Mercurial > pidgin.yaz

comparison libpurple/util.c @ 27944:cfa78428d8b2

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
propagate from branch 'im.pidgin.pidgin' (head 8f2b3a7063a7a0e5cae9de55e55f7066c0d202d6) to branch 'im.pidgin.pidgin.yaz' (head f0674cac79a9d60c5a3d998b37fc2cd75ce0a6b2)
author Yoshiki Yazawa <yaz@honeyplanet.jp>
date Sat, 02 May 2009 20:35:36 +0000
parents ab31daf1c1ee 1688f7e15530
children c2ac87c5a035
comparison
equal deleted inserted replaced
26861:d387f1164b3a 27944:cfa78428d8b2
1221 1221
1222 if (check_value != '\0' && *p == check_value) 1222 if (check_value != '\0' && *p == check_value)
1223 return FALSE; 1223 return FALSE;
1224 1224
1225 q = strstr(p, end_token); 1225 q = strstr(p, end_token);
1226 if(q == NULL) //yaz
1227 return FALSE;
1226 1228
1227 /* Trim leading blanks */ 1229 /* Trim leading blanks */
1228 while (*p != '\n' && g_ascii_isspace(*p)) { 1230 while (*p != '\n' && g_ascii_isspace(*p)) {
1229 p += 1; 1231 p += 1;
1230 } 1232 }
1233 while (q > p && g_ascii_isspace(*(q - 1))) { 1235 while (q > p && g_ascii_isspace(*(q - 1))) {
1234 q -= 1; 1236 q -= 1;
1235 } 1237 }
1236 1238
1237 /* Don't bother with null strings */ 1239 /* Don't bother with null strings */
1238 if (p == q) 1240 if (p >= q)
1239 return FALSE; 1241 return FALSE;
1240 1242
1241 if (q != NULL && (!no_value_token || 1243 if (q != NULL && (!no_value_token ||
1242 (no_value_token && strncmp(p, no_value_token, 1244 (no_value_token && strncmp(p, no_value_token,
1243 strlen(no_value_token))))) 1245 strlen(no_value_token)))))
2004 2006
2005 return str2; 2007 return str2;
2006 } 2008 }
2007 2009
2008 static gboolean 2010 static gboolean
2011 is_zenkaku_space(const char *c)
2012 {
2013 gboolean rv = FALSE;
2014 const guchar *u = (guchar *)c;
2015
2016 if(!c || !strcmp(c, "") || strlen(c) < 3)
2017 rv = FALSE;
2018 else if(*u == 0xe3 && *(u+1) == 0x80 && *(u+2) == 0x80)
2019 rv = TRUE;
2020
2021 return rv;
2022 }
2023
2024 static gboolean
2009 badchar(char c) 2025 badchar(char c)
2010 { 2026 {
2011 switch (c) { 2027 switch (c) {
2012 case ' ': 2028 case ' ':
2013 case ',': 2029 case ',':
2041 const char *c, *t, *q = NULL; 2057 const char *c, *t, *q = NULL;
2042 char *tmpurlbuf, *url_buf; 2058 char *tmpurlbuf, *url_buf;
2043 gunichar g; 2059 gunichar g;
2044 gboolean inside_html = FALSE; 2060 gboolean inside_html = FALSE;
2045 int inside_paren = 0; 2061 int inside_paren = 0;
2062 int inside_bracket = 0;
2046 GString *ret; 2063 GString *ret;
2047 2064
2048 if (text == NULL) 2065 if (text == NULL)
2049 return NULL; 2066 return NULL;
2050 2067
2053 c = text; 2070 c = text;
2054 while (*c) { 2071 while (*c) {
2055 2072
2056 if(*c == '(' && !inside_html) { 2073 if(*c == '(' && !inside_html) {
2057 inside_paren++; 2074 inside_paren++;
2075 ret = g_string_append_c(ret, *c);
2076 c++;
2077 }
2078
2079 if(*c == '[' && !inside_html) {
2080 inside_bracket++;
2058 ret = g_string_append_c(ret, *c); 2081 ret = g_string_append_c(ret, *c);
2059 c++; 2082 c++;
2060 } 2083 }
2061 2084
2062 if(inside_html) { 2085 if(inside_html) {
2084 } 2107 }
