + If you want to get full details of all captured substrings for a given + name, you must use the pcre2_substring_nametable_scan() function. The + first argument is the compiled pattern, and the second is the name. If + the third and fourth arguments are NULL, the function returns a group number for a unique name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise. When the third and fourth arguments are not NULL, they must be pointers - to variables that are updated by the function. After it has run, they + to variables that are updated by the function. After it has run, they point to the first and last entries in the name-to-number table for the - given name, and the function returns the length of each entry in code - units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are + given name, and the function returns the length of each entry in code + units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name. The format of the name table is described above in the section entitled - Information about a pattern. Given all the relevant entries for the - name, you can extract each of their numbers, and hence the captured + Information about a pattern. Given all the relevant entries for the + name, you can extract each of their numbers, and hence the captured data. FINDING ALL POSSIBLE MATCHES AT ONE POSITION - The traditional matching function uses a similar algorithm to Perl, - which stops when it finds the first match at a given point in the sub- + The traditional matching function uses a similar algorithm to Perl, + which stops when it finds the first match at a given point in the sub- ject. If you want to find all possible matches, or the longest possible - match at a given position, consider using the alternative matching - function (see below) instead. If you cannot use the alternative func- + match at a given position, consider using the alternative matching + function (see below) instead. If you cannot use the alternative func- tion, you can kludge it up by making use of the callout facility, which is described in the pcre2callout documentation. What you have to do is to insert a callout right at the end of the pat- - tern. When your callout function is called, extract and save the cur- - rent matched substring. Then return 1, which forces pcre2_match() to - backtrack and try other alternatives. Ultimately, when it runs out of + tern. When your callout function is called, extract and save the cur- + rent matched substring. Then return 1, which forces pcre2_match() to + backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre2_match() will yield PCRE2_ERROR_NOMATCH. @@ -3669,27 +3670,27 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION pcre2_match_context *mcontext, int *workspace, PCRE2_SIZE wscount); - The function pcre2_dfa_match() is called to match a subject string - against a compiled pattern, using a matching algorithm that scans the + The function pcre2_dfa_match() is called to match a subject string + against a compiled pattern, using a matching algorithm that scans the subject string just once (not counting lookaround assertions), and does - not backtrack (except when processing lookaround assertions). This has - different characteristics to the normal algorithm, and is not compati- - ble with Perl. Some of the features of PCRE2 patterns are not sup- + not backtrack (except when processing lookaround assertions). This has + different characteristics to the normal algorithm, and is not compati- + ble with Perl. Some of the features of PCRE2 patterns are not sup- ported. Nevertheless, there are times when this kind of matching can be - useful. For a discussion of the two matching algorithms, and a list of + useful. For a discussion of the two matching algorithms, and a list of features that pcre2_dfa_match() does not support, see the pcre2matching documentation. - The arguments for the pcre2_dfa_match() function are the same as for + The arguments for the pcre2_dfa_match() function are the same as for pcre2_match(), plus two extras. The ovector within the match data block is used in a different way, and this is described below. The other com- - mon arguments are used in the same way as for pcre2_match(), so their + mon arguments are used in the same way as for pcre2_match(), so their description is not repeated here. - The two additional arguments provide workspace for the function. The - workspace vector should contain at least 20 elements. It is used for + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for keeping track of multiple paths through the pattern tree. More - workspace is needed for patterns and subjects where there are a lot of + workspace is needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre2_dfa_match(): @@ -3709,45 +3710,45 