1 const char encode_rcs[] = "$Id: encode.c,v 1.3 2001/11/13 00:16:40 jongfoster 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 * IJBSWA team. http://ijbswa.sourceforge.net
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 1.3 2001/11/13 00:16:40 jongfoster
37 * Replacing references to malloc.h with the standard stdlib.h
38 * (See ANSI or K&R 2nd Ed)
40 * Revision 1.2 2001/05/17 22:52:35 oes
41 * - Cleaned CRLF's from the sources and related files
43 * Revision 1.1.1.1 2001/05/15 13:58:51 oes
44 * Initial import of version 2.9.3 source tree
47 *********************************************************************/
58 const char encode_h_rcs[] = ENCODE_H_VERSION;
60 /* Maps special characters in a URL to their equivalent % codes. */
61 static const char * const url_code_map[256] = {
62 NULL, "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09",
63 "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13",
64 "%14", "%15", "%16", "%17", "%18", "%19", "%1A", "%1B", "%1C", "%1D",
65 "%1E", "%1F", "+", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
66 "%28", "%29", NULL, "%2B", "%2C", NULL, NULL, "%2F", NULL, NULL,
67 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3A", "%3B",
68 "%3C", "%3D", "%3E", "%3F", NULL, NULL, NULL, NULL, NULL, NULL,
69 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
70 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
71 NULL, "%5B", "%5C", "%5D", "%5E", NULL, "%60", NULL, NULL, NULL,
72 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
73 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
74 NULL, NULL, NULL, "%7B", "%7C", "%7D", "%7E", "%7F", "%80", "%81",
75 "%82", "%83", "%84", "%85", "%86", "%87", "%88", "%89", "%8A", "%8B",
76 "%8C", "%8D", "%8E", "%8F", "%90", "%91", "%92", "%93", "%94", "%95",
77 "%96", "%97", "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
78 "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", "%A8", "%A9",
79 "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", "%B0", "%B1", "%B2", "%B3",
80 "%B4", "%B5", "%B6", "%B7", "%B8", "%B9", "%BA", "%BB", "%BC", "%BD",
81 "%BE", "%BF", "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
82 "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", "%D0", "%D1",
83 "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", "%D8", "%D9", "%DA", "%DB",
84 "%DC", "%DD", "%DE", "%DF", "%E0", "%E1", "%E2", "%E3", "%E4", "%E5",
85 "%E6", "%E7", "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
86 "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", "%F8", "%F9",
87 "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
90 /* Maps special characters in HTML to their equivalent entites. */
91 static const char * const html_code_map[256] = {
92 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
93 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
94 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
95 NULL, NULL, NULL, NULL,""",NULL,NULL,NULL,"&",NULL,
96 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
97 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
98 "<",NULL,">",NULL,NULL, NULL, NULL, NULL, NULL, NULL,
99 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
100 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
101 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
102 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
103 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
104 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
105 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
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, 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, 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
120 /* Maps special characters in a cookie to their equivalent % codes. */
121 static const char * const cookie_code_map[256] = {
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,
126 NULL, NULL, NULL, NULL, "%2C",NULL, NULL, NULL, NULL, NULL,
127 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3B",
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, NULL, NULL, NULL, NULL,
135 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
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, 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, 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
151 /*********************************************************************
153 * Function : html_encode
155 * Description : Encodes a string so it's not interpreted as
156 * containing HTML tags or entities.
157 * Replaces <, >, &, and " with the appropriate HTML
161 * 1 : s = String to encode. Null-terminated.
163 * Returns : Encoded string, newly allocated on the heap.
164 * Caller is responsible for freeing it with free().
165 * If s is NULL, or on out-of memory, returns NULL.