2085 } else if ((*c=='h') && (!g_ascii_strncasecmp(c, "http://", 7) || 2108 } else if ((*c=='h') && (!g_ascii_strncasecmp(c, "http://", 7) ||
2086 (!g_ascii_strncasecmp(c, "https://", 8)))) { 2109 (!g_ascii_strncasecmp(c, "https://", 8)))) {
2087 t = c; 2110 t = c;
2088 while (1) { 2111 while (1) {
2089 if (badchar(*t) || badentity(t)) { 2112 if (badchar(*t) || badentity(t) || is_zenkaku_space(t)) {
2090 2113
2091 if ((!g_ascii_strncasecmp(c, "http://", 7) && (t - c == 7)) || 2114 if ((!g_ascii_strncasecmp(c, "http://", 7) && (t - c == 7)) ||
2092 (!g_ascii_strncasecmp(c, "https://", 8) && (t - c == 8))) { 2115 (!g_ascii_strncasecmp(c, "https://", 8) && (t - c == 8))) {
2093 break; 2116 break;
2094 } 2117 }
2099 } 2122 }
2100 2123
2101 if (*(t - 1) == '.') 2124 if (*(t - 1) == '.')
2102 t--; 2125 t--;
2103 if ((*(t - 1) == ')' && (inside_paren > 0))) { 2126 if ((*(t - 1) == ')' && (inside_paren > 0))) {
2127 t--;
2128 }
2129 if ((*(t - 1) == ']' && (inside_bracket > 0))) {
2104 t--; 2130 t--;
2105 } 2131 }
2106 2132
2107 url_buf = g_strndup(c, t - c); 2133 url_buf = g_strndup(c, t - c);
2108 tmpurlbuf = purple_unescape_html(url_buf); 2134 tmpurlbuf = purple_unescape_html(url_buf);
2118 } 2144 }
2119 } else if (!g_ascii_strncasecmp(c, "www.", 4) && (c == text || badchar(c[-1]) || badentity(c-1))) { 2145 } else if (!g_ascii_strncasecmp(c, "www.", 4) && (c == text || badchar(c[-1]) || badentity(c-1))) {
2120 if (c[4] != '.') { 2146 if (c[4] != '.') {
2121 t = c; 2147 t = c;
2122 while (1) { 2148 while (1) {
2123 if (badchar(*t) || badentity(t)) { 2149 if (badchar(*t) || badentity(t) || is_zenkaku_space(t)) {
2124 if (t - c == 4) { 2150 if (t - c == 4) {
2125 break; 2151 break;
2126 } 2152 }
2127 2153
2128 if (*(t) == ',' && (*(t + 1) != ' ')) { 2154 if (*(t) == ',' && (*(t + 1) != ' ')) {
2131 } 2157 }
2132 2158
2133 if (*(t - 1) == '.') 2159 if (*(t - 1) == '.')
2134 t--; 2160 t--;
2135 if ((*(t - 1) == ')' && (inside_paren > 0))) { 2161 if ((*(t - 1) == ')' && (inside_paren > 0))) {
2162 t--;
2163 }
2164 if ((*(t - 1) == ']' && (inside_bracket > 0))) {
2136 t--; 2165 t--;
2137 } 2166 }
2138 url_buf = g_strndup(c, t - c); 2167 url_buf = g_strndup(c, t - c);
2139 tmpurlbuf = purple_unescape_html(url_buf); 2168 tmpurlbuf = purple_unescape_html(url_buf);
2140 g_string_append_printf(ret, 2169 g_string_append_printf(ret,
2149 } 2178 }
2150 } 2179 }
2151 } else if (!g_ascii_strncasecmp(c, "ftp://", 6) || !g_ascii_strncasecmp(c, "sftp://", 7)) { 2180 } else if (!g_ascii_strncasecmp(c, "ftp://", 6) || !g_ascii_strncasecmp(c, "sftp://", 7)) {
2152 t = c; 2181 t = c;
2153 while (1) { 2182 while (1) {
2154 if (badchar(*t) || badentity(t)) { 2183 if (badchar(*t) || badentity(t) || is_zenkaku_space(t)) {
2155 2184
2156 if ((!g_ascii_strncasecmp(c, "ftp://", 6) && (t - c == 6)) || 2185 if ((!g_ascii_strncasecmp(c, "ftp://", 6) && (t - c == 6)) ||
2157 (!g_ascii_strncasecmp(c, "sftp://", 7) && (t - c == 7))) { 2186 (!g_ascii_strncasecmp(c, "sftp://", 7) && (t - c == 7))) {
2158 break; 2187 break;
2159 } 2188 }
2160 2189
2161 if (*(t - 1) == '.') 2190 if (*(t - 1) == '.')
