haproxy/include/common/regex.h

159 lines
4.9 KiB
C
Raw Normal View History

/*
* include/common/regex.h
* This file defines everything related to regular expressions.
*
* Copyright (C) 2000-2010 Willy Tarreau - w@1wt.eu
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation, version 2.1
* exclusively.
*
* This library 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. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef _COMMON_REGEX_H
#define _COMMON_REGEX_H
#include <stdlib.h>
#include <string.h>
#include <common/config.h>
#ifdef USE_PCRE
#include <pcre.h>
#include <pcreposix.h>
MEDIUM: regex: Use pcre_study always when PCRE is used, regardless of JIT pcre_study() has been around long before JIT has been added. It also seems to affect the performance in some cases (positive). Below I've attached some test restults. The test is based on http://sljit.sourceforge.net/regex_perf.html (see bottom). It has been modified to just test pcre_study vs. no pcre_study. Note: This test does not try to match specific header it's instead run over a larger text with more and less complex patterns to make the differences more clear. % ./runtest 'mark.txt' loaded. (Length: 19665221 bytes) ----------------- Regex: 'Twain' [pcre-nostudy] time: 14 ms (2388 matches) [pcre-study] time: 21 ms (2388 matches) ----------------- Regex: '^Twain' [pcre-nostudy] time: 109 ms (100 matches) [pcre-study] time: 109 ms (100 matches) ----------------- Regex: 'Twain$' [pcre-nostudy] time: 14 ms (127 matches) [pcre-study] time: 16 ms (127 matches) ----------------- Regex: 'Huck[a-zA-Z]+|Finn[a-zA-Z]+' [pcre-nostudy] time: 695 ms (83 matches) [pcre-study] time: 26 ms (83 matches) ----------------- Regex: 'a[^x]{20}b' [pcre-nostudy] time: 90 ms (12495 matches) [pcre-study] time: 91 ms (12495 matches) ----------------- Regex: 'Tom|Sawyer|Huckleberry|Finn' [pcre-nostudy] time: 1236 ms (3015 matches) [pcre-study] time: 34 ms (3015 matches) ----------------- Regex: '.{0,3}(Tom|Sawyer|Huckleberry|Finn)' [pcre-nostudy] time: 5696 ms (3015 matches) [pcre-study] time: 5655 ms (3015 matches) ----------------- Regex: '[a-zA-Z]+ing' [pcre-nostudy] time: 1290 ms (95863 matches) [pcre-study] time: 1167 ms (95863 matches) ----------------- Regex: '^[a-zA-Z]{0,4}ing[^a-zA-Z]' [pcre-nostudy] time: 136 ms (4507 matches) [pcre-study] time: 134 ms (4507 matches) ----------------- Regex: '[a-zA-Z]+ing$' [pcre-nostudy] time: 1334 ms (5360 matches) [pcre-study] time: 1214 ms (5360 matches) ----------------- Regex: '^[a-zA-Z ]{5,}$' [pcre-nostudy] time: 198 ms (26236 matches) [pcre-study] time: 197 ms (26236 matches) ----------------- Regex: '^.{16,20}$' [pcre-nostudy] time: 173 ms (4902 matches) [pcre-study] time: 175 ms (4902 matches) ----------------- Regex: '([a-f](.[d-m].){0,2}[h-n]){2}' [pcre-nostudy] time: 1242 ms (68621 matches) [pcre-study] time: 690 ms (68621 matches) ----------------- Regex: '([A-Za-z]awyer|[A-Za-z]inn)[^a-zA-Z]' [pcre-nostudy] time: 1215 ms (675 matches) [pcre-study] time: 952 ms (675 matches) ----------------- Regex: '"[^"]{0,30}[?!\.]"' [pcre-nostudy] time: 27 ms (5972 matches) [pcre-study] time: 28 ms (5972 matches) ----------------- Regex: 'Tom.{10,25}river|river.{10,25}Tom' [pcre-nostudy] time: 705 ms (2 matches) [pcre-study] time: 68 ms (2 matches) In some cases it's more or less the same but when it's faster than by a huge margin. It always depends on the pattern, the string(s) to match against etc. Signed-off-by: Christian Ruppert <c.ruppert@babiel.com>
2014-11-18 12:03:58 +00:00
/* For pre-8.20 PCRE compatibility */
#ifndef PCRE_STUDY_JIT_COMPILE
#define PCRE_STUDY_JIT_COMPILE 0
#endif
#else /* no PCRE */
#include <regex.h>
#endif
struct my_regex {
#ifdef USE_PCRE
pcre *reg;
pcre_extra *extra;
#ifdef USE_PCRE_JIT
#ifndef PCRE_CONFIG_JIT
#error "The PCRE lib doesn't support JIT. Change your lib, or remove the option USE_PCRE_JIT."
