1 /*- 2 * SPDX-License-Identifier: BSD-3-Clause 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 36 /* 37 * the outer shell of regexec() 38 * 39 * This file includes engine.c three times, after muchos fiddling with the 40 * macros that code uses. This lets the same code operate on two different 41 * representations for state sets and characters. 42 */ 43 #include <sys/types.h> 44 #include <stdio.h> 45 #include <stdlib.h> 46 #include <string.h> 47 #include <limits.h> 48 #include <ctype.h> 49 #include <regex.h> 50 #include <wchar.h> 51 #include <wctype.h> 52 53 #include "utils.h" 54 #include "regex2.h" 55 56 static int nope __unused = 0; /* for use in asserts; shuts lint up */ 57 58 static __inline size_t 59 xmbrtowc(wint_t *wi, const char *s, size_t n, mbstate_t *mbs, wint_t dummy) 60 { 61 size_t nr; 62 wchar_t wc; 63 64 nr = mbrtowc(&wc, s, n, mbs); 65 if (wi != NULL) 66 *wi = wc; 67 if (nr == 0) 68 return (1); 69 else if (nr == (size_t)-1 || nr == (size_t)-2) { 70 memset(mbs, 0, sizeof(*mbs)); 71 if (wi != NULL) 72 *wi = dummy; 73 return (1); 74 } else 75 return (nr); 76 } 77 78 static __inline size_t 79 xmbrtowc_dummy(wint_t *wi, 80 const char *s, 81 size_t n __unused, 82 mbstate_t *mbs __unused, 83 wint_t dummy __unused) 84 { 85 86 if (wi != NULL) 87 *wi = (unsigned char)*s; 88 return (1); 89 } 90 91 /* macros for manipulating states, small version */ 92 #define states1 long /* for later use in regexec() decision */ 93 #define states states1 94 #define CLEAR(v) ((v) = 0) 95 #define SET0(v, n) ((v) &= ~((unsigned long)1 << (n))) 96 #define SET1(v, n) ((v) |= (unsigned long)1 << (n)) 97 #define ISSET(v, n) (((v) & ((unsigned long)1 << (n))) != 0) 98 #define ASSIGN(d, s) ((d) = (s)) 99 #define EQ(a, b) ((a) == (b)) 100 #define STATEVARS long dummy /* dummy version */ 101 #define STATESETUP(m, n) /* nothing */ 102 #define STATETEARDOWN(m) /* nothing */ 103 #define SETUP(v) ((v) = 0) 104 #define onestate long 105 #define INIT(o, n) ((o) = (unsigned long)1 << (n)) 106 #define INC(o) ((o) <<= 1) 107 #define ISSTATEIN(v, o) (((v) & (o)) != 0) 108 /* some abbreviations; note that some of these know variable names! */ 109 /* do "if I'm here, I can also be there" etc without branches */ 110 #define FWD(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) << (n)) 111 #define BACK(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) >> (n)) 112 #define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0) 113 /* no multibyte support */ 114 #define XMBRTOWC xmbrtowc_dummy 115 #define ZAPSTATE(mbs) ((void)(mbs)) 116 /* function names */ 117 #define SNAMES /* engine.c looks after details */ 118 119 #include "engine.c" 120 121 /* now undo things */ 122 #undef states 123 #undef CLEAR 124 #undef SET0 125 #undef SET1 126 #undef ISSET 127 #undef ASSIGN 128 #undef EQ 129 #undef STATEVARS 130 #undef STATESETUP 131 #undef STATETEARDOWN 132 #undef SETUP 133 #undef onestate 134 #undef INIT 135 #undef INC 136 #undef ISSTATEIN 137 #undef FWD 138 #undef BACK 139 #undef ISSETBACK 140 #undef SNAMES 141 #undef XMBRTOWC 142 #undef ZAPSTATE 143 144 /* macros for manipulating states, large version */ 145 #define states char * 146 #define CLEAR(v) memset(v, 0, m->g->nstates) 147 #define SET0(v, n) ((v)[n] = 0) 148 #define SET1(v, n) ((v)[n] = 1) 149 #define ISSET(v, n) ((v)[n]) 150 #define ASSIGN(d, s) memcpy(d, s, m->g->nstates) 151 #define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0) 152 #define STATEVARS long vn; char *space 153 #define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \ 154 if ((m)->space == NULL) return(REG_ESPACE); \ 155 (m)->vn = 0; } 156 #define STATETEARDOWN(m) { free((m)->space); } 157 #define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates]) 158 #define onestate long 159 #define INIT(o, n) ((o) = (n)) 160 #define INC(o) ((o)++) 161 #define ISSTATEIN(v, o) ((v)[o]) 162 /* some abbreviations; note that some of these know variable names! */ 163 /* do "if I'm here, I can also be there" etc without branches */ 164 #define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here]) 165 #define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here]) 166 #define ISSETBACK(v, n) ((v)[here - (n)]) 167 /* no multibyte support */ 168 #define XMBRTOWC xmbrtowc_dummy 169 #define ZAPSTATE(mbs) ((void)(mbs)) 170 /* function names */ 171 #define LNAMES /* flag */ 172 173 #include "engine.c" 174 175 /* multibyte character & large states version */ 176 #undef LNAMES 177 #undef XMBRTOWC 178 #undef ZAPSTATE 179 #define XMBRTOWC xmbrtowc 180 #define ZAPSTATE(mbs) memset((mbs), 0, sizeof(*(mbs))) 181 #define MNAMES 182 183 #include "engine.c" 184 185 /* 186 - regexec - interface for matching 187 = extern int regexec(const regex_t *, const char *, size_t, \ 188 = regmatch_t [], int); 189 = #define REG_NOTBOL 00001 190 = #define REG_NOTEOL 00002 191 = #define REG_STARTEND 00004 192 = #define REG_TRACE 00400 // tracing of execution 193 = #define REG_LARGE 01000 // force large representation 194 = #define REG_BACKR 02000 // force use of backref code 195 * 196 * We put this here so we can exploit knowledge of the state representation 197 * when choosing which matcher to call. Also, by this point the matchers 198 * have been prototyped. 199 */ 200 int /* 0 success, REG_NOMATCH failure */ 201 regexec(const regex_t * __restrict preg, 202 const char * __restrict string, 203 size_t nmatch, 204 regmatch_t pmatch[__restrict], 205 int eflags) 206 { 207 struct re_guts *g = preg->re_g; 208 #ifdef REDEBUG 209 # define GOODFLAGS(f) (f) 210 #else 211 # define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND)) 212 #endif 213 214 if (preg->re_magic != MAGIC1 || g->magic != MAGIC2) 215 return(REG_BADPAT); 216 assert(!(g->iflags&BAD)); 217 if (g->iflags&BAD) /* backstop for no-debug case */ 218 return(REG_BADPAT); 219 eflags = GOODFLAGS(eflags); 220 221 if (MB_CUR_MAX > 1) 222 return(mmatcher(g, string, nmatch, pmatch, eflags)); 223 else if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags®_LARGE)) 224 return(smatcher(g, string, nmatch, pmatch, eflags)); 225 else 226 return(lmatcher(g, string, nmatch, pmatch, eflags)); 227 } 228