Package: jesred / 1.2pl1-22

04-urlgroup Patch series | download
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
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
Author: Alexander Zangerl <az@debian.org>
Subject: #487980 add support for urlgroups (squid 2.6)

--- a/etc/redirect.rules
+++ b/etc/redirect.rules
@@ -4,11 +4,13 @@
 
 # Syntax: 
 # 
-#	regex|regexi pattern replacement
+#	regex[i] pattern replacement
+#	regex[i]ug urlgroup pattern replacement
 #
 # or
 #
 #	abort .filename_extension
+#	abortug urlgroup .filename_extension
 
 # jesred uses a linear list of redirect rules and terminates on first match, 
 # so the order of rules is important!
@@ -31,12 +33,23 @@
 
 # regex RE [RURL]
 # regexi RE [RURL]
+# regexug URLGROUP RE [RURL]
+# regexiug URLGROUP RE [RURL]
 #
 # regex  ... indicates, that the following RE is case-sensitive
 # regexi ... indicates, that the following RE is case-insensitive
 # RE     ... is the regular expression, which has to match the passed URL to get
 #            rewritten with the following RURL (see regex(7)).
 # RURL   ... if RE matches the passed URL, jesred returns RURL
+# URLGROUP   ... URLGROUP must also match for jesred to return RURL
+
+# To indicate that a client-side redirect should be performed with
+# the new URL prefixing the RURL with "301:" (moved permanently) 
+# or 302: (moved temporarily).
+
+# RURL can also include a "urlgroup" that can subsequently be matched
+# in cache_peer_access and similar ACL driven rules. An urlgroup is
+# returned by prefixing the RURL with "!urlgroup!".  2.6STABLE19
 
 # If RURL is omitted, all URLs which match RE are NOT rewritten.
 # So the following two rules prevent jesred from rewriting matched URLs, but
--- a/main.c
+++ b/main.c
@@ -75,7 +75,7 @@ int main(int argc, char **argv)
 /*    int first_run = 1; */
     char buff[BUFSIZE];
     char redirect_url[BUFSIZE];
-    char *url, *src_addr, *ident, *method;
+    char *url, *src_addr, *ident, *method, *urlgroup;
     int finished = 0;
     int buff_status = 0;
     ip_acl *ip_list = NULL;
@@ -118,7 +118,7 @@ int main(int argc, char **argv)
 	    }
 	    /* separate the four fields from the single input line of stdin */
 	    buff_status = parse_buff(buff, &url, &src_addr, &ident, &method,
-				     ip_list, pattern_list);
+				     &urlgroup, ip_list, pattern_list);
 	    /* error during parsing the passed line from squid - no rewrite */
 	    if(buff_status) {
 		puts("");
@@ -133,7 +133,7 @@ int main(int argc, char **argv)
 		continue;
 	    }
 	    /* find a rule for rewriting the URL */
-	    val = pattern_compare(url, redirect_url, pattern_list);
+	    val = pattern_compare(url, urlgroup, redirect_url, pattern_list);
 	    if( val < 1 ) {
 		/* no rule found = 0, or ABORT rule -N */
 		puts("");
--- a/pattern_list.c
+++ b/pattern_list.c
@@ -1,5 +1,5 @@
 /*
- * $Id: pattern_list.c,v 1.2 1998/07/25 02:32:45 elkner Exp $
+ * $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/
@@ -53,17 +53,23 @@ char * get_accel(char *, int *, int);
 void
 add_to_patterns(char *pattern, pattern_item **plist)
 {
-    char first[BUFSIZE];
-    char second[BUFSIZE];
-    char type[BUFSIZE];
+    char * rgxurl = "";
+    char * repurl = "";
 #ifdef USE_ACCEL
-    char accel[BUFSIZE];
+    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 
@@ -73,11 +79,9 @@ add_to_patterns(char *pattern, pattern_i
     
     rpattern.type = EXTENDED;
     rpattern.case_sensitive = 1;
-#ifdef USE_ACCEL   
-    stored = sscanf(pattern, "%s %s %s %s", type, first, second, accel);
-#else
-    stored = sscanf(pattern, "%s %s %s", type, first, second);
-#endif
+
+    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);
@@ -85,39 +89,100 @@ add_to_patterns(char *pattern, pattern_i
 	return;
     }
   
-    if(stored == 2)
-	strcpy(second, "");
     
-    if(strcmp(type, "abort") == 0) {
+    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) {
+    if((strcmp(type, "regexi") == 0) || (strcmp(type, "regexiug") == 0)) {
 	regex_flags |= REG_ICASE;
 	rpattern.case_sensitive = 0;
     }
     
-    if(regcomp(&compiled, first, regex_flags)) {
-	mylog(ERROR, "Invalid regex [%s] in pattern file\n", first);
+    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(first) +1));
+    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, first);
-    rpattern.replacement = (char *)malloc(sizeof(char) * (strlen(second) +1));
+    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, second);
+    strcpy(rpattern.replacement, repurl);
 
