From 5eb556c8497ddd680c28e53e04c4badfe612004a Mon Sep 17 00:00:00 2001 From: Corinna Vinschen Date: Sat, 6 Feb 2010 18:28:33 +0000 Subject: * libc/ctype/ctype_cp.h (_CTYPE_GEORGIAN_PS_128_254): Define. (_CTYPE_GEORGIAN_PS_255): Define. (_CTYPE_PT154_128_254): Define. (_CTYPE_PT154_255): Define. (__ctype_cp): Add array members for above ctype definitions. * libc/locale/locale.c (loadlocale): Make TIS-620 charset name available for all targets. Add guards for setting the conversion function pointers. Add support for GEORGIAN-PS and PT154 charsets. Change documentation to reflect current behaviour more closely. * libc/locale/nl_langinfo.c (nl_langinfo): On Cygwin, translate "CP101" to "GEORGIAN-PS" and "CP102" to "PT154". * libc/stdlib/sb_charsets.c (__cp_conv): Add conversion arrays for GEORGIAN-PS and PT154. (__cp_index): Map invalid Windows codepage number 101 to GEORGIAN-PS conversion array, 102 to PT154 conversion array. --- newlib/libc/stdlib/sb_charsets.c | 50 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 48 insertions(+), 2 deletions(-) (limited to 'newlib/libc/stdlib') diff --git a/newlib/libc/stdlib/sb_charsets.c b/newlib/libc/stdlib/sb_charsets.c index 4ab1de69a..e668c4b83 100644 --- a/newlib/libc/stdlib/sb_charsets.c +++ b/newlib/libc/stdlib/sb_charsets.c @@ -203,7 +203,7 @@ wchar_t __iso_8859_conv[14][0x60] = { value (function __cp_index), the second index is the value of the incoming character - 0x80. Values < 0x80 don't have to be converted anyway. */ -wchar_t __cp_conv[24][0x80] = { +wchar_t __cp_conv[26][0x80] = { /* CP437 */ { 0xc7, 0xfc, 0xe9, 0xe2, 0xe4, 0xe0, 0xe5, 0xe7, 0xea, 0xeb, 0xe8, 0xef, 0xee, 0xec, 0xc4, 0xc5, @@ -611,7 +611,47 @@ wchar_t __cp_conv[24][0x80] = { 0x42e, 0x410, 0x411, 0x426, 0x414, 0x415, 0x424, 0x413, 0x425, 0x418, 0x419, 0x41a, 0x41b, 0x41c, 0x41d, 0x41e, 0x41f, 0x42f, 0x420, 0x421, 0x422, 0x423, 0x416, 0x412, - 0x42c, 0x42b, 0x417, 0x428, 0x42d, 0x429, 0x427, 0x42a } + 0x42c, 0x42b, 0x417, 0x428, 0x42d, 0x429, 0x427, 0x42a }, + /* The following are not valid Windows codepages, but they fit nicely here. + The CP numbers are only used internally and are guranteed not to clash + with valid Windows codepage identifier. */ + /* CP101 (GEORGIAN-PS) Georgian charset, used as the default charset in + the ka_GE locale (Georgian, Georgia). Apparently derived from Windows + CP1252. */ + { 0x80, 0x81, 0x201a, 0x192, 0x201e, 0x2026, 0x2020, 0x2021, + 0x2c6, 0x2030, 0x160, 0x2039, 0x152, 0x8d, 0x8e, 0x8f, + 0x90, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014, + 0x2dc, 0x2122, 0x161, 0x203a, 0x153, 0x9d, 0x9e, 0x178, + 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, + 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, + 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, + 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, + 0x10d0, 0x10d1, 0x10d2, 0x10d3, 0x10d4, 0x10d5, 0x10d6, 0x10f1, + 0x10d7, 0x10d8, 0x10d9, 0x10da, 0x10db, 0x10dc, 0x10f2, 0x10dd, + 0x10de, 0x10df, 0x10e0, 0x10e1, 0x10e2, 0x10f3, 0x10e3, 0x10e4, + 0x10e5, 0x10e6, 0x10e7, 0x10e8, 0x10e9, 0x10ea, 0x10eb, 0x10ec, + 0x10ed, 0x10ee, 0x10f4, 0x10ef, 0x10f0, 0x10f5, 0xe6, 0xe7, + 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, + 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, + 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff }, + /* CP102 (PT154) Cyrillic-Asian charset, used as the default charset in + the kk_KZ locale (Kazakh, Kazakhstan). */ + { 0x496, 0x492, 0x4ee, 0x493, 0x201e, 0x2026, 0x4b6, 0x4ae, + 0x4b2, 0x4af, 0x4a0, 0x4e2, 0x4a2, 0x49a, 0x4ba, 0x4b8, + 0x497, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014, + 0x4b3, 0x4b7, 0x4a1, 0x4e3, 0x4a3, 0x49b, 0x4bb, 0x4b9, + 0xa0, 0x40e, 0x45e, 0x408, 0x4e8, 0x498, 0x4b0, 0xa7, + 0x401, 0xa9, 0x4d8, 0xab, 0xac, 0x4ef, 0xae, 0x49c, + 0xb0, 0x4b1, 0x406, 0x456, 0x499, 0x4e9, 0xb6, 0xb7, + 0x451, 0x2116, 0x4d9, 0xbb, 0x458, 0x4aa, 0x4ab, 0x49d, + 0x410, 0x411, 0x412, 0x413, 0x414, 0x415, 0x416, 0x417, + 0x418, 0x419, 0x41a, 0x41b, 0x41c, 0x41d, 0x41e, 0x41f, + 0x420, 0x421, 0x422, 0x423, 0x424, 0x425, 0x426, 0x427, + 0x428, 0x429, 0x42a, 0x42b, 0x42c, 0x42d, 0x42e, 0x42f, + 0x430, 0x431, 0x432, 0x433, 0x434, 0x435, 0x436, 0x437, + 0x438, 0x439, 0x43a, 0x43b, 0x43c, 0x43d, 0x43e, 0x43f, + 0x440, 0x441, 0x442, 0x443, 0x444, 0x445, 0x446, 0x447, + 0x448, 0x449, 0x44a, 0x44b, 0x44c, 0x44d, 0x44e, 0x44f } }; #endif /* _MB_EXTENDED_CHARSETS_WINDOWS */ @@ -727,6 +767,12 @@ __cp_index (const char *charset_ext) case 21866: cp_idx = 23; break; + case 101: + cp_idx = 24; + break; + case 102: + cp_idx = 25; + break; default: cp_idx = -1; break; -- cgit v1.2.3