File manager - Edit - /home/newsbmcs.com/public_html/static/img/logo/encodings.tar
Back
cp424.py 0000644 00000027427 15030477433 0005774 0 ustar 00 """ Python Character Mapping Codec cp424 generated from 'MAPPINGS/VENDORS/MISC/CP424.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp424', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( '\x00' # 0x00 -> NULL '\x01' # 0x01 -> START OF HEADING '\x02' # 0x02 -> START OF TEXT '\x03' # 0x03 -> END OF TEXT '\x9c' # 0x04 -> SELECT '\t' # 0x05 -> HORIZONTAL TABULATION '\x86' # 0x06 -> REQUIRED NEW LINE '\x7f' # 0x07 -> DELETE '\x97' # 0x08 -> GRAPHIC ESCAPE '\x8d' # 0x09 -> SUPERSCRIPT '\x8e' # 0x0A -> REPEAT '\x0b' # 0x0B -> VERTICAL TABULATION '\x0c' # 0x0C -> FORM FEED '\r' # 0x0D -> CARRIAGE RETURN '\x0e' # 0x0E -> SHIFT OUT '\x0f' # 0x0F -> SHIFT IN '\x10' # 0x10 -> DATA LINK ESCAPE '\x11' # 0x11 -> DEVICE CONTROL ONE '\x12' # 0x12 -> DEVICE CONTROL TWO '\x13' # 0x13 -> DEVICE CONTROL THREE '\x9d' # 0x14 -> RESTORE/ENABLE PRESENTATION '\x85' # 0x15 -> NEW LINE '\x08' # 0x16 -> BACKSPACE '\x87' # 0x17 -> PROGRAM OPERATOR COMMUNICATION '\x18' # 0x18 -> CANCEL '\x19' # 0x19 -> END OF MEDIUM '\x92' # 0x1A -> UNIT BACK SPACE '\x8f' # 0x1B -> CUSTOMER USE ONE '\x1c' # 0x1C -> FILE SEPARATOR '\x1d' # 0x1D -> GROUP SEPARATOR '\x1e' # 0x1E -> RECORD SEPARATOR '\x1f' # 0x1F -> UNIT SEPARATOR '\x80' # 0x20 -> DIGIT SELECT '\x81' # 0x21 -> START OF SIGNIFICANCE '\x82' # 0x22 -> FIELD SEPARATOR '\x83' # 0x23 -> WORD UNDERSCORE '\x84' # 0x24 -> BYPASS OR INHIBIT PRESENTATION '\n' # 0x25 -> LINE FEED '\x17' # 0x26 -> END OF TRANSMISSION BLOCK '\x1b' # 0x27 -> ESCAPE '\x88' # 0x28 -> SET ATTRIBUTE '\x89' # 0x29 -> START FIELD EXTENDED '\x8a' # 0x2A -> SET MODE OR SWITCH '\x8b' # 0x2B -> CONTROL SEQUENCE PREFIX '\x8c' # 0x2C -> MODIFY FIELD ATTRIBUTE '\x05' # 0x2D -> ENQUIRY '\x06' # 0x2E -> ACKNOWLEDGE '\x07' # 0x2F -> BELL '\x90' # 0x30 -> <reserved> '\x91' # 0x31 -> <reserved> '\x16' # 0x32 -> SYNCHRONOUS IDLE '\x93' # 0x33 -> INDEX RETURN '\x94' # 0x34 -> PRESENTATION POSITION '\x95' # 0x35 -> TRANSPARENT '\x96' # 0x36 -> NUMERIC BACKSPACE '\x04' # 0x37 -> END OF TRANSMISSION '\x98' # 0x38 -> SUBSCRIPT '\x99' # 0x39 -> INDENT TABULATION '\x9a' # 0x3A -> REVERSE FORM FEED '\x9b' # 0x3B -> CUSTOMER USE THREE '\x14' # 0x3C -> DEVICE CONTROL FOUR '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE '\x9e' # 0x3E -> <reserved> '\x1a' # 0x3F -> SUBSTITUTE ' ' # 0x40 -> SPACE '\u05d0' # 0x41 -> HEBREW LETTER ALEF '\u05d1' # 0x42 -> HEBREW LETTER BET '\u05d2' # 0x43 -> HEBREW LETTER GIMEL '\u05d3' # 0x44 -> HEBREW LETTER DALET '\u05d4' # 0x45 -> HEBREW LETTER HE '\u05d5' # 0x46 -> HEBREW LETTER VAV '\u05d6' # 0x47 -> HEBREW LETTER ZAYIN '\u05d7' # 0x48 -> HEBREW LETTER HET '\u05d8' # 0x49 -> HEBREW LETTER TET '\xa2' # 0x4A -> CENT SIGN '.' # 0x4B -> FULL STOP '<' # 0x4C -> LESS-THAN SIGN '(' # 0x4D -> LEFT PARENTHESIS '+' # 0x4E -> PLUS SIGN '|' # 0x4F -> VERTICAL LINE '&' # 0x50 -> AMPERSAND '\u05d9' # 0x51 -> HEBREW LETTER YOD '\u05da' # 0x52 -> HEBREW LETTER FINAL KAF '\u05db' # 0x53 -> HEBREW LETTER KAF '\u05dc' # 0x54 -> HEBREW LETTER LAMED '\u05dd' # 0x55 -> HEBREW LETTER FINAL MEM '\u05de' # 0x56 -> HEBREW LETTER MEM '\u05df' # 0x57 -> HEBREW LETTER FINAL NUN '\u05e0' # 0x58 -> HEBREW LETTER NUN '\u05e1' # 0x59 -> HEBREW LETTER SAMEKH '!' # 0x5A -> EXCLAMATION MARK '$' # 0x5B -> DOLLAR SIGN '*' # 0x5C -> ASTERISK ')' # 0x5D -> RIGHT PARENTHESIS ';' # 0x5E -> SEMICOLON '\xac' # 0x5F -> NOT SIGN '-' # 0x60 -> HYPHEN-MINUS '/' # 0x61 -> SOLIDUS '\u05e2' # 0x62 -> HEBREW LETTER AYIN '\u05e3' # 0x63 -> HEBREW LETTER FINAL PE '\u05e4' # 0x64 -> HEBREW LETTER PE '\u05e5' # 0x65 -> HEBREW LETTER FINAL TSADI '\u05e6' # 0x66 -> HEBREW LETTER TSADI '\u05e7' # 0x67 -> HEBREW LETTER QOF '\u05e8' # 0x68 -> HEBREW LETTER RESH '\u05e9' # 0x69 -> HEBREW LETTER SHIN '\xa6' # 0x6A -> BROKEN BAR ',' # 0x6B -> COMMA '%' # 0x6C -> PERCENT SIGN '_' # 0x6D -> LOW LINE '>' # 0x6E -> GREATER-THAN SIGN '?' # 0x6F -> QUESTION MARK '\ufffe' # 0x70 -> UNDEFINED '\u05ea' # 0x71 -> HEBREW LETTER TAV '\ufffe' # 0x72 -> UNDEFINED '\ufffe' # 0x73 -> UNDEFINED '\xa0' # 0x74 -> NO-BREAK SPACE '\ufffe' # 0x75 -> UNDEFINED '\ufffe' # 0x76 -> UNDEFINED '\ufffe' # 0x77 -> UNDEFINED '\u2017' # 0x78 -> DOUBLE LOW LINE '`' # 0x79 -> GRAVE ACCENT ':' # 0x7A -> COLON '#' # 0x7B -> NUMBER SIGN '@' # 0x7C -> COMMERCIAL AT "'" # 0x7D -> APOSTROPHE '=' # 0x7E -> EQUALS SIGN '"' # 0x7F -> QUOTATION MARK '\ufffe' # 0x80 -> UNDEFINED 'a' # 0x81 -> LATIN SMALL LETTER A 'b' # 0x82 -> LATIN SMALL LETTER B 'c' # 0x83 -> LATIN SMALL LETTER C 'd' # 0x84 -> LATIN SMALL LETTER D 'e' # 0x85 -> LATIN SMALL LETTER E 'f' # 0x86 -> LATIN SMALL LETTER F 'g' # 0x87 -> LATIN SMALL LETTER G 'h' # 0x88 -> LATIN SMALL LETTER H 'i' # 0x89 -> LATIN SMALL LETTER I '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK '\ufffe' # 0x8C -> UNDEFINED '\ufffe' # 0x8D -> UNDEFINED '\ufffe' # 0x8E -> UNDEFINED '\xb1' # 0x8F -> PLUS-MINUS SIGN '\xb0' # 0x90 -> DEGREE SIGN 'j' # 0x91 -> LATIN SMALL LETTER J 'k' # 0x92 -> LATIN SMALL LETTER K 'l' # 0x93 -> LATIN SMALL LETTER L 'm' # 0x94 -> LATIN SMALL LETTER M 'n' # 0x95 -> LATIN SMALL LETTER N 'o' # 0x96 -> LATIN SMALL LETTER O 'p' # 0x97 -> LATIN SMALL LETTER P 'q' # 0x98 -> LATIN SMALL LETTER Q 'r' # 0x99 -> LATIN SMALL LETTER R '\ufffe' # 0x9A -> UNDEFINED '\ufffe' # 0x9B -> UNDEFINED '\ufffe' # 0x9C -> UNDEFINED '\xb8' # 0x9D -> CEDILLA '\ufffe' # 0x9E -> UNDEFINED '\xa4' # 0x9F -> CURRENCY SIGN '\xb5' # 0xA0 -> MICRO SIGN '~' # 0xA1 -> TILDE 's' # 0xA2 -> LATIN SMALL LETTER S 't' # 0xA3 -> LATIN SMALL LETTER T 'u' # 0xA4 -> LATIN SMALL LETTER U 'v' # 0xA5 -> LATIN SMALL LETTER V 'w' # 0xA6 -> LATIN SMALL LETTER W 'x' # 0xA7 -> LATIN SMALL LETTER X 'y' # 0xA8 -> LATIN SMALL LETTER Y 'z' # 0xA9 -> LATIN SMALL LETTER Z '\ufffe' # 0xAA -> UNDEFINED '\ufffe' # 0xAB -> UNDEFINED '\ufffe' # 0xAC -> UNDEFINED '\ufffe' # 0xAD -> UNDEFINED '\ufffe' # 0xAE -> UNDEFINED '\xae' # 0xAF -> REGISTERED SIGN '^' # 0xB0 -> CIRCUMFLEX ACCENT '\xa3' # 0xB1 -> POUND SIGN '\xa5' # 0xB2 -> YEN SIGN '\xb7' # 0xB3 -> MIDDLE DOT '\xa9' # 0xB4 -> COPYRIGHT SIGN '\xa7' # 0xB5 -> SECTION SIGN '\xb6' # 0xB6 -> PILCROW SIGN '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS '[' # 0xBA -> LEFT SQUARE BRACKET ']' # 0xBB -> RIGHT SQUARE BRACKET '\xaf' # 0xBC -> MACRON '\xa8' # 0xBD -> DIAERESIS '\xb4' # 0xBE -> ACUTE ACCENT '\xd7' # 0xBF -> MULTIPLICATION SIGN '{' # 0xC0 -> LEFT CURLY BRACKET 'A' # 0xC1 -> LATIN CAPITAL LETTER A 'B' # 0xC2 -> LATIN CAPITAL LETTER B 'C' # 0xC3 -> LATIN CAPITAL LETTER C 'D' # 0xC4 -> LATIN CAPITAL LETTER D 'E' # 0xC5 -> LATIN CAPITAL LETTER E 'F' # 0xC6 -> LATIN CAPITAL LETTER F 'G' # 0xC7 -> LATIN CAPITAL LETTER G 'H' # 0xC8 -> LATIN CAPITAL LETTER H 'I' # 0xC9 -> LATIN CAPITAL LETTER I '\xad' # 0xCA -> SOFT HYPHEN '\ufffe' # 0xCB -> UNDEFINED '\ufffe' # 0xCC -> UNDEFINED '\ufffe' # 0xCD -> UNDEFINED '\ufffe' # 0xCE -> UNDEFINED '\ufffe' # 0xCF -> UNDEFINED '}' # 0xD0 -> RIGHT CURLY BRACKET 'J' # 0xD1 -> LATIN CAPITAL LETTER J 'K' # 0xD2 -> LATIN CAPITAL LETTER K 'L' # 0xD3 -> LATIN CAPITAL LETTER L 'M' # 0xD4 -> LATIN CAPITAL LETTER M 'N' # 0xD5 -> LATIN CAPITAL LETTER N 'O' # 0xD6 -> LATIN CAPITAL LETTER O 'P' # 0xD7 -> LATIN CAPITAL LETTER P 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q 'R' # 0xD9 -> LATIN CAPITAL LETTER R '\xb9' # 0xDA -> SUPERSCRIPT ONE '\ufffe' # 0xDB -> UNDEFINED '\ufffe' # 0xDC -> UNDEFINED '\ufffe' # 0xDD -> UNDEFINED '\ufffe' # 0xDE -> UNDEFINED '\ufffe' # 0xDF -> UNDEFINED '\\' # 0xE0 -> REVERSE SOLIDUS '\xf7' # 0xE1 -> DIVISION SIGN 'S' # 0xE2 -> LATIN CAPITAL LETTER S 'T' # 0xE3 -> LATIN CAPITAL LETTER T 'U' # 0xE4 -> LATIN CAPITAL LETTER U 'V' # 0xE5 -> LATIN CAPITAL LETTER V 'W' # 0xE6 -> LATIN CAPITAL LETTER W 'X' # 0xE7 -> LATIN CAPITAL LETTER X 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z '\xb2' # 0xEA -> SUPERSCRIPT TWO '\ufffe' # 0xEB -> UNDEFINED '\ufffe' # 0xEC -> UNDEFINED '\ufffe' # 0xED -> UNDEFINED '\ufffe' # 0xEE -> UNDEFINED '\ufffe' # 0xEF -> UNDEFINED '0' # 0xF0 -> DIGIT ZERO '1' # 0xF1 -> DIGIT ONE '2' # 0xF2 -> DIGIT TWO '3' # 0xF3 -> DIGIT THREE '4' # 0xF4 -> DIGIT FOUR '5' # 0xF5 -> DIGIT FIVE '6' # 0xF6 -> DIGIT SIX '7' # 0xF7 -> DIGIT SEVEN '8' # 0xF8 -> DIGIT EIGHT '9' # 0xF9 -> DIGIT NINE '\xb3' # 0xFA -> SUPERSCRIPT THREE '\ufffe' # 0xFB -> UNDEFINED '\ufffe' # 0xFC -> UNDEFINED '\ufffe' # 0xFD -> UNDEFINED '\ufffe' # 0xFE -> UNDEFINED '\x9f' # 0xFF -> EIGHT ONES ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) koi8_u.py 0000644 00000032702 15030477433 0006326 0 ustar 00 """ Python Character Mapping Codec koi8_u generated from 'python-mappings/KOI8-U.