1 const char encode_rcs[] = "$Id: encode.c,v 1.7 2002/03/24 13:25:43 swa Exp $";
2 /*********************************************************************
4 * File : $Source: /cvsroot/ijbswa/current/encode.c,v $
6 * Purpose : Functions to encode and decode URLs, and also to
7 * encode cookies and HTML text.
9 * Copyright : Written by and Copyright (C) 2001 the SourceForge
10 * Privoxy team. http://www.privoxy.org/
12 * Based on the Internet Junkbuster originally written
13 * by and Copyright (C) 1997 Anonymous Coders and
14 * Junkbusters Corporation. http://www.junkbusters.com
16 * This program is free software; you can redistribute it
17 * and/or modify it under the terms of the GNU General
18 * Public License as published by the Free Software
19 * Foundation; either version 2 of the License, or (at
20 * your option) any later version.
22 * This program is distributed in the hope that it will
23 * be useful, but WITHOUT ANY WARRANTY; without even the
24 * implied warranty of MERCHANTABILITY or FITNESS FOR A
25 * PARTICULAR PURPOSE. See the GNU General Public
26 * License for more details.
28 * The GNU General Public License should be included with
29 * this file. If not, you can view it at
30 * http://www.gnu.org/copyleft/gpl.html
31 * or write to the Free Software Foundation, Inc., 59
32 * Temple Place - Suite 330, Boston, MA 02111-1307, USA.
36 * Revision 1.7 2002/03/24 13:25:43 swa
37 * name change related issues
39 * Revision 1.6 2002/03/13 00:27:04 jongfoster
42 * Revision 1.5 2002/03/07 03:46:53 oes
43 * Fixed compiler warnings etc
45 * Revision 1.4 2002/01/22 23:28:07 jongfoster
46 * Adding convenience function html_encode_and_free_original()
47 * Making all functions accept NULL paramaters - in this case, they
48 * simply return NULL. This allows error-checking to be deferred.
50 * Revision 1.3 2001/11/13 00:16:40 jongfoster
51 * Replacing references to malloc.h with the standard stdlib.h
52 * (See ANSI or K&R 2nd Ed)
54 * Revision 1.2 2001/05/17 22:52:35 oes
55 * - Cleaned CRLF's from the sources and related files
57 * Revision 1.1.1.1 2001/05/15 13:58:51 oes
58 * Initial import of version 2.9.3 source tree
61 *********************************************************************/
72 const char encode_h_rcs[] = ENCODE_H_VERSION;
74 /* Maps special characters in a URL to their equivalent % codes. */
75 static const char * const url_code_map[256] = {
76 NULL, "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09",
77 "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13",
78 "%14", "%15", "%16", "%17", "%18", "%19", "%1A", "%1B", "%1C", "%1D",
79 "%1E", "%1F", "+", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
80 "%28", "%29", NULL, "%2B", "%2C", NULL, NULL, "%2F", NULL, NULL,
81 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3A", "%3B",
82 "%3C", "%3D", "%3E", "%3F", NULL, NULL, NULL, NULL, NULL, NULL,
83 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
84 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
85 NULL, "%5B", "%5C", "%5D", "%5E", NULL, "%60", NULL, NULL, NULL,
86 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
87 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
88 NULL, NULL, NULL, "%7B", "%7C", "%7D", "%7E", "%7F", "%80", "%81",
89 "%82", "%83", "%84", "%85", "%86", "%87", "%88", "%89", "%8A", "%8B",
90 "%8C", "%8D", "%8E", "%8F", "%90", "%91", "%92", "%93", "%94", "%95",
91 "%96", "%97", "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
92 "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", "%A8", "%A9",
93 "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", "%B0", "%B1", "%B2", "%B3",
94 "%B4", "%B5", "%B6", "%B7", "%B8", "%B9", "%BA", "%BB", "%BC", "%BD",
95 "%BE", "%BF", "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
96 "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", "%D0", "%D1",
97 "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", "%D8", "%D9", "%DA", "%DB",
98 "%DC", "%DD", "%DE", "%DF", "%E0", "%E1", "%E2", "%E3", "%E4", "%E5",
99 "%E6", "%E7", "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
100 "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", "%F8", "%F9",
101 "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
104 /* Maps special characters in HTML to their equivalent entites. */
105 static const char * const html_code_map[256] = {
106 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
107 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
108 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
109 NULL, NULL, NULL, NULL,""",NULL,NULL,NULL,"&",NULL,
110 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
111 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
112 "<",NULL,">",NULL,NULL, NULL, NULL, NULL, NULL, NULL,
113 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
114 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
115 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
116 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
117 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
118 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
119 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
120 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
121 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
122 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
123 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
124 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
125 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
126 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
127 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
128 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
129 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
130 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
131 NULL, NULL, NULL, NULL, NULL, NULL
134 /* Maps special characters in a cookie to their equivalent % codes. */
135 static const char * const cookie_code_map[256] = {
136 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
137 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
138 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
139 NULL, NULL, "+", NULL, NULL, NULL, NULL, NULL, NULL, NULL,
140 NULL, NULL, NULL, NULL, "%2C",NULL, NULL, NULL, NULL, NULL,
141 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3B",
142 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
143 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
144 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
145 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
146 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
147 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
148 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
149 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
150 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
151 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
152 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
153 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
154 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
155 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
156 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
157 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
158 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
159 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
160 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
161 NULL, NULL, NULL, NULL, NULL, NULL
165 /*********************************************************************
167 * Function : html_encode
169 * Description : Encodes a string so it's not interpreted as
170 * containing HTML tags or entities.
