From ae913fbee7e8f2a3668dc5e566f41f66928879aa Mon Sep 17 00:00:00 2001 From: "Philip.Hazel" Date: Wed, 30 Jan 2019 16:11:16 +0000 Subject: [PATCH] Update POSIX wrapper to use macros in the .h file, but also have the POSIX function names in the library. --- ChangeLog | 9 +- README | 17 +-- doc/html/README.txt | 17 +-- doc/html/pcre2posix.html | 163 ++++++++++++------------- doc/pcre2.txt | 257 ++++++++++++++++++++------------------- doc/pcre2posix.3 | 133 ++++++++++---------- src/pcre2posix.c | 27 +++- src/pcre2posix.h | 29 +++-- 8 files changed, 332 insertions(+), 320 deletions(-) diff --git a/ChangeLog b/ChangeLog index 10641ac..c0a8a69 100644 --- a/ChangeLog +++ b/ChangeLog @@ -14,9 +14,12 @@ a greater than 1 fixed quantifier. This issue was found by Yunho Kim. 3. Added support for callouts from pcre2_substitute(). -4. The POSIX functions are now all called pcre2_regcomp() etc., with wrappers -that use the standard POSIX names. This should help avoid linking with the -wrong library in some environments. +4. The POSIX functions are now all called pcre2_regcomp() etc., with wrapper +functions that use the standard POSIX names. However, in pcre2posix.h the POSIX +names are defined as macros. This should help avoid linking with the wrong +library in some environments while still exporting the POSIX names for +pre-existing programs that use them. (The Debian alternative names are also +defined as macros, but not documented.) 5. Fix an xclass matching issue in JIT. diff --git a/README b/README index 9c46ac4..af5af63 100644 --- a/README +++ b/README @@ -53,19 +53,8 @@ The header file for the POSIX-style functions is called pcre2posix.h. The official POSIX name is regex.h, but I did not want to risk possible problems with existing files of that name by distributing it that way. To use PCRE2 with an existing program that uses the POSIX API, pcre2posix.h will have to be -renamed or pointed at by a link (or the program modified, of course). - -If you are using the POSIX interface to PCRE2 and there is already a POSIX -regex library installed on your system, as well as worrying about the regex.h -header file (as mentioned above), you must also take care when linking programs -to ensure that they link with PCRE2's libpcre2-posix library. Otherwise they -may pick up the POSIX functions of the same name from the other library. - -To help with this issue, the libpcre2-posix library provides alternative names -for the POSIX functions. These are the POSIX names, prefixed with "pcre2_", for -example, pcre2_regcomp(). If an application can be compiled to use the -alternative names (for example by the use of -Dregcomp=pcre2_regcomp etc.) it -can be sure of linking with the PCRE2 functions. +renamed or pointed at by a link (or the program modified, of course). See the +pcre2posix documentation for more details. Documentation for PCRE2 @@ -897,4 +886,4 @@ The distribution should contain the files listed below. Philip Hazel Email local part: ph10 Email domain: cam.ac.uk -Last updated: 15 November 2018 +Last updated: 29 January 2019 diff --git a/doc/html/README.txt b/doc/html/README.txt index 9c46ac4..af5af63 100644 --- a/doc/html/README.txt +++ b/doc/html/README.txt @@ -53,19 +53,8 @@ The header file for the POSIX-style functions is called pcre2posix.h. The official POSIX name is regex.h, but I did not want to risk possible problems with existing files of that name by distributing it that way. To use PCRE2 with an existing program that uses the POSIX API, pcre2posix.h will have to be -renamed or pointed at by a link (or the program modified, of course). - -If you are using the POSIX interface to PCRE2 and there is already a POSIX -regex library installed on your system, as well as worrying about the regex.h -header file (as mentioned above), you must also take care when linking programs -to ensure that they link with PCRE2's libpcre2-posix library. Otherwise they -may pick up the POSIX functions of the same name from the other library. - -To help with this issue, the libpcre2-posix library provides alternative names -for the POSIX functions. These are the POSIX names, prefixed with "pcre2_", for -example, pcre2_regcomp(). If an application can be compiled to use the -alternative names (for example by the use of -Dregcomp=pcre2_regcomp etc.) it -can be sure of linking with the PCRE2 functions. +renamed or pointed at by a link (or the program modified, of course). See the +pcre2posix documentation for more details. Documentation for PCRE2 @@ -897,4 +886,4 @@ The distribution should contain the files listed below. Philip Hazel Email local part: ph10 Email domain: cam.ac.uk -Last updated: 15 November 2018 +Last updated: 29 January 2019 diff --git a/doc/html/pcre2posix.html b/doc/html/pcre2posix.html index b1acd35..b03948e 100644 --- a/doc/html/pcre2posix.html +++ b/doc/html/pcre2posix.html @@ -15,74 +15,75 @@ please consult the man page, in case the conversion went wrong.
SYNOPSIS

#include <pcre2posix.h>

-int regcomp(regex_t *preg, const char *pattern, - int cflags); -
-
int pcre2_regcomp(regex_t *preg, const char *pattern, int cflags);

-int regexec(const regex_t *preg, const char *string, - size_t nmatch, regmatch_t pmatch[], int eflags); -
-
int pcre2_regexec(const regex_t *preg, const char *string, size_t nmatch, regmatch_t pmatch[], int eflags);

-size_t regerror(int errcode, const regex_t *preg, - char *errbuf, size_t errbuf_size); -
-
size_t pcre2_regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size);

-void regfree(regex_t *preg); -
-
void pcre2_regfree(regex_t *preg);


DESCRIPTION

This set of functions provides a POSIX-style API for the PCRE2 regular -expression 8-bit library. See the +expression 8-bit library. There are no POSIX-style wrappers for PCRE2's 16-bit +and 32-bit libraries. See the pcre2api documentation for a description of PCRE2's native API, which contains much -additional functionality. There are no POSIX-style wrappers for PCRE2's 16-bit -and 32-bit libraries. +additional functionality.

