regex/regexec.c

   1 /*
   2  * Copyright (c) 1999 Apple Computer, Inc. All rights reserved.
   3  *
   4  * @APPLE_LICENSE_HEADER_START@
   5  *
   6  * The contents of this file constitute Original Code as defined in and
   7  * are subject to the Apple Public Source License Version 1.1 (the
   8  * "License").  You may not use this file except in compliance with the
   9  * License.  Please obtain a copy of the License at
  10  * http://www.apple.com/publicsource and read it before using this file.
  11  *
  12  * This Original Code and all software distributed under the License are
  13  * distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, EITHER
  14  * EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
  15  * INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
  16  * FITNESS FOR A PARTICULAR PURPOSE OR NON-INFRINGEMENT.  Please see the
  17  * License for the specific language governing rights and limitations
  18  * under the License.
  19  *
  20  * @APPLE_LICENSE_HEADER_END@
  21  */
  22 /*
  23  * Copyright (c) 1992, 1993, 1994
  24  *      The Regents of the University of California.  All rights reserved.
  25  *
  26  * This code is derived from software contributed to Berkeley by
  27  * Henry Spencer.
  28  *
  29  * Redistribution and use in source and binary forms, with or without
  30  * modification, are permitted provided that the following conditions
  31  * are met:
  32  * 1. Redistributions of source code must retain the above copyright
  33  *    notice, this list of conditions and the following disclaimer.
  34  * 2. Redistributions in binary form must reproduce the above copyright
  35  *    notice, this list of conditions and the following disclaimer in the
  36  *    documentation and/or other materials provided with the distribution.
  37  * 3. All advertising materials mentioning features or use of this software
  38  *    must display the following acknowledgement:
  39  *      This product includes software developed by the University of
  40  *      California, Berkeley and its contributors.
  41  * 4. Neither the name of the University nor the names of its contributors
  42  *    may be used to endorse or promote products derived from this software
  43  *    without specific prior written permission.
  44  *
  45  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  46  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  47  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  48  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  49  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  50  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  51  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  52  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  53  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  54  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  55  * SUCH DAMAGE.
  56  */
  57
  58 /*
  59  * the outer shell of regexec()
  60  *
  61  * This file includes engine.c *twice*, after muchos fiddling with the
  62  * macros that code uses.  This lets the same code operate on two different
  63  * representations for state sets.
  64  */
  65 #include <sys/types.h>
  66 #include <stdio.h>
  67 #include <stdlib.h>
  68 #include <string.h>
  69 #include <limits.h>
  70 #include <ctype.h>
  71 #include <regex.h>
  72
  73 #include "utils.h"
  74 #include "regex2.h"
  75
  76 static int nope = 0;            /* for use in asserts; shuts lint up */
  77
  78 /* macros for manipulating states, small version */
  79 #define states  long
  80 #define states1 states          /* for later use in regexec() decision */
  81 #define CLEAR(v)        ((v) = 0)
  82 #define SET0(v, n)      ((v) &= ~(1 << (n)))
  83 #define SET1(v, n)      ((v) |= 1 << (n))
  84 #define ISSET(v, n)     ((v) & (1 << (n)))
  85 #define ASSIGN(d, s)    ((d) = (s))
  86 #define EQ(a, b)        ((a) == (b))
  87 #define STATEVARS       int dummy       /* dummy version */
  88 #define STATESETUP(m, n)        /* nothing */
  89 #define STATETEARDOWN(m)        /* nothing */
  90 #define SETUP(v)        ((v) = 0)
  91 #define onestate        int
