regex/FreeBSD/regexec.c

   1 /*-
   2  * Copyright (c) 1992, 1993, 1994 Henry Spencer.
   3  * Copyright (c) 1992, 1993, 1994
   4  *      The Regents of the University of California.  All rights reserved.
   5  *
   6  * This code is derived from software contributed to Berkeley by
   7  * Henry Spencer.
   8  *
   9  * Redistribution and use in source and binary forms, with or without
  10  * modification, are permitted provided that the following conditions
  11  * are met:
  12  * 1. Redistributions of source code must retain the above copyright
  13  *    notice, this list of conditions and the following disclaimer.
  14  * 2. Redistributions in binary form must reproduce the above copyright
  15  *    notice, this list of conditions and the following disclaimer in the
  16  *    documentation and/or other materials provided with the distribution.
  17  * 3. All advertising materials mentioning features or use of this software
  18  *    must display the following acknowledgement:
  19  *      This product includes software developed by the University of
  20  *      California, Berkeley and its contributors.
  21  * 4. Neither the name of the University nor the names of its contributors
  22  *    may be used to endorse or promote products derived from this software
  23  *    without specific prior written permission.
  24  *
  25  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  26  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  27  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  28  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  29  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  30  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  31  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  32  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  33  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  34  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  35  * SUCH DAMAGE.
  36  *
  37  *      @(#)regexec.c   8.3 (Berkeley) 3/20/94
  38  */
  39
  40 #if defined(LIBC_SCCS) && !defined(lint)
  41 static char sccsid[] = "@(#)regexec.c   8.3 (Berkeley) 3/20/94";
  42 #endif /* LIBC_SCCS and not lint */
  43 #include <sys/cdefs.h>
  44 __FBSDID("$FreeBSD: src/lib/libc/regex/regexec.c,v 1.6 2004/07/12 07:35:59 tjr Exp $");
  45
  46 /*
  47  * the outer shell of regexec()
  48  *
  49  * This file includes engine.c three times, after muchos fiddling with the
  50  * macros that code uses.  This lets the same code operate on two different
  51  * representations for state sets and characters.
  52  */
  53 #include <sys/types.h>
  54 #include <stdio.h>
  55 #include <stdlib.h>
  56 #include <string.h>
  57 #include <limits.h>
  58 #include <ctype.h>
  59 #include <regex.h>
  60 #include <wchar.h>
  61 #include <wctype.h>
  62
  63 #include "utils.h"
  64 #include "regex2.h"
  65
  66 static int nope __unused = 0;   /* for use in asserts; shuts lint up */
  67
  68 static __inline size_t
  69 xmbrtowc(wi, s, n, mbs, dummy)
  70 wint_t *wi;
  71 const char *s;
  72 size_t n;
  73 mbstate_t *mbs;
  74 wint_t dummy;
  75 {
  76         size_t nr;
  77         wchar_t wc;
  78
  79         nr = mbrtowc(&wc, s, n, mbs);
  80         if (wi != NULL)
  81                 *wi = wc;
  82         if (nr == 0)
  83                 return (1);
  84         else if (nr == (size_t)-1 || nr == (size_t)-2) {
  85                 memset(mbs, 0, sizeof(*mbs));
  86                 if (wi != NULL)
  87                         *wi = dummy;
  88                 return (1);
  89         } else
  90                 return (nr);
  91 }
  92
  93 static __inline size_t
  94 xmbrtowc_dummy(wi, s, n, mbs, dummy)
  95 wint_t *wi;
  96 const char *s;
  97 size_t n __unused;
  98 mbstate_t *mbs __unused;
  99 wint_t dummy __unused;
 100 {
 101
 102         if (wi != NULL)
 103                 *wi = (unsigned char)*s;
 104         return (1);
 105 }
 106
 107 /* macros for manipulating states, small version */
 108 #define states  long
 109 #define states1 states          /* for later use in regexec() decision */
 110 #define CLEAR(v)        ((v) = 0)
 111 #define SET0(v, n)      ((v) &= ~((unsigned long)1 << (n)))
 112 #define SET1(v, n)      ((v) |= (unsigned long)1 << (n))
 113 #define ISSET(v, n)     (((v) & ((unsigned long)1 << (n))) != 0)
 114 #define ASSIGN(d, s)    ((d) = (s))
 115 #define EQ(a, b)        ((a) == (b))
 116 #define STATEVARS       long dummy      /* dummy version */
 117 #define STATESETUP(m, n)        /* nothing */
 118 #define STATETEARDOWN(m)        /* nothing */
 119 #define SETUP(v)        ((v) = 0)
 120 #define onestate        long
 121 #define INIT(o, n)      ((o) = (unsigned long)1 << (n))
 122 #define INC(o)  ((o) <<= 1)
 123 #define ISSTATEIN(v, o) (((v) & (o)) != 0)