#endif
#endif
#else /* no PCRE */
regex_t regex;
#endif
};
/* what to do when a header matches a regex */
#define ACT_ALLOW 0 /* allow the request */
#define ACT_REPLACE 1 /* replace the matching header */
#define ACT_REMOVE 2 /* remove the matching header */
#define ACT_DENY 3 /* deny the request */
#define ACT_PASS 4 /* pass this header without allowing or denying the request */
#define ACT_TARPIT 5 /* tarpit the connection matching this request */
struct hdr_exp {
struct hdr_exp *next;
struct my_regex *preg; /* expression to look for */
int action; /* ACT_ALLOW, ACT_REPLACE, ACT_REMOVE, ACT_DENY */
const char *replace; /* expression to set instead */
void *cond; /* a possible condition or NULL */
};
extern regmatch_t pmatch[MAX_MATCH];
/* "str" is the string that contain the regex to compile.
* "regex" is preallocated memory. After the execution of this function, this
* struct contain the compiled regex.
* "cs" is the case sensitive flag. If cs is true, case sensitive is enabled.
* "cap" is capture flag. If cap if true the regex can capture into
* parenthesis strings.
* "err" is the standar error message pointer.
*
* The function return 1 is succes case, else return 0 and err is filled.
*/
int regex_comp(const char *str, struct my_regex *regex, int cs, int cap, char **err);
int exp_replace(char *dst, unsigned int dst_size, char *src, const char *str, const regmatch_t *matches);
const char *check_replace_string(const char *str);
const char *chain_regex(struct hdr_exp **head, struct my_regex *preg,
int action, const char *replace, void *cond);
/* If the function doesn't match, it returns false, else it returns true.
*/
static inline int regex_exec(const struct my_regex *preg, char *subject) {
#if defined(USE_PCRE) || defined(USE_PCRE_JIT)
if (pcre_exec(preg->reg, preg->extra, subject, strlen(subject), 0, 0, NULL, 0) < 0)
return 0;
return 1;
#else
int match;
match = regexec(&preg->regex, subject, 0, NULL, 0);
if (match == REG_NOMATCH)
return 0;
return 1;
#endif
}
/* Note that <subject> MUST be at least <length+1> characters long and must
* be writable because the function will temporarily force a zero past the
* last character.
*
* If the function doesn't match, it returns false, else it returns true.