-The functions described here are just wrapper functions that ultimately call -the PCRE2 native API. Their prototypes are defined in the pcre2posix.h -header file, and on Unix systems the library itself is called -libpcre2-posix.a, so can be accessed by adding -lpcre2-posix to the -command for linking an application that uses them. Because the POSIX functions -call the native ones, it is also necessary to add -lpcre2-8. +The functions described here are wrapper functions that ultimately call the +PCRE2 native API. Their prototypes are defined in the pcre2posix.h header +file, and they all have unique names starting with pcre2_. However, the +pcre2posix.h header also contains macro definitions that convert the +standard POSIX names such regcomp() into pcre2_regcomp() etc. This +means that a program can use the usual POSIX names without running the risk of +accidentally linking with POSIX functions from a different library.

-When another POSIX regex library is also installed, there is the possibility of -linking an application with the wrong library. To help avoid this issue, the -PCRE2 POSIX library provides alternative names for the functions, all starting -with "pcre2_". If an application uses these names, possible ambiguity is -avoided. In the following description, however, the standard POSIX function -names are used. +On Unix-like systems the PCRE2 POSIX library is called libpcre2-posix, so +can be accessed by adding -lpcre2-posix to the command for linking an +application. Because the POSIX functions call the native ones, it is also +necessary to add -lpcre2-8.

+Although they are not defined as protypes in pcre2posix.h, the library +does contain functions with the POSIX names regcomp() etc. These simply +pass their arguments to the PCRE2 functions. These functions are provided for +backwards compatibility with earlier versions of PCRE2, so that existing +programs do not have to be recompiled. +

+

+Calling the header file pcre2posix.h avoids any conflict with other POSIX +libraries. It can, of course, be renamed or aliased as regex.h, which is +the "correct" name, if there is no clash. It provides two structure types, +regex_t for compiled internal forms, and regmatch_t for returning +captured substrings. It also defines some constants whose names start with +"REG_"; these are used for setting options and identifying error codes. +

+
USING THE POSIX FUNCTIONS
+

Those POSIX option bits that can reasonably be mapped to PCRE2 native options have been implemented. In addition, the option REG_EXTENDED is defined with the value zero. This has no effect, but since programs that are written to the @@ -103,17 +104,13 @@ POSIX definition; it is not fully POSIX-compatible, and in multi-unit encoding domains it is probably even less compatible.

-The header for these functions is supplied as pcre2posix.h to avoid any -potential clash with other POSIX libraries. It can, of course, be renamed or -aliased as regex.h, which is the "correct" name. It provides two -structure types, regex_t for compiled internal forms, and -regmatch_t for returning captured substrings. It also defines some -constants whose names start with "REG_"; these are used for setting options and -identifying error codes. +The descriptions below use the actual names of the functions, but, as described +above, the standard POSIX names (without the pcre2_ prefix) may also be +used.

-
COMPILING A PATTERN
+
COMPILING A PATTERN

-The function regcomp() is called to compile a pattern into an +The function pcre2_regcomp() is called to compile a pattern into an internal form. By default, the pattern is a C string terminated by a binary zero (but see REG_PEND below). The preg argument is a pointer to a regex_t structure that is used as a base for storing information about @@ -151,18 +148,18 @@ REG_UTF. Note that REG_NOSPEC is not part of the POSIX standard. 

   REG_NOSUB
-When a pattern that is compiled with this flag is passed to regexec() for -matching, the nmatch and pmatch arguments are ignored, and no -captured strings are returned. Versions of the PCRE library prior to 10.22 used -to set the PCRE2_NO_AUTO_CAPTURE compile option, but this no longer happens -because it disables the use of backreferences. +When a pattern that is compiled with this flag is passed to +pcre2_regexec() for matching, the nmatch and pmatch arguments +are ignored, and no captured strings are returned. Versions of the PCRE library +prior to 10.22 used to set the PCRE2_NO_AUTO_CAPTURE compile option, but this +no longer happens because it disables the use of backreferences. 
   REG_PEND
If this option is set, the reg_endp field in the preg structure (which has the type const char *) must be set to point to the character beyond -the end of the pattern before calling regcomp(). The pattern itself may -now contain binary zeros, which are treated as data characters. Without +the end of the pattern before calling pcre2_regcomp(). The pattern itself +may now contain binary zeros, which are treated as data characters. Without REG_PEND, a binary zero terminates the pattern and the re_endp field is ignored. This is a GNU extension to the POSIX standard and should be used with caution in software intended to be portable to other systems. @@ -197,18 +194,19 @@ newlines are matched by the dot metacharacter (they are not) or by a negative class such as [^a] (they are).

-The yield of regcomp() is zero on success, and non-zero otherwise. The -preg structure is filled in on success, and one other member of the +The yield of pcre2_regcomp() is zero on success, and non-zero otherwise. +The preg structure is filled in on success, and one other member of the structure (as well as re_endp) is public: re_nsub contains the number of capturing subpatterns in the regular expression. Various error codes are defined in the header file.

-NOTE: If the yield of regcomp() is non-zero, you must not attempt to -use the contents of the preg structure. If, for example, you pass it to -regexec(), the result is undefined and your program is likely to crash. +NOTE: If the yield of pcre2_regcomp() is non-zero, you must not attempt +to use the contents of the preg structure. If, for example, you pass it +to pcre2_regexec(), the result is undefined and your program is likely to +crash.

-
MATCHING NEWLINE CHARACTERS
+
MATCHING NEWLINE CHARACTERS

This area is not simple, because POSIX and Perl take different views of things. It is not possible to get PCRE2 to obey POSIX semantics, but then PCRE2 was @@ -242,16 +240,16 @@ is no way to stop newline from matching [^a]. Default POSIX newline handling can be obtained by setting PCRE2_DOTALL and PCRE2_DOLLAR_ENDONLY when calling pcre2_compile() directly, but there is no way to make PCRE2 behave exactly as for the REG_NEWLINE action. When using -the POSIX API, passing REG_NEWLINE to PCRE2's regcomp() function +the POSIX API, passing REG_NEWLINE to PCRE2's pcre2_regcomp() function causes PCRE2_MULTILINE to be passed to pcre2_compile(), and REG_DOTALL passes PCRE2_DOTALL. There is no way to pass PCRE2_DOLLAR_ENDONLY.

