Added koi8-r, cp866, and cp1251 support for htmlentities

diff --git a/ext/standard/html.c b/ext/standard/html.c
index fe3b9ad9408b8dd8379c79bf90cd061100425233..aa1b3b91ca63cc76fba41f4590c23d1935ba08ca 100644 (file)
--- a/ext/standard/html.c
+++ b/ext/standard/html.c
@@ -46,7 +46,9 @@ ZEND_EXTERN_MODULE_GLOBALS(mbstring)
 
 enum entity_charset { cs_terminator, cs_8859_1, cs_cp1252,
                                          cs_8859_15, cs_utf_8, cs_big5, cs_gb2312, 
-                                         cs_big5hkscs, cs_sjis, cs_eucjp};
+                                         cs_big5hkscs, cs_sjis, cs_eucjp, cs_koi8r,
+                                         cs_cp1251, cs_8859_5, cs_cp866
+                                       };
 typedef const char *entity_table_t;
 
 /* codepage 1252 is a Windows extension to iso-8859-1. */
@@ -255,6 +257,73 @@ static entity_table_t ent_uni_9824_9830[] = {
        "spades", NULL, NULL, "clubs", NULL, "hearts", "diams"
 };
 
+static entity_table_t ent_koi8r[] = {
+       "#1105", /* "jo "*/
+       NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, 
+       NULL, NULL, NULL, NULL, NULL, "#1025", /* "JO" */
+       NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, 
+       "#1102", "#1072", "#1073", "#1094", "#1076", "#1077", "#1092", 
+       "#1075", "#1093", "#1080", "#1081", "#1082", "#1083", "#1084", 
+       "#1085", "#1086", "#1087", "#1103", "#1088", "#1089", "#1090", 
+       "#1091", "#1078", "#1074", "#1100", "#1099", "#1079", "#1096", 
+       "#1101", "#1097", "#1095", "#1098", "#1070", "#1040", "#1041", 
+       "#1062", "#1044", "#1045", "#1060", "#1043", "#1061", "#1048", 
+       "#1049", "#1050", "#1051", "#1052", "#1053", "#1054", "#1055", 
+       "#1071", "#1056", "#1057", "#1058", "#1059", "#1046", "#1042",
+       "#1068", "#1067", "#1047", "#1064", "#1069", "#1065", "#1063", 
+       "#1066"
+};
+
+static entity_table_t ent_cp_1251[] = {
+       "#1026", "#1027", "#8218", "#1107", "#8222", "hellip", "dagger",
+       "Dagger", "euro", "permil", "#1033", "#8249", "#1034", "#1036",
+       "#1035", "#1039", "#1106", "#8216", "#8217", "#8219", "#8220",
+       "bull", "ndash", "mdash", NULL, "trade", "#1113", "#8250",
+       "#1114", "#1116", "#1115", "#1119", "nbsp", "#1038", "#1118",
+       "#1032", "curren", "#1168", "brvbar", "sect", "#1025", "copy",
+       "#1028", "laquo", "not", "shy", "reg", "#1031", "deg", "plusmn",
+       "#1030", "#1110", "#1169", "micro", "para", "middot", "#1105",
+       "#8470", "#1108", "raquo", "#1112", "#1029", "#1109", "#1111",
+       "#1040", "#1041", "#1042", "#1043", "#1044", "#1045", "#1046",
+       "#1047", "#1048", "#1049", "#1050", "#1051", "#1052", "#1053",
+       "#1054", "#1055", "#1056", "#1057", "#1058", "#1059", "#1060",
+       "#1061", "#1062", "#1063", "#1064", "#1065", "#1066", "#1067",
+       "#1068", "#1069", "#1070", "#1071", "#1072", "#1073", "#1074",
+       "#1075", "#1076", "#1077", "#1078", "#1079", "#1080", "#1081",
+       "#1082", "#1083", "#1084", "#1085", "#1086", "#1087", "#1088",
+       "#1089", "#1090", "#1091", "#1092", "#1093", "#1094", "#1095",
+       "#1096", "#1097", "#1098", "#1099", "#1100", "#1101", "#1102",
+       "#1103"
+};
+
+static entity_table_t ent_iso_8859_5[] = {
+       "#1056", "#1057", "#1058", "#1059", "#1060", "#1061", "#1062",
+       "#1063", "#1064", "#1065", "#1066", "#1067", "#1068", "#1069",
+       "#1070", "#1071", "#1072", "#1073", "#1074", "#1075", "#1076",
+       "#1077", "#1078", "#1079", "#1080", "#1081", "#1082", "#1083",
+       "#1084", "#1085", "#1086", "#1087", "#1088", "#1089", "#1090",
+       "#1091", "#1092", "#1093", "#1094", "#1095", "#1096", "#1097",
+       "#1098", "#1099", "#1100", "#1101", "#1102", "#1103", "#1104",
+       "#1105", "#1106", "#1107", "#1108", "#1109", "#1110", "#1111",
+       "#1112", "#1113", "#1114", "#1115", "#1116", "#1117", "#1118",
+       "#1119"
+};
+
+static entity_table_t ent_cp_866[] = {
+
+       "#9492", "#9524", "#9516", "#9500", "#9472", "#9532", "#9566", 
+       "#9567", "#9562", "#9556", "#9577", "#9574", "#9568", "#9552", 
+       "#9580", "#9575", "#9576", "#9572", "#9573", "#9561", "#9560", 
+       "#9554", "#9555", "#9579", "#9578", "#9496", "#9484", "#9608", 
+       "#9604", "#9612", "#9616", "#9600", "#1088", "#1089", "#1090", 
+       "#1091", "#1092", "#1093", "#1094", "#1095", "#1096", "#1097", 
+       "#1098", "#1099", "#1100", "#1101", "#1102", "#1103", "#1025", 
+       "#1105", "#1028", "#1108", "#1031", "#1111", "#1038", "#1118", 
+       "#176", "#8729", "#183", "#8730", "#8470", "#164",  "#9632", 
+       "#160"
+};
+
+
 struct html_entity_map {
        enum entity_charset charset;    /* charset identifier */
        unsigned short basechar;                        /* char code at start of table */
@@ -281,6 +350,10 @@ static const struct html_entity_map entity_map[] = {
        { cs_big5hkscs,         0xa0, 0xff, ent_iso_8859_1 },
        { cs_sjis,                      0xa0, 0xff, ent_iso_8859_1 },
        { cs_eucjp,                     0xa0, 0xff, ent_iso_8859_1 },
+       { cs_koi8r,                 0xa3, 0xff, ent_koi8r },
+       { cs_cp1251,            0x80, 0xff, ent_cp_1251 },
+       { cs_8859_5,            0xc0, 0xff, ent_iso_8859_5 },
+       { cs_cp866,                 0xc0, 0xff, ent_cp_866 },
        { cs_terminator }
 };
 
