| 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 | * charset_from_localenc will attempt all other text translations |
| 10 | * as well as this table, to maximise the number of different ways |
| 11 | * you can select a supported charset. |
| 12 | */ |
| 13 | |
| 14 | #include <ctype.h> |
| 15 | #include "charset.h" |
| 16 | #include "internal.h" |
| 17 | |
| 18 | static const struct { |
| 19 | const char *name; |
| 20 | int charset; |
| 21 | int return_in_enum; /* enumeration misses some charsets */ |
| 22 | } localencs[] = { |
| 23 | { "<UNKNOWN>", CS_NONE, 0 }, |
| 24 | { "UTF-8", CS_UTF8, 1 }, |
| 25 | { "ISO-8859-1", CS_ISO8859_1, 1 }, |
| 26 | { "ISO-8859-1 with X11 line drawing", CS_ISO8859_1_X11, 0 }, |
| 27 | { "ISO-8859-2", CS_ISO8859_2, 1 }, |
| 28 | { "ISO-8859-3", CS_ISO8859_3, 1 }, |
| 29 | { "ISO-8859-4", CS_ISO8859_4, 1 }, |
| 30 | { "ISO-8859-5", CS_ISO8859_5, 1 }, |
| 31 | { "ISO-8859-6", CS_ISO8859_6, 1 }, |
| 32 | { "ISO-8859-7", CS_ISO8859_7, 1 }, |
| 33 | { "ISO-8859-8", CS_ISO8859_8, 1 }, |
| 34 | { "ISO-8859-9", CS_ISO8859_9, 1 }, |
| 35 | { "ISO-8859-10", CS_ISO8859_10, 1 }, |
| 36 | { "ISO-8859-11", CS_ISO8859_11, 1 }, |
| 37 | { "ISO-8859-13", CS_ISO8859_13, 1 }, |
| 38 | { "ISO-8859-14", CS_ISO8859_14, 1 }, |
| 39 | { "ISO-8859-15", CS_ISO8859_15, 1 }, |
| 40 | { "ISO-8859-16", CS_ISO8859_16, 1 }, |
| 41 | { "CP437", CS_CP437, 1 }, |
| 42 | { "CP850", CS_CP850, 1 }, |
| 43 | { "CP852", CS_CP852, 1 }, |
| 44 | { "CP866", CS_CP866, 1 }, |
| 45 | { "CP1250", CS_CP1250, 1 }, |
| 46 | { "CP1251", CS_CP1251, 1 }, |
| 47 | { "CP1252", CS_CP1252, 1 }, |
| 48 | { "CP1253", CS_CP1253, 1 }, |
| 49 | { "CP1254", CS_CP1254, 1 }, |
| 50 | { "CP1255", CS_CP1255, 1 }, |
| 51 | { "CP1256", CS_CP1256, 1 }, |
| 52 | { "CP1257", CS_CP1257, 1 }, |
| 53 | { "CP1258", CS_CP1258, 1 }, |
| 54 | { "KOI8-R", CS_KOI8_R, 1 }, |
| 55 | { "KOI8-U", CS_KOI8_U, 1 }, |
| 56 | { "Mac Roman", CS_MAC_ROMAN, 1 }, |
| 57 | { "Mac Turkish", CS_MAC_TURKISH, 1 }, |
| 58 | { "Mac Croatian", CS_MAC_CROATIAN, 1 }, |
| 59 | { "Mac Iceland", CS_MAC_ICELAND, 1 }, |
| 60 | { "Mac Romanian", CS_MAC_ROMANIAN, 1 }, |
| 61 | { "Mac Greek", CS_MAC_GREEK, 1 }, |
| 62 | { "Mac Cyrillic", CS_MAC_CYRILLIC, 1 }, |
| 63 | { "Mac Thai", CS_MAC_THAI, 1 }, |
| 64 | { "Mac Centeuro", CS_MAC_CENTEURO, 1 }, |
| 65 | { "Mac Symbol", CS_MAC_SYMBOL, 1 }, |
| 66 | { "Mac Dingbats", CS_MAC_DINGBATS, 1 }, |
| 67 | { "Mac Roman (old)", CS_MAC_ROMAN_OLD, 0 }, |
| 68 | { "Mac Croatian (old)", CS_MAC_CROATIAN_OLD, 0 }, |
| 69 | { "Mac Iceland (old)", CS_MAC_ICELAND_OLD, 0 }, |
| 70 | { "Mac Romanian (old)", CS_MAC_ROMANIAN_OLD, 0 }, |
| 71 | { "Mac Greek (old)", CS_MAC_GREEK_OLD, 0 }, |
| 72 | { "Mac Cyrillic (old)", CS_MAC_CYRILLIC_OLD, 0 }, |
| 73 | { "Mac Ukraine", CS_MAC_UKRAINE, 1 }, |
| 74 | { "Mac VT100", CS_MAC_VT100, 1 }, |
| 75 | { "Mac VT100 (old)", CS_MAC_VT100_OLD, 0 }, |
| 76 | { "VISCII", CS_VISCII, 1 }, |
| 77 | { "HP ROMAN8", CS_HP_ROMAN8, 1 }, |
| 78 | { "DEC MCS", CS_DEC_MCS, 1 }, |
| 79 | }; |
| 80 | |
| 81 | const char *charset_to_localenc(int charset) |
| 82 | { |
| 83 | int i; |
| 84 | |
| 85 | for (i = 0; i < (int)lenof(localencs); i++) |
| 86 | if (charset == localencs[i].charset) |
| 87 | return localencs[i].name; |
| 88 | |
| 89 | return NULL; /* not found */ |
| 90 | } |
| 91 | |
| 92 | int charset_from_localenc(const char *name) |
| 93 | { |
| 94 | int i; |
| 95 | |
| 96 | if ( (i = charset_from_mimeenc(name)) != CS_NONE) |
| 97 | return i; |
| 98 | if ( (i = charset_from_xenc(name)) != CS_NONE) |
| 99 | return i; |
| 100 | |
| 101 | for (i = 0; i < (int)lenof(localencs); i++) { |
| 102 | const char *p, *q; |
| 103 | p = name; |
| 104 | q = localencs[i].name; |
| 105 | while (*p || *q) { |
| 106 | if (tolower((unsigned char)*p) != tolower((unsigned char)*q)) |
| 107 | break; |
| 108 | p++; q++; |
| 109 | } |
| 110 | if (!*p && !*q) |
| 111 | return localencs[i].charset; |
| 112 | } |
| 113 | |
| 114 | return CS_NONE; /* not found */ |
| 115 | } |
| 116 | |
| 117 | int charset_localenc_nth(int n) |
| 118 | { |
| 119 | int i; |
| 120 | |
| 121 | for (i = 0; i < (int)lenof(localencs); i++) |
| 122 | if (localencs[i].return_in_enum && !n--) |
| 123 | return localencs[i].charset; |
| 124 | |
| 125 | return CS_NONE; /* end of list */ |
| 126 | } |