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION Option bits for pcre2_dfa_match() - The unused bits of the options argument for pcre2_dfa_match() must be - zero. The only bits that may be set are PCRE2_ANCHORED, - PCRE2_COPY_MATCHED_SUBJECT, PCRE2_ENDANCHORED, PCRE2_NOTBOL, PCRE2_NO- + The unused bits of the options argument for pcre2_dfa_match() must be + zero. The only bits that may be set are PCRE2_ANCHORED, + PCRE2_COPY_MATCHED_SUBJECT, PCRE2_ENDANCHORED, PCRE2_NOTBOL, PCRE2_NO- TEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, - PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, PCRE2_DFA_SHORTEST, and - PCRE2_DFA_RESTART. All but the last four of these are exactly the same + PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, PCRE2_DFA_SHORTEST, and + PCRE2_DFA_RESTART. All but the last four of these are exactly the same as for pcre2_match(), so their description is not repeated here. PCRE2_PARTIAL_HARD PCRE2_PARTIAL_SOFT - These have the same general effect as they do for pcre2_match(), but - the details are slightly different. When PCRE2_PARTIAL_HARD is set for - pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the + These have the same general effect as they do for pcre2_match(), but + the details are slightly different. When PCRE2_PARTIAL_HARD is set for + pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the subject is reached and there is still at least one matching possibility that requires additional characters. This happens even if some complete - matches have already been found. When PCRE2_PARTIAL_SOFT is set, the - return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL - if the end of the subject is reached, there have been no complete + matches have already been found. When PCRE2_PARTIAL_SOFT is set, the + return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL + if the end of the subject is reached, there have been no complete matches, but there is still at least one matching possibility. The por- - tion of the string that was inspected when the longest partial match + tion of the string that was inspected when the longest partial match was found is set as the first matching string in both cases. There is a - more detailed discussion of partial and multi-segment matching, with + more detailed discussion of partial and multi-segment matching, with examples, in the pcre2partial documentation. PCRE2_DFA_SHORTEST - Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to + Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to stop as soon as it has found one match. Because of the way the alterna- - tive algorithm works, this is necessarily the shortest possible match + tive algorithm works, this is necessarily the shortest possible match at the first possible matching point in the subject string. PCRE2_DFA_RESTART - When pcre2_dfa_match() returns a partial match, it is possible to call + When pcre2_dfa_match() returns a partial match, it is possible to call it again, with additional subject characters, and have it continue with the same match. The PCRE2_DFA_RESTART option requests this action; when - it is set, the workspace and wscount options must reference the same - vector as before because data about the match so far is left in them + it is set, the workspace and wscount options must reference the same + vector as before because data about the match so far is left in them after a partial match. There is more discussion of this facility in the pcre2partial documentation. @@ -3755,8 +3756,8 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION When pcre2_dfa_match() succeeds, it may have matched more than one sub- string in the subject. Note, however, that all the matches from one run - of the function start at the same point in the subject. The shorter - matches are all initial substrings of the longer matches. For example, + of the function start at the same point in the subject. The shorter + matches are all initial substrings of the longer matches. For example, if the pattern <.*> @@ -3771,80 +3772,80 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The offsets of the sub- - strings are returned in the ovector, and can be extracted by number in - the same way as for pcre2_match(), but the numbers bear no relation to - any capture groups that may exist in the pattern, because DFA matching + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The offsets of the sub- + strings are returned in the ovector, and can be extracted by number in + the same way as for pcre2_match(), but the numbers bear no relation to + any capture groups that may exist in the pattern, because DFA matching does not support capturing. - Calls to the convenience functions that extract substrings by name re- + Calls to the convenience functions that extract substrings by name re- turn