2162 t--; 2191 t--;
2163 if ((*(t - 1) == ')' && (inside_paren > 0))) { 2192 if ((*(t - 1) == ')' && (inside_paren > 0))) {
2193 t--;
2194 }
2195 if ((*(t - 1) == ']' && (inside_bracket > 0))) {
2164 t--; 2196 t--;
2165 } 2197 }
2166 url_buf = g_strndup(c, t - c); 2198 url_buf = g_strndup(c, t - c);
2167 tmpurlbuf = purple_unescape_html(url_buf); 2199 tmpurlbuf = purple_unescape_html(url_buf);
2168 g_string_append_printf(ret, "<A HREF=\"%s\">%s</A>", 2200 g_string_append_printf(ret, "<A HREF=\"%s\">%s</A>",
2179 } 2211 }
2180 } else if (!g_ascii_strncasecmp(c, "ftp.", 4) && (c == text || badchar(c[-1]) || badentity(c-1))) { 2212 } else if (!g_ascii_strncasecmp(c, "ftp.", 4) && (c == text || badchar(c[-1]) || badentity(c-1))) {
2181 if (c[4] != '.') { 2213 if (c[4] != '.') {
2182 t = c; 2214 t = c;
2183 while (1) { 2215 while (1) {
2184 if (badchar(*t) || badentity(t)) { 2216 if (badchar(*t) || badentity(t) || is_zenkaku_space(t)) {
2185 if (t - c == 4) { 2217 if (t - c == 4) {
2186 break; 2218 break;
2187 } 2219 }
2188 if (*(t - 1) == '.') 2220 if (*(t - 1) == '.')
2189 t--; 2221 t--;
2190 if ((*(t - 1) == ')' && (inside_paren > 0))) { 2222 if ((*(t - 1) == ')' && (inside_paren > 0))) {
2223 t--;
2224 }
2225 if ((*(t - 1) == ']' && (inside_bracket > 0))) {
2191 t--; 2226 t--;
2192 } 2227 }
2193 url_buf = g_strndup(c, t - c); 2228 url_buf = g_strndup(c, t - c);
2194 tmpurlbuf = purple_unescape_html(url_buf); 2229 tmpurlbuf = purple_unescape_html(url_buf);
2195 g_string_append_printf(ret, 2230 g_string_append_printf(ret,
2206 } 2241 }
2207 } 2242 }
2208 } else if (!g_ascii_strncasecmp(c, "mailto:", 7)) { 2243 } else if (!g_ascii_strncasecmp(c, "mailto:", 7)) {
2209 t = c; 2244 t = c;
2210 while (1) { 2245 while (1) {
2211 if (badchar(*t) || badentity(t)) { 2246 if (badchar(*t) || badentity(t) || is_zenkaku_space(t)) {
2212 char *d; 2247 char *d;
2213 if (t - c == 7) { 2248 if (t - c == 7) {
2214 break; 2249 break;
2215 } 2250 }
2216 if (*(t - 1) == '.') 2251 if (*(t - 1) == '.')
