Line data Source code
1 : /*********************************************************************
2 : *
3 : * File : $Source: /cvsroot/ijbswa/current/encode.c,v $
4 : *
5 : * Purpose : Functions to encode and decode URLs, and also to
6 : * encode cookies and HTML text.
7 : *
8 : * Copyright : Written by and Copyright (C) 2001 the
9 : * Privoxy team. https://www.privoxy.org/
10 : *
11 : * Based on the Internet Junkbuster originally written
12 : * by and Copyright (C) 1997 Anonymous Coders and
13 : * Junkbusters Corporation. http://www.junkbusters.com
14 : *
15 : * This program is free software; you can redistribute it
16 : * and/or modify it under the terms of the GNU General
17 : * Public License as published by the Free Software
18 : * Foundation; either version 2 of the License, or (at
19 : * your option) any later version.
20 : *
21 : * This program is distributed in the hope that it will
22 : * be useful, but WITHOUT ANY WARRANTY; without even the
23 : * implied warranty of MERCHANTABILITY or FITNESS FOR A
24 : * PARTICULAR PURPOSE. See the GNU General Public
25 : * License for more details.
26 : *
27 : * The GNU General Public License should be included with
28 : * this file. If not, you can view it at
29 : * http://www.gnu.org/copyleft/gpl.html
30 : * or write to the Free Software Foundation, Inc., 59
31 : * Temple Place - Suite 330, Boston, MA 02111-1307, USA.
32 : *
33 : *********************************************************************/
34 :
35 :
36 : #include "config.h"
37 :
38 : #include <stdio.h>
39 : #include <stdlib.h>
40 : #include <string.h>
41 : #include <assert.h>
42 :
43 : #include "miscutil.h"
44 : #include "encode.h"
45 :
46 : /* Maps special characters in a URL to their equivalent % codes. */
47 : static const char url_code_map[256][4] = {
48 : "", "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09",
49 : "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13",
50 : "%14", "%15", "%16", "%17", "%18", "%19", "%1A", "%1B", "%1C", "%1D",
51 : "%1E", "%1F", "%20", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
52 : "%28", "%29", "", "%2B", "%2C", "", "", "%2F", "", "",
53 : "", "", "", "", "", "", "", "", "%3A", "%3B",
54 : "%3C", "%3D", "%3E", "%3F", "", "", "", "", "", "",
55 : "", "", "", "", "", "", "", "", "", "",
56 : "", "", "", "", "", "", "", "", "", "",
57 : "", "%5B", "%5C", "%5D", "%5E", "", "%60", "", "", "",
58 : "", "", "", "", "", "", "", "", "", "",
59 : "", "", "", "", "", "", "", "", "", "",
60 : "", "", "", "%7B", "%7C", "%7D", "%7E", "%7F", "%80", "%81",
61 : "%82", "%83", "%84", "%85", "%86", "%87", "%88", "%89", "%8A", "%8B",
62 : "%8C", "%8D", "%8E", "%8F", "%90", "%91", "%92", "%93", "%94", "%95",
63 : "%96", "%97", "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
64 : "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", "%A8", "%A9",
65 : "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", "%B0", "%B1", "%B2", "%B3",
66 : "%B4", "%B5", "%B6", "%B7", "%B8", "%B9", "%BA", "%BB", "%BC", "%BD",
67 : "%BE", "%BF", "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
68 : "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", "%D0", "%D1",
69 : "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", "%D8", "%D9", "%DA", "%DB",
70 : "%DC", "%DD", "%DE", "%DF", "%E0", "%E1", "%E2", "%E3", "%E4", "%E5",
71 : "%E6", "%E7", "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
72 : "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", "%F8", "%F9",
73 : "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
74 : };
75 :
76 : /* Maps special characters in HTML to their equivalent entities. */
77 : static const char * const html_code_map[256] = {
78 : NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
79 : NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
80 : NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
81 : NULL, NULL, NULL, NULL,""",NULL,NULL,NULL,"&","'",
82 : NULL, NULL, NULL, NULL, 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,
85 : NULL, NULL, NULL, NULL, 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, NULL, NULL, NULL, NULL, NULL, NULL, 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, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
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, 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, 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
104 : };
105 :
106 :
107 : /*********************************************************************
108 : *
109 : * Function : html_encode
110 : *
111 : * Description : Encodes a string so it's not interpreted as
112 : * containing HTML tags or entities.
113 : * Replaces <, >, &, and " with the appropriate HTML
114 : * entities.
115 : *
116 : * Parameters :
117 : * 1 : s = String to encode. Null-terminated.
118 : *
119 : * Returns : Encoded string, newly allocated on the heap.
120 : * Caller is responsible for freeing it with free().
121 : * If s is NULL, or on out-of memory, returns NULL.
