Thread: [KoCo-CVS] [Commit] cjkcodecs/src/maps map_big5.h map_cp950ext.h
Brought to you by:
perky
From: Hye-Shik C. <pe...@us...> - 2003-06-19 17:49:04
|
perky 03/06/19 10:49:01 Modified: src/maps map_big5.h map_cp950ext.h Log: Fix some big5 mappings to give more roundtrip compatibility. Revision Changes Path 1.3 +10 -13 cjkcodecs/src/maps/map_big5.h Index: map_big5.h =================================================================== RCS file: /cvsroot/koco/cjkcodecs/src/maps/map_big5.h,v retrieving revision 1.2 retrieving revision 1.3 diff -u -r1.2 -r1.3 --- map_big5.h 17 May 2003 20:58:58 -0000 1.2 +++ map_big5.h 19 Jun 2003 17:49:01 -0000 1.3 @@ -1,12 +1,12 @@ /* - * $Id: map_big5.h,v 1.2 2003/05/17 20:58:58 perky Exp $ + * $Id: map_big5.h,v 1.3 2003/06/19 17:49:01 perky Exp $ */ static const Py_UNICODE __big5_decmap[16702] = { 0x3000, 0xff0c, 0x3001, 0x3002, 0xff0e, 0x2022, 0xff1b, 0xff1a, 0xff1f, 0xff01, 0xfe30, 0x2026, 0x2025, 0xfe50, 0xff64, 0xfe52, 0x00b7, 0xfe54, 0xfe55, 0xfe56, 0xfe57, 0xff5c, 0x2013, 0xfe31, - 0x2014, 0xfe33, 0xfffd, 0xfe34, 0xfe4f, 0xff08, 0xff09, 0xfe35, + 0x2014, 0xfe33, 0x2574, 0xfe34, 0xfe4f, 0xff08, 0xff09, 0xfe35, 0xfe36, 0xff5b, 0xff5d, 0xfe37, 0xfe38, 0x3014, 0x3015, 0xfe39, 0xfe3a, 0x3010, 0x3011, 0xfe3b, 0xfe3c, 0x300a, 0x300b, 0xfe3d, 0xfe3e, 0x3008, 0x3009, 0xfe3f, 0xfe40, 0x300c, 0x300d, 0xfe41, @@ -19,14 +19,14 @@ 0x201d, 0x301d, 0x301e, 0x2035, 0x2032, 0xff03, 0xff06, 0xff0a, 0x203b, 0x00a7, 0x3003, 0x25cb, 0x25cf, 0x25b3, 0x25b2, 0x25ce, 0x2606, 0x2605, 0x25c7, 0x25c6, 0x25a1, 0x25a0, 0x25bd, 0x25bc, - 0x32a3, 0x2105, 0x203e, 0xfffd, 0xff3f, 0xfffd, 0xfe49, 0xfe4a, + 0x32a3, 0x2105, 0x203e, 0xffe3, 0xff3f, 0x02cd, 0xfe49, 0xfe4a, 0xfe4d, 0xfe4e, 0xfe4b, 0xfe4c, 0xfe5f, 0xfe60, 0xfe61, 0xff0b, 0xff0d, 0x00d7, 0x00f7, 0x00b1, 0x221a, 0xff1c, 0xff1e, 0xff1d, 0x2266, 0x2267, 0x2260, 0x221e, 0x2252, 0x2261, 0xfe62, 0xfe63, 0xfe64, 0xfe65, 0xfe66, 0x223c, 0x2229, 0x222a, 0x22a5, 0x2220, 0x221f, 0x22bf, 0x33d2, 0x33d1, 0x222b, 0x222e, 0x2235, 0x2234, 0x2640, 0x2642, 0x2641, 0x2609, 0x2191, 0x2193, 0x2190, 0x2192, - 0x2196, 0x2197, 0x2199, 0x2198, 0x2225, 0x2223, 0xfffd, 0xfffd, + 0x2196, 0x2197, 0x2199, 0x2198, 0x2225, 0x2223, 0xff0f, 0xff3c, 0xff0f, 0xff3c, 0xff04, 0x00a5, 0x3012, 0x00a2, 0x00a3, 0xff05, 0xff20, 0x2103, 0x2109, 0xfe69, 0xfe6a, 0xfe6b, 0x33d5, 0x339c, 0x339d, 0x339e, 0x33ce, 0x33a1, 0x338e, 0x338f, 0x33c4, 0x00b0, @@ -44,7 +44,7 @@ 0xff12, 0xff13, 0xff14, 0xff15, 0xff16, 0xff17, 0xff18, 0xff19, 0x2160, 0x2161, 0x2162, 0x2163, 0x2164, 