 124 /* some abbreviations; note that some of these know variable names! */
 125 /* do "if I'm here, I can also be there" etc without branches */
 126 #define FWD(dst, src, n)        ((dst) |= ((unsigned long)(src)&(here)) << (n))
 127 #define BACK(dst, src, n)       ((dst) |= ((unsigned long)(src)&(here)) >> (n))
 128 #define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0)
 129 /* no multibyte support */
 130 #define XMBRTOWC        xmbrtowc_dummy
 131 #define ZAPSTATE(mbs)   ((void)(mbs))
 132 /* function names */
 133 #define SNAMES                  /* engine.c looks after details */
 134
 135 #include "engine.c"
 136
 137 /* now undo things */
 138 #undef  states
 139 #undef  CLEAR
 140 #undef  SET0
 141 #undef  SET1
 142 #undef  ISSET
 143 #undef  ASSIGN
 144 #undef  EQ
 145 #undef  STATEVARS
 146 #undef  STATESETUP
 147 #undef  STATETEARDOWN
 148 #undef  SETUP
 149 #undef  onestate
 150 #undef  INIT
 151 #undef  INC
 152 #undef  ISSTATEIN
 153 #undef  FWD
 154 #undef  BACK
 155 #undef  ISSETBACK
 156 #undef  SNAMES
 157 #undef  XMBRTOWC
 158 #undef  ZAPSTATE
 159
 160 /* macros for manipulating states, large version */
 161 #define states  char *
 162 #define CLEAR(v)        memset(v, 0, m->g->nstates)
 163 #define SET0(v, n)      ((v)[n] = 0)
 164 #define SET1(v, n)      ((v)[n] = 1)
 165 #define ISSET(v, n)     ((v)[n])
 166 #define ASSIGN(d, s)    memcpy(d, s, m->g->nstates)
 167 #define EQ(a, b)        (memcmp(a, b, m->g->nstates) == 0)
 168 #define STATEVARS       long vn; char *space
 169 #define STATESETUP(m, nv)       { (m)->space = malloc((nv)*(m)->g->nstates); \
 170                                 if ((m)->space == NULL) return(REG_ESPACE); \
 171                                 (m)->vn = 0; }
 172 #define STATETEARDOWN(m)        { free((m)->space); }
 173 #define SETUP(v)        ((v) = &m->space[m->vn++ * m->g->nstates])
 174 #define onestate        long
 175 #define INIT(o, n)      ((o) = (n))
 176 #define INC(o)  ((o)++)
 177 #define ISSTATEIN(v, o) ((v)[o])
 178 /* some abbreviations; note that some of these know variable names! */
 179 /* do "if I'm here, I can also be there" etc without branches */
 180 #define FWD(dst, src, n)        ((dst)[here+(n)] |= (src)[here])
 181 #define BACK(dst, src, n)       ((dst)[here-(n)] |= (src)[here])
 182 #define ISSETBACK(v, n) ((v)[here - (n)])
 183 /* no multibyte support */
 184 #define XMBRTOWC        xmbrtowc_dummy
 185 #define ZAPSTATE(mbs)   ((void)(mbs))
 186 /* function names */
 187 #define LNAMES                  /* flag */
 188
 189 #include "engine.c"
 190
 191 /* multibyte character & large states version */
 192 #undef  LNAMES
 193 #undef  XMBRTOWC
 194 #undef  ZAPSTATE
 195 #define XMBRTOWC        xmbrtowc
 196 #define ZAPSTATE(mbs)   memset((mbs), 0, sizeof(*(mbs)))
 197 #define MNAMES
 198
 199 #include "engine.c"
 200
 201 /*
 202  - regexec - interface for matching
 203  = extern int regexec(const regex_t *, const char *, size_t, \
 204  =                                      regmatch_t [], int);
 205  = #define      REG_NOTBOL      00001
 206  = #define      REG_NOTEOL      00002
 207  = #define      REG_STARTEND    00004
 208  = #define      REG_TRACE       00400   // tracing of execution
 209  = #define      REG_LARGE       01000   // force large representation
 210  = #define      REG_BACKR       02000   // force use of backref code
 211  *
 212  * We put this here so we can exploit knowledge of the state representation
 213  * when choosing which matcher to call.  Also, by this point the matchers
 214  * have been prototyped.
 215  */
 216 int                             /* 0 success, REG_NOMATCH failure */
 217 regexec(preg, string, nmatch, pmatch, eflags)
 218 const regex_t * __restrict preg;
 219 const char * __restrict string;
 220 size_t nmatch;
 221 regmatch_t pmatch[__restrict];
 222 int eflags;
 223 {
 224         struct re_guts *g = preg->re_g;
 225 #ifdef REDEBUG
 226 #       define  GOODFLAGS(f)    (f)
 227 #else
 228 #       define  GOODFLAGS(f)    ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
 229 #endif
 230
 231         if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
 232                 return(REG_BADPAT);
 233         assert(!(g->iflags&BAD));
 234         if (g->iflags&BAD)              /* backstop for no-debug case */
 235                 return(REG_BADPAT);
 236         eflags = GOODFLAGS(eflags);
 237
 238         if (MB_CUR_MAX > 1)
 239                 return(mmatcher(g, (char *)string, nmatch, pmatch, eflags));
 240         else if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags&REG_LARGE))
 241                 return(smatcher(g, (char *)string, nmatch, pmatch, eflags));
 242         else
 243                 return(lmatcher(g, (char *)string, nmatch, pmatch, eflags));
 244 }