Mercurial > pidgin.yaz

comparison libpurple/util.c @ 27930:25319f536d93

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
propagate from branch 'im.pidgin.pidgin' (head 5aca19ea8964e864e3374ac4fd3c1c81cd23a426) to branch 'im.pidgin.pidgin.yaz' (head 908c143511eb03dcaab43319cf4555427004823f)
author Yoshiki Yazawa <yaz@honeyplanet.jp>
date Tue, 24 Feb 2009 10:26:45 +0000
parents 45434c3fd878
children d8e6a2d592a4
comparison
equal deleted inserted replaced
25144:ac8defe6eee4 27930:25319f536d93
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)
4886 } else { 4929 } else {
4887 return hostname; 4930 return hostname;
4888 } 4931 }
4889 #endif 4932 #endif
4890 } 4933 }
4934
4935 #ifdef _WIN32
4936 void botch_ucs(gchar *ucs_src, gsize len)
4937 {
4938 /* no operation */
4939 }
4940 #else
4941 void botch_ucs(gchar *ucs_src, gsize len)
4942 {
4943 gint i;
4944 guchar *ucs = (guchar *)ucs_src;
4945
4946 g_return_if_fail(ucs_src != NULL);
4947 g_return_if_fail(len > 0);
4948
4949 for(i=0;i<len;i+=2){
4950 switch(*(ucs+i)){
4951 case 0x00:
4952 switch(*(ucs+i+1)){
4953 case 0xa2: // ¢
4954 *(ucs+i) = 0xff;
4955 *(ucs+i+1) = 0xe0;
4956 break;
4957 case 0xa3: // £
4958 *(ucs+i) = 0xff;
4959 *(ucs+i+1) = 0xe1;
4960 break;
4961 case 0xac: // ¬
4962 *(ucs+i) = 0xff;
4963 *(ucs+i+1) = 0xe2;
4964 break;
4965 }
4966 break;
4967 case 0x20: // ‖
4968 if(*(ucs+i+1) == 0x16){
4969 *(ucs+i) = 0x22;
4970 *(ucs+i+1) = 0x25;
4971 }
4972 break;
4973 case 0x22: // −
4974 if(*(ucs+i+1) == 0x12){
4975 *(ucs+i) = 0xff;
4976 *(ucs+i+1) = 0x0d;
4977 }
4978 break;
4979 case 0x30: // 〜
4980 if(*(ucs+i+1) == 0x1c){
4981 *(ucs+i) = 0xff;
4982 *(ucs+i+1) = 0x5e;
4983 }
4984 break;
4985 }
4986 }
4987
4988 }
4989 #endif
4990
4991 #ifdef _WIN32
4992 void sanitize_ucs(gchar *ucs, gsize len)
4993 {
4994 /* no operation */
4995 }
4996 #else
4997 void sanitize_ucs(gchar *ucs_src, gsize len)
4998 {
4999 gint i;
5000 guchar *ucs = (guchar *)ucs_src;
5001
5002 g_return_if_fail(ucs_src != NULL);
5003 g_return_if_fail(len > 0);
5004
5005 for(i=0;i<len;i+=2){
5006 switch(*(ucs+i)){
5007 case 0x22:
5008 switch(*(ucs+i+1)){
5009 case 0x25: // ‖
5010 *(ucs+i) = 0x20;
5011 *(ucs+i+1) = 0x16;
5012 break;
5013 }
5014 break;
5015 case 0xff:
5016 switch(*(ucs+i+1)){
5017 case 0x0d: // −
5018 *(ucs+i) = 0x22;
5019 *(ucs+i+1) = 0x12;
5020 break;
5021 case 0x5e: // 〜
5022 *(ucs+i) = 0x30;
5023 *(ucs+i+1) = 0x1c;
5024 break;
5025 case 0xe0: // ¢
5026 *(ucs+i) = 0x00;
5027 *(ucs+i+1) = 0xa2;
5028 break;
5029 case 0xe1: // £
5030 *(ucs+i) = 0x00;
5031 *(ucs+i+1) = 0xa3;
5032 break;
5033 case 0xe2: // ¬
5034 *(ucs+i) = 0x00;
5035 *(ucs+i+1) = 0xac;
5036 break;
5037 }
5038 break;
5039 }
5040 }
5041 }
5042 #endif
5043
5044 #ifdef _WIN32
5045 gchar *sanitize_utf(const gchar *msg, gsize len, gsize *newlen)
5046 {
5047 g_return_val_if_fail(msg != NULL, NULL);
5048 if(len == -1)
5049 len = strlen(msg);
5050 g_return_val_if_fail(len > 0, NULL);
5051
5052 if(newlen)
5053 *newlen = len;
5054
5055 return g_strndup(msg, len);
5056 }
5057 #else
5058 gchar *sanitize_utf(const gchar *msg, gsize len, gsize *newlen)
5059 {
5060 gint i;
5061 size_t bytes;
5062 guchar *utf;
5063
5064 g_return_val_if_fail(msg != NULL, NULL);
5065 if(len == -1)
5066 len = strlen(msg);
5067 g_return_val_if_fail(len > 0, NULL);
