regex/regexec-fbsd.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 #include "xlocale_private.h"
  47
  48 /*
  49  * the outer shell of regexec()
  50  *
  51  * This file includes engine.c three times, after muchos fiddling with the
  52  * macros that code uses.  This lets the same code operate on two different
  53  * representations for state sets and characters.
  54  */
  55 #include <sys/types.h>
  56 #include <stdio.h>
  57 #include <stdlib.h>
  58 #include <string.h>
  59 #include <limits.h>
  60 #include <ctype.h>
  61 #include <regex.h>
  62 #include <wchar.h>
  63 #include <wctype.h>
  64
  65 #include "utils.h"
  66 #include "regex2.h"
  67
  68 static int nope __unused = 0;   /* for use in asserts; shuts lint up */
  69
  70 static __inline size_t
  71 xmbrtowc(wi, s, n, mbs, dummy, loc)
  72 wint_t *wi;
  73 const char *s;
  74 size_t n;
  75 mbstate_t *mbs;
  76 wint_t dummy;
  77 locale_t loc;
  78 {
  79         size_t nr;
  80         wchar_t wc;
  81
  82         nr = mbrtowc_l(&wc, s, n, mbs, loc);
  83         if (wi != NULL)
  84                 *wi = wc;
  85         if (nr == 0)
  86                 return (1);
  87         else if (nr == (size_t)-1 || nr == (size_t)-2) {
  88                 memset(mbs, 0, sizeof(*mbs));
  89                 if (wi != NULL)
  90                         *wi = dummy;
  91                 return (1);
  92         } else
  93                 return (nr);
  94 }
  95
  96 static __inline size_t
  97 xmbrtowc_dummy(wi, s, n, mbs, dummy, loc)
  98 wint_t *wi;
  99 const char *s;
 100 size_t n __unused;
 101 mbstate_t *mbs __unused;
 102 wint_t dummy __unused;
 103 locale_t loc;
 104 {
 105
 106         if (wi != NULL)
 107                 *wi = (unsigned char)*s;
 108         return (1);
 109 }
 110
 111 /* macros for manipulating states, small version */
 112 #define states  long
 113 #define states1 states          /* for later use in regexec() decision */
 114 #define CLEAR(v)        ((v) = 0)
 115 #define SET0(v, n)      ((v) &= ~((unsigned long)1 << (n)))
 116 #define SET1(v, n)      ((v) |= (unsigned long)1 << (n))
 117 #define ISSET(v, n)     (((v) & ((unsigned long)1 << (n))) != 0)
 118 #define ASSIGN(d, s)    ((d) = (s))
 119 #define EQ(a, b)        ((a) == (b))
 120 #define STATEVARS       long dummy      /* dummy version */
 121 #define STATESETUP(m, n)        /* nothing */
 122 #define STATETEARDOWN(m)        /* nothing */
 123 #define SETUP(v)        ((v) = 0)
 124 #define onestate        long
 125 #define INIT(o, n)      ((o) = (unsigned long)1 << (n))
 126 #define INC(o)  ((o) <<= 1)
 127 #define ISSTATEIN(v, o) (((v) & (o)) != 0)
 128 /* some abbreviations; note that some of these know variable names! */
 129 /* do "if I'm here, I can also be there" etc without branches */
 130 #define FWD(dst, src, n)        ((dst) |= ((unsigned long)(src)&(here)) << (n))
 131 #define BACK(dst, src, n)       ((dst) |= ((unsigned long)(src)&(here)) >> (n))
 132 #define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0)
 133 /* no multibyte support */
 134 #define XMBRTOWC        xmbrtowc_dummy
 135 #define ZAPSTATE(mbs)   ((void)(mbs))
 136 /* function names */
 137 #define SNAMES                  /* engine.c looks after details */
 138
 139 #include "engine.c"
 140
 141 /* now undo things */
 142 #undef  states
 143 #undef  CLEAR
 144 #undef  SET0
 145 #undef  SET1
 146 #undef  ISSET
 147 #undef  ASSIGN
 148 #undef  EQ
 149 #undef  STATEVARS
 150 #undef  STATESETUP
 151 #undef  STATETEARDOWN
 152 #undef  SETUP
 153 #undef  onestate
 154 #undef  INIT
 155 #undef  INC
 156 #undef  ISSTATEIN
 157 #undef  FWD
 158 #undef  BACK
 159 #undef  ISSETBACK
 160 #undef  SNAMES
 161 #undef  XMBRTOWC
 162 #undef  ZAPSTATE
 163
 164 /* macros for manipulating states, large version */
