1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
|
/*
* Wireshark - Network traffic analyzer
* By Gerald Combs <gerald@wireshark.org>
* Copyright 1998 Gerald Combs
*
* SPDX-License-Identifier: GPL-2.0-or-later
*/
#include "config.h"
#include "regex.h"
#include <wsutil/str_util.h>
#include <pcre2.h>
struct _ws_regex {
pcre2_code *code;
char *pattern;
};
#define ERROR_MAXLEN_IN_CODE_UNITS 128
static char *
get_error_msg(int errorcode)
{
char *buffer;
/*
* We have to provide a buffer and we don't know how long the
* error message is or even the maximum size. From pcre2api(3):
* "None of the messages are very long; a
* buffer size of 120 code units is ample."
*/
/* Code unit = one byte */
buffer = g_malloc(ERROR_MAXLEN_IN_CODE_UNITS);
/* Message is returned with a trailing zero. */
pcre2_get_error_message(errorcode, buffer, ERROR_MAXLEN_IN_CODE_UNITS);
/* One more at the end for good luck. */
buffer[ERROR_MAXLEN_IN_CODE_UNITS-1] = '\0';
return buffer;
}
static pcre2_code *
compile_pcre2(const char *patt, ssize_t size, char **errmsg, unsigned flags)
{
pcre2_code *code;
int errorcode;
PCRE2_SIZE length;
PCRE2_SIZE erroroffset;
uint32_t options = 0;
if (size < 0)
length = PCRE2_ZERO_TERMINATED;
else
length = (PCRE2_SIZE)size;
if (flags & WS_REGEX_NEVER_UTF)
options |= PCRE2_NEVER_UTF;
if (flags & WS_REGEX_CASELESS)
options |= PCRE2_CASELESS;
/* By default UTF-8 is off. */
code = pcre2_compile_8((PCRE2_SPTR)patt,
length,
options,
&errorcode,
&erroroffset,
NULL);
if (code == NULL) {
*errmsg = get_error_msg(errorcode);
return NULL;
}
return code;
}
ws_regex_t *
ws_regex_compile_ex(const char *patt, ssize_t size, char **errmsg, unsigned flags)
{
ws_return_val_if(!patt, NULL);
pcre2_code *code = compile_pcre2(patt, size, errmsg, flags);
if (code == NULL)
return NULL;
ws_regex_t *re = g_new(ws_regex_t, 1);
re->code = code;
re->pattern = ws_escape_string_len(NULL, patt, size, false);
return re;
}
ws_regex_t *
ws_regex_compile(const char *patt, char **errmsg)
{
return ws_regex_compile_ex(patt, -1, errmsg, 0);
}
static bool
match_pcre2(pcre2_code *code, const char *subject, ssize_t subj_length,
pcre2_match_data *match_data)
{
PCRE2_SIZE length;
int rc;
if (subj_length < 0)
length = PCRE2_ZERO_TERMINATED;
else
length = (PCRE2_SIZE)subj_length;
rc = pcre2_match(code,
subject,
length,
0, /* start at offset zero of the subject */
0, /* default options */
match_data,
NULL);
if (rc < 0) {
/* No match */
if (rc != PCRE2_ERROR_NOMATCH) {
/* Error. Should not happen with UTF-8 disabled. Some huge
* subject strings could hit some internal limit. */
char *msg = get_error_msg(rc);
ws_debug("Unexpected pcre2_match() error: %s.", msg);
g_free(msg);
}
return false;
}
/* Matched */
return true;
}
bool
ws_regex_matches(const ws_regex_t *re, const char *subj)
{
return ws_regex_matches_length(re, subj, -1);
}
bool
ws_regex_matches_length(const ws_regex_t *re,
const char *subj, ssize_t subj_length)
{
bool matched;
pcre2_match_data *match_data;
ws_return_val_if(!re, false);
ws_return_val_if(!subj, false);
/* We don't use the matched substring but pcre2_match requires
* at least one pair of offsets. */
match_data = pcre2_match_data_create(1, NULL);
matched = match_pcre2(re->code, subj, subj_length, match_data);
pcre2_match_data_free(match_data);
return matched;
}
bool
ws_regex_matches_pos(const ws_regex_t *re,
const char *subj, ssize_t subj_length,
size_t pos_vect[2])
{
bool matched;
pcre2_match_data *match_data;
ws_return_val_if(!re, false);
ws_return_val_if(!subj, false);
match_data = pcre2_match_data_create(1, NULL);
matched = match_pcre2(re->code, subj, subj_length, match_data);
if (matched && pos_vect) {
PCRE2_SIZE *ovect = pcre2_get_ovector_pointer(match_data);
pos_vect[0] = ovect[0];
pos_vect[1] = ovect[1];
}
pcre2_match_data_free(match_data);
return matched;
}
void
ws_regex_free(ws_regex_t *re)
{
pcre2_code_free(re->code);
g_free(re->pattern);
g_free(re);
}
const char *
ws_regex_pattern(const ws_regex_t *re)
{
return re->pattern;
}
|
