File: pattern_list.c

package info (click to toggle)
jesred 1.2pl1-22
  • links: PTS
  • area: main
  • in suites: bullseye, buster, sid, stretch
  • size: 580 kB
  • ctags: 286
  • sloc: ansic: 1,359; makefile: 76
file content (405 lines) | stat: -rw-r--r-- 10,334 bytes parent folder | download | duplicates (2)
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
/*
 * $Id: pattern_list.c,v 1.7 2008/04/21 01:51:17 nrickerby Exp nrickerby $
 *
 * Author:  Squirm derived      http://www.senet.com.au/squirm/
 * Project: Jesred       http://ivs.cs.uni-magdeburg.de/~elkner/webtools/jesred/
 *
 * 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
 * of the License, 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.
 *
 * http://www.gnu.org/copyleft/gpl.html or ./gpl.html
 * 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.
 *
 * Thanks to Chris Foote, chris@senet.com.au - not much to change here ;-)
 *
 */

#include<stdio.h>
#include<stdlib.h>
#include<string.h>
#include<sys/types.h>

#ifdef LINUX
#include <ctype.h>	/* for tolower() */
#endif

#ifdef LOCAL_REGEX
#include "regex.h"
#else
#include<regex.h>
#endif

#include "main.h"
#include "log.h"
#include "util.h"
#include "pattern_list.h"

int count_parenthesis (char *pattern);

void add_to_plist(pattern_item, pattern_item **);
#ifdef USE_ACCEL
char * get_accel(char *, int *, int);
#endif

void
add_to_patterns(char *pattern, pattern_item **plist)
{
    char * rgxurl = "";
    char * repurl = "";
#ifdef USE_ACCEL
    char * accel = "";
#endif
    char * urlgroup = NULL;
    regex_t compiled;
    pattern_item rpattern;
    int abort_type = 0;
    int stored;
    
    char type[BUFSIZE];
    char arg1[BUFSIZE];
    char arg2[BUFSIZE];
    char arg3[BUFSIZE];
    char arg4[BUFSIZE];

    /*  The regex_flags that we use are:
	REG_EXTENDED 
	REG_NOSUB 
	REG_ICASE; */
    
    int regex_flags = REG_EXTENDED;
    
    rpattern.type = EXTENDED;
    rpattern.case_sensitive = 1;

    stored = sscanf(pattern, "%s %s %s %s %s", type, arg1, arg2, arg3, arg4);

    if((stored < 2) || (stored > 4)) {
	mylog(ERROR, "unable to get a pair of patterns in add_to_patterns() "
	    "for [%s]\n", pattern);
	echo_mode = 1;
	return;
    }
  
    
    if ( (strcmp(type, "regexug") == 0) || (strcmp(type, "regexiug") == 0) ) {
        switch( stored )
        {
            case 3 : urlgroup = arg1;
                     rgxurl = arg2;
                     break;
            case 4 : urlgroup = arg1;
                     rgxurl = arg2;
                     repurl = arg3;
                     break;
#ifdef USE_ACCEL   
            case 5 : urlgroup = arg1;
                     rgxurl = arg2;
                     repurl = arg3;
                     accel = arg4;
                     break;
#endif
            default  : mylog(ERROR, "unable to parse rule for [%s]\n", pattern);
                       echo_mode = 1;
                       break;
        }		
    }
    else if ( (strcmp(type, "regex") == 0) || (strcmp(type, "regexi") == 0) ) {
        switch( stored )
        {
            case 2 : rgxurl = arg1;
	             strcpy(repurl, "");
                     break;
            case 3 : rgxurl = arg1;
                     repurl = arg2;
                     break;
#ifdef USE_ACCEL   
            case 4 : rgxurl = arg1;
                     repurl = arg2;
                     accel = arg3;
                     break;
#endif
            default  : mylog(ERROR, "unable to parse rule for [%s]\n", pattern);
                       echo_mode = 1;
                     break;
        }		
    }
    else if (strcmp(type, "abortug") == 0) {
	rpattern.type = ABORT;
	abort_type = 1;
        if ( stored == 3 ) {
            urlgroup = arg1;
            rgxurl = arg2;
        } else {
            mylog(ERROR, "unable to parse rule for [%s]\n", pattern);
            echo_mode = 1;
        }
    }
    else if (strcmp(type, "abort") == 0) {
	rpattern.type = ABORT;
	abort_type = 1;
        if ( stored == 2 ) {
            rgxurl = arg1;
        } else {
            mylog(ERROR, "unable to parse rule for [%s]\n", pattern);
            echo_mode = 1;
        }
    }
    else {
        mylog(ERROR, "unable to parse rule for [%s]\n", pattern);
	echo_mode = 1;
    }
  
