1 /* $NetBSD: regexec.c,v 1.4 2009/10/31 20:11:53 dsl Exp $ */ 2 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 of the University of Toronto. 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 8.2 (Berkeley) 3/16/94 36 */ 37 38 #if defined(LIBC_SCCS) && !defined(lint) 39 static char sccsid[] = "@(#)regexec.c 8.2 (Berkeley) 3/16/94"; 40 #endif /* LIBC_SCCS and not lint */ 41 42 /* 43 * the outer shell of regexec() 44 * 45 * This file includes engine.c *twice*, after muchos fiddling with the 46 * macros that code uses. This lets the same code operate on two different 47 * representations for state sets. 48 */ 49 #include <sys/types.h> 50 #include <stdio.h> 51 #include <stdlib.h> 52 #include <string.h> 53 #include <limits.h> 54 #include <ctype.h> 55 #include <regex.h> 56 57 #include "utils.h" 58 #include "regex2.h" 59 60 /* macros for manipulating states, small version */ 61 #define states int 62 #define states1 int /* for later use in regexec() decision */ 63 #define CLEAR(v) ((v) = 0) 64 #define SET0(v, n) ((v) &= ~(1 << (n))) 65 #define SET1(v, n) ((v) |= 1 << (n)) 66 #define ISSET(v, n) ((v) & (1 << (n))) 67 #define ASSIGN(d, s) ((d) = (s)) 68 #define EQ(a, b) ((a) == (b)) 69 #define STATEVARS int dummy /* dummy version */ 70 #define STATESETUP(m, n) /* nothing */ 71 #define STATETEARDOWN(m) /* nothing */ 72 #define SETUP(v) ((v) = 0) 73 #define onestate int 74 #define INIT(o, n) ((o) = (unsigned)1 << (n)) 75 #define INC(o) ((o) <<= 1) 76 #define ISSTATEIN(v, o) ((v) & (o)) 77 /* some abbreviations; note that some of these know variable names! */ 78 /* do "if I'm here, I can also be there" etc without branches */ 79 #define FWD(dst, src, n) ((dst) |= ((unsigned)(src)&(here)) << (n)) 80 #define BACK(dst, src, n) ((dst) |= ((unsigned)(src)&(here)) >> (n)) 81 #define ISSETBACK(v, n) ((v) & ((unsigned)here >> (n))) 82 /* function names */ 83 #define SNAMES /* engine.c looks after details */ 84 85 #include "engine.c" 86 87 /* now undo things */ 88 #undef states 89 #undef CLEAR 90 #undef SET0 91 #undef SET1 92 #undef ISSET 93 #undef ASSIGN 94 #undef EQ 95 #undef STATEVARS 96 #undef STATESETUP 97 #undef STATETEARDOWN 98 #undef SETUP 99 #undef onestate 100 #undef INIT 101 #undef INC 102 #undef ISSTATEIN 103 #undef FWD 104 #undef BACK 105 #undef ISSETBACK 106 #undef SNAMES 107 108 /* macros for manipulating states, large version */ 109 #define states char * 110 #define CLEAR(v) memset(v, 0, m->g->nstates) 111 #define SET0(v, n) ((v)[n] = 0) 112 #define SET1(v, n) ((v)[n] = 1) 113 #define ISSET(v, n) ((v)[n]) 114 #define ASSIGN(d, s) memcpy(d, s, m->g->nstates) 115 #define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0) 116 #define STATEVARS int vn; char *space 117 #define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \ 118 if ((m)->space == NULL) return(REG_ESPACE); \ 119 (m)->vn = 0; } 120 #define STATETEARDOWN(m) { free((m)->space); } 121 #define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates]) 122 #define onestate int 123 #define INIT(o, n) ((o) = (n)) 124 #define INC(o) ((o)++) 125 #define ISSTATEIN(v, o) ((v)[o]) 126 /* some abbreviations; note that some of these know variable names! */ 127 /* do "if I'm here, I can also be there" etc without branches */ 128 #define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here]) 129 #define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here]) 130 #define ISSETBACK(v, n) ((v)[here - (n)]) 131 /* function names */ 132 #define LNAMES /* flag */ 133 134 #include "engine.c" 135 136 /* 137 - regexec - interface for matching 138 = extern int regexec(const regex_t *, const char *, size_t, \ 139 = regmatch_t [], int); 140 = #define REG_NOTBOL 00001 141 = #define REG_NOTEOL 00002 142 = #define REG_STARTEND 00004 143 = #define REG_TRACE 00400 // tracing of execution 144 = #define REG_LARGE 01000 // force large representation 145 = #define REG_BACKR 02000 // force use of backref code 146 * 147 * We put this here so we can exploit knowledge of the state representation 148 * when choosing which matcher to call. Also, by this point the matchers 149 * have been prototyped. 150 */ 151 int /* 0 success, REG_NOMATCH failure */ 152 regexec(const regex_t *preg, const RCHAR_T *string, size_t nmatch, 153 regmatch_t *pmatch, int eflags) 154 { 155 struct re_guts *g = preg->re_g; 156 #ifdef REDEBUG 157 # define GOODFLAGS(f) (f) 158 #else 159 # define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND)) 160 #endif 161 162 if (preg->re_magic != MAGIC1 || g->magic != MAGIC2) 163 return(REG_BADPAT); 164 assert(!(g->iflags&BAD)); 165 if (g->iflags&BAD) /* backstop for no-debug case */ 166 return(REG_BADPAT); 167 eflags = GOODFLAGS(eflags); 168 169 if (g->nstates <= (int)(CHAR_BIT*sizeof(states1)) && !(eflags®_LARGE)) 170 return(smatcher(g, string, nmatch, pmatch, eflags)); 171 else 172 return(lmatcher(g, string, nmatch, pmatch, eflags)); 173 } 174