 #ifdef USE_ACCEL
     /* use accelerator string if it exists */
@@ -136,6 +201,20 @@ add_to_patterns(char *pattern, pattern_i
 	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);
 }
 
@@ -233,6 +312,7 @@ add_to_plist(pattern_item pattern, patte
     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;
@@ -268,6 +348,42 @@ int count_parenthesis (char *pattern)
     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)
 {
--- a/pattern_list.h
+++ b/pattern_list.h
@@ -39,6 +39,7 @@
 typedef struct _pattern_item {
     char *pattern;
     char *replacement;
+    char *urlgroup;
     int case_sensitive;
     int type;
 #ifdef USE_ACCEL
--- a/rewrite.c
+++ b/rewrite.c
@@ -61,52 +61,72 @@ static int match_accel(char *, char *, i
 
 int
 parse_buff(char *buff, char **url, char **src_addr, char **ident,
-	     char **method, ip_acl *ip, pattern_item *p)
+	     char **method, char **urlgroup, ip_acl *ip, pattern_item *p)
+	     //char **method, ip_acl *ip, pattern_item *p)
 {
     int c, i;
     struct in_addr address;
     char *token, *new_token;
-    char *end[4];
+    char *end[5];
+    //char **urlgroup;
     
     c = 0;
+    *urlgroup = '\0';
+
     token = strchr(buff,' ');
     if ( token ) {       /* URL */
 	c++;
 	*token = '\0';
 	end[0] = token;
 	*url = buff;
+
 	new_token = strchr(++token,' ');
 	if (new_token) {     /* Address */
 	    c++;
 	    *new_token = '\0';
 	    end[1] = new_token;
 	    *src_addr = token;
+
 	    token = strchr(++new_token,' ');
 	    if (token) {      /* Ident */
 		c++;
 		*token = '\0';
 		end[2] = token;
 		*ident = new_token;
-		new_token = strchr(++token,'\n');
+
+		/* this might be the last token, check for a space
+		 or a newline */
+		if (!( new_token = strchr(++token,' ')))
+			new_token = strchr(token,'\n');
 		if (new_token) { /* Method */
 		    c++;
 		    *new_token = '\0';
 		    end[3] = new_token;
 		    *method = token;
-		    /* Squid 2.6 adds Url-group,
-		       this should make jesred backwards-compatible */
-		    new_token = strchr(token,' '); 
-		    if (new_token)
-		    {
-		       *new_token = '\0';
-		       end[3] = new_token;
-		    }
+
+		    /* this will be the last token, stop at a space or newline
+                       to avoid spaces in urlgroup.  maybe be too rare to 
+                       waste a test on */
+		    if (!( token = strchr(++new_token,' ')))
+			token = strchr(new_token,'\n');
+		    if (token) {      /* urlgroup */
+			c++;
+			*token = '\0';
+			end[4] = token;
+			/* squid sends "-" as indicator for no urlgroup  */
+			if (strcmp(new_token,"-"))
+			   *urlgroup = new_token;
 
 		}
 	    }
+
+	    }
 	}
     }
-    if(c != 4) {
+
+    /* 4 pre 2.6 or no urlgroup
+       5 post 2.6 with a urlgroup */
+    if(( c != 5) && ( c != 4)) {
 	for(i = 0; i < c; i++) {
 	    if ( end[i] )
 		*end[i] = ' ';
@@ -114,6 +134,9 @@ parse_buff(char *buff, char **url, char
 	mylog(ERROR, "incorrect input (%d): %s", c, buff);
 	return 1;
     }
+
+    
+
 #ifdef DEBUG
     mylog(DEBG, "Request: %s %s %s %s\n", *url, *src_addr, *ident, *method);
 #endif    
@@ -159,7 +182,7 @@ parse_buff(char *buff, char **url, char
    < 0 if abort pattern match, 0 if no match found, > 1 pattern match
    if match, the number of the matching rule will be returned */
 int
-pattern_compare(char *url,char *newurl, pattern_item *phead)
+pattern_compare(char *url, char *urlgroup, char *newurl, pattern_item *phead)
 {
     pattern_item *curr;
     int pos;
@@ -173,6 +196,16 @@ pattern_compare(char *url,char *newurl,
 	pattern_no++;
 	matched = 1;
 	/* assume a match until a character isn't the same */
+
+	/* urlgroup is checked ONLY IF the rule has one */
+        if (curr->urlgroup) {
+            if (!urlgroup || strcmp(curr->urlgroup, urlgroup) != 0) 
+	    {
+               matched = 0;
+               continue;
+            } 
+	}
+
 	if(curr->type == ABORT) {
 	    len = strlen(curr->pattern);
 	    pos = strlen(url) - len; /* this is dangerous */
--- a/rewrite.h
+++ b/rewrite.h
@@ -28,7 +28,7 @@
 #ifndef REWRITE_H
 #define REWRITE_H
 
-extern int parse_buff(char *, char **, char **, char **, char **,
+extern int parse_buff(char *, char **, char **, char **, char **, char **,
 		      ip_acl *, pattern_item *);
 
 #endif