0x2165, 0x2166, 0x2167, 0x2168, 0x2169, 0x3021, 0x3022, 0x3023, 0x3024, 0x3025, 0x3026, - 0x3027, 0x3028, 0x3029, 0xfffd, 0x5344, 0xfffd, 0xff21, 0xff22, + 0x3027, 0x3028, 0x3029, 0x5341, 0x5344, 0x5345, 0xff21, 0xff22, 0xff23, 0xff24, 0xff25, 0xff26, 0xff27, 0xff28, 0xff29, 0xff2a, 0xff2b, 0xff2c, 0xff2d, 0xff2e, 0xff2f, 0xff30, 0xff31, 0xff32, 0xff33, 0xff34, 0xff35, 0xff36, 0xff37, 0xff38, 0xff39, 0xff3a, @@ -2352,7 +2352,7 @@ /* 0xFF */ {0, 0, 0}, }; -static const DBCHAR __big5_encmap[21790] = { +static const DBCHAR __big5_encmap[21764] = { 0xa246, 0xa247, NOCHAR, 0xa244, NOCHAR, 0xa1b1, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa258, 0xa1d3, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa150, NOCHAR, NOCHAR, @@ -2364,7 +2364,7 @@ NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa1d2, 0xa3be, NOCHAR, - 0xa3bc, 0xa3bd, 0xa3bf, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + 0xa3bc, 0xa3bd, 0xa3bf, NOCHAR, 0xa1c5, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa3bb, 0xa344, 0xa345, 0xa346, 0xa347, 0xa348, 0xa349, 0xa34a, 0xa34b, 0xa34c, 0xa34d, 0xa34e, 0xa34f, 0xa350, 0xa351, 0xa352, @@ -2446,7 +2446,7 @@ NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa2a5, NOCHAR, NOCHAR, 0xa2a7, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa2a6, NOCHAR, NOCHAR, 0xa27e, - 0xa2a1, 0xa2a3, 0xa2a2, 0xa2ac, 0xa2ad, 0xa2ae, NOCHAR, NOCHAR, + 0xa2a1, 0xa2a3, 0xa2a2, 0xa2ac, 0xa2ad, 0xa2ae, 0xa15a, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa262, 0xa263, 0xa264, 0xa265, 0xa266, 0xa267, 0xa268, 0xa269, 0xa270, 0xa26f, 0xa26e, 0xa26d, 0xa26c, @@ -5073,10 +5073,7 @@ NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa2ce, + NOCHAR, NOCHAR, NOCHAR, 0xa1c3, }; static const struct unim_index big5_encmap[256] = { @@ -5335,6 +5332,6 @@ /* 0xFC */ {0, 0, 0}, /* 0xFD */ {0, 0, 0}, /* 0xFE */ {__big5_encmap+21477, 0x30, 0x6b}, -/* 0xFF */ {__big5_encmap+21537, 0x01, 0xfd}, +/* 0xFF */ {__big5_encmap+21537, 0x01, 0xe3}, }; 1.4 +41 -71 cjkcodecs/src/maps/map_cp950ext.h Index: map_cp950ext.h =================================================================== RCS file: /cvsroot/koco/cjkcodecs/src/maps/map_cp950ext.h,v retrieving revision 1.3 retrieving revision 1.4 diff -u -r1.3 -r1.4 --- map_cp950ext.h 28 May 2003 06:51:34 -0000 1.3 +++ map_cp950ext.h 19 Jun 2003 17:49:01 -0000 1.4 @@ -1,11 +1,10 @@ /* - * $Id: map_cp950ext.h,v 1.3 2003/05/28 06:51:34 perky Exp $ + * $Id: map_cp950ext.h,v 1.4 2003/06/19 17:49:01 perky Exp $ */ -static const Py_UNICODE __cp950ext_decmap[371] = { +static const Py_UNICODE __cp950ext_decmap[224] = { 0x2027, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, 0xfe51, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, 0x2574, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, @@ -18,38 +17,20 @@ UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, 0x00af, 0xffe3, UNIINV, - 0x02cd, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, 0xff5e, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, 0x2295, 0x2299, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, 0xff0f, 0xff3c, 0x2215, 0xfe68, UNIINV, 0xffe5, UNIINV, - 0xffe0, 0xffe1, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, + UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, 0x00af, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, + UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, 0xff5e, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, - UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, 0x5341, UNIINV, - 0x5345, 0x20ac, 0x7881, 0x92b9, 0x88cf, 0x58bb, 0x6052, 0x7ca7, - 0x5afa, 0x2554, 0x2566, 0x2557, 0x2560, 0x256c, 0x2563, 0x255a, - 0x2569, 0x255d, 0x2552, 0x2564, 0x2555, 0x255e, 0x256a, 0x2561, - 0x2558, 0x2567, 0x255b, 0x2553, 0x2565, 0x2556, 0x255f, 0x256b, - 0x2562, 0x2559, 0x2568, 0x255c, 0x2551, 0x2550, 0x256d, 0x256e, - 0x2570, 0x256f, 0x2593, + UNIINV, UNIINV, UNIINV, UNIINV, UNIINV, 0x2295, 0x2299, 0x2215, + 0xfe68, UNIINV, 0xffe5, UNIINV, 0xffe0, 0xffe1, 0x20ac, 0x7881, + 0x92b9, 0x88cf, 0x58bb, 0x6052, 0x7ca7, 0x5afa, 0x2554, 0x2566, + 0x2557, 0x2560, 0x256c, 0x2563, 0x255a, 0x2569, 0x255d, 0x2552, + 0x2564, 0x2555, 0x255e, 0x256a, 0x2561, 0x2558, 0x2567, 0x255b, + 0x2553, 0x2565, 0x2556, 0x255f, 0x256b, 0x2562, 0x2559, 0x2568, + 0x255c, 0x2551, 0x2550, 0x256d, 0x256e, 0x2570, 0x256f, 0x2593, }; static const struct dbcs_index cp950ext_decmap[256] = { @@ -214,9 +195,9 @@ /* 0x9E */ {0, 0, 0}, /* 0x9F */ {0, 0, 0}, /* 0xA0 */ {0, 0, 0}, -/* 0xA1 */ {__cp950ext_decmap+0, 0x45, 0xfe}, -/* 0xA2 */ {__cp950ext_decmap+186, 0x40, 0xce}, -/* 0xA3 */ {__cp950ext_decmap+329, 0xe1, 0xe1}, +/* 0xA1 */ {__cp950ext_decmap+0, 0x45, 0xf3}, +/* 0xA2 */ {__cp950ext_decmap+175, 0x41, 0x47}, +/* 0xA3 */ {__cp950ext_decmap+182, 0xe1, 0xe1}, /* 0xA4 */ {0, 0, 0}, /* 0xA5 */ {0, 0, 0}, /* 0xA6 */ {0, 0, 0}, @@ -302,7 +283,7 @@ /* 0xF6 */ {0, 0, 0}, /* 0xF7 */ {0, 0, 0}, /* 0xF8 */ {0, 0, 0}, -/* 0xF9 */ {__cp950ext_decmap+330, 0xd6, 0xfe}, +/* 0xF9 */ {__cp950ext_decmap+183, 0xd6, 0xfe}, /* 0xFA */ {0, 0, 0}, /* 0xFB */ {0, 0, 0}, /* 0xFC */ {0, 0, 0}, @@ -311,10 +292,8 @@ /* 0xFF */ {0, 0, 0}, }; -static const DBCHAR __cp950ext_encmap[587] = { - 0xa1c2, 0xa1c5, 0xa145, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, +static const DBCHAR __cp950ext_encmap[502] = { + 0xa1c2, 0xa145, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, @@ -328,10 +307,9 @@ NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa3e1, - 0xa241, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa3e1, 0xa241, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, @@ -345,30 +323,26 @@ NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - 0xa1f2, NOCHAR, NOCHAR, NOCHAR, 0xa1f3, 0xf9f8, 0xf9e6, 0xf9ef, - 0xf9dd, 0xf9e8, 0xf9f1, 0xf9df, 0xf9ec, 0xf9f5, 0xf9e3, 0xf9ee, - 0xf9f7, 0xf9e5, NOCHAR, 0xf9f2, 0xf9e0, NOCHAR, 0xf9f4, 0xf9e2, - 0xf9e7, 0xf9f0, 0xf9de, 0xf9ed, 0xf9f6, 0xf9e4, NOCHAR, 0xf9f3, - 0xf9e1, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - 0xa15a, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xf9fe, - 0xa2cc, NOCHAR, NOCHAR, NOCHAR, 0xa2ce, 0xf9d9, 0xf9dc, 0xf9da, - 0xf9d6, 0xf9db, 0xf9d8, 0xf9d7, 0xa14e, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa1f2, + NOCHAR, NOCHAR, NOCHAR, 0xa1f3, 0xf9f8, 0xf9e6, 0xf9ef, 0xf9dd, + 0xf9e8, 0xf9f1, 0xf9df, 0xf9ec, 0xf9f5, 0xf9e3, 0xf9ee, 0xf9f7, + 0xf9e5, NOCHAR, 0xf9f2, 0xf9e0, NOCHAR, 0xf9f4, 0xf9e2, 0xf9e7, + 0xf9f0, 0xf9de, 0xf9ed, 0xf9f6, 0xf9e4, NOCHAR, 0xf9f3, 0xf9e1, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, 0xa242, 0xa1fe, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xf9fe, 0xf9d9, + 0xf9dc, 0xf9da, 0xf9d6, 0xf9db, 0xf9d8, 0xf9d7, 0xa14e, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa242, 0xa1e3, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, 0xa240, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, 0xa1e3, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, @@ -381,17 +355,13 @@ NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa246, 0xa247, NOCHAR, - 0xa1c3, NOCHAR, 0xa244, + 0xa246, 0xa247, NOCHAR, NOCHAR, NOCHAR, 0xa244, }; static const struct unim_index cp950ext_encmap[256] = { /* 0x00 */ {__cp950ext_encmap+0, 0xaf, 0xaf}, /* 0x01 */ {0, 0, 0}, -/* 0x02 */ {__cp950ext_encmap+1, 0xcd, 0xcd}, +/* 0x02 */ {0, 0, 0}, /* 0x03 */ {0, 0, 0}, /* 0x04 */ {0, 0, 0}, /* 0x05 */ {0, 0, 0}, @@ -421,12 +391,12 @@ /* 0x1D */ {0, 0, 0}, /* 0x1E */ {0, 0, 0}, /* 0x1F */ {0, 0, 0}, -/* 0x20 */ {__cp950ext_encmap+2, 0x27, 0xac}, +/* 0x20 */ {__cp950ext_encmap+1, 0x27, 0xac}, /* 0x21 */ {0, 0, 0}, -/* 0x22 */ {__cp950ext_encmap+136, 0x15, 0x99}, +/* 0x22 */ {__cp950ext_encmap+135, 0x15, 0x99}, /* 0x23 */ {0, 0, 0}, /* 0x24 */ {0, 0, 0}, -/* 0x25 */ {__cp950ext_encmap+269, 0x51, 0x93}, +/* 0x25 */ {__cp950ext_encmap+268, 0x51, 0x93}, /* 0x26 */ {0, 0, 0}, /* 0x27 */ {0, 0, 0}, /* 0x28 */ {0, 0, 0}, @@ -472,20 +442,20 @@ /* 0x50 */ {0, 0, 0}, /* 0x51 */ {0, 0, 0}, /* 0x52 */ {0, 0, 0}, -/* 0x53 */ {__cp950ext_encmap+336, 0x41, 0x45}, +/* 0x53 */ {0, 0, 0}, /* 0x54 */ {0, 0, 0}, /* 0x55 */ {0, 0, 0}, /* 0x56 */ {0, 0, 0}, /* 0x57 */ {0, 0, 0}, -/* 0x58 */ {__cp950ext_encmap+341, 0xbb, 0xbb}, +/* 0x58 */ {__cp950ext_encmap+335, 0xbb, 0xbb}, /* 0x59 */ {0, 0, 0}, -/* 0x5A */ {__cp950ext_encmap+342, 0xfa, 0xfa}, +/* 0x5A */ {__cp950ext_encmap+336, 0xfa, 0xfa}, /* 0x5B */ {0, 0, 0}, /* 0x5C */ {0, 0, 0}, /* 0x5D */ {0, 0, 0}, /* 0x5E */ {0, 0, 0}, /* 0x5F */ {0, 0, 0}, -/* 0x60 */ {__cp950ext_encmap+343, 0x52, 0x52}, +/* 0x60 */ {__cp950ext_encmap+337, 0x52, 0x52}, /* 0x61 */ {0, 0, 0}, /* 0x62 */ {0, 0, 0}, /* 0x63 */ {0, 0, 0}, @@ -509,11 +479,11 @@ /* 0x75 */ {0, 0, 0}, /* 0x76 */ {0, 0, 0}, /* 0x77 */ {0, 0, 0}, -/* 0x78 */ {__cp950ext_encmap+344, 0x81, 0x81}, +/* 0x78 */ {__cp950ext_encmap+338, 0x81, 0x81}, /* 0x79 */ {0, 0, 0}, /* 0x7A */ {0, 0, 0}, /* 0x7B */ {0, 0, 0}, -/* 0x7C */ {__cp950ext_encmap+345, 0xa7, 0xa7}, +/* 0x7C */ {__cp950ext_encmap+339, 0xa7, 0xa7}, /* 0x7D */ {0, 0, 0}, /* 0x7E */ {0, 0, 0}, /* 0x7F */ {0, 0, 0}, @@ -525,7 +495,7 @@ /* 0x85 */ {0, 0, 0}, /* 0x86 */ {0, 0, 0}, /* 0x87 */ {0, 0, 0}, -/* 0x88 */ {__cp950ext_encmap+346, 0xcf, 0xcf}, +/* 0x88 */ {__cp950ext_encmap+340, 0xcf, 0xcf}, /* 0x89 */ {0, 0, 0}, /* 0x8A */ {0, 0, 0}, /* 0x8B */ {0, 0, 0}, @@ -535,7 +505,7 @@ /* 0x8F */ {0, 0, 0}, /* 0x90 */ {0, 0, 0}, /* 0x91 */ {0, 0, 0}, -/* 0x92 */ {__cp950ext_encmap+347, 0xb9, 0xb9}, +/* 0x92 */ {__cp950ext_encmap+341, 0xb9, 0xb9}, /* 0x93 */ {0, 0, 0}, /* 0x94 */ {0, 0, 0}, /* 0x95 */ {0, 0, 0}, @@ -643,7 +613,7 @@ /* 0xFB */ {0, 0, 0}, /* 0xFC */ {0, 0, 0}, /* 0xFD */ {0, 0, 0}, -/* 0xFE */ {__cp950ext_encmap+348, 0x51, 0x68}, -/* 0xFF */ {__cp950ext_encmap+372, 0x0f, 0xe5}, +/* 0xFE */ {__cp950ext_encmap+342, 0x51, 0x68}, +/* 0xFF */ {__cp950ext_encmap+366, 0x5e, 0xe5}, }; |
From: Hye-Shik C. <pe...@us...> - 2003-06-20 09:04:54
|
