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 37 #define tre_regcomp regcomp 38 #define tre_regexec regexec 39 #define tre_regerror regerror 40 #define tre_regfree regfree 41 42 #define tre_regwcomp regwcomp 43 #define tre_regwexec regwexec 44 #define tre_regncomp regncomp 45 #define tre_regnexec regnexec 46 #define tre_regnwcomp regnwcomp 47 #define tre_regnwexec regnwexec 48 49 typedef enum { 50 REG_OK = 0, /* No error. */ 51 REG_NOMATCH, /* No match. */ 52 REG_BADPAT, /* Invalid regexp. */ 53 REG_ECOLLATE, /* Unknown collating element. */ 54 REG_ECTYPE, /* Unknown character class name. */ 55 REG_EESCAPE, /* Trailing backslash. */ 56 REG_ESUBREG, /* Invalid back reference. */ 57 REG_EBRACK, /* "[]" imbalance */ 58 REG_EPAREN, /* "\(\)" or "()" imbalance */ 59 REG_EBRACE, /* "\{\}" or "{}" imbalance */ 60 REG_BADBR, /* Invalid content of {} */ 61 REG_ERANGE, /* Invalid use of range operator */ 62 REG_ESPACE, /* Out of memory. */ 63 REG_BADRPT, /* Invalid use of repetition operators. */ 64 REG_EMPTY, /* rexexp was zero-length string */ 65 REG_INVARG, /* invalid argument to regex routine */ 66 REG_ILLSEQ /* illegal byte sequence */ 67 } reg_errcode_t; 68 69 enum { 70 TRE_CONFIG_APPROX, 71 TRE_CONFIG_WCHAR, 72 TRE_CONFIG_MULTIBYTE, 73 TRE_CONFIG_SYSTEM_ABI, 74 TRE_CONFIG_VERSION 75 }; 76 77 typedef int regoff_t; 78 typedef wchar_t tre_char_t; 79 80 typedef struct { 81 int re_magic; 82 size_t re_nsub; /* Number of parenthesized subexpressions. */ 83 const void *re_endp; /* regex string end pointer (REG_PEND) */ 84 void *value; /* For internal use only. */ 85 } regex_t; 86 87 typedef struct { 88 regoff_t rm_so; 89 regoff_t rm_eo; 90 } regmatch_t; 91 92 /* Approximate matching parameter struct. */ 93 typedef struct { 94 int cost_ins; /* Default cost of an inserted character. */ 95 int cost_del; /* Default cost of a deleted character. */ 96 int cost_subst; /* Default cost of a substituted character. */ 97 int max_cost; /* Maximum allowed cost of a match. */ 98 99 int max_ins; /* Maximum allowed number of inserts. */ 100 int max_del; /* Maximum allowed number of deletes. */ 101 int max_subst; /* Maximum allowed number of substitutes. */ 102 int max_err; /* Maximum allowed number of errors total. */ 103 } regaparams_t; 104 105 /* Approximate matching result struct. */ 106 typedef struct { 107 size_t nmatch; /* Length of pmatch[] array. */ 108 regmatch_t *pmatch; /* Submatch data. */ 109 int cost; /* Cost of the match. */ 110 int num_ins; /* Number of inserts in the match. */ 111 int num_del; /* Number of deletes in the match. */ 112 int num_subst; /* Number of substitutes in the match. */ 113 } regamatch_t; 114 115 typedef struct { 116 int (*get_next_char)(tre_char_t *c, unsigned int *pos_add, void *context); 117 void (*rewind)(size_t pos, void *context); 118 int (*compare)(size_t pos1, size_t pos2, size_t len, void *context); 119 void *context; 120 } tre_str_source; 121 122 /* POSIX tre_regcomp() flags. */ 123 #define REG_EXTENDED 1 124 #define REG_ICASE (REG_EXTENDED << 1) 125 #define REG_NEWLINE (REG_ICASE << 1) 126 #define REG_NOSUB (REG_NEWLINE << 1) 127 128 /* Extra tre_regcomp() flags. */ 129 #define REG_BASIC 0 130 #define