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='koi8-u', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( '\x00' # 0x00 -> NULL '\x01' # 0x01 -> START OF HEADING '\x02' # 0x02 -> START OF TEXT '\x03' # 0x03 -> END OF TEXT '\x04' # 0x04 -> END OF TRANSMISSION '\x05' # 0x05 -> ENQUIRY '\x06' # 0x06 -> ACKNOWLEDGE '\x07' # 0x07 -> BELL '\x08' # 0x08 -> BACKSPACE '\t' # 0x09 -> HORIZONTAL TABULATION '\n' # 0x0A -> LINE FEED '\x0b' # 0x0B -> VERTICAL TABULATION '\x0c' # 0x0C -> FORM FEED '\r' # 0x0D -> CARRIAGE RETURN '\x0e' # 0x0E -> SHIFT OUT '\x0f' # 0x0F -> SHIFT IN '\x10' # 0x10 -> DATA LINK ESCAPE '\x11' # 0x11 -> DEVICE CONTROL ONE '\x12' # 0x12 -> DEVICE CONTROL TWO '\x13' # 0x13 -> DEVICE CONTROL THREE '\x14' # 0x14 -> DEVICE CONTROL FOUR '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE '\x16' # 0x16 -> SYNCHRONOUS IDLE '\x17' # 0x17 -> END OF TRANSMISSION BLOCK '\x18' # 0x18 -> CANCEL '\x19' # 0x19 -> END OF MEDIUM '\x1a' # 0x1A -> SUBSTITUTE '\x1b' # 0x1B -> ESCAPE '\x1c' # 0x1C -> FILE SEPARATOR '\x1d' # 0x1D -> GROUP SEPARATOR '\x1e' # 0x1E -> RECORD SEPARATOR '\x1f' # 0x1F -> UNIT SEPARATOR ' ' # 0x20 -> SPACE '!' # 0x21 -> EXCLAMATION MARK '"' # 0x22 -> QUOTATION MARK '#' # 0x23 -> NUMBER SIGN '$' # 0x24 -> DOLLAR SIGN '%' # 0x25 -> PERCENT SIGN '&' # 0x26 -> AMPERSAND "'" # 0x27 -> APOSTROPHE '(' # 0x28 -> LEFT PARENTHESIS ')' # 0x29 -> RIGHT PARENTHESIS '*' # 0x2A -> ASTERISK '+' # 0x2B -> PLUS SIGN ',' # 0x2C -> COMMA '-' # 0x2D -> HYPHEN-MINUS '.' # 0x2E -> FULL STOP '/' # 0x2F -> SOLIDUS '0' # 0x30 -> DIGIT ZERO '1' # 0x31 -> DIGIT ONE '2' # 0x32 -> DIGIT TWO '3' # 0x33 -> DIGIT THREE '4' # 0x34 -> DIGIT FOUR '5' # 0x35 -> DIGIT FIVE '6' # 0x36 -> DIGIT SIX '7' # 0x37 -> DIGIT SEVEN '8' # 0x38 -> DIGIT EIGHT '9' # 0x39 -> DIGIT NINE ':' # 0x3A -> COLON ';' # 0x3B -> SEMICOLON '<' # 0x3C -> LESS-THAN SIGN '=' # 0x3D -> EQUALS SIGN '>' # 0x3E -> GREATER-THAN SIGN '?' # 0x3F -> QUESTION MARK '@' # 0x40 -> COMMERCIAL AT 'A' # 0x41 -> LATIN CAPITAL LETTER A 'B' # 0x42 -> LATIN CAPITAL LETTER B 'C' # 0x43 -> LATIN CAPITAL LETTER C 'D' # 0x44 -> LATIN CAPITAL LETTER D 'E' # 0x45 -> LATIN CAPITAL LETTER E 'F' # 0x46 -> LATIN CAPITAL LETTER F 'G' # 0x47 -> LATIN CAPITAL LETTER G 'H' # 0x48 -> LATIN CAPITAL LETTER H 'I' # 0x49 -> LATIN CAPITAL LETTER I 'J' # 0x4A -> LATIN CAPITAL LETTER J 'K' # 0x4B -> LATIN CAPITAL LETTER K 'L' # 0x4C -> LATIN CAPITAL LETTER L 'M' # 0x4D -> LATIN CAPITAL LETTER M 'N' # 0x4E -> LATIN CAPITAL LETTER N 'O' # 0x4F -> LATIN CAPITAL LETTER O 'P' # 0x50 -> LATIN CAPITAL LETTER P 'Q' # 0x51 -> LATIN CAPITAL LETTER Q 'R' # 0x52 -> LATIN CAPITAL LETTER R 'S' # 0x53 -> LATIN CAPITAL LETTER S 'T' # 0x54 -> LATIN CAPITAL LETTER T 'U' # 0x55 -> LATIN CAPITAL LETTER U 'V' # 0x56 -> LATIN CAPITAL LETTER V 'W' # 0x57 -> LATIN CAPITAL LETTER W 'X' # 0x58 -> LATIN CAPITAL LETTER X 'Y' # 0x59 -> LATIN CAPITAL LETTER Y 'Z' # 0x5A -> LATIN CAPITAL LETTER Z '[' # 0x5B -> LEFT SQUARE BRACKET '\\' # 0x5C -> REVERSE SOLIDUS ']' # 0x5D -> RIGHT SQUARE BRACKET '^' # 0x5E -> CIRCUMFLEX ACCENT '_' # 0x5F -> LOW LINE '`' # 0x60 -> GRAVE ACCENT 'a' # 0x61 -> LATIN SMALL LETTER A 'b' # 0x62 -> LATIN SMALL LETTER B 'c' # 0x63 -> LATIN SMALL LETTER C 'd' # 0x64 -> LATIN SMALL LETTER D 'e' # 0x65 -> LATIN SMALL LETTER E 'f' # 0x66 -> LATIN SMALL LETTER F 'g' # 0x67 -> LATIN SMALL LETTER G 'h' # 0x68 -> LATIN SMALL LETTER H 'i' # 0x69 -> LATIN SMALL LETTER I 'j' # 0x6A -> LATIN SMALL LETTER J 'k' # 0x6B -> LATIN SMALL LETTER K 'l' # 0x6C -> LATIN SMALL LETTER L 'm' # 0x6D -> LATIN SMALL LETTER M 'n' # 0x6E -> LATIN SMALL LETTER N 'o' # 0x6F -> LATIN SMALL LETTER O 'p' # 0x70 -> LATIN SMALL LETTER P 'q' # 0x71 -> LATIN SMALL LETTER Q 'r' # 0x72 -> LATIN SMALL LETTER R 's' # 0x73 -> LATIN SMALL LETTER S 't' # 0x74 -> LATIN SMALL LETTER T 'u' # 0x75 -> LATIN SMALL LETTER U 'v' # 0x76 -> LATIN SMALL LETTER V 'w' # 0x77 -> LATIN SMALL LETTER W 'x' # 0x78 -> LATIN SMALL LETTER X 'y' # 0x79 -> LATIN SMALL LETTER Y 'z' # 0x7A -> LATIN SMALL LETTER Z '{' # 0x7B -> LEFT CURLY BRACKET '|' # 0x7C -> VERTICAL LINE '}' # 0x7D -> RIGHT CURLY BRACKET '~' # 0x7E -> TILDE '\x7f' # 0x7F -> DELETE '\u2500' # 0x80 -> BOX DRAWINGS LIGHT HORIZONTAL '\u2502' # 0x81 -> BOX DRAWINGS LIGHT VERTICAL '\u250c' # 0x82 -> BOX DRAWINGS LIGHT DOWN AND RIGHT '\u2510' # 0x83 -> BOX DRAWINGS LIGHT DOWN AND LEFT '\u2514' # 0x84 -> BOX DRAWINGS LIGHT UP AND RIGHT '\u2518' # 0x85 -> BOX DRAWINGS LIGHT UP AND LEFT '\u251c' # 0x86 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT '\u2524' # 0x87 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT '\u252c' # 0x88 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL '\u2534' # 0x89 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL '\u253c' # 0x8A -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL '\u2580' # 0x8B -> UPPER HALF BLOCK '\u2584' # 0x8C -> LOWER HALF BLOCK '\u2588' # 0x8D -> FULL BLOCK '\u258c' # 0x8E -> LEFT HALF BLOCK '\u2590' # 0x8F -> RIGHT HALF BLOCK '\u2591' # 0x90 -> LIGHT SHADE '\u2592' # 0x91 -> MEDIUM SHADE '\u2593' # 0x92 -> DARK SHADE '\u2320' # 0x93 -> TOP HALF INTEGRAL '\u25a0' # 0x94 -> BLACK SQUARE '\u2219' # 0x95 -> BULLET OPERATOR '\u221a' # 0x96 -> SQUARE ROOT '\u2248' # 0x97 -> ALMOST EQUAL TO '\u2264' # 0x98 -> LESS-THAN OR EQUAL TO '\u2265' # 0x99 -> GREATER-THAN OR EQUAL TO '\xa0' # 0x9A -> NO-BREAK SPACE '\u2321' # 0x9B -> BOTTOM HALF INTEGRAL '\xb0' # 0x9C -> DEGREE SIGN '\xb2' # 0x9D -> SUPERSCRIPT TWO '\xb7' # 0x9E -> MIDDLE DOT '\xf7' # 0x9F -> DIVISION SIGN '\u2550' # 0xA0 -> BOX DRAWINGS DOUBLE HORIZONTAL '\u2551' # 0xA1 -> BOX DRAWINGS DOUBLE VERTICAL '\u2552' # 0xA2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE '\u0451' # 0xA3 -> CYRILLIC SMALL LETTER IO '\u0454' # 0xA4 -> CYRILLIC SMALL LETTER UKRAINIAN IE '\u2554' # 0xA5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT '\u0456' # 0xA6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I '\u0457' # 0xA7 -> CYRILLIC SMALL LETTER YI (UKRAINIAN) '\u2557' # 0xA8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT '\u2558' # 0xA9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE '\u2559' # 0xAA -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE '\u255a' # 0xAB -> BOX DRAWINGS DOUBLE UP AND RIGHT '\u255b' # 0xAC -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE '\u0491' # 0xAD -> CYRILLIC SMALL LETTER UKRAINIAN GHE WITH UPTURN '\u255d' # 0xAE -> BOX DRAWINGS DOUBLE UP AND LEFT '\u255e' # 0xAF -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE '\u255f' # 0xB0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE '\u2560' # 0xB1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT '\u2561' # 0xB2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE '\u0401' # 0xB3 -> CYRILLIC CAPITAL LETTER IO '\u0404' # 0xB4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE '\u2563' # 0xB5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT '\u0406' # 0xB6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I '\u0407' # 0xB7 -> CYRILLIC CAPITAL LETTER YI (UKRAINIAN) '\u2566' # 0xB8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL '\u2567' # 0xB9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE '\u2568' # 0xBA -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE '\u2569' # 0xBB -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL '\u256a' # 0xBC -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE '\u0490' # 0xBD -> CYRILLIC CAPITAL LETTER UKRAINIAN GHE WITH UPTURN '\u256c' # 0xBE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL '\xa9' # 0xBF -> COPYRIGHT SIGN '\u044e' # 0xC0 -> CYRILLIC SMALL LETTER YU '\u0430' # 0xC1 -> CYRILLIC SMALL LETTER A '\u0431' # 0xC2 -> CYRILLIC SMALL LETTER BE '\u0446' # 0xC3 -> CYRILLIC SMALL LETTER TSE '\u0434' # 0xC4 -> CYRILLIC SMALL LETTER DE '\u0435' # 0xC5 -> CYRILLIC SMALL LETTER IE '\u0444' # 0xC6 -> CYRILLIC SMALL LETTER EF '\u0433' # 0xC7 -> CYRILLIC SMALL LETTER GHE '\u0445' # 0xC8 -> CYRILLIC SMALL LETTER HA '\u0438' # 0xC9 -> CYRILLIC SMALL LETTER I '\u0439' # 0xCA -> CYRILLIC SMALL LETTER SHORT I '\u043a' # 0xCB -> CYRILLIC SMALL LETTER KA '\u043b' # 0xCC -> CYRILLIC SMALL LETTER EL '\u043c' # 0xCD -> CYRILLIC SMALL LETTER EM '\u043d' # 0xCE -> CYRILLIC SMALL LETTER EN '\u043e' # 0xCF -> CYRILLIC SMALL LETTER O '\u043f' # 0xD0 -> CYRILLIC SMALL LETTER PE '\u044f' # 0xD1 -> CYRILLIC SMALL LETTER YA '\u0440' # 0xD2 -> CYRILLIC SMALL LETTER ER '\u0441' # 0xD3 -> CYRILLIC SMALL LETTER ES '\u0442' # 0xD4 -> CYRILLIC SMALL LETTER TE '\u0443' # 0xD5 -> CYRILLIC SMALL LETTER U '\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE '\u0432' # 0xD7 -> CYRILLIC SMALL LETTER VE '\u044c' # 0xD8 -> CYRILLIC SMALL LETTER SOFT SIGN '\u044b' # 0xD9 -> CYRILLIC SMALL LETTER YERU '\u0437' # 0xDA -> CYRILLIC SMALL LETTER ZE '\u0448' # 0xDB -> CYRILLIC SMALL LETTER SHA '\u044d' # 0xDC -> CYRILLIC SMALL LETTER E '\u0449' # 0xDD -> CYRILLIC SMALL LETTER SHCHA '\u0447' # 0xDE -> CYRILLIC SMALL LETTER CHE '\u044a' # 0xDF -> CYRILLIC SMALL LETTER HARD SIGN '\u042e' # 0xE0 -> CYRILLIC CAPITAL LETTER YU '\u0410' # 0xE1 -> CYRILLIC CAPITAL LETTER A '\u0411' # 0xE2 -> CYRILLIC CAPITAL LETTER BE '\u0426' # 0xE3 -> CYRILLIC CAPITAL LETTER TSE '\u0414' # 0xE4 -> CYRILLIC CAPITAL LETTER DE '\u0415' # 0xE5 -> CYRILLIC CAPITAL LETTER IE '\u0424' # 0xE6 -> CYRILLIC CAPITAL LETTER EF '\u0413' # 0xE7 -> CYRILLIC CAPITAL LETTER GHE '\u0425' # 0xE8 -> CYRILLIC CAPITAL LETTER HA '\u0418' # 0xE9 -> CYRILLIC CAPITAL LETTER I '\u0419' # 0xEA -> CYRILLIC CAPITAL LETTER SHORT I '\u041a' # 0xEB -> CYRILLIC CAPITAL LETTER KA '\u041b' # 0xEC -> CYRILLIC CAPITAL LETTER EL '\u041c' # 0xED -> CYRILLIC CAPITAL LETTER EM '\u041d' # 0xEE -> CYRILLIC CAPITAL LETTER EN '\u041e' # 0xEF -> CYRILLIC CAPITAL LETTER O '\u041f' # 0xF0 -> CYRILLIC CAPITAL LETTER PE '\u042f' # 0xF1 -> CYRILLIC CAPITAL LETTER YA '\u0420' # 0xF2 -> CYRILLIC CAPITAL LETTER ER '\u0421' # 0xF3 -> CYRILLIC CAPITAL LETTER ES '\u0422' # 0xF4 -> CYRILLIC CAPITAL LETTER TE '\u0423' # 0xF5 -> CYRILLIC CAPITAL LETTER U '\u0416' # 0xF6 -> CYRILLIC CAPITAL LETTER ZHE '\u0412' # 0xF7 -> CYRILLIC CAPITAL LETTER VE '\u042c' # 0xF8 -> CYRILLIC CAPITAL LETTER SOFT SIGN '\u042b' # 0xF9 -> CYRILLIC CAPITAL LETTER YERU '\u0417' # 0xFA -> CYRILLIC CAPITAL LETTER ZE '\u0428' # 0xFB -> CYRILLIC CAPITAL LETTER SHA '\u042d' # 0xFC -> CYRILLIC CAPITAL LETTER E '\u0429' # 0xFD -> CYRILLIC CAPITAL LETTER SHCHA '\u0427' # 0xFE -> CYRILLIC CAPITAL LETTER CHE '\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) punycode.py 0000644 00000015343 15030477433 0006760 0 ustar 00 """ Codec for the Punicode encoding, as specified in RFC 3492 Written by Martin v. Löwis. """ import codecs ##################### Encoding ##################################### def segregate(str): """3.1 Basic code point segregation""" base = bytearray() extended = set() for c in str: if ord(c) < 128: base.append(ord(c)) else: extended.add(c) extended = sorted(extended) return bytes(base), extended def selective_len(str, max): """Return the length of str, considering only characters below max.""" res = 0 for c in str: if ord(c) < max: res += 1 return res def selective_find(str, char, index, pos): """Return a pair (index, pos), indicating the next occurrence of char in str. index is the position of the character considering only ordinals up to and including char, and pos is the position in the full string. index/pos is the starting position in the full string.""" l = len(str) while 1: pos += 1 if pos == l: return (-1, -1) c = str[pos] if c == char: return index+1, pos elif c < char: index += 1 def insertion_unsort(str, extended): """3.2 Insertion unsort coding""" oldchar = 0x80 result = [] oldindex = -1 for c in extended: index = pos = -1 char = ord(c) curlen = selective_len(str, char) delta = (curlen+1) * (char - oldchar) while 1: index,pos = selective_find(str,c,index,pos) if index == -1: break delta += index - oldindex result.append(delta-1) oldindex = index delta = 0 oldchar = char return result def T(j, bias): # Punycode parameters: tmin = 1, tmax = 26, base = 36 res = 36 * (j + 1) - bias if res < 1: return 1 if res > 26: return 26 return res digits = b"abcdefghijklmnopqrstuvwxyz0123456789" def generate_generalized_integer(N, bias): """3.3 Generalized variable-length integers""" result = bytearray() j = 0 while 1: t = T(j, bias) if N < t: result.append(digits[N]) return bytes(result) result.append(digits[t + ((N - t) % (36 - t))]) N = (N - t) // (36 - t) j += 1 def adapt(delta, first, numchars): if first: delta //= 700 else: delta //= 2 delta += delta // numchars # ((base - tmin) * tmax) // 2 == 455 divisions = 0 while delta > 455: delta = delta // 35 # base - tmin divisions += 36 bias = divisions + (36 * delta // (delta + 38)) return bias def generate_integers(baselen, deltas): """3.4 Bias adaptation""" # Punycode parameters: initial bias = 72, damp = 700, skew = 38 result = bytearray() bias = 72 for points, delta in enumerate(deltas): s = generate_generalized_integer(delta, bias) result.extend(s) bias = adapt(delta, points==0, baselen+points+1) return bytes(result) def punycode_encode(text): base, extended = segregate(text) deltas = insertion_unsort(text, extended) extended = generate_integers(len(base), deltas) if base: return base + b"-" + extended return extended ##################### Decoding ##################################### def decode_generalized_number(extended, extpos, bias, errors): """3.3 Generalized variable-length integers""" result = 0 w = 1 j = 0 while 1: try: char = ord(extended[extpos]) except IndexError: if errors == "strict": raise UnicodeError("incomplete punicode string") return extpos + 1, None extpos += 1 if 0x41 <= char <= 0x5A: # A-Z digit = char - 0x41 elif 0x30 <= char <= 0x39: digit = char - 22 # 0x30-26 elif errors == "strict": raise UnicodeError("Invalid extended code point '%s'" % extended[extpos-1]) else: return extpos, None t = T(j, bias) result += digit * w if digit < t: return extpos, result w = w * (36 - t) j += 1 def insertion_sort(base, extended, errors): """3.2 Insertion unsort coding""" char = 0x80 pos = -1 bias = 72 extpos = 0 while extpos < len(extended): newpos, delta = decode_generalized_number(extended, extpos, bias, errors) if delta is None: # There was an error in decoding. We can't continue because # synchronization is lost. return base pos += delta+1 char += pos // (len(base) + 1) if char > 0x10FFFF: if errors == "strict": raise UnicodeError("Invalid character U+%x" % char) char = ord('?') pos = pos % (len(base) + 1) base = base[:pos] + chr(char) + base[pos:] bias = adapt(delta, (extpos == 0), len(base)) extpos = newpos return base def punycode_decode(text, errors): if isinstance(text, str): text = text.encode("ascii") if isinstance(text, memoryview): text = bytes(text) pos = text.rfind(b"-") if pos == -1: base = "" extended = str(text, "ascii").upper() else: base = str(text[:pos], "ascii", errors) extended = str(text[pos+1:], "ascii").upper() return insertion_sort(base, extended, errors) ### Codec APIs class Codec(codecs.Codec): def encode(self, input, errors='strict'): res = punycode_encode(input) return res, len(input) def decode(self, input, errors='strict'): if errors not in ('strict', 'replace', 'ignore'): raise UnicodeError("Unsupported error handling "+errors) res = punycode_decode(input, errors) return res, len(input) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return punycode_encode(input) class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): if self.errors not in ('strict', 'replace', 'ignore'): raise UnicodeError("Unsupported error handling "+self.errors) return punycode_decode(input, self.errors) class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='punycode', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) ascii.py 