1 const char encode_rcs[] = "$Id: encode.c,v 1.8 2002/03/26 22:29:54 swa Exp $";
2 /*********************************************************************
4 * File : $Source: /cvsroot/ijbswa/current/Attic/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 1.8 2002/03/26 22:29:54 swa
37 * we have a new homepage!
39 * Revision 1.7 2002/03/24 13:25:43 swa
40 * name change related issues
42 * Revision 1.6 2002/03/13 00:27:04 jongfoster
45 * Revision 1.5 2002/03/07 03:46:53 oes
46 * Fixed compiler warnings etc
48 * Revision 1.4 2002/01/22 23:28:07 jongfoster
49 * Adding convenience function html_encode_and_free_original()
50 * Making all functions accept NULL paramaters - in this case, they
51 * simply return NULL. This allows error-checking to be deferred.
53 * Revision 1.3 2001/11/13 00:16:40 jongfoster
54 * Replacing references to malloc.h with the standard stdlib.h
55 * (See ANSI or K&R 2nd Ed)
57 * Revision 1.2 2001/05/17 22:52:35 oes
58 * - Cleaned CRLF's from the sources and related files
60 * Revision 1.1.1.1 2001/05/15 13:58:51 oes
61 * Initial import of version 2.9.3 source tree
64 *********************************************************************/
75 const char encode_h_rcs[] = ENCODE_H_VERSION;
77 /* Maps special characters in a URL to their equivalent % codes. */
78 static const char * const url_code_map[256] = {
79 NULL, "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09",
80 "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13",
81 "%14", "%15", "%16", "%17", "%18", "%19", "%1A", "%1B", "%1C", "%1D",
82 "%1E", "%1F", "+", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
83 "%28", "%29", NULL, "%2B", "%2C", NULL, NULL, "%2F", NULL, NULL,
84 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3A", "%3B",
85 "%3C", "%3D", "%3E", "%3F", NULL, NULL, NULL, 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, "%5B", "%5C", "%5D", "%5E", NULL, "%60", NULL, NULL, NULL,
89 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
90 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
91 NULL, NULL, NULL, "%7B", "%7C", "%7D", "%7E", "%7F", "%80", "%81",
92 "%82", "%83", "%84", "%85", "%86", "%87", "%88", "%89", "%8A", "%8B",
93 "%8C", "%8D", "%8E", "%8F", "%90", "%91", "%92", "%93", "%94", "%95",
94 "%96", "%97", "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
95 "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", "%A8", "%A9",
96 "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", "%B0", "%B1", "%B2", "%B3",
97 "%B4", "%B5", "%B6", "%B7", "%B8", "%B9", "%BA", "%BB", "%BC", "%BD",
98 "%BE", "%BF", "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
99 "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", "%D0", "%D1",
100 "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", "%D8", "%D9", "%DA", "%DB",
101 "%DC", "%DD", "%DE", "%DF", "%E0", "%E1", "%E2", "%E3", "%E4", "%E5",
102 "%E6", "%E7", "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
103 "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", "%F8", "%F9",
104 "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
107 /* Maps special characters in HTML to their equivalent entites. */
108 static const char * const html_code_map[256] = {
109 NULL, NULL, 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,
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, NULL, NULL, NULL, NULL,
132 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
133 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
134 NULL, NULL, NULL, NULL, NULL, NULL
137 /* Maps special characters in a cookie to their equivalent % codes. */
138 static const char * const cookie_code_map[256] = {
139 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
140 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
141 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
142 NULL, NULL, "+", NULL, NULL, NULL, NULL, NULL, NULL, NULL,
143 NULL, NULL, NULL, NULL, "%2C",NULL, NULL, NULL, NULL, NULL,
144 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3B",
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, NULL, NULL, NULL, NULL,
162 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
163 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
164 NULL, NULL, NULL, NULL, NULL, NULL
168 /*********************************************************************
170 * Function : html_encode
172 * Description : Encodes a string so it's not interpreted as
173 * containing HTML tags or entities.
174 * Replaces <, >, &, and " with the appropriate HTML
178 * 1 : s = String to encode. Null-terminated.
180 * Returns : Encoded string, newly allocated on the heap.
181 * Caller is responsible for freeing it with free().