-
MATCHING A PATTERN
+
MATCHING A PATTERN

-The function regexec() is called to match a compiled pattern preg -against a given string, which is by default terminated by a zero byte -(but see REG_STARTEND below), subject to the options in eflags. These can -be: +The function pcre2_regexec() is called to match a compiled pattern +preg against a given string, which is by default terminated by a +zero byte (but see REG_STARTEND below), subject to the options in eflags. +These can be: 

   REG_NOTBOL
@@ -295,7 +293,7 @@ are mutually exclusive; the error REG_INVARG is returned.

If the pattern was compiled with the REG_NOSUB flag, no data about any matched strings is returned. The nmatch and pmatch arguments of -regexec() are ignored (except possibly as input for REG_STARTEND). +pcre2_regexec() are ignored (except possibly as input for REG_STARTEND).

The value of nmatch may be zero, and the value pmatch may be NULL @@ -317,24 +315,25 @@ array have both structure members set to -1. A successful match yields a zero return; various error codes are defined in the header file, of which REG_NOMATCH is the "expected" failure code.

-
ERROR MESSAGES
+
ERROR MESSAGES

-The regerror() function maps a non-zero errorcode from either -regcomp() or regexec() to a printable message. If preg is not -NULL, the error should have arisen from the use of that structure. A message -terminated by a binary zero is placed in errbuf. If the buffer is too -short, only the first errbuf_size - 1 characters of the error message are -used. The yield of the function is the size of buffer needed to hold the whole -message, including the terminating zero. This value is greater than -errbuf_size if the message was truncated. +The pcre2_regerror() function maps a non-zero errorcode from either +pcre2_regcomp() or pcre2_regexec() to a printable message. If +preg is not NULL, the error should have arisen from the use of that +structure. A message terminated by a binary zero is placed in errbuf. If +the buffer is too short, only the first errbuf_size - 1 characters of the +error message are used. The yield of the function is the size of buffer needed +to hold the whole message, including the terminating zero. This value is +greater than errbuf_size if the message was truncated.

-
MEMORY USAGE
+
MEMORY USAGE

Compiling a regular expression causes memory to be allocated and associated -with the preg structure. The function regfree() frees all such -memory, after which preg may no longer be used as a compiled expression. +with the preg structure. The function pcre2_regfree() frees all +such memory, after which preg may no longer be used as a compiled +expression.

-
AUTHOR
+
AUTHOR

Philip Hazel
@@ -343,11 +342,11 @@ University Computing Service Cambridge, England.

-
REVISION
+
REVISION

-Last updated: 19 September 2018 +Last updated: 30 January 2019
-Copyright © 1997-2018 University of Cambridge. +Copyright © 1997-2019 University of Cambridge.

