1 /* ====================================================================
2  * The Kannel Software License, Version 1.0
3  *
4  * Copyright (c) 2001-2014 Kannel Group
5  * Copyright (c) 1998-2001 WapIT Ltd.
6  * All rights reserved.
7  *
8  * Redistribution and use in source and binary forms, with or without
9  * modification, are permitted provided that the following conditions
10  * are met:
11  *
12  * 1. Redistributions of source code must retain the above copyright
13  *    notice, this list of conditions and the following disclaimer.
14  *
15  * 2. Redistributions in binary form must reproduce the above copyright
16  *    notice, this list of conditions and the following disclaimer in
17  *    the documentation and/or other materials provided with the
18  *    distribution.
19  *
20  * 3. The end-user documentation included with the redistribution,
21  *    if any, must include the following acknowledgment:
22  *       "This product includes software developed by the
23  *        Kannel Group (http://www.kannel.org/)."
24  *    Alternately, this acknowledgment may appear in the software itself,
25  *    if and wherever such third-party acknowledgments normally appear.
26  *
27  * 4. The names "Kannel" and "Kannel Group" must not be used to
28  *    endorse or promote products derived from this software without
29  *    prior written permission. For written permission, please
30  *    contact org@kannel.org.
31  *
32  * 5. Products derived from this software may not be called "Kannel",
33  *    nor may "Kannel" appear in their name, without prior written
34  *    permission of the Kannel Group.
35  *
36  * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
37  * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
38  * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
39  * DISCLAIMED.  IN NO EVENT SHALL THE KANNEL GROUP OR ITS CONTRIBUTORS
40  * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY,
41  * OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
42  * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
43  * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
44  * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
45  * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
46  * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
47  * ====================================================================
48  *
49  * This software consists of voluntary contributions made by many
50  * individuals on behalf of the Kannel Group.  For more information on
51  * the Kannel Group, please see <http://www.kannel.org/>.
52  *
53  * Portions of this software are based upon software originally written at
54  * WapIT Ltd., Helsinki, Finland for the Kannel project.
55  */
56 
57 /*
58  * xml_shared.c: Common functions of xml compilers (mainly charset handling
59  * and operations with wbxml binary not using a string table)
60  *
61  * By Tuomas Luttinen & Aarno Syv�nen (for Wiral Ltd)
62  */
63 
64 #include <ctype.h>
65 
66 #include "xml_shared.h"
67 #include "xml_definitions.h"
68 
69 #include <string.h>
70 
71 struct charset_t {
72     char *charset;
73     char *nro;
74     unsigned int MIBenum;
75 };
76 
77 charset_t character_sets[] = {
78     { "ISO", "8859-1", 4 },
79     { "ISO", "8859-2", 5 },
80     { "ISO", "8859-3", 6 },
81     { "ISO", "8859-4", 7 },
82     { "ISO", "8859-5", 8 },
83     { "ISO", "8859-6", 9 },
84     { "ISO", "8859-7", 10 },
85     { "ISO", "8859-8", 11 },
86     { "ISO", "8859-9", 12 },
87     { "WINDOWS", "1250", 2250 },
88     { "WINDOWS", "1251", 2251 },
89     { "WINDOWS", "1252", 2252 },
90     { "WINDOWS", "1253", 2253 },
91     { "WINDOWS", "1254", 2254 },
92     { "WINDOWS", "1255", 2255 },
93     { "WINDOWS", "1256", 2256 },
94     { "WINDOWS", "1257", 2257 },
95     { "WINDOWS", "1258", 2258 },
96     { "UTF", "8", 106 },
97     { NULL }
98 };
99 
100 /****************************************************************************
101  *
102  * Implementation of external functions
103  */
104 
105 
106 /*
107  * set_charset - if xml doesn't have an <?xml..encoding=something>,
108  * converts body from argument charset to UTF-8
109  */
110 
