1 /* 2 * Copyright 2010 Nexenta Systems, Inc. All rights reserved. 3 * Copyright (c) 1992, 1993, 1994 Henry Spencer. 4 * Copyright (c) 1992, 1993, 1994 5 * The Regents of the University of California. All rights reserved. 6 * 7 * This code is derived from software contributed to Berkeley by 8 * Henry Spencer. 9 * 10 * Redistribution and use in source and binary forms, with or without 11 * modification, are permitted provided that the following conditions 12 * are met: 13 * 1. Redistributions of source code must retain the above copyright 14 * notice, this list of conditions and the following disclaimer. 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in the 17 * documentation and/or other materials provided with the distribution. 18 * 3. Neither the name of the University nor the names of its contributors 19 * may be used to endorse or promote products derived from this software 20 * without specific prior written permission. 21 * 22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32 * SUCH DAMAGE. 33 */ 34 35 /* 36 * the outer shell of regexec() 37 * 38 * This file includes engine.c three times, after muchos fiddling with the 39 * macros that code uses. This lets the same code operate on two different 40 * representations for state sets and characters. 41 */ 42 #include "lint.h" 43 #include "file64.h" 44 #include <sys/types.h> 45 #include <stdio.h> 46 #include <stdlib.h> 47 #include <string.h> 48 #include <limits.h> 49 #include <ctype.h> 50 #include <regex.h> 51 #include <wchar.h> 52 #include <wctype.h> 53 #include <assert.h> 54 55 #include "utils.h" 56 #include "regex2.h" 57 58 static 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 (void) memset(mbs, 0, sizeof (*mbs)); 71 if (wi != NULL) 72 *wi = dummy; 73 return (1); 74 } else 75 return (nr); 76 } 77 78 static size_t 79 xmbrtowc_dummy(wint_t *wi, const char *s, size_t n __unused, 80 mbstate_t *mbs __unused, wint_t dummy __unused) 81 { 82 if (wi != NULL) 83 *wi = (unsigned char)*s; 84 return (1); 85 } 86 87 /* macros for manipulating states, small version */ 88 #define states long 89 #define states1 states /* for later use in regexec() decision */ 90 #define CLEAR(v) ((v) = 0) 91 #define SET0(v, n) ((v) &= ~((unsigned long)1 << (n))) 92 #define SET1(v, n) ((v) |= (unsigned long)1 << (n)) 93 #define ISSET(v, n) (((v) & ((unsigned long)1 << (n))) != 0) 94 #define ASSIGN(d, s) ((d) = (s)) 95 #define EQ(a, b) ((a) == (b)) 96 #define STATEVARS long dummy /* dummy version */ 97 #define STATESETUP(m, n) /* nothing */ 98 #define STATETEARDOWN(m) /* nothing */ 99 #define SETUP(v) ((v) = 0) 100 #define onestate long 101 #define INIT(o, n) ((o) = (unsigned long)1 << (n)) 102 #define INC(o) ((o) <<= 1) 103 #define ISSTATEIN(v, o) (((v) & (o)) != 0) 104 /* some abbreviations; note that some of these know variable names! */ 105 /* do "if I'm here, I can also be there" etc without branches */ 106 #define FWD(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) << (n)) 107 #define BACK(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) >> (n)) 108 #define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0) 109 /* no multibyte support */ 110 #define XMBRTOWC xmbrtowc_dummy 111 #define ZAPSTATE(mbs) ((void)(mbs)) 112 /* function names */ 113 #define SNAMES /* engine.c looks after details */ 114 115 #include "engine.c" 116 117 /* now undo things */ 118 #undef states 119 #undef CLEAR 120 #undef SET0 121 #undef SET1 122 #undef ISSET 123 #undef ASSIGN 124 #undef EQ 125 #undef STATEVARS 126 #undef STATESETUP 127 #undef STATETEARDOWN 128 #undef SETUP 129 #undef onestate 130 #undef INIT 131 #undef INC 132 #undef ISSTATEIN 133 #undef FWD 134 #undef BACK 135 #undef ISSETBACK 136 #undef SNAMES 137 #undef XMBRTOWC 138 #undef ZAPSTATE 139 140 /* macros for manipulating states, large version */ 141 #define states char * 142 #define CLEAR(v) (void) memset(v, 0, m->g->nstates) 143 #define SET0(v, n) ((v)[n] = 0) 144 #define SET1(v, n) ((v)[n] = 1) 145 #define ISSET(v, n) ((v)[n]) 146 #define ASSIGN(d, s) (void) memcpy(d, s, m->g->nstates) 147 #define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0) 148 #define STATEVARS long vn; char *space 149 #define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \ 150 if ((m)->space == NULL) \ 151 return (REG_ESPACE); \ 152 (m)->vn = 0; } 153 #define STATETEARDOWN(m) { free((m)->space); } 154 #define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates]) 155 #define onestate long 156 #define INIT(o, n) ((o) = (n)) 157 #define INC(o) ((o)++) 158 #define ISSTATEIN(v, o) ((v)[o]) 159 /* some abbreviations; note that some of these know variable names! */ 160 /* do "if I'm here, I can also be there" etc without branches */ 161 #define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here]) 162 #define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here]) 163 #define ISSETBACK(v, n) ((v)[here - (n)]) 164 /* no multibyte support */ 165 #define XMBRTOWC xmbrtowc_dummy 166 #define ZAPSTATE(mbs) ((void)(mbs)) 167 /* function names */ 168 #define LNAMES /* flag */ 169 170 #include "engine.c" 171 172 /* multibyte character & large states version */ 173 #undef LNAMES 174 #undef XMBRTOWC 175 #undef ZAPSTATE 176 #define XMBRTOWC xmbrtowc 177 #define ZAPSTATE(mbs) (void) memset((mbs), 0, sizeof (*(mbs))) 178 #define MNAMES 179 180 #include "engine.c" 181 182 /* 183 * regexec - interface for matching 184 * 185 * We put this here so we can exploit knowledge of the state representation 186 * when choosing which matcher to call. Also, by this point the matchers 187 * have been prototyped. 188 */ 189 int /* 0 success, REG_NOMATCH failure */ 190 regexec(const regex_t *_RESTRICT_KYWD preg, const char *_RESTRICT_KYWD string, 191 size_t nmatch, regmatch_t pmatch[_RESTRICT_KYWD], int eflags) 192 { 193 struct re_guts *g = preg->re_g; 194 #ifdef REDEBUG 195 #define GOODFLAGS(f) (f) 196 #else 197 #ifdef REG_STARTEND 198 #define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND)) 199 #else 200 #define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL)) 201 #endif 202 #endif 203 204 if (preg->re_magic != MAGIC1 || g->magic != MAGIC2) 205 return (REG_BADPAT); 206 assert(!(g->iflags&BAD)); 207 if (g->iflags&BAD) /* backstop for no-debug case */ 208 return (REG_BADPAT); 209 eflags = GOODFLAGS(eflags); 210 211 if (MB_CUR_MAX > 1) 212 return (mmatcher(g, string, nmatch, pmatch, eflags)); 213 else if (g->nstates <= CHAR_BIT*sizeof (states1) && !(eflags®_LARGE)) 214 return (smatcher(g, string, nmatch, pmatch, eflags)); 215 else 216 return (lmatcher(g, string, nmatch, pmatch, eflags)); 217 } 218