Return to the PCRE2 index page. diff --git a/doc/pcre2.txt b/doc/pcre2.txt index 0a54e89..332a4b8 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -9587,175 +9587,179 @@ SYNOPSIS #include - int regcomp(regex_t *preg, const char *pattern, - int cflags); - int pcre2_regcomp(regex_t *preg, const char *pattern, int cflags); - int regexec(const regex_t *preg, const char *string, - size_t nmatch, regmatch_t pmatch[], int eflags); - int pcre2_regexec(const regex_t *preg, const char *string, size_t nmatch, regmatch_t pmatch[], int eflags); - size_t regerror(int errcode, const regex_t *preg, - char *errbuf, size_t errbuf_size); - size_t pcre2_regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size); - void regfree(regex_t *preg); - void pcre2_regfree(regex_t *preg); DESCRIPTION This set of functions provides a POSIX-style API for the PCRE2 regular - expression 8-bit library. See the pcre2api documentation for a descrip- - tion of PCRE2's native API, which contains much additional functional- - ity. There are no POSIX-style wrappers for PCRE2's 16-bit and 32-bit - libraries. + expression 8-bit library. There are no POSIX-style wrappers for PCRE2's + 16-bit and 32-bit libraries. See the pcre2api documentation for a + description of PCRE2's native API, which contains much additional func- + tionality. - The functions described here are just wrapper functions that ultimately - call the PCRE2 native API. Their prototypes are defined in the - pcre2posix.h header file, and on Unix systems the library itself is - called libpcre2-posix.a, so can be accessed by adding -lpcre2-posix to - the command for linking an application that uses them. Because the - POSIX functions call the native ones, it is also necessary to add - -lpcre2-8. + The functions described here are wrapper functions that ultimately call + the PCRE2 native API. Their prototypes are defined in the pcre2posix.h + header file, and they all have unique names starting with pcre2_. How- + ever, the pcre2posix.h header also contains macro definitions that con- + vert the standard POSIX names such regcomp() into pcre2_regcomp() etc. + This means that a program can use the usual POSIX names without running + the risk of accidentally linking with POSIX functions from a different + library. - When another POSIX regex library is also installed, there is the possi- - bility of linking an application with the wrong library. To help avoid - this issue, the PCRE2 POSIX library provides alternative names for the - functions, all starting with "pcre2_". If an application uses these - names, possible ambiguity is avoided. In the following description, - however, the standard POSIX function names are used. + On Unix-like systems the PCRE2 POSIX library is called libpcre2-posix, + so can be accessed by adding -lpcre2-posix to the command for linking + an application. Because the POSIX functions call the native ones, it is + also necessary to add -lpcre2-8. - Those POSIX option bits that can reasonably be mapped to PCRE2 native - options have been implemented. In addition, the option REG_EXTENDED is - defined with the value zero. This has no effect, but since programs - that are written to the POSIX interface often use it, this makes it - easier to slot in PCRE2 as a replacement library. Other POSIX options + Although they are not defined as protypes in pcre2posix.h, the library + does contain functions with the POSIX names regcomp() etc. These simply + pass their arguments to the PCRE2 functions. These functions are pro- + vided for backwards compatibility with earlier versions of PCRE2, so + that existing programs do not have to be recompiled. + + Calling the header file pcre2posix.h avoids any conflict with other + POSIX libraries. It can, of course, be renamed or aliased as regex.h, + which is the "correct" name, if there is no clash. It provides two + structure types, regex_t for compiled internal forms, and regmatch_t + for returning captured substrings. It also defines some constants whose + names start with "REG_"; these are used for setting options and identi- + fying error codes. + + +USING THE POSIX FUNCTIONS + + Those POSIX option bits that can reasonably be mapped to PCRE2 native + options have been implemented. In addition, the option REG_EXTENDED is + defined with the value zero. This has no effect, but since programs + that are written to the POSIX interface often use it, this makes it + easier to slot in PCRE2 as a replacement library. Other POSIX options are not even defined. - There are also some options that are not defined by POSIX. These have - been added at the request of users who want to make use of certain - PCRE2-specific features via the POSIX calling interface or to add BSD + There are also some options that are not defined by POSIX. These have + been added at the request of users who want to make use of certain + PCRE2-specific features via the POSIX calling interface or to add BSD or GNU functionality. - When PCRE2 is called via these functions, it is only the API that is - POSIX-like in style. The syntax and semantics of the regular expres- - sions themselves are still those of Perl, subject to the setting of - various PCRE2 options, as described below. "POSIX-like in style" means - that the API approximates to the POSIX definition; it is not fully - POSIX-compatible, and in multi-unit encoding domains it is probably + When PCRE2 is called via these functions, it is only the API that is + POSIX-like in style. The syntax and semantics of the regular expres- + sions themselves are still those of Perl, subject to the setting of + various PCRE2 options, as described below. "POSIX-like in style" means + that the API approximates to the POSIX definition; it is not fully + POSIX-compatible, and in multi-unit encoding domains it is probably even less compatible. - The header for these functions is supplied as pcre2posix.h to avoid any - potential clash with other POSIX libraries. It can, of course, be - renamed or aliased as regex.h, which is the "correct" name. It provides - two structure types, regex_t for compiled internal forms, and reg- - match_t for returning captured substrings. It also defines some con- - stants whose names start with "REG_"; these are used for setting - options and identifying error codes. + The descriptions below use the actual names of the functions, but, as + described above, the standard POSIX names (without the pcre2_ prefix) + may also be used. COMPILING A PATTERN - The function regcomp() is called to compile a pattern into an internal - form. By default, the pattern is a C string terminated by a binary zero - (but see REG_PEND below). The preg argument is a pointer to a regex_t - structure that is used as a base for storing information about the com- - piled regular expression. (It is also used for input when REG_PEND is - set.) + The function pcre2_regcomp() is called to compile a pattern into an + internal form. By default, the pattern is a C string terminated by a + binary zero (but see REG_PEND below). The preg argument is a pointer to + a regex_t structure that is used as a base for storing information + about the compiled regular expression. (It