| c6d25d8d |
1 | /* |
| 2 | * xenc.c - translate our internal character set codes to and from |
| 3 | * X11 character encoding names. |
| 4 | * |
| 5 | */ |
| 6 | |
| 7 | #include <ctype.h> |
| 8 | #include "charset.h" |
| 9 | #include "internal.h" |
| 10 | |
| 11 | static const struct { |
| 12 | const char *name; |
| 13 | int charset; |
| 14 | } xencs[] = { |
| 15 | /* |
| 16 | * Officially registered encoding names. This list is derived |
| 17 | * from the font encodings section of |
| 18 | * |
| 19 | * http://ftp.x.org/pub/DOCS/registry |
| 20 | * |
| 21 | * Where multiple encoding names map to the same encoding id |
| 22 | * (such as iso8859-15 and fcd8859-15), the first is considered |
| 23 | * canonical and will be returned when translating the id to a |
| 24 | * string. |
| 25 | */ |
| 3f2ff6ae |
26 | { "iso646.1991-irv", CS_ASCII }, |
| c6d25d8d |
27 | { "iso8859-1", CS_ISO8859_1 }, |
| 28 | { "iso8859-2", CS_ISO8859_2 }, |
| 29 | { "iso8859-3", CS_ISO8859_3 }, |
| 30 | { "iso8859-4", CS_ISO8859_4 }, |
| 31 | { "iso8859-5", CS_ISO8859_5 }, |
| 32 | { "iso8859-6", CS_ISO8859_6 }, |
| 33 | { "iso8859-7", CS_ISO8859_7 }, |
| 34 | { "iso8859-8", CS_ISO8859_8 }, |
| 35 | { "iso8859-9", CS_ISO8859_9 }, |
| 36 | { "iso8859-10", CS_ISO8859_10 }, |
| 37 | { "iso8859-13", CS_ISO8859_13 }, |
| 38 | { "iso8859-14", CS_ISO8859_14 }, |
| 39 | { "iso8859-15", CS_ISO8859_15 }, |
| 40 | { "fcd8859-15", CS_ISO8859_15 }, |
| 41 | { "hp-roman8", CS_HP_ROMAN8 }, |
| 42 | { "koi8-r", CS_KOI8_R }, |
| 3c80ed0c |
43 | { "jisx0201.1976-0", CS_JISX0201 }, |
| c6d25d8d |
44 | /* |
| 45 | * Unofficial encoding names found in the wild. |
| 46 | */ |
| 47 | { "iso8859-16", CS_ISO8859_16 }, |
| 48 | { "koi8-u", CS_KOI8_U }, |
| 49 | { "ibm-cp437", CS_CP437 }, |
| 50 | { "ibm-cp850", CS_CP850 }, |
| 51 | { "microsoft-cp1250", CS_CP1250 }, |
| 52 | { "microsoft-cp1251", CS_CP1251 }, |
| 53 | { "microsoft-cp1252", CS_CP1252 }, |
| 54 | { "microsoft-cp1253", CS_CP1253 }, |
| 55 | { "microsoft-cp1254", CS_CP1254 }, |
| 56 | { "microsoft-cp1255", CS_CP1255 }, |
| 57 | { "microsoft-cp1256", CS_CP1256 }, |
| 58 | { "microsoft-cp1257", CS_CP1257 }, |
| 59 | { "microsoft-cp1258", CS_CP1258 }, |
| 60 | { "mac-roman", CS_MAC_ROMAN }, |
| 61 | { "viscii1.1-1", CS_VISCII }, |
| 62 | { "viscii1-1", CS_VISCII }, |
| 63 | }; |
| 64 | |
| 65 | const char *charset_to_xenc(int charset) |
| 66 | { |
| 67 | int i; |
| 68 | |
| 69 | for (i = 0; i < (int)lenof(xencs); i++) |
| 70 | if (charset == xencs[i].charset) |
| 71 | return xencs[i].name; |
| 72 | |
| 73 | return NULL; /* not found */ |
| 74 | } |
| 75 | |
| 76 | int charset_from_xenc(const char *name) |
| 77 | { |
| 78 | int i; |
| 79 | |
| 80 | for (i = 0; i < (int)lenof(xencs); i++) { |
| 81 | const char *p, *q; |
| 82 | p = name; |
| 83 | q = xencs[i].name; |
| 84 | while (*p || *q) { |
| 85 | if (tolower(*p) != tolower(*q)) |
| 86 | break; |
| 87 | p++; q++; |
| 88 | } |
| 89 | if (!*p && !*q) |
| 90 | return xencs[i].charset; |
| 91 | } |
| 92 | |
| 93 | return CS_NONE; /* not found */ |
| 94 | } |
~mdw / sgt / charset / blame