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 * 4. Neither the name of the University nor the names of its contributors
18 * may be used to endorse or promote products derived from this software
19 * without specific prior written permission.
20 *
21 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
22 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
23 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
24 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
25 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
26 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
27 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
28 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
29 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
30 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
31 * SUCH DAMAGE.
32 *
33 * @(#)regexec.c 8.3 (Berkeley) 3/20/94
34 */
35
36 #ifndef _NO_REGEX
37
38 #if defined(LIBC_SCCS) && !defined(lint)
39 static char sccsid[] = "@(#)regexec.c 8.3 (Berkeley) 3/20/94";
40 #endif /* LIBC_SCCS and not lint */
41 #include <sys/cdefs.h>
42
43 /*
44 * the outer shell of regexec()
45 *
46 * This file includes engine.c *twice*, after muchos fiddling with the
47 * macros that code uses. This lets the same code operate on two different
48 * representations for state sets.
49 */
50 #include <sys/types.h>
51 #include <stdio.h>
52 #include <stdlib.h>
53 #include <string.h>
54 #include <limits.h>
55 #include <ctype.h>
56 #include <regex.h>
57
58 #include "utils.h"
59 #include "regex2.h"
60
61 #ifndef NDEBUG
62 static int nope = 0; /* for use in asserts; shuts lint up */
63 #endif
64
65 /* macros for manipulating states, small version */
66 #define states long
67 #define states1 states /* for later use in regexec() decision */
68 #define CLEAR(v) ((v) = 0)
69 #define SET0(v, n) ((v) &= ~((unsigned long)1 << (n)))
70 #define SET1(v, n) ((v) |= (unsigned long)1 << (n))
71 #define ISSET(v, n) (((v) & ((unsigned long)1 << (n))) != 0)
72 #define ASSIGN(d, s) ((d) = (s))
73 #define EQ(a, b) ((a) == (b))
74 #define STATEVARS long dummy /* dummy version */
75 #define STATESETUP(m, n) /* nothing */
76 #define STATETEARDOWN(m) /* nothing */
77 #define SETUP(v) ((v) = 0)
78 #define onestate long
79 #define INIT(o, n) ((o) = (unsigned long)1 << (n))
80 #define INC(o) ((o) <<= 1)
81 #define ISSTATEIN(v, o) (((v) & (o)) != 0)
82 /* some abbreviations; note that some of these know variable names! */
83 /* do "if I'm here, I can also be there" etc without branches */
84 #define FWD(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) << (n))
85 #define BACK(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) >> (n))
86 #define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0)
87 /* function names */
88 #define SNAMES /* engine.c looks after details */
89
90 #include "engine.c"
91
92 /* now undo things */
93 #undef states
94 #undef CLEAR
95 #undef SET0
96 #undef SET1
97 #undef ISSET
98 #undef ASSIGN
99 #undef EQ
100 #undef STATEVARS
101 #undef STATESETUP
102 #undef STATETEARDOWN
103 #undef SETUP
104 #undef onestate
105 #undef INIT
106 #undef INC
107 #undef ISSTATEIN
108 #undef FWD
109 #undef BACK
110 #undef ISSETBACK
111 #undef SNAMES
112
113 /* macros for manipulating states, large version */
114 #define states char *
115 #define CLEAR(v) memset(v, 0, m->g->nstates)
116 #define SET0(v, n) ((v)[n] = 0)
117 #define SET1(v, n) ((v)[n] = 1)
118 #define ISSET(v, n) ((v)[n])
119 #define ASSIGN(d, s) memcpy(d, s, m->g->nstates)
120 #define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0)
121 #define STATEVARS long vn; char *space
122 #define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \
123 if ((m)->space == NULL) return(REG_ESPACE); \
124 (m)->vn = 0; }
125 #define STATETEARDOWN(m) { free((m)->space); }
126 #define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates])
127 #define onestate long
128 #define INIT(o, n) ((o) = (n))
129 #define INC(o) ((o)++)
130 #define ISSTATEIN(v, o) ((v)[o])
131 /* some abbreviations; note that some of these know variable names! */
132 /* do "if I'm here, I can also be there" etc without branches */
133 #define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here])
134 #define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here])
135 #define ISSETBACK(v, n) ((v)[here - (n)])
136 /* function names */
137 #define LNAMES /* flag */
138
139 #include "engine.c"
140
141 /*
142 - regexec - interface for matching
143 = extern int regexec(const regex_t *__restrict, const char *__restrict,
144 = size_t, regmatch_t [__restrict], int);
145 = #define REG_NOTBOL 00001
146 = #define REG_NOTEOL 00002
147 = #define REG_STARTEND 00004
148 = #define REG_TRACE 00400 // tracing of execution
149 = #define REG_LARGE 01000 // force large representation
150 = #define REG_BACKR 02000 // force use of backref code
151 *
152 * We put this here so we can exploit knowledge of the state representation
153 * when choosing which matcher to call. Also, by this point the matchers
154 * have been prototyped.
155 */
156 int /* 0 success, REG_NOMATCH failure */
regexec(const regex_t * __restrict preg,const char * __restrict string,size_t nmatch,regmatch_t pmatch[__restrict],int eflags)157 regexec(const regex_t *__restrict preg,
158 const char *__restrict string,
159 size_t nmatch,
160 regmatch_t pmatch[__restrict],
161 int eflags)
162 {
163 struct re_guts *g = preg->re_g;
164 #ifdef REDEBUG
165 # define GOODFLAGS(f) (f)
166 #else
167 # define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
168 #endif
169
170 if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
171 return(REG_BADPAT);
172 assert(!(g->iflags&BAD));
173 if (g->iflags&BAD) /* backstop for no-debug case */
174 return(REG_BADPAT);
175 eflags = GOODFLAGS(eflags);
176
177 if (g->nstates <= (sopno) (CHAR_BIT*sizeof(states1)) && !(eflags®_LARGE))
178 return(smatcher(g, (char *)string, nmatch, pmatch, eflags));
179 else
180 return(lmatcher(g, (char *)string, nmatch, pmatch, eflags));
181 }
182
183 #endif /* !_NO_REGEX */
184
