regex/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 of the University of Toronto.
   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   8.2 (Berkeley) 3/16/94
  38  */
  39
  40 #if defined(LIBC_SCCS) && !defined(lint)
  41 static char sccsid[] = "@(#)regexec.c   8.2 (Berkeley) 3/16/94";
  42 #endif /* LIBC_SCCS and not lint */
  43
  44 /*
  45  * the outer shell of regexec()
  46  *
  47  * This file includes engine.c *twice*, after muchos fiddling with the
  48  * macros that code uses.  This lets the same code operate on two different
  49  * representations for state sets.
  50  */
  51 #include <sys/types.h>
  52 #include <stdio.h>
  53 #include <stdlib.h>
  54 #include <string.h>
  55 #include <limits.h>
  56 #include <ctype.h>
  57 #include <regex.h>
  58
  59 #include "utils.h"
  60 #include "regex2.h"
  61
  62 static int nope = 0;            /* for use in asserts; shuts lint up */
  63
  64 /* macros for manipulating states, small version */
  65 #define states  int
  66 #define states1 states          /* for later use in regexec() decision */
  67 #define CLEAR(v)        ((v) = 0)
  68 #define SET0(v, n)      ((v) &= ~(1 << (n)))
  69 #define SET1(v, n)      ((v) |= 1 << (n))
  70 #define ISSET(v, n)     ((v) & (1 << (n)))
  71 #define ASSIGN(d, s)    ((d) = (s))
  72 #define EQ(a, b)        ((a) == (b))
  73 #define STATEVARS       int dummy       /* dummy version */
  74 #define STATESETUP(m, n)        /* nothing */
  75 #define STATETEARDOWN(m)        /* nothing */
  76 #define SETUP(v)        ((v) = 0)
  77 #define onestate        int
  78 #define INIT(o, n)      ((o) = (unsigned)1 << (n))
  79 #define INC(o)  ((o) <<= 1)
  80 #define ISSTATEIN(v, o) ((v) & (o))
  81 /* some abbreviations; note that some of these know variable names! */
  82 /* do "if I'm here, I can also be there" etc without branches */
  83 #define FWD(dst, src, n)        ((dst) |= ((unsigned)(src)&(here)) << (n))
  84 #define BACK(dst, src, n)       ((dst) |= ((unsigned)(src)&(here)) >> (n))
  85 #define ISSETBACK(v, n) ((v) & ((unsigned)here >> (n)))
  86 /* function names */
  87 #define SNAMES                  /* engine.c looks after details */
  88
  89 #include "engine.c"
  90
  91 /* now undo things */
  92 #undef  states
  93 #undef  CLEAR
  94 #undef  SET0
  95 #undef  SET1
  96 #undef  ISSET
  97 #undef  ASSIGN
  98 #undef  EQ
  99 #undef  STATEVARS
 100 #undef  STATESETUP
 101 #undef  STATETEARDOWN
 102 #undef  SETUP
 103 #undef  onestate
 104 #undef  INIT
 105 #undef  INC
 106 #undef  ISSTATEIN
 107 #undef  FWD
 108 #undef  BACK
 109 #undef  ISSETBACK
 110 #undef  SNAMES
 111
 112 /* macros for manipulating states, large version */
 113 #define states  char *
 114 #define CLEAR(v)        memset(v, 0, m->g->nstates)
 115 #define SET0(v, n)      ((v)[n] = 0)
 116 #define SET1(v, n)      ((v)[n] = 1)
 117 #define ISSET(v, n)     ((v)[n])
 118 #define ASSIGN(d, s)    memcpy(d, s, m->g->nstates)
 119 #define EQ(a, b)        (memcmp(a, b, m->g->nstates) == 0)
 120 #define STATEVARS       int vn; char *space
 121 #define STATESETUP(m, nv)       { (m)->space = malloc((nv)*(m)->g->nstates); \
 122                                 if ((m)->space == NULL) return(REG_ESPACE); \
 123                                 (m)->vn = 0; }
 124 #define STATETEARDOWN(m)        { free((m)->space); }
 125 #define SETUP(v)        ((v) = &m->space[m->vn++ * m->g->nstates])
 126 #define onestate        int
 127 #define INIT(o, n)      ((o) = (n))
 128 #define INC(o)  ((o)++)
 129 #define ISSTATEIN(v, o) ((v)[o])
 130 /* some abbreviations; note that some of these know variable names! */
 131 /* do "if I'm here, I can also be there" etc without branches */
 132 #define FWD(dst, src, n)        ((dst)[here+(n)] |= (src)[here])
 133 #define BACK(dst, src, n)       ((dst)[here-(n)] |= (src)[here])
 134 #define ISSETBACK(v, n) ((v)[here - (n)])
 135 /* function names */
 136 #define LNAMES                  /* flag */
 137
 138 #include "engine.c"
 139
 140 /*
 141  - regexec - interface for matching
 142  = extern int regexec(const regex_t *, const char *, size_t, \
 143  =                                      regmatch_t [], int);
 144  = #define      REG_NOTBOL      00001
 145  = #define      REG_NOTEOL      00002
 146  = #define      REG_STARTEND    00004
 147  = #define      REG_TRACE       00400   // tracing of execution
 148  = #define      REG_LARGE       01000   // force large representation
 149  = #define      REG_BACKR       02000   // force use of backref code
 150  *
 151  * We put this here so we can exploit knowledge of the state representation
 152  * when choosing which matcher to call.  Also, by this point the matchers
 153  * have been prototyped.
 154  */
 155 int                             /* 0 success, REG_NOMATCH failure */
 156 regexec(const regex_t *preg, const RCHAR_T *string, size_t nmatch, regmatch_t *pmatch, int eflags)
 157 {
 158         register struct re_guts *g = preg->re_g;
 159 #ifdef REDEBUG
 160 #       define  GOODFLAGS(f)    (f)
 161 #else
 162 #       define  GOODFLAGS(f)    ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
 163 #endif
 164
 165         if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
 166                 return(REG_BADPAT);
 167         assert(!(g->iflags&BAD));
 168         if (g->iflags&BAD)              /* backstop for no-debug case */
 169                 return(REG_BADPAT);
 170         eflags = GOODFLAGS(eflags);
 171
 172         if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags&REG_LARGE))
 173                 return(smatcher(g, (RCHAR_T *)string, nmatch, pmatch, eflags));
 174         else
 175                 return(lmatcher(g, (RCHAR_T *)string, nmatch, pmatch, eflags));
 176 }