1 /* 2 * Copyright (c) 2001-2009 Ville Laurikari <vl@iki.fi> 3 * All rights reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 8 * 9 * 1. Redistributions of source code must retain the above copyright 10 * notice, this list of conditions and the following disclaimer. 11 * 12 * 2. Redistributions in binary form must reproduce the above copyright 13 * notice, this list of conditions and the following disclaimer in the 14 * documentation and/or other materials provided with the distribution. 15 * 16 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS 17 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 18 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 19 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 20 * HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 21 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 22 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 23 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 24 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 25 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 26 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 27 * 28 */ 29 30 #ifndef _REGEX_H_ 31 #define _REGEX_H_ 32 33 #include <sys/cdefs.h> 34 #include <sys/types.h> 35 #include <wchar.h> 36 #include <xlocale.h> 37 38 #define tre_regcomp regcomp 39 #define tre_regexec regexec 40 #define tre_regerror regerror 41 #define tre_regfree regfree 42 43 #define tre_regwcomp regwcomp 44 #define tre_regwexec regwexec 45 #define tre_regncomp regncomp 46 #define tre_regnexec regnexec 47 #define tre_regnwcomp regnwcomp 48 #define tre_regnwexec regnwexec 49 50 typedef enum { 51 REG_OK = 0, /* No error. */ 52 REG_NOMATCH, /* No match. */ 53 REG_BADPAT, /* Invalid regexp. */ 54 REG_ECOLLATE, /* Unknown collating element. */ 55 REG_ECTYPE, /* Unknown character class name. */ 56 REG_EESCAPE, /* Trailing backslash. */ 57 REG_ESUBREG, /* Invalid back reference. */ 58 REG_EBRACK, /* "[]" imbalance */ 59 REG_EPAREN, /* "\(\)" or "()" imbalance */ 60 REG_EBRACE, /* "\{\}" or "{}" imbalance */ 61 REG_BADBR, /* Invalid content of {} */ 62 REG_ERANGE, /* Invalid use of range operator */ 63 REG_ESPACE, /* Out of memory. */ 64 REG_BADRPT, /* Invalid use of repetition operators. */ 65 REG_EMPTY, /* rexexp was zero-length string */ 66 REG_INVARG, /* invalid argument to regex routine */ 67 REG_ILLSEQ /* illegal byte sequence */ 68 } reg_errcode_t; 69 70 enum { 71 TRE_CONFIG_APPROX, 72 TRE_CONFIG_WCHAR, 73 TRE_CONFIG_MULTIBYTE, 74 TRE_CONFIG_SYSTEM_ABI, 75 TRE_CONFIG_VERSION 76 }; 77 78 typedef int regoff_t; 79 typedef wchar_t tre_char_t; 80 81 typedef struct { 82 int re_magic; 83 size_t re_nsub; /* Number of parenthesized subexpressions. */ 84 const void *re_endp; /* regex string end pointer (REG_PEND) */ 85 void *value; /* For internal use only. */ 86 } regex_t; 87 88 typedef struct { 89 regoff_t rm_so; 90 regoff_t rm_eo; 91 } regmatch_t; 92 93 /* Approximate matching parameter struct. */ 94 typedef struct { 95 int cost_ins; /* Default cost of an inserted character. */ 96 int cost_del; /* Default cost of a deleted character. */ 97 int cost_subst; /* Default cost of a substituted character. */ 98 int max_cost; /* Maximum allowed cost of a match. */ 99 100 int max_ins; /* Maximum allowed number of inserts. */ 101 int max_del; /* Maximum allowed number of deletes. */ 102 int max_subst; /* Maximum allowed number of substitutes. */ 103 int max_err; /* Maximum allowed number of errors total. */ 104 } regaparams_t; 105 106 /* Approximate matching result struct. */ 107 typedef struct { 108 size_t nmatch; /* Length of pmatch[] array. */ 109 regmatch_t *pmatch; /* Submatch data. */ 110 int cost; /* Cost of the match. */ 111 int num_ins; /* Number of inserts in the match. */ 112 int num_del; /* Number of deletes in the match. */ 