the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used af- - ter a DFA match. The convenience functions that extract substrings by + ter a DFA match. The convenience functions that extract substrings by number never return PCRE2_ERROR_NOSUBSTRING. - The matched strings are stored in the ovector in reverse order of - length; that is, the longest matching string is first. If there were - too many matches to fit into the ovector, the yield of the function is + The matched strings are stored in the ovector in reverse order of + length; that is, the longest matching string is first. If there were + too many matches to fit into the ovector, the yield of the function is zero, and the vector is filled with the longest matches. - NOTE: PCRE2's "auto-possessification" optimization usually applies to - character repeats at the end of a pattern (as well as internally). For - example, the pattern "a\d+" is compiled as if it were "a\d++". For DFA - matching, this means that only one possible match is found. If you re- + NOTE: PCRE2's "auto-possessification" optimization usually applies to + character repeats at the end of a pattern (as well as internally). For + example, the pattern "a\d+" is compiled as if it were "a\d++". For DFA + matching, this means that only one possible match is found. If you re- ally do want multiple matches in such cases, either use an ungreedy re- - peat such as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when com- + peat such as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when com- piling. Error returns from pcre2_dfa_match() The pcre2_dfa_match() function returns a negative number when it fails. - Many of the errors are the same as for pcre2_match(), as described + Many of the errors are the same as for pcre2_match(), as described above. There are in addition the following errors that are specific to pcre2_dfa_match(): PCRE2_ERROR_DFA_UITEM - This return is given if pcre2_dfa_match() encounters an item in the - pattern that it does not support, for instance, the use of \C in a UTF + This return is given if pcre2_dfa_match() encounters an item in the + pattern that it does not support, for instance, the use of \C in a UTF mode or a backreference. PCRE2_ERROR_DFA_UCOND - This return is given if pcre2_dfa_match() encounters a condition item + This return is given if pcre2_dfa_match() encounters a condition item that uses a backreference for the condition, or a test for recursion in a specific capture group. These are not supported. PCRE2_ERROR_DFA_UINVALID_UTF - This return is given if pcre2_dfa_match() is called for a pattern that - was compiled with PCRE2_MATCH_INVALID_UTF. This is not supported for + This return is given if pcre2_dfa_match() is called for a pattern that + was compiled with PCRE2_MATCH_INVALID_UTF. This is not supported for DFA matching. PCRE2_ERROR_DFA_WSSIZE - This return is given if pcre2_dfa_match() runs out of space in the + This return is given if pcre2_dfa_match() runs out of space in the workspace vector. PCRE2_ERROR_DFA_RECURSE When a recursion or subroutine call is processed, the matching function - calls itself recursively, using private memory for the ovector and - workspace. This error is given if the internal ovector is not large - enough. This should be extremely rare, as a vector of size 1000 is + calls itself recursively, using private memory for the ovector and + workspace. This error is given if the internal ovector is not large + enough. This should be extremely rare, as a vector of size 1000 is used. PCRE2_ERROR_DFA_BADRESTART - When pcre2_dfa_match() is called with the PCRE2_DFA_RESTART option, - some plausibility checks are made on the contents of the workspace, - which should contain data about the previous partial match. If any of + When pcre2_dfa_match() is called with the PCRE2_DFA_RESTART option, + some plausibility checks are made on the contents of the workspace, + which should contain data about the previous partial match. If any of these checks fail, this error is given. SEE ALSO - pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), + pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), pcre2partial(3), pcre2posix(3), pcre2sample(3), pcre2unicode(3). @@ -3857,7 +3858,7 @@ AUTHOR REVISION - Last updated: 08 December 2021 + Last updated: 14 December 2021 Copyright (c) 1997-2021 University of Cambridge. ------------------------------------------------------------------------------ diff --git a/doc/pcre2api.3 b/doc/pcre2api.3 index 47d4d07..18d18bf 100644 --- a/doc/pcre2api.3 +++ b/doc/pcre2api.3 @@ -1,4 +1,4 @@ -.TH PCRE2API 3 "08 December 2021" "PCRE2 10.40" +.TH PCRE2API 3 "14 December 2021" "PCRE2 10.40" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .sp @@ -3453,12 +3453,12 @@ block may or may not have been changed. As well as