122 : *
123 : *********************************************************************/
124 619959 : char * html_encode(const char *s)
125 : {
126 : char * buf;
127 : size_t buf_size;
128 :
129 619959 : if (s == NULL)
130 : {
131 108 : return NULL;
132 : }
133 :
134 : /* each input char can expand to at most 6 chars */
135 619851 : buf_size = (strlen(s) * 6) + 1;
136 619851 : buf = (char *) malloc(buf_size);
137 :
138 619851 : if (buf)
139 : {
140 : char c;
141 619851 : char * p = buf;
142 11663564 : while ((c = *s++) != '\0')
143 : {
144 11043713 : const char * replace_with = html_code_map[(unsigned char) c];
145 11043713 : if (replace_with != NULL)
146 : {
147 21272 : const size_t bytes_written = (size_t)(p - buf);
148 21272 : assert(bytes_written < buf_size);
149 21272 : p += strlcpy(p, replace_with, buf_size - bytes_written);
150 : }
151 : else
152 : {
153 11022441 : *p++ = c;
154 : }
155 : }
156 :
157 619851 : *p = '\0';
158 :
159 619851 : assert(strlen(buf) < buf_size);
160 : }
161 :
162 619851 : return(buf);
163 : }
164 :
165 :
166 : /*********************************************************************
167 : *
168 : * Function : html_encode_and_free_original
169 : *
170 : * Description : Encodes a string so it's not interpreted as
171 : * containing HTML tags or entities.
172 : * Replaces <, >, &, and " with the appropriate HTML
173 : * entities. Free()s original string.
174 : * If original string is NULL, simply returns NULL.
175 : *
176 : * Parameters :
177 : * 1 : s = String to encode. Null-terminated.
178 : *
179 : * Returns : Encoded string, newly allocated on the heap.
180 : * Caller is responsible for freeing it with free().
181 : * If s is NULL, or on out-of memory, returns NULL.
182 : *
183 : *********************************************************************/
184 337 : char * html_encode_and_free_original(char *s)
185 : {
186 : char * result;
187 :
188 337 : if (s == NULL)
189 : {
190 0 : return NULL;
191 : }
192 :
193 337 : result = html_encode(s);
194 337 : free(s);
195 :
196 337 : return result;
197 : }
198 :
199 :
200 : /*********************************************************************
201 : *
202 : * Function : url_encode
203 : *
204 : * Description : Encodes a string so it can be used in a URL
205 : * query string. Replaces special characters with
206 : * the appropriate %xx codes.
207 : *
208 : * XXX: url_query_encode() would be a more fitting
209 : * name.
210 : *
211 : * Parameters :
212 : * 1 : s = String to encode. Null-terminated.
213 : *
214 : * Returns : Encoded string, newly allocated on the heap.
215 : * Caller is responsible for freeing it with free().
216 : * If s is NULL, or on out-of memory, returns NULL.
217 : *
218 : *********************************************************************/
219 32718 : char * url_encode(const char *s)
220 : {
221 : char * buf;
222 : size_t buf_size;
223 :
224 32718 : if (s == NULL)
225 : {
226 0 : return NULL;
227 : }
228 :
229 : /* each input char can expand to at most 3 chars */
230 32718 : buf_size = (strlen(s) * 3) + 1;
231 32718 : buf = (char *) malloc(buf_size);
232 :
233 32718 : if (buf)
234 : {
235 : char c;
236 32718 : char * p = buf;
237 692180 : while((c = *s++) != '\0')
238 : {
239 659462 : const char *replace_with = url_code_map[(unsigned char) c];
240 659462 : if (*replace_with != '\0')
241 : {
242 142647 : const size_t bytes_written = (size_t)(p - buf);
243 142647 : assert(bytes_written < buf_size);
244 142647 : p += strlcpy(p, replace_with, buf_size - bytes_written);
245 : }
246 : else
247 : {
248 516815 : *p++ = c;
249 : }
250 : }
251 :
252 32718 : *p = '\0';
253 :
254 32718 : assert(strlen(buf) < buf_size);
255 : }
256 :
257 32718 : return(buf);
258 : }
259 :
260 :
261 : /*********************************************************************
262 : *
263 : * Function : xdtoi
264 : *
265 : * Description : Converts a single hex digit to an integer.
266 : *
267 : * Parameters :
268 : * 1 : d = in the range of ['0'..'9', 'A'..'F', 'a'..'f']
269 : *
270 : * Returns : The integer value, or -1 for non-hex characters.
271 : *
272 : *********************************************************************/
273 16773 : static int xdtoi(const int d)
274 : {
275 16773 : if ((d >= '0') && (d <= '9'))
276 : {
277 7286 : return(d - '0');
278 : }
279 9487 : else if ((d >= 'a') && (d <= 'f'))
280 : {
281 999 : return(d - 'a' + 10);
282 : }
283 8488 : else if ((d >= 'A') && (d <= 'F'))
284 : {
285 6127 : return(d - 'A' + 10);
286 : }
287 : else
288 : {
289 2361 : return(-1);
290 : }
291 : }
292 :
293 :
294 : /*********************************************************************
295 : *
296 : * Function : xtoi
297 : *
298 : * Description : Hex string to integer conversion.
