| 1 | /* |
| 2 | * local.c - translate our internal character set codes to and from |
| 3 | * our own set of plausibly legible character-set names. Also |
| 4 | * provides a canonical name for each encoding (useful for software |
| 5 | * announcing what character set it will be using), and a set of |
| 6 | * enumeration functions which return a list of supported |
| 7 | * encodings one by one. |
| 8 | * |
| 9 | * Also in this table are other ways people might plausibly refer |
| 10 | * to a charset (for example, Win1252 as well as CP1252). Where |
| 11 | * more than one string is given for a particular character set, |
| 12 | * the first one is the canonical one returned by |
| 13 | * charset_to_localenc. |
| 14 | * |
| 15 | * charset_from_localenc will attempt all other text translations |
| 16 | * as well as this table, to maximise the number of different ways |
| 17 | * you can select a supported charset. |
| 18 | */ |
| 19 | |
| 20 | #include <ctype.h> |
| 21 | #include "charset.h" |
| 22 | #include "internal.h" |
| 23 | |
| 24 | static const struct { |
| 25 | const char *name; |
| 26 | int charset; |
| 27 | int return_in_enum; /* enumeration misses some charsets */ |
| 28 | } localencs[] = { |
| 29 | { "<UNKNOWN>", CS_NONE, 0 }, |
| 30 | { "ASCII", CS_ASCII, 1 }, |
| 31 | { "BS 4730", CS_BS4730, 1 }, |
| 32 | { "ISO-8859-1", CS_ISO8859_1, 1 }, |
| 33 | { "ISO-8859-1 with X11 line drawing", CS_ISO8859_1_X11, 0 }, |
| 34 | { "ISO-8859-2", CS_ISO8859_2, 1 }, |
| 35 | { "ISO-8859-3", CS_ISO8859_3, 1 }, |
| 36 | { "ISO-8859-4", CS_ISO8859_4, 1 }, |
| 37 | { "ISO-8859-5", CS_ISO8859_5, 1 }, |
| 38 | { "ISO-8859-6", CS_ISO8859_6, 1 }, |
| 39 | { "ISO-8859-7", CS_ISO8859_7, 1 }, |
| 40 | { "ISO-8859-8", CS_ISO8859_8, 1 }, |
| 41 | { "ISO-8859-9", CS_ISO8859_9, 1 }, |
| 42 | { "ISO-8859-10", CS_ISO8859_10, 1 }, |
| 43 | { "ISO-8859-11", CS_ISO8859_11, 1 }, |
| 44 | { "ISO-8859-13", CS_ISO8859_13, 1 }, |
| 45 | { "ISO-8859-14", CS_ISO8859_14, 1 }, |
| 46 | { "ISO-8859-15", CS_ISO8859_15, 1 }, |
| 47 | { "ISO-8859-16", CS_ISO8859_16, 1 }, |
| 48 | { "CP437", CS_CP437, 1 }, |
| 49 | { "CP850", CS_CP850, 1 }, |
| 50 | { "CP852", CS_CP852, 1 }, |
| 51 | { "CP866", CS_CP866, 1 }, |
| 52 | { "CP874", CS_CP874, 1 }, |
| 53 | { "Win874", CS_CP874, 0 }, |
| 54 | { "Win-874", CS_CP874, 0 }, |
| 55 | { "CP1250", CS_CP1250, 1 }, |
| 56 | { "Win1250", CS_CP1250, 0 }, |
| 57 | { "CP1251", CS_CP1251, 1 }, |
| 58 | { "Win1251", CS_CP1251, 0 }, |
| 59 | { "CP1252", CS_CP1252, 1 }, |
| 60 | { "Win1252", CS_CP1252, 0 }, |
| 61 | { "CP1253", CS_CP1253, 1 }, |
| 62 | { "Win1253", CS_CP1253, 0 }, |
| 63 | { "CP1254", CS_CP1254, 1 }, |
| 64 | { "Win1254", CS_CP1254, 0 }, |
| 65 | { "CP1255", CS_CP1255, 1 }, |
| 66 | { "Win1255", CS_CP1255, 0 }, |
| 67 | { "CP1256", CS_CP1256, 1 }, |
| 68 | { "Win1256", CS_CP1256, 0 }, |
| 69 | { "CP1257", CS_CP1257, 1 }, |
| 70 | { "Win1257", CS_CP1257, 0 }, |
| 71 | { "CP1258", CS_CP1258, 1 }, |
| 72 | { "Win1258", CS_CP1258, 0 }, |
| 73 | { "KOI8-R", CS_KOI8_R, 1 }, |
| 74 | { "KOI8-U", CS_KOI8_U, 1 }, |
| 75 | { "KOI8-RU", CS_KOI8_RU, 1 }, |
| 76 | { "JIS X 0201", CS_JISX0201, 1 }, |
| 77 | { "JIS-X-0201", CS_JISX0201, 0 }, |
| 78 | { "JIS_X_0201", CS_JISX0201, 0 }, |
| 79 | { "JISX0201", CS_JISX0201, 0 }, |
| 80 | { "Mac Roman", CS_MAC_ROMAN, 1 }, |
| 81 | { "Mac Turkish", CS_MAC_TURKISH, 1 }, |
| 82 | { "Mac Croatian", CS_MAC_CROATIAN, 1 }, |
| 83 | { "Mac Iceland", CS_MAC_ICELAND, 1 }, |