*/
static inline int regex_exec2(const struct my_regex *preg, char *subject, int length) {
#if defined(USE_PCRE) || defined(USE_PCRE_JIT)
if (pcre_exec(preg->reg, preg->extra, subject, length, 0, 0, NULL, 0) < 0)
return 0;
return 1;
#else
int match;
char old_char = subject[length];
subject[length] = 0;
match = regexec(&preg->regex, subject, 0, NULL, 0);
subject[length] = old_char;
if (match == REG_NOMATCH)
return 0;
return 1;
#endif
}
int regex_exec_match(const struct my_regex *preg, const char *subject,
size_t nmatch, regmatch_t pmatch[], int flags);
int regex_exec_match2(const struct my_regex *preg, char *subject, int length,
size_t nmatch, regmatch_t pmatch[], int flags);
static inline void regex_free(struct my_regex *preg) {
#if defined(USE_PCRE) || defined(USE_PCRE_JIT)
pcre_free(preg->reg);
MEDIUM: regex: Use pcre_study always when PCRE is used, regardless of JIT pcre_study() has been around long before JIT has been added. It also seems to affect the performance in some cases (positive). Below I've attached some test restults. The test is based on http://sljit.sourceforge.net/regex_perf.html (see bottom). It has been modified to just test pcre_study vs. no pcre_study. Note: This test does not try to match specific header it's instead run over a larger text with more and less complex patterns to make the differences more clear. % ./runtest 'mark.txt' loaded. (Length: 19665221 bytes) ----------------- Regex: 'Twain' [pcre-nostudy] time: 14 ms (2388 matches) [pcre-study] time: 21 ms (2388 matches) ----------------- Regex: '^Twain' [pcre-nostudy] time: 109 ms (100 matches) [pcre-study] time: 109 ms (100 matches) ----------------- Regex: 'Twain$' [pcre-nostudy] time: 14 ms (127 matches) [pcre-study] time: 16 ms (127 matches) ----------------- Regex: 'Huck[a-zA-Z]+|Finn[a-zA-Z]+' [pcre-nostudy] time: 695 ms (83 matches) [pcre-study] time: 26 ms (83 matches) ----------------- Regex: 'a[^x]{20}b' [pcre-nostudy] time: 90 ms (12495 matches) [pcre-study] time: 91 ms (12495 matches) ----------------- Regex: 'Tom|Sawyer|Huckleberry|Finn' [pcre-nostudy] time: 1236 ms (3015 matches) [pcre-study] time: 34 ms (3015 matches) ----------------- Regex: '.{0,3}(Tom|Sawyer|Huckleberry|Finn)' [pcre-nostudy] time: 5696 ms (3015 matches) [pcre-study] time: 5655 ms (3015 matches) ----------------- Regex: '[a-zA-Z]+ing' [pcre-nostudy] time: 1290 ms (95863 matches) [pcre-study] time: 1167 ms (95863 matches) ----------------- Regex: '^[a-zA-Z]{0,4}ing[^a-zA-Z]' [pcre-nostudy] time: 136 ms (4507 matches) [pcre-study] time: 134 ms (4507 matches) ----------------- Regex: '[a-zA-Z]+ing$' [pcre-nostudy] time: 1334 ms (5360 matches) [pcre-study] time: 1214 ms (5360 matches) ----------------- Regex: '^[a-zA-Z ]{5,}$' [pcre-nostudy] time: 198 ms (26236 matches) [pcre-study] time: 197 ms (26236 matches) ----------------- Regex: '^.{16,20}$' [pcre-nostudy] time: 173 ms (4902 matches) [pcre-study] time: 175 ms (4902 matches) ----------------- Regex: '([a-f](.[d-m].){0,2}[h-n]){2}' [pcre-nostudy] time: 1242 ms (68621 matches) [pcre-study] time: 690 ms (68621 matches) ----------------- Regex: '([A-Za-z]awyer|[A-Za-z]inn)[^a-zA-Z]' [pcre-nostudy] time: 1215 ms (675 matches) [pcre-study] time: 952 ms (675 matches) ----------------- Regex: '"[^"]{0,30}[?!\.]"' [pcre-nostudy] time: 27 ms (5972 matches) [pcre-study] time: 28 ms (5972 matches) ----------------- Regex: 'Tom.{10,25}river|river.{10,25}Tom' [pcre-nostudy] time: 705 ms (2 matches) [pcre-study] time: 68 ms (2 matches) In some cases it's more or less the same but when it's faster than by a huge margin. It always depends on the pattern, the string(s) to match against etc. Signed-off-by: Christian Ruppert <c.ruppert@babiel.com>
2014-11-18 12:03:58 +00:00
/* PCRE < 8.20 requires pcre_free() while >= 8.20 requires pcre_study_free(),
* which is easily detected using PCRE_CONFIG_JIT.
