From: Jarkko Hietaniemi Date: Mon, 17 Sep 2001 23:39:28 +0000 (+0000) Subject: Add various encodings. X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=f7ac36769021f6698f374d5dc8c288f14c86c3fd;p=p5sagit%2Fp5-mst-13.2.git Add various encodings. p4raw-id: //depot/perl@12063 --- diff --git a/MANIFEST b/MANIFEST index 8a3d5bc..ed5f26c 100644 --- a/MANIFEST +++ b/MANIFEST @@ -245,6 +245,8 @@ ext/Encode/Encode/iso8859-1.enc Encoding tables ext/Encode/Encode/iso8859-1.ucm Encoding tables ext/Encode/Encode/iso8859-10.enc Encoding tables ext/Encode/Encode/iso8859-10.ucm Encoding tables +ext/Encode/Encode/iso8859-11.enc Encoding tables +ext/Encode/Encode/iso8859-11.ucm Encoding tables ext/Encode/Encode/iso8859-13.enc Encoding tables ext/Encode/Encode/iso8859-13.ucm Encoding tables ext/Encode/Encode/iso8859-14.enc Encoding tables @@ -273,8 +275,12 @@ ext/Encode/Encode/isoir-197.enc Encoding tables ext/Encode/Encode/jis0201.enc Encoding tables ext/Encode/Encode/jis0208.enc Encoding tables ext/Encode/Encode/jis0212.enc Encoding tables +ext/Encode/Encode/koi8-f.enc Encoding tables +ext/Encode/Encode/koi8-f.ucm Encoding tables ext/Encode/Encode/koi8-r.enc Encoding tables ext/Encode/Encode/koi8-r.ucm Encoding tables +ext/Encode/Encode/koi8-u.enc Encoding tables +ext/Encode/Encode/koi8-u.ucm Encoding tables ext/Encode/Encode/ksc5601.enc Encoding tables ext/Encode/Encode/macCentEuro.enc Encoding tables ext/Encode/Encode/macCroatian.enc Encoding tables @@ -289,11 +295,17 @@ ext/Encode/Encode/macSami.enc Encoding tables ext/Encode/Encode/macThai.enc Encoding tables ext/Encode/Encode/macTurkish.enc Encoding tables ext/Encode/Encode/macUkraine.enc Encoding tables +ext/Encode/Encode/nextstep.enc Encoding tables +ext/Encode/Encode/nextstep.ucm Encoding tables ext/Encode/Encode/posix-bc.enc Encoding tables ext/Encode/Encode/posix-bc.ucm Encoding tables +ext/Encode/Encode/roman8.enc Encoding tables +ext/Encode/Encode/roman8.ucm Encoding tables ext/Encode/Encode/shiftjis.enc Encoding tables ext/Encode/Encode/symbol.enc Encoding tables ext/Encode/Encode/symbol.ucm Encoding tables +ext/Encode/Encode/viscii.enc Encoding tables +ext/Encode/Encode/viscii.ucm Encoding tables ext/Encode/Encode/Tcl.pm Handler for .enc encodings ext/Encode/Encode/Tcl.t See if Encode::Tcl works ext/Encode/Makefile.PL Encode extension diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index 45e5abd..ec813f6 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -42,9 +42,22 @@ use Carp; our %encoding; my @alias; # ordered matching list my %alias; # cached known aliases + # 0 1 2 3 4 5 6 7 8 9 10 our @latin2iso_num = ( 0, 1, 2, 3, 4, 9, 10, 13, 14, 15, 16 ); +our %winlatin2cp = ( + 'Latin1' => 1252, + 'Latin2' => 1250, + 'Cyrillic' => 1251, + 'Baltic' => 1257, + 'Greek' => 1253, + 'Turkish' => 1254, + 'Hebrew' => 1255, + 'Arabic' => 1256, + 'Baltic' => 1257, + 'Vietnamese' => 1258, + ); sub encodings { @@ -105,6 +118,9 @@ define_alias( qr/^iso[-_]?(\d+)[-_](\d+)$/i => '"iso-$1-$2"' ); # At least HP-UX has these. define_alias( qr/^iso8859(\d+)$/i => '"iso-8859-$1"' ); +# More HP stuff. +define_alias( qr/^(?:hp-)?(arabic|greek|hebrew|kana|roman|thai|turkish)8$/i => '"${1}8"' ); + # This is a font issue, not an encoding issue. # (The currency symbol of the Latin 1 upper half # has been redefined as the euro symbol.) @@ -113,12 +129,18 @@ define_alias( qr/^(.+)\@euro$/i => '"$1"' ); # Allow latin-1 style names as well define_alias( qr/^(?:iso[-_]?)?latin[-_]?(\d+)$/i => '"iso-8859-$latin2iso_num[$1]"' ); +# Allow winlatin1 style names as well +define_alias( qr/^win(latin[12]|cyrillic|baltic|greek|turkish|hebrew|arabic|baltic|vietnamese)$/i => '"cp$winlatin2cp{$1}"' ); + # Common names for non-latin prefered MIME names define_alias( 'ascii' => 'US-ascii', 'cyrillic' => 'iso-8859-5', 'arabic' => 'iso-8859-6', 'greek' => 'iso-8859-7', - 'hebrew' => 'iso-8859-8'); + 'hebrew' => 'iso-8859-8', + 'thai' => 'iso-8859-11', + 'tis620' => 'iso-8859-11', + ); # At least AIX has IBM-NNN (surprisingly...) instead of cpNNN. define_alias( qr/^ibm[-_]?(\d\d\d\d?)$/i => '"cp$1"'); @@ -126,11 +148,24 @@ define_alias( qr/^ibm[-_]?(\d\d\d\d?)$/i => '"cp$1"'); # Standardize on the dashed versions. define_alias( qr/^utf8$/i => 'utf-8' ); define_alias( qr/^koi8r$/i => 'koi8-r' ); - -# TODO: the HP-UX '8' encodings: arabic8 greek8 hebrew8 roman8 turkish8 -# TODO: the Thai Encoding tis620 -# TODO: the Chinese Encoding gb18030 -# TODO: what is the Japanese 'ujis' encoding seen in some Linuxes? +define_alias( qr/^koi8u$/i => 'koi8-u' ); + +# TODO: HP-UX '8' encodings arabic8 greek8 hebrew8 kana8 thai8 turkish8 +# TODO: HP-UX '15' encodings japanese15 korean15 roi15 +# TODO: Cyrillic encoding ISO-IR-111 (useful?) +# TODO: Chinese encodings GB18030 GBK Big5-HSKCS EUC-TW +# TODO: Armenian encoding ARMSCII-8 +# TODO: Hebrew encoding ISO-8859-8-1 +# TODO: Thai encoding TCVN +# TODO: Korean encoding Johab +# TODO: Vietnamese encodings VISCII VPS +# TODO: Japanese encoding JIS (not the same as SJIS) +# TODO: Mac Asian+African encodings: Arabic Armenian Bengali Burmese +# ChineseSimp ChineseTrad Devanagari Ethiopic ExtArabic +# Farsi Georgian Gujarati Gurmukhi Hebrew Japanese +# Kannada Khmer Korean Laotian Malayalam Mongolian +# Oriya Sinhalese Symbol Tamil Telugu Tibetan Vietnamese +# TODO: what is the Japanese 'UJIS' encoding seen in some Linuxes? # Map white space and _ to '-' define_alias( qr/^(\S+)[\s_]+(.*)$/i => '"$1-$2"' ); diff --git a/ext/Encode/Encode/iso8859-11.enc b/ext/Encode/Encode/iso8859-11.enc new file mode 100644 index 0000000..ea6ed4a --- /dev/null +++ b/ext/Encode/Encode/iso8859-11.enc @@ -0,0 +1,20 @@ +# Encoding file: iso8859-11, single-byte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diff --git a/ext/Encode/Encode/iso8859-11.ucm b/ext/Encode/Encode/iso8859-11.ucm new file mode 100644 index 0000000..e869852 --- /dev/null +++ b/ext/Encode/Encode/iso8859-11.ucm @@ -0,0 +1,265 @@ +# Written $Id$ +# ./compile -n iso-8859-11 -o Encode/iso8859-11.ucm Encode/iso8859-11.enc + "iso-8859-11" + 1 + 1 + \x3F +# +CHARMAP + \x00 |0 # + \x01 |0 # + \x02 |0 # + \x03 |0 # + \x04 |0 # + \x05 |0 # + \x06 |0 # + \x07 |0 # + \x08 |0 # + \x09 |0 # + \x0A |0 # + \x0B |0 # + \x0C |0 # + \x0D |0 # + \x0E |0 # + \x0F |0 # + \x10 |0 # + \x11 |0 # + \x12 |0 # + \x13 |0 # + \x14 |0 # + \x15 |0 # + \x16 |0 # + \x17 |0 # + \x18 |0 # + \x19 |0 # + \x1A |0 # + \x1B |0 # + \x1C |0 # + \x1D |0 # + \x1E |0 # + \x1F |0 # + \x20 |0 # SPACE + \x21 |0 # EXCLAMATION MARK + \x22 |0 # QUOTATION MARK + \x23 |0 # NUMBER SIGN + \x24 |0 # DOLLAR SIGN + \x25 |0 # PERCENT SIGN + \x26 |0 # AMPERSAND + \x27 |0 # APOSTROPHE + \x28 |0 # LEFT PARENTHESIS + \x29 |0 # RIGHT PARENTHESIS + \x2A |0 # ASTERISK + \x2B |0 # PLUS SIGN + \x2C |0 # COMMA + \x2D |0 # HYPHEN-MINUS + \x2E |0 # FULL STOP + \x2F |0 # SOLIDUS + \x30 |0 # DIGIT ZERO + \x31 |0 # DIGIT ONE + \x32 |0 # DIGIT TWO + \x33 |0 # DIGIT THREE + \x34 |0 # DIGIT FOUR + \x35 |0 # DIGIT FIVE + \x36 |0 # DIGIT SIX + \x37 |0 # DIGIT SEVEN + \x38 |0 # DIGIT EIGHT + \x39 |0 # DIGIT NINE + \x3A |0 # COLON + \x3B |0 # SEMICOLON + \x3C |0 # LESS-THAN SIGN + \x3D |0 # EQUALS SIGN + \x3E |0 # GREATER-THAN SIGN + \x3F |0 # QUESTION MARK + \x40 |0 # COMMERCIAL AT + \x41 |0 # LATIN CAPITAL LETTER A + \x42 |0 # LATIN CAPITAL LETTER B + \x43 |0 # LATIN CAPITAL LETTER C + \x44 |0 # LATIN CAPITAL LETTER D + \x45 |0 # LATIN CAPITAL LETTER E + \x46 |0 # LATIN CAPITAL LETTER F + \x47 |0 # LATIN CAPITAL LETTER G + \x48 |0 # LATIN