REG_LITERAL (REG_NOSUB << 1) 131 #define REG_RIGHT_ASSOC (REG_LITERAL << 1) 132 #define REG_UNGREEDY (REG_RIGHT_ASSOC << 1) 133 #define REG_PEND (REG_UNGREEDY << 1) 134 #define REG_ENHANCED (REG_PEND << 1) 135 136 /* alias regcomp flags. */ 137 #define REG_NOSPEC REG_LITERAL 138 #define REG_MINIMAL REG_UNGREEDY 139 140 /* POSIX tre_regexec() flags. */ 141 #define REG_NOTBOL 1 142 #define REG_NOTEOL (REG_NOTBOL << 1) 143 #define REG_STARTEND (REG_NOTEOL << 1) 144 #define REG_BACKR (REG_STARTEND << 1) 145 146 /* Extra tre_regexec() flags. */ 147 #define REG_APPROX_MATCHER (REG_NOTEOL << 1) 148 #define REG_BACKTRACKING_MATCHER (REG_APPROX_MATCHER << 1) 149 150 /* The maximum number of iterations in a bound expression. */ 151 #define RE_DUP_MAX 255 152 153 #define _REG_nexec 1 154 155 __BEGIN_DECLS 156 157 /* The POSIX.2 regexp functions */ 158 int 159 tre_regcomp(regex_t *preg, const char *regex, int cflags); 160 161 int 162 tre_regexec(const regex_t *preg, const char *string, size_t nmatch, 163 regmatch_t pmatch[], int eflags); 164 165 size_t 166 tre_regerror(int errcode, const regex_t *preg, char *errbuf, 167 size_t errbuf_size); 168 169 void 170 tre_regfree(regex_t *preg); 171 172 /* Wide character versions (not in POSIX.2). */ 173 int 174 tre_regwcomp(regex_t *preg, const wchar_t *regex, int cflags); 175 176 int 177 tre_regwexec(const regex_t *preg, const wchar_t *string, 178 size_t nmatch, regmatch_t pmatch[], int eflags); 179 180 /* Versions with a maximum length argument and therefore the capability to 181 handle null characters in the middle of the strings (not in POSIX.2). */ 182 int 183 tre_regncomp(regex_t *preg, const char *regex, size_t len, int cflags); 184 185 int 186 tre_regnexec(const regex_t *preg, const char *string, size_t len, 187 size_t nmatch, regmatch_t pmatch[], int eflags); 188 189 int 190 tre_regwncomp(regex_t *preg, const wchar_t *regex, size_t len, int cflags); 191 192 int 193 tre_regwnexec(const regex_t *preg, const wchar_t *string, size_t len, 194 size_t nmatch, regmatch_t pmatch[], int eflags); 195 196 /* Returns the version string. The returned string is static. */ 197 char * 198 tre_version(void); 199 200 /* Returns the value for a config parameter. The type to which `result' 201 must point to depends of the value of `query', see documentation for 202 more details. */ 203 int 204 tre_config(int query, void *result); 205 206 /* Returns 1 if the compiled pattern has back references, 0 if not. */ 207 int 208 tre_have_backrefs(const regex_t *preg); 209 210 /* Returns 1 if the compiled pattern uses approximate matching features, 211 0 if not. */ 212 int 213 tre_have_approx(const regex_t *preg); 214 __END_DECLS 215 216 /* The POSIX.2 regexp functions, locale version */ 217 int 218 tre_regcomp_l(regex_t *preg, const char *regex, int cflags, locale_t locale); 219 220 int 221 tre_regncomp_l(regex_t *preg, const char *regex, size_t len, int cflags, 222 locale_t locale); 223 224 int 225 tre_regwcomp_l(regex_t *preg, const wchar_t *regex, int cflags, 226 locale_t locale); 227 228 int 229 tre_regwncomp_l(regex_t *preg, const wchar_t *regex, size_t len, int cflags, 230 locale_t locale); 231 232 #endif /* !_REGEX_H_ */ 233