0000644 00000002340 15030477433 0006213 0 ustar 00 """ Python 'ascii' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs class Codec(codecs.Codec): # Note: Binding these as C functions will result in the class not # converting them to methods. This is intended. encode = codecs.ascii_encode decode = codecs.ascii_decode class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.ascii_encode(input, self.errors)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.ascii_decode(input, self.errors)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass class StreamConverter(StreamWriter,StreamReader): encode = codecs.ascii_decode decode = codecs.ascii_encode ### encodings module API def getregentry(): return codecs.CodecInfo( name='ascii', encode=Codec.encode, decode=Codec.decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) cp950.py 0000644 00000001777 15030477433 0006000 0 ustar 00 # # cp950.py: Python Unicode Codec for CP950 # # Written by Hye-Shik Chang <perky@FreeBSD.org> # import _codecs_tw, codecs import _multibytecodec as mbc codec = _codecs_tw.getcodec('cp950') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='cp950', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) utf_7.py 0000644 00000001662 15030477433 0006155 0 ustar 00 """ Python 'utf-7' Codec Written by Brian Quinlan (brian@sweetapp.com). """ import codecs ### Codec APIs encode = codecs.utf_7_encode def decode(input, errors='strict'): return codecs.utf_7_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.utf_7_encode(input, self.errors)[0] class IncrementalDecoder(codecs.BufferedIncrementalDecoder): _buffer_decode = codecs.utf_7_decode class StreamWriter(codecs.StreamWriter): encode = codecs.utf_7_encode class StreamReader(codecs.StreamReader): decode = codecs.utf_7_decode ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-7', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) cp850.py 0000644 00000102471 15030477433 0005770 0 ustar 00 """ Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP850.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp850', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE 0x009e: 0x00d7, # MULTIPLICATION SIGN 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x00ae, # REGISTERED SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE 0x00b8: 0x00a9, # COPYRIGHT SIGN 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x00a2, # CENT SIGN 0x00be: 0x00a5, # YEN SIGN 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x00a4, # CURRENCY SIGN 0x00d0: 0x00f0, # LATIN SMALL LETTER ETH 0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE 0x00d5: 0x0131, # LATIN SMALL LETTER DOTLESS I 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x00a6, # BROKEN BAR 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x00fe, # LATIN SMALL LETTER THORN 0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00ee: 0x00af, # MACRON 0x00ef: 0x00b4, # ACUTE ACCENT 0x00f0: 0x00ad, # SOFT HYPHEN 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2017, # DOUBLE LOW LINE 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS 0x00f4: 0x00b6, # PILCROW SIGN 0x00f5: 0x00a7, # SECTION SIGN 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x00b8, # CEDILLA 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x00a8, # DIAERESIS 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x00b9, # SUPERSCRIPT ONE 0x00fc: 0x00b3, # SUPERSCRIPT THREE 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( '\x00' # 0x0000 -> NULL '\x01' # 0x0001 -> START OF HEADING '\x02' # 0x0002 -> START OF TEXT '\x03' # 0x0003 -> END OF TEXT '\x04' # 0x0004 -> END OF TRANSMISSION '\x05' # 0x0005 -> ENQUIRY '\x06' # 0x0006 -> ACKNOWLEDGE '\x07' # 0x0007 -> BELL '\x08' # 0x0008 -> BACKSPACE '\t' # 0x0009 -> HORIZONTAL TABULATION '\n' # 0x000a -> LINE FEED '\x0b' # 0x000b -> VERTICAL TABULATION '\x0c' # 0x000c -> FORM FEED '\r' # 0x000d -> CARRIAGE RETURN '\x0e' # 0x000e -> SHIFT OUT '\x0f' # 0x000f -> SHIFT IN '\x10' # 0x0010 -> DATA LINK ESCAPE '\x11' # 0x0011 -> DEVICE CONTROL ONE '\x12' # 0x0012 -> DEVICE CONTROL TWO '\x13' # 0x0013 -> DEVICE CONTROL THREE '\x14' # 0x0014 -> DEVICE CONTROL FOUR '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE '\x16' # 0x0016 -> SYNCHRONOUS IDLE '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK '\x18' # 0x0018 -> CANCEL '\x19' # 0x0019 -> END OF MEDIUM '\x1a' # 0x001a -> SUBSTITUTE '\x1b' # 0x001b -> ESCAPE '\x1c' # 0x001c -> FILE SEPARATOR '\x1d' # 0x001d -> GROUP SEPARATOR '\x1e' # 0x001e -> RECORD SEPARATOR '\x1f' # 0x001f -> UNIT SEPARATOR ' ' # 0x0020 -> SPACE '!' # 0x0021 -> EXCLAMATION MARK '"' # 0x0022 -> QUOTATION MARK '#' # 0x0023 -> NUMBER SIGN '$' # 0x0024 -> DOLLAR SIGN '%' # 0x0025 -> PERCENT SIGN '&' # 0x0026 -> AMPERSAND "'" # 0x0027 -> APOSTROPHE '(' # 0x0028 -> LEFT PARENTHESIS ')' # 0x0029 -> RIGHT PARENTHESIS '*' # 0x002a -> ASTERISK '+' # 0x002b -> PLUS SIGN ',' # 0x002c -> COMMA '-' # 0x002d -> HYPHEN-MINUS '.' # 0x002e -> FULL STOP '/' # 0x002f -> SOLIDUS '0' # 0x0030 -> DIGIT ZERO '1' # 0x0031 -> DIGIT ONE '2' # 0x0032 -> DIGIT TWO '3' # 0x0033 -> DIGIT THREE '4' # 0x0034 -> DIGIT FOUR '5' # 0x0035 -> DIGIT FIVE '6' # 0x0036 -> DIGIT SIX '7' # 0x0037 -> DIGIT SEVEN '8' # 0x0038 -> DIGIT EIGHT '9' # 0x0039 -> DIGIT NINE ':' # 0x003a -> COLON ';' # 0x003b -> SEMICOLON '<' # 0x003c -> LESS-THAN SIGN '=' # 0x003d -> EQUALS SIGN '>' # 0x003e -> GREATER-THAN SIGN '?' # 0x003f -> QUESTION MARK '@' # 0x0040 -> COMMERCIAL AT 'A' # 0x0041 -> LATIN CAPITAL LETTER A 'B' # 0x0042 -> LATIN CAPITAL LETTER B 'C' # 0x0043 -> LATIN CAPITAL LETTER C 'D' # 0x0044 -> LATIN CAPITAL LETTER D 'E' # 0x0045 -> LATIN CAPITAL LETTER E 'F' # 0x0046 -> LATIN CAPITAL LETTER F 'G' # 0x0047 -> LATIN CAPITAL LETTER G 'H' # 0x0048 -> LATIN CAPITAL LETTER H 'I' # 0x0049 -> LATIN CAPITAL LETTER I 'J' # 0x004a -> LATIN CAPITAL LETTER J 'K' # 0x004b -> LATIN CAPITAL LETTER K 'L' # 0x004c -> LATIN CAPITAL LETTER L 'M' # 0x004d -> LATIN CAPITAL LETTER M 'N' # 0x004e -> LATIN CAPITAL LETTER N 'O' # 0x004f -> LATIN CAPITAL LETTER O 'P' # 0x0050 -> LATIN CAPITAL LETTER P 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q 'R' # 0x0052 -> LATIN CAPITAL LETTER R 'S' # 0x0053 -> LATIN CAPITAL LETTER S 'T' # 0x0054 -> LATIN CAPITAL LETTER T 'U' # 0x0055 -> LATIN CAPITAL LETTER U 'V' # 0x0056 -> LATIN CAPITAL LETTER V 'W' # 0x0057 -> LATIN CAPITAL LETTER W 'X' # 0x0058 -> LATIN CAPITAL LETTER X 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y 'Z' # 0x005a -> LATIN CAPITAL LETTER Z '[' # 0x005b -> LEFT SQUARE BRACKET '\\' # 0x005c -> REVERSE SOLIDUS ']' # 0x005d -> RIGHT SQUARE BRACKET '^' # 0x005e -> CIRCUMFLEX ACCENT '_' # 0x005f -> LOW LINE '`' # 0x0060 -> GRAVE ACCENT 'a' # 0x0061 -> LATIN SMALL LETTER A 'b' # 0x0062 -> LATIN SMALL LETTER B 'c' # 0x0063 -> LATIN SMALL LETTER C 'd' # 0x0064 -> LATIN SMALL LETTER D 'e' # 0x0065 -> LATIN SMALL LETTER E 'f' # 0x0066 -> LATIN SMALL LETTER F 'g' # 0x0067 -> LATIN SMALL LETTER G 'h' # 0x0068 -> LATIN SMALL LETTER H 'i' # 0x0069 -> LATIN SMALL LETTER I 'j' # 0x006a -> LATIN SMALL LETTER J 'k' # 0x006b -> LATIN SMALL LETTER K 'l' # 0x006c -> LATIN SMALL LETTER L 'm' # 0x006d -> LATIN SMALL LETTER M 'n' # 0x006e -> LATIN SMALL LETTER N 'o' # 0x006f -> LATIN SMALL LETTER O 'p' # 0x0070 -> LATIN SMALL LETTER P 'q' # 0x0071 -> LATIN SMALL LETTER Q 'r' # 0x0072 -> LATIN SMALL LETTER R 's' # 0x0073 -> LATIN SMALL LETTER S 't' # 0x0074 -> LATIN SMALL LETTER T 'u' # 0x0075 -> LATIN SMALL LETTER U 'v' # 0x0076 -> LATIN SMALL LETTER V 'w' # 0x0077 -> LATIN SMALL LETTER W 'x' # 0x0078 -> LATIN SMALL LETTER X 'y' # 0x0079 -> LATIN SMALL LETTER Y 'z' # 0x007a -> LATIN SMALL LETTER Z '{' # 0x007b -> LEFT CURLY BRACKET '|' # 0x007c -> VERTICAL LINE '}' # 0x007d -> RIGHT CURLY BRACKET '~' # 0x007e -> TILDE '\x7f' # 0x007f -> DELETE '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE '\xa3' # 0x009c -> POUND SIGN '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE '\xd7' # 0x009e -> MULTIPLICATION SIGN '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR '\xbf' # 0x00a8 -> INVERTED QUESTION MARK '\xae' # 0x00a9 -> REGISTERED SIGN '\xac' # 