is also used for input when + REG_PEND is set.) The argument cflags is either zero, or contains one or more of the bits defined by the following macros: REG_DOTALL - The PCRE2_DOTALL option is set when the regular expression is passed - for compilation to the native function. Note that REG_DOTALL is not + The PCRE2_DOTALL option is set when the regular expression is passed + for compilation to the native function. Note that REG_DOTALL is not part of the POSIX standard. REG_ICASE - The PCRE2_CASELESS option is set when the regular expression is passed + The PCRE2_CASELESS option is set when the regular expression is passed for compilation to the native function. REG_NEWLINE The PCRE2_MULTILINE option is set when the regular expression is passed - for compilation to the native function. Note that this does not mimic - the defined POSIX behaviour for REG_NEWLINE (see the following sec- + for compilation to the native function. Note that this does not mimic + the defined POSIX behaviour for REG_NEWLINE (see the following sec- tion). REG_NOSPEC - The PCRE2_LITERAL option is set when the regular expression is passed - for compilation to the native function. This disables all meta charac- - ters in the pattern, causing it to be treated as a literal string. The - only other options that are allowed with REG_NOSPEC are REG_ICASE, - REG_NOSUB, REG_PEND, and REG_UTF. Note that REG_NOSPEC is not part of + The PCRE2_LITERAL option is set when the regular expression is passed + for compilation to the native function. This disables all meta charac- + ters in the pattern, causing it to be treated as a literal string. The + only other options that are allowed with REG_NOSPEC are REG_ICASE, + REG_NOSUB, REG_PEND, and REG_UTF. Note that REG_NOSPEC is not part of the POSIX standard. REG_NOSUB - When a pattern that is compiled with this flag is passed to regexec() - for matching, the nmatch and pmatch arguments are ignored, and no cap- - tured strings are returned. Versions of the PCRE library prior to 10.22 - used to set the PCRE2_NO_AUTO_CAPTURE compile option, but this no - longer happens because it disables the use of backreferences. + When a pattern that is compiled with this flag is passed to + pcre2_regexec() for matching, the nmatch and pmatch arguments are + ignored, and no captured strings are returned. Versions of the PCRE + library prior to 10.22 used to set the PCRE2_NO_AUTO_CAPTURE compile + option, but this no longer happens because it disables the use of back- + references. REG_PEND If this option is set, the reg_endp field in the preg structure (which has the type const char *) must be set to point to the character beyond - the end of the pattern before calling regcomp(). The pattern itself may - now contain binary zeros, which are treated as data characters. Without - REG_PEND, a binary zero terminates the pattern and the re_endp field is - ignored. This is a GNU extension to the POSIX standard and should be - used with caution in software intended to be portable to other systems. + the end of the pattern before calling pcre2_regcomp(). The pattern + itself may now contain binary zeros, which are treated as data charac- + ters. Without REG_PEND, a binary zero terminates the pattern and the + re_endp field is ignored. This is a GNU extension to the POSIX standard + and should be used with caution in software intended to be portable to + other systems. REG_UCP - The PCRE2_UCP option is set when the regular expression is passed for - compilation to the native function. This causes PCRE2 to use Unicode - properties when matchine \d, \w, etc., instead of just recognizing + The PCRE2_UCP option is set when the regular expression is passed for + compilation to the native function. This causes PCRE2 to use Unicode + properties when matchine \d, \w, etc., instead of just recognizing ASCII values. Note that REG_UCP is not part of the POSIX standard. REG_UNGREEDY - The PCRE2_UNGREEDY option is set when the regular expression is passed - for compilation to the native function. Note that REG_UNGREEDY is not + The PCRE2_UNGREEDY option is set when the regular expression is passed + for compilation to the native function. Note that REG_UNGREEDY is not part of the POSIX standard. REG_UTF - The PCRE2_UTF option is set when the regular expression is passed for - compilation to the native function. This causes the pattern itself and - all data strings used for matching it to be treated as UTF-8 strings. + The PCRE2_UTF option is set when the regular expression is passed for + compilation to the native function. This causes the pattern itself and + all data strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF is not part of the POSIX standard. - In the absence of these flags, no options are passed to the native - function. This means the the regex is compiled with PCRE2 default - semantics. In particular, the way it handles newline characters in the - subject string is the Perl way, not the POSIX way. Note that setting + In the absence of these flags, no options are passed to the native + function. This means the the regex is compiled with PCRE2 default + semantics. In particular, the way it handles newline characters in the + subject string is the Perl way, not the POSIX way. Note that setting PCRE2_MULTILINE has only some of the effects specified for REG_NEWLINE. - It does not affect the way newlines are matched by the dot metacharac- + It does not affect the way newlines are matched by the dot metacharac- ter (they are not) or by a negative class such as [^a] (they are). - The yield of regcomp() is zero on success, and non-zero otherwise. The - preg structure is filled in on success, and one other member of the - structure (as well as re_endp) is public: re_nsub contains the number - of capturing subpatterns in the regular expression. Various error codes - are defined in the header file. + The yield of pcre2_regcomp() is zero on success, and non-zero other- + wise. The preg structure is filled in on success, and one other member + of the structure (as well as re_endp) is public: re_nsub contains the + number of capturing subpatterns in the regular expression. Various + error codes are defined in the header file. - NOTE: If the yield of regcomp() is non-zero, you must not attempt to - use the contents of the preg structure. If, for example, you pass it to - regexec(), the result is undefined and your program is likely to crash. + NOTE: If the yield of pcre2_regcomp() is non-zero, you must not attempt + to use the contents of the preg structure. If, for example, you pass it + to pcre2_regexec(), the result is undefined and your program is likely + to crash. MATCHING NEWLINE CHARACTERS @@ -9792,17 +9796,17 @@ MATCHING NEWLINE CHARACTERS Default POSIX newline handling can be obtained by setting PCRE2_DOTALL and PCRE2_DOLLAR_ENDONLY when calling pcre2_compile() directly, but there is no way to make PCRE2 behave exactly as for the REG_NEWLINE - action. When using the POSIX API, passing REG_NEWLINE to PCRE2's reg- - comp() function causes PCRE2_MULTILINE to be passed to pcre2_compile(), - and REG_DOTALL passes PCRE2_DOTALL. There is no way to pass