CAPITAL LETTER H + \x49 |0 # LATIN CAPITAL LETTER I + \x4A |0 # LATIN CAPITAL LETTER J + \x4B |0 # LATIN CAPITAL LETTER K + \x4C |0 # LATIN CAPITAL LETTER L + \x4D |0 # LATIN CAPITAL LETTER M + \x4E |0 # LATIN CAPITAL LETTER N + \x4F |0 # LATIN CAPITAL LETTER O + \x50 |0 # LATIN CAPITAL LETTER P + \x51 |0 # LATIN CAPITAL LETTER Q + \x52 |0 # LATIN CAPITAL LETTER R + \x53 |0 # LATIN CAPITAL LETTER S + \x54 |0 # LATIN CAPITAL LETTER T + \x55 |0 # LATIN CAPITAL LETTER U + \x56 |0 # LATIN CAPITAL LETTER V + \x57 |0 # LATIN CAPITAL LETTER W + \x58 |0 # LATIN CAPITAL LETTER X + \x59 |0 # LATIN CAPITAL LETTER Y + \x5A |0 # LATIN CAPITAL LETTER Z + \x5B |0 # LEFT SQUARE BRACKET + \x5C |0 # REVERSE SOLIDUS + \x5D |0 # RIGHT SQUARE BRACKET + \x5E |0 # CIRCUMFLEX ACCENT + \x5F |0 # LOW LINE + \x60 |0 # GRAVE ACCENT + \x61 |0 # LATIN SMALL LETTER A + \x62 |0 # LATIN SMALL LETTER B + \x63 |0 # LATIN SMALL LETTER C + \x64 |0 # LATIN SMALL LETTER D + \x65 |0 # LATIN SMALL LETTER E + \x66 |0 # LATIN SMALL LETTER F + \x67 |0 # LATIN SMALL LETTER G + \x68 |0 # LATIN SMALL LETTER H + \x69 |0 # LATIN SMALL LETTER I + \x6A |0 # LATIN SMALL LETTER J + \x6B |0 # LATIN SMALL LETTER K + \x6C |0 # LATIN SMALL LETTER L + \x6D |0 # LATIN SMALL LETTER M + \x6E |0 # LATIN SMALL LETTER N + \x6F |0 # LATIN SMALL LETTER O + \x70 |0 # LATIN SMALL LETTER P + \x71 |0 # LATIN SMALL LETTER Q + \x72 |0 # LATIN SMALL LETTER R + \x73 |0 # LATIN SMALL LETTER S + \x74 |0 # LATIN SMALL LETTER T + \x75 |0 # LATIN SMALL LETTER U + \x76 |0 # LATIN SMALL LETTER V + \x77 |0 # LATIN SMALL LETTER W + \x78 |0 # LATIN SMALL LETTER X + \x79 |0 # LATIN SMALL LETTER Y + \x7A |0 # LATIN SMALL LETTER Z + \x7B |0 # LEFT CURLY BRACKET + \x7C |0 # VERTICAL LINE + \x7D |0 # RIGHT CURLY BRACKET + \x7E |0 # TILDE + \x7F |0 # + \x80 |0 # + \x81 |0 # + \x82 |0 # + \x83 |0 # + \x84 |0 # + \x85 |0 # + \x86 |0 # + \x87 |0 # + \x88 |0 # + \x89 |0 # + \x8A |0 # + \x8B |0 # + \x8C |0 # + \x8D |0 # + \x8E |0 # + \x8F |0 # + \x90 |0 # + \x91 |0 # + \x92 |0 # + \x93 |0 # + \x94 |0 # + \x95 |0 # + \x96 |0 # + \x97 |0 # + \x98 |0 # + \x99 |0 # + \x9A |0 # + \x9B |0 # + \x9C |0 # + \x9D |0 # + \x9E |0 # + \x9F |0 # + \xA0 |0 # NO-BREAK SPACE + \xA1 |0 # THAI CHARACTER KO KAI + \xA2 |0 # THAI CHARACTER KHO KHAI + \xA3 |0 # THAI CHARACTER KHO KHUAT + \xA4 |0 # THAI CHARACTER KHO KHWAI + \xA5 |0 # THAI CHARACTER KHO KHON + \xA6 |0 # THAI CHARACTER KHO RAKHANG + \xA7 |0 # THAI CHARACTER NGO NGU + \xA8 |0 # THAI CHARACTER CHO CHAN + \xA9 |0 # THAI CHARACTER CHO CHING + \xAA |0 # THAI CHARACTER CHO CHANG + \xAB |0 # THAI CHARACTER SO SO + \xAC |0 # THAI CHARACTER CHO CHOE + \xAD |0 # THAI CHARACTER YO YING + \xAE |0 # THAI CHARACTER DO CHADA + \xAF |0 # THAI CHARACTER TO PATAK + \xB0 |0 # THAI CHARACTER THO THAN + \xB1 |0 # THAI CHARACTER THO NANGMONTHO + \xB2 |0 # THAI CHARACTER THO PHUTHAO + \xB3 |0 # THAI CHARACTER NO NEN + \xB4 |0 # THAI CHARACTER DO DEK + \xB5 |0 # THAI CHARACTER TO TAO + \xB6 |0 # THAI CHARACTER THO THUNG + \xB7 |0 # THAI CHARACTER THO THAHAN + \xB8 |0 # THAI CHARACTER THO THONG + \xB9 |0 # THAI CHARACTER NO NU + \xBA |0 # THAI CHARACTER BO BAIMAI + \xBB |0 # THAI CHARACTER PO PLA + \xBC |0 # THAI CHARACTER PHO PHUNG + \xBD |0 # THAI CHARACTER FO FA + \xBE |0 # THAI CHARACTER PHO PHAN + \xBF |0 # THAI CHARACTER FO FAN + \xC0 |0 # THAI CHARACTER PHO SAMPHAO + \xC1 |0 # THAI CHARACTER MO MA + \xC2 |0 # THAI CHARACTER YO YAK + \xC3 |0 # THAI CHARACTER RO RUA + \xC4 |0 # THAI CHARACTER RU + \xC5 |0 # THAI CHARACTER LO LING + \xC6 |0 # THAI CHARACTER LU + \xC7 |0 # THAI CHARACTER WO WAEN + \xC8 |0 # THAI CHARACTER SO SALA + \xC9 |0 # THAI CHARACTER SO RUSI + \xCA |0 # THAI CHARACTER SO SUA + \xCB |0 # THAI CHARACTER HO HIP + \xCC |0 # THAI CHARACTER LO CHULA + \xCD |0 # THAI CHARACTER O ANG + \xCE |0 # THAI CHARACTER HO NOKHUK + \xCF |0 # THAI CHARACTER PAIYANNOI + \xD0 |0 # THAI CHARACTER SARA A + \xD1 |0 # THAI CHARACTER MAI HAN-AKAT + \xD2 |0 # THAI CHARACTER SARA AA + \xD3 |0 # THAI CHARACTER SARA AM + \xD4 |0 # THAI CHARACTER SARA I + \xD5 |0 # THAI CHARACTER SARA II + \xD6 |0 # THAI CHARACTER SARA UE + \xD7 |0 # THAI CHARACTER SARA UEE + \xD8 |0 # THAI CHARACTER SARA U + \xD9 |0 # THAI CHARACTER SARA UU + \xDA |0 # THAI CHARACTER PHINTHU + \xDB |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + \xDC |0 # LATIN CAPITAL LETTER U WITH DIAERESIS + \xDD |0 # LATIN CAPITAL LETTER Y WITH ACUTE + \xDE |0 # LATIN CAPITAL LETTER THORN + \xDF |0 # THAI CURRENCY SYMBOL BAHT + \xE0 |0 # THAI CHARACTER SARA E + \xE1 |0 # THAI CHARACTER SARA AE + \xE2 |0 # THAI CHARACTER SARA O + \xE3 |0 # THAI CHARACTER SARA AI MAIMUAN + \xE4 |0 # THAI CHARACTER SARA AI MAIMALAI + \xE5 |0 # THAI CHARACTER LAKKHANGYAO + \xE6 |0 # THAI CHARACTER MAIYAMOK + \xE7 |0 # THAI CHARACTER MAITAIKHU + \xE8 |0 # THAI CHARACTER MAI EK + \xE9 |0 # THAI CHARACTER MAI THO + \xEA |0 # THAI CHARACTER MAI TRI + \xEB |0 # THAI CHARACTER MAI CHATTAWA + \xEC |0 # THAI CHARACTER THANTHAKHAT + \xED |0 # THAI CHARACTER NIKHAHIT + \xEE |0 # THAI CHARACTER YAMAKKAN + \xEF |0 # THAI CHARACTER FONGMAN + \xF0 |0 # THAI DIGIT ZERO + \xF1 |0 # THAI DIGIT ONE + \xF2 |0 # THAI DIGIT TWO + \xF3 |0 # THAI DIGIT THREE + \xF4 |0 # THAI DIGIT FOUR + \xF5 |0 # THAI DIGIT FIVE + \xF6 |0 # THAI DIGIT SIX + \xF7 |0 # THAI DIGIT SEVEN + \xF8 |0 # THAI DIGIT EIGHT + \xF9 |0 # THAI DIGIT NINE + \xFA |0 # THAI CHARACTER ANGKHANKHU + \xFB |0 # THAI CHARACTER KHOMUT + \xFC |0 # LATIN SMALL LETTER U WITH DIAERESIS + \xFD |0 # LATIN SMALL LETTER Y WITH ACUTE + \xFE |0 # LATIN SMALL LETTER THORN + \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS +END CHARMAP diff --git a/ext/Encode/Encode/koi8-f.enc b/ext/Encode/Encode/koi8-f.enc new file mode 100644 index 0000000..14faabd --- /dev/null +++ b/ext/Encode/Encode/koi8-f.enc @@ -0,0 +1,20 @@ +# Encoding file: koi8-f, single-byte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diff --git a/ext/Encode/Encode/koi8-f.ucm b/ext/Encode/Encode/koi8-f.ucm new file mode 100644 index 0000000..0945072 --- /dev/null +++ b/ext/Encode/Encode/koi8-f.ucm @@ -0,0 +1,264 @@ +# Written $Id$ +# ./compile -n koi8-f -o Encode/koi8-f.ucm Encode/koi8-f.enc + "koi8-f" + 1 + 1 + \x3F +# +CHARMAP + \x00 |0 # + \x01 |0 # + \x02 |0 # + \x03 |0 # + \x04 |0 # + \x05 |0 # + \x06 |0 # + \x07 |0 # + \x08 |0 # + \x09 |0 # + \x0A |0 # + \x0B |0 # + \x0C |0 # + \x0D |0 # + \x0E |0 # + \x0F |0 # + \x10 |0 # + \x11 |0 # + \x12 |0 # + \x13 |0 # + \x14 |0 # + \x15 |0 # + \x16 |0 # + \x17 |0 # + \x18 |0 # + \x19 |0 # + \x1A |0 # + \x1B |0 # + \x1C |0 # + \x1D |0 # + \x1E |0 # + \x1F |0 # + \x20 |0 # SPACE + \x21 |0 # EXCLAMATION MARK + \x22 |0 # QUOTATION MARK + \x23 |0 # NUMBER SIGN + \x24 |0 # DOLLAR SIGN + \x25 |0 # PERCENT SIGN + \x26 |0 # AMPERSAND + \x27 |0 # APOSTROPHE + \x28 |0 # LEFT PARENTHESIS + \x29 |0 # RIGHT PARENTHESIS + \x2A |0 # ASTERISK + \x2B |0 # PLUS SIGN + \x2C |0 # COMMA + \x2D |0 # HYPHEN-MINUS + \x2E |0 # FULL STOP + \x2F |0 # SOLIDUS + \x30 |0 # DIGIT ZERO + \x31 |0 # DIGIT ONE + \x32 |0 # DIGIT TWO + \x33 |0 # DIGIT THREE + \x34 |0 # DIGIT FOUR + \x35 |0 # DIGIT FIVE + \x36 |0 # DIGIT SIX + \x37 |0 # DIGIT SEVEN + \x38 |0 # DIGIT EIGHT + \x39 |0 # DIGIT NINE + \x3A |0 # COLON + \x3B |0 # SEMICOLON + \x3C |0 # LESS-THAN SIGN + \x3D |0 # EQUALS SIGN + \x3E |0 # GREATER-THAN SIGN + \x3F |0 # QUESTION MARK + \x40 |0 # COMMERCIAL AT + \x41 |0 # LATIN CAPITAL LETTER A + \x42 |0 # LATIN CAPITAL LETTER B + \x43 |0 # LATIN CAPITAL LETTER C + \x44 |0 # LATIN CAPITAL LETTER D + \x45 |0 # LATIN CAPITAL LETTER E + \x46 |0 # LATIN CAPITAL LETTER F + \x47 |0 # LATIN CAPITAL LETTER G + \x48 |0 # LATIN CAPITAL LETTER H + \x49 |0 # LATIN CAPITAL LETTER I + \x4A |0 # LATIN CAPITAL LETTER J + \x4B |0 # LATIN CAPITAL LETTER K + \x4C |0 # LATIN CAPITAL LETTER L + \x4D |0 # LATIN CAPITAL LETTER M + \x4E |0 # LATIN CAPITAL LETTER N + \x4F |0 # LATIN CAPITAL LETTER O + \x50 |0 # LATIN CAPITAL LETTER P + \x51 |0 # LATIN CAPITAL LETTER Q + \x52 |0 # LATIN CAPITAL LETTER R + \x53 |0 # LATIN CAPITAL LETTER S + \x54 |0 # LATIN CAPITAL LETTER T + \x55 |0 # LATIN CAPITAL LETTER U + \x56 |0 # LATIN CAPITAL LETTER V + \x57 |0 # LATIN CAPITAL LETTER W + \x58 |0 # LATIN CAPITAL LETTER X + \x59 |0 # LATIN CAPITAL LETTER Y + \x5A |0 # LATIN CAPITAL LETTER Z + \x5B |0 # LEFT SQUARE BRACKET + \x5C |0 # REVERSE SOLIDUS + \x5D |0 # RIGHT SQUARE BRACKET + \x5E |0 # CIRCUMFLEX ACCENT + \x5F |0 # LOW LINE + \x60 |0 # GRAVE ACCENT + \x61 |0 # LATIN SMALL LETTER A + \x62 |0 # LATIN SMALL LETTER B + \x63 |0 # LATIN SMALL LETTER C + \x64 |0 # LATIN SMALL LETTER D + \x65 |0 # LATIN SMALL LETTER E + \x66 |0 # LATIN SMALL LETTER F + \x67 |0 # LATIN SMALL LETTER G + \x68 |0 # LATIN SMALL LETTER H + \x69 |0 # LATIN SMALL LETTER I + \x6A |0 # LATIN SMALL LETTER J + \x6B |0 # LATIN SMALL LETTER K + \x6C |0 # LATIN SMALL LETTER L + \x6D |0 # LATIN SMALL LETTER M + \x6E |0 # LATIN SMALL LETTER N + \x6F |0 # LATIN SMALL LETTER O + \x70 |0 # LATIN SMALL LETTER P + \x71 |0 # LATIN SMALL LETTER Q + \x72 |0 # LATIN SMALL LETTER R + \x73 |0 # LATIN SMALL LETTER S + \x74 |0 # LATIN SMALL LETTER T + \x75 |0 # LATIN SMALL LETTER U + \x76 |0 # LATIN SMALL LETTER V + \x77 |0 # LATIN SMALL LETTER W + \x78 |0 # LATIN SMALL LETTER X + \x79 |0 # LATIN SMALL LETTER Y + \x7A |0 # LATIN SMALL LETTER Z + \x7B |0 # LEFT CURLY BRACKET + \x7C |0 # VERTICAL LINE + \x7D |0 # RIGHT CURLY BRACKET + \x7E |0 # TILDE + \x7F |0 # + \x80 |0 # BOX DRAWINGS LIGHT HORIZONTAL + \x81 |0 # BOX DRAWINGS LIGHT VERTICAL + \x82 |0 # BOX DRAWINGS LIGHT DOWN AND RIGHT + \x83 |0 # BOX DRAWINGS LIGHT DOWN AND LEFT + \x84 |0 # BOX DRAWINGS LIGHT UP AND RIGHT + \x85 |0 # BOX DRAWINGS LIGHT UP AND LEFT + \x86 |0 # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + \x87 |0 # BOX DRAWINGS LIGHT VERTICAL AND LEFT + \x88 |0 # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + \x89 |0 # BOX DRAWINGS LIGHT UP AND HORIZONTAL + \x8A |0 # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + \x8B |0 # UPPER HALF BLOCK + \x8C |0 # LOWER HALF BLOCK + \x8D |0 # FULL BLOCK + \x8E |0 # LEFT HALF BLOCK + \x8F |0 # RIGHT HALF BLOCK + \x90 |0 # LIGHT SHADE + \x91 |0 # LEFT SINGLE QUOTATION MARK + \x92 |0 # RIGHT SINGLE QUOTATION MARK + \x93 |0 # LEFT DOUBLE QUOTATION MARK + \x94 |0 # RIGHT DOUBLE QUOTATION MARK + \x95 |0 # BULLET + \x96 |0 # EN DASH + \x97 |0 # EM DASH + \x98 |0 # COPYRIGHT SIGN + \x99 |0 # TRADE MARK SIGN + \x9B |0 # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + \x9C |0 # REGISTERED SIGN + \x9D |0 # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + \x9E |0 # MIDDLE DOT + \x9F |0 # CURRENCY SIGN + \xA0 |0 # NO-BREAK SPACE + \xA1 |0 # CYRILLIC SMALL LETTER DJE + \xA2 |0 # CYRILLIC SMALL LETTER GJE + \xA3 |0 # CYRILLIC SMALL LETTER IO + \xA4 |0 # CYRILLIC SMALL LETTER UKRAINIAN IE + \xA5 |0 # CYRILLIC SMALL LETTER DZE + \xA6 |0 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + \xA7 |0 # CYRILLIC SMALL LETTER YI + \xA8 |0 # CYRILLIC SMALL LETTER JE + \xA9 |0 # CYRILLIC SMALL LETTER LJE + \xAA |0 # CYRILLIC SMALL LETTER NJE + \xAB |0 # CYRILLIC SMALL LETTER TSHE + \xAC |0 # CYRILLIC SMALL LETTER KJE + \xAD |0 # CYRILLIC SMALL LETTER GHE WITH UPTURN + \xAE |0 # CYRILLIC SMALL LETTER SHORT U + \xAF |0 # CYRILLIC SMALL LETTER DZHE + \xB0 |0 # NUMERO SIGN + \xB1 |0 # CYRILLIC CAPITAL LETTER DJE + \xB2 |0 # CYRILLIC CAPITAL LETTER GJE + \xB3 |0 # CYRILLIC CAPITAL LETTER IO + \xB4 |0 # CYRILLIC CAPITAL LETTER UKRAINIAN IE + \xB5 |0 # CYRILLIC CAPITAL LETTER DZE + \xB6 |0 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + \xB7 |0 # CYRILLIC CAPITAL LETTER YI + \xB8 |0 # CYRILLIC CAPITAL LETTER JE + \xB9 |0 # CYRILLIC CAPITAL LETTER LJE + \xBA |0 # CYRILLIC CAPITAL LETTER NJE + \xBB |0 # CYRILLIC CAPITAL LETTER TSHE + \xBC |0 # CYRILLIC CAPITAL LETTER KJE + \xBD |0 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN + \xBE |0 # CYRILLIC CAPITAL LETTER SHORT U + \xBF |0 # CYRILLIC CAPITAL LETTER DZHE + \xC0 |0 # CYRILLIC SMALL LETTER YU + \xC1 |0 # CYRILLIC SMALL LETTER A + \xC2 |0 # CYRILLIC SMALL LETTER BE + \xC3 |0 # CYRILLIC SMALL LETTER TSE + \xC4 |0 # CYRILLIC SMALL LETTER DE + \xC5 |0 # CYRILLIC SMALL LETTER IE + \xC6 |0 # CYRILLIC SMALL LETTER EF + \xC7 |0 # CYRILLIC SMALL LETTER GHE + \xC8 |0 # CYRILLIC SMALL LETTER HA + \xC9 |0 # CYRILLIC SMALL LETTER I + \xCA |0 # CYRILLIC SMALL LETTER SHORT I + \xCB |0 # CYRILLIC SMALL LETTER KA + \xCC |0 # CYRILLIC SMALL LETTER EL + \xCD |0 # CYRILLIC SMALL LETTER EM + \xCE |0 # CYRILLIC SMALL LETTER EN + \xCF |0 # CYRILLIC SMALL LETTER O + \xD0 |0 # CYRILLIC SMALL LETTER PE + \xD1 |0 # CYRILLIC SMALL LETTER YA + \xD2 |0 # CYRILLIC SMALL LETTER ER + \xD3 |0 # CYRILLIC SMALL LETTER ES + \xD4 |0 # CYRILLIC SMALL LETTER TE + \xD5 |0 # CYRILLIC SMALL LETTER U + \xD6 |0 # CYRILLIC SMALL LETTER ZHE + \xD7 |0 # CYRILLIC SMALL LETTER VE + \xD8 |0 # CYRILLIC SMALL LETTER SOFT SIGN + \xD9 |0 # CYRILLIC SMALL LETTER YERU + \xDA |0 # CYRILLIC SMALL LETTER ZE + \xDB |0 # CYRILLIC SMALL LETTER SHA + \xDC |0 # CYRILLIC SMALL LETTER E + \xDD |0 # CYRILLIC SMALL LETTER SHCHA + \xDE |0 # CYRILLIC SMALL LETTER CHE + \xDF |0 # CYRILLIC SMALL LETTER HARD SIGN + \xE0 |0 # CYRILLIC CAPITAL LETTER YU + \xE1 |0 # CYRILLIC CAPITAL LETTER A + \xE2 |0 # CYRILLIC CAPITAL LETTER BE + \xE3 |0 # CYRILLIC CAPITAL LETTER TSE + \xE4 |0 # CYRILLIC CAPITAL LETTER DE + \xE5 |0 # CYRILLIC CAPITAL LETTER IE + \xE6 |0 # CYRILLIC CAPITAL LETTER EF + \xE7 |0 # CYRILLIC CAPITAL LETTER GHE + \xE8 |0 # CYRILLIC CAPITAL LETTER HA + \xE9 |0 # CYRILLIC CAPITAL LETTER I + \xEA |0 # CYRILLIC CAPITAL LETTER SHORT I + \xEB |0 # CYRILLIC CAPITAL LETTER KA + \xEC |0 # CYRILLIC CAPITAL LETTER EL + \xED |0 # CYRILLIC CAPITAL LETTER EM + \xEE |0 # CYRILLIC CAPITAL LETTER EN + \xEF |0 # CYRILLIC CAPITAL LETTER O + \xF0 |0 # CYRILLIC CAPITAL LETTER PE + \xF1 |0 # CYRILLIC CAPITAL LETTER YA + \xF2 |0 # CYRILLIC CAPITAL LETTER ER + \xF3 |0 # CYRILLIC CAPITAL LETTER ES + \xF4 |0 # CYRILLIC CAPITAL LETTER TE + \xF5 |0 # CYRILLIC CAPITAL LETTER U + \xF6 |0 # CYRILLIC CAPITAL LETTER ZHE + \xF7 |0 # CYRILLIC CAPITAL LETTER VE + \xF8 |0 # CYRILLIC CAPITAL LETTER SOFT SIGN + \xF9 |0 # CYRILLIC CAPITAL LETTER YERU + \xFA |0 # CYRILLIC CAPITAL LETTER ZE + \xFB |0 # CYRILLIC CAPITAL LETTER SHA + \xFC |0 # CYRILLIC CAPITAL LETTER E + \xFD |0 # CYRILLIC CAPITAL LETTER SHCHA + \xFE |0 # CYRILLIC CAPITAL LETTER CHE + \xFF |0 # CYRILLIC CAPITAL LETTER HARD SIGN +END CHARMAP diff --git a/ext/Encode/Encode/koi8-u.enc b/ext/Encode/Encode/koi8-u.enc new file mode 100644 index 0000000..e1f90c4 --- /dev/null +++ b/ext/Encode/Encode/koi8-u.enc @@ -0,0 +1,20 @@ +# Encoding file: koi8-u, single-byte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diff --git a/ext/Encode/Encode/koi8-u.ucm b/ext/Encode/Encode/koi8-u.ucm new file mode 100644 index 0000000..bfc0ec7 --- /dev/null +++ b/ext/Encode/Encode/koi8-u.ucm @@ -0,0 +1,265 @@ +# Written $Id$ +# ./compile -n koi8-u -o Encode/koi8-u.ucm Encode/koi8-u.enc + "koi8-u" + 