the usual options for \fBpcre2_match()\fP, a number of additional options can be set in the \fIoptions\fP argument of \fBpcre2_substitute()\fP. One such option is PCRE2_SUBSTITUTE_MATCHED. When this is set, an external -\fImatch_data\fP block must be provided, and it must have been used for an -external call to \fBpcre2_match()\fP. The data in the \fImatch_data\fP block -(return code, offset vector) is used for the first substitution instead of -calling \fBpcre2_match()\fP from within \fBpcre2_substitute()\fP. This allows -an application to check for a match before choosing to substitute, without -having to repeat the match. +\fImatch_data\fP block must be provided, and it must have already been used for +an external call to \fBpcre2_match()\fP with the same pattern and subject +arguments. The data in the \fImatch_data\fP block (return code, offset vector) +is then used for the first substitution instead of calling \fBpcre2_match()\fP +from within \fBpcre2_substitute()\fP. This allows an application to check for a +match before choosing to substitute, without having to repeat the match. .P The contents of the externally supplied match data block are not changed when PCRE2_SUBSTITUTE_MATCHED is set. If PCRE2_SUBSTITUTE_GLOBAL is also set, @@ -4025,6 +4025,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 08 December 2021 +Last updated: 14 December 2021 Copyright (c) 1997-2021 University of Cambridge. .fi diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c index ea02910..8e79e09 100644 --- a/src/pcre2_compile.c +++ b/src/pcre2_compile.c @@ -124,7 +124,7 @@ static unsigned int static int compile_regex(uint32_t, PCRE2_UCHAR **, uint32_t **, int *, uint32_t, - uint32_t *, int32_t *, uint32_t *, int32_t *, branch_chain *, + uint32_t *, uint32_t *, uint32_t *, uint32_t *, branch_chain *, compile_block *, PCRE2_SIZE *); static int @@ -385,13 +385,15 @@ compiler is clever with identical subexpressions. */ #define SETBIT(a,b) a[(b)/8] = (uint8_t)(a[(b)/8] | (1u << ((b)&7))) -/* Private flags added to firstcu and reqcu. */ +/* Values and flags for the unsigned xxcuflags variables that accompany xxcu +variables, which are concerned with first and required code units. A value +greater than or equal to REQ_NONE means "no code unit set"; otherwise the +matching xxcu variable is set, and the low valued bits are relevant. */ -#define REQ_CASELESS (1u << 0) /* Indicates caselessness */ -#define REQ_VARY (1u << 1) /* reqcu followed non-literal item */ -/* Negative values for the firstcu and reqcu flags */ -#define REQ_UNSET (-2) /* Not yet found anything */ -#define REQ_NONE (-1) /* Found not fixed char */ +#define REQ_UNSET 0xffffffffu /* Not yet found anything */ +#define REQ_NONE 0xfffffffeu /* Found not fixed character */ +#define REQ_CASELESS 0x00000001u /* Code unit in xxcu is caseless */ +#define REQ_VARY 0x00000002u /* Code unit is followed by non-literal */ /* These flags are used in the groupinfo vector. */ @@ -2139,7 +2141,7 @@ if (c == CHAR_LEFT_CURLY_BRACKET) while (top != bot) { - size_t mid = ((top + bot)/2) & (-2); + size_t mid = ((top + bot)/2) & (size_t)(~2+1); /* Mask off bottom bit */ int cf = PRIV(strcmp_c8)(name, prop_synonyms[mid]); if (cf == 0) { @@ -5343,9 +5345,9 @@ Arguments: pptrptr points to the current parsed pattern pointer errorcodeptr points to error code variable firstcuptr place to put the first required code unit - firstcuflagsptr place to put the first code unit flags, or a negative number + firstcuflagsptr place to put the first code unit flags reqcuptr place to put the last required code unit - reqcuflagsptr place to put the last required code unit flags, or a negative number + reqcuflagsptr place to put the last required code unit flags bcptr points to current branch chain cb contains pointers to tables etc. lengthptr NULL during the real compile phase @@ -5358,8 +5360,8 @@ Returns: 0 There's been an error, *errorcodeptr is non-zero static int compile_branch(uint32_t *optionsptr, PCRE2_UCHAR **codeptr, uint32_t **pptrptr, - int *errorcodeptr, uint32_t *firstcuptr, int32_t *firstcuflagsptr, - uint32_t *reqcuptr, int32_t *reqcuflagsptr, branch_chain *bcptr, + int *errorcodeptr, uint32_t *firstcuptr, uint32_t *firstcuflagsptr, + uint32_t *reqcuptr, uint32_t *reqcuflagsptr, branch_chain *bcptr, compile_block *cb, PCRE2_SIZE *lengthptr) { int bravalue = 0; @@ -5374,9 +5376,9 @@ uint32_t zeroreqcu, zerofirstcu; uint32_t escape; uint32_t *pptr = *pptrptr; uint32_t meta, meta_arg; -int32_t firstcuflags, reqcuflags; -int32_t zeroreqcuflags, zerofirstcuflags; -int32_t req_caseopt, reqvary, tempreqvary; +uint32_t firstcuflags, reqcuflags; +uint32_t zeroreqcuflags, zerofirstcuflags; +uint32_t req_caseopt, reqvary, tempreqvary; PCRE2_SIZE offset = 0; PCRE2_SIZE length_prevgroup = 0; PCRE2_UCHAR *code = *codeptr; @@ -5432,13 +5434,13 @@ item types that can be repeated set these backoff variables appropriately. */ firstcu = reqcu = zerofirstcu = zeroreqcu = 0; firstcuflags = reqcuflags = zerofirstcuflags = zeroreqcuflags = REQ_UNSET; -/* The variable req_caseopt contains either the REQ_CASELESS value or zero, +/* The variable req_caseopt contains either the REQ_CASELESS bit or zero, according to the current setting of the caseless flag. The REQ_CASELESS value leaves the lower 28 bit empty. It is added into the firstcu or reqcu variables to record the case status of the value. This is used only for ASCII characters. */ -req_caseopt = ((options & PCRE2_CASELESS) != 0)? REQ_CASELESS:0; +req_caseopt = ((options & PCRE2_CASELESS) != 0)? REQ_CASELESS : 0; /* Switch on next META item until the end of the branch */ @@ -5453,13 +5455,12 @@ for (;; pptr++) BOOL possessive_quantifier; BOOL note_group_empty; int class_has_8bitchar; - int i; uint32_t mclength; uint32_t skipunits; uint32_t subreqcu, subfirstcu; uint32_t groupnumber; uint32_t verbarglen, verbculen; - int32_t subreqcuflags, subfirstcuflags; /* Must be signed */ + uint32_t subreqcuflags, subfirstcuflags; open_capitem *oc; PCRE2_UCHAR mcbuffer[8]; @@ -5828,9 +5829,9 @@ for (;; pptr++) if (taboffset >= 0) { if (tabopt >= 0) - for (i = 0; i < 32; i++) pbits[i] |= cbits[(int)i + taboffset]; + for (int i = 0; i < 32; i++) pbits[i] |= cbits[(int)i + taboffset]; else - for (i = 0; i < 32; i++) pbits[i] &= ~cbits[(int)i + taboffset]; + for (int i = 0; i < 32; i++) pbits[i] &= ~cbits[(int)i + taboffset]; } /* Now see if we need to remove any special characters. An option @@ -5844,9 +5845,9 @@ for (;; pptr++) being built and we are done. */ if (local_negate) - for (i = 0; i < 32; i++) classbits[i] |= ~pbits[i]; + for (int i = 0; i < 32; i++) classbits[i] |= (uint8_t)(~pbits[i]); else - for (i = 0; i < 32; i++) classbits[i] |= pbits[i]; + for (int i = 0; i < 32; i++) classbits[i] |= pbits[i]; /* Every class contains at least one < 256 character. */ @@ -5885,21 +5886,23 @@ for (;; pptr++) switch(escape) { case ESC_d: - for (i = 0; i < 32; i++) classbits[i] |= cbits[i+cbit_digit]; + for (int i = 0; i < 32; i++) classbits[i] |= cbits[i+cbit_digit]; break; case ESC_D: should_flip_negation = TRUE; - for (i = 0; i < 32; i++) classbits[i] |= ~cbits[i+cbit_digit]; + for (int i = 0; i < 32; i++) + classbits[i] |= (uint8_t)(~cbits[i+cbit_digit]); break; case ESC_w: - for (i = 0; i < 32; i++) classbits[i] |= cbits[i+cbit_word]; + for (int i = 0; i < 32; i++) classbits[i] |= cbits[i+cbit_word]; break; case ESC_W: should_flip_negation = TRUE; - for (i = 0; i < 32; i++) classbits[i] |= ~cbits[i+cbit_word]; + for (int i = 0; i < 32; i++) + classbits[i] |= (uint8_t)(~cbits[i+cbit_word]); break; /* Perl 5.004 onwards omitted VT from \s, but restored it at Perl @@ -5910,12 +5913,13 @@ for (;; pptr++) longer treat \s and \S specially. */ case ESC_s: - for (i = 0; i < 32; i++) classbits[i] |= cbits[i+cbit_space]; + for (int i = 0; i < 32; i++) classbits[i] |= cbits[i+cbit_space]; break; case ESC_S: should_flip_negation = TRUE; - for (i = 0; i < 32; i++) classbits[i] |= ~cbits[i+cbit_space]; + for (int i = 0; i < 32; i++) + classbits[i] |= (uint8_t)(~cbits[i+cbit_space]); break; /* When adding the horizontal or vertical space lists to a class, or @@ -6156,7 +6160,7 @@ for (;; pptr++) if (negate_class && !xclass_has_prop) { /* Using 255 ^ instead of ~ avoids clang sanitize warning. */ - for (i = 0; i < 32; i++) classbits[i] = 255 ^ classbits[i]; + for (int i = 0; i < 32; i++) classbits[i] = 255 ^ classbits[i]; } memcpy(code, classbits, 32); code = class_uchardata + (32 / sizeof(PCRE2_UCHAR)); @@ -6182,7 +6186,7 @@ for (;; pptr++) if (negate_class) { /* Using 255 ^ instead of ~ avoids clang sanitize warning. */ - for (i = 0; i < 32; i++) classbits[i] = 255 ^ classbits[i]; + for (int i = 0; i < 32; i++) classbits[i] = 255 ^ classbits[i]; } memcpy(code, classbits, 32); } @@ -6256,7 +6260,7 @@ for (;; pptr++) verbarglen = *(++pptr); verbculen = 0; tempcode = code++; - for (i = 0; i < (int)verbarglen; i++) + for (int i = 0; i < (int)verbarglen; i++) { meta = *(++pptr); #ifdef SUPPORT_UNICODE @@ -6305,6 +6309,7 @@ for (;; pptr++) bravalue = OP_COND; { int count, index; + unsigned int i; PCRE2_SPTR name; named_group *ng = cb->named_groups; uint32_t length = *(++pptr); @@ -6344,7 +6349,7 @@ for (;; pptr++) groupnumber = 0; if (meta == META_COND_RNUMBER) { - for (i = 1; i < (int)length; i++) + for (i = 1; i < length; i++) { groupnumber = groupnumber * 10 + name[i] - CHAR_0; if (groupnumber > MAX_GROUP_NUMBER) @@ -6666,7 +6671,7 @@ for (;; pptr++) if (firstcuflags == REQ_UNSET && subfirstcuflags != REQ_UNSET) { - if (subfirstcuflags >= 0) + if (subfirstcuflags < REQ_NONE) { firstcu = subfirstcu; firstcuflags = subfirstcuflags; @@ -6680,7 +6685,7 @@ for (;; pptr++) into reqcu if there wasn't one, using the vary flag that was in existence beforehand. */ - else if (subfirstcuflags >= 0 && subreqcuflags < 0) + else if (subfirstcuflags < REQ_NONE && subreqcuflags >= REQ_NONE) { subreqcu = subfirstcu; subreqcuflags = subfirstcuflags | tempreqvary; @@ -6689,7 +6694,7 @@ for (;; pptr++) /* If the subpattern set a required code unit (or set a first code unit that isn't really the first code unit - see above), set it. */ - if (subreqcuflags >= 0) + if (subreqcuflags < REQ_NONE) { reqcu = subreqcu; reqcuflags = subreqcuflags; @@ -6708,7 +6713,7 @@ for (;; pptr++) in that example, 'X' ends up set for both. */ else if ((bravalue == OP_ASSERT || bravalue == OP_ASSERT_NA) && - subreqcuflags >= 0 && subfirstcuflags >= 0) + subreqcuflags < REQ_NONE && subfirstcuflags < REQ_NONE) { reqcu = subreqcu; reqcuflags = subreqcuflags; @@ -6738,7 +6743,7 @@ for (;; pptr++) this name is duplicated. */ groupnumber = 0; - for (i = 0; i < cb->names_found; i++, ng++) + for (unsigned int i = 0; i < cb->names_found; i++, ng++) { if (length == ng->length && PRIV(strncmp)(name, ng->name, length) == 0) @@ -7092,7 +7097,7 @@ for (;; pptr++) *lengthptr += delta; } - else for (i = 0; i < replicate; i++) + else for (int i = 0; i < replicate; i++) { memcpy(code, previous, CU2BYTES(1 + LINK_SIZE)); previous = code; @@ -7268,12 +7273,12 @@ for (;; pptr++) else { - if (groupsetfirstcu && reqcuflags < 0) + if (groupsetfirstcu && reqcuflags >= REQ_NONE) { reqcu = firstcu; reqcuflags = firstcuflags; } - for (i = 1; (uint32_t)i < repeat_min; i++) + for (uint32_t i = 1; i < repeat_min; i++) { memcpy(code, previous, CU2BYTES(len)); code += len; @@ -7317,14 +7322,14 @@ for (;; pptr++) /* This is compiling for real */ - else for (i = repeat_max - 1; i >= 0; i--) + else for (uint32_t i = repeat_max; i >= 1; i--) { *code++ = OP_BRAZERO + repeat_type; /* All but the final copy start a new nesting, maintaining the chain of brackets outstanding. */ - if (i != 0) + if (i != 1) { int linkoffset; *code++ = OP_BRA; @@ -8043,9 +8048,9 @@ Arguments: errorcodeptr -> pointer to error code variable skipunits skip this many code units at start (for brackets and OP_COND) firstcuptr place to put the first required code unit - firstcuflagsptr place to put the first code unit flags, or a negative number + firstcuflagsptr place to put the first code unit flags reqcuptr place to put the last required code unit - reqcuflagsptr place to put the last required code unit flags, or a negative number + reqcuflagsptr place to put the last required code unit flags bcptr pointer to the chain of currently open branches cb points to the data block with tables pointers etc. lengthptr NULL during the real compile phase @@ -8059,7 +8064,7 @@ Returns: 0 There has been an error static int compile_regex(uint32_t options, PCRE2_UCHAR **codeptr, uint32_t **pptrptr, int *errorcodeptr, uint32_t skipunits, uint32_t *firstcuptr, - int32_t *firstcuflagsptr, uint32_t *reqcuptr,int32_t *reqcuflagsptr, + uint32_t *firstcuflagsptr, uint32_t *reqcuptr, uint32_t *reqcuflagsptr, branch_chain *bcptr, compile_block *cb, PCRE2_SIZE *lengthptr) { PCRE2_UCHAR *code = *codeptr; @@ -8072,9 +8077,9 @@ int okreturn = 1; uint32_t *pptr = *pptrptr; uint32_t firstcu, reqcu; uint32_t lookbehindlength; -int32_t firstcuflags, reqcuflags; +uint32_t firstcuflags, reqcuflags; uint32_t branchfirstcu, branchreqcu; -int32_t branchfirstcuflags, branchreqcuflags; +uint32_t branchfirstcuflags, branchreqcuflags; PCRE2_SIZE length; branch_chain bc; @@ -8193,9 +8198,9 @@ for (;;) if (firstcuflags != branchfirstcuflags || firstcu != branchfirstcu) { - if (firstcuflags >= 0) + if (firstcuflags < REQ_NONE) { - if (reqcuflags < 0) + if (reqcuflags >= REQ_NONE) { reqcu = firstcu; reqcuflags = firstcuflags; @@ -8207,8 +8212,8 @@ for (;;) /* If we (now or from before) have no firstcu, a firstcu from the branch becomes a reqcu if there isn't a branch reqcu. */ - if (firstcuflags < 0 && branchfirstcuflags >= 0 && - branchreqcuflags < 0) + if (firstcuflags >= REQ_NONE && branchfirstcuflags < REQ_NONE && + branchreqcuflags >= REQ_NONE) { branchreqcu = branchfirstcu; branchreqcuflags = branchfirstcuflags; @@ -8356,7 +8361,7 @@ Returns: TRUE or FALSE */ static BOOL -is_anchored(PCRE2_SPTR code, unsigned int bracket_map, compile_block *cb, +is_anchored(PCRE2_SPTR code, uint32_t bracket_map, compile_block *cb, int atomcount, BOOL inassert) { do { @@ -8379,7 +8384,7 @@ do { op == OP_SCBRA || op == OP_SCBRAPOS) { int n = GET2(scode, 1+LINK_SIZE); - int new_map = bracket_map | ((n < 32)? (1u << n) : 1); + uint32_t new_map = bracket_map | ((n < 32)? (1u << n) : 1); if (!is_anchored(scode, new_map, cb, atomcount, inassert)) return FALSE; } @@ -8739,15 +8744,15 @@ Returns: the fixed first code unit, or 0 with REQ_NONE in flags */ static uint32_t -find_firstassertedcu(PCRE2_SPTR code, int32_t *flags, uint32_t inassert) +find_firstassertedcu(PCRE2_SPTR code, uint32_t *flags, uint32_t inassert) { uint32_t c = 0; -int cflags = REQ_NONE; +uint32_t cflags = REQ_NONE; *flags = REQ_NONE; do { uint32_t d; - int dflags; + uint32_t dflags; int xl = (*code == OP_CBRA || *code == OP_SCBRA || *code == OP_CBRAPOS || *code == OP_SCBRAPOS)? IMM2_SIZE:0; PCRE2_SPTR scode = first_significant_code(code + 1+LINK_SIZE + xl, TRUE); @@ -8770,9 +8775,8 @@ do { case OP_SCRIPT_RUN: d = find_firstassertedcu(scode, &dflags, inassert + ((op == OP_ASSERT || op == OP_ASSERT_NA)?1:0)); - if (dflags < 0) - return 0; - if (cflags < 0) { c = d; cflags = dflags; } + if (dflags >= REQ_NONE) return 0; + if (cflags >= REQ_NONE) { c = d; cflags = dflags; } else if (c != d || cflags != dflags) return 0; break; @@ -8785,7 +8789,7 @@ do { case OP_MINPLUS: case OP_POSPLUS: if (inassert == 0) return 0; - if (cflags < 0) { c = scode[1]; cflags = 0; } + if (cflags >= REQ_NONE) { c = scode[1]; cflags = 0; } else if (c != scode[1]) return 0; break; @@ -8811,7 +8815,7 @@ do { #endif #endif - if (cflags < 0) { c = scode[1]; cflags = REQ_CASELESS; } + if (cflags >= REQ_NONE) { c = scode[1]; cflags = REQ_CASELESS; } else if (c != scode[1]) return 0; break; } @@ -9747,7 +9751,7 @@ PCRE2_SIZE re_blocksize; /* Size of memory block */ PCRE2_SIZE big32count = 0; /* 32-bit literals >= 0x80000000 */ PCRE2_SIZE parsed_size_needed; /* Needed for parsed pattern */ -int32_t firstcuflags, reqcuflags; /* Type of first/req code unit */ +uint32_t firstcuflags, reqcuflags; /* Type of first/req code unit */ uint32_t firstcu, reqcu; /* Value of first/req code unit */ uint32_t setflags = 0; /* NL and BSR set flags */ @@ -10427,13 +10431,13 @@ if ((re->overall_options & PCRE2_NO_START_OPTIMIZE) == 0) (these are not saved during the compile because they can cause conflicts with actual literals that follow). */ - if (firstcuflags < 0) + if (firstcuflags >= REQ_NONE) firstcu = find_firstassertedcu(codestart, &firstcuflags, 0); /* Save the data for a first code unit. The existence of one means the minimum length must be at least 1. */ - if (firstcuflags >= 0) + if (firstcuflags < REQ_NONE) { re->first_codeunit = firstcu; re->flags |= PCRE2_FIRSTSET; @@ -10480,16 +10484,16 @@ if ((re->overall_options & PCRE2_NO_START_OPTIMIZE) == 0) different character and not a non-starting code unit of the first character, because the minimum length count is in characters, not code units. */ - if (reqcuflags >= 0) + if (reqcuflags < REQ_NONE) { #if PCRE2_CODE_UNIT_WIDTH == 16 if ((re->overall_options & PCRE2_UTF) == 0 || /* Not UTF */ - firstcuflags < 0 || /* First not set */ + firstcuflags >= REQ_NONE || /* First not set */ (firstcu & 0xf800) != 0xd800 || /* First not surrogate */ (reqcu & 0xfc00) != 0xdc00) /* Req not low surrogate */ #elif PCRE2_CODE_UNIT_WIDTH == 8 if ((re->overall_options & PCRE2_UTF) == 0 || /* Not UTF */ - firstcuflags < 0 || /* First not set */ + firstcuflags >= REQ_NONE || /* First not set */ (firstcu & 0x80) == 0 || /* First is ASCII */ (reqcu & 0x80) == 0) /* Req is ASCII */ #endif diff --git a/src/pcre2_intmodedep.h b/src/pcre2_intmodedep.h index 4a4a4c5..3daf21b 100644 --- a/src/pcre2_intmodedep.h +++ b/src/pcre2_intmodedep.h @@ -747,8 +747,8 @@ typedef struct compile_block { uint32_t class_range_start; /* Overall class range start */ uint32_t class_range_end; /* Overall class range end */ PCRE2_UCHAR nl[4]; /* Newline string when fixed length */ + uint32_t req_varyopt; /* "After variable item" flag for reqbyte */ int max_lookbehind; /* Maximum lookbehind (characters) */ - int req_varyopt; /* "After variable item" flag for reqbyte */ BOOL had_accept; /* (*ACCEPT) encountered */ BOOL had_pruneorskip; /* (*PRUNE) or (*SKIP) encountered */ BOOL had_recurse; /* Had a recursion or subroutine call */ diff --git a/src/pcre2_match.c b/src/pcre2_match.c index 710d4a2..95e6dcd 100644 --- a/src/pcre2_match.c +++ b/src/pcre2_match.c @@ -6571,7 +6571,7 @@ if (utf && /* Validate the relevant portion of the subject. There's a loop in case we encounter bad UTF in the characters preceding start_match which we are scanning because of a lookbehind. */ - + for (;;) { match_data->rc = PRIV(valid_utf)(mb->check_subject, @@ -6591,7 +6591,7 @@ if (utf && /* If the end precedes start_match, it means there is invalid UTF in the extra code units we reversed over because of a lookbehind. Advance past the first bad code unit, and then skip invalid character starting code units in - 8-bit and 16-bit modes, and try again. */ + 8-bit and 16-bit modes, and try again with the original end point. */ if (end_subject < start_match) { @@ -6600,6 +6600,7 @@ if (utf && while (mb->check_subject < start_match && NOT_FIRSTCU(*mb->check_subject)) mb->check_subject++; #endif + end_subject = true_end_subject; } /* Otherwise, set the not end of line option, and do the match. */ diff --git a/src/pcre2_study.c b/src/pcre2_study.c index 9bbb375..4db3ad1 100644 --- a/src/pcre2_study.c +++ b/src/pcre2_study.c @@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel Original API code Copyright (c) 1997-2012 University of Cambridge - New API code Copyright (c) 2016-2020 University of Cambridge + New API code Copyright (c) 2016-2021 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -908,7 +908,7 @@ set_nottype_bits(pcre2_real_code *re, int cbit_type, unsigned int table_limit) { uint32_t c; for (c = 0; c < table_limit; c++) - re->start_bitmap[c] |= ~(re->tables[c+cbits_offset+cbit_type]); + re->start_bitmap[c] |= (uint8_t)(~(re->tables[c+cbits_offset+cbit_type])); #if defined SUPPORT_UNICODE && PCRE2_CODE_UNIT_WIDTH == 8 if (table_limit != 32) for (c = 24; c < 32; c++) re->start_bitmap[c] = 0xff; #endif diff --git a/src/pcre2_substitute.c b/src/pcre2_substitute.c index bddd6b0..8b2c369 100644 --- a/src/pcre2_substitute.c +++ b/src/pcre2_substitute.c @@ -259,7 +259,7 @@ PCRE2_UNSET, so as not to imply an offset in the replacement. */ if ((options & (PCRE2_PARTIAL_HARD|PCRE2_PARTIAL_SOFT)) != 0) return PCRE2_ERROR_BADOPTION; - + /* Validate length and find the end of the replacement. A NULL replacement of zero length is interpreted as an empty string. */ @@ -304,7 +304,6 @@ else if (use_existing_match) (pcre2_general_context *)mcontext; int pairs = (code->top_bracket + 1 < match_data->oveccount)? code->top_bracket + 1 : match_data->oveccount; - if (subject == NULL) return PCRE2_ERROR_NULL; internal_match_data = pcre2_match_data_create(match_data->oveccount, gcontext); if (internal_match_data == NULL) return PCRE2_ERROR_NOMEMORY; @@ -325,7 +324,16 @@ scb.input = subject; scb.output = (PCRE2_SPTR)buffer; scb.ovector = ovector; -/* Find lengths of zero-terminated subject */ +/* A NULL subject of zero length is treated as an empty string. */ + +if (subject == NULL) + { + if (length != 0) return PCRE2_ERROR_NULL; + subject = (PCRE2_SPTR)""; + } + +/* Find length of zero-terminated subject */ + if (length == PCRE2_ZERO_TERMINATED) length = subject? PRIV(strlen)(subject) : 0; diff --git a/src/pcre2test.c b/src/pcre2test.c index e9d0148..52c94a7 100644 --- a/src/pcre2test.c +++ b/src/pcre2test.c @@ -3152,7 +3152,7 @@ Returns: 0 on success, with the length updated to the number of 16-bit OR -3 if a value > 0xffff is encountered when not in UTF mode */ -static PCRE2_SIZE +static int to16(uint8_t *p, int utf, PCRE2_SIZE *lenptr) { uint16_t *pp; @@ -3239,7 +3239,7 @@ Returns: 0 on success, with the length updated to the number of 32-bit OR -2 if a value > 0x10ffff is encountered in UTF mode */ -static PCRE2_SIZE +static int to32(uint8_t *p, int utf, PCRE2_SIZE *lenptr) { uint32_t *pp; @@ -5490,24 +5490,27 @@ if ((pat_patctl.control & CTL_POSIX) != 0) if ((pat_patctl.options & ~POSIX_SUPPORTED_COMPILE_OPTIONS) != 0) { show_compile_options( - pat_patctl.options & ~POSIX_SUPPORTED_COMPILE_OPTIONS, msg, ""); - msg = ""; - } - - if ((FLD(pat_context, extra_options) & - ~POSIX_SUPPORTED_COMPILE_EXTRA_OPTIONS) != 0) - { - show_compile_extra_options( - FLD(pat_context, extra_options) & ~POSIX_SUPPORTED_COMPILE_EXTRA_OPTIONS, + pat_patctl.options & (uint32_t)(~POSIX_SUPPORTED_COMPILE_OPTIONS), msg, ""); msg = ""; } - if ((pat_patctl.control & ~POSIX_SUPPORTED_COMPILE_CONTROLS) != 0 || - (pat_patctl.control2 & ~POSIX_SUPPORTED_COMPILE_CONTROLS2) != 0) + if ((FLD(pat_context, extra_options) & + (uint32_t)(~POSIX_SUPPORTED_COMPILE_EXTRA_OPTIONS)) != 0) { - show_controls(pat_patctl.control & ~POSIX_SUPPORTED_COMPILE_CONTROLS, - pat_patctl.control2 & ~POSIX_SUPPORTED_COMPILE_CONTROLS2, msg); + show_compile_extra_options( + FLD(pat_context, extra_options) & + (uint32_t)(~POSIX_SUPPORTED_COMPILE_EXTRA_OPTIONS), msg, ""); + msg = ""; + } + + if ((pat_patctl.control & (uint32_t)(~POSIX_SUPPORTED_COMPILE_CONTROLS)) != 0 || + (pat_patctl.control2 & (uint32_t)(~POSIX_SUPPORTED_COMPILE_CONTROLS2)) != 0) + { + show_controls( + pat_patctl.control & (uint32_t)(~POSIX_SUPPORTED_COMPILE_CONTROLS), + pat_patctl.control2 & (uint32_t)(~POSIX_SUPPORTED_COMPILE_CONTROLS2), + msg); msg = ""; } @@ -7652,11 +7655,15 @@ for (gmatched = 0;; gmatched++) } /* The result of the match is now in capcount. First handle a successful - match. */ + match. If pp was forced to be NULL (to test NULL handling) it will have been + treated as an empty string if the length was zero. So re-create that for + outputting. */ if (capcount >= 0) { int i; + + if (pp == NULL) pp = (uint8_t *)""; if (capcount > (int)oveccount) /* Check for lunatic return value */ {