  92 #define INIT(o, n)      ((o) = (unsigned)1 << (n))
  93 #define INC(o)  ((o) <<= 1)
  94 #define ISSTATEIN(v, o) ((v) & (o))
  95 /* some abbreviations; note that some of these know variable names! */
  96 /* do "if I'm here, I can also be there" etc without branches */
  97 #define FWD(dst, src, n)        ((dst) |= ((unsigned)(src)&(here)) << (n))
  98 #define BACK(dst, src, n)       ((dst) |= ((unsigned)(src)&(here)) >> (n))
  99 #define ISSETBACK(v, n) ((v) & ((unsigned)here >> (n)))
 100 /* function names */
 101 #define SNAMES                  /* engine.c looks after details */
 102
 103 #include "engine.c"
 104
 105 /* now undo things */
 106 #undef  states
 107 #undef  CLEAR
 108 #undef  SET0
 109 #undef  SET1
 110 #undef  ISSET
 111 #undef  ASSIGN
 112 #undef  EQ
 113 #undef  STATEVARS
 114 #undef  STATESETUP
 115 #undef  STATETEARDOWN
 116 #undef  SETUP
 117 #undef  onestate
 118 #undef  INIT
 119 #undef  INC
 120 #undef  ISSTATEIN
 121 #undef  FWD
 122 #undef  BACK
 123 #undef  ISSETBACK
 124 #undef  SNAMES
 125
 126 /* macros for manipulating states, large version */
 127 #define states  char *
 128 #define CLEAR(v)        memset(v, 0, m->g->nstates)
 129 #define SET0(v, n)      ((v)[n] = 0)
 130 #define SET1(v, n)      ((v)[n] = 1)
 131 #define ISSET(v, n)     ((v)[n])
 132 #define ASSIGN(d, s)    memcpy(d, s, m->g->nstates)
 133 #define EQ(a, b)        (memcmp(a, b, m->g->nstates) == 0)
 134 #define STATEVARS       int vn; char *space
 135 #define STATESETUP(m, nv)       { (m)->space = malloc((nv)*(m)->g->nstates); \
 136                                 if ((m)->space == NULL) return(REG_ESPACE); \
 137                                 (m)->vn = 0; }
 138 #define STATETEARDOWN(m)        { free((m)->space); }
 139 #define SETUP(v)        ((v) = &m->space[m->vn++ * m->g->nstates])
 140 #define onestate        int
 141 #define INIT(o, n)      ((o) = (n))
 142 #define INC(o)  ((o)++)
 143 #define ISSTATEIN(v, o) ((v)[o])
 144 /* some abbreviations; note that some of these know variable names! */
 145 /* do "if I'm here, I can also be there" etc without branches */
 146 #define FWD(dst, src, n)        ((dst)[here+(n)] |= (src)[here])
 147 #define BACK(dst, src, n)       ((dst)[here-(n)] |= (src)[here])
 148 #define ISSETBACK(v, n) ((v)[here - (n)])
 149 /* function names */
 150 #define LNAMES                  /* flag */
 151
 152 #include "engine.c"
 153
 154 /*
 155  - regexec - interface for matching
 156  = extern int regexec(const regex_t *, const char *, size_t, \
 157  =                                      regmatch_t [], int);
 158  = #define      REG_NOTBOL      00001
 159  = #define      REG_NOTEOL      00002
 160  = #define      REG_STARTEND    00004
 161  = #define      REG_TRACE       00400   // tracing of execution
 162  = #define      REG_LARGE       01000   // force large representation
 163  = #define      REG_BACKR       02000   // force use of backref code
 164  *
 165  * We put this here so we can exploit knowledge of the state representation
 166  * when choosing which matcher to call.  Also, by this point the matchers
 167  * have been prototyped.
 168  */
 169 int                             /* 0 success, REG_NOMATCH failure */
 170 regexec(preg, string, nmatch, pmatch, eflags)
 171 const regex_t *preg;
 172 const char *string;
 173 size_t nmatch;
 174 regmatch_t pmatch[];
 175 int eflags;
 176 {
 177         register struct re_guts *g = preg->re_g;
 178 #ifdef REDEBUG
 179 #       define  GOODFLAGS(f)    (f)
 180 #else
 181 #       define  GOODFLAGS(f)    ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
 182 #endif
 183
 184         if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
 185                 return(REG_BADPAT);
 186         assert(!(g->iflags&BAD));
 187         if (g->iflags&BAD)              /* backstop for no-debug case */
 188                 return(REG_BADPAT);
 189         eflags = GOODFLAGS(eflags);
 190
 191         if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags&REG_LARGE))
 192                 return(smatcher(g, (char *)string, nmatch, pmatch, eflags));
 193         else
 194                 return(lmatcher(g, (char *)string, nmatch, pmatch, eflags));
 195 }