Mercurial > pidgin.yaz

comparison libpurple/protocols/oscar/encoding.c @ 32010:ce968e115c95

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
propagate from branch 'im.pidgin.cpw.masca.p2p' (head 33ca865dacb9e5bcf763d06f6a42cbaca337cc64) to branch 'im.pidgin.pidgin' (head 92f47f4e8b0cbb107fd97e1ab814d1cedbf109ad)
author Elliott Sales de Andrade <qulogic@pidgin.im>
date Fri, 06 May 2011 06:25:14 +0000
parents 52801bade70e
children 8b9e9c61d061
comparison
equal deleted inserted replaced
32009:f021d93a1f9b 32010:ce968e115c95
19 */ 19 */
20 20
21 #include "encoding.h" 21 #include "encoding.h"
22 22
23 static gchar * 23 static gchar *
24 encoding_multi_convert_to_utf8(const gchar *text, gssize textlen, const gchar *encodings, GError **error, gboolean fallback)
25 {
26 gchar *utf8 = NULL;
27 const gchar *begin = encodings;
28 const gchar *end = NULL;
29 gchar *curr_encoding = NULL; /* allocated buffer for encoding name */
30 const gchar *curr_encoding_ro = NULL; /* read-only encoding name */
31
32 if (!encodings) {
33 purple_debug_error("oscar", "encodings is NULL");
34 return NULL;
35 }
36
37 for (;;)
38 {
39 /* extract next encoding */
40 end = strchr(begin, ',');
41 if (!end) {
42 curr_encoding_ro = begin;
43 } else { /* allocate buffer for encoding */
44 curr_encoding = g_strndup(begin, end - begin);
45 if (!curr_encoding) {
46 purple_debug_error("oscar", "Error allocating memory for encoding");
47 break;
48 }
49 curr_encoding_ro = curr_encoding;
50 }
51
52 if (!g_ascii_strcasecmp(curr_encoding_ro, "utf-8") && g_utf8_validate(text, textlen, NULL)) {
53 break;
54 }
55
56 utf8 = g_convert(text, textlen, "UTF-8", curr_encoding_ro, NULL, NULL, NULL);
57
58 if (!end) /* last occurence. do not free curr_encoding: buffer was'nt allocated */
59 break;
60
61 g_free(curr_encoding); /* free allocated buffer for encoding here */
62
63 if (utf8) /* text was successfully converted */
64 break;
65
66 begin = end + 1;
67 }
68
69 if (!utf8 && fallback)
70 { /* "begin" points to last encoding */
71 utf8 = g_convert_with_fallback(text, textlen, "UTF-8", begin, "?", NULL, NULL, error);
72 }
73
74 return utf8;
75 }
76
77 static gchar *
24 encoding_extract(const char *encoding) 78 encoding_extract(const char *encoding)
25 { 79 {
26 char *begin, *end; 80 char *begin, *end;
27 81
28 if (encoding == NULL) { 82 if (encoding == NULL) {
49 oscar_encoding_to_utf8(const char *encoding, const char *text, int textlen) 103 oscar_encoding_to_utf8(const char *encoding, const char *text, int textlen)
50 { 104 {
51 gchar *utf8 = NULL; 105 gchar *utf8 = NULL;
52 const gchar *glib_encoding = NULL; 106 const gchar *glib_encoding = NULL;
53 gchar *extracted_encoding = encoding_extract(encoding); 107 gchar *extracted_encoding = encoding_extract(encoding);
54 108
55 if (extracted_encoding == NULL || *extracted_encoding == '\0') { 109 if (extracted_encoding == NULL || *extracted_encoding == '\0') {
56 purple_debug_info("oscar", "Empty encoding, assuming UTF-8\n"); 110 purple_debug_info("oscar", "Empty encoding, assuming UTF-8\n");
57 } else if (!g_ascii_strcasecmp(extracted_encoding, "iso-8859-1")) { 111 } else if (!g_ascii_strcasecmp(extracted_encoding, "iso-8859-1")) {
58 glib_encoding = "iso-8859-1"; 112 glib_encoding = "iso-8859-1";
59 } else if (!g_ascii_strcasecmp(extracted_encoding, "ISO-8859-1-Windows-3.1-Latin-1") || !g_ascii_strcasecmp(extracted_encoding, "us-ascii")) { 113 } else if (!g_ascii_strcasecmp(extracted_encoding, "ISO-8859-1-Windows-3.1-Latin-1") || !g_ascii_strcasecmp(extracted_encoding, "us-ascii")) {
63 } else if (g_ascii_strcasecmp(extracted_encoding, "utf-8")) { 117 } else if (g_ascii_strcasecmp(extracted_encoding, "utf-8")) {
64 glib_encoding = extracted_encoding; 118 glib_encoding = extracted_encoding;
65 } 119 }
66 120
67 if (glib_encoding != NULL) { 121 if (glib_encoding != NULL) {
68 utf8 = g_convert(text, textlen, "UTF-8", glib_encoding, NULL, NULL, NULL); 122 utf8 = encoding_multi_convert_to_utf8(text, textlen, glib_encoding, NULL, FALSE);
69 } 123 }
70 124
71 /* 125 /*
72 * If utf8 is still NULL then either the encoding is utf-8 or 126 * If utf8 is still NULL then either the encoding is utf-8 or
73 * we have been unable to convert the text to utf-8 from the encoding 127 * we have been unable to convert the text to utf-8 from the encoding
99 153
100 if (od->icq) 154 if (od->icq)
101 charset = purple_account_get_string(account, "encoding", NULL); 155 charset = purple_account_get_string(account, "encoding", NULL);
102 156
103 if(charset && *charset) 157 if(charset && *charset)
104 ret = g_convert(msg, -1, "UTF-8", charset, NULL, NULL, NULL); 158 ret = encoding_multi_convert_to_utf8(msg, -1, charset, NULL, FALSE);
105 159
106 if(!ret) 160 if(!ret)
107 ret = purple_utf8_try_convert(msg); 161 ret = purple_utf8_try_convert(msg);
108 162
109 return ret; 163 return ret;
117 171
118 if ((charsetstr == NULL) || (*charsetstr == '\0')) 172 if ((charsetstr == NULL) || (*charsetstr == '\0'))
119 return NULL; 173 return NULL;
120 174
121 if (g_ascii_strcasecmp("UTF-8", charsetstr)) { 175 if (g_ascii_strcasecmp("UTF-8", charsetstr)) {
122 if (fallback) 176 ret = encoding_multi_convert_to_utf8(data, datalen, charsetstr, &err, fallback);
123 ret = g_convert_with_fallback(data, datalen, "UTF-8", charsetstr, "?", NULL, NULL, &err);
124 else
125 ret = g_convert(data, datalen, "UTF-8", charsetstr, NULL, NULL, &err);
126 if (err != NULL) { 177 if (err != NULL) {
127 purple_debug_warning("oscar", "Conversion from %s failed: %s.\n", 178 purple_debug_warning("oscar", "Conversion from %s failed: %s.\n",
128 charsetstr, err->message); 179 charsetstr, err->message);
129 g_error_free(err); 180 g_error_free(err);
130 } 181 }