set_charset(Octstr * document,Octstr * charset)111 void set_charset(Octstr *document, Octstr *charset)
112 {
113     long gt = 0, enc = 0;
114     Octstr *encoding = NULL, *text = NULL, *temp = NULL;
115 
116     if (octstr_len(charset) == 0)
117         return;
118 
119     encoding = octstr_create(" encoding");
120     enc = octstr_search(document, encoding, 0);
121     gt = octstr_search_char(document, '>', 0);
122 
123     if (enc < 0 || enc > gt) {
124         gt++;
125         text = octstr_copy(document, gt, octstr_len(document) - gt);
126         if (charset_to_utf8(text, &temp, charset) >= 0) {
127             octstr_delete(document, gt, octstr_len(document) - gt);
128             octstr_append_data(document, octstr_get_cstr(temp),
129                                octstr_len(temp));
130         }
131 
132         octstr_destroy(temp);
133         octstr_destroy(text);
134     }
135 
136     octstr_destroy(encoding);
137 }
138 
139 
140 /*
141  * find_charset_encoding -- parses for a encoding argument within
142  * the xml preabmle, ie. <?xml verion="xxx" encoding="ISO-8859-1"?>
143  */
144 
find_charset_encoding(Octstr * document)145 Octstr *find_charset_encoding(Octstr *document)
146 {
147     long gt = 0, enc = 0;
148     Octstr *encoding = NULL, *temp = NULL;
149 
150     enc = octstr_search(document, octstr_imm(" encoding="), 0);
151     gt = octstr_search(document, octstr_imm("?>"), 0);
152 
153     /* in case there is no encoding argument, assume always UTF-8 */
154     if (enc < 0 || enc + 10 > gt)
155         return NULL;
156 
157 	temp = octstr_copy(document, enc + 10, gt - (enc + 10));
158     octstr_strip_blanks(temp);
159     encoding = octstr_copy(temp, 1, octstr_len(temp) - 2);
160     octstr_destroy(temp);
161 
162     return encoding;
163 }
164 
165 
166 /*
167  * only_blanks - checks if a text node contains only white space, when it can
168  * be left out as a element content.
169  */
170 
only_blanks(const char * text)171 int only_blanks(const char *text)
172 {
173     int blank = 1;
174     int j=0;
175     int len = strlen(text);
176 
177     while ((j<len) && blank) {
178 	blank = blank && isspace((int)text[j]);
179 	j++;
180     }
181 
182     return blank;
183 }
184 
185 /*
186  * Parses the character set of the document.
187  */
188 
parse_charset(Octstr * os)189 int parse_charset(Octstr *os)
190 {
191     Octstr *charset = NULL;
192     Octstr *number = NULL;
193     int i, j, cut = 0, ret = 0;
194 
195     gw_assert(os != NULL);
196     charset = octstr_duplicate(os);
197 
198     /* The charset might be in lower case, so... */
199     octstr_convert_range(charset, 0, octstr_len(charset), toupper);
200 
201     /*
202      * The character set is handled in two parts to make things easier.
203      * The cutting.
204      */
205     if ((cut = octstr_search_char(charset, '_', 0)) > 0) {
206         number = octstr_copy(charset, cut + 1, (octstr_len(charset) - (cut + 1)));
207         octstr_truncate(charset, cut);
208     }
209     else if ((cut = octstr_search_char(charset, '-', 0)) > 0) {
210         number = octstr_copy(charset, cut + 1, (octstr_len(charset) - (cut + 1)));
211         octstr_truncate(charset, cut);
212     }
213 
214     /* And table search. */
215     for (i = 0; character_sets[i].charset != NULL; i++)
216         if (octstr_str_compare(charset, character_sets[i].charset) == 0) {
217             for (j = i; octstr_str_compare(charset,
218                                            character_sets[j].charset) == 0; j++)
219                 if (octstr_str_compare(number, character_sets[j].nro) == 0) {
220                     ret = character_sets[j].MIBenum;
221                     break;
222                 }
223             break;
224         }
225 
226     /* UTF-8 is the default value */
227     if (character_sets[i].charset == NULL)
228         ret = character_sets[i-1].MIBenum;
229 
230     octstr_destroy(number);
231     octstr_destroy(charset);
232 
233     return ret;
234 }
235 
236 /*
237  * element_check_content - a helper function for parse_element for checking
238  * if an element has content or attributes. Returns status bit for attributes
239  * (0x80) and another for content (0x40) added into one octet.