2240 } 2275 }
2241 } else if ((*c=='x') && (!g_ascii_strncasecmp(c, "xmpp:", 5)) && 2276 } else if ((*c=='x') && (!g_ascii_strncasecmp(c, "xmpp:", 5)) &&
2242 (c == text || badchar(c[-1]) || badentity(c-1))) { 2277 (c == text || badchar(c[-1]) || badentity(c-1))) {
2243 t = c; 2278 t = c;
2244 while (1) { 2279 while (1) {
2245 if (badchar(*t) || badentity(t)) { 2280 if (badchar(*t) || badentity(t) || is_zenkaku_space(t)) {
2246 2281
2247 if (t - c == 5) { 2282 if (t - c == 5) {
2248 break; 2283 break;
2249 } 2284 }
2250 2285
2254 } 2289 }
2255 2290
2256 if (*(t - 1) == '.') 2291 if (*(t - 1) == '.')
2257 t--; 2292 t--;
2258 if ((*(t - 1) == ')' && (inside_paren > 0))) { 2293 if ((*(t - 1) == ')' && (inside_paren > 0))) {
2294 t--;
2295 }
2296 if ((*(t - 1) == ']' && (inside_bracket > 0))) {
2259 t--; 2297 t--;
2260 } 2298 }
2261 2299
2262 url_buf = g_strndup(c, t - c); 2300 url_buf = g_strndup(c, t - c);
2263 tmpurlbuf = purple_unescape_html(url_buf); 2301 tmpurlbuf = purple_unescape_html(url_buf);
2340 } 2378 }
2341 } 2379 }
2342 2380
2343 if(*c == ')' && !inside_html) { 2381 if(*c == ')' && !inside_html) {
2344 inside_paren--; 2382 inside_paren--;
2383 ret = g_string_append_c(ret, *c);
2384 c++;
2385 }
2386 if(*c == ']' && !inside_html) {
2387 inside_bracket--;
2345 ret = g_string_append_c(ret, *c); 2388 ret = g_string_append_c(ret, *c);
2346 c++; 2389 c++;
2347 } 2390 }
2348 2391
2349 if (*c == 0) 2392 if (*c == 0)
4847 } else { 4890 } else {
4848 return hostname; 4891 return hostname;
4849 } 4892 }
4850 #endif 4893 #endif
4851 } 4894 }
4895
4896 #ifdef _WIN32
4897 void botch_ucs(gchar *ucs_src, gsize len)
4898 {
4899 /* no operation */
4900 }
4901 #else
4902 void botch_ucs(gchar *ucs_src, gsize len)
4903 {
4904 gint i;
4905 guchar *ucs = (guchar *)ucs_src;
4906
4907 g_return_if_fail(ucs_src != NULL);
4908 g_return_if_fail(len > 0);
4909
4910 for(i=0;i<len;i+=2){
4911 switch(*(ucs+i)){
4912 case 0x00:
4913 switch(*(ucs+i+1)){
4914 case 0xa2: // ¢
4915 *(ucs+i) = 0xff;
4916 *(ucs+i+1) = 0xe0;
4917 break;
4918 case 0xa3: // £
4919 *(ucs+i) = 0xff;
4920 *(ucs+i+1) = 0xe1;
4921 break;
4922 case 0xac: // ¬
4923 *(ucs+i) = 0xff;
4924 *(ucs+i+1) = 0xe2;
4925 break;
4926 }
4927 break;
4928 case 0x20: // ‖
4929 if(*(ucs+i+1) == 0x16){
4930 *(ucs+i) = 0x22;
4931 *(ucs+i+1) = 0x25;
4932 }
4933 break;
4934 case 0x22: // −
4935 if(*(ucs+i+1) == 0x12){
4936 *(ucs+i) = 0xff;
4937 *(ucs+i+1) = 0x0d;
4938 }
4939 break;
4940 case 0x30: // 〜
4941 if(*(ucs+i+1) == 0x1c){