1 + 1 + \x3F +# +CHARMAP + \x00 |0 # + \x01 |0 # + \x02 |0 # + \x03 |0 # + \x04 |0 # + \x05 |0 # + \x06 |0 # + \x07 |0 # + \x08 |0 # + \x09 |0 # + \x0A |0 # + \x0B |0 # + \x0C |0 # + \x0D |0 # + \x0E |0 # + \x0F |0 # + \x10 |0 # + \x11 |0 # + \x12 |0 # + \x13 |0 # + \x14 |0 # + \x15 |0 # + \x16 |0 # + \x17 |0 # + \x18 |0 # + \x19 |0 # + \x1A |0 # + \x1B |0 # + \x1C |0 # + \x1D |0 # + \x1E |0 # + \x1F |0 # + \x20 |0 # SPACE + \x21 |0 # EXCLAMATION MARK + \x22 |0 # QUOTATION MARK + \x23 |0 # NUMBER SIGN + \x24 |0 # DOLLAR SIGN + \x25 |0 # PERCENT SIGN + \x26 |0 # AMPERSAND + \x27 |0 # APOSTROPHE + \x28 |0 # LEFT PARENTHESIS + \x29 |0 # RIGHT PARENTHESIS + \x2A |0 # ASTERISK + \x2B |0 # PLUS SIGN + \x2C |0 # COMMA + \x2D |0 # HYPHEN-MINUS + \x2E |0 # FULL STOP + \x2F |0 # SOLIDUS + \x30 |0 # DIGIT ZERO + \x31 |0 # DIGIT ONE + \x32 |0 # DIGIT TWO + \x33 |0 # DIGIT THREE + \x34 |0 # DIGIT FOUR + \x35 |0 # DIGIT FIVE + \x36 |0 # DIGIT SIX + \x37 |0 # DIGIT SEVEN + \x38 |0 # DIGIT EIGHT + \x39 |0 # DIGIT NINE + \x3A |0 # COLON + \x3B |0 # SEMICOLON + \x3C |0 # LESS-THAN SIGN + \x3D |0 # EQUALS SIGN + \x3E |0 # GREATER-THAN SIGN + \x3F |0 # QUESTION MARK + \x40 |0 # COMMERCIAL AT + \x41 |0 # LATIN CAPITAL LETTER A + \x42 |0 # LATIN CAPITAL LETTER B + \x43 |0 # LATIN CAPITAL LETTER C + \x44 |0 # LATIN CAPITAL LETTER D + \x45 |0 # LATIN CAPITAL LETTER E + \x46 |0 # LATIN CAPITAL LETTER F + \x47 |0 # LATIN CAPITAL LETTER G + \x48 |0 # LATIN CAPITAL LETTER H + \x49 |0 # LATIN CAPITAL LETTER I + \x4A |0 # LATIN CAPITAL LETTER J + \x4B |0 # LATIN CAPITAL LETTER K + \x4C |0 # LATIN CAPITAL LETTER L + \x4D |0 # LATIN CAPITAL LETTER M + \x4E |0 # LATIN CAPITAL LETTER N + \x4F |0 # LATIN CAPITAL LETTER O + \x50 |0 # LATIN CAPITAL LETTER P + \x51 |0 # LATIN CAPITAL LETTER Q + \x52 |0 # LATIN CAPITAL LETTER R + \x53 |0 # LATIN CAPITAL LETTER S + \x54 |0 # LATIN CAPITAL LETTER T + \x55 |0 # LATIN CAPITAL LETTER U + \x56 |0 # LATIN CAPITAL LETTER V + \x57 |0 # LATIN CAPITAL LETTER W + \x58 |0 # LATIN CAPITAL LETTER X + \x59 |0 # LATIN CAPITAL LETTER Y + \x5A |0 # LATIN CAPITAL LETTER Z + \x5B |0 # LEFT SQUARE BRACKET + \x5C |0 # REVERSE SOLIDUS + \x5D |0 # RIGHT SQUARE BRACKET + \x5E |0 # CIRCUMFLEX ACCENT + \x5F |0 # LOW LINE + \x60 |0 # GRAVE ACCENT + \x61 |0 # LATIN SMALL LETTER A + \x62 |0 # LATIN SMALL LETTER B + \x63 |0 # LATIN SMALL LETTER C + \x64 |0 # LATIN SMALL LETTER D + \x65 |0 # LATIN SMALL LETTER E + \x66 |0 # LATIN SMALL LETTER F + \x67 |0 # LATIN SMALL LETTER G + \x68 |0 # LATIN SMALL LETTER H + \x69 |0 # LATIN SMALL LETTER I + \x6A |0 # LATIN SMALL LETTER J + \x6B |0 # LATIN SMALL LETTER K + \x6C |0 # LATIN SMALL LETTER L + \x6D |0 # LATIN SMALL LETTER M + \x6E |0 # LATIN SMALL LETTER N + \x6F |0 # LATIN SMALL LETTER O + \x70 |0 # LATIN SMALL LETTER P + \x71 |0 # LATIN SMALL LETTER Q + \x72 |0 # LATIN SMALL LETTER R + \x73 |0 # LATIN SMALL LETTER S + \x74 |0 # LATIN SMALL LETTER T + \x75 |0 # LATIN SMALL LETTER U + \x76 |0 # LATIN SMALL LETTER V + \x77 |0 # LATIN SMALL LETTER W + \x78 |0 # LATIN SMALL LETTER X + \x79 |0 # LATIN SMALL LETTER Y + \x7A |0 # LATIN SMALL LETTER Z + \x7B |0 # LEFT CURLY BRACKET + \x7C |0 # VERTICAL LINE + \x7D |0 # RIGHT CURLY BRACKET + \x7E |0 # TILDE + \x7F |0 # + \x80 |0 # BOX DRAWINGS LIGHT HORIZONTAL + \x81 |0 # BOX DRAWINGS LIGHT VERTICAL + \x82 |0 # BOX DRAWINGS LIGHT DOWN AND RIGHT + \x83 |0 # BOX DRAWINGS LIGHT DOWN AND LEFT + \x84 |0 # BOX DRAWINGS LIGHT UP AND RIGHT + \x85 |0 # BOX DRAWINGS LIGHT UP AND LEFT + \x86 |0 # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + \x87 |0 # BOX DRAWINGS LIGHT VERTICAL AND LEFT + \x88 |0 # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + \x89 |0 # BOX DRAWINGS LIGHT UP AND HORIZONTAL + \x8A |0 # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + \x8B |0 # UPPER HALF BLOCK + \x8C |0 # LOWER HALF BLOCK + \x8D |0 # FULL BLOCK + \x8E |0 # LEFT HALF BLOCK + \x8F |0 # RIGHT HALF BLOCK + \x90 |0 # LIGHT SHADE + \x91 |0 # MEDIUM SHADE + \x92 |0 # DARK SHADE + \x93 |0 # TOP HALF INTEGRAL + \x94 |0 # BLACK SQUARE + \x95 |0 # BULLET + \x96 |0 # SQUARE ROOT + \x97 |0 # ALMOST EQUAL TO + \x98 |0 # LESS-THAN OR EQUAL TO + \x99 |0 # GREATER-THAN OR EQUAL TO + \x9A |0 # NO-BREAK SPACE + \x9B |0 # BOTTOM HALF INTEGRAL + \x9C |0 # DEGREE SIGN + \x9D |0 # SUPERSCRIPT TWO + \x9E |0 # MIDDLE DOT + \x9F |0 # DIVISION SIGN + \xA0 |0 # BOX DRAWINGS DOUBLE HORIZONTAL + \xA1 |0 # BOX DRAWINGS DOUBLE VERTICAL + \xA2 |0 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + \xA3 |0 # CYRILLIC SMALL LETTER IO + \xA4 |0 # CYRILLIC SMALL LETTER UKRAINIAN IE + \xA5 |0 # BOX DRAWINGS DOUBLE DOWN AND RIGHT + \xA6 |0 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + \xA7 |0 # CYRILLIC SMALL LETTER YI + \xA8 |0 # BOX DRAWINGS DOUBLE DOWN AND LEFT + \xA9 |0 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + \xAA |0 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + \xAB |0 # BOX DRAWINGS DOUBLE UP AND RIGHT + \xAC |0 # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + \xAD |0 # CYRILLIC SMALL LETTER GHE WITH UPTURN + \xAE |0 # BOX DRAWINGS DOUBLE UP AND LEFT + \xAF |0 # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + \xB0 |0 # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + \xB1 |0 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + \xB2 |0 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + \xB3 |0 # CYRILLIC CAPITAL LETTER IO + \xB4 |0 # CYRILLIC CAPITAL LETTER UKRAINIAN IE + \xB5 |0 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + \xB6 |0 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + \xB7 |0 # CYRILLIC CAPITAL LETTER YI + \xB8 |0 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + \xB9 |0 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + \xBA |0 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + \xBB |0 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + \xBC |0 # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + \xBD |0 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN + \xBE |0 # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + \xBF |0 # COPYRIGHT SIGN + \xC0 |0 # CYRILLIC SMALL LETTER YU + \xC1 |0 # CYRILLIC SMALL LETTER A + \xC2 |0 # CYRILLIC SMALL LETTER BE + \xC3 |0 # CYRILLIC SMALL LETTER TSE + \xC4 |0 # CYRILLIC SMALL LETTER DE + \xC5 |0 # CYRILLIC SMALL LETTER IE + \xC6 |0 # CYRILLIC SMALL LETTER EF + \xC7 |0 # CYRILLIC SMALL LETTER GHE + \xC8 |0 # CYRILLIC SMALL LETTER HA + \xC9 |0 # CYRILLIC SMALL LETTER I + \xCA |0 # CYRILLIC SMALL LETTER SHORT I + \xCB |0 # CYRILLIC SMALL LETTER KA + \xCC |0 # CYRILLIC SMALL LETTER EL + \xCD |0 # CYRILLIC SMALL LETTER EM + \xCE |0 # CYRILLIC SMALL LETTER EN + \xCF |0 # CYRILLIC SMALL LETTER O + \xD0 |0 # CYRILLIC SMALL LETTER PE + \xD1 |0 # CYRILLIC SMALL LETTER YA + \xD2 |0 # CYRILLIC SMALL LETTER ER + \xD3 |0 # CYRILLIC SMALL LETTER ES + \xD4 |0 # CYRILLIC SMALL LETTER TE + \xD5 |0 # CYRILLIC SMALL LETTER U + \xD6 |0 # CYRILLIC SMALL LETTER ZHE + \xD7 |0 # CYRILLIC SMALL LETTER VE + \xD8 |0 # CYRILLIC SMALL LETTER SOFT SIGN + \xD9 |0 # CYRILLIC SMALL LETTER YERU + \xDA |0 # CYRILLIC SMALL LETTER ZE + \xDB |0 # CYRILLIC SMALL LETTER SHA + \xDC |0 # CYRILLIC SMALL LETTER E + \xDD |0 # CYRILLIC SMALL LETTER SHCHA + \xDE |0 # CYRILLIC SMALL LETTER CHE + \xDF |0 # CYRILLIC SMALL LETTER HARD SIGN + \xE0 |0 # CYRILLIC CAPITAL LETTER YU + \xE1 |0 # CYRILLIC CAPITAL LETTER A + \xE2 |0 # CYRILLIC CAPITAL LETTER BE + \xE3 |0 # CYRILLIC CAPITAL LETTER TSE + \xE4 |0 # CYRILLIC CAPITAL