0x00aa -> NOT SIGN '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK '\u2591' # 0x00b0 -> LIGHT SHADE '\u2592' # 0x00b1 -> MEDIUM SHADE '\u2593' # 0x00b2 -> DARK SHADE '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX '\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE '\xa9' # 0x00b8 -> COPYRIGHT SIGN '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT '\xa2' # 0x00bd -> CENT SIGN '\xa5' # 0x00be -> YEN SIGN '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL '\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE '\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL '\xa4' # 0x00cf -> CURRENCY SIGN '\xf0' # 0x00d0 -> LATIN SMALL LETTER ETH '\xd0' # 0x00d1 -> LATIN CAPITAL LETTER ETH '\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS '\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE '\u0131' # 0x00d5 -> LATIN SMALL LETTER DOTLESS I '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX '\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT '\u2588' # 0x00db -> FULL BLOCK '\u2584' # 0x00dc -> LOWER HALF BLOCK '\xa6' # 0x00dd -> BROKEN BAR '\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE '\u2580' # 0x00df -> UPPER HALF BLOCK '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX '\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE '\xb5' # 0x00e6 -> MICRO SIGN '\xfe' # 0x00e7 -> LATIN SMALL LETTER THORN '\xde' # 0x00e8 -> LATIN CAPITAL LETTER THORN '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE '\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX '\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE '\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE '\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE '\xaf' # 0x00ee -> MACRON '\xb4' # 0x00ef -> ACUTE ACCENT '\xad' # 0x00f0 -> SOFT HYPHEN '\xb1' # 0x00f1 -> PLUS-MINUS SIGN '\u2017' # 0x00f2 -> DOUBLE LOW LINE '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS '\xb6' # 0x00f4 -> PILCROW SIGN '\xa7' # 0x00f5 -> SECTION SIGN '\xf7' # 0x00f6 -> DIVISION SIGN '\xb8' # 0x00f7 -> CEDILLA '\xb0' # 0x00f8 -> DEGREE SIGN '\xa8' # 0x00f9 -> DIAERESIS '\xb7' # 0x00fa -> MIDDLE DOT '\xb9' # 0x00fb -> SUPERSCRIPT ONE '\xb3' # 0x00fc -> SUPERSCRIPT THREE '\xb2' # 0x00fd -> SUPERSCRIPT TWO '\u25a0' # 0x00fe -> BLACK SQUARE '\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a2: 0x00bd, # CENT SIGN 0x00a3: 0x009c, # POUND SIGN 0x00a4: 0x00cf, # CURRENCY SIGN 0x00a5: 0x00be, # YEN SIGN 0x00a6: 0x00dd, # BROKEN BAR 0x00a7: 0x00f5, # SECTION SIGN 0x00a8: 0x00f9, # DIAERESIS 0x00a9: 0x00b8, # COPYRIGHT SIGN 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00ad: 0x00f0, # SOFT HYPHEN 0x00ae: 0x00a9, # REGISTERED SIGN 0x00af: 0x00ee, # MACRON 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b3: 0x00fc, # SUPERSCRIPT THREE 0x00b4: 0x00ef, # ACUTE ACCENT 0x00b5: 0x00e6, # MICRO SIGN 0x00b6: 0x00f4, # PILCROW SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00b8: 0x00f7, # CEDILLA 0x00b9: 0x00fb, # SUPERSCRIPT ONE 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS 0x00d0: 0x00d1, # LATIN CAPITAL LETTER ETH 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00d7: 0x009e, # MULTIPLICATION SIGN 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00de: 0x00e8, # LATIN CAPITAL LETTER THORN 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS 0x00f0: 0x00d0, # LATIN SMALL LETTER ETH 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x00f6, # DIVISION SIGN 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE 0x00fe: 0x00e7, # LATIN SMALL LETTER THORN 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS 0x0131: 0x00d5, # LATIN SMALL LETTER DOTLESS I 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK 0x2017: 0x00f2, # DOUBLE LOW LINE 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } hex_codec.py 0000644 00000002744 15030477433 0007054 0 ustar 00 """Python 'hex_codec' Codec - 2-digit hex content transfer encoding. This codec de/encodes from bytes to bytes. Written by Marc-Andre Lemburg (mal@lemburg.com). """ import codecs import binascii ### Codec APIs def hex_encode(input, errors='strict'): assert errors == 'strict' return (binascii.b2a_hex(input), len(input)) def hex_decode(input, errors='strict'): assert errors == 'strict' return (binascii.a2b_hex(input), len(input)) class Codec(codecs.Codec): def encode(self, input, errors='strict'): return hex_encode(input, errors) def decode(self, input, errors='strict'): return hex_decode(input, errors) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): assert self.errors == 'strict' return binascii.b2a_hex(input) class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): assert self.errors == 'strict' return binascii.a2b_hex(input) class StreamWriter(Codec, codecs.StreamWriter): charbuffertype = bytes class StreamReader(Codec, codecs.StreamReader): charbuffertype = bytes ### encodings module API def getregentry(): return codecs.CodecInfo( name='hex', encode=hex_encode, decode=hex_decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, _is_text_encoding=False, ) cp1258.py 0000644 00000032064 15030477433 0006053 0 ustar 00 """ Python Character Mapping Codec cp1258 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1258', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( '\x00' # 0x00 -> NULL '\x01' # 0x01 -> START OF HEADING '\x02' # 0x02 -> START OF TEXT '\x03' # 0x03 -> END OF TEXT '\x04' # 0x04 -> END OF TRANSMISSION '\x05' # 0x05 -> ENQUIRY '\x06' # 0x06 -> ACKNOWLEDGE '\x07' # 0x07 -> BELL '\x08' # 0x08 -> BACKSPACE '\t' # 0x09 -> HORIZONTAL TABULATION '\n' # 0x0A -> LINE FEED '\x0b' # 0x0B -> VERTICAL TABULATION '\x0c' # 0x0C -> FORM FEED '\r' # 0x0D -> CARRIAGE RETURN '\x0e' # 0x0E -> SHIFT OUT '\x0f' # 0x0F -> SHIFT IN '\x10' # 0x10 -> DATA LINK ESCAPE '\x11' # 0x11 -> DEVICE CONTROL ONE '\x12' # 0x12 -> DEVICE CONTROL TWO '\x13' # 0x13 -> DEVICE CONTROL THREE '\x14' # 0x14 -> DEVICE CONTROL FOUR '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE '\x16' # 0x16 -> SYNCHRONOUS IDLE '\x17' # 0x17 -> END OF TRANSMISSION BLOCK '\x18' # 0x18 -> CANCEL '\x19' # 0x19 -> END OF MEDIUM '\x1a' # 0x1A -> SUBSTITUTE '\x1b' # 0x1B -> ESCAPE '\x1c' # 0x1C -> FILE SEPARATOR '\x1d' # 0x1D -> GROUP SEPARATOR '\x1e' # 0x1E -> RECORD SEPARATOR '\x1f' # 0x1F -> UNIT SEPARATOR ' ' # 0x20 -> SPACE '!' # 0x21 -> EXCLAMATION MARK '"' # 0x22 -> QUOTATION MARK '#' # 0x23 -> NUMBER SIGN '$' # 0x24 -> DOLLAR SIGN '%' # 0x25 -> PERCENT SIGN '&' # 0x26 -> AMPERSAND "'" # 0x27 -> APOSTROPHE '(' # 0x28 -> LEFT PARENTHESIS ')' # 0x29 -> RIGHT PARENTHESIS '*' # 0x2A -> ASTERISK '+' # 0x2B -> PLUS SIGN ',' # 0x2C -> COMMA '-' # 0x2D -> HYPHEN-MINUS '.' # 0x2E -> FULL STOP '/' # 0x2F -> SOLIDUS '0' # 0x30 -> DIGIT ZERO '1' # 0x31 -> DIGIT ONE '2' # 0x32 -> DIGIT TWO '3' # 0x33 -> DIGIT THREE '4' # 0x34 -> DIGIT FOUR '5' # 0x35 -> DIGIT FIVE '6' # 0x36 -> DIGIT SIX '7' # 0x37 -> DIGIT SEVEN '8' # 0x38 -> DIGIT EIGHT '9' # 0x39 -> DIGIT NINE ':' # 0x3A -> COLON ';' # 0x3B -> SEMICOLON '<' # 0x3C -> LESS-THAN SIGN '=' # 0x3D -> EQUALS SIGN '>' # 0x3E -> GREATER-THAN SIGN '?' # 0x3F -> QUESTION MARK '@' # 0x40 -> COMMERCIAL AT 'A' # 0x41 -> LATIN CAPITAL LETTER A 'B' # 0x42 -> LATIN CAPITAL LETTER B 'C' # 0x43 -> LATIN CAPITAL LETTER C 'D' # 0x44 -> LATIN CAPITAL LETTER D 'E' # 0x45 -> LATIN CAPITAL LETTER E 'F' # 0x46 -> LATIN CAPITAL LETTER F 'G' # 0x47 -> LATIN CAPITAL LETTER G 'H' # 0x48 -> LATIN CAPITAL LETTER H 'I' # 0x49 -> LATIN CAPITAL LETTER I 'J' # 0x4A -> LATIN CAPITAL LETTER J 'K' # 0x4B -> LATIN CAPITAL LETTER K 'L' # 0x4C -> LATIN CAPITAL LETTER L 'M' # 0x4D -> LATIN CAPITAL LETTER M 'N' # 0x4E -> LATIN CAPITAL LETTER N 'O' # 0x4F -> LATIN CAPITAL LETTER O 'P' # 0x50 -> LATIN CAPITAL LETTER P 'Q' # 0x51 -> LATIN CAPITAL LETTER Q 'R' # 0x52 -> LATIN CAPITAL LETTER R 'S' # 0x53 -> LATIN CAPITAL LETTER S 'T' # 0x54 -> LATIN CAPITAL LETTER T 'U' # 0x55 -> LATIN CAPITAL LETTER U 'V' # 0x56 -> LATIN CAPITAL LETTER V 'W' # 0x57 -> LATIN CAPITAL LETTER W 'X' # 0x58 -> LATIN CAPITAL LETTER X 'Y' # 0x59 -> LATIN CAPITAL LETTER Y 'Z' # 0x5A -> LATIN CAPITAL LETTER Z '[' # 0x5B -> LEFT SQUARE BRACKET '\\' # 0x5C -> REVERSE SOLIDUS ']' # 