    if((strcmp(type, "regexi") == 0) || (strcmp(type, "regexiug") == 0)) {
	regex_flags |= REG_ICASE;
	rpattern.case_sensitive = 0;
    }
    
    if(regcomp(&compiled, rgxurl, regex_flags)) {
	mylog(ERROR, "Invalid regex [%s] in pattern file\n", rgxurl);
	echo_mode = 1;
	return;
    }
    rpattern.cpattern = compiled;
    rpattern.pattern = (char *)malloc(sizeof(char) * (strlen(rgxurl) +1));
    if(rpattern.pattern == NULL) {
	mylog(ERROR, "unable to allocate memory in add_to_patterns()\n");
	echo_mode = 1;
	return;
    }
    strcpy(rpattern.pattern, rgxurl);
    rpattern.replacement = (char *)malloc(sizeof(char) * (strlen(repurl) +1));
    if(rpattern.replacement == NULL) {
	mylog(ERROR, "unable to allocate memory in add_to_patterns()\n");
	echo_mode = 1;
	return;
    }
    strcpy(rpattern.replacement, repurl);

#ifdef USE_ACCEL
    /* use accelerator string if it exists */
    if(stored == 4) {
	rpattern.has_accel = 1;
	rpattern.accel = get_accel(accel, &rpattern.accel_type, 
				   rpattern.case_sensitive);
	if(rpattern.accel == NULL) {
	    mylog(ERROR, "unable to allocate memory from get_accel()\n");
	    echo_mode = 1;
	    return;
	}
    }
    else {
	rpattern.has_accel = 0;
	rpattern.accel = NULL;
    }
#endif

    if ( urlgroup ) {
        rpattern.urlgroup = (char *)malloc(sizeof(char) * (strlen(urlgroup) +1));
        if(rpattern.urlgroup == NULL) {
            mylog(ERROR, "unable to allocate memory in add_to_patterns()\n");
            echo_mode = 1;
            return;
        }
        strcpy(rpattern.urlgroup, urlgroup);
        }
    else {
        rpattern.urlgroup = NULL;
    }

    add_to_plist(rpattern, plist);
}

#ifdef USE_ACCEL
char *
get_accel(char *accel, int *accel_type, int case_sensitive) {
    /* returns the stripped accelerator string or NULL if memory can't be
       allocated 
       converts the accel string to lower case if(case_sensitive) */
    
    /* accel_type is assigned one of the values:
       #define ACCEL_NORMAL 1
       #define ACCEL_START  2
       #define ACCEL_END    3     */
    
    int len, i;
    char *new_accel = NULL;
    *accel_type = 0;
  
    len = strlen(accel);
    if(accel[0] == '^')
	*accel_type = ACCEL_START;
    if(accel[len - 1] == '$')
	*accel_type = ACCEL_END;
    if(! *accel_type)
	*accel_type = ACCEL_NORMAL;
    
