external/bsd/nvi/dist/regex/regexec.c

   1 /*      $NetBSD: regexec.c,v 1.5 2014/01/26 21:47:00 christos Exp $ */
   2 /*-
   3  * Copyright (c) 1992, 1993, 1994 Henry Spencer.
   4  * Copyright (c) 1992, 1993, 1994
   5  *      The Regents of the University of California.  All rights reserved.
   6  *
   7  * This code is derived from software contributed to Berkeley by
   8  * Henry Spencer of the University of Toronto.
   9  *
  10  * Redistribution and use in source and binary forms, with or without
  11  * modification, are permitted provided that the following conditions
  12  * are met:
  13  * 1. Redistributions of source code must retain the above copyright
  14  *    notice, this list of conditions and the following disclaimer.
  15  * 2. Redistributions in binary form must reproduce the above copyright
  16  *    notice, this list of conditions and the following disclaimer in the
  17  *    documentation and/or other materials provided with the distribution.
  18  * 3. All advertising materials mentioning features or use of this software
  19  *    must display the following acknowledgement:
  20  *      This product includes software developed by the University of
  21  *      California, Berkeley and its contributors.
  22  * 4. Neither the name of the University nor the names of its contributors
  23  *    may be used to endorse or promote products derived from this software
  24  *    without specific prior written permission.
  25  *
  26  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  27  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  28  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  29  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  30  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  31  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  32  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  33  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  34  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  35  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  36  * SUCH DAMAGE.
  37  *
  38  *      @(#)regexec.c   8.2 (Berkeley) 3/16/94
  39  */
  40
  41 #include <sys/cdefs.h>
  42 #if 0
  43 #if defined(LIBC_SCCS) && !defined(lint)
  44 static char sccsid[] = "@(#)regexec.c   8.2 (Berkeley) 3/16/94";
  45 #endif /* LIBC_SCCS and not lint */
  46 #else
  47 __RCSID("$NetBSD: regexec.c,v 1.5 2014/01/26 21:47:00 christos Exp $");
  48 #endif
  49
  50 /*
  51  * the outer shell of regexec()
  52  *
  53  * This file includes engine.c *twice*, after muchos fiddling with the
  54  * macros that code uses.  This lets the same code operate on two different
  55  * representations for state sets.
  56  */
  57 #include <sys/types.h>
  58 #include <stdio.h>
  59 #include <stdlib.h>
  60 #include <string.h>
  61 #include <limits.h>
  62 #include <ctype.h>
  63 #include <regex.h>
  64
  65 #include "utils.h"
  66 #include "regex2.h"
  67
  68 #ifdef notdef
  69 static int nope = 0;            /* for use in asserts; shuts lint up */
  70 #endif
  71
  72 /* macros for manipulating states, small version */
  73 #define states  int
  74 #define states1 int             /* for later use in regexec() decision */
  75 #define CLEAR(v)        ((v) = 0)
  76 #define SET0(v, n)      ((v) &= ~(1 << (n)))
  77 #define SET1(v, n)      ((v) |= 1 << (n))
  78 #define ISSET(v, n)     ((v) & (1 << (n)))
  79 #define ASSIGN(d, s)    ((d) = (s))
  80 #define EQ(a, b)        ((a) == (b))
  81 #define STATEVARS       int dummy       /* dummy version */
  82 #define STATESETUP(m, n)        /* nothing */
  83 #define STATETEARDOWN(m)        /* nothing */
  84 #define SETUP(v)        ((v) = 0)
  85 #define onestate        int
  86 #define INIT(o, n)      ((o) = (unsigned)1 << (n))
  87 #define INC(o)  ((o) <<= 1)
  88 #define ISSTATEIN(v, o) ((v) & (o))
  89 /* some abbreviations; note that some of these know variable names! */
