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
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
|
/*
* Copyright (C) 2013 Internet Systems Consortium, Inc. ("ISC")
*
* Permission to use, copy, modify, and/or distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND ISC DISCLAIMS ALL WARRANTIES WITH
* REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
* AND FITNESS. IN NO EVENT SHALL ISC BE LIABLE FOR ANY SPECIAL, DIRECT,
* INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
* LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
* OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
* PERFORMANCE OF THIS SOFTWARE.
*/
#include <config.h>
#include <isc/file.h>
#include <isc/regex.h>
#include <isc/string.h>
#if VALREGEX_REPORT_REASON
#define FAIL(x) do { reason = (x); goto error; } while(0)
#else
#define FAIL(x) goto error
#endif
/*
* Validate the regular expression 'C' locale.
*/
int
isc_regex_validate(const char *c) {
enum {
none, parse_bracket, parse_bound,
parse_ce, parse_ec, parse_cc
} state = none;
/* Well known character classes. */
const char *cc[] = {
":alnum:", ":digit:", ":punct:", ":alpha:", ":graph:",
":space:", ":blank:", ":lower:", ":upper:", ":cntrl:",
":print:", ":xdigit:"
};
isc_boolean_t seen_comma = ISC_FALSE;
isc_boolean_t seen_high = ISC_FALSE;
isc_boolean_t seen_char = ISC_FALSE;
isc_boolean_t seen_ec = ISC_FALSE;
isc_boolean_t seen_ce = ISC_FALSE;
isc_boolean_t have_atom = ISC_FALSE;
int group = 0;
int range = 0;
int sub = 0;
isc_boolean_t empty_ok = ISC_FALSE;
isc_boolean_t neg = ISC_FALSE;
isc_boolean_t was_multiple = ISC_FALSE;
unsigned int low = 0;
unsigned int high = 0;
const char *ccname = NULL;
int range_start = 0;
#if VALREGEX_REPORT_REASON
const char *reason = "";
#endif
if (c == NULL || *c == 0)
FAIL("empty string");
while (c != NULL && *c != 0) {
switch (state) {
case none:
switch (*c) {
case '\\': /* make literal */
++c;
switch (*c) {
case '1': case '2': case '3':
case '4': case '5': case '6':
case '7': case '8': case '9':
if ((*c - '0') > sub)
FAIL("bad back reference");
have_atom = ISC_TRUE;
was_multiple = ISC_FALSE;
break;
case 0:
FAIL("escaped end-of-string");
default:
goto literal;
}
++c;
break;
case '[': /* bracket start */
++c;
neg = ISC_FALSE;
was_multiple = ISC_FALSE;
seen_char = ISC_FALSE;
state = parse_bracket;
break;
case '{': /* bound start */
switch (c[1]) {
case '0': case '1': case '2': case '3':
case '4': case '5': case '6': case '7':
case '8': case '9':
if (!have_atom)
FAIL("no atom");
if (was_multiple)
FAIL("was multiple");
seen_comma = ISC_FALSE;
seen_high = ISC_FALSE;
low = high = 0;
state = parse_bound;
break;
default:
goto literal;
}
++c;
have_atom = ISC_TRUE;
was_multiple = ISC_TRUE;
break;
case '}':
goto literal;
case '(': /* group start */
have_atom = ISC_FALSE;
was_multiple = ISC_FALSE;
empty_ok = ISC_TRUE;
++group;
++sub;
++c;
break;
case ')': /* group end */
if (group && !have_atom && !empty_ok)
FAIL("empty alternative");
have_atom = ISC_TRUE;
was_multiple = ISC_FALSE;
if (group != 0)
--group;
++c;
break;
case '|': /* alternative seperator */
if (!have_atom)
FAIL("no atom");
have_atom = ISC_FALSE;