182 * If s is NULL, or on out-of memory, returns NULL.
184 *********************************************************************/
185 char * html_encode(const char *s)
194 /* each input char can expand to at most 6 chars */
195 buf = (char *) malloc((strlen(s) * 6) + 1);
201 while ( (c = *s++) != '\0')
203 const char * replace_with = html_code_map[(unsigned char) c];
204 if(replace_with != NULL)
206 strcpy(p, replace_with);
207 p += strlen(replace_with);
222 /*********************************************************************
224 * Function : html_encode_and_free_original
226 * Description : Encodes a string so it's not interpreted as
227 * containing HTML tags or entities.
228 * Replaces <, >, &, and " with the appropriate HTML
229 * entities. Free()s original string.
230 * If original string is NULL, simply returns NULL.
233 * 1 : s = String to encode. Null-terminated.
235 * Returns : Encoded string, newly allocated on the heap.
236 * Caller is responsible for freeing it with free().
237 * If s is NULL, or on out-of memory, returns NULL.
239 *********************************************************************/
240 char * html_encode_and_free_original(char *s)
249 result = html_encode(s);
256 /*********************************************************************
258 * Function : cookie_encode
260 * Description : Encodes a string so it can be used in a cookie.
261 * Replaces " ", ",", and ";" with the appropriate
265 * 1 : s = String to encode. Null-terminated.
267 * Returns : Encoded string, newly allocated on the heap.
268 * Caller is responsible for freeing it with free().
269 * If s is NULL, or on out-of memory, returns NULL.
271 *********************************************************************/
272 char * cookie_encode(const char *s)
281 /* each input char can expand to at most 3 chars */
282 buf = (char *) malloc((strlen(s) * 3) + 1);
288 while ( (c = *s++) != '\0')
290 const char * replace_with = cookie_code_map[(unsigned char) c];
291 if (replace_with != NULL)
293 strcpy(p, replace_with);
294 p += strlen(replace_with);
308 /*********************************************************************
310 * Function : url_encode
312 * Description : Encodes a string so it can be used in a URL
313 * query string. Replaces special characters with
314 * the appropriate %xx codes.
317 * 1 : s = String to encode. Null-terminated.
319 * Returns : Encoded string, newly allocated on the heap.
320 * Caller is responsible for freeing it with free().
321 * If s is NULL, or on out-of memory, returns NULL.
323 *********************************************************************/
324 char * url_encode(const char *s)
333 /* each input char can expand to at most 3 chars */
334 buf = (char *) malloc((strlen(s) * 3) + 1);
340 while( (c = *s++) != '\0')
342 const char * replace_with = url_code_map[(unsigned char) c];
343 if (replace_with != NULL)
345 strcpy(p, replace_with);
346 p += strlen(replace_with);
362 /*********************************************************************
366 * Description : Converts a single hex digit to an integer.
369 * 1 : d = in the range of ['0'..'9', 'A'..'F', 'a'..'f']
371 * Returns : The integer value, or -1 for non-hex characters.
373 *********************************************************************/
374 static int xdtoi(const int d)
376 if ((d >= '0') && (d <= '9'))
380 else if ((d >= 'a') && (d <= 'f'))
382 return(d - 'a' + 10);
384 else if ((d >= 'A') && (d <= 'F'))
386 return(d - 'A' + 10);
395 /*********************************************************************
399 * Description : Hex string to integer conversion.
402 * 1 : s = a 2 digit hex string (e.g. "1f"). Only the
403 * first two characters will be looked at.
405 * Returns : The integer value, or 0 for non-hex strings.
407 *********************************************************************/
408 static int xtoi(const char *s)
418 return (d1 << 4) + d2;
426 /*********************************************************************
428 * Function : url_decode
430 * Description : Decodes a URL query string, replacing %xx codes
431 * with their decoded form.
434 * 1 : s = String to decode. Null-terminated.
436 * Returns : Decoded string, newly allocated on the heap.
437 * Caller is responsible for freeing it with free().
439 *********************************************************************/
440 char *url_decode(const char * s)
442 char *buf = malloc(strlen(s) + 1);
457 if ((*q = xtoi(s + 1)) != '\0')
464 /* malformed, just use it */