1 /* $NetBSD: regexec.c,v 1.26 2021/02/26 19:24:47 christos Exp $ */ 2 3 /*- 4 * SPDX-License-Identifier: BSD-3-Clause 5 * 6 * Copyright (c) 1992, 1993, 1994 Henry Spencer. 7 * Copyright (c) 1992, 1993, 1994 8 * The Regents of the University of California. All rights reserved. 9 * 10 * This code is derived from software contributed to Berkeley by 11 * Henry Spencer. 12 * 13 * Redistribution and use in source and binary forms, with or without 14 * modification, are permitted provided that the following conditions 15 * are met: 16 * 1. Redistributions of source code must retain the above copyright 17 * notice, this list of conditions and the following disclaimer. 18 * 2. Redistributions in binary form must reproduce the above copyright 19 * notice, this list of conditions and the following disclaimer in the 20 * documentation and/or other materials provided with the distribution. 21 * 3. 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 HAVE_NBTOOL_CONFIG_H 41 #include "nbtool_config.h" 42 #endif 43 44 #include <sys/cdefs.h> 45 #if 0 46 static char sccsid[] = "@(#)regexec.c 8.3 (Berkeley) 3/20/94"; 47 __FBSDID("$FreeBSD: head/lib/libc/regex/regexec.c 326025 2017-11-20 19:49:47Z pfg $"); 48 #endif 49 __RCSID("$NetBSD: regexec.c,v 1.26 2021/02/26 19:24:47 christos Exp $"); 50 51 /* 52 * the outer shell of regexec() 53 * 54 * This file includes engine.c three times, after muchos fiddling with the 55 * macros that code uses. This lets the same code operate on two different 56 * representations for state sets and characters. 57 */ 58 59 #ifndef LIBHACK 60 #include "namespace.h" 61 #endif 62 #include <sys/types.h> 63 #include <stdio.h> 64 #include <stdlib.h> 65 #include <string.h> 66 #include <limits.h> 67 #include <ctype.h> 68 #include <regex.h> 69 70 #if defined(__weak_alias) && !defined(LIBHACK) 71 __weak_alias(regexec,_regexec) 72 #endif 73 74 #include "utils.h" 75 #include "regex2.h" 76 77 static __inline size_t 78 xmbrtowc(wint_t *wi, const char *s, size_t n, mbstate_t *mbs, wint_t dummy) 79 { 80 #ifdef NLS 81 size_t nr; 82 wchar_t wc; 83 84 nr = mbrtowc(&wc, s, n, mbs); 85 if (wi != NULL) 86 *wi = wc; 87 if (nr == 0) 88 return (1); 89 else if (nr == (size_t)-1 || nr == (size_t)-2) { 90 memset(mbs, 0, sizeof(*mbs)); 91 if (wi != NULL) 92 *wi = dummy; 93 return (1); 94 } else 95 return (nr); 96 #else 97 if (wi) 98 *wi = *s; 99 return 1; 100 #endif 101 } 102 103 static __inline size_t 104 xmbrtowc_dummy(wint_t *wi, 105 const char *s, 106 size_t n __unused, 107 mbstate_t *mbs __unused, 108 wint_t dummy __unused) 109 { 110 111 if (wi != NULL) 112 *wi = (unsigned char)*s; 113 return (1); 114 } 115 116 /* macros for manipulating states, small version */ 117 #define states long 118 #define states1 states /* for later use in regexec() decision */ 119 #define CLEAR(v) ((v) = 0) 120 #define SET0(v, n) ((v) &= ~((unsigned long)1 << (n))) 121 #define SET1(v, n) ((v) |= (unsigned long)1 << (n)) 122 #define ISSET(v, n) (((v) & ((unsigned long)1 << (n))) != 0) 123 #define ASSIGN(d, s) ((d) = (s)) 124 #define EQ(a, b) ((a) == (b)) 125 #define STATEVARS long dummy /* dummy version */ 126 #define STATESETUP(m, n) /* nothing */ 127 #define STATETEARDOWN(m) /* nothing */ 128 #define SETUP(v) ((v) = 0) 129 #define onestate long 130 #define INIT(o, n) ((o) = (unsigned long)1 << (n)) 131 #define INC(o) ((o) <<= 1) 132 #define ISSTATEIN(v, o) (((v) & (o)) != 0) 133 /* some abbreviations; note that some of these know variable names! */ 134 /* do "if I'm here, I can also be there" etc without branches */ 135 #define FWD(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) << (n)) 136 #define BACK(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) >> (n)) 137 #define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0) 