empty_ok = ISC_FALSE;
was_multiple = ISC_FALSE;
++c;
break;
case '^':
case '$':
have_atom = ISC_TRUE;
was_multiple = ISC_TRUE;
++c;
break;
case '+':
case '*':
case '?':
if (was_multiple)
FAIL("was multiple");
if (!have_atom)
FAIL("no atom");
have_atom = ISC_TRUE;
was_multiple = ISC_TRUE;
++c;
break;
case '.':
default:
literal:
have_atom = ISC_TRUE;
was_multiple = ISC_FALSE;
++c;
break;
}
break;
case parse_bound:
switch (*c) {
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
if (!seen_comma) {
low = low * 10 + *c - '0';
if (low > 255)
FAIL("lower bound too big");
} else {
seen_high = ISC_TRUE;
high = high * 10 + *c - '0';
if (high > 255)
FAIL("upper bound too big");
}
++c;
break;
case ',':
if (seen_comma)
FAIL("multiple commas");
seen_comma = ISC_TRUE;
++c;
break;
default:
case '{':
FAIL("non digit/comma");
case '}':
if (seen_high && low > high)
FAIL("bad parse bound");
seen_comma = ISC_FALSE;
state = none;
++c;
break;
}
break;
case parse_bracket:
switch (*c) {
case '^':
if (seen_char || neg) goto inside;
neg = ISC_TRUE;
++c;
break;
case '-':
if (range == 2) goto inside;
if (!seen_char) goto inside;
if (range == 1)
FAIL("bad range");
range = 2;
++c;
break;
case '[':
++c;
switch (*c) {
case '.': /* collating element */
if (range) --range;
++c;
state = parse_ce;
seen_ce = ISC_FALSE;
break;
case '=': /* equivalence class */
if (range == 2)
FAIL("equivalence class in range");
++c;
state = parse_ec;
seen_ec = ISC_FALSE;
break;
case ':': /* character class */
if (range == 2)
FAIL("character class in range");
ccname = c;
++c;
state = parse_cc;
break;
}
seen_char = ISC_TRUE;
break;
case ']':
if (!c[1] && !seen_char)
FAIL("unfinished brace");
if (!seen_char)
goto inside;
++c;
range = 0;
have_atom = ISC_TRUE;
state = none;
break;
default:
inside:
seen_char = ISC_TRUE;
if (range == 2 && *c < range_start)
FAIL("out of order range");
if (range != 0)
--range;
range_start = *c;
++c;
break;
};
break;
case parse_ce:
switch (*c) {
case '.':
++c;
switch (*c) {
case ']':
if (!seen_ce)
FAIL("empty ce");
++c;
state = parse_bracket;
break;
default:
if (seen_ce)
range_start = 256;
else
range_start = '.';
seen_ce = ISC_TRUE;
break;
}
break;
default:
if (seen_ce)
range_start = 256;
else
range_start = *c;
seen_ce = ISC_TRUE;
++c;
break;
}
break;
case parse_ec:
switch (*c) {
case '=':
++c;
switch (*c) {
case ']':
if (!seen_ec)
FAIL("no ec");
++c;
state = parse_bracket;
break;
default:
seen_ec = ISC_TRUE;
break;
}
break;
default:
seen_ec = ISC_TRUE;
++c;
break;
}
break;
case parse_cc:
switch (*c) {
case ':':
++c;
switch (*c) {
case ']': {
unsigned int i;
isc_boolean_t found = ISC_FALSE;
for (i = 0;
i < sizeof(cc)/sizeof(*cc);
i++)
{
unsigned int len;
len = strlen(cc[i]);
if (len !=
(unsigned int)(c - ccname))
continue;
if (strncmp(cc[i], ccname, len))
continue;
found = ISC_TRUE;
}
if (!found)
FAIL("unknown cc");
++c;
state = parse_bracket;
break;
}
default:
break;
}
break;
default:
++c;
break;
}
break;
}
}
if (group != 0)
FAIL("group open");
if (state != none)
FAIL("incomplete");
if (!have_atom)
FAIL("no atom");
return (sub);
error:
#if VALREGEX_REPORT_REASON
fprintf(stderr, "%s\n", reason);
#endif
return (-1);
}
|