PCRE2_DOL- - LAR_ENDONLY. + action. When using the POSIX API, passing REG_NEWLINE to PCRE2's + pcre2_regcomp() function causes PCRE2_MULTILINE to be passed to + pcre2_compile(), and REG_DOTALL passes PCRE2_DOTALL. There is no way to + pass PCRE2_DOLLAR_ENDONLY. MATCHING A PATTERN - The function regexec() is called to match a compiled pattern preg + The function pcre2_regexec() is called to match a compiled pattern preg against a given string, which is by default terminated by a zero byte - (but see REG_STARTEND below), subject to the options in eflags. These + (but see REG_STARTEND below), subject to the options in eflags. These can be: REG_NOTBOL @@ -9846,45 +9850,46 @@ MATCHING A PATTERN If the pattern was compiled with the REG_NOSUB flag, no data about any matched strings is returned. The nmatch and pmatch arguments of - regexec() are ignored (except possibly as input for REG_STARTEND). + pcre2_regexec() are ignored (except possibly as input for REG_STAR- + TEND). - The value of nmatch may be zero, and the value pmatch may be NULL - (unless REG_STARTEND is set); in both these cases no data about any + The value of nmatch may be zero, and the value pmatch may be NULL + (unless REG_STARTEND is set); in both these cases no data about any matched strings is returned. - Otherwise, the portion of the string that was matched, and also any + Otherwise, the portion of the string that was matched, and also any captured substrings, are returned via the pmatch argument, which points - to an array of nmatch structures of type regmatch_t, containing the - members rm_so and rm_eo. These contain the byte offset to the first + to an array of nmatch structures of type regmatch_t, containing the + members rm_so and rm_eo. These contain the byte offset to the first character of each substring and the offset to the first character after - the end of each substring, respectively. The 0th element of the vector - relates to the entire portion of string that was matched; subsequent + the end of each substring, respectively. The 0th element of the vector + relates to the entire portion of string that was matched; subsequent elements relate to the capturing subpatterns of the regular expression. Unused entries in the array have both structure members set to -1. - A successful match yields a zero return; various error codes are - defined in the header file, of which REG_NOMATCH is the "expected" + A successful match yields a zero return; various error codes are + defined in the header file, of which REG_NOMATCH is the "expected" failure code. ERROR MESSAGES - The regerror() function maps a non-zero errorcode from either regcomp() - or regexec() to a printable message. If preg is not NULL, the error - should have arisen from the use of that structure. A message terminated - by a binary zero is placed in errbuf. If the buffer is too short, only - the first errbuf_size - 1 characters of the error message are used. The - yield of the function is the size of buffer needed to hold the whole - message, including the terminating zero. This value is greater than - errbuf_size if the message was truncated. + The pcre2_regerror() function maps a non-zero errorcode from either + pcre2_regcomp() or pcre2_regexec() to a printable message. If preg is + not NULL, the error should have arisen from the use of that structure. + A message terminated by a binary zero is placed in errbuf. If the buf- + fer is too short, only the first errbuf_size - 1 characters of the + error message are used. The yield of the function is the size of buffer + needed to hold the whole message, including the terminating zero. This + value is greater than errbuf_size if the message was truncated. MEMORY USAGE - Compiling a regular expression causes memory to be allocated and asso- - ciated with the preg structure. The function regfree() frees all such - memory, after which preg may no longer be used as a compiled expres- - sion. + Compiling a regular expression causes memory to be allocated and asso- + ciated with the preg structure. The function pcre2_regfree() frees all + such memory, after which preg may no longer be used as a compiled + expression. AUTHOR @@ -9896,8 +9901,8 @@ AUTHOR REVISION - Last updated: 19 September 2018 - Copyright (c) 1997-2018 University of Cambridge. + Last updated: 30 January 2019 + Copyright (c) 1997-2019 University of Cambridge. ------------------------------------------------------------------------------ diff --git a/doc/pcre2posix.3 b/doc/pcre2posix.3 index a91ccbf..05eb605 100644 --- a/doc/pcre2posix.3 +++ b/doc/pcre2posix.3 @@ -1,4 +1,4 @@ -.TH PCRE2POSIX 3 "19 September 2018" "PCRE2 10.33" +.TH PCRE2POSIX 3 "30 January 2019" "PCRE2 10.33" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH "SYNOPSIS" @@ -7,26 +7,15 @@ PCRE2 - Perl-compatible regular expressions (revised API) .B #include .PP .nf -.B int regcomp(regex_t *\fIpreg\fP, const char *\fIpattern\fP, -.B " int \fIcflags\fP);" -.sp .B int pcre2_regcomp(regex_t *\fIpreg\fP, const char *\fIpattern\fP, .B " int \fIcflags\fP);" .sp -.B int regexec(const regex_t *\fIpreg\fP, const char *\fIstring\fP, -.B " size_t \fInmatch\fP, regmatch_t \fIpmatch\fP[], int \fIeflags\fP);" -.sp .B int pcre2_regexec(const regex_t *\fIpreg\fP, const char *\fIstring\fP, .B " size_t \fInmatch\fP, regmatch_t \fIpmatch\fP[], int \fIeflags\fP);" .sp -.B "size_t regerror(int \fIerrcode\fP, const regex_t *\fIpreg\fP," -.B " char *\fIerrbuf\fP, size_t \fIerrbuf_size\fP);" -.sp .B "size_t pcre2_regerror(int \fIerrcode\fP, const regex_t *\fIpreg\fP," .B " char *\fIerrbuf\fP, size_t \fIerrbuf_size\fP);" .sp -.B void regfree(regex_t *\fIpreg\fP); -.sp .B void pcre2_regfree(regex_t *\fIpreg\fP); .fi . @@ -34,28 +23,44 @@ PCRE2 - Perl-compatible regular expressions (revised API) .rs .sp This set of functions provides a POSIX-style API for the PCRE2 regular -expression 8-bit library. See the +expression 8-bit library. There are no POSIX-style wrappers for PCRE2's 16-bit +and 32-bit libraries. See the .\" HREF \fBpcre2api\fP .\" documentation for a description of PCRE2's native API, which contains much -additional functionality. There are no POSIX-style wrappers for PCRE2's 16-bit -and 32-bit libraries. +additional functionality. .P -The functions described here are just wrapper functions that ultimately call -the PCRE2 native API. Their prototypes are defined in the \fBpcre2posix.h\fP -header file, and on Unix systems the library itself is called -\fBlibpcre2-posix.a\fP, so can be accessed by adding \fB-lpcre2-posix\fP to the -command for linking an application that uses them. Because the POSIX functions -call the native ones, it is also necessary to add \fB-lpcre2-8\fP. +The functions described here are wrapper functions that ultimately call the +PCRE2 native API. Their prototypes are defined in the \fBpcre2posix.h\fP header +file, and they all have unique names starting with \fBpcre2_\fP. However, the +\fBpcre2posix.h\fP header also contains macro definitions that convert the +standard POSIX names such \fBregcomp()\fP into \fBpcre2_regcomp()\fP etc. This +means that a program can use the usual POSIX names without running the risk of +accidentally