From 69e087c14439f0e92d3c8cc5e97d66b7e6e7ffea Mon Sep 17 00:00:00 2001 From: Vadim Zeitlin Date: Fri, 23 Jul 2010 23:33:16 +0000 Subject: [PATCH] Add support for CP-866 encoding to wxEncodingConverter. Recognize yet another Cyrillic encoding, a DOS OEM one. Closes #2318. git-svn-id: https://svn.wxwidgets.org/svn/wx/wxWidgets/trunk@65062 c3d73ce0-8a6f-49c7-b76d-6d57e0e08775 --- docs/changes.txt | 1 + misc/unictabl/mappings/CP866.txt | 273 +++++++++++++++++++++++++++++++ src/common/fmapbase.cpp | 4 + src/common/unictabl.inc | 26 +++ 4 files changed, 304 insertions(+) create mode 100644 misc/unictabl/mappings/CP866.txt diff --git a/docs/changes.txt b/docs/changes.txt index e99dd4bdc9..971993ede0 100644 --- a/docs/changes.txt +++ b/docs/changes.txt @@ -411,6 +411,7 @@ MSW: All (GUI): - wxAUI: support auto-orientable toolbars (wsu). +- Add support for CP-866 encoding to wxEncodingConverter (madnut). 2.9.1: diff --git a/misc/unictabl/mappings/CP866.txt b/misc/unictabl/mappings/CP866.txt new file mode 100644 index 0000000000..64d29ef1fb --- /dev/null +++ b/misc/unictabl/mappings/CP866.txt @@ -0,0 +1,273 @@ +# +# Name: cp866_DOSCyrillicRussian to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp866_DOSCyrillicRussian code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp866_DOSCyrillicRussian order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0a 0x000a #LINE FEED +0x0b 0x000b #VERTICAL TABULATION +0x0c 0x000c #FORM FEED +0x0d 0x000d #CARRIAGE RETURN +0x0e 0x000e #SHIFT OUT +0x0f 0x000f #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1a 0x001a #SUBSTITUTE +0x1b 0x001b #ESCAPE +0x1c 0x001c #FILE SEPARATOR +0x1d 0x001d #GROUP SEPARATOR +0x1e 0x001e #RECORD SEPARATOR +0x1f 0x001f #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2a 0x002a #ASTERISK +0x2b 0x002b #PLUS SIGN +0x2c 0x002c #COMMA +0x2d 0x002d #HYPHEN-MINUS +0x2e 0x002e #FULL STOP +0x2f 0x002f #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3a 0x003a #COLON +0x3b 0x003b #SEMICOLON +0x3c 0x003c #LESS-THAN SIGN +0x3d 0x003d #EQUALS SIGN +0x3e 0x003e #GREATER-THAN SIGN +0x3f 0x003f #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4a 0x004a #LATIN CAPITAL LETTER J +0x4b 0x004b #LATIN CAPITAL LETTER K +0x4c 0x004c #LATIN CAPITAL LETTER L +0x4d 0x004d #LATIN CAPITAL LETTER M +0x4e 0x004e #LATIN CAPITAL LETTER N +0x4f 0x004f #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5a 0x005a #LATIN CAPITAL LETTER Z +0x5b 0x005b #LEFT SQUARE BRACKET +0x5c 0x005c #REVERSE SOLIDUS +0x5d 0x005d #RIGHT SQUARE BRACKET +0x5e 0x005e #CIRCUMFLEX ACCENT +0x5f 0x005f #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6a 0x006a #LATIN SMALL LETTER J +0x6b 0x006b #LATIN SMALL LETTER K +0x6c 0x006c #LATIN SMALL LETTER L +0x6d 0x006d #LATIN SMALL LETTER M +0x6e 0x006e #LATIN SMALL LETTER N +0x6f 0x006f #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7a 0x007a #LATIN SMALL LETTER Z +0x7b 0x007b #LEFT CURLY BRACKET +0x7c 0x007c #VERTICAL LINE +0x7d 0x007d #RIGHT CURLY BRACKET +0x7e 0x007e #TILDE +0x7f 0x007f #DELETE +0x80 0x0410 #CYRILLIC CAPITAL LETTER A +0x81 0x0411 #CYRILLIC CAPITAL LETTER BE +0x82 0x0412 #CYRILLIC