0x5D -> RIGHT SQUARE BRACKET '^' # 0x5E -> CIRCUMFLEX ACCENT '_' # 0x5F -> LOW LINE '`' # 0x60 -> GRAVE ACCENT 'a' # 0x61 -> LATIN SMALL LETTER A 'b' # 0x62 -> LATIN SMALL LETTER B 'c' # 0x63 -> LATIN SMALL LETTER C 'd' # 0x64 -> LATIN SMALL LETTER D 'e' # 0x65 -> LATIN SMALL LETTER E 'f' # 0x66 -> LATIN SMALL LETTER F 'g' # 0x67 -> LATIN SMALL LETTER G 'h' # 0x68 -> LATIN SMALL LETTER H 'i' # 0x69 -> LATIN SMALL LETTER I 'j' # 0x6A -> LATIN SMALL LETTER J 'k' # 0x6B -> LATIN SMALL LETTER K 'l' # 0x6C -> LATIN SMALL LETTER L 'm' # 0x6D -> LATIN SMALL LETTER M 'n' # 0x6E -> LATIN SMALL LETTER N 'o' # 0x6F -> LATIN SMALL LETTER O 'p' # 0x70 -> LATIN SMALL LETTER P 'q' # 0x71 -> LATIN SMALL LETTER Q 'r' # 0x72 -> LATIN SMALL LETTER R 's' # 0x73 -> LATIN SMALL LETTER S 't' # 0x74 -> LATIN SMALL LETTER T 'u' # 0x75 -> LATIN SMALL LETTER U 'v' # 0x76 -> LATIN SMALL LETTER V 'w' # 0x77 -> LATIN SMALL LETTER W 'x' # 0x78 -> LATIN SMALL LETTER X 'y' # 0x79 -> LATIN SMALL LETTER Y 'z' # 0x7A -> LATIN SMALL LETTER Z '{' # 0x7B -> LEFT CURLY BRACKET '|' # 0x7C -> VERTICAL LINE '}' # 0x7D -> RIGHT CURLY BRACKET '~' # 0x7E -> TILDE '\x7f' # 0x7F -> DELETE '\u20ac' # 0x80 -> EURO SIGN '\ufffe' # 0x81 -> UNDEFINED '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS '\u2020' # 0x86 -> DAGGER '\u2021' # 0x87 -> DOUBLE DAGGER '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT '\u2030' # 0x89 -> PER MILLE SIGN '\ufffe' # 0x8A -> UNDEFINED '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE '\ufffe' # 0x8D -> UNDEFINED '\ufffe' # 0x8E -> UNDEFINED '\ufffe' # 0x8F -> UNDEFINED '\ufffe' # 0x90 -> UNDEFINED '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK '\u2022' # 0x95 -> BULLET '\u2013' # 0x96 -> EN DASH '\u2014' # 0x97 -> EM DASH '\u02dc' # 0x98 -> SMALL TILDE '\u2122' # 0x99 -> TRADE MARK SIGN '\ufffe' # 0x9A -> UNDEFINED '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE '\ufffe' # 0x9D -> UNDEFINED '\ufffe' # 0x9E -> UNDEFINED '\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS '\xa0' # 0xA0 -> NO-BREAK SPACE '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK '\xa2' # 0xA2 -> CENT SIGN '\xa3' # 0xA3 -> POUND SIGN '\xa4' # 0xA4 -> CURRENCY SIGN '\xa5' # 0xA5 -> YEN SIGN '\xa6' # 0xA6 -> BROKEN BAR '\xa7' # 0xA7 -> SECTION SIGN '\xa8' # 0xA8 -> DIAERESIS '\xa9' # 0xA9 -> COPYRIGHT SIGN '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK '\xac' # 0xAC -> NOT SIGN '\xad' # 0xAD -> SOFT HYPHEN '\xae' # 0xAE -> REGISTERED SIGN '\xaf' # 0xAF -> MACRON '\xb0' # 0xB0 -> DEGREE SIGN '\xb1' # 0xB1 -> PLUS-MINUS SIGN '\xb2' # 0xB2 -> SUPERSCRIPT TWO '\xb3' # 0xB3 -> SUPERSCRIPT THREE '\xb4' # 0xB4 -> ACUTE ACCENT '\xb5' # 0xB5 -> MICRO SIGN '\xb6' # 0xB6 -> PILCROW SIGN '\xb7' # 0xB7 -> MIDDLE DOT '\xb8' # 0xB8 -> CEDILLA '\xb9' # 0xB9 -> SUPERSCRIPT ONE '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS '\xbf' # 0xBF -> INVERTED QUESTION MARK '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX '\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS '\u0300' # 0xCC -> COMBINING GRAVE ACCENT '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE '\u0309' # 0xD2 -> COMBINING HOOK ABOVE '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX '\u01a0' # 0xD5 -> LATIN CAPITAL LETTER O WITH HORN '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS '\xd7' # 0xD7 -> MULTIPLICATION SIGN '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS '\u01af' # 0xDD -> LATIN CAPITAL LETTER U WITH HORN '\u0303' # 0xDE -> COMBINING TILDE '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX '\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE '\xe6' # 0xE6 -> LATIN SMALL LETTER AE '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS '\u0301' # 0xEC -> COMBINING ACUTE ACCENT '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE '\u0323' # 0xF2 -> COMBINING DOT BELOW '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX '\u01a1' # 0xF5 -> LATIN SMALL LETTER O WITH HORN '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS '\xf7' # 0xF7 -> DIVISION SIGN '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS '\u01b0' # 0xFD -> LATIN SMALL LETTER U WITH HORN '\u20ab' # 0xFE -> DONG SIGN '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) kz1048.py 0000644 00000032633 15030477433 0006074 0 ustar 00 """ Python Character Mapping Codec kz1048 generated from 'MAPPINGS/VENDORS/MISC/KZ1048.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self, input, errors='strict'): return codecs.charmap_encode(input, errors, encoding_table) def decode(self, input, errors='strict'): return codecs.charmap_decode(input, errors, decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input, self.errors, encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input, self.errors, decoding_table)[0] class StreamWriter(Codec, codecs.StreamWriter): pass class StreamReader(Codec, codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='kz1048', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( '\x00' # 0x00 -> NULL '\x01' # 0x01 -> START OF HEADING '\x02' # 0x02 -> START OF TEXT '\x03' # 0x03 -> END OF TEXT '\x04' # 0x04 -> END OF TRANSMISSION '\x05' # 0x05 -> ENQUIRY '\x06' # 0x06 -> ACKNOWLEDGE '\x07' # 0x07 -> BELL '\x08' # 0x08 -> BACKSPACE '\t' # 0x09 -> HORIZONTAL TABULATION '\n' # 0x0A -> LINE FEED '\x0b' # 0x0B -> VERTICAL TABULATION '\x0c' # 0x0C -> FORM FEED '\r' # 0x0D -> CARRIAGE RETURN '\x0e' # 0x0E -> SHIFT OUT '\x0f' # 0x0F -> SHIFT IN '\x10' # 0x10 -> DATA LINK ESCAPE '\x11' # 0x11 -> DEVICE CONTROL ONE '\x12' # 0x12 -> DEVICE CONTROL TWO '\x13' # 0x13 -> DEVICE CONTROL THREE '\x14' # 0x14 -> DEVICE CONTROL FOUR '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE '\x16' # 0x16 -> SYNCHRONOUS IDLE '\x17' # 0x17 -> END OF TRANSMISSION BLOCK '\x18' # 0x18 -> CANCEL '\x19' # 0x19 -> END OF MEDIUM '\x1a' # 0x1A -> SUBSTITUTE '\x1b' # 0x1B -> ESCAPE '\x1c' # 0x1C -> FILE SEPARATOR '\x1d' # 0x1D -> GROUP SEPARATOR '\x1e' # 0x1E -> RECORD SEPARATOR '\x1f' # 0x1F -> UNIT SEPARATOR ' ' # 0x20 -> SPACE '!' # 0x21 -> EXCLAMATION MARK '"' # 0x22 -> QUOTATION MARK '#' # 0x23 -> NUMBER SIGN '$' # 0x24 -> DOLLAR SIGN '%' # 0x25 -> PERCENT SIGN '&' # 0x26 -> AMPERSAND "'" # 0x27 -> APOSTROPHE '(' # 0x28 -> LEFT PARENTHESIS ')' # 0x29 -> RIGHT PARENTHESIS '*' # 0x2A -> ASTERISK '+' # 0x2B -> PLUS SIGN ',' # 0x2C -> COMMA '-' # 0x2D -> HYPHEN-MINUS '.' # 0x2E -> FULL STOP '/' # 0x2F -> SOLIDUS '0' # 0x30 -> DIGIT ZERO '1' # 0x31 -> DIGIT ONE '2' # 0x32 -> DIGIT TWO '3' # 0x33 -> DIGIT THREE '4' # 0x34 -> DIGIT FOUR '5' # 0x35 -> DIGIT FIVE '6' # 0x36 -> DIGIT SIX '7' # 0x37 -> DIGIT SEVEN '8' # 0x38 -> DIGIT EIGHT '9' # 0x39 -> DIGIT NINE ':' # 0x3A -> COLON ';' # 0x3B -> SEMICOLON '<' # 0x3C -> LESS-THAN SIGN '=' # 0x3D -> EQUALS SIGN '>' # 0x3E -> GREATER-THAN SIGN '?' # 0x3F -> QUESTION MARK '@' # 0x40 -> COMMERCIAL AT 'A' # 0x41 -> LATIN CAPITAL LETTER A 'B' # 0x42 -> LATIN CAPITAL LETTER B 'C' # 0x43 -> LATIN CAPITAL LETTER C 'D' # 0x44 -> LATIN CAPITAL LETTER D 'E' # 0x45 -> LATIN CAPITAL LETTER E 'F' # 0x46 -> LATIN CAPITAL LETTER F 'G' # 0x47 -> LATIN CAPITAL LETTER G 'H' # 0x48 -> LATIN CAPITAL LETTER H 'I' # 0x49 -> LATIN CAPITAL LETTER I 'J' # 0x4A -> LATIN CAPITAL LETTER J 'K' # 0x4B -> LATIN CAPITAL LETTER K 'L' # 0x4C -> LATIN CAPITAL LETTER L 'M' # 0x4D -> LATIN CAPITAL LETTER M 'N' # 0x4E -> LATIN CAPITAL LETTER N 'O' # 0x4F -> LATIN CAPITAL LETTER O 'P' # 0x50 -> LATIN CAPITAL LETTER P 'Q' # 0x51 -> LATIN CAPITAL LETTER Q 'R' # 0x52 -> LATIN CAPITAL LETTER R 'S' # 0x53 -> LATIN CAPITAL LETTER S 'T' # 0x54 -> LATIN CAPITAL LETTER T 'U' # 0x55 -> LATIN CAPITAL LETTER U 'V' # 0x56 -> LATIN CAPITAL LETTER V 'W' # 0x57 -> LATIN CAPITAL LETTER W 'X' # 0x58 -> LATIN CAPITAL LETTER X 'Y' # 0x59 -> LATIN CAPITAL LETTER Y 'Z' # 0x5A -> LATIN CAPITAL LETTER Z '[' # 0x5B -> LEFT SQUARE BRACKET '\\' # 0x5C -> REVERSE SOLIDUS ']' # 0x5D -> RIGHT SQUARE BRACKET '^' # 0x5E -> CIRCUMFLEX ACCENT '_' # 0x5F -> LOW LINE '`' # 0x60 -> GRAVE ACCENT 'a' # 0x61 -> LATIN SMALL LETTER A 'b' # 0x62 -> LATIN SMALL LETTER B 'c' # 0x63 -> LATIN SMALL LETTER C 'd' # 0x64 -> LATIN SMALL LETTER D 'e' # 0x65 -> LATIN SMALL LETTER