linking with POSIX functions from a different library. .P -When another POSIX regex library is also installed, there is the possibility of -linking an application with the wrong library. To help avoid this issue, the -PCRE2 POSIX library provides alternative names for the functions, all starting -with "pcre2_". If an application uses these names, possible ambiguity is -avoided. In the following description, however, the standard POSIX function -names are used. +On Unix-like systems the PCRE2 POSIX library is called \fBlibpcre2-posix\fP, so +can be accessed by adding \fB-lpcre2-posix\fP to the command for linking an +application. Because the POSIX functions call the native ones, it is also +necessary to add \fB-lpcre2-8\fP. .P +Although they are not defined as protypes in \fBpcre2posix.h\fP, the library +does contain functions with the POSIX names \fBregcomp()\fP etc. These simply +pass their arguments to the PCRE2 functions. These functions are provided for +backwards compatibility with earlier versions of PCRE2, so that existing +programs do not have to be recompiled. +.P +Calling the header file \fBpcre2posix.h\fP avoids any conflict with other POSIX +libraries. It can, of course, be renamed or aliased as \fBregex.h\fP, which is +the "correct" name, if there is no clash. It provides two structure types, +\fIregex_t\fP for compiled internal forms, and \fIregmatch_t\fP for returning +captured substrings. It also defines some constants whose names start with +"REG_"; these are used for setting options and identifying error codes. +. +. +.SH "USING THE POSIX FUNCTIONS" +.rs +.sp Those POSIX option bits that can reasonably be mapped to PCRE2 native options have been implemented. In addition, the option REG_EXTENDED is defined with the value zero. This has no effect, but since programs that are written to the @@ -73,19 +78,15 @@ described below. "POSIX-like in style" means that the API approximates to the POSIX definition; it is not fully POSIX-compatible, and in multi-unit encoding domains it is probably even less compatible. .P -The header for these functions is supplied as \fBpcre2posix.h\fP to avoid any -potential clash with other POSIX libraries. It can, of course, be renamed or -aliased as \fBregex.h\fP, which is the "correct" name. It provides two -structure types, \fIregex_t\fP for compiled internal forms, and -\fIregmatch_t\fP for returning captured substrings. It also defines some -constants whose names start with "REG_"; these are used for setting options and -identifying error codes. +The descriptions below use the actual names of the functions, but, as described +above, the standard POSIX names (without the \fBpcre2_\fP prefix) may also be +used. . . .SH "COMPILING A PATTERN" .rs .sp -The function \fBregcomp()\fP is called to compile a pattern into an +The function \fBpcre2_regcomp()\fP is called to compile a pattern into an internal form. By default, the pattern is a C string terminated by a binary zero (but see REG_PEND below). The \fIpreg\fP argument is a pointer to a \fBregex_t\fP structure that is used as a base for storing information about @@ -122,18 +123,18 @@ REG_UTF. Note that REG_NOSPEC is not part of the POSIX standard. .sp REG_NOSUB .sp -When a pattern that is compiled with this flag is passed to \fBregexec()\fP for -matching, the \fInmatch\fP and \fIpmatch\fP arguments are ignored, and no -captured strings are returned. Versions of the PCRE library prior to 10.22 used -to set the PCRE2_NO_AUTO_CAPTURE compile option, but this no longer happens -because it disables the use of backreferences. +When a pattern that is compiled with this flag is passed to +\fBpcre2_regexec()\fP for matching, the \fInmatch\fP and \fIpmatch\fP arguments +are ignored, and no captured strings are returned. Versions of the PCRE library +prior to 10.22 used to set the PCRE2_NO_AUTO_CAPTURE compile option, but this +no longer happens because it disables the use of backreferences. .sp REG_PEND .sp If this option is set, the \fBreg_endp\fP field in the \fIpreg\fP structure (which has the type const char *) must be set to point to the character beyond -the end of the pattern before calling \fBregcomp()\fP. The pattern itself may -now contain binary zeros, which are treated as data characters. Without +the end of the pattern before calling \fBpcre2_regcomp()\fP. The pattern itself +may now contain binary zeros, which are treated as data characters. Without REG_PEND, a binary zero terminates the pattern and the \fBre_endp\fP field is ignored. This is a GNU extension to the POSIX standard and should be used with caution in software intended to be portable to other systems. @@ -166,15 +167,16 @@ Perl way, not the POSIX way. Note that setting PCRE2_MULTILINE has only newlines are matched by the dot metacharacter (they are not) or by a negative class such as [^a] (they are). .P -The yield of \fBregcomp()\fP is zero on success, and non-zero otherwise. The -\fIpreg\fP structure is filled in on success, and one other member of the +The yield of \fBpcre2_regcomp()\fP is zero on success, and non-zero otherwise. +The \fIpreg\fP structure is filled in on success, and one other member of the structure (as well as \fIre_endp\fP) is public: \fIre_nsub\fP contains the number of capturing subpatterns in the regular expression. Various error codes are defined in the header file. .P -NOTE: If the yield of \fBregcomp()\fP is non-zero, you must not attempt to -use the contents of the \fIpreg\fP structure. If, for example, you pass it to -\fBregexec()\fP, the result is undefined and your program is likely to crash. +NOTE: If the yield of \fBpcre2_regcomp()\fP is non-zero, you must not attempt +to use the contents of the \fIpreg\fP structure. If, for example, you pass it +to \fBpcre2_regexec()\fP, the result is undefined and your program is likely to +crash. . . .SH "MATCHING NEWLINE CHARACTERS" @@ -211,7 +213,7 @@ is no way to stop newline from matching [^a]. Default POSIX newline handling can be obtained by setting PCRE2_DOTALL and PCRE2_DOLLAR_ENDONLY when calling \fBpcre2_compile()\fP directly, but there is no way to make PCRE2 behave exactly as for the REG_NEWLINE action. When using -the POSIX API, passing REG_NEWLINE to PCRE2's \fBregcomp()\fP function +the POSIX API, passing REG_NEWLINE to PCRE2's \fBpcre2_regcomp()\fP function causes PCRE2_MULTILINE to be passed to \fBpcre2_compile()\fP, and REG_DOTALL passes PCRE2_DOTALL. There is no way to pass PCRE2_DOLLAR_ENDONLY. . @@ -219,10 +221,10 @@ passes PCRE2_DOTALL. There is no way to pass PCRE2_DOLLAR_ENDONLY. .SH "MATCHING A PATTERN" .rs .sp -The function \fBregexec()\fP is called to match a compiled pattern \fIpreg\fP -against a given \fIstring\fP, which is by default terminated by a zero byte -(but see REG_STARTEND below), subject to the options in \fIeflags\fP. These can -be: +The function \fBpcre2_regexec()\fP is called to match a compiled pattern +\fIpreg\fP against a given \fIstring\fP, which is by default terminated by a +zero byte (but see REG_STARTEND below), subject to the options in \fIeflags\fP. +These can be: .sp REG_NOTBOL .sp @@ -263,7 +265,7 @@ are mutually exclusive; the error REG_INVARG is