LETTER DE + \xE5 |0 # CYRILLIC CAPITAL LETTER IE + \xE6 |0 # CYRILLIC CAPITAL LETTER EF + \xE7 |0 # CYRILLIC CAPITAL LETTER GHE + \xE8 |0 # CYRILLIC CAPITAL LETTER HA + \xE9 |0 # CYRILLIC CAPITAL LETTER I + \xEA |0 # CYRILLIC CAPITAL LETTER SHORT I + \xEB |0 # CYRILLIC CAPITAL LETTER KA + \xEC |0 # CYRILLIC CAPITAL LETTER EL + \xED |0 # CYRILLIC CAPITAL LETTER EM + \xEE |0 # CYRILLIC CAPITAL LETTER EN + \xEF |0 # CYRILLIC CAPITAL LETTER O + \xF0 |0 # CYRILLIC CAPITAL LETTER PE + \xF1 |0 # CYRILLIC CAPITAL LETTER YA + \xF2 |0 # CYRILLIC CAPITAL LETTER ER + \xF3 |0 # CYRILLIC CAPITAL LETTER ES + \xF4 |0 # CYRILLIC CAPITAL LETTER TE + \xF5 |0 # CYRILLIC CAPITAL LETTER U + \xF6 |0 # CYRILLIC CAPITAL LETTER ZHE + \xF7 |0 # CYRILLIC CAPITAL LETTER VE + \xF8 |0 # CYRILLIC CAPITAL LETTER SOFT SIGN + \xF9 |0 # CYRILLIC CAPITAL LETTER YERU + \xFA |0 # CYRILLIC CAPITAL LETTER ZE + \xFB |0 # CYRILLIC CAPITAL LETTER SHA + \xFC |0 # CYRILLIC CAPITAL LETTER E + \xFD |0 # CYRILLIC CAPITAL LETTER SHCHA + \xFE |0 # CYRILLIC CAPITAL LETTER CHE + \xFF |0 # CYRILLIC CAPITAL LETTER HARD SIGN +END CHARMAP diff --git a/ext/Encode/Encode/nextstep.enc b/ext/Encode/Encode/nextstep.enc new file mode 100644 index 0000000..3361e2a --- /dev/null +++ b/ext/Encode/Encode/nextstep.enc @@ -0,0 +1,20 @@ +# Encoding file: nextstep, single-byte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diff --git a/ext/Encode/Encode/nextstep.ucm b/ext/Encode/Encode/nextstep.ucm new file mode 100644 index 0000000..6e73ace --- /dev/null +++ b/ext/Encode/Encode/nextstep.ucm @@ -0,0 +1,263 @@ +# Written $Id$ +# ./compile -n nextstep -o Encode/nextstep.ucm Encode/nextstep.enc + "nextstep" + 1 + 1 + \x3F +# +CHARMAP + \x00 |0 # + \x01 |0 # + \x02 |0 # + \x03 |0 # + \x04 |0 # + \x05 |0 # + \x06 |0 # + \x07 |0 # + \x08 |0 # + \x09 |0 # + \x0A |0 # + \x0B |0 # + \x0C |0 # + \x0D |0 # + \x0E |0 # + \x0F |0 # + \x10 |0 # + \x11 |0 # + \x12 |0 # + \x13 |0 # + \x14 |0 # + \x15 |0 # + \x16 |0 # + \x17 |0 # + \x18 |0 # + \x19 |0 # + \x1A |0 # + \x1B |0 # + \x1C |0 # + \x1D |0 # + \x1E |0 # + \x1F |0 # + \x20 |0 # SPACE + \x21 |0 # EXCLAMATION MARK + \x22 |0 # QUOTATION MARK + \x23 |0 # NUMBER SIGN + \x24 |0 # DOLLAR SIGN + \x25 |0 # PERCENT SIGN + \x26 |0 # AMPERSAND + \x27 |0 # APOSTROPHE + \x28 |0 # LEFT PARENTHESIS + \x29 |0 # RIGHT PARENTHESIS + \x2A |0 # ASTERISK + \x2B |0 # PLUS SIGN + \x2C |0 # COMMA + \x2D |0 # HYPHEN-MINUS + \x2E |0 # FULL STOP + \x2F |0 # SOLIDUS + \x30 |0 # DIGIT ZERO + \x31 |0 # DIGIT ONE + \x32 |0 # DIGIT TWO + \x33 |0 # DIGIT THREE + \x34 |0 # DIGIT FOUR + \x35 |0 # DIGIT FIVE + \x36 |0 # DIGIT SIX + \x37 |0 # DIGIT SEVEN + \x38 |0 # DIGIT EIGHT + \x39 |0 # DIGIT NINE + \x3A |0 # COLON + \x3B |0 # SEMICOLON + \x3C |0 # LESS-THAN SIGN + \x3D |0 # EQUALS SIGN + \x3E |0 # GREATER-THAN SIGN + \x3F |0 # QUESTION MARK + \x40 |0 # COMMERCIAL AT + \x41 |0 # LATIN CAPITAL LETTER A + \x42 |0 # LATIN CAPITAL LETTER B + \x43 |0 # LATIN CAPITAL LETTER C + \x44 |0 # LATIN CAPITAL LETTER D + \x45 |0 # LATIN CAPITAL LETTER E + \x46 |0 # LATIN CAPITAL LETTER F + \x47 |0 # LATIN CAPITAL LETTER G + \x48 |0 # LATIN CAPITAL LETTER H + \x49 |0 # LATIN CAPITAL LETTER I + \x4A |0 # LATIN CAPITAL LETTER J + \x4B |0 # LATIN CAPITAL LETTER K + \x4C |0 # LATIN CAPITAL LETTER L + \x4D |0 # LATIN CAPITAL LETTER M + \x4E |0 # LATIN CAPITAL LETTER N + \x4F |0 # LATIN CAPITAL LETTER O + \x50 |0 # LATIN CAPITAL LETTER P + \x51 |0 # LATIN CAPITAL LETTER Q + \x52 |0 # LATIN CAPITAL LETTER R + \x53 |0 # LATIN CAPITAL LETTER S + \x54 |0 # LATIN CAPITAL LETTER T + \x55 |0 # LATIN CAPITAL LETTER U + \x56 |0 # LATIN CAPITAL LETTER V + \x57 |0 # LATIN CAPITAL LETTER W + \x58 |0 # LATIN CAPITAL LETTER X + \x59 |0 # LATIN CAPITAL LETTER Y + \x5A |0 # LATIN CAPITAL LETTER Z + \x5B |0 # LEFT SQUARE BRACKET + \x5C |0 # REVERSE SOLIDUS + \x5D |0 # RIGHT SQUARE BRACKET + \x5E |0 # CIRCUMFLEX ACCENT + \x5F |0 # LOW LINE + \x60 |0 # GRAVE ACCENT + \x61 |0 # LATIN SMALL LETTER A + \x62 |0 # LATIN SMALL LETTER B + \x63 |0 # LATIN SMALL LETTER C + \x64 |0 # LATIN SMALL LETTER D + \x65 |0 # LATIN SMALL LETTER E + \x66 |0 # LATIN SMALL LETTER F + \x67 |0 # LATIN SMALL LETTER G + \x68 |0 # LATIN SMALL LETTER H + \x69 |0 # LATIN SMALL LETTER I + \x6A |0 # LATIN SMALL LETTER J + \x6B |0 # LATIN SMALL LETTER K + \x6C |0 # LATIN SMALL LETTER L + \x6D |0 # LATIN SMALL LETTER M + \x6E |0 # LATIN SMALL LETTER N + \x6F |0 # LATIN SMALL LETTER O + \x70 |0 # LATIN SMALL LETTER P + \x71 |0 # LATIN SMALL LETTER Q + \x72 |0 # LATIN SMALL LETTER R + \x73 |0 # LATIN SMALL LETTER S + \x74 |0 # LATIN SMALL LETTER T + \x75 |0 # LATIN SMALL LETTER U + \x76 |0 # LATIN SMALL LETTER V + \x77 |0 # LATIN SMALL LETTER W + \x78 |0 # LATIN SMALL LETTER X + \x79 |0 # LATIN SMALL LETTER Y + \x7A |0 # LATIN SMALL LETTER Z + \x7B |0 # LEFT CURLY BRACKET + \x7C |0 # VERTICAL LINE + \x7D |0 # RIGHT CURLY BRACKET + \x7E |0 # TILDE + \x7F |0 # + \x80 |0 # NO-BREAK SPACE + \x81 |0 # LATIN CAPITAL LETTER A WITH GRAVE + \x82 |0 # LATIN CAPITAL LETTER A WITH ACUTE + \x83 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + \x84 |0 # LATIN CAPITAL LETTER A WITH TILDE + \x85 |0 # LATIN CAPITAL LETTER A WITH DIAERESIS + \x86 |0 # LATIN CAPITAL LETTER A WITH RING ABOVE + \x87 |0 # LATIN CAPITAL LETTER C WITH CEDILLA + \x88 |0 # LATIN CAPITAL LETTER E WITH GRAVE + \x89 |0 # LATIN CAPITAL LETTER E WITH ACUTE + \x8A |0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + \x8B |0 # LATIN CAPITAL LETTER E WITH DIAERESIS + \x8C |0 # LATIN CAPITAL LETTER I WITH GRAVE + \x8D |0 # LATIN CAPITAL LETTER I WITH ACUTE + \x8E |0 # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + \x8F |0 # LATIN CAPITAL LETTER I WITH DIAERESIS + \x90 |0 # LATIN CAPITAL LETTER ETH + \x91 |0 # LATIN CAPITAL LETTER N WITH TILDE + \x92 |0 # LATIN CAPITAL LETTER O WITH GRAVE + \x93 |0 # LATIN CAPITAL LETTER O WITH ACUTE + \x94 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + \x95 |0 # LATIN CAPITAL LETTER O WITH TILDE + \x96 |0 # LATIN CAPITAL LETTER O WITH DIAERESIS + \x97 |0 # LATIN CAPITAL LETTER U WITH GRAVE + \x98 |0 # LATIN CAPITAL LETTER U WITH ACUTE + \x99 |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + \x9A |0 # LATIN CAPITAL LETTER U WITH DIAERESIS + \x9B |0 # LATIN CAPITAL LETTER Y WITH ACUTE + \x9C |0 # LATIN CAPITAL LETTER THORN + \x9D |0 # MICRO SIGN + \x9E |0 # MULTIPLICATION SIGN + \x9F |0 # DIVISION SIGN + \xA0 |0 # COPYRIGHT SIGN + \xA1 |0 # INVERTED EXCLAMATION MARK + \xA2 |0 # CENT SIGN + \xA3 |0 # POUND SIGN + \xA4 |0 # FRACTION SLASH + \xA5 |0 # YEN SIGN + \xA6 |0 # LATIN SMALL LETTER F WITH HOOK + \xA7 |0 # SECTION SIGN + \xA8 |0 # CURRENCY SIGN + \xA9 |0 # RIGHT SINGLE QUOTATION MARK + \xAA |0 # LEFT DOUBLE QUOTATION MARK + \xAB |0 # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + \xAC |0 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + \xAD |0 # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + \xAE |0 # LATIN SMALL LIGATURE FI + \xAF |0 # LATIN SMALL LIGATURE FL + \xB0 |0 # REGISTERED SIGN + \xB1 |0 # EN DASH + \xB2 |0 # DAGGER + \xB3 |0 # DOUBLE DAGGER + \xB4 |0 # MIDDLE DOT + \xB5 |0 # BROKEN BAR + \xB6 |0 # PILCROW SIGN + \xB7 |0 # BULLET + \xB8 |0 # SINGLE LOW-9 QUOTATION MARK + \xB9 |0 # DOUBLE LOW-9 QUOTATION MARK + \xBA |0 # RIGHT DOUBLE QUOTATION MARK + \xBB |0 # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + \xBC |0 # HORIZONTAL ELLIPSIS + \xBD |0 # PER MILLE SIGN + \xBE |0 # NOT SIGN + \xBF |0 # INVERTED QUESTION MARK + \xC0 |0 # SUPERSCRIPT