240  */
241 
element_check_content(xmlNodePtr node)242 unsigned char element_check_content(xmlNodePtr node)
243 {
244     unsigned char status_bits = 0x00;
245 
246     if ((node->children != NULL) &&
247 	!((node->children->next == NULL) &&
248 	  (node->children->type == XML_TEXT_NODE) &&
249 	  (only_blanks((char *)node->children->content))))
250 	status_bits = WBXML_CONTENT_BIT;
251 
252     if (node->properties != NULL)
253 	status_bits = status_bits | WBXML_ATTR_BIT;
254 
255     return status_bits;
256 }
257 
258 /*
259  * Return the character sets supported by the WML compiler, as a List
260  * of Octstrs, where each string is the MIME identifier for one charset.
261  */
wml_charsets(void)262 List *wml_charsets(void)
263 {
264     int i;
265     List *result;
266     Octstr *charset;
267 
268     result = gwlist_create();
269     for (i = 0; character_sets[i].charset != NULL; i++) {
270          charset = octstr_create(character_sets[i].charset);
271          octstr_append_char(charset, '-');
272          octstr_append(charset, octstr_imm(character_sets[i].nro));
273          gwlist_append(result, charset);
274     }
275 
276     return result;
277 }
278 
279 /*
280  * Functions working with simple binary data type (no string table). No
281  * variables are present either.
282  */
283 
simple_binary_create(void)284 simple_binary_t *simple_binary_create(void)
285 {
286     simple_binary_t *binary;
287 
288     binary = gw_malloc(sizeof(simple_binary_t));
289 
290     binary->wbxml_version = 0x00;
291     binary->public_id = 0x00;
292     binary->charset = 0x00;
293     binary->binary = octstr_create("");
294 
295     return binary;
296 }
297 
simple_binary_destroy(simple_binary_t * binary)298 void simple_binary_destroy(simple_binary_t *binary)
299 {
300     if (binary == NULL)
301         return;
302 
303     octstr_destroy(binary->binary);
304     gw_free(binary);
305 }
306 
307 /*
308  * Output the wbxml content field after field into octet string os. We add
309  * string table length 0 (meaning no string table) before the content.
310  */
simple_binary_output(Octstr * os,simple_binary_t * binary)311 void simple_binary_output(Octstr *os, simple_binary_t *binary)
312 {
313     gw_assert(octstr_len(os) == 0);
314     octstr_format_append(os, "%c", binary->wbxml_version);
315     octstr_format_append(os, "%c", binary->public_id);
316     octstr_append_uintvar(os, binary->charset);
317     octstr_format_append(os, "%c", 0x00);
318     octstr_format_append(os, "%S", binary->binary);
319 }
320 
parse_end(simple_binary_t ** binary)321 void parse_end(simple_binary_t **binary)
322 {
323     output_char(WBXML_END, binary);
324 }
325 
output_char(int byte,simple_binary_t ** binary)326 void output_char(int byte, simple_binary_t **binary)
327 {
328     octstr_append_char((**binary).binary, byte);
329 }
330 
parse_octet_string(Octstr * os,simple_binary_t ** binary)331 void parse_octet_string(Octstr *os, simple_binary_t **binary)
332 {
333     output_octet_string(os, binary);
334 }
335 
336 /*
337  * Add global tokens to the start and to the end of an inline string.
338  */
parse_inline_string(Octstr * temp,simple_binary_t ** binary)339 void parse_inline_string(Octstr *temp, simple_binary_t **binary)
340 {
341     Octstr *startos;
342 
343     octstr_insert(temp, startos = octstr_format("%c", WBXML_STR_I), 0);
344     octstr_destroy(startos);
345     octstr_format_append(temp, "%c", WBXML_STR_END);
346     parse_octet_string(temp, binary);
347 }
348 
output_octet_string(Octstr * os,simple_binary_t ** sibxml)349 void output_octet_string(Octstr *os, simple_binary_t **sibxml)
350 {
351     octstr_insert((*sibxml)->binary, os, octstr_len((*sibxml)->binary));
352 }
353