regexec.c revision 111010
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 * @(#)regexec.c 8.3 (Berkeley) 3/20/94 38 */ 39 40#if defined(LIBC_SCCS) && !defined(lint) 41static char sccsid[] = "@(#)regexec.c 8.3 (Berkeley) 3/20/94"; 42#endif /* LIBC_SCCS and not lint */ 43#include <sys/cdefs.h> 44__FBSDID("$FreeBSD: head/lib/libc/regex/regexec.c 111010 2003-02-16 17:29:11Z nectar $"); 45 46/* 47 * the outer shell of regexec() 48 * 49 * This file includes engine.c *twice*, after muchos fiddling with the 50 * macros that code uses. This lets the same code operate on two different 51 * representations for state sets. 52 */ 53#include <sys/types.h> 54#include <stdio.h> 55#include <stdlib.h> 56#include <string.h> 57#include <limits.h> 58#include <ctype.h> 59#include <regex.h> 60 61#include "utils.h" 62#include "regex2.h" 63 64static int nope __unused = 0; /* for use in asserts; shuts lint up */ 65 66/* macros for manipulating states, small version */ 67#define states long 68#define states1 states /* for later use in regexec() decision */ 69#define CLEAR(v) ((v) = 0) 70#define SET0(v, n) ((v) &= ~((unsigned long)1 << (n))) 71#define SET1(v, n) ((v) |= (unsigned long)1 << (n)) 72#define ISSET(v, n) (((v) & ((unsigned long)1 << (n))) != 0) 73#define ASSIGN(d, s) ((d) = (s)) 74#define EQ(a, b) ((a) == (b)) 75#define STATEVARS long dummy /* dummy version */ 76#define STATESETUP(m, n) /* nothing */ 77#define STATETEARDOWN(m) /* nothing */ 78#define SETUP(v) ((v) = 0) 79#define onestate long 80#define INIT(o, n) ((o) = (unsigned long)1 << (n)) 81#define INC(o) ((o) <<= 1) 82#define ISSTATEIN(v, o) (((v) & (o)) != 0) 83/* some abbreviations; note that some of these know variable names! */ 84/* do "if I'm here, I can also be there" etc without branches */ 85#define FWD(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) << (n)) 86#define BACK(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) >> (n)) 87#define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0) 88/* function names */ 89#define SNAMES /* engine.c looks after details */ 90 91#include "engine.c" 92 93/* now undo things */ 94#undef states 95#undef CLEAR 96#undef SET0 97#undef SET1 98#undef ISSET 99#undef ASSIGN 100#undef EQ 101#undef STATEVARS 102#undef STATESETUP 103#undef STATETEARDOWN 104#undef SETUP 105#undef onestate 106#undef INIT 107#undef INC 108#undef ISSTATEIN 109#undef FWD 110#undef BACK 111#undef ISSETBACK 112#undef SNAMES 113 114/* macros for manipulating states, large version */ 115#define states char * 116#define CLEAR(v) memset(v, 0, m->g->nstates) 117#define SET0(v, n) ((v)[n] = 0) 118#define SET1(v, n) ((v)[n] = 1) 119#define ISSET(v, n) ((v)[n]) 120#define ASSIGN(d, s) memcpy(d, s, m->g->nstates) 121#define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0) 122#define STATEVARS long vn; char *space 123#define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \ 124 if ((m)->space == NULL) return(REG_ESPACE); \ 125 (m)->vn = 0; } 126#define STATETEARDOWN(m) { free((m)->space); } 127#define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates]) 128#define onestate long 129#define INIT(o, n) ((o) = (n)) 130#define INC(o) ((o)++) 131#define ISSTATEIN(v, o) ((v)[o]) 132/* some abbreviations; note that some of these know variable names! */ 133/* do "if I'm here, I can also be there" etc without branches */ 134#define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here]) 135#define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here]) 136#define ISSETBACK(v, n) ((v)[here - (n)]) 137/* function names */ 138#define LNAMES /* flag */ 139 140#include "engine.c" 141 142/* 143 - regexec - interface for matching 144 = extern int regexec(const regex_t *, const char *, size_t, \ 145 = regmatch_t [], int); 146 = #define REG_NOTBOL 00001 147 = #define REG_NOTEOL 00002 148 = #define REG_STARTEND 00004 149 = #define REG_TRACE 00400 // tracing of execution 150 = #define REG_LARGE 01000 // force large representation 151 = #define REG_BACKR 02000 // force use of backref code 152 * 153 * We put this here so we can exploit knowledge of the state representation 154 * when choosing which matcher to call. Also, by this point the matchers 155 * have been prototyped. 156 */ 157int /* 0 success, REG_NOMATCH failure */ 158regexec(preg, string, nmatch, pmatch, eflags) 159const regex_t * __restrict preg; 160const char * __restrict string; 161size_t nmatch; 162regmatch_t pmatch[__restrict]; 163int eflags; 164{ 165 struct re_guts *g = preg->re_g; 166#ifdef REDEBUG 167# define GOODFLAGS(f) (f) 168#else 169# define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND)) 170#endif 171 172 if (preg->re_magic != MAGIC1 || g->magic != MAGIC2) 173 return(REG_BADPAT); 174 assert(!(g->iflags&BAD)); 175 if (g->iflags&BAD) /* backstop for no-debug case */ 176 return(REG_BADPAT); 177 eflags = GOODFLAGS(eflags); 178 179 if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags®_LARGE)) 180 return(smatcher(g, (char *)string, nmatch, pmatch, eflags)); 181 else 182 return(lmatcher(g, (char *)string, nmatch, pmatch, eflags)); 183} 184