ONE + \xC1 |0 # MODIFIER LETTER GRAVE ACCENT + \xC2 |0 # ACUTE ACCENT + \xC3 |0 # MODIFIER LETTER CIRCUMFLEX ACCENT + \xC4 |0 # SMALL TILDE + \xC5 |0 # MACRON + \xC6 |0 # BREVE + \xC7 |0 # DOT ABOVE + \xC8 |0 # DIAERESIS + \xC9 |0 # SUPERSCRIPT TWO + \xCA |0 # RING ABOVE + \xCB |0 # CEDILLA + \xCC |0 # SUPERSCRIPT THREE + \xCD |0 # DOUBLE ACUTE ACCENT + \xCE |0 # OGONEK + \xCF |0 # CARON + \xD0 |0 # EM DASH + \xD1 |0 # PLUS-MINUS SIGN + \xD2 |0 # VULGAR FRACTION ONE QUARTER + \xD3 |0 # VULGAR FRACTION ONE HALF + \xD4 |0 # VULGAR FRACTION THREE QUARTERS + \xD5 |0 # LATIN SMALL LETTER A WITH GRAVE + \xD6 |0 # LATIN SMALL LETTER A WITH ACUTE + \xD7 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX + \xD8 |0 # LATIN SMALL LETTER A WITH TILDE + \xD9 |0 # LATIN SMALL LETTER A WITH DIAERESIS + \xDA |0 # LATIN SMALL LETTER A WITH RING ABOVE + \xDB |0 # LATIN SMALL LETTER C WITH CEDILLA + \xDC |0 # LATIN SMALL LETTER E WITH GRAVE + \xDD |0 # LATIN SMALL LETTER E WITH ACUTE + \xDE |0 # LATIN SMALL LETTER E WITH CIRCUMFLEX + \xDF |0 # LATIN SMALL LETTER E WITH DIAERESIS + \xE0 |0 # LATIN SMALL LETTER I WITH GRAVE + \xE1 |0 # LATIN CAPITAL LETTER AE + \xE2 |0 # LATIN SMALL LETTER I WITH ACUTE + \xE3 |0 # FEMININE ORDINAL INDICATOR + \xE4 |0 # LATIN SMALL LETTER I WITH CIRCUMFLEX + \xE5 |0 # LATIN SMALL LETTER I WITH DIAERESIS + \xE6 |0 # LATIN SMALL LETTER ETH + \xE7 |0 # LATIN SMALL LETTER N WITH TILDE + \xE8 |0 # LATIN CAPITAL LETTER L WITH STROKE + \xE9 |0 # LATIN CAPITAL LETTER O WITH STROKE + \xEA |0 # LATIN CAPITAL LIGATURE OE + \xEB |0 # MASCULINE ORDINAL INDICATOR + \xEC |0 # LATIN SMALL LETTER O WITH GRAVE + \xED |0 # LATIN SMALL LETTER O WITH ACUTE + \xEE |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX + \xEF |0 # LATIN SMALL LETTER O WITH TILDE + \xF0 |0 # LATIN SMALL LETTER O WITH DIAERESIS + \xF1 |0 # LATIN SMALL LETTER AE + \xF2 |0 # LATIN SMALL LETTER U WITH GRAVE + \xF3 |0 # LATIN SMALL LETTER U WITH ACUTE + \xF4 |0 # LATIN SMALL LETTER U WITH CIRCUMFLEX + \xF5 |0 # LATIN SMALL LETTER DOTLESS I + \xF6 |0 # LATIN SMALL LETTER U WITH DIAERESIS + \xF7 |0 # LATIN SMALL LETTER Y WITH ACUTE + \xF8 |0 # LATIN SMALL LETTER L WITH STROKE + \xF9 |0 # LATIN SMALL LETTER O WITH STROKE + \xFA |0 # LATIN SMALL LIGATURE OE + \xFB |0 # LATIN SMALL LETTER SHARP S + \xFE |0 # LATIN SMALL LETTER THORN + \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS +END CHARMAP diff --git a/ext/Encode/Encode/roman8.enc b/ext/Encode/Encode/roman8.enc new file mode 100644 index 0000000..7e8fbdd --- /dev/null +++ b/ext/Encode/Encode/roman8.enc @@ -0,0 +1,20 @@ +# Encoding file: roman8, single-byte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diff --git a/ext/Encode/Encode/roman8.ucm b/ext/Encode/Encode/roman8.ucm new file mode 100644 index 0000000..358642a --- /dev/null +++ b/ext/Encode/Encode/roman8.ucm @@ -0,0 +1,264 @@ +# Written $Id$ +# ./compile -n roman8 -o Encode/roman8.ucm Encode/roman8.enc + "roman8" + 1 + 1 + \x3F +# +CHARMAP + \x00 |0 # + \x01 |0 # + \x02 |0 # + \x03 |0 # + \x04 |0 # + \x05 |0 # + \x06 |0 # + \x07 |0 # + \x08 |0 # + \x09 |0 # + \x0A |0 # + \x0B |0 # + \x0C |0 # + \x0D |0 # + \x0E |0 # + \x0F |0 # + \x10 |0 # + \x11 |0 # + \x12 |0 # + \x13 |0 # + \x14 |0 # + \x15 |0 # + \x16 |0 # + \x17 |0 # + \x18 |0 # + \x19 |0 # + \x1A |0 # + \x1B |0 # + \x1C |0 # + \x1D |0 # + \x1E |0 # + \x1F |0 # + \x20 |0 # SPACE + \x21 |0 # EXCLAMATION MARK + \x22 |0 # QUOTATION MARK + \x23 |0 # NUMBER SIGN + \x24 |0 # DOLLAR SIGN + \x25 |0 # PERCENT SIGN + \x26 |0 # AMPERSAND + \x27 |0 # APOSTROPHE + \x28 |0 # LEFT PARENTHESIS + \x29 |0 # RIGHT PARENTHESIS + \x2A |0 # ASTERISK + \x2B |0 # PLUS SIGN + \x2C |0 # COMMA + \x2D |0 # HYPHEN-MINUS + \x2E |0 # FULL STOP + \x2F |0 # SOLIDUS + \x30 |0 # DIGIT ZERO + \x31 |0 # DIGIT ONE + \x32 |0 # DIGIT TWO + \x33 |0 # DIGIT THREE + \x34 |0 # DIGIT FOUR + \x35 |0 # DIGIT FIVE + \x36 |0 # DIGIT SIX + \x37 |0 # DIGIT SEVEN + \x38 |0 # DIGIT EIGHT + \x39 |0 # DIGIT NINE + \x3A |0 # COLON + \x3B |0 # SEMICOLON + \x3C |0 # LESS-THAN SIGN + \x3D |0 # EQUALS SIGN + \x3E |0 # GREATER-THAN SIGN + \x3F |0 # QUESTION MARK + \x40 |0 # COMMERCIAL AT + \x41 |0 # LATIN CAPITAL LETTER A + \x42 |0 # LATIN CAPITAL LETTER B + \x43 |0 # LATIN CAPITAL LETTER C + \x44 |0 # LATIN CAPITAL LETTER D + \x45 |0 # LATIN CAPITAL LETTER E + \x46 |0 # LATIN CAPITAL LETTER F + \x47 |0 # LATIN CAPITAL LETTER G + \x48 |0 # LATIN CAPITAL LETTER H + \x49 |0 # LATIN CAPITAL LETTER I + \x4A |0 # LATIN CAPITAL LETTER J + \x4B |0 # LATIN CAPITAL LETTER K + \x4C |0 # LATIN CAPITAL LETTER L + \x4D |0 # LATIN CAPITAL LETTER M + \x4E |0 # LATIN CAPITAL LETTER N + \x4F |0 # LATIN CAPITAL LETTER O + \x50 |0 # LATIN CAPITAL LETTER P + \x51 |0 # LATIN CAPITAL LETTER Q + \x52 |0 # LATIN CAPITAL LETTER R + \x53 |0 # LATIN CAPITAL LETTER S + \x54 |0 # LATIN CAPITAL LETTER T + \x55 |0 # LATIN CAPITAL LETTER U + \x56 |0 # LATIN CAPITAL LETTER V + \x57 |0 # LATIN CAPITAL LETTER W + \x58 |0 # LATIN CAPITAL LETTER X + \x59 |0 # LATIN CAPITAL LETTER Y + \x5A |0 # LATIN CAPITAL LETTER Z + \x5B |0 # LEFT SQUARE BRACKET + \x5C |0 # REVERSE SOLIDUS + \x5D |0 # RIGHT SQUARE BRACKET + \x5E |0 # CIRCUMFLEX ACCENT + \x5F |0 # LOW LINE + \x60 |0 # GRAVE ACCENT + \x61 |0 # LATIN SMALL LETTER A + \x62 |0 # LATIN SMALL LETTER B + \x63 |0 # LATIN SMALL LETTER C + \x64 |0 # LATIN SMALL LETTER D + \x65 |0 # LATIN SMALL LETTER E + \x66 |0 # LATIN SMALL LETTER F + \x67 |0 # LATIN SMALL LETTER G + \x68 |0 # LATIN SMALL LETTER H + \x69 |0 # LATIN SMALL LETTER I + \x6A |0 # LATIN SMALL LETTER J + \x6B |0 # LATIN SMALL LETTER K + \x6C |0 # LATIN SMALL LETTER L + \x6D |0 # LATIN SMALL LETTER M + \x6E |0 # LATIN SMALL LETTER N + \x6F |0 # LATIN SMALL LETTER O + \x70 |0 # LATIN SMALL LETTER P + \x71 |0 # LATIN SMALL LETTER Q + \x72 |0 # LATIN SMALL LETTER R + \x73 |0 # LATIN SMALL LETTER S + \x74 |0 # LATIN SMALL LETTER T + \x75 |0 # LATIN SMALL LETTER U + \x76 |0 # LATIN SMALL LETTER V + \x77 |0 # LATIN SMALL LETTER W + \x78 |0 # LATIN SMALL LETTER X + \x79 |0 # LATIN SMALL LETTER Y + \x7A |0 # LATIN SMALL LETTER Z + \x7B |0 # LEFT CURLY BRACKET + \x7C |0 # VERTICAL LINE + \x7D |0 # RIGHT CURLY BRACKET + \x7E |0 # TILDE + \x7F |0 # + \x80 |0 # + \x81 |0 # + \x82 |0 # + \x83 |0 # + \x84 |0 # + \x85 |0 # + \x86 |0 # + \x87 |0 # + \x88 |0 # + \x89 |0 # + \x8A |0 # + \x8B |0 # + \x8C |0 # + \x8D |0 # + \x8E |0 # + \x8F |0 # + \x90 |0 # + \x91 |0 # + \x92 |0 # + \x93 |0 # + \x94 |0 # + \x95 |0 # + \x96 |0 # + \x97 |0 # + \x98 |0 # + \x99 |0 # + \x9A |0 # + \x9B |0 # + \x9C |0 # + \x9D |0 # + \x9E |0 # + \x9F |0 # + \xA0 |0 # NO-BREAK SPACE + \xA1 |0 # LATIN CAPITAL LETTER A WITH GRAVE + \xA2 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + \xA3 |0 # LATIN CAPITAL LETTER E WITH GRAVE + \xA4 |0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + \xA5 |0 # LATIN CAPITAL LETTER E WITH DIAERESIS + \xA6 |0 # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + \xA7 |0 # LATIN CAPITAL LETTER I WITH DIAERESIS + \xA8 |0 # ACUTE ACCENT + \xA9 |0 # MODIFIER LETTER GRAVE ACCENT + \xAA |0 # MODIFIER LETTER CIRCUMFLEX ACCENT + \xAB |0 # DIAERESIS + \xAC |0 # SMALL TILDE + \xAD |0 # LATIN CAPITAL LETTER U WITH GRAVE + \xAE |0 # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + \xAF |0 # LIRA SIGN + \xB0 |0 # MACRON + \xB1 |0 # LATIN CAPITAL LETTER Y WITH ACUTE + \xB2 |0 # LATIN SMALL LETTER Y WITH ACUTE + \xB3 |0 # DEGREE SIGN + \xB4 |0 # LATIN CAPITAL LETTER C WITH CEDILLA + \xB5 |0 # LATIN SMALL