299 : *
300 : * Parameters :
301 : * 1 : s = a 2 digit hex string (e.g. "1f"). Only the
302 : * first two characters will be looked at.
303 : *
304 : * Returns : The integer value, or 0 for non-hex strings.
305 : *
306 : *********************************************************************/
307 9311 : int xtoi(const char *s)
308 : {
309 : int d1;
310 :
311 9311 : d1 = xdtoi(*s);
312 9311 : if (d1 >= 0)
313 : {
314 7462 : int d2 = xdtoi(*(s+1));
315 7462 : if (d2 >= 0)
316 : {
317 6950 : return (d1 << 4) + d2;
318 : }
319 : }
320 :
321 2361 : return 0;
322 : }
323 :
324 :
325 : /*********************************************************************
326 : *
327 : * Function : url_decode
328 : *
329 : * Description : Decodes a URL query string, replacing %xx codes
330 : * with their decoded form.
331 : *
332 : * Parameters :
333 : * 1 : s = String to decode. Null-terminated.
334 : *
335 : * Returns : Decoded string, newly allocated on the heap.
336 : * Caller is responsible for freeing it with free().
337 : *
338 : *********************************************************************/
339 157519 : char *url_decode(const char * s)
340 : {
341 157519 : char *buf = malloc(strlen(s) + 1);
342 157519 : char *q = buf;
343 :
344 157519 : if (buf)
345 : {
346 1751821 : while (*s)
347 : {
348 1594302 : switch (*s)
349 : {
350 37950 : case '+':
351 37950 : s++;
352 37950 : *q++ = ' ';
353 37950 : break;
354 :
355 9311 : case '%':
356 9311 : if ((*q = (char)xtoi(s + 1)) != '\0')
357 : {
358 6736 : s += 3;
359 6736 : q++;
360 : }
361 : else
362 : {
363 : /* malformed, just use it */
364 2575 : *q++ = *s++;
365 : }
366 9311 : break;
367 :
368 1547041 : default:
369 1547041 : *q++ = *s++;
370 1547041 : break;
371 : }
372 : }
373 157519 : *q = '\0';
374 : }
375 :
376 157519 : return(buf);
377 :
378 : }
379 :
380 :
381 : /*********************************************************************
382 : *
383 : * Function : percent_encode_url
384 : *
385 : * Description : Percent-encodes a string so it no longer contains
386 : * any characters that aren't valid in an URL according
387 : * to RFC 3986.
388 : *
389 : * XXX: Do not confuse with encode_url()
390 : *
391 : * Parameters :
392 : * 1 : s = String to encode. Null-terminated.
393 : *
394 : * Returns : Encoded string, newly allocated on the heap.
395 : * Caller is responsible for freeing it with free().
396 : * If s is NULL, or on out-of memory, returns NULL.
397 : *
398 : *********************************************************************/
399 314 : char *percent_encode_url(const char *s)
400 : {
401 : static const char allowed_characters[128] = {
402 : '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
403 : '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
404 : '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
405 : '\0', '\0', '\0', '!', '\0', '#', '$', '%', '&', '\'',
406 : '(', ')', '*', '+', ',', '-', '.', '/', '0', '1',
407 : '2', '3', '4', '5', '6', '7', '8', '9', ':', ';',
408 : '\0', '=', '\0', '?', '@', 'A', 'B', 'C', 'D', 'E',
409 : 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O',
410 : 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y',
411 : 'Z', '[', '\0', ']', '\0', '_', '\0', 'a', 'b', 'c',
412 : 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
413 : 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w',
414 : 'x', 'y', 'z', '\0', '\0', '\0', '~', '\0'
415 : };
416 : char *buf;
417 : size_t buf_size;
418 :
419 314 : assert(s != NULL);
420 :
421 : /* Each input char can expand to at most 3 chars. */
422 314 : buf_size = (strlen(s) * 3) + 1;
423 314 : buf = (char *)malloc(buf_size);
424 :
425 314 : if (buf != NULL)
426 : {
427 : char c;
428 314 : char *p = buf;
429 15756 : while ((c = *s++) != '\0')
430 : {
431 15442 : const unsigned int i = (unsigned char)c;
432 15442 : if (i >= sizeof(allowed_characters) || '\0' == allowed_characters[i])
433 4263 : {
434 4263 : const char *replace_with = url_code_map[i];
435 4263 : assert(*replace_with != '\0');
436 4263 : if (*replace_with != '\0')
437 : {
438 4263 : const size_t bytes_written = (size_t)(p - buf);
439 4263 : assert(bytes_written < buf_size);
440 4263 : p += strlcpy(p, replace_with, buf_size - bytes_written);
441 : }
442 : }
443 : else
444 : {
445 11179 : *p++ = c;
446 : }
447 : }
448 314 : *p = '\0';
449 :
450 314 : assert(strlen(buf) < buf_size);
451 : }
452 :
453 314 : return(buf);
454 :
455 : }
456 :
457 :
458 : /*
459 : Local Variables:
460 : tab-width: 3
461 : end:
462 : */
|