171 * Replaces <, >, &, and " with the appropriate HTML
175 * 1 : s = String to encode. Null-terminated.
177 * Returns : Encoded string, newly allocated on the heap.
178 * Caller is responsible for freeing it with free().
179 * If s is NULL, or on out-of memory, returns NULL.
181 *********************************************************************/
182 char * html_encode(const char *s)
191 /* each input char can expand to at most 6 chars */
192 buf = (char *) malloc((strlen(s) * 6) + 1);
198 while ( (c = *s++) != '\0')
200 const char * replace_with = html_code_map[(unsigned char) c];
201 if(replace_with != NULL)
203 strcpy(p, replace_with);
204 p += strlen(replace_with);
219 /*********************************************************************
221 * Function : html_encode_and_free_original
223 * Description : Encodes a string so it's not interpreted as
224 * containing HTML tags or entities.
225 * Replaces <, >, &, and " with the appropriate HTML
226 * entities. Free()s original string.
227 * If original string is NULL, simply returns NULL.
230 * 1 : s = String to encode. Null-terminated.
232 * Returns : Encoded string, newly allocated on the heap.
233 * Caller is responsible for freeing it with free().
234 * If s is NULL, or on out-of memory, returns NULL.
236 *********************************************************************/
237 char * html_encode_and_free_original(char *s)
246 result = html_encode(s);
253 /*********************************************************************
255 * Function : cookie_encode
257 * Description : Encodes a string so it can be used in a cookie.
258 * Replaces " ", ",", and ";" with the appropriate
262 * 1 : s = String to encode. Null-terminated.
264 * Returns : Encoded string, newly allocated on the heap.
265 * Caller is responsible for freeing it with free().
266 * If s is NULL, or on out-of memory, returns NULL.
268 *********************************************************************/
269 char * cookie_encode(const char *s)
278 /* each input char can expand to at most 3 chars */
279 buf = (char *) malloc((strlen(s) * 3) + 1);
285 while ( (c = *s++) != '\0')
287 const char * replace_with = cookie_code_map[(unsigned char) c];
288 if (replace_with != NULL)
290 strcpy(p, replace_with);
291 p += strlen(replace_with);
305 /*********************************************************************
307 * Function : url_encode
309 * Description : Encodes a string so it can be used in a URL
310 * query string. Replaces special characters with
311 * the appropriate %xx codes.
314 * 1 : s = String to encode. Null-terminated.
316 * Returns : Encoded string, newly allocated on the heap.
317 * Caller is responsible for freeing it with free().
318 * If s is NULL, or on out-of memory, returns NULL.
320 *********************************************************************/
321 char * url_encode(const char *s)
330 /* each input char can expand to at most 3 chars */
331 buf = (char *) malloc((strlen(s) * 3) + 1);
337 while( (c = *s++) != '\0')
339 const char * replace_with = url_code_map[(unsigned char) c];
340 if (replace_with != NULL)
342 strcpy(p, replace_with);
343 p += strlen(replace_with);
359 /*********************************************************************
363 * Description : Converts a single hex digit to an integer.
366 * 1 : d = in the range of ['0'..'9', 'A'..'F', 'a'..'f']
368 * Returns : The integer value, or -1 for non-hex characters.
370 *********************************************************************/
371 static int xdtoi(const int d)
373 if ((d >= '0') && (d <= '9'))
377 else if ((d >= 'a') && (d <= 'f'))
379 return(d - 'a' + 10);
381 else if ((d >= 'A') && (d <= 'F'))
383 return(d - 'A' + 10);
392 /*********************************************************************
396 * Description : Hex string to integer conversion.
399 * 1 : s = a 2 digit hex string (e.g. "1f"). Only the
400 * first two characters will be looked at.
402 * Returns : The integer value, or 0 for non-hex strings.
404 *********************************************************************/
405 static int xtoi(const char *s)
415 return (d1 << 4) + d2;
423 /*********************************************************************
425 * Function : url_decode
427 * Description : Decodes a URL query string, replacing %xx codes
428 * with their decoded form.
431 * 1 : s = String to decode. Null-terminated.
433 * Returns : Decoded string, newly allocated on the heap.
434 * Caller is responsible for freeing it with free().
436 *********************************************************************/
437 char *url_decode(const char * s)
439 char *buf = malloc(strlen(s) + 1);
454 if ((*q = xtoi(s + 1)) != '\0')
461 /* malformed, just use it */