LETTER C WITH CEDILLA + \xB6 |0 # LATIN CAPITAL LETTER N WITH TILDE + \xB7 |0 # LATIN SMALL LETTER N WITH TILDE + \xB8 |0 # INVERTED EXCLAMATION MARK + \xB9 |0 # INVERTED QUESTION MARK + \xBA |0 # CURRENCY SIGN + \xBB |0 # POUND SIGN + \xBC |0 # YEN SIGN + \xBD |0 # SECTION SIGN + \xBE |0 # LATIN SMALL LETTER F WITH HOOK + \xBF |0 # CENT SIGN + \xC0 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX + \xC1 |0 # LATIN SMALL LETTER E WITH CIRCUMFLEX + \xC2 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX + \xC3 |0 # LATIN SMALL LETTER U WITH CIRCUMFLEX + \xC4 |0 # LATIN SMALL LETTER A WITH ACUTE + \xC5 |0 # LATIN SMALL LETTER E WITH ACUTE + \xC6 |0 # LATIN SMALL LETTER O WITH ACUTE + \xC7 |0 # LATIN SMALL LETTER U WITH ACUTE + \xC8 |0 # LATIN SMALL LETTER A WITH GRAVE + \xC9 |0 # LATIN SMALL LETTER E WITH GRAVE + \xCA |0 # LATIN SMALL LETTER O WITH GRAVE + \xCB |0 # LATIN SMALL LETTER U WITH GRAVE + \xCC |0 # LATIN SMALL LETTER A WITH DIAERESIS + \xCD |0 # LATIN SMALL LETTER E WITH DIAERESIS + \xCE |0 # LATIN SMALL LETTER O WITH DIAERESIS + \xCF |0 # LATIN SMALL LETTER U WITH DIAERESIS + \xD0 |0 # LATIN CAPITAL LETTER A WITH RING ABOVE + \xD1 |0 # LATIN SMALL LETTER I WITH CIRCUMFLEX + \xD2 |0 # LATIN CAPITAL LETTER O WITH STROKE + \xD3 |0 # LATIN CAPITAL LETTER AE + \xD4 |0 # LATIN SMALL LETTER A WITH RING ABOVE + \xD5 |0 # LATIN SMALL LETTER I WITH ACUTE + \xD6 |0 # LATIN SMALL LETTER O WITH STROKE + \xD7 |0 # LATIN SMALL LETTER AE + \xD8 |0 # LATIN CAPITAL LETTER A WITH DIAERESIS + \xD9 |0 # LATIN SMALL LETTER I WITH GRAVE + \xDA |0 # LATIN CAPITAL LETTER O WITH DIAERESIS + \xDB |0 # LATIN CAPITAL LETTER U WITH DIAERESIS + \xDC |0 # LATIN CAPITAL LETTER E WITH ACUTE + \xDD |0 # LATIN SMALL LETTER I WITH DIAERESIS + \xDE |0 # LATIN SMALL LETTER SHARP S + \xDF |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + \xE0 |0 # LATIN CAPITAL LETTER A WITH ACUTE + \xE1 |0 # LATIN CAPITAL LETTER A WITH TILDE + \xE2 |0 # LATIN SMALL LETTER A WITH TILDE + \xE3 |0 # LATIN CAPITAL LETTER ETH + \xE4 |0 # LATIN SMALL LETTER ETH + \xE5 |0 # LATIN CAPITAL LETTER I WITH ACUTE + \xE6 |0 # LATIN CAPITAL LETTER I WITH GRAVE + \xE7 |0 # LATIN CAPITAL LETTER O WITH ACUTE + \xE8 |0 # LATIN CAPITAL LETTER O WITH GRAVE + \xE9 |0 # LATIN CAPITAL LETTER O WITH TILDE + \xEA |0 # LATIN SMALL LETTER O WITH TILDE + \xEB |0 # LATIN CAPITAL LETTER S WITH CARON + \xEC |0 # LATIN SMALL LETTER S WITH CARON + \xED |0 # LATIN CAPITAL LETTER U WITH ACUTE + \xEE |0 # LATIN CAPITAL LETTER Y WITH DIAERESIS + \xF0 |0 # LATIN CAPITAL LETTER THORN + \xF1 |0 # LATIN SMALL LETTER THORN + \xF2 |0 # MIDDLE DOT + \xF3 |0 # MICRO SIGN + \xF4 |0 # PILCROW SIGN + \xF5 |0 # VULGAR FRACTION THREE QUARTERS + \xF6 |0 # EM DASH + \xF7 |0 # VULGAR FRACTION ONE QUARTER + \xF8 |0 # VULGAR FRACTION ONE HALF + \xF9 |0 # FEMININE ORDINAL INDICATOR + \xFA |0 # MASCULINE ORDINAL INDICATOR + \xFB |0 # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + \xFC |0 # BLACK SQUARE + \xFD |0 # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + \xFE |0 # PLUS-MINUS SIGN + \xFF |0 # LATIN SMALL LETTER Y WITH DIAERESIS +END CHARMAP diff --git a/ext/Encode/Encode/viscii.enc b/ext/Encode/Encode/viscii.enc new file mode 100644 index 0000000..3be7733 --- /dev/null +++ b/ext/Encode/Encode/viscii.enc @@ -0,0 +1,20 @@ +# Encoding file: viscii, single-byte +S +003F 0 1 +00 +000000011EB2000300041EB41EAA000700080009000A000B000C000D000E000F +00100011001200131EF600150016001700181EF8001A001B001C001D1EF4001F +0020002100220023002400250026002700280029002A002B002C002D002E002F +0030003100320033003400350036003700380039003A003B003C003D003E003F +0040004100420043004400450046004700480049004A004B004C004D004E004F +0050005100520053005400550056005700580059005A005B005C005D005E005F +0060006100620063006400650066006700680069006A006B006C006D006E006F +0070007100720073007400750076007700780079007A007B007C007D007E007F +1EA01EAE1EB01EB61EA41EA61EA81EAC1EBC1EB81EBE1EC01EC21EC41EC61ED0 +1ED21ED41ED61ED81EE21EDA1EDC1EDE1ECA1ECE1ECC1EC81EE601681EE41EF2 +00D51EAF1EB11EB71EA51EA71EA81EAD1EBD1EB91EBF1EC11EC31EC51EC71ED1 +1ED31ED51ED71EE001A01ED91EDD1EDF1ECB1EF01EE81EEA1EEC01A11EDB01AF +00C000C100C200C31EA201021EB31EB500C800C900CA1EBA00CC00CD01281EF3 +01101EE900D200D300D41EA11EF71EEB1EED00D900DA1EF91EF500DD1EE101B0 +00E000E100E200E31EA301031EEF1EAB00E800E900EA1EBB00EC00ED01291EC9 +01111EF100F200F300F400F51ECF1ECD1EE500F900FA01691EE700FD1EE31EEE diff --git a/ext/Encode/Encode/viscii.ucm b/ext/Encode/Encode/viscii.ucm new file mode 100644 index 0000000..23bec90 --- /dev/null +++ b/ext/Encode/Encode/viscii.ucm @@ -0,0 +1,264 @@ +# Written $Id$ +# ./compile -n viscii -o Encode/viscii.ucm Encode/viscii.enc + "viscii" + 1 + 1 + \x3F +# +CHARMAP + \x00 |0 # + \x01 |0 # + \x02 |0 # LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE + \x03 |0 # + \x04 |0 # + \x05 |0 # LATIN CAPITAL LETTER A WITH BREVE AND TILDE + \x06 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE + \x07 |0 # + \x08 |0 # + \x09 |0 # + \x0A |0 # + \x0B |0 # + \x0C |0 # + \x0D |0 # + \x0E |0 # + \x0F |0 # + \x10 |0 # + \x11 |0 # + \x12 |0 # + \x13 |0 # + \x14 |0 # LATIN CAPITAL LETTER Y WITH HOOK ABOVE + \x15 |0 # + \x16 |0 # + \x17 |0 # + \x18 |0 # + \x19 |0 # LATIN CAPITAL LETTER Y WITH TILDE + \x1A |0 # + \x1B |0 # + \x1C |0 # + \x1D |0 # + \x1E |0 # LATIN CAPITAL LETTER Y WITH DOT BELOW + \x1F |0 # + \x20 |0 # SPACE + \x21 |0 # EXCLAMATION MARK + \x22 |0 # QUOTATION MARK + \x23 |0 # NUMBER SIGN + \x24 |0 # DOLLAR SIGN + \x25 |0 # PERCENT SIGN + \x26 |0 # AMPERSAND + \x27 |0 # APOSTROPHE + \x28 |0 # LEFT PARENTHESIS + \x29 |0 # RIGHT PARENTHESIS + \x2A |0 # ASTERISK + \x2B |0 # PLUS SIGN + \x2C |0 # COMMA + \x2D |0 # HYPHEN-MINUS + \x2E |0 # FULL STOP + \x2F |0 # SOLIDUS + \x30 |0 # DIGIT ZERO + \x31 |0 # DIGIT ONE + \x32 |0 # DIGIT TWO + \x33 |0 # DIGIT THREE + \x34 |0 # DIGIT FOUR + \x35 |0 # DIGIT FIVE + \x36 |0 # DIGIT SIX + \x37 |0 # DIGIT SEVEN + \x38 |0 # DIGIT EIGHT + \x39 |0 # DIGIT NINE + \x3A |0 # COLON + \x3B |0 # SEMICOLON + \x3C |0 # LESS-THAN SIGN + \x3D |0 # EQUALS SIGN + \x3E |0 # GREATER-THAN SIGN + \x3F |0 # QUESTION MARK + \x40 |0 # COMMERCIAL AT + \x41 |0 # LATIN CAPITAL LETTER A + \x42 |0 # LATIN CAPITAL LETTER B + \x43 |0 # LATIN CAPITAL LETTER C + \x44 |0 # LATIN CAPITAL LETTER D + \x45 |0 # LATIN CAPITAL LETTER E + \x46 |0 # LATIN CAPITAL LETTER F + \x47 |0 # LATIN CAPITAL LETTER G + \x48 |0 # LATIN CAPITAL LETTER H + \x49 |0 # LATIN CAPITAL LETTER I + \x4A |0 # LATIN CAPITAL LETTER J + \x4B |0 # LATIN CAPITAL LETTER K + \x4C |0 # LATIN CAPITAL LETTER L + \x4D |0 # LATIN CAPITAL LETTER M + \x4E |0 # LATIN CAPITAL LETTER N + \x4F |0 # LATIN CAPITAL LETTER O + \x50 |0 # LATIN CAPITAL LETTER P + \x51 |0 # LATIN CAPITAL LETTER Q + \x52 |0 # LATIN CAPITAL LETTER R + \x53 |0 # LATIN CAPITAL LETTER S + \x54 |0 # LATIN CAPITAL LETTER T + \x55 |0 # LATIN CAPITAL LETTER U + \x56 |0 # LATIN CAPITAL LETTER V + \x57 |0 # LATIN CAPITAL LETTER W + \x58 |0 # LATIN CAPITAL LETTER X + \x59 |0 # LATIN CAPITAL LETTER Y + \x5A |0 # LATIN CAPITAL LETTER Z + \x5B |0 # LEFT SQUARE BRACKET + \x5C |0 # REVERSE SOLIDUS + \x5D |0 # RIGHT SQUARE BRACKET + \x5E |0 # CIRCUMFLEX ACCENT + \x5F |0 # LOW LINE + \x60 |0 # GRAVE ACCENT + \x61 |0 # LATIN SMALL LETTER A + \x62 |0 # LATIN SMALL LETTER B + \x63 |0 # LATIN SMALL LETTER C + \x64 |0 # LATIN SMALL LETTER D + \x65 |0 # LATIN SMALL LETTER E + \x66 |0 # LATIN SMALL LETTER F + \x67 |0 # LATIN SMALL LETTER G + \x68 |0 # LATIN SMALL LETTER H + \x69 |0 # LATIN SMALL LETTER I + \x6A |0 # LATIN SMALL LETTER J + \x6B |0 # LATIN SMALL LETTER K + \x6C |0 # LATIN SMALL LETTER L + \x6D |0 # LATIN SMALL LETTER M + \x6E |0 # LATIN SMALL LETTER N + \x6F |0 # LATIN SMALL LETTER O + \x70 |0 # LATIN SMALL LETTER P + \x71 |0 # LATIN SMALL LETTER Q + \x72 |0 # LATIN SMALL LETTER R + \x73 |0 # LATIN SMALL LETTER S + \x74 |0 # LATIN SMALL LETTER T + \x75 |0 # LATIN SMALL LETTER U + \x76 |0 # LATIN SMALL LETTER V + \x77 |0 # LATIN SMALL LETTER W + \x78 |0 # LATIN SMALL LETTER X + \x79 |0 # LATIN SMALL LETTER Y + \x7A |0 # LATIN SMALL LETTER Z + \x7B |0 # LEFT CURLY BRACKET + \x7C |0 # VERTICAL LINE + \x7D |0 # RIGHT CURLY BRACKET + \x7E |0 # TILDE + \x7F |0 # + \x80 |0 # LATIN CAPITAL LETTER A WITH DOT BELOW + \x81 |0 # LATIN CAPITAL LETTER A WITH BREVE AND ACUTE + \x82 |0 # LATIN CAPITAL LETTER A WITH BREVE AND GRAVE + \x83 |0 # LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW + \x84 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE + \x85 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE + \x87 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW + \x88 |0 # LATIN CAPITAL LETTER E WITH TILDE + \x89 |0 # LATIN CAPITAL LETTER E WITH DOT BELOW + \x8A |0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE + \x8B |0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE + \x8C |0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE + \x8D |0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE + \x8E |0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW + \x8F |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE + \x90 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE + \x91 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE + \x92 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE + \x93 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW + \x94 |0 # LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW + \x95 |0 # LATIN CAPITAL LETTER O WITH HORN AND ACUTE + \x96 |0 # LATIN CAPITAL LETTER O WITH HORN AND GRAVE + \x97 |0 # LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE + \x98 |0 # LATIN CAPITAL LETTER I WITH DOT BELOW + \x99 |0 # LATIN CAPITAL LETTER O WITH HOOK ABOVE + \x9A |0 # LATIN CAPITAL LETTER O WITH DOT BELOW + \x9B |0 # LATIN CAPITAL LETTER I WITH HOOK ABOVE + \x9C |0 # LATIN CAPITAL LETTER U WITH HOOK ABOVE + \x9D |0 # LATIN CAPITAL LETTER U WITH TILDE + \x9E |0 # LATIN CAPITAL LETTER U WITH DOT BELOW + \x9F |0 # LATIN CAPITAL LETTER Y WITH GRAVE + \xA0 |0 # LATIN CAPITAL LETTER O WITH TILDE + \xA1 |0 # LATIN SMALL LETTER A WITH BREVE AND ACUTE + \xA2 |0 # LATIN SMALL LETTER A WITH BREVE AND GRAVE + \xA3 |0 # LATIN SMALL LETTER A WITH BREVE AND DOT BELOW + \xA4 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE + \xA5 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE + \xA6 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE + \xA7 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW + \xA8 |0 # LATIN SMALL LETTER E WITH TILDE + \xA9 |0 # LATIN SMALL LETTER E WITH DOT BELOW + \xAA |0 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE + \xAB |0 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE + \xAC |0 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE + \xAD |0 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE + \xAE |0 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW + \xAF |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE + \xB0 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE + \xB1 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE + \xB2 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE + \xB3 |0 # LATIN CAPITAL LETTER O WITH HORN AND TILDE + \xB4 |0 # LATIN CAPITAL LETTER O WITH HORN + \xB5 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW + \xB6 |0 # LATIN SMALL LETTER O WITH HORN AND GRAVE + \xB7 |0 # LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE + \xB8 |0 # LATIN SMALL LETTER I WITH DOT BELOW + \xB9 |0 # LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW + \xBA |0 # LATIN CAPITAL LETTER U WITH HORN AND ACUTE + \xBB |0 # LATIN CAPITAL LETTER U WITH HORN AND GRAVE + \xBC |0 # LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE + \xBD |0 # LATIN SMALL LETTER O WITH HORN + \xBE |0 # LATIN SMALL LETTER O WITH HORN AND ACUTE + \xBF |0 # LATIN CAPITAL LETTER U WITH HORN + \xC0 |0 # LATIN CAPITAL LETTER A WITH GRAVE + \xC1 |0 # LATIN CAPITAL LETTER A WITH ACUTE + \xC2 |0 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + \xC3 |0 # LATIN CAPITAL LETTER A WITH TILDE + \xC4 |0 # LATIN CAPITAL LETTER A WITH HOOK ABOVE + \xC5 |0 # LATIN CAPITAL LETTER A WITH BREVE + \xC6 |0 # LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE + \xC7 |0 # LATIN SMALL LETTER A WITH BREVE AND TILDE + \xC8 |0 # LATIN CAPITAL LETTER E WITH GRAVE + \xC9 |0 # LATIN CAPITAL LETTER E WITH ACUTE + \xCA |0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + \xCB |0 # LATIN CAPITAL LETTER E WITH HOOK ABOVE + \xCC |0 # LATIN CAPITAL LETTER I WITH GRAVE + \xCD |0 # LATIN CAPITAL LETTER I WITH ACUTE + \xCE |0 # LATIN CAPITAL LETTER I WITH TILDE + \xCF |0 # LATIN SMALL LETTER Y WITH GRAVE + \xD0 |0 # LATIN CAPITAL LETTER D WITH STROKE + \xD1 |0 # LATIN SMALL LETTER U WITH HORN AND ACUTE + \xD2 |0 # LATIN CAPITAL LETTER O WITH GRAVE + \xD3 |0 # LATIN CAPITAL LETTER O WITH ACUTE + \xD4 |0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + \xD5 |0 # LATIN SMALL LETTER A WITH DOT BELOW + \xD6 |0 # LATIN SMALL LETTER Y WITH HOOK ABOVE + \xD7 |0 # LATIN SMALL LETTER U WITH HORN AND GRAVE + \xD8 |0 # LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE + \xD9 |0 # LATIN CAPITAL LETTER U WITH GRAVE + \xDA |0 # LATIN CAPITAL LETTER U WITH ACUTE + \xDB |0 # LATIN SMALL LETTER Y WITH TILDE + \xDC |0 # LATIN SMALL LETTER Y WITH DOT BELOW + \xDD |0 # LATIN CAPITAL LETTER Y WITH ACUTE + \xDE |0 # LATIN SMALL LETTER O WITH HORN AND TILDE + \xDF |0 # LATIN SMALL LETTER U WITH HORN + \xE0 |0 # LATIN SMALL LETTER A WITH GRAVE + \xE1 |0 # LATIN SMALL LETTER A WITH ACUTE + \xE2 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX + \xE3 |0 # LATIN SMALL LETTER A WITH TILDE + \xE4 |0 # LATIN SMALL LETTER A WITH HOOK ABOVE + \xE5 |0 # LATIN SMALL LETTER A WITH BREVE + \xE6 |0 # LATIN SMALL LETTER U WITH HORN AND TILDE + \xE7 |0 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE + \xE8 |0 # LATIN SMALL LETTER E WITH GRAVE + \xE9 |0 # LATIN SMALL LETTER E WITH ACUTE + \xEA |0 # LATIN SMALL LETTER E WITH CIRCUMFLEX + \xEB |0 # LATIN SMALL LETTER E WITH HOOK ABOVE + \xEC |0 # LATIN SMALL LETTER I WITH GRAVE + \xED |0 # LATIN SMALL LETTER I WITH ACUTE + \xEE |0 # LATIN SMALL LETTER I WITH TILDE + \xEF |0 # LATIN SMALL LETTER I WITH HOOK ABOVE + \xF0 |0 # LATIN SMALL LETTER D WITH STROKE + \xF1 |0 # LATIN SMALL LETTER U WITH HORN AND DOT BELOW + \xF2 |0 # LATIN SMALL LETTER O WITH GRAVE + \xF3 |0 # LATIN SMALL LETTER O WITH ACUTE + \xF4 |0 # LATIN SMALL LETTER O WITH CIRCUMFLEX + \xF5 |0 # LATIN SMALL LETTER O WITH TILDE + \xF6 |0 # LATIN SMALL LETTER O WITH HOOK ABOVE + \xF7 |0 # LATIN SMALL LETTER O WITH DOT BELOW + \xF8 |0 # LATIN SMALL LETTER U WITH DOT BELOW + \xF9 |0 # LATIN SMALL LETTER U WITH GRAVE + \xFA |0 # LATIN SMALL LETTER U WITH ACUTE + \xFB |0 # LATIN SMALL LETTER U WITH TILDE + \xFC |0 # LATIN SMALL LETTER U WITH HOOK ABOVE + \xFD |0 # LATIN SMALL LETTER Y WITH ACUTE + \xFE |0 # LATIN SMALL LETTER O WITH HORN AND DOT BELOW + \xFF |0 # LATIN CAPITAL LETTER U WITH HORN AND TILDE +END CHARMAP