    /* copy the strings */
    new_accel = (char *)malloc(sizeof(char) * strlen(accel));
    strcpy(new_accel,accel);
    if(*accel_type == ACCEL_START || *accel_type == ACCEL_END) {
	if(new_accel == NULL)
	    return NULL;
	if(*accel_type == ACCEL_START) {
	    if(case_sensitive)
		for(i = 0; i < len; i++)
		    new_accel[i] = accel[i+1];
	    else
		for(i = 0; i < len; i++)
		    new_accel[i] = tolower(accel[i+1]);
	}
	if(*accel_type == ACCEL_END) {
	    if(case_sensitive)
		for(i = 0; i < len - 1; i++)
		    new_accel[i] = accel[i];
	    else
		for(i = 0; i < len - 1; i++)
		    new_accel[i] = tolower(accel[i]);
	    new_accel[i] = '\0';
	}
    }
    else {
	if(!case_sensitive) {
	    for(i = 0; i < len; i++)
		new_accel[i] = tolower(accel[i]);
	    new_accel[i] = '\0';
	}
    }
    return new_accel;
}
#endif

void
add_to_plist(pattern_item pattern, pattern_item **plist) {
    pattern_item *curr;
    pattern_item *new;
    
    curr = NULL;
    new = NULL;

    if (! (*plist)) {
	/* empty list */
	*plist = xcalloc(1, sizeof(pattern_item));
	new = *plist;
    } else {
	/* find end of list */
	curr = *plist;
	while(curr->next)
	    curr = curr->next;
	new = xcalloc(1, sizeof(pattern_item));
	curr->next = new;
    }
    if(! new) {
	mylog(ERROR, "unable to allocate memory in add_to_plist()\n");
	/* exit(3); */
	echo_mode = 1;
	return;
    }
    new->pattern = pattern.pattern;
    new->replacement = pattern.replacement;
    new->type = pattern.type;
#ifdef USE_ACCEL
    new->has_accel = pattern.has_accel;
    new->accel = pattern.accel;
    new->accel_type = pattern.accel_type;
#endif
    new->case_sensitive = pattern.case_sensitive;
    new->urlgroup = pattern.urlgroup;
    
    /* not sure whether we need to copy each item in the struct */
    new->cpattern = pattern.cpattern;
    new->next = NULL;
}

int count_parenthesis (char *pattern)
{
    int lcount = 0;
    int rcount = 0;
    int i;
    
    /* Traverse string looking for ( and ) */
    for (i = 0; i < strlen (pattern); i++) {
	/* We have found a left ( */
	if (pattern [i] == '(') {
	    /* Do not count if there is a backslash */
	    if ((i != 0) && (pattern [i-1] == '\\'))
		continue;
	    else
		lcount++;
	}    
	if (pattern [i] == ')') {
	    if ((i != 0) && (pattern [i-1] == '\\'))
		continue;
	    else
		rcount++;
	}
    }
    /* Check that left == right */
    if (lcount != rcount)
	return (-1);
    return (lcount);
}

#ifdef DEBUG
void
print_plist(pattern_item **plist) {
    pattern_item *curr;
    pattern_item *new;

    curr = NULL;
    new = NULL;
    int count = 0;

    if (! (*plist)) {
        /* empty list */
        printf("empty list\n");
    } else {
        /* find end of list */
        curr = *plist;
        while(curr) {
            printf("rule %d\n", count);
            switch( curr->type )
            {
                case 1 : printf( "\tnormal\n" ); break;
                case 2 : printf( "\textended\n" ); break;
                case 3 : printf( "\tabort\n" ); break;
	    }
            printf("\tpattern \"%s\"\n", curr->pattern );
            printf("\treplacement \"%s\"\n", curr->replacement );
            printf("\turlgroup \"%s\"\n", curr->urlgroup );
            curr = curr->next;
	    count++;
            printf("\n");
        }
    }
}
#endif


void
plist_destroy(pattern_item **a)
{
    pattern_item *b;
    pattern_item *n;
    for (b = *a; b; b = n) {
	n = b->next;
	safe_free(b->pattern);
	safe_free(b->replacement);
#ifdef USE_ACCEL
	if (b->accel)
	    safe_free(b->accel);
#endif
	regfree(&(b->cpattern));
	safe_free(b);
    }
    *a = NULL;
}