4942 *(ucs+i) = 0xff;
4943 *(ucs+i+1) = 0x5e;
4944 }
4945 break;
4946 }
4947 }
4948
4949 }
4950 #endif
4951
4952 #ifdef _WIN32
4953 void sanitize_ucs(gchar *ucs, gsize len)
4954 {
4955 /* no operation */
4956 }
4957 #else
4958 void sanitize_ucs(gchar *ucs_src, gsize len)
4959 {
4960 gint i;
4961 guchar *ucs = (guchar *)ucs_src;
4962
4963 g_return_if_fail(ucs_src != NULL);
4964 g_return_if_fail(len > 0);
4965
4966 for(i=0;i<len;i+=2){
4967 switch(*(ucs+i)){
4968 case 0x22:
4969 switch(*(ucs+i+1)){
4970 case 0x25: // ‖
4971 *(ucs+i) = 0x20;
4972 *(ucs+i+1) = 0x16;
4973 break;
4974 }
4975 break;
4976 case 0xff:
4977 switch(*(ucs+i+1)){
4978 case 0x0d: // −
4979 *(ucs+i) = 0x22;
4980 *(ucs+i+1) = 0x12;
4981 break;
4982 case 0x5e: // 〜
4983 *(ucs+i) = 0x30;
4984 *(ucs+i+1) = 0x1c;
4985 break;
4986 case 0xe0: // ¢
4987 *(ucs+i) = 0x00;
4988 *(ucs+i+1) = 0xa2;
4989 break;
4990 case 0xe1: // £
4991 *(ucs+i) = 0x00;
4992 *(ucs+i+1) = 0xa3;
4993 break;
4994 case 0xe2: // ¬
4995 *(ucs+i) = 0x00;
4996 *(ucs+i+1) = 0xac;
4997 break;
4998 }
4999 break;
5000 }
5001 }
5002 }
5003 #endif
5004
5005 #ifdef _WIN32
5006 gchar *sanitize_utf(const gchar *msg, gsize len, gsize *newlen)
5007 {
5008 g_return_val_if_fail(msg != NULL, NULL);
5009 if(len == -1)
5010 len = strlen(msg);
5011 g_return_val_if_fail(len > 0, NULL);
5012
5013 if(newlen)
5014 *newlen = len;
5015
5016 return g_strndup(msg, len);
5017 }
5018 #else
5019 gchar *sanitize_utf(const gchar *msg, gsize len, gsize *newlen)
5020 {
5021 gint i;
5022 size_t bytes;
5023 guchar *utf;
5024
5025 g_return_val_if_fail(msg != NULL, NULL);
5026 if(len == -1)
5027 len = strlen(msg);
5028 g_return_val_if_fail(len > 0, NULL);
5029
5030 utf = (guchar *)g_strndup(msg, len);
5031
5032 bytes = len;
5033
5034 for(i=0;i<len;i++){
5035 switch(*(utf+i)){
5036 case 0xe2:
5037 if(*(utf+i+1) == 0x88) {
5038 if(*(utf+i+2) == 0xa5) { // ‖
5039 *(utf+i) = 0xe2;
5040 *(utf+i+1) = 0x80;
5041 *(utf+i+2) = 0x96;
5042 }
5043 }
5044 break;
5045 case 0xef:
5046 switch(*(utf+i+1)){
5047 case 0xbc:
5048 if(*(utf+i+2) == 0x8d) { // −
5049 *(utf+i) = 0xe2;
5050 *(utf+i+1) = 0x88;
5051 *(utf+i+2) = 0x92;
5052 }
5053 break;
5054 case 0xbd:
5055 if(*(utf+i+2) == 0x9e) { // 〜
5056 *(utf+i) = 0xe3;
5057 *(utf+i+1) = 0x80;
5058 *(utf+i+2) = 0x9c;
5059 }
5060 break;
5061 case 0xbf:
5062 switch(*(utf+i+2)){
5063 case 0xa0: // ¢
5064 *(utf+i) = 0xc2;
5065 *(utf+i+1) = 0xa2;
5066 memmove(utf+i+2, utf+i+3,
5067 len-i-3); //shorten by 1byte
