1 |
148 |
jeremybenn |
/*-
|
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 |
|
|
static int nope = 0; /* for use in asserts; shuts lint up */
|
62 |
|
|
|
63 |
|
|
/* macros for manipulating states, small version */
|
64 |
|
|
#define states long
|
65 |
|
|
#define states1 states /* for later use in regexec() decision */
|
66 |
|
|
#define CLEAR(v) ((v) = 0)
|
67 |
|
|
#define SET0(v, n) ((v) &= ~((unsigned long)1 << (n)))
|
68 |
|
|
#define SET1(v, n) ((v) |= (unsigned long)1 << (n))
|
69 |
|
|
#define ISSET(v, n) (((v) & ((unsigned long)1 << (n))) != 0)
|
70 |
|
|
#define ASSIGN(d, s) ((d) = (s))
|
71 |
|
|
#define EQ(a, b) ((a) == (b))
|
72 |
|
|
#define STATEVARS long dummy /* dummy version */
|
73 |
|
|
#define STATESETUP(m, n) /* nothing */
|
74 |
|
|
#define STATETEARDOWN(m) /* nothing */
|
75 |
|
|
#define SETUP(v) ((v) = 0)
|
76 |
|
|
#define onestate long
|
77 |
|
|
#define INIT(o, n) ((o) = (unsigned long)1 << (n))
|
78 |
|
|
#define INC(o) ((o) <<= 1)
|
79 |
|
|
#define ISSTATEIN(v, o) (((v) & (o)) != 0)
|
80 |
|
|
/* some abbreviations; note that some of these know variable names! */
|
81 |
|
|
/* do "if I'm here, I can also be there" etc without branches */
|
82 |
|
|
#define FWD(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) << (n))
|
83 |
|
|
#define BACK(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) >> (n))
|
84 |
|
|
#define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0)
|
85 |
|
|
/* function names */
|
86 |
|
|
#define SNAMES /* engine.c looks after details */
|
87 |
|
|
|
88 |
|
|
#include "engine.c"
|
89 |
|
|
|
90 |
|
|
/* now undo things */
|
91 |
|
|
#undef states
|
92 |
|
|
#undef CLEAR
|
93 |
|
|
#undef SET0
|
94 |
|
|
#undef SET1
|
95 |
|
|
#undef ISSET
|
96 |
|
|
#undef ASSIGN
|
97 |
|
|
#undef EQ
|
98 |
|
|
#undef STATEVARS
|
99 |
|
|
#undef STATESETUP
|
100 |
|
|
#undef STATETEARDOWN
|
101 |
|
|
#undef SETUP
|
102 |
|
|
#undef onestate
|
103 |
|
|
#undef INIT
|
104 |
|
|
#undef INC
|
105 |
|
|
#undef ISSTATEIN
|
106 |
|
|
#undef FWD
|
107 |
|
|
#undef BACK
|
108 |
|
|
#undef ISSETBACK
|
109 |
|
|
#undef SNAMES
|
110 |
|
|
|
111 |
|
|
/* macros for manipulating states, large version */
|
112 |
|
|
#define states char *
|
113 |
|
|
#define CLEAR(v) memset(v, 0, m->g->nstates)
|
114 |
|
|
#define SET0(v, n) ((v)[n] = 0)
|
115 |
|
|
#define SET1(v, n) ((v)[n] = 1)
|
116 |
|
|
#define ISSET(v, n) ((v)[n])
|
117 |
|
|
#define ASSIGN(d, s) memcpy(d, s, m->g->nstates)
|
118 |
|
|
#define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0)
|
119 |
|
|
#define STATEVARS long vn; char *space
|
120 |
|
|
#define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \
|
121 |
|
|
if ((m)->space == NULL) return(REG_ESPACE); \
|
122 |
|
|
(m)->vn = 0; }
|
123 |
|
|
#define STATETEARDOWN(m) { free((m)->space); }
|
124 |
|
|
#define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates])
|
125 |
|
|
#define onestate long
|
126 |
|
|
#define INIT(o, n) ((o) = (n))
|
127 |
|
|
#define INC(o) ((o)++)
|
128 |
|
|
#define ISSTATEIN(v, o) ((v)[o])
|
129 |
|
|
/* some abbreviations; note that some of these know variable names! */
|
130 |
|
|
/* do "if I'm here, I can also be there" etc without branches */
|
131 |
|
|
#define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here])
|
132 |
|
|
#define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here])
|
133 |
|
|
#define ISSETBACK(v, n) ((v)[here - (n)])
|
134 |
|
|
/* function names */
|
135 |
|
|
#define LNAMES /* flag */
|
136 |
|
|
|
137 |
|
|
#include "engine.c"
|
138 |
|
|
|
139 |
|
|
/*
|
140 |
|
|
- regexec - interface for matching
|
141 |
|
|
= extern int regexec(const regex_t *, const char *, size_t, \
|
142 |
|
|
= regmatch_t [], int);
|
143 |
|
|
= #define REG_NOTBOL 00001
|
144 |
|
|
= #define REG_NOTEOL 00002
|
145 |
|
|
= #define REG_STARTEND 00004
|
146 |
|
|
= #define REG_TRACE 00400 // tracing of execution
|
147 |
|
|
= #define REG_LARGE 01000 // force large representation
|
148 |
|
|
= #define REG_BACKR 02000 // force use of backref code
|
149 |
|
|
*
|
150 |
|
|
* We put this here so we can exploit knowledge of the state representation
|
151 |
|
|
* when choosing which matcher to call. Also, by this point the matchers
|
152 |
|
|
* have been prototyped.
|
153 |
|
|
*/
|
154 |
|
|
int /* 0 success, REG_NOMATCH failure */
|
155 |
|
|
regexec(preg, string, nmatch, pmatch, eflags)
|
156 |
|
|
const regex_t *preg;
|
157 |
|
|
const char *string;
|
158 |
|
|
size_t nmatch;
|
159 |
|
|
regmatch_t pmatch[];
|
160 |
|
|
int eflags;
|
161 |
|
|
{
|
162 |
|
|
struct re_guts *g = preg->re_g;
|
163 |
|
|
#ifdef REDEBUG
|
164 |
|
|
# define GOODFLAGS(f) (f)
|
165 |
|
|
#else
|
166 |
|
|
# define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
|
167 |
|
|
#endif
|
168 |
|
|
|
169 |
|
|
if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
|
170 |
|
|
return(REG_BADPAT);
|
171 |
|
|
assert(!(g->iflags&BAD));
|
172 |
|
|
if (g->iflags&BAD) /* backstop for no-debug case */
|
173 |
|
|
return(REG_BADPAT);
|
174 |
|
|
eflags = GOODFLAGS(eflags);
|
175 |
|
|
|
176 |
|
|
if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags®_LARGE))
|
177 |
|
|
return(smatcher(g, (char *)string, nmatch, pmatch, eflags));
|
178 |
|
|
else
|
179 |
|
|
return(lmatcher(g, (char *)string, nmatch, pmatch, eflags));
|
180 |
|
|
}
|
181 |
|
|
|
182 |
|
|
#endif /* !_NO_REGEX */
|