perky 03/06/20 02:04:53 Modified: src/maps map_big5.h map_cp950ext.h Log: - Tweaked some mapping for cp932 and cp950 to make more consistency with MS Windows. - CP932: Added single byte "UNDEFINED" characters 0x80, 0xa0, 0xfd, 0xfe, 0xff (documented on NOTES.cp932) - CP950: Changed encode mappings to another more popular for duplicated unicode points: 5341 -> A451, 5345 -> A4CA - A unittest for big5 mapping is added. - Fixed a bug that cp932 codec couldn't decode half-width katakana. Revision Changes Path 1.4 +0 -0 cjkcodecs/src/maps/map_big5.h Index: map_big5.h =================================================================== RCS file: /cvsroot/koco/cjkcodecs/src/maps/map_big5.h,v retrieving revision 1.3 retrieving revision 1.4 diff -u -r1.3 -r1.4 --- map_big5.h 19 Jun 2003 17:49:01 -0000 1.3 +++ map_big5.h 20 Jun 2003 09:04:53 -0000 1.4 @@ -1,5 +1,5 @@ /* - * $Id: map_big5.h,v 1.3 2003/06/19 17:49:01 perky Exp $ + * $Id: map_big5.h,v 1.4 2003/06/20 09:04:53 perky Exp $ */ static const Py_UNICODE __big5_decmap[16702] = { 1.5 +14 -4 cjkcodecs/src/maps/map_cp950ext.h Index: map_cp950ext.h =================================================================== RCS file: /cvsroot/koco/cjkcodecs/src/maps/map_cp950ext.h,v retrieving revision 1.4 retrieving revision 1.5 diff -u -r1.4 -r1.5 --- map_cp950ext.h 19 Jun 2003 17:49:01 -0000 1.4 +++ map_cp950ext.h 20 Jun 2003 09:04:53 -0000 1.5 @@ -1,5 +1,5 @@ /* - * $Id: map_cp950ext.h,v 1.4 2003/06/19 17:49:01 perky Exp $ + * $Id: map_cp950ext.h,v 1.5 2003/06/20 09:04:53 perky Exp $ */ static const Py_UNICODE __cp950ext_decmap[224] = { @@ -292,7 +292,7 @@ /* 0xFF */ {0, 0, 0}, }; -static const DBCHAR __cp950ext_encmap[502] = { +static const DBCHAR __cp950ext_encmap[581] = { 0xa1c2, 0xa145, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, @@ -338,15 +338,17 @@ 0xf9dc, 0xf9da, 0xf9d6, 0xf9db, 0xf9d8, 0xf9d7, 0xa14e, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa242, 0xa1e3, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa242, 0xa1fe, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, 0xa240, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa1e3, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, @@ -355,7 +357,15 @@ NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, - 0xa246, 0xa247, NOCHAR, NOCHAR, NOCHAR, 0xa244, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, + NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, NOCHAR, 0xa246, + 0xa247, NOCHAR, NOCHAR, NOCHAR, 0xa244, }; static const struct unim_index cp950ext_encmap[256] = { @@ -614,6 +624,6 @@ /* 0xFC */ {0, 0, 0}, /* 0xFD */ {0, 0, 0}, /* 0xFE */ {__cp950ext_encmap+342, 0x51, 0x68}, -/* 0xFF */ {__cp950ext_encmap+366, 0x5e, 0xe5}, +/* 0xFF */ {__cp950ext_encmap+366, 0x0f, 0xe5}, }; |