--- code/trunk/pcreposix.c 2007/02/24 21:39:42 53 +++ code/trunk/pcreposix.c 2007/05/09 14:48:28 166 @@ -2,94 +2,119 @@ * Perl-Compatible Regular Expressions * *************************************************/ -/* -This is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. See -the file Tech.Notes for some information on the internals. +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. -This module is a wrapper that provides a POSIX API to the underlying PCRE -functions. + Written by Philip Hazel + Copyright (c) 1997-2007 University of Cambridge -Written by: Philip Hazel +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: - Copyright (c) 1997-2001 University of Cambridge + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. ------------------------------------------------------------------------------ -Permission is granted to anyone to use this software for any purpose on any -computer system, and to redistribute it freely, subject to the following -restrictions: - -1. This software is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - -2. The origin of this software must not be misrepresented, either by - explicit claim or by omission. - -3. Altered versions must be plainly marked as such, and must not be - misrepresented as being the original software. - -4. If PCRE is embedded in any software that is released under the GNU - General Purpose Licence (GPL), then the terms of that licence shall - supersede any condition above with which it is incompatible. + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. ----------------------------------------------------------------------------- */ -#include "internal.h" + +/* This module is a wrapper that provides a POSIX API to the underlying PCRE +functions. */ + + +#include "pcre_internal.h" #include "pcreposix.h" #include "stdlib.h" -/* Corresponding tables of PCRE error messages and POSIX error codes. */ +/* Table to translate PCRE compile time error codes into POSIX error codes. */ -static const char *estring[] = { - ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, ERR10, - ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19, ERR20, - ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR29, ERR29, ERR30, - ERR31 }; - -static int eint[] = { - REG_EESCAPE, /* "\\ at end of pattern" */ - REG_EESCAPE, /* "\\c at end of pattern" */ - REG_EESCAPE, /* "unrecognized character follows \\" */ - REG_BADBR, /* "numbers out of order in {} quantifier" */ - REG_BADBR, /* "number too big in {} quantifier" */ - REG_EBRACK, /* "missing terminating ] for character class" */ - REG_ECTYPE, /* "invalid escape sequence in character class" */ - REG_ERANGE, /* "range out of order in character class" */ - REG_BADRPT, /* "nothing to repeat" */ - REG_BADRPT, /* "operand of unlimited repeat could match the empty string" */ - REG_ASSERT, /* "internal error: unexpected repeat" */ - REG_BADPAT, /* "unrecognized character after (?" */ - REG_ASSERT, /* "unused error" */ - REG_EPAREN, /* "missing )" */ - REG_ESUBREG, /* "back reference to non-existent subpattern" */ - REG_INVARG, /* "erroffset passed as NULL" */ - REG_INVARG, /* "unknown option bit(s) set" */ - REG_EPAREN, /* "missing ) after comment" */ - REG_ESIZE, /* "parentheses nested too deeply" */ - REG_ESIZE, /* "regular expression too large" */ - REG_ESPACE, /* "failed to get memory" */ - REG_EPAREN, /* "unmatched brackets" */ - REG_ASSERT, /* "internal error: code overflow" */ - REG_BADPAT, /* "unrecognized character after (?<" */ - REG_BADPAT, /* "lookbehind assertion is not fixed length" */ - REG_BADPAT, /* "malformed number after (?(" */ - REG_BADPAT, /* "conditional group containe more than two branches" */ - REG_BADPAT, /* "assertion expected after (?(" */ - REG_BADPAT, /* "(?p must be followed by )" */ - REG_ECTYPE, /* "unknown POSIX class name" */ - REG_BADPAT, /* "POSIX collating elements are not supported" */ - REG_INVARG, /* "this version of PCRE is not compiled with PCRE_UTF8 support" */ - REG_BADPAT, /* "characters with values > 255 are not yet supported in classes" */ - REG_BADPAT, /* "character value in \x{...} sequence is too large" */ - REG_BADPAT /* "invalid condition (?