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
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
|
/* search.c - searching subroutines using dfa, kwset and regex for grep.
Copyright 1992, 1998, 2000 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
02111-1307, USA. */
/* Written August 1992 by Mike Haertel. */
/* $FreeBSD$ */
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <sys/types.h>
#include "system.h"
#include "grep.h"
#include "regex.h"
#include "dfa.h"
#include "kwset.h"
#define NCHAR (UCHAR_MAX + 1)
static void Gcompile PARAMS((char *, size_t));
static void Ecompile PARAMS((char *, size_t));
static char *EGexecute PARAMS((char *, size_t, char **));
static void Fcompile PARAMS((char *, size_t));
static char *Fexecute PARAMS((char *, size_t, char **));
static void kwsinit PARAMS((void));
/* Here is the matchers vector for the main program. */
struct matcher matchers[] = {
{ "default", Gcompile, EGexecute },
{ "grep", Gcompile, EGexecute },
{ "egrep", Ecompile, EGexecute },
{ "awk", Ecompile, EGexecute },
{ "fgrep", Fcompile, Fexecute },
{ 0, 0, 0 },
};
/* For -w, we also consider _ to be word constituent. */
#define WCHAR(C) (ISALNUM(C) || (C) == '_')
/* DFA compiled regexp. */
static struct dfa dfa;
/* Regex compiled regexp. */
static struct re_pattern_buffer regexbuf;
/* KWset compiled pattern. For Ecompile and Gcompile, we compile
a list of strings, at least one of which is known to occur in
any string matching the regexp. */
static kwset_t kwset;
/* Last compiled fixed string known to exactly match the regexp.
If kwsexec() returns < lastexact, then we don't need to
call the regexp matcher at all. */
static int lastexact;
void
dfaerror (char const *mesg)
{
fatal(mesg, 0);
}
static void
kwsinit (void)
{
static char trans[NCHAR];
int i;
if (match_icase)
for (i = 0; i < NCHAR; ++i)
trans[i] = TOLOWER(i);
if (!(kwset = kwsalloc(match_icase ? trans : (char *) 0)))
fatal("memory exhausted", 0);
}
/* If the DFA turns out to have some set of fixed strings one of
which must occur in the match, then we build a kwset matcher
to find those strings, and thus quickly filter out impossible
matches. */
static void
kwsmusts (void)
{
struct dfamust *dm;
char *err;
if (dfa.musts)
{
kwsinit();
/* First, we compile in the substrings known to be exact
matches. The kwset matcher will return the index
of the matching string that it chooses. */
for (dm = dfa.musts; dm; dm = dm->next)
{
if (!dm->exact)
continue;
++lastexact;
if ((err = kwsincr(kwset, dm->must, strlen(dm->must))) != 0)
fatal(err, 0);
}
/* Now, we compile the substrings that will require
the use of the regexp matcher. */
for (dm = dfa.musts; dm; dm = dm->next)
{
if (dm->exact)
continue;
if ((err = kwsincr(kwset, dm->must, strlen(dm->must))) != 0)
fatal(err, 0);
}
if ((err = kwsprep(kwset)) != 0)
fatal(err, 0);
}
}
static void
Gcompile (char *pattern, size_t size)
{
const char *err;
re_set_syntax(RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE);
dfasyntax(RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE, match_icase, eolbyte);
if ((err = re_compile_pattern(pattern, size, ®exbuf)) != 0)
fatal(err, 0);
/* In the match_words and match_lines cases, we use a different pattern
for the DFA matcher that will quickly throw out cases that won't work.
Then if DFA succeeds we do some hairy stuff using the regex matcher
to decide whether the match should really count. */
if (match_words || match_lines)
{
/* In the whole-word case, we use the pattern:
(^|[^A-Za-z_])(userpattern)([^A-Za-z_]|$).
In the whole-line case, we use the pattern:
^(userpattern)$.
BUG: Using [A-Za-z_] is locale-dependent!
So will use [:alnum:] */
char *n = malloc(size + 50);
int i = 0;
strcpy(n, "");
if (match_lines)
strcpy(n, "^\\(");
if (match_words)
strcpy(n, "\\(^\\|[^[:alnum:]_]\\)\\(");
i = strlen(n);
memcpy(n + i, pattern, size);
i += size;
if (match_words)
strcpy(n + i, "\\)\\([^[:alnum:]_]\\|$\\)");
if (match_lines)
strcpy(n + i, "\\)$");
i += strlen(n + i);
dfacomp(n, i, &dfa, 1);
}
else
dfacomp(pattern, size, &dfa, 1);
kwsmusts();
}
static void
Ecompile (char *pattern, size_t size)
{
const char *err;
if (strcmp(matcher, "awk") == 0)
{
re_set_syntax(RE_SYNTAX_AWK);
dfasyntax(RE_SYNTAX_AWK, match_icase, eolbyte);
}
else
{
re_set_syntax (RE_SYNTAX_POSIX_EGREP);
dfasyntax (RE_SYNTAX_POSIX_EGREP, match_icase, eolbyte);
}
if ((err = re_compile_pattern(pattern, size, ®exbuf)) != 0)
fatal(err, 0);
/* In the match_words and match_lines cases, we use a different pattern
for the DFA matcher that will quickly throw out cases that won't work.
Then if DFA succeeds we do some hairy stuff using the regex matcher
to decide whether the match should really count. */
if (match_words || match_lines)
{
/* In the whole-word case, we use the pattern:
(^|[^A-Za-z_])(userpattern)([^A-Za-z_]|$).