167 *********************************************************************/
168 char * html_encode(const char *s)
177 /* each input char can expand to at most 6 chars */
178 buf = (char *) malloc((strlen(s) * 6) + 1);
184 while ( (c = *s++) != '\0')
186 const char * replace_with = html_code_map[(unsigned char) c];
187 if(replace_with != NULL)
189 strcpy(p, replace_with);
190 p += strlen(replace_with);
205 /*********************************************************************
207 * Function : html_encode_and_free_original
209 * Description : Encodes a string so it's not interpreted as
210 * containing HTML tags or entities.
211 * Replaces <, >, &, and " with the appropriate HTML
212 * entities. Free()s original string.
213 * If original string is NULL, simply returns NULL.
216 * 1 : s = String to encode. Null-terminated.
218 * Returns : Encoded string, newly allocated on the heap.
219 * Caller is responsible for freeing it with free().
220 * If s is NULL, or on out-of memory, returns NULL.
222 *********************************************************************/
223 char * html_encode_and_free_original(char *s)
232 result = html_encode(s);
239 /*********************************************************************
241 * Function : cookie_encode
243 * Description : Encodes a string so it can be used in a cookie.
244 * Replaces " ", ",", and ";" with the appropriate
248 * 1 : s = String to encode. Null-terminated.
250 * Returns : Encoded string, newly allocated on the heap.
251 * Caller is responsible for freeing it with free().
252 * If s is NULL, or on out-of memory, returns NULL.
254 *********************************************************************/
255 char * cookie_encode(const char *s)
264 /* each input char can expand to at most 3 chars */
265 buf = (char *) malloc((strlen(s) * 3) + 1);
271 while ( (c = *s++) != '\0')
273 const char * replace_with = cookie_code_map[(unsigned char) c];
274 if (replace_with != NULL)
276 strcpy(p, replace_with);
277 p += strlen(replace_with);
291 /*********************************************************************
293 * Function : url_encode
295 * Description : Encodes a string so it can be used in a URL
296 * query string. Replaces special characters with
297 * the appropriate %xx codes.
300 * 1 : s = String to encode. Null-terminated.
302 * Returns : Encoded string, newly allocated on the heap.
303 * Caller is responsible for freeing it with free().
304 * If s is NULL, or on out-of memory, returns NULL.
306 *********************************************************************/
307 char * url_encode(const char *s)
316 /* each input char can expand to at most 3 chars */
317 buf = (char *) malloc((strlen(s) * 3) + 1);
323 while( (c = *s++) != '\0')
325 const char * replace_with = url_code_map[(unsigned char) c];
326 if (replace_with != NULL)
328 strcpy(p, replace_with);
329 p += strlen(replace_with);
345 /*********************************************************************
349 * Description : Converts a single hex digit to an integer.
352 * 1 : d = in the range of ['0'..'9', 'A'..'F', 'a'..'f']
354 * Returns : The integer value, or -1 for non-hex characters.
356 *********************************************************************/
357 static int xdtoi(char d)
359 if ((d >= '0') && (d <= '9'))
363 else if ((d >= 'a') && (d <= 'f'))
365 return(d - 'a' + 10);
367 else if ((d >= 'A') && (d <= 'F'))
369 return(d - 'A' + 10);
378 /*********************************************************************
382 * Description : Hex string to integer conversion.
385 * 1 : s = a 2 digit hex string (e.g. "1f"). Only the
386 * first two characters will be looked at.
388 * Returns : The integer value, or 0 for non-hex strings.
390 *********************************************************************/
391 static int xtoi(const char *s)
401 return (d1 << 4) + d2;
409 /*********************************************************************
411 * Function : url_decode
413 * Description : Decodes a URL query string, replacing %xx codes
414 * with their decoded form.
417 * 1 : s = String to decode. Null-terminated.
419 * Returns : Decoded string, newly allocated on the heap.
420 * Caller is responsible for freeing it with free().
422 *********************************************************************/
423 char *url_decode(const char * s)
425 char *buf = malloc(strlen(s) + 1);
440 if ((*q = xtoi(s + 1)))
447 /* malformed, just use it */