lib/libc/tre-regex/regex.h

   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_regcomp_l regcomp_l
  40 #define tre_regexec   regexec
  41 #define tre_regerror  regerror
  42 #define tre_regfree   regfree
  43
  44 #define tre_regncomp  regncomp
  45 #define tre_regncomp_l regncomp_l
  46 #define tre_regnexec  regnexec
  47 #define tre_regwcomp  regwcomp
  48 #define tre_regwcomp_l regwcomp_l
  49 #define tre_regwexec  regwexec
  50 #define tre_regwncomp regwncomp
  51 #define tre_regwncomp_l regwncomp_l
  52 #define tre_regwnexec regwnexec
  53
  54 typedef enum {
  55 #if __BSD_VISIBLE || (__POSIX_VISIBLE && __POSIX_VISIBLE < 200809)
  56   REG_ENOSYS = -1,      /* Reserved */
  57 #endif
  58   REG_OK = 0,           /* No error. */
  59   REG_NOMATCH,          /* No match. */
  60   REG_BADPAT,           /* Invalid regexp. */
  61   REG_ECOLLATE,         /* Unknown collating element. */
  62   REG_ECTYPE,           /* Unknown character class name. */
  63   REG_EESCAPE,          /* Trailing backslash. */
  64   REG_ESUBREG,          /* Invalid back reference. */
  65   REG_EBRACK,           /* "[]" imbalance */
  66   REG_EPAREN,           /* "\(\)" or "()" imbalance */
  67   REG_EBRACE,           /* "\{\}" or "{}" imbalance */
  68   REG_BADBR,            /* Invalid content of {} */
  69   REG_ERANGE,           /* Invalid use of range operator */
  70   REG_ESPACE,           /* Out of memory.  */
  71   REG_BADRPT,           /* Invalid use of repetition operators. */
  72   REG_EMPTY,            /* rexexp was zero-length string */
  73   REG_INVARG,           /* invalid argument to regex routine */
  74   REG_ILLSEQ            /* illegal byte sequence */
  75 } reg_errcode_t;
  76
  77 enum {
  78   TRE_CONFIG_APPROX,
  79   TRE_CONFIG_WCHAR,
  80   TRE_CONFIG_MULTIBYTE,
  81   TRE_CONFIG_SYSTEM_ABI,
  82   TRE_CONFIG_VERSION
  83 };
  84
  85 typedef int regoff_t;
  86 typedef wchar_t tre_char_t;
  87
  88 typedef struct {
  89   int re_magic;
  90   size_t re_nsub;  /* Number of parenthesized subexpressions. */
  91   const void *re_endp; /* regex string end pointer (REG_PEND) */
  92   void *value;     /* For internal use only. */
  93 } regex_t;
  94
  95 typedef struct {
  96   regoff_t rm_so;
  97   regoff_t rm_eo;
  98 } regmatch_t;
  99
 100 /* Approximate matching parameter struct. */
 101 typedef struct {
 102   int cost_ins;         /* Default cost of an inserted character. */
 103   int cost_del;         /* Default cost of a deleted character. */
 104   int cost_subst;       /* Default cost of a substituted character. */
 105   int max_cost;         /* Maximum allowed cost of a match. */
 106
 107   int max_ins;          /* Maximum allowed number of inserts. */
 108   int max_del;          /* Maximum allowed number of deletes. */
 109   int max_subst;        /* Maximum allowed number of substitutes. */
 110   int max_err;          /* Maximum allowed number of errors total. */
 111 } regaparams_t;
 112
 113 /* Approximate matching result struct. */
 114 typedef struct {
 115   size_t nmatch;        /* Length of pmatch[] array. */
 116   regmatch_t *pmatch;   /* Submatch data. */
 117   int cost;             /* Cost of the match. */
 118   int num_ins;          /* Number of inserts in the match. */
 119   int num_del;          /* Number of deletes in the match. */
 120   int num_subst;        /* Number of substitutes in the match. */
 121 } regamatch_t;
 122
 123 typedef struct {
 124   int (*get_next_char)(tre_char_t *c, unsigned int *pos_add, void *context);
 125   void (*rewind)(size_t pos, void *context);
 126   int (*compare)(size_t pos1, size_t pos2, size_t len, void *context);
 127   void *context;
 128 } tre_str_source;
 129
 130 /* POSIX tre_regcomp() flags. */