In the whole-line case, we use the pattern:
^(userpattern)$.
BUG: Using [A-Za-z_] is locale-dependent!
so will use the char class */
char *n = malloc(size + 50);
int i = 0;
strcpy(n, "");
if (match_lines)
strcpy(n, "^(");
if (match_words)
strcpy(n, "(^|[^[:alnum:]_])(");
i = strlen(n);
memcpy(n + i, pattern, size);
i += size;
if (match_words)
strcpy(n + i, ")([^[:alnum:]_]|$)");
if (match_lines)
strcpy(n + i, ")$");
i += strlen(n + i);
dfacomp(n, i, &dfa, 1);
}
else
dfacomp(pattern, size, &dfa, 1);
kwsmusts();
}
static char *
EGexecute (char *buf, size_t size, char **endp)
{
register char *buflim, *beg, *end, save;
char eol = eolbyte;
int backref, start, len;
struct kwsmatch kwsm;
static struct re_registers regs; /* This is static on account of a BRAIN-DEAD
Q@#%!# library interface in regex.c. */
buflim = buf + size;
for (beg = end = buf; end < buflim; beg = end + 1)
{
if (kwset)
{
/* Find a possible match using the KWset matcher. */
beg = kwsexec(kwset, beg, buflim - beg, &kwsm);
if (!beg)
goto failure;
/* Narrow down to the line containing the candidate, and
run it through DFA. */
end = memchr(beg, eol, buflim - beg);
if (!end)
end = buflim;
while (beg > buf && beg[-1] != eol)
--beg;
save = *end;
if (kwsm.index < lastexact)
goto success;
if (!dfaexec(&dfa, beg, end, 0, (int *) 0, &backref))
{
*end = save;
continue;
}
*end = save;
/* Successful, no backreferences encountered. */
if (!backref)
goto success;
}
else
{
/* No good fixed strings; start with DFA. */
save = *buflim;
beg = dfaexec(&dfa, beg, buflim, 0, (int *) 0, &backref);
*buflim = save;
if (!beg)
goto failure;
/* Narrow down to the line we've found. */
end = memchr(beg, eol, buflim - beg);
if (!end)
end = buflim;
while (beg > buf && beg[-1] != eol)
--beg;
/* Successful, no backreferences encountered! */
if (!backref)
goto success;
}
/* If we've made it to this point, this means DFA has seen
a probable match, and we need to run it through Regex. */
regexbuf.not_eol = 0;
if ((start = re_search(®exbuf, beg, end - beg, 0, end - beg, ®s)) >= 0)
{
len = regs.end[0] - start;
if ((!match_lines && !match_words)
|| (match_lines && len == end - beg))
goto success;
/* If -w, check if the match aligns with word boundaries.
We do this iteratively because:
(a) the line may contain more than one occurence of the pattern, and
(b) Several alternatives in the pattern might be valid at a given
point, and we may need to consider a shorter one to find a word
boundary. */
if (match_words)
while (start >= 0)
{
if ((start == 0 || !WCHAR ((unsigned char) beg[start - 1]))
&& (len == end - beg
|| !WCHAR ((unsigned char) beg[start + len])))
goto success;
if (len > 0)
{
/* Try a shorter length anchored at the same place. */
--len;
regexbuf.not_eol = 1;
len = re_match(®exbuf, beg, start + len, start, ®s);
}
if (len <= 0)
{
/* Try looking further on. */
if (start == end - beg)
break;
++start;
regexbuf.not_eol = 0;
start = re_search(®exbuf, beg, end - beg,
start, end - beg - start, ®s);
len = regs.end[0] - start;
}
}
}
}
failure:
return 0;
success:
*endp = end < buflim ? end + 1 : end;
return beg;
}
static void
Fcompile (char *pattern, size_t size)
{
char *beg, *lim, *err;
kwsinit();
beg = pattern;
do
{
for (lim = beg; lim < pattern + size && *lim != '\n'; ++lim)
;
if ((err = kwsincr(kwset, beg, lim - beg)) != 0)
fatal(err, 0);
if (lim < pattern + size)
++lim;
beg = lim;
}
while (beg < pattern + size);
if ((err = kwsprep(kwset)) != 0)
fatal(err, 0);
}
static char *
Fexecute (char *buf, size_t size, char **endp)
{
register char *beg, *try, *end;
register size_t len;
char eol = eolbyte;
struct kwsmatch kwsmatch;
for (beg = buf; beg <= buf + size; ++beg)
{
if (!(beg = kwsexec(kwset, beg, buf + size - beg, &kwsmatch)))
return 0;
len = kwsmatch.size[0];
if (match_lines)
{
if (beg > buf && beg[-1] != eol)
continue;
if (beg + len < buf + size && beg[len] != eol)
continue;
goto success;
}
else if (match_words)
for (try = beg; len && try;)
{
if (try > buf && WCHAR((unsigned char) try[-1]))
break;
if (try + len < buf + size && WCHAR((unsigned char) try[len]))
{
try = kwsexec(kwset, beg, --len, &kwsmatch);
len = kwsmatch.size[0];
}
else
goto success;
}
else
goto success;
}
return 0;
success:
if ((end = memchr(beg + len, eol, (buf + size) - (beg + len))) != 0)
++end;
else
end = buf + size;
*endp = end;
while (beg > buf && beg[-1] != '\n')
--beg;
return beg;
}
|