5068
5069 utf = (guchar *)g_strndup(msg, len);
5070
5071 bytes = len;
5072
5073 for(i=0;i<len;i++){
5074 switch(*(utf+i)){
5075 case 0xe2:
5076 if(*(utf+i+1) == 0x88) {
5077 if(*(utf+i+2) == 0xa5) { // ‖
5078 *(utf+i) = 0xe2;
5079 *(utf+i+1) = 0x80;
5080 *(utf+i+2) = 0x96;
5081 }
5082 }
5083 break;
5084 case 0xef:
5085 switch(*(utf+i+1)){
5086 case 0xbc:
5087 if(*(utf+i+2) == 0x8d) { // −
5088 *(utf+i) = 0xe2;
5089 *(utf+i+1) = 0x88;
5090 *(utf+i+2) = 0x92;
5091 }
5092 break;
5093 case 0xbd:
5094 if(*(utf+i+2) == 0x9e) { // 〜
5095 *(utf+i) = 0xe3;
5096 *(utf+i+1) = 0x80;
5097 *(utf+i+2) = 0x9c;
5098 }
5099 break;
5100 case 0xbf:
5101 switch(*(utf+i+2)){
5102 case 0xa0: // ¢
5103 *(utf+i) = 0xc2;
5104 *(utf+i+1) = 0xa2;
5105 memmove(utf+i+2, utf+i+3,
5106 len-i-3); //shorten by 1byte
5107 bytes--;
5108 break;
5109 case 0xa1: // £
5110 *(utf+i) = 0xc2;
5111 *(utf+i+1) = 0xa3;
5112 memmove(utf+i+2, utf+i+3,
5113 len-i-3); //shorten by 1byte
5114 bytes--;
5115 break;
5116 case 0xa2: // ¬
5117 *(utf+i) = 0xc2;
5118 *(utf+i+1) = 0xac;
5119 memmove(utf+i+2, utf+i+3,
5120 len-i-3); //shorten by 1byte
5121 bytes--;
5122 break;
5123 }
5124 break;
5125 }
5126 break;
5127 }
5128 }
5129 *(utf+bytes)= 0x00; //terminate
5130 if(newlen)
5131 *newlen = bytes;
5132 return (gchar *)utf;
5133 }
5134 #endif
5135
5136 #ifdef _WIN32
5137 gchar *botch_utf(const gchar *msg, gsize len, gsize *newlen)
5138 {
5139 g_return_val_if_fail(msg != NULL, NULL);
5140 if(len == -1)
5141 len = strlen(msg);
5142 g_return_val_if_fail(len > 0, NULL);
5143
5144 if(newlen)
5145 *newlen = len;
5146
5147 return g_strndup(msg, len);
5148 }
5149 #else
5150 gchar *botch_utf(const gchar *msg, gsize len, gsize *newlen)
5151 {
5152 int i,bytes;
5153 unsigned char *utf;
5154
5155 g_return_val_if_fail(msg != NULL, NULL);
5156 if(len == -1)
5157 len = strlen(msg);
5158 g_return_val_if_fail(len > 0, NULL);
5159
5160 bytes = len;
5161
5162 utf = g_malloc0(bytes*3/2+1); /* new length might be 3/2 in the worst case */
5163 memcpy(utf, msg, bytes);
5164
5165 for(i=0;i<bytes;i++){
5166 switch(*(utf+i)){
5167 case 0xc2:
5168 switch(*(utf+i+1)){
5169 case 0xa2: // ¢
5170 *(utf+i) = 0xef;
5171 *(utf+i+1) = 0xbf;
5172 memmove(utf+i+3, utf+i+2, bytes-i-2);
5173 *(utf+i+2) = 0xa0;
5174 bytes++;
5175 break;
5176 case 0xa3: // £
5177 *(utf+i) = 0xef;
5178 *(utf+i+1) = 0xbf;
5179 memmove(utf+i+3, utf+i+2, bytes-i-2);
5180 *(utf+i+2) = 0xa1;
5181 bytes++;
5182 break;
5183 case 0xac: // ¬
5184 *(utf+i) = 0xef;
5185 *(utf+i+1) = 0xbf;
5186 memmove(utf+i+3, utf+i+2, bytes-i-2);
5187 *(utf+i+2) = 0xa2;
5188 bytes++;
5189 break;
5190 }
5191 break;
5192 case 0xe2:
5193 switch(*(utf+i+1)){
5194 case 0x80: // ‖
5195 if(*(utf+i+2) == 0x96){
5196 *(utf+i) = 0xe2;
5197 *(utf+i+1) = 0x88;
5198 *(utf+i+2) = 0xa5;
5199 }
5200 break;
5201 case 0x88: // −
5202 if(*(utf+i+1) == 0x92){
5203 *(utf+i) = 0xef;
5204 *(utf+i+1) = 0xbc;
5205 *(utf+i+2) = 0x8d;
5206 }
5207 break;
5208 }
5209 break;
5210 case 0xe3: // 〜
5211 if(*(utf+i+1) == 0x80){
5212 if(*(utf+i+2) == 0x9c){
5213 *(utf+i) = 0xef;
5214 *(utf+i+1) = 0xbd;
5215 *(utf+i+2) = 0x9e;
5216 }
5217 }
5218 break;
5219 } //switch
5220 }
5221 *(utf+bytes) = 0x00; //terminate
5222 if(newlen)
5223 *newlen = bytes;
5224 return (gchar *)utf;
5225 }
5226 #endif