5068 bytes--;
5069 break;
5070 case 0xa1: // £
5071 *(utf+i) = 0xc2;
5072 *(utf+i+1) = 0xa3;
5073 memmove(utf+i+2, utf+i+3,
5074 len-i-3); //shorten by 1byte
5075 bytes--;
5076 break;
5077 case 0xa2: // ¬
5078 *(utf+i) = 0xc2;
5079 *(utf+i+1) = 0xac;
5080 memmove(utf+i+2, utf+i+3,
5081 len-i-3); //shorten by 1byte
5082 bytes--;
5083 break;
5084 }
5085 break;
5086 }
5087 break;
5088 }
5089 }
5090 *(utf+bytes)= 0x00; //terminate
5091 if(newlen)
5092 *newlen = bytes;
5093 return (gchar *)utf;
5094 }
5095 #endif
5096
5097 #ifdef _WIN32
5098 gchar *botch_utf(const gchar *msg, gsize len, gsize *newlen)
5099 {
5100 g_return_val_if_fail(msg != NULL, NULL);
5101 if(len == -1)
5102 len = strlen(msg);
5103 g_return_val_if_fail(len > 0, NULL);
5104
5105 if(newlen)
5106 *newlen = len;
5107
5108 return g_strndup(msg, len);
5109 }
5110 #else
5111 gchar *botch_utf(const gchar *msg, gsize len, gsize *newlen)
5112 {
5113 int i,bytes;
5114 unsigned char *utf;
5115
5116 g_return_val_if_fail(msg != NULL, NULL);
5117 if(len == -1)
5118 len = strlen(msg);
5119 g_return_val_if_fail(len > 0, NULL);
5120
5121 bytes = len;
5122
5123 utf = g_malloc0(bytes*3/2+1); /* new length might be 3/2 in the worst case */
5124 memcpy(utf, msg, bytes);
5125
5126 for(i=0;i<bytes;i++){
5127 switch(*(utf+i)){
5128 case 0xc2:
5129 switch(*(utf+i+1)){
5130 case 0xa2: // ¢
5131 *(utf+i) = 0xef;
5132 *(utf+i+1) = 0xbf;
5133 memmove(utf+i+3, utf+i+2, bytes-i-2);
5134 *(utf+i+2) = 0xa0;
5135 bytes++;
5136 break;
5137 case 0xa3: // £
5138 *(utf+i) = 0xef;
5139 *(utf+i+1) = 0xbf;
5140 memmove(utf+i+3, utf+i+2, bytes-i-2);
5141 *(utf+i+2) = 0xa1;
5142 bytes++;
5143 break;
5144 case 0xac: // ¬
5145 *(utf+i) = 0xef;
5146 *(utf+i+1) = 0xbf;
5147 memmove(utf+i+3, utf+i+2, bytes-i-2);
5148 *(utf+i+2) = 0xa2;
5149 bytes++;
5150 break;
5151 }
5152 break;
5153 case 0xe2:
5154 switch(*(utf+i+1)){
5155 case 0x80: // ‖
5156 if(*(utf+i+2) == 0x96){
5157 *(utf+i) = 0xe2;
5158 *(utf+i+1) = 0x88;
5159 *(utf+i+2) = 0xa5;
5160 }
5161 break;
5162 case 0x88: // −
5163 if(*(utf+i+1) == 0x92){
5164 *(utf+i) = 0xef;
5165 *(utf+i+1) = 0xbc;
5166 *(utf+i+2) = 0x8d;
5167 }
5168 break;
5169 }
5170 break;
5171 case 0xe3: // 〜
5172 if(*(utf+i+1) == 0x80){
5173 if(*(utf+i+2) == 0x9c){
5174 *(utf+i) = 0xef;
5175 *(utf+i+1) = 0xbd;
5176 *(utf+i+2) = 0x9e;
5177 }
5178 }
5179 break;
5180 } //switch
5181 }
5182 *(utf+bytes) = 0x00; //terminate
5183 if(newlen)
5184 *newlen = bytes;
5185 return (gchar *)utf;
5186 }
5187 #endif