*/
#ifdef PCRE_CONFIG_JIT
pcre_free_study(preg->extra);
MEDIUM: regex: Use pcre_study always when PCRE is used, regardless of JIT pcre_study() has been around long before JIT has been added. It also seems to affect the performance in some cases (positive). Below I've attached some test restults. The test is based on http://sljit.sourceforge.net/regex_perf.html (see bottom). It has been modified to just test pcre_study vs. no pcre_study. Note: This test does not try to match specific header it's instead run over a larger text with more and less complex patterns to make the differences more clear. % ./runtest 'mark.txt' loaded. (Length: 19665221 bytes) ----------------- Regex: 'Twain' [pcre-nostudy] time: 14 ms (2388 matches) [pcre-study] time: 21 ms (2388 matches) ----------------- Regex: '^Twain' [pcre-nostudy] time: 109 ms (100 matches) [pcre-study] time: 109 ms (100 matches) ----------------- Regex: 'Twain$' [pcre-nostudy] time: 14 ms (127 matches) [pcre-study] time: 16 ms (127 matches) ----------------- Regex: 'Huck[a-zA-Z]+|Finn[a-zA-Z]+' [pcre-nostudy] time: 695 ms (83 matches) [pcre-study] time: 26 ms (83 matches) ----------------- Regex: 'a[^x]{20}b' [pcre-nostudy] time: 90 ms (12495 matches) [pcre-study] time: 91 ms (12495 matches) ----------------- Regex: 'Tom|Sawyer|Huckleberry|Finn' [pcre-nostudy] time: 1236 ms (3015 matches) [pcre-study] time: 34 ms (3015 matches) ----------------- Regex: '.{0,3}(Tom|Sawyer|Huckleberry|Finn)' [pcre-nostudy] time: 5696 ms (3015 matches) [pcre-study] time: 5655 ms (3015 matches) ----------------- Regex: '[a-zA-Z]+ing' [pcre-nostudy] time: 1290 ms (95863 matches) [pcre-study] time: 1167 ms (95863 matches) ----------------- Regex: '^[a-zA-Z]{0,4}ing[^a-zA-Z]' [pcre-nostudy] time: 136 ms (4507 matches) [pcre-study] time: 134 ms (4507 matches) ----------------- Regex: '[a-zA-Z]+ing$' [pcre-nostudy] time: 1334 ms (5360 matches) [pcre-study] time: 1214 ms (5360 matches) ----------------- Regex: '^[a-zA-Z ]{5,}$' [pcre-nostudy] time: 198 ms (26236 matches) [pcre-study] time: 197 ms (26236 matches) ----------------- Regex: '^.{16,20}$' [pcre-nostudy] time: 173 ms (4902 matches) [pcre-study] time: 175 ms (4902 matches) ----------------- Regex: '([a-f](.[d-m].){0,2}[h-n]){2}' [pcre-nostudy] time: 1242 ms (68621 matches) [pcre-study] time: 690 ms (68621 matches) ----------------- Regex: '([A-Za-z]awyer|[A-Za-z]inn)[^a-zA-Z]' [pcre-nostudy] time: 1215 ms (675 matches) [pcre-study] time: 952 ms (675 matches) ----------------- Regex: '"[^"]{0,30}[?!\.]"' [pcre-nostudy] time: 27 ms (5972 matches) [pcre-study] time: 28 ms (5972 matches) ----------------- Regex: 'Tom.{10,25}river|river.{10,25}Tom' [pcre-nostudy] time: 705 ms (2 matches) [pcre-study] time: 68 ms (2 matches) In some cases it's more or less the same but when it's faster than by a huge margin. It always depends on the pattern, the string(s) to match against etc. Signed-off-by: Christian Ruppert <c.ruppert@babiel.com>
2014-11-18 12:03:58 +00:00
#else /* PCRE_CONFIG_JIT */
pcre_free(preg->extra);
#endif /* PCRE_CONFIG_JIT */
#else
regfree(&preg->regex);
#endif
}
#endif /* _COMMON_REGEX_H */
/*
* Local variables:
* c-indent-level: 8
* c-basic-offset: 8
* End:
*/