| 84 | { "Mac Romanian", CS_MAC_ROMANIAN, 1 }, |
| 85 | { "Mac Greek", CS_MAC_GREEK, 1 }, |
| 86 | { "Mac Cyrillic", CS_MAC_CYRILLIC, 1 }, |
| 87 | { "Mac Thai", CS_MAC_THAI, 1 }, |
| 88 | { "Mac Centeuro", CS_MAC_CENTEURO, 1 }, |
| 89 | { "Mac Symbol", CS_MAC_SYMBOL, 1 }, |
| 90 | { "Mac Dingbats", CS_MAC_DINGBATS, 1 }, |
| 91 | { "Mac Roman (old)", CS_MAC_ROMAN_OLD, 0 }, |
| 92 | { "Mac Croatian (old)", CS_MAC_CROATIAN_OLD, 0 }, |
| 93 | { "Mac Iceland (old)", CS_MAC_ICELAND_OLD, 0 }, |
| 94 | { "Mac Romanian (old)", CS_MAC_ROMANIAN_OLD, 0 }, |
| 95 | { "Mac Greek (old)", CS_MAC_GREEK_OLD, 0 }, |
| 96 | { "Mac Cyrillic (old)", CS_MAC_CYRILLIC_OLD, 0 }, |
| 97 | { "Mac Ukraine", CS_MAC_UKRAINE, 1 }, |
| 98 | { "Mac VT100", CS_MAC_VT100, 1 }, |
| 99 | { "Mac VT100 (old)", CS_MAC_VT100_OLD, 0 }, |
| 100 | { "VISCII", CS_VISCII, 1 }, |
| 101 | { "HP ROMAN8", CS_HP_ROMAN8, 1 }, |
| 102 | { "DEC MCS", CS_DEC_MCS, 1 }, |
| 103 | { "DEC graphics", CS_DEC_GRAPHICS, 1 }, |
| 104 | { "DEC-graphics", CS_DEC_GRAPHICS, 0 }, |
| 105 | { "DECgraphics", CS_DEC_GRAPHICS, 0 }, |
| 106 | { "UTF-8", CS_UTF8, 1 }, |
| 107 | { "UTF-7", CS_UTF7, 1 }, |
| 108 | { "UTF-7-conservative", CS_UTF7_CONSERVATIVE, 0 }, |
| 109 | { "EUC-CN", CS_EUC_CN, 1 }, |
| 110 | { "EUC-KR", CS_EUC_KR, 1 }, |
| 111 | { "EUC-JP", CS_EUC_JP, 1 }, |
| 112 | { "EUC-TW", CS_EUC_TW, 1 }, |
| 113 | { "ISO-2022-JP", CS_ISO2022_JP, 1 }, |
| 114 | { "ISO-2022-KR", CS_ISO2022_KR, 1 }, |
| 115 | { "Big5", CS_BIG5, 1 }, |
| 116 | { "Shift-JIS", CS_SHIFT_JIS, 1 }, |
| 117 | { "HZ", CS_HZ, 1 }, |
| 118 | { "UTF-16BE", CS_UTF16BE, 1 }, |
| 119 | { "UTF-16LE", CS_UTF16LE, 1 }, |
| 120 | { "UTF-16", CS_UTF16, 1 }, |
| 121 | { "CP949", CS_CP949, 1 }, |
| 122 | { "PDFDocEncoding", CS_PDF, 1 }, |
| 123 | { "StandardEncoding", CS_PSSTD, 1 }, |
| 124 | { "COMPOUND_TEXT", CS_CTEXT, 1 }, |
| 125 | { "COMPOUND-TEXT", CS_CTEXT, 0 }, |
| 126 | { "COMPOUND TEXT", CS_CTEXT, 0 }, |
| 127 | { "COMPOUNDTEXT", CS_CTEXT, 0 }, |
| 128 | { "CTEXT", CS_CTEXT, 0 }, |
| 129 | { "ISO-2022", CS_ISO2022, 1 }, |
| 130 | { "ISO2022", CS_ISO2022, 0 }, |
| 131 | }; |
| 132 | |
| 133 | const char *charset_to_localenc(int charset) |
| 134 | { |
| 135 | int i; |
| 136 | |
| 137 | for (i = 0; i < (int)lenof(localencs); i++) |
| 138 | if (charset == localencs[i].charset) |
| 139 | return localencs[i].name; |
| 140 | |
| 141 | return NULL; /* not found */ |
| 142 | } |
| 143 | |
| 144 | int charset_from_localenc(const char *name) |
| 145 | { |
| 146 | int i; |
| 147 | |
| 148 | if ( (i = charset_from_mimeenc(name)) != CS_NONE) |
| 149 | return i; |
| 150 | if ( (i = charset_from_xenc(name)) != CS_NONE) |
| 151 | return i; |
| 152 | if ( (i = charset_from_emacsenc(name)) != CS_NONE) |
| 153 | return i; |
| 154 | |
| 155 | for (i = 0; i < (int)lenof(localencs); i++) { |
| 156 | const char *p, *q; |
| 157 | p = name; |
| 158 | q = localencs[i].name; |
| 159 | while (*p || *q) { |
| 160 | if (tolower((unsigned char)*p) != tolower((unsigned char)*q)) |
| 161 | break; |
| 162 | p++; q++; |
| 163 | } |
| 164 | if (!*p && !*q) |
| 165 | return localencs[i].charset; |
| 166 | } |
| 167 | |
| 168 | return CS_NONE; /* not found */ |
| 169 | } |
| 170 | |
| 171 | int charset_localenc_nth(int n) |
| 172 | { |
| 173 | int i; |
| 174 | |
| 175 | for (i = 0; i < (int)lenof(localencs); i++) |
| 176 | if (localencs[i].return_in_enum && !n--) |
| 177 | return localencs[i].charset; |
| 178 | |
| 179 | return CS_NONE; /* end of list */ |
| 180 | } |