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. 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 38 #if defined(LIBC_SCCS) && !defined(lint) 39 static char rcsid[] = "$OpenBSD: regexec.c,v 1.4 1996/09/15 09:31:27 tholo Exp $"; 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 long 62 #define states1 states /* for later use in regexec() decision */ 63 #define CLEAR(v) ((v) = 0) 64 #define SET0(v, n) ((v) &= ~((unsigned long)1 << (n))) 65 #define SET1(v, n) ((v) |= (unsigned long)1 << (n)) 66 #define ISSET(v, n) (((v) & ((unsigned long)1 << (n))) != 0) 67 #define ASSIGN(d, s) ((d) = (s)) 68 #define EQ(a, b) ((a) == (b)) 69 #define STATEVARS long dummy /* dummy version */ 70 #define STATESETUP(m, n) /* nothing */ 71 #define STATETEARDOWN(m) /* nothing */ 72 #define SETUP(v) ((v) = 0) 73 #define onestate long 74 #define INIT(o, n) ((o) = (unsigned long)1 << (n)) 75 #define INC(o) ((o) = (unsigned long)(o) << 1) 76 #define ISSTATEIN(v, o) (((v) & (o)) != 0) 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 long)(src)&(here)) << (n)) 80 #define BACK(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) >> (n)) 81 #define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0) 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 long 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 long 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(preg, string, nmatch, pmatch, eflags) 153 const regex_t *preg; 154 const char *string; 155 size_t nmatch; 156 regmatch_t pmatch[]; 157 int eflags; 158 { 159 register struct re_guts *g = preg->re_g; 160 #ifdef REDEBUG 161 # define GOODFLAGS(f) (f) 162 #else 163 # define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND)) 164 #endif 165 166 if (preg->re_magic != MAGIC1 || g->magic != MAGIC2) 167 return(REG_BADPAT); 168 assert(!(g->iflags&BAD)); 169 if (g->iflags&BAD) /* backstop for no-debug case */ 170 return(REG_BADPAT); 171 eflags = GOODFLAGS(eflags); 172 173 if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags®_LARGE)) 174 return(smatcher(g, (char *)string, nmatch, pmatch, eflags)); 175 else 176 return(lmatcher(g, (char *)string, nmatch, pmatch, eflags)); 177 } 178