@@ -306,6 +379,17 @@ static const struct {
        { "932",            cs_sjis },
        { "EUCJP",              cs_eucjp },
        { "EUC-JP",             cs_eucjp },
+       { "KOI8-R",         cs_koi8r },
+       { "koi8-ru",        cs_koi8r },
+       { "koi8r",          cs_koi8r },
+       { "cp1251",         cs_cp1251 },
+       { "Windows-1251",   cs_cp1251 },
+       { "win-1251",       cs_cp1251 },
+       { "iso8859-5",      cs_8859_5 },
+       { "iso-8859-5",     cs_8859_5 },
+       { "cp866",          cs_cp866 },
+       { "866",            cs_cp866 },    
+       { "ibm866",         cs_cp866 },
        { NULL }
 };
 
@@ -580,6 +664,18 @@ static enum entity_charset determine_charset(char *charset_hint TSRMLS_DC)
                case mbfl_no_encoding_hz:
                case mbfl_no_encoding_cp936:
                        return cs_gb2312;
+
+               case mbfl_no_encoding_koi8r:
+                       return cs_koi8r;
+
+               case mbfl_no_encoding_cp866:
+                       return cs_cp866;
+
+               case mbfl_no_encoding_cp1251:
+                       return cs_cp1251;
+
+               case mbfl_no_encoding_8859_5:
+                       return cs_8859_5;
        }
 #else
        {