diff options
Diffstat (limited to 'sal/textenc/convertiscii.tab')
| -rw-r--r-- | sal/textenc/convertiscii.tab | 115 |
1 files changed, 115 insertions, 0 deletions
diff --git a/sal/textenc/convertiscii.tab b/sal/textenc/convertiscii.tab new file mode 100644 index 000000000000..93ef2dbf3061 --- /dev/null +++ b/sal/textenc/convertiscii.tab @@ -0,0 +1,115 @@ +/************************************************************************* + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2008 by Sun Microsystems, Inc. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * $RCSfile: convertiscii.tab,v $ + * $Revision: 1.4 $ + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +#include "tenchelp.h" + +#include "rtl/tencinfo.h" +#include "sal/types.h" + +#include <stddef.h> + +/* Conversion tables for the Devanagari version of ISCII (IS 13194:1991). + * + * They do not map the ISCII characters INV (0xD9), ATR (0xEF), and EXT (0xF0). + * They do not map U+0958--095E to sequences of two ISCII characters, of which + * the second would be the combining nukta (0xE9). + */ + +/* The following table is based on LGPL code by Sandeep Patnaik + * (patnaik@students.iiit.net) and Sunil Mohan Adapa + * (sunilmohanadapa@postmark.net). + */ +#define RTL_TEXTENC_ISCII_DEVANAGARI_START 0xA1 +#define RTL_TEXTENC_ISCII_DEVANAGARI_END 0xFA +static sal_uInt16 const +aImplIsciiDevanagariToUniTab[RTL_TEXTENC_ISCII_DEVANAGARI_END + - RTL_TEXTENC_ISCII_DEVANAGARI_START + 1] += { 0x0901, 0x0902, 0x0903, 0x0905, 0x0906, 0x0907, 0x0908, /* A0 */ + 0x0909, 0x090A, 0x090B, 0x090E, 0x090F, 0x0910, 0x090D, 0x0912, + 0x0913, 0x0914, 0x0911, 0x0915, 0x0916, 0x0917, 0x0918, 0x0919, /* B0 */ + 0x091A, 0x091B, 0x091C, 0x091D, 0x091E, 0x091F, 0x0920, 0x0921, + 0x0922, 0x0923, 0x0924, 0x0925, 0x0926, 0x0927, 0x0928, 0x0929, /* C0 */ + 0x092A, 0x092B, 0x092C, 0x092D, 0x092E, 0x092F, 0x095F, 0x0930, + 0x0931, 0x0932, 0x0933, 0x0934, 0x0935, 0x0936, 0x0937, 0x0938, /* D0 */ + 0x0939, 0, 0x093E, 0x093F, 0x0940, 0x0941, 0x0942, 0x0943, + 0x0946, 0x0947, 0x0948, 0x0945, 0x094A, 0x094B, 0x094C, 0x0949, /* E0 */ + 0x094D, 0x093C, 0x0964, 0, 0, 0, 0, 0, + 0, 0x0966, 0x0967, 0x0968, 0x0969, 0x096A, 0x096B, 0x096C, /* F0 */ + 0x096D, 0x096E, 0x096F }; + +#define RTL_TEXTENC_UNICODE_DEVANAGARI_START 0x0901 +#define RTL_TEXTENC_UNICODE_DEVANAGARI_END 0x096F +static sal_uChar const +aImplUniToIsciiDevanagariTab[RTL_TEXTENC_UNICODE_DEVANAGARI_END + - RTL_TEXTENC_UNICODE_DEVANAGARI_START + 1] += { 0xA1, 0xA2, 0xA3, 0, 0xA4, 0xA5, 0xA6, /* U+0900 */ + 0xA7, 0xA8, 0xA9, 0xAA, 0, 0xAE, 0xAB, 0xAC, + 0xAD, 0xB2, 0xAF, 0xB0, 0xB1, 0xB3, 0xB4, 0xB5, /* U+0910 */ + 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, + 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, /* U+0920 */ + 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, + 0xCF, 0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, /* U+0930 */ + 0xD7, 0xD8, 0, 0, 0xE9, 0, 0xDA, 0xDB, + 0xDC, 0xDD, 0xDE, 0xDF, 0, 0xE3, 0xE0, 0xE1, /* U+0940 */ + 0xE2, 0xE7, 0xE4, 0xE5, 0xE6, 0xE8, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, /* U+0950 */ + 0, 0, 0, 0, 0, 0, 0, 0xCE, + 0, 0, 0, 0, 0xEA, 0, 0xF1, 0xF2, /* U+0960 */ + 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA }; + +static ImplByteConvertData const aImplIsciiDevanagariConvertData += { aImplIsciiDevanagariToUniTab, + NULL, + RTL_TEXTENC_ISCII_DEVANAGARI_START, RTL_TEXTENC_ISCII_DEVANAGARI_END, + NOTABUNI_START, NOTABUNI_END, + aImplUniToIsciiDevanagariTab, + NULL, + NULL, + RTL_TEXTENC_UNICODE_DEVANAGARI_START, RTL_TEXTENC_UNICODE_DEVANAGARI_END, + NOTABCHAR_START, NOTABCHAR_END, + 0 }; + +static ImplTextEncodingData const aImplIsciiDevanagariTextEncodingData + = { { &aImplIsciiDevanagariConvertData, + &ImplCharToUnicode, + &ImplUnicodeToChar, + NULL, + NULL, + NULL, + NULL, + NULL, + NULL }, + 1, + 1, + 1, + 1, + NULL, + NULL, + RTL_TEXTENCODING_INFO_ASCII }; |