138 /* no multibyte support */ 139 #define XMBRTOWC xmbrtowc_dummy 140 #define ZAPSTATE(mbs) ((void)(mbs)) 141 /* function names */ 142 #define SNAMES /* engine.c looks after details */ 143 144 #include "engine.c" 145 146 /* now undo things */ 147 #undef states 148 #undef CLEAR 149 #undef SET0 150 #undef SET1 151 #undef ISSET 152 #undef ASSIGN 153 #undef EQ 154 #undef STATEVARS 155 #undef STATESETUP 156 #undef STATETEARDOWN 157 #undef SETUP 158 #undef onestate 159 #undef INIT 160 #undef INC 161 #undef ISSTATEIN 162 #undef FWD 163 #undef BACK 164 #undef ISSETBACK 165 #undef SNAMES 166 #undef XMBRTOWC 167 #undef ZAPSTATE 168 169 /* macros for manipulating states, large version */ 170 #define states char * 171 #define CLEAR(v) memset(v, 0, m->g->nstates) 172 #define SET0(v, n) ((v)[n] = 0) 173 #define SET1(v, n) ((v)[n] = 1) 174 #define ISSET(v, n) ((v)[n]) 175 #define ASSIGN(d, s) memcpy(d, s, m->g->nstates) 176 #define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0) 177 #define STATEVARS long vn; char *space 178 #define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \ 179 if ((m)->space == NULL) return(REG_ESPACE); \ 180 (m)->vn = 0; } 181 #define STATETEARDOWN(m) { free((m)->space); } 182 #define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates]) 183 #define onestate long 184 #define INIT(o, n) ((o) = (n)) 185 #define INC(o) ((o)++) 186 #define ISSTATEIN(v, o) ((v)[o]) 187 /* some abbreviations; note that some of these know variable names! */ 188 /* do "if I'm here, I can also be there" etc without branches */ 189 #define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here]) 190 #define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here]) 191 #define ISSETBACK(v, n) ((v)[here - (n)]) 192 /* no multibyte support */ 193 #define XMBRTOWC xmbrtowc_dummy 194 #define ZAPSTATE(mbs) ((void)(mbs)) 195 /* function names */ 196 #define LNAMES /* flag */ 197 198 #include "engine.c" 199 200 /* multibyte character & large states version */ 201 #undef LNAMES 202 #undef XMBRTOWC 203 #undef ZAPSTATE 204 #define XMBRTOWC xmbrtowc 205 #define ZAPSTATE(mbs) memset((mbs), 0, sizeof(*(mbs))) 206 #define MNAMES 207 208 #include "engine.c" 209 210 /* 211 - regexec - interface for matching 212 = extern int regexec(const regex_t *, const char *, size_t, \ 213 = regmatch_t [], int); 214 = #define REG_NOTBOL 00001 215 = #define REG_NOTEOL 00002 216 = #define REG_STARTEND 00004 217 = #define REG_TRACE 00400 // tracing of execution 218 = #define REG_LARGE 01000 // force large representation 219 = #define REG_BACKR 02000 // force use of backref code 220 * 221 * We put this here so we can exploit knowledge of the state representation 222 * when choosing which matcher to call. Also, by this point the matchers 223 * have been prototyped. 224 */ 225 int /* 0 success, REG_NOMATCH failure */ 226 regexec(const regex_t * __restrict preg, 227 const char * __restrict string, 228 size_t nmatch, 229 regmatch_t pmatch[__restrict], 230 int eflags) 231 { 232 struct re_guts *g = preg->re_g; 233 #ifdef REDEBUG 234 # define GOODFLAGS(f) (f) 235 #else 236 # define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND)) 237 #endif 238 _DIAGASSERT(preg != NULL); 239 _DIAGASSERT(string != NULL); 240 241 if (preg->re_magic != MAGIC1 || g->magic != MAGIC2) 242 return(REG_BADPAT); 243 assert(!(g->iflags&BAD)); 244 if (g->iflags&BAD) /* backstop for no-debug case */ 245 return(REG_BADPAT); 246 eflags = GOODFLAGS(eflags); 247 248 if (MB_CUR_MAX > 1) 249 return(mmatcher(g, string, nmatch, pmatch, eflags)); 250 else if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags®_LARGE)) 251 return(smatcher(g, string, nmatch, pmatch, eflags)); 252 else 253 return(lmatcher(g, string, nmatch, pmatch, eflags)); 254 } 255