113 int num_subst; /* Number of substitutes in the match. */ 114 } regamatch_t; 115 116 typedef struct { 117 int (*get_next_char)(tre_char_t *c, unsigned int *pos_add, void *context); 118 void (*rewind)(size_t pos, void *context); 119 int (*compare)(size_t pos1, size_t pos2, size_t len, void *context); 120 void *context; 121 } tre_str_source; 122 123 /* POSIX tre_regcomp() flags. */ 124 #define REG_EXTENDED 1 125 #define REG_ICASE (REG_EXTENDED << 1) 126 #define REG_NEWLINE (REG_ICASE << 1) 127 #define REG_NOSUB (REG_NEWLINE << 1) 128 129 /* Extra tre_regcomp() flags. */ 130 #define REG_BASIC 0 131 #define REG_LITERAL (REG_NOSUB << 1) 132 #define REG_RIGHT_ASSOC (REG_LITERAL << 1) 133 #define REG_UNGREEDY (REG_RIGHT_ASSOC << 1) 134 #define REG_PEND (REG_UNGREEDY << 1) 135 #define REG_ENHANCED (REG_PEND << 1) 136 137 /* alias regcomp flags. */ 138 #define REG_NOSPEC REG_LITERAL 139 #define REG_MINIMAL REG_UNGREEDY 140 141 /* POSIX tre_regexec() flags. */ 142 #define REG_NOTBOL 1 143 #define REG_NOTEOL (REG_NOTBOL << 1) 144 #define REG_STARTEND (REG_NOTEOL << 1) 145 #define REG_BACKR (REG_STARTEND << 1) 146 147 /* Extra tre_regexec() flags. */ 148 #define REG_APPROX_MATCHER (REG_NOTEOL << 1) 149 #define REG_BACKTRACKING_MATCHER (REG_APPROX_MATCHER << 1) 150 151 /* The maximum number of iterations in a bound expression. */ 152 #define RE_DUP_MAX 255 153 154 #define _REG_nexec 1 155 156 __BEGIN_DECLS 157 158 /* The POSIX.2 regexp functions */ 159 int 160 tre_regcomp(regex_t *preg, const char *regex, int cflags); 161 162 int 163 tre_regexec(const regex_t *preg, const char *string, size_t nmatch, 164 regmatch_t pmatch[], int eflags); 165 166 size_t 167 tre_regerror(int errcode, const regex_t *preg, char *errbuf, 168 size_t errbuf_size); 169 170 void 171 tre_regfree(regex_t *preg); 172 173 /* Wide character versions (not in POSIX.2). */ 174 int 175 tre_regwcomp(regex_t *preg, const wchar_t *regex, int cflags); 176 177 int 178 tre_regwexec(const regex_t *preg, const wchar_t *string, 179 size_t nmatch, regmatch_t pmatch[], int eflags); 180 181 /* Versions with a maximum length argument and therefore the capability to 182 handle null characters in the middle of the strings (not in POSIX.2). */ 183 int 184 tre_regncomp(regex_t *preg, const char *regex, size_t len, int cflags); 185 186 int 187 tre_regnexec(const regex_t *preg, const char *string, size_t len, 188 size_t nmatch, regmatch_t pmatch[], int eflags); 189 190 int 191 tre_regwncomp(regex_t *preg, const wchar_t *regex, size_t len, int cflags); 192 193 int 194 tre_regwnexec(const regex_t *preg, const wchar_t *string, size_t len, 195 size_t nmatch, regmatch_t pmatch[], int eflags); 196 197 /* Returns the version string. The returned string is static. */ 198 char * 199 tre_version(void); 200 201 /* Returns the value for a config parameter. The type to which `result' 202 must point to depends of the value of `query', see documentation for 203 more details. */ 204 int 205 tre_config(int query, void *result); 206 207 /* Returns 1 if the compiled pattern has back references, 0 if not. */ 208 int 209 tre_have_backrefs(const regex_t *preg); 210 211 /* Returns 1 if the compiled pattern uses approximate matching features, 212 0 if not. */ 213 int 214 tre_have_approx(const regex_t *preg); 215 __END_DECLS 216 217 /* The POSIX.2 regexp functions, locale version */ 218 int 219 tre_regcomp_l(regex_t *preg, const char *regex, int cflags, locale_t locale); 220 221 int 222 tre_regncomp_l(regex_t *preg, const char *regex, size_t len, int cflags, 223 locale_t locale); 224 225 int 226 tre_regwcomp_l(regex_t *preg, const wchar_t *regex, int cflags, 227 locale_t locale); 228 229 int 230 tre_regwncomp_l(regex_t *preg, const wchar_t *regex, size_t len, int cflags, 231 locale_t locale); 232 233 #endif /* !_REGEX_H_ */ 234