(0)" */ +static const int eint[] = { + 0, /* no error */ + REG_EESCAPE, /* \ at end of pattern */ + REG_EESCAPE, /* \c at end of pattern */ + REG_EESCAPE, /* unrecognized character follows \ */ + REG_BADBR, /* numbers out of order in {} quantifier */ + REG_BADBR, /* number too big in {} quantifier */ + REG_EBRACK, /* missing terminating ] for character class */ + REG_ECTYPE, /* invalid escape sequence in character class */ + REG_ERANGE, /* range out of order in character class */ + REG_BADRPT, /* nothing to repeat */ + REG_BADRPT, /* operand of unlimited repeat could match the empty string */ + REG_ASSERT, /* internal error: unexpected repeat */ + REG_BADPAT, /* unrecognized character after (? */ + REG_BADPAT, /* POSIX named classes are supported only within a class */ + REG_EPAREN, /* missing ) */ + REG_ESUBREG, /* reference to non-existent subpattern */ + REG_INVARG, /* erroffset passed as NULL */ + REG_INVARG, /* unknown option bit(s) set */ + REG_EPAREN, /* missing ) after comment */ + REG_ESIZE, /* parentheses nested too deeply */ + REG_ESIZE, /* regular expression too large */ + REG_ESPACE, /* failed to get memory */ + REG_EPAREN, /* unmatched brackets */ + REG_ASSERT, /* internal error: code overflow */ + REG_BADPAT, /* unrecognized character after (?< */ + REG_BADPAT, /* lookbehind assertion is not fixed length */ + REG_BADPAT, /* malformed number or name after (?( */ + REG_BADPAT, /* conditional group contains more than two branches */ + REG_BADPAT, /* assertion expected after (?( */ + REG_BADPAT, /* (?R or (?[+-]digits must be followed by ) */ + REG_ECTYPE, /* unknown POSIX class name */ + REG_BADPAT, /* POSIX collating elements are not supported */ + REG_INVARG, /* this version of PCRE is not compiled with PCRE_UTF8 support */ + REG_BADPAT, /* spare error */ + REG_BADPAT, /* character value in \x{...} sequence is too large */ + REG_BADPAT, /* invalid condition (?(0) */ + REG_BADPAT, /* \C not allowed in lookbehind assertion */ + REG_EESCAPE, /* PCRE does not support \L, \l, \N, \U, or \u */ + REG_BADPAT, /* number after (?C is > 255 */ + REG_BADPAT, /* closing ) for (?C expected */ + REG_BADPAT, /* recursive call could loop indefinitely */ + REG_BADPAT, /* unrecognized character after (?P */ + REG_BADPAT, /* syntax error in subpattern name (missing terminator) */ + REG_BADPAT, /* two named subpatterns have the same name */ + REG_BADPAT, /* invalid UTF-8 string */ + REG_BADPAT, /* support for \P, \p, and \X has not been compiled */ + REG_BADPAT, /* malformed \P or \p sequence */ + REG_BADPAT, /* unknown property name after \P or \p */ + REG_BADPAT, /* subpattern name is too long (maximum 32 characters) */ + REG_BADPAT, /* too many named subpatterns (maximum 10,000) */ + REG_BADPAT, /* repeated subpattern is too long */ + REG_BADPAT, /* octal value is greater than \377 (not in UTF-8 mode) */ + REG_BADPAT, /* internal error: overran compiling workspace */ + REG_BADPAT, /* internal error: previously-checked referenced subpattern not found */ + REG_BADPAT, /* DEFINE group contains more than one branch */ + REG_BADPAT, /* repeating a DEFINE group is not allowed */ + REG_INVARG, /* inconsistent NEWLINE options */ + REG_BADPAT, /* \g is not followed followed by an (optionally braced) non-zero number */ + REG_BADPAT /* (?+ or (?- must be followed by a non-zero number */ }; /* Table of texts corresponding to POSIX error codes */ -static const char *pstring[] = { +static const char *const pstring[] = { "", /* Dummy for value 0 */ "internal error", /* REG_ASSERT */ "invalid repeat counts in {}", /* BADBR */ @@ -114,28 +139,10 @@ /************************************************* -* Translate PCRE text code to int * -*************************************************/ - -/* PCRE compile-time errors are given as strings defined as macros. We can just -look them up in a table to turn them into POSIX-style error codes. */ - -static int -pcre_posix_error_code(const char *s) -{ -size_t i; -for (i = 0; i < sizeof(estring)/sizeof(char *); i++) - if (strcmp(s, estring[i]) == 0) return eint[i]; -return REG_ASSERT; -} - - - -/************************************************* * Translate error code to string * *************************************************/ -size_t +PCREPOSIX_EXP_DEFN size_t regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) { const char *message, *addmessage; @@ -170,7 +177,7 @@ * Free store held by a regex * *************************************************/ -void +PCREPOSIX_EXP_DEFN void regfree(regex_t *preg) { (pcre_free)(preg->re_pcre); @@ -193,22 +200,27 @@ various non-zero codes on failure */ -int +PCREPOSIX_EXP_DEFN int regcomp(regex_t *preg, const char *pattern, int cflags) { const char *errorptr; int erroffset; +int errorcode; int options = 0; -if ((cflags & REG_ICASE) != 0) options |= PCRE_CASELESS; +if ((cflags & REG_ICASE) != 0) options |= PCRE_CASELESS; if ((cflags & REG_NEWLINE) != 0) options |= PCRE_MULTILINE; +if ((cflags & REG_DOTALL) != 0) options |= PCRE_DOTALL; +if ((cflags & REG_NOSUB) != 0) options |= PCRE_NO_AUTO_CAPTURE; +if ((cflags & REG_UTF8) != 0) options |= PCRE_UTF8; -preg->re_pcre = pcre_compile(pattern, options, &errorptr, &erroffset, NULL); +preg->re_pcre = pcre_compile2(pattern, options, &errorcode, &errorptr, + &erroffset, NULL); preg->re_erroffset = erroffset; -if (preg->re_pcre == NULL) return pcre_posix_error_code(errorptr); +if (preg->re_pcre == NULL) return eint[errorcode]; -preg->re_nsub = pcre_info(preg->re_pcre, NULL, NULL); +preg->re_nsub = pcre_info((const pcre *)preg->re_pcre, NULL, NULL); return 0; } @@ -222,48 +234,75 @@ /* Unfortunately, PCRE requires 3 ints of working space for each captured substring, so we have to get and release working store instead of just using the POSIX structures as was done in earlier releases when PCRE needed only 2 -ints. */ +ints. However, if the number of possible capturing brackets is small, use a +block of store on the stack, to reduce the use of malloc/free. The threshold is +in a macro that can be changed at configure time. + +If REG_NOSUB was specified at compile time, the PCRE_NO_AUTO_CAPTURE flag will +be set. When this is the case, the nmatch and pmatch arguments are ignored, and +the only result is yes/no/error. */ -int -regexec(regex_t *preg, const char *string, size_t nmatch, +PCREPOSIX_EXP_DEFN int +regexec(const regex_t *preg, const char *string, size_t nmatch, regmatch_t pmatch[], int eflags) { int rc; int options = 0; int *ovector = NULL; +int small_ovector[POSIX_MALLOC_THRESHOLD * 3]; +BOOL allocated_ovector = FALSE; +BOOL nosub = + (((const pcre *)preg->re_pcre)->options & PCRE_NO_AUTO_CAPTURE) != 0; if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL; if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL; -preg->re_erroffset = (size_t)(-1); /* Only has meaning after compile */ +((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */ + +/* When no string data is being returned, ensure that nmatch is zero. +Otherwise, ensure the vector for holding the return data is large enough. */ + +if (nosub) nmatch = 0; -if (nmatch > 0) +else if (nmatch > 0) { - ovector = (int *)malloc(sizeof(int) * nmatch * 3); - if (ovector == NULL) return REG_ESPACE; + if (nmatch <= POSIX_MALLOC_THRESHOLD) + { + ovector = &(small_ovector[0]); + } + else + { + if (nmatch > INT_MAX/(sizeof(int) * 3)) return REG_ESPACE; + ovector = (int *)malloc(sizeof(int) * nmatch * 3); + if (ovector == NULL) return REG_ESPACE; + allocated_ovector = TRUE; + } } -rc = pcre_exec(preg->re_pcre, NULL, string, (int)strlen(string), 0, options, - ovector, nmatch * 3); +rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string, (int)strlen(string), + 0, options, ovector, nmatch * 3); if (rc == 0) rc = nmatch; /* All captured slots were filled in */ if (rc >= 0) { size_t i; - for (i = 0; i < rc; i++) + if (!nosub) { - pmatch[i].rm_so = ovector[i*2]; - pmatch[i].rm_eo = ovector[i*2+1]; + for (i = 0; i < (size_t)rc; i++) + { + pmatch[i].rm_so = ovector[i*2]; + pmatch[i].rm_eo = ovector[i*2+1]; + } + if (allocated_ovector) free(ovector); + for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; } - if (ovector != NULL) free(ovector); - for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; return 0; } else { - if (ovector != NULL) free(ovector); + if (allocated_ovector) free(ovector); switch(rc) { case PCRE_ERROR_NOMATCH: return REG_NOMATCH; @@ -272,6 +311,9 @@ case PCRE_ERROR_BADMAGIC: return REG_INVARG; case PCRE_ERROR_UNKNOWN_NODE: return REG_ASSERT; case PCRE_ERROR_NOMEMORY: return REG_ESPACE; + case PCRE_ERROR_MATCHLIMIT: return REG_ESPACE; + case PCRE_ERROR_BADUTF8: return REG_INVARG; + case PCRE_ERROR_BADUTF8_OFFSET: return REG_INVARG; default: return REG_ASSERT; } }