 165 #define states  char *
 166 #define CLEAR(v)        memset(v, 0, m->g->nstates)
 167 #define SET0(v, n)      ((v)[n] = 0)
 168 #define SET1(v, n)      ((v)[n] = 1)
 169 #define ISSET(v, n)     ((v)[n])
 170 #define ASSIGN(d, s)    memcpy(d, s, m->g->nstates)
 171 #define EQ(a, b)        (memcmp(a, b, m->g->nstates) == 0)
 172 #define STATEVARS       long vn; char *space
 173 #define STATESETUP(m, nv)       { (m)->space = malloc((nv)*(m)->g->nstates); \
 174                                 if ((m)->space == NULL) return(REG_ESPACE); \
 175                                 (m)->vn = 0; }
 176 #define STATETEARDOWN(m)        { free((m)->space); }
 177 #define SETUP(v)        ((v) = &m->space[m->vn++ * m->g->nstates])
 178 #define onestate        long
 179 #define INIT(o, n)      ((o) = (n))
 180 #define INC(o)  ((o)++)
 181 #define ISSTATEIN(v, o) ((v)[o])
 182 /* some abbreviations; note that some of these know variable names! */
 183 /* do "if I'm here, I can also be there" etc without branches */
 184 #define FWD(dst, src, n)        ((dst)[here+(n)] |= (src)[here])
 185 #define BACK(dst, src, n)       ((dst)[here-(n)] |= (src)[here])
 186 #define ISSETBACK(v, n) ((v)[here - (n)])
 187 /* no multibyte support */
 188 #define XMBRTOWC        xmbrtowc_dummy
 189 #define ZAPSTATE(mbs)   ((void)(mbs))
 190 /* function names */
 191 #define LNAMES                  /* flag */
 192
 193 #undef __FBSDID
 194 #define __FBSDID(x)
 195 #include "engine.c"
 196
 197 /* multibyte character & large states version */
 198 #undef  LNAMES
 199 #undef  XMBRTOWC
 200 #undef  ZAPSTATE
 201 #define XMBRTOWC        xmbrtowc
 202 #define ZAPSTATE(mbs)   memset((mbs), 0, sizeof(*(mbs)))
 203 #define MNAMES
 204
 205 #include "engine.c"
 206
 207 /*
 208  - regexec - interface for matching
 209  = extern int regexec(const regex_t *, const char *, size_t, \
 210  =                                      regmatch_t [], int);
 211  = #define      REG_NOTBOL      00001
 212  = #define      REG_NOTEOL      00002
 213  = #define      REG_STARTEND    00004
 214  = #define      REG_TRACE       00400   // tracing of execution
 215  = #define      REG_LARGE       01000   // force large representation
 216  = #define      REG_BACKR       02000   // force use of backref code
 217  *
 218  * We put this here so we can exploit knowledge of the state representation
 219  * when choosing which matcher to call.  Also, by this point the matchers
 220  * have been prototyped.
 221  */
 222 int                             /* 0 success, REG_NOMATCH failure */
 223 regexec(preg, string, nmatch, pmatch, eflags)
 224 const regex_t * __restrict preg;
 225 const char * __restrict string;
 226 size_t nmatch;
 227 regmatch_t pmatch[__restrict];
 228 int eflags;
 229 {
 230         struct re_guts *g = preg->re_g;
 231 #ifdef REDEBUG
 232 #       define  GOODFLAGS(f)    (f)
 233 #else
 234 #       define  GOODFLAGS(f)    ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
 235 #endif
 236
 237         if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
 238                 return(REG_BADPAT);
 239         assert(!(g->iflags&BAD));
 240         if (g->iflags&BAD)              /* backstop for no-debug case */
 241                 return(REG_BADPAT);
 242         eflags = GOODFLAGS(eflags);
 243
 244         g->loc = __current_locale();
 245         if (MB_CUR_MAX_L(g->loc) > 1)
 246                 return(mmatcher(g, (char *)string, nmatch, pmatch, eflags));
 247         else if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags&REG_LARGE))
 248                 return(smatcher(g, (char *)string, nmatch, pmatch, eflags));
 249         else
 250                 return(lmatcher(g, (char *)string, nmatch, pmatch, eflags));
 251 }