  90 /* do "if I'm here, I can also be there" etc without branches */
  91 #define FWD(dst, src, n)        ((dst) |= ((unsigned)(src)&(here)) << (n))
  92 #define BACK(dst, src, n)       ((dst) |= ((unsigned)(src)&(here)) >> (n))
  93 #define ISSETBACK(v, n) ((v) & ((unsigned)here >> (n)))
  94 /* function names */
  95 #define SNAMES                  /* engine.c looks after details */
  96
  97 #include "engine.c"
  98
  99 /* now undo things */
 100 #undef  states
 101 #undef  CLEAR
 102 #undef  SET0
 103 #undef  SET1
 104 #undef  ISSET
 105 #undef  ASSIGN
 106 #undef  EQ
 107 #undef  STATEVARS
 108 #undef  STATESETUP
 109 #undef  STATETEARDOWN
 110 #undef  SETUP
 111 #undef  onestate
 112 #undef  INIT
 113 #undef  INC
 114 #undef  ISSTATEIN
 115 #undef  FWD
 116 #undef  BACK
 117 #undef  ISSETBACK
 118 #undef  SNAMES
 119
 120 /* macros for manipulating states, large version */
 121 #define states  char *
 122 #define CLEAR(v)        memset(v, 0, m->g->nstates)
 123 #define SET0(v, n)      ((v)[n] = 0)
 124 #define SET1(v, n)      ((v)[n] = 1)
 125 #define ISSET(v, n)     ((v)[n])
 126 #define ASSIGN(d, s)    memcpy(d, s, m->g->nstates)
 127 #define EQ(a, b)        (memcmp(a, b, m->g->nstates) == 0)
 128 #define STATEVARS       int vn; char *space
 129 #define STATESETUP(m, nv)       { (m)->space = malloc((nv)*(m)->g->nstates); \
 130                                 if ((m)->space == NULL) return(REG_ESPACE); \
 131                                 (m)->vn = 0; }
 132 #define STATETEARDOWN(m)        { free((m)->space); }
 133 #define SETUP(v)        ((v) = &m->space[m->vn++ * m->g->nstates])
 134 #define onestate        int
 135 #define INIT(o, n)      ((o) = (n))
 136 #define INC(o)  ((o)++)
 137 #define ISSTATEIN(v, o) ((v)[o])
 138 /* some abbreviations; note that some of these know variable names! */
 139 /* do "if I'm here, I can also be there" etc without branches */
 140 #define FWD(dst, src, n)        ((dst)[here+(n)] |= (src)[here])
 141 #define BACK(dst, src, n)       ((dst)[here-(n)] |= (src)[here])
 142 #define ISSETBACK(v, n) ((v)[here - (n)])
 143 /* function names */
 144 #define LNAMES                  /* flag */
 145
 146 #include "engine.c"
 147
 148 /*
 149  - regexec - interface for matching
 150  = extern int regexec(const regex_t *, const char *, size_t, \
 151  =                                      regmatch_t [], int);
 152  = #define      REG_NOTBOL      00001
 153  = #define      REG_NOTEOL      00002
 154  = #define      REG_STARTEND    00004
 155  = #define      REG_TRACE       00400   // tracing of execution
 156  = #define      REG_LARGE       01000   // force large representation
 157  = #define      REG_BACKR       02000   // force use of backref code
 158  *
 159  * We put this here so we can exploit knowledge of the state representation
 160  * when choosing which matcher to call.  Also, by this point the matchers
 161  * have been prototyped.
 162  */
 163 int                             /* 0 success, REG_NOMATCH failure */
 164 regexec(const regex_t *preg, const RCHAR_T *string, size_t nmatch, regmatch_t *pmatch, int eflags)
 165 {
 166         struct re_guts *g = preg->re_g;
 167 #ifdef REDEBUG
 168 #       define  GOODFLAGS(f)    (f)
 169 #else
 170 #       define  GOODFLAGS(f)    ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
 171 #endif
 172
 173         if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
 174                 return(REG_BADPAT);
 175         assert(!(g->iflags&BAD));
 176         if (g->iflags&BAD)              /* backstop for no-debug case */
 177                 return(REG_BADPAT);
 178         eflags = GOODFLAGS(eflags);
 179
 180         if (g->nstates <= (int)(CHAR_BIT*sizeof(states1)) && !(eflags&REG_LARGE))
 181                 return(smatcher(g, (RCHAR_T *)__UNCONST(string), nmatch, pmatch, eflags));
 182         else
 183                 return(lmatcher(g, (RCHAR_T *)__UNCONST(string), nmatch, pmatch, eflags));
 184 }