returned. .P If the pattern was compiled with the REG_NOSUB flag, no data about any matched strings is returned. The \fInmatch\fP and \fIpmatch\fP arguments of -\fBregexec()\fP are ignored (except possibly as input for REG_STARTEND). +\fBpcre2_regexec()\fP are ignored (except possibly as input for REG_STARTEND). .P The value of \fInmatch\fP may be zero, and the value \fIpmatch\fP may be NULL (unless REG_STARTEND is set); in both these cases no data about any matched @@ -286,22 +288,23 @@ header file, of which REG_NOMATCH is the "expected" failure code. .SH "ERROR MESSAGES" .rs .sp -The \fBregerror()\fP function maps a non-zero errorcode from either -\fBregcomp()\fP or \fBregexec()\fP to a printable message. If \fIpreg\fP is not -NULL, the error should have arisen from the use of that structure. A message -terminated by a binary zero is placed in \fIerrbuf\fP. If the buffer is too -short, only the first \fIerrbuf_size\fP - 1 characters of the error message are -used. The yield of the function is the size of buffer needed to hold the whole -message, including the terminating zero. This value is greater than -\fIerrbuf_size\fP if the message was truncated. +The \fBpcre2_regerror()\fP function maps a non-zero errorcode from either +\fBpcre2_regcomp()\fP or \fBpcre2_regexec()\fP to a printable message. If +\fIpreg\fP is not NULL, the error should have arisen from the use of that +structure. A message terminated by a binary zero is placed in \fIerrbuf\fP. If +the buffer is too short, only the first \fIerrbuf_size\fP - 1 characters of the +error message are used. The yield of the function is the size of buffer needed +to hold the whole message, including the terminating zero. This value is +greater than \fIerrbuf_size\fP if the message was truncated. . . .SH MEMORY USAGE .rs .sp Compiling a regular expression causes memory to be allocated and associated -with the \fIpreg\fP structure. The function \fBregfree()\fP frees all such -memory, after which \fIpreg\fP may no longer be used as a compiled expression. +with the \fIpreg\fP structure. The function \fBpcre2_regfree()\fP frees all +such memory, after which \fIpreg\fP may no longer be used as a compiled +expression. . . .SH AUTHOR @@ -318,6 +321,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 19 September 2018 -Copyright (c) 1997-2018 University of Cambridge. +Last updated: 30 January 2019 +Copyright (c) 1997-2019 University of Cambridge. .fi diff --git a/src/pcre2posix.c b/src/pcre2posix.c index 3666100..34a8d80 100644 --- a/src/pcre2posix.c +++ b/src/pcre2posix.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) 2016-2018 University of Cambridge + New API code Copyright (c) 2016-2019 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -41,9 +41,11 @@ POSSIBILITY OF SUCH DAMAGE. /* This module is a wrapper that provides a POSIX API to the underlying PCRE2 functions. The operative functions are called pcre2_regcomp(), etc., with -wrappers that use the plain POSIX names. This makes it easier for an -application to be sure it gets the PCRE2 versions in the presence of other -POSIX regex libraries. */ +wrappers that use the plain POSIX names. In addition, pcre2posix.h defines the +POSIX names as macros for the pcre2_xxx functions, so any program that includes +it and uses the POSIX names will call the base functions directly. This makes +it easier for an application to be sure it gets the PCRE2 versions in the +presence of other POSIX regex libraries. */ #ifdef HAVE_CONFIG_H @@ -177,24 +179,39 @@ static const char *const pstring[] = { * Wrappers with traditional POSIX names * *************************************************/ +/* Keep defining them to preseve the ABI for applications linked to the pcre2 +POSIX library before these names were changed into macros in pcre2posix.h. +This also ensures that the POSIX names are callable from languages that do not +include pcre2posix.h. It is vital to #undef the macro definitions from +pcre2posix.h! */ + +#undef regerror +PCRE2POSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t); PCRE2POSIX_EXP_DEFN size_t PCRE2_CALL_CONVENTION regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) { return pcre2_regerror(errcode, preg, errbuf, errbuf_size); } +#undef regfree +PCRE2POSIX_EXP_DECL void regfree(regex_t *); PCRE2POSIX_EXP_DEFN void PCRE2_CALL_CONVENTION regfree(regex_t *preg) { pcre2_regfree(preg); } +#undef regcomp +PCRE2POSIX_EXP_DECL int regcomp(regex_t *, const char *, int); PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION regcomp(regex_t *preg, const char *pattern, int cflags) { return pcre2_regcomp(preg, pattern, cflags); } +#undef regexec +PCRE2POSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t, + regmatch_t *, int); PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION regexec(const regex_t *preg, const char *string, size_t nmatch, regmatch_t pmatch[], int eflags) @@ -209,7 +226,7 @@ return pcre2_regexec(preg, string, nmatch, pmatch, eflags); *************************************************/ PCRE2POSIX_EXP_DEFN size_t PCRE2_CALL_CONVENTION -pcre2_regerror(int errcode, const regex_t *preg, char *errbuf, +pcre2_regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) { int used; diff --git a/src/pcre2posix.h b/src/pcre2posix.h index bfe347e..cb59d03 100644 --- a/src/pcre2posix.h +++ b/src/pcre2posix.h @@ -9,7 +9,7 @@ POSIX wrapper interface. Written by Philip Hazel Original API code Copyright (c) 1997-2012 University of Cambridge - New API code Copyright (c) 2016-2018 University of Cambridge + New API code Copyright (c) 2016-2019 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -139,22 +139,29 @@ file. */ #endif /* The functions. The actual code is in functions with pcre2_xxx names for -uniqueness. Wrappers with the POSIX names are provided for those who can ensure -they get them from the PCRE2 library and not by accident from elsewhere. */ +uniqueness. POSIX names are provided as macros for API compatibility with POSIX +regex functions. It's done this way to ensure to they are always linked from +the PCRE2 library and not by accident from elsewhere (regex_t differs in size +elsewhere). */ PCRE2POSIX_EXP_DECL int pcre2_regcomp(regex_t *, const char *, int); -PCRE2POSIX_EXP_DECL int regcomp(regex_t *, const char *, int); - PCRE2POSIX_EXP_DECL int pcre2_regexec(const regex_t *, const char *, size_t, regmatch_t *, int); -PCRE2POSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t, - regmatch_t *, int); - PCRE2POSIX_EXP_DECL size_t pcre2_regerror(int, const regex_t *, char *, size_t); -PCRE2POSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t); - PCRE2POSIX_EXP_DECL void pcre2_regfree(regex_t *); -PCRE2POSIX_EXP_DECL void regfree(regex_t *); + +#define regcomp pcre2_regcomp +#define regexec pcre2_regexec +#define regerror pcre2_regerror +#define regfree pcre2_regfree + +/* Debian had a patch that used different names. These are now here to save +them having to maintain their own patch, but are not documented by PCRE2. */ + +#define PCRE2regcomp pcre2_regcomp +#define PCRE2regexec pcre2_regexec +#define PCRE2regerror pcre2_regerror +#define PCRE2regfree pcre2_regfree #ifdef __cplusplus } /* extern "C" */