lib/Support/regexec.c

   1 /*-
   2  * This code is derived from OpenBSD's libc/regex, original license follows:
   3  *
   4  * Copyright (c) 1992, 1993, 1994 Henry Spencer.
   5  * Copyright (c) 1992, 1993, 1994
   6  *      The Regents of the University of California.  All rights reserved.
   7  *
   8  * This code is derived from software contributed to Berkeley by
   9  * Henry Spencer.
  10  *
  11  * Redistribution and use in source and binary forms, with or without
  12  * modification, are permitted provided that the following conditions
  13  * are met:
  14  * 1. Redistributions of source code must retain the above copyright
  15  *    notice, this list of conditions and the following disclaimer.
  16  * 2. Redistributions in binary form must reproduce the above copyright
  17  *    notice, this list of conditions and the following disclaimer in the
  18  *    documentation and/or other materials provided with the distribution.
  19  * 3. Neither the name of the University nor the names of its contributors
  20  *    may be used to endorse or promote products derived from this software
  21  *    without specific prior written permission.
  22  *
  23  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  24  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  25  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  26  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  27  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  28  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  29  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  30  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  31  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  32  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  33  * SUCH DAMAGE.
  34  *
  35  *      @(#)regexec.c   8.3 (Berkeley) 3/20/94
  36  */
  37
  38 /*
  39  * the outer shell of llvm_regexec()
  40  *
  41  * This file includes engine.inc *twice*, after muchos fiddling with the
  42  * macros that code uses.  This lets the same code operate on two different
  43  * representations for state sets.
  44  */
  45 #include <sys/types.h>
  46 #include <stdio.h>
  47 #include <stdlib.h>
  48 #include <string.h>
  49 #include <limits.h>
  50 #include <ctype.h>
  51 #include "regex_impl.h"
  52
  53 #include "regutils.h"
  54 #include "regex2.h"
  55
  56 /* macros for manipulating states, small version */
  57 #define states  long
  58 #define states1 states          /* for later use in llvm_regexec() decision */
  59 #define CLEAR(v)        ((v) = 0)
  60 #define SET0(v, n)      ((v) &= ~((unsigned long)1 << (n)))
  61 #define SET1(v, n)      ((v) |= (unsigned long)1 << (n))
  62 #define ISSET(v, n)     (((v) & ((unsigned long)1 << (n))) != 0)
  63 #define ASSIGN(d, s)    ((d) = (s))
  64 #define EQ(a, b)        ((a) == (b))
  65 #define STATEVARS       long dummy      /* dummy version */
  66 #define STATESETUP(m, n)        /* nothing */
  67 #define STATETEARDOWN(m)        /* nothing */
  68 #define SETUP(v)        ((v) = 0)
  69 #define onestate        long
  70 #define INIT(o, n)      ((o) = (unsigned long)1 << (n))
  71 #define INC(o)          ((o) <<= 1)
  72 #define ISSTATEIN(v, o) (((v) & (o)) != 0)
  73 /* some abbreviations; note that some of these know variable names! */
  74 /* do "if I'm here, I can also be there" etc without branches */
  75 #define FWD(dst, src, n)        ((dst) |= ((unsigned long)(src)&(here)) << (n))
  76 #define BACK(dst, src, n)       ((dst) |= ((unsigned long)(src)&(here)) >> (n))
  77 #define ISSETBACK(v, n)         (((v) & ((unsigned long)here >> (n))) != 0)
  78 /* function names */
  79 #define SNAMES                  /* engine.inc looks after details */
  80
  81 #include "regengine.inc"
  82
  83 /* now undo things */
  84 #undef  states
  85 #undef  CLEAR
  86 #undef  SET0
  87 #undef  SET1
  88 #undef  ISSET
  89 #undef  ASSIGN
  90 #undef  EQ
  91 #undef  STATEVARS
  92 #undef  STATESETUP
  93 #undef  STATETEARDOWN
  94 #undef  SETUP
  95 #undef  onestate
  96 #undef  INIT
  97 #undef  INC
  98 #undef  ISSTATEIN
  99 #undef  FWD
 100 #undef  BACK
 101 #undef  ISSETBACK
 102 #undef  SNAMES
 103
 104 /* macros for manipulating states, large version */
 105 #define states  char *
 106 #define CLEAR(v)        memset(v, 0, m->g->nstates)
 107 #define SET0(v, n)      ((v)[n] = 0)
 108 #define SET1(v, n)      ((v)[n] = 1)
 109 #define ISSET(v, n)     ((v)[n])
 110 #define ASSIGN(d, s)    memmove(d, s, m->g->nstates)
 111 #define EQ(a, b)        (memcmp(a, b, m->g->nstates) == 0)
 112 #define STATEVARS       long vn; char *space
 113 #define STATESETUP(m, nv)       { (m)->space = malloc((nv)*(m)->g->nstates); \
 114                                 if ((m)->space == NULL) return(REG_ESPACE); \
 115                                 (m)->vn = 0; }
 116 #define STATETEARDOWN(m)        { free((m)->space); }
 117 #define SETUP(v)        ((v) = &m->space[m->vn++ * m->g->nstates])
 118 #define onestate        long
 119 #define INIT(o, n)      ((o) = (n))
 120 #define INC(o)  ((o)++)
 121 #define ISSTATEIN(v, o) ((v)[o])
 122 /* some abbreviations; note that some of these know variable names! */
 123 /* do "if I'm here, I can also be there" etc without branches */
 124 #define FWD(dst, src, n)        ((dst)[here+(n)] |= (src)[here])
 125 #define BACK(dst, src, n)       ((dst)[here-(n)] |= (src)[here])
 126 #define ISSETBACK(v, n) ((v)[here - (n)])
 127 /* function names */
 128 #define LNAMES                  /* flag */
 129
 130 #include "regengine.inc"
 131
 132 /*
 133  - llvm_regexec - interface for matching
 134  *
 135  * We put this here so we can exploit knowledge of the state representation
 136  * when choosing which matcher to call.  Also, by this point the matchers
 137  * have been prototyped.
 138  */
 139 int                             /* 0 success, REG_NOMATCH failure */
 140 llvm_regexec(const llvm_regex_t *preg, const char *string, size_t nmatch,
 141              llvm_regmatch_t pmatch[], int eflags)
 142 {
 143         struct re_guts *g = preg->re_g;
 144 #ifdef REDEBUG
 145 #       define  GOODFLAGS(f)    (f)
 146 #else
 147 #       define  GOODFLAGS(f)    ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
 148 #endif
 149
 150         if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
 151                 return(REG_BADPAT);
 152         assert(!(g->iflags&REGEX_BAD));
 153         if (g->iflags&REGEX_BAD)                /* backstop for no-debug case */
 154                 return(REG_BADPAT);
 155         eflags = GOODFLAGS(eflags);
 156
 157         if (g->nstates <= (long)(CHAR_BIT*sizeof(states1)) && !(eflags&REG_LARGE))
 158                 return(smatcher(g, (char *)string, nmatch, pmatch, eflags));
 159         else
 160                 return(lmatcher(g, (char *)string, nmatch, pmatch, eflags));
 161 }