 131 #define REG_EXTENDED    1
 132 #define REG_ICASE       (REG_EXTENDED << 1)
 133 #define REG_NEWLINE     (REG_ICASE << 1)
 134 #define REG_NOSUB       (REG_NEWLINE << 1)
 135
 136 /* Extra tre_regcomp() flags. */
 137 #define REG_BASIC       0
 138 #define REG_LITERAL     (REG_NOSUB << 1)
 139 #define REG_RIGHT_ASSOC (REG_LITERAL << 1)
 140 #define REG_UNGREEDY    (REG_RIGHT_ASSOC << 1)
 141 #define REG_PEND        (REG_UNGREEDY << 1)
 142 #define REG_ENHANCED    (REG_PEND << 1)
 143
 144 /* alias regcomp flags. */
 145 #define REG_NOSPEC      REG_LITERAL
 146 #define REG_MINIMAL     REG_UNGREEDY
 147
 148 /* POSIX tre_regexec() flags. */
 149 #define REG_NOTBOL      1
 150 #define REG_NOTEOL      (REG_NOTBOL << 1)
 151 #define REG_STARTEND    (REG_NOTEOL << 1)
 152 #define REG_BACKR       (REG_STARTEND << 1)
 153
 154 /* Extra tre_regexec() flags. */
 155 #define REG_APPROX_MATCHER       (REG_NOTEOL << 1)
 156 #define REG_BACKTRACKING_MATCHER (REG_APPROX_MATCHER << 1)
 157
 158 /* The maximum number of iterations in a bound expression. */
 159 #define RE_DUP_MAX 255
 160
 161 #define _REG_nexec 1
 162
 163 __BEGIN_DECLS
 164
 165 /* The POSIX.2 regexp functions */
 166 int
 167 tre_regcomp(regex_t * __restrict preg, const char * __restrict regex,
 168     int cflags);
 169
 170 int
 171 tre_regexec(const regex_t * __restrict preg, const char * __restrict string,
 172     size_t nmatch, regmatch_t pmatch[__restrict_arr], int eflags);
 173
 174 size_t
 175 tre_regerror(int errcode, const regex_t * __restrict preg,
 176     char * __restrict errbuf, size_t errbuf_size);
 177
 178 void
 179 tre_regfree(regex_t *preg);
 180
 181 /* Wide character versions (not in POSIX.2). */
 182 int
 183 tre_regwcomp(regex_t *preg, const wchar_t *regex, int cflags);
 184
 185 int
 186 tre_regwexec(const regex_t *preg, const wchar_t *string,
 187          size_t nmatch, regmatch_t pmatch[], int eflags);
 188
 189 /* Versions with a maximum length argument and therefore the capability to
 190    handle null characters in the middle of the strings (not in POSIX.2). */
 191 int
 192 tre_regncomp(regex_t *preg, const char *regex, size_t len, int cflags);
 193
 194 int
 195 tre_regnexec(const regex_t *preg, const char *string, size_t len,
 196          size_t nmatch, regmatch_t pmatch[], int eflags);
 197
 198 int
 199 tre_regwncomp(regex_t *preg, const wchar_t *regex, size_t len, int cflags);
 200
 201 int
 202 tre_regwnexec(const regex_t *preg, const wchar_t *string, size_t len,
 203           size_t nmatch, regmatch_t pmatch[], int eflags);
 204
 205 /* Returns the version string.  The returned string is static. */
 206 char *
 207 tre_version(void);
 208
 209 /* Returns the value for a config parameter.  The type to which `result'
 210    must point to depends of the value of `query', see documentation for
 211    more details. */
 212 int
 213 tre_config(int query, void *result);
 214
 215 /* Returns 1 if the compiled pattern has back references, 0 if not. */
 216 int
 217 tre_have_backrefs(const regex_t *preg);
 218
 219 /* Returns 1 if the compiled pattern uses approximate matching features,
 220    0 if not. */
 221 int
 222 tre_have_approx(const regex_t *preg);
 223 __END_DECLS
 224
 225 /* The POSIX.2 regexp functions, locale version */
 226 int
 227 tre_regcomp_l(regex_t *preg, const char *regex, int cflags, locale_t locale);
 228
 229 int
 230 tre_regncomp_l(regex_t *preg, const char *regex, size_t len, int cflags,
 231     locale_t locale);
 232
 233 int
 234 tre_regwcomp_l(regex_t *preg, const wchar_t *regex, int cflags,
 235     locale_t locale);
 236
 237 int
 238 tre_regwncomp_l(regex_t *preg, const wchar_t *regex, size_t len, int cflags,
 239     locale_t locale);
 240
 241 #endif /* !_REGEX_H_ */