CAPITAL LETTER VE +0x83 0x0413 #CYRILLIC CAPITAL LETTER GHE +0x84 0x0414 #CYRILLIC CAPITAL LETTER DE +0x85 0x0415 #CYRILLIC CAPITAL LETTER IE +0x86 0x0416 #CYRILLIC CAPITAL LETTER ZHE +0x87 0x0417 #CYRILLIC CAPITAL LETTER ZE +0x88 0x0418 #CYRILLIC CAPITAL LETTER I +0x89 0x0419 #CYRILLIC CAPITAL LETTER SHORT I +0x8a 0x041a #CYRILLIC CAPITAL LETTER KA +0x8b 0x041b #CYRILLIC CAPITAL LETTER EL +0x8c 0x041c #CYRILLIC CAPITAL LETTER EM +0x8d 0x041d #CYRILLIC CAPITAL LETTER EN +0x8e 0x041e #CYRILLIC CAPITAL LETTER O +0x8f 0x041f #CYRILLIC CAPITAL LETTER PE +0x90 0x0420 #CYRILLIC CAPITAL LETTER ER +0x91 0x0421 #CYRILLIC CAPITAL LETTER ES +0x92 0x0422 #CYRILLIC CAPITAL LETTER TE +0x93 0x0423 #CYRILLIC CAPITAL LETTER U +0x94 0x0424 #CYRILLIC CAPITAL LETTER EF +0x95 0x0425 #CYRILLIC CAPITAL LETTER HA +0x96 0x0426 #CYRILLIC CAPITAL LETTER TSE +0x97 0x0427 #CYRILLIC CAPITAL LETTER CHE +0x98 0x0428 #CYRILLIC CAPITAL LETTER SHA +0x99 0x0429 #CYRILLIC CAPITAL LETTER SHCHA +0x9a 0x042a #CYRILLIC CAPITAL LETTER HARD SIGN +0x9b 0x042b #CYRILLIC CAPITAL LETTER YERU +0x9c 0x042c #CYRILLIC CAPITAL LETTER SOFT SIGN +0x9d 0x042d #CYRILLIC CAPITAL LETTER E +0x9e 0x042e #CYRILLIC CAPITAL LETTER YU +0x9f 0x042f #CYRILLIC CAPITAL LETTER YA +0xa0 0x0430 #CYRILLIC SMALL LETTER A +0xa1 0x0431 #CYRILLIC SMALL LETTER BE +0xa2 0x0432 #CYRILLIC SMALL LETTER VE +0xa3 0x0433 #CYRILLIC SMALL LETTER GHE +0xa4 0x0434 #CYRILLIC SMALL LETTER DE +0xa5 0x0435 #CYRILLIC SMALL LETTER IE +0xa6 0x0436 #CYRILLIC SMALL LETTER ZHE +0xa7 0x0437 #CYRILLIC SMALL LETTER ZE +0xa8 0x0438 #CYRILLIC SMALL LETTER I +0xa9 0x0439 #CYRILLIC SMALL LETTER SHORT I +0xaa 0x043a #CYRILLIC SMALL LETTER KA +0xab 0x043b #CYRILLIC SMALL LETTER EL +0xac 0x043c #CYRILLIC SMALL LETTER EM +0xad 0x043d #CYRILLIC SMALL LETTER EN +0xae 0x043e #CYRILLIC SMALL LETTER O +0xaf 0x043f #CYRILLIC SMALL LETTER PE +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x258c #LEFT HALF BLOCK +0xde 0x2590 #RIGHT HALF BLOCK +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x0440 #CYRILLIC SMALL LETTER ER +0xe1 0x0441 #CYRILLIC SMALL LETTER ES +0xe2 0x0442 #CYRILLIC SMALL LETTER TE +0xe3 0x0443 #CYRILLIC SMALL LETTER U +0xe4 0x0444 #CYRILLIC SMALL LETTER EF +0xe5 0x0445 #CYRILLIC SMALL LETTER HA +0xe6 0x0446 #CYRILLIC SMALL LETTER TSE +0xe7 0x0447 #CYRILLIC SMALL LETTER CHE +0xe8 0x0448 #CYRILLIC SMALL LETTER SHA +0xe9 0x0449 #CYRILLIC SMALL LETTER SHCHA +0xea 0x044a #CYRILLIC SMALL LETTER HARD SIGN +0xeb 0x044b #CYRILLIC SMALL LETTER YERU +0xec 0x044c #CYRILLIC SMALL LETTER SOFT SIGN +0xed 0x044d #CYRILLIC SMALL LETTER E +0xee 0x044e #CYRILLIC SMALL LETTER YU +0xef 0x044f #CYRILLIC SMALL LETTER YA +0xf0 0x0401 #CYRILLIC CAPITAL LETTER IO +0xf1 0x0451 #CYRILLIC SMALL LETTER IO +0xf2 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xf3 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE +0xf4 0x0407 #CYRILLIC CAPITAL LETTER YI +0xf5 0x0457 #CYRILLIC SMALL LETTER YI +0xf6 0x040e #CYRILLIC CAPITAL LETTER SHORT U +0xf7 0x045e #CYRILLIC SMALL LETTER SHORT U +0xf8 0x00b0 #DEGREE SIGN +0xf9 0x2219 #BULLET OPERATOR +0xfa 0x00b7 #MIDDLE DOT +0xfb 0x221a #SQUARE ROOT +0xfc 0x2116 #NUMERO SIGN +0xfd 0x00a4 #CURRENCY SIGN +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE diff --git a/src/common/fmapbase.cpp b/src/common/fmapbase.cpp index 9f3a6e70cf..8f09c9a04e 100644 --- a/src/common/fmapbase.cpp +++ b/src/common/fmapbase.cpp @@ -74,6 +74,7 @@ static const wxFontEncoding gs_encodings[] = wxFONTENCODING_ISO8859_15, wxFONTENCODING_KOI8, wxFONTENCODING_KOI8_U, + wxFONTENCODING_CP866, wxFONTENCODING_CP874, wxFONTENCODING_CP932, wxFONTENCODING_CP936, @@ -163,6 +164,7 @@ static const char* const gs_encodingDescs[] = wxTRANSLATE( "Western European with Euro (ISO-8859-15)" ), wxTRANSLATE( "KOI8-R" ), wxTRANSLATE( "KOI8-U" ), + wxTRANSLATE( "Windows/DOS OEM Cyrillic (CP 866)" ), wxTRANSLATE( "Windows Thai (CP 874)" ), wxTRANSLATE( "Windows Japanese (CP 932)" ), wxTRANSLATE( "Windows Chinese Simplified (CP 936)" ), @@ -266,6 +268,8 @@ static const wxChar* const gs_encodingNames[WXSIZEOF(gs_encodingDescs)][9] = { wxT( "KOI8-R" ), wxT( "KOI8-RU" ), NULL }, { wxT( "KOI8-U" ), NULL }, + { wxT( "WINDOWS-866" ), wxT( "CP866" ), NULL }, + { wxT( "WINDOWS-874" ), wxT( "CP874" ), wxT( "MS874" ), wxT( "IBM-874" ), NULL }, { wxT( "WINDOWS-932" ), wxT( "CP932" ), wxT( "MS932" ), wxT( "IBM-932" ), NULL }, { wxT( "WINDOWS-936" ), wxT( "CP936" ), wxT( "MS936" ), wxT( "IBM-936" ), NULL }, diff --git a/src/common/unictabl.inc b/src/common/unictabl.inc index de258f6d50..5bb0e1d311 100644 --- a/src/common/unictabl.inc +++ b/src/common/unictabl.inc @@ -561,6 +561,31 @@ static const wxUint16 encoding_table__CP1257[128] = { }; +/* + * CP866 to Unicode recoding table + * based on file mappings/CP866.TXT by Unicode Consortium + */ + +static const wxUint16 encoding_table__CP866[128] = { + 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, + 0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E, 0x041F, + 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, + 0x0428, 0x0429, 0x042A, 0x042B, 0x042C, 0x042D, 0x042E, 0x042F, + 0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437, + 0x0438, 0x0439, 0x043A, 0x043B, 0x043C, 0x043D, 0x043E, 0x043F, + 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, + 0x2555, 0x2563, 0x2551, 0x2557, 0x255D, 0x255C, 0x255B, 0x2510, + 0x2514, 0x2534, 0x252C, 0x251C, 0x2500, 0x253C, 0x255E, 0x255F, + 0x255A, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256C, 0x2567, + 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256B, + 0x256A, 0x2518, 0x250C, 0x2588, 0x2584, 0x258C, 0x2590, 0x2580, + 0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447, + 0x0448, 0x0449, 0x044A, 0x044B, 0x044C, 0x044D, 0x044E, 0x044F, + 0x0401, 0x0451, 0x0404, 0x0454, 0x0407, 0x0457, 0x040E, 0x045E, + 0x00B0, 0x2219, 0x00B7, 0x221A, 0x2116, 0x00A4, 0x25A0, 0x00A0 + }; + + /* * KOI8 to Unicode recoding table * based on file mappings/KOI8-R.TXT by Unicode Consortium @@ -868,5 +893,6 @@ static const struct { { wxFONTENCODING_CP1257, encoding_table__CP1257}, { wxFONTENCODING_KOI8, encoding_table__KOI8}, { wxFONTENCODING_KOI8_U, encoding_table__KOI8_U}, + { wxFONTENCODING_CP866, encoding_table__CP866}, {wxFONTENCODING_MAX /*anything*/, NULL} }; -- 2.45.2