E 'f' # 0x66 -> LATIN SMALL LETTER F 'g' # 0x67 -> LATIN SMALL LETTER G 'h' # 0x68 -> LATIN SMALL LETTER H 'i' # 0x69 -> LATIN SMALL LETTER I 'j' # 0x6A -> LATIN SMALL LETTER J 'k' # 0x6B -> LATIN SMALL LETTER K 'l' # 0x6C -> LATIN SMALL LETTER L 'm' # 0x6D -> LATIN SMALL LETTER M 'n' # 0x6E -> LATIN SMALL LETTER N 'o' # 0x6F -> LATIN SMALL LETTER O 'p' # 0x70 -> LATIN SMALL LETTER P 'q' # 0x71 -> LATIN SMALL LETTER Q 'r' # 0x72 -> LATIN SMALL LETTER R 's' # 0x73 -> LATIN SMALL LETTER S 't' # 0x74 -> LATIN SMALL LETTER T 'u' # 0x75 -> LATIN SMALL LETTER U 'v' # 0x76 -> LATIN SMALL LETTER V 'w' # 0x77 -> LATIN SMALL LETTER W 'x' # 0x78 -> LATIN SMALL LETTER X 'y' # 0x79 -> LATIN SMALL LETTER Y 'z' # 0x7A -> LATIN SMALL LETTER Z '{' # 0x7B -> LEFT CURLY BRACKET '|' # 0x7C -> VERTICAL LINE '}' # 0x7D -> RIGHT CURLY BRACKET '~' # 0x7E -> TILDE '\x7f' # 0x7F -> DELETE '\u0402' # 0x80 -> CYRILLIC CAPITAL LETTER DJE '\u0403' # 0x81 -> CYRILLIC CAPITAL LETTER GJE '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK '\u0453' # 0x83 -> CYRILLIC SMALL LETTER GJE '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS '\u2020' # 0x86 -> DAGGER '\u2021' # 0x87 -> DOUBLE DAGGER '\u20ac' # 0x88 -> EURO SIGN '\u2030' # 0x89 -> PER MILLE SIGN '\u0409' # 0x8A -> CYRILLIC CAPITAL LETTER LJE '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK '\u040a' # 0x8C -> CYRILLIC CAPITAL LETTER NJE '\u049a' # 0x8D -> CYRILLIC CAPITAL LETTER KA WITH DESCENDER '\u04ba' # 0x8E -> CYRILLIC CAPITAL LETTER SHHA '\u040f' # 0x8F -> CYRILLIC CAPITAL LETTER DZHE '\u0452' # 0x90 -> CYRILLIC SMALL LETTER DJE '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK '\u2022' # 0x95 -> BULLET '\u2013' # 0x96 -> EN DASH '\u2014' # 0x97 -> EM DASH '\ufffe' # 0x98 -> UNDEFINED '\u2122' # 0x99 -> TRADE MARK SIGN '\u0459' # 0x9A -> CYRILLIC SMALL LETTER LJE '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK '\u045a' # 0x9C -> CYRILLIC SMALL LETTER NJE '\u049b' # 0x9D -> CYRILLIC SMALL LETTER KA WITH DESCENDER '\u04bb' # 0x9E -> CYRILLIC SMALL LETTER SHHA '\u045f' # 0x9F -> CYRILLIC SMALL LETTER DZHE '\xa0' # 0xA0 -> NO-BREAK SPACE '\u04b0' # 0xA1 -> CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE '\u04b1' # 0xA2 -> CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE '\u04d8' # 0xA3 -> CYRILLIC CAPITAL LETTER SCHWA '\xa4' # 0xA4 -> CURRENCY SIGN '\u04e8' # 0xA5 -> CYRILLIC CAPITAL LETTER BARRED O '\xa6' # 0xA6 -> BROKEN BAR '\xa7' # 0xA7 -> SECTION SIGN '\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO '\xa9' # 0xA9 -> COPYRIGHT SIGN '\u0492' # 0xAA -> CYRILLIC CAPITAL LETTER GHE WITH STROKE '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK '\xac' # 0xAC -> NOT SIGN '\xad' # 0xAD -> SOFT HYPHEN '\xae' # 0xAE -> REGISTERED SIGN '\u04ae' # 0xAF -> CYRILLIC CAPITAL LETTER STRAIGHT U '\xb0' # 0xB0 -> DEGREE SIGN '\xb1' # 0xB1 -> PLUS-MINUS SIGN '\u0406' # 0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I '\u0456' # 0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I '\u04e9' # 0xB4 -> CYRILLIC SMALL LETTER BARRED O '\xb5' # 0xB5 -> MICRO SIGN '\xb6' # 0xB6 -> PILCROW SIGN '\xb7' # 0xB7 -> MIDDLE DOT '\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO '\u2116' # 0xB9 -> NUMERO SIGN '\u0493' # 0xBA -> CYRILLIC SMALL LETTER GHE WITH STROKE '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK '\u04d9' # 0xBC -> CYRILLIC SMALL LETTER SCHWA '\u04a2' # 0xBD -> CYRILLIC CAPITAL LETTER EN WITH DESCENDER '\u04a3' # 0xBE -> CYRILLIC SMALL LETTER EN WITH DESCENDER '\u04af' # 0xBF -> CYRILLIC SMALL LETTER STRAIGHT U '\u0410' # 0xC0 -> CYRILLIC CAPITAL LETTER A '\u0411' # 0xC1 -> CYRILLIC CAPITAL LETTER BE '\u0412' # 0xC2 -> CYRILLIC CAPITAL LETTER VE '\u0413' # 0xC3 -> CYRILLIC CAPITAL LETTER GHE '\u0414' # 0xC4 -> CYRILLIC CAPITAL LETTER DE '\u0415' # 0xC5 -> CYRILLIC CAPITAL LETTER IE '\u0416' # 0xC6 -> CYRILLIC CAPITAL LETTER ZHE '\u0417' # 0xC7 -> CYRILLIC CAPITAL LETTER ZE '\u0418' # 0xC8 -> CYRILLIC CAPITAL LETTER I '\u0419' # 0xC9 -> CYRILLIC CAPITAL LETTER SHORT I '\u041a' # 0xCA -> CYRILLIC CAPITAL LETTER KA '\u041b' # 0xCB -> CYRILLIC CAPITAL LETTER EL '\u041c' # 0xCC -> CYRILLIC CAPITAL LETTER EM '\u041d' # 0xCD -> CYRILLIC CAPITAL LETTER EN '\u041e' # 0xCE -> CYRILLIC CAPITAL LETTER O '\u041f' # 0xCF -> CYRILLIC CAPITAL LETTER PE '\u0420' # 0xD0 -> CYRILLIC CAPITAL LETTER ER '\u0421' # 0xD1 -> CYRILLIC CAPITAL LETTER ES '\u0422' # 0xD2 -> CYRILLIC CAPITAL LETTER TE '\u0423' # 0xD3 -> CYRILLIC CAPITAL LETTER U '\u0424' # 0xD4 -> CYRILLIC CAPITAL LETTER EF '\u0425' # 0xD5 -> CYRILLIC CAPITAL LETTER HA '\u0426' # 0xD6 -> CYRILLIC CAPITAL LETTER TSE '\u0427' # 0xD7 -> CYRILLIC CAPITAL LETTER CHE '\u0428' # 0xD8 -> CYRILLIC CAPITAL LETTER SHA '\u0429' # 0xD9 -> CYRILLIC CAPITAL LETTER SHCHA '\u042a' # 0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN '\u042b' # 0xDB -> CYRILLIC CAPITAL LETTER YERU '\u042c' # 0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN '\u042d' # 0xDD -> CYRILLIC CAPITAL LETTER E '\u042e' # 0xDE -> CYRILLIC CAPITAL LETTER YU '\u042f' # 0xDF -> CYRILLIC CAPITAL LETTER YA '\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A '\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE '\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE '\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE '\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE '\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE '\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE '\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE '\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I '\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I '\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA '\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL '\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM '\u043d' # 0xED -> CYRILLIC SMALL LETTER EN '\u043e' # 0xEE -> CYRILLIC SMALL LETTER O '\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE '\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER '\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES '\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE '\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U '\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF '\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA '\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE '\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE '\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA '\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA '\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN '\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU '\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN '\u044d' # 0xFD -> CYRILLIC SMALL LETTER E '\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU '\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA ) ### Encoding table encoding_table = codecs.charmap_build(decoding_table) koi8_t.py 0000644 00000031611 15030477433 0006323 0 ustar 00 """ Python Character Mapping Codec koi8_t """ # http://ru.wikipedia.org/wiki/КОИ-8 # http://www.opensource.apple.com/source/libiconv/libiconv-4/libiconv/tests/KOI8-T.TXT import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='koi8-t', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( '\x00' # 0x00 -> NULL '\x01' # 0x01 -> START OF HEADING '\x02' # 0x02 -> START OF TEXT '\x03' # 0x03 -> END OF TEXT '\x04' # 0x04 -> END OF TRANSMISSION '\x05' # 0x05 -> ENQUIRY '\x06' # 0x06 -> ACKNOWLEDGE '\x07' # 0x07 -> BELL '\x08' # 0x08 -> BACKSPACE '\t' # 0x09 -> HORIZONTAL TABULATION '\n' # 0x0A -> LINE FEED '\x0b' # 0x0B -> VERTICAL TABULATION '\x0c' # 0x0C -> FORM FEED '\r' # 0x0D -> CARRIAGE RETURN '\x0e' # 0x0E -> SHIFT OUT '\x0f' # 0x0F -> SHIFT IN '\x10' # 0x10 -> DATA LINK ESCAPE '\x11' # 0x11 -> DEVICE CONTROL ONE '\x12' # 0x12 -> DEVICE CONTROL TWO '\x13' # 0x13 -> DEVICE CONTROL THREE '\x14' # 0x14 -> DEVICE CONTROL FOUR '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE '\x16' # 0x16 -> SYNCHRONOUS IDLE '\x17' # 0x17 -> END OF TRANSMISSION BLOCK '\x18' # 0x18 -> CANCEL '\x19' # 0x19 -> END OF MEDIUM '\x1a' # 0x1A -> SUBSTITUTE '\x1b' # 0x1B -> ESCAPE '\x1c' # 0x1C -> FILE SEPARATOR '\x1d' # 0x1D -> GROUP SEPARATOR '\x1e' # 0x1E -> RECORD SEPARATOR '\x1f' # 0x1F -> UNIT SEPARATOR ' ' # 0x20 -> SPACE '!' # 0x21 -> EXCLAMATION MARK '"' # 0x22 -> QUOTATION MARK '#' # 0x23 -> NUMBER SIGN '$' # 0x24 -> DOLLAR SIGN '%' # 0x25 -> PERCENT SIGN '&' # 0x26 -> AMPERSAND "'" # 0x27 -> APOSTROPHE '(' # 0x28 -> LEFT PARENTHESIS ')' # 0x29 -> RIGHT PARENTHESIS '*' # 0x2A -> ASTERISK '+' # 0x2B -> PLUS SIGN ',' # 0x2C -> COMMA '-' # 0x2D -> HYPHEN-MINUS '.' # 0x2E -> FULL STOP '/' # 0x2F -> SOLIDUS '0' # 0x30 -> DIGIT ZERO '1' # 0x31 -> DIGIT ONE '2' # 0x32 -> DIGIT TWO '3' # 0x33 -> DIGIT THREE '4' # 0x34 -> DIGIT FOUR '5' # 0x35 -> DIGIT FIVE '6' # 0x36 -> DIGIT SIX '7' # 0x37 -> DIGIT SEVEN '8' # 0x38 -> DIGIT EIGHT '9' # 0x39 -> DIGIT NINE ':' # 0x3A -> COLON ';' # 0x3B -> SEMICOLON '<' # 0x3C -> LESS-THAN SIGN '=' # 0x3D -> EQUALS SIGN '>' # 0x3E -> GREATER-THAN SIGN '?' # 0x3F -> QUESTION MARK '@' # 0x40 -> COMMERCIAL AT 'A' # 0x41 -> LATIN CAPITAL LETTER A 'B' # 0x42 -> LATIN CAPITAL LETTER B 'C' # 0x43 -> LATIN CAPITAL LETTER C 'D' # 0x44 -> LATIN CAPITAL LETTER D 'E' # 0x45 -> LATIN CAPITAL LETTER E 'F' # 0x46 -> LATIN CAPITAL LETTER F 'G' # 0x47 -> LATIN CAPITAL LETTER G 'H' # 0x48 -> LATIN CAPITAL LETTER H 'I' # 0x49 -> LATIN CAPITAL LETTER I 'J' # 0x4A -> LATIN CAPITAL LETTER J 'K' # 0x4B -> LATIN CAPITAL LETTER K 'L' # 0x4C -> LATIN CAPITAL LETTER L 'M' # 0x4D -> LATIN CAPITAL LETTER M 'N' # 0x4E -> LATIN CAPITAL LETTER N 'O' # 0x4F -> LATIN CAPITAL LETTER O 'P' # 0x50 -> LATIN CAPITAL LETTER P 'Q' # 0x51 -> LATIN CAPITAL LETTER Q 'R' # 0x52 -> LATIN CAPITAL LETTER R 'S' # 0x53 -> LATIN CAPITAL LETTER S 'T' # 0x54 -> LATIN CAPITAL LETTER T 'U' # 0x55 -> LATIN CAPITAL LETTER U 'V' # 0x56 -> LATIN CAPITAL LETTER V 'W' # 0x57 -> LATIN CAPITAL LETTER W 'X' # 0x58 -> LATIN CAPITAL LETTER X 'Y' # 0x59 -> LATIN CAPITAL LETTER Y 'Z' # 0x5A -> LATIN CAPITAL LETTER Z '[' # 0x5B -> LEFT SQUARE BRACKET '\\' # 0x5C -> REVERSE SOLIDUS ']' # 0x5D -> RIGHT SQUARE BRACKET '^' # 0x5E -> CIRCUMFLEX ACCENT '_' # 0x5F -> LOW LINE '`' # 0x60 -> GRAVE ACCENT 'a' # 0x61 -> LATIN SMALL LETTER A 'b' # 0x62 -> LATIN SMALL LETTER B 'c' # 0x63 -> LATIN SMALL LETTER C 'd' # 0x64 -> LATIN SMALL LETTER D 'e' # 0x65 -> LATIN SMALL LETTER E 'f' # 0x66 -> LATIN SMALL LETTER F 'g' # 0x67 -> LATIN SMALL LETTER G 'h' # 0x68 -> LATIN SMALL LETTER H 'i' # 0x69 -> LATIN SMALL LETTER I 'j' # 0x6A -> LATIN SMALL LETTER J 'k' # 0x6B -> LATIN SMALL LETTER K 'l' # 0x6C -> LATIN SMALL LETTER L 'm' # 0x6D -> LATIN SMALL LETTER M 'n' # 0x6E -> LATIN SMALL LETTER N 'o' # 0x6F -> LATIN SMALL LETTER O 'p' # 0x70 -> LATIN SMALL LETTER P 'q' # 0x71 -> LATIN SMALL LETTER Q 'r' # 0x72 -> LATIN SMALL LETTER R 's' # 0x73 -> LATIN SMALL LETTER S 't' # 0x74 -> LATIN SMALL LETTER T 'u' # 0x75 -> LATIN SMALL LETTER U 'v' # 0x76 -> LATIN SMALL LETTER V 'w' # 0x77 -> LATIN SMALL LETTER W 'x' # 0x78 -> LATIN SMALL LETTER X 'y' # 0x79 -> LATIN SMALL LETTER Y 'z' # 0x7A -> LATIN SMALL LETTER Z '{' # 0x7B -> LEFT CURLY BRACKET '|' # 0x7C -> VERTICAL LINE '}' # 0x7D -> RIGHT CURLY BRACKET '~' # 0x7E -> TILDE '\x7f' # 0x7F -> DELETE '\u049b' # 0x80 -> CYRILLIC SMALL LETTER KA WITH DESCENDER '\u0493' # 0x81 -> CYRILLIC SMALL LETTER GHE WITH STROKE '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK '\u0492' # 0x83 -> CYRILLIC CAPITAL LETTER GHE WITH STROKE '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS '\u2020' # 0x86 -> DAGGER '\u2021' # 0x87 -> DOUBLE DAGGER '\ufffe' # 0x88 -> UNDEFINED '\u2030' # 0x89 -> PER MILLE SIGN '\u04b3' # 0x8A -> CYRILLIC SMALL LETTER HA WITH DESCENDER '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK '\u04b2' # 0x8C -> CYRILLIC CAPITAL LETTER HA WITH DESCENDER '\u04b7' # 0x8D -> CYRILLIC SMALL LETTER CHE WITH DESCENDER '\u04b6' # 0x8E -> CYRILLIC CAPITAL LETTER CHE WITH DESCENDER '\ufffe' # 0x8F -> UNDEFINED '\u049a' # 0x90 -> CYRILLIC CAPITAL LETTER KA WITH DESCENDER '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK '\u2022' # 0x95 -> BULLET '\u2013' # 0x96 -> EN DASH '\u2014' # 0x97 -> EM DASH '\ufffe' # 0x98 -> UNDEFINED '\u2122' # 0x99 -> TRADE MARK SIGN '\ufffe' # 0x9A -> UNDEFINED '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK '\ufffe' # 0x9C -> UNDEFINED '\ufffe' # 0x9D -> UNDEFINED '\ufffe' # 0x9E -> UNDEFINED '\ufffe' # 0x9F -> UNDEFINED '\ufffe' # 0xA0 -> UNDEFINED '\u04ef' # 0xA1 -> CYRILLIC SMALL LETTER U WITH MACRON '\u04ee' # 0xA2 -> CYRILLIC CAPITAL LETTER U WITH MACRON '\u0451' # 0xA3 -> CYRILLIC SMALL LETTER IO '\xa4' # 0xA4 -> CURRENCY SIGN '\u04e3' # 0xA5 -> CYRILLIC SMALL LETTER I WITH MACRON '\xa6' # 0xA6 -> BROKEN BAR '\xa7' # 0xA7 -> SECTION SIGN '\ufffe' # 0xA8 -> UNDEFINED '\ufffe' # 0xA9 -> UNDEFINED '\ufffe' # 0xAA -> UNDEFINED '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK '\xac' # 0xAC -> NOT SIGN '\xad' # 0xAD -> SOFT HYPHEN '\xae' # 0xAE -> REGISTERED SIGN '\ufffe' # 0xAF -> UNDEFINED '\xb0' # 0xB0 -> DEGREE SIGN '\xb1' # 0xB1 -> PLUS-MINUS SIGN '\xb2' # 0xB2 -> SUPERSCRIPT TWO '\u0401' # 0xB3 -> CYRILLIC CAPITAL LETTER IO '\ufffe' # 0xB4 -> UNDEFINED '\u04e2' # 0xB5 -> CYRILLIC CAPITAL LETTER I WITH MACRON '\xb6' # 0xB6 -> PILCROW SIGN '\xb7' # 0xB7 -> MIDDLE DOT '\ufffe' # 0xB8 -> UNDEFINED '\u2116' # 0xB9 -> NUMERO SIGN '\ufffe' # 0xBA -> UNDEFINED '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK '\ufffe' # 0xBC -> UNDEFINED '\ufffe' # 0xBD -> UNDEFINED '\ufffe' # 0xBE -> UNDEFINED '\xa9' # 0xBF -> COPYRIGHT SIGN '\u044e' # 0xC0 -> CYRILLIC SMALL LETTER YU '\u0430' # 0xC1 -> CYRILLIC SMALL LETTER A '\u0431' # 0xC2 -> CYRILLIC SMALL LETTER BE '\u0446' # 0xC3 -> CYRILLIC SMALL LETTER TSE '\u0434' # 0xC4 -> CYRILLIC SMALL LETTER DE '\u0435' # 0xC5 -> CYRILLIC SMALL LETTER IE '\u0444' # 0xC6 -> CYRILLIC SMALL LETTER EF '\u0433' # 0xC7 -> CYRILLIC SMALL LETTER GHE '\u0445' # 0xC8 -> CYRILLIC SMALL LETTER HA '\u0438' # 0xC9 -> CYRILLIC SMALL LETTER I '\u0439' # 0xCA -> CYRILLIC SMALL LETTER SHORT I '\u043a' # 0xCB -> CYRILLIC SMALL LETTER KA '\u043b' # 0xCC -> CYRILLIC SMALL LETTER EL '\u043c' # 0xCD -> CYRILLIC SMALL LETTER EM '\u043d' # 0xCE -> CYRILLIC SMALL LETTER EN '\u043e' # 0xCF -> CYRILLIC SMALL LETTER O '\u043f' # 0xD0 -> CYRILLIC SMALL LETTER PE '\u044f' # 0xD1 -> CYRILLIC SMALL LETTER YA '\u0440' # 0xD2 -> CYRILLIC SMALL LETTER ER '\u0441' # 0xD3 -> CYRILLIC SMALL LETTER ES '\u0442' # 0xD4 -> CYRILLIC SMALL LETTER TE '\u0443' # 0xD5 -> CYRILLIC SMALL LETTER U '\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE '\u0432' # 0xD7 -> CYRILLIC SMALL LETTER VE '\u044c' # 0xD8 -> CYRILLIC SMALL LETTER SOFT SIGN '\u044b' # 0xD9 -> CYRILLIC SMALL LETTER YERU '\u0437' # 0xDA -> CYRILLIC SMALL LETTER ZE '\u0448' # 0xDB -> CYRILLIC SMALL LETTER SHA '\u044d' # 0xDC -> CYRILLIC SMALL LETTER E '\u0449' # 0xDD -> CYRILLIC SMALL LETTER SHCHA '\u0447' # 0xDE -> CYRILLIC SMALL LETTER CHE '\u044a' # 0xDF -> CYRILLIC SMALL LETTER HARD SIGN '\u042e' # 0xE0 -> CYRILLIC CAPITAL LETTER YU '\u0410' # 0xE1 -> CYRILLIC CAPITAL LETTER A '\u0411' # 0xE2 -> CYRILLIC CAPITAL LETTER BE '\u0426' # 0xE3 -> CYRILLIC CAPITAL LETTER TSE '\u0414' # 0xE4 -> CYRILLIC CAPITAL LETTER DE '\u0415' # 0xE5 -> CYRILLIC CAPITAL LETTER IE '\u0424' # 0xE6 -> CYRILLIC CAPITAL LETTER EF '\u0413' # 0xE7 -> CYRILLIC CAPITAL LETTER GHE '\u0425' # 0xE8 -> CYRILLIC CAPITAL LETTER HA '\u0418' # 0xE9 -> CYRILLIC CAPITAL LETTER I '\u0419' # 0xEA -> CYRILLIC CAPITAL LETTER SHORT I '\u041a' # 0xEB -> CYRILLIC CAPITAL LETTER KA '\u041b' # 0xEC -> CYRILLIC CAPITAL LETTER EL '\u041c' # 0xED -> CYRILLIC CAPITAL LETTER EM '\u041d' # 0xEE -> CYRILLIC CAPITAL LETTER EN '\u041e' # 0xEF -> CYRILLIC CAPITAL LETTER O '\u041f' # 0xF0 -> CYRILLIC CAPITAL LETTER PE '\u042f' # 0xF1 -> CYRILLIC CAPITAL LETTER YA '\u0420' # 0xF2 -> CYRILLIC CAPITAL LETTER ER '\u0421' # 0xF3 -> CYRILLIC CAPITAL LETTER ES '\u0422' # 0xF4 -> CYRILLIC CAPITAL LETTER TE '\u0423' # 0xF5 -> CYRILLIC CAPITAL LETTER U '\u0416' # 0xF6 -> CYRILLIC CAPITAL LETTER ZHE '\u0412' # 0xF7 -> CYRILLIC CAPITAL LETTER VE '\u042c' # 0xF8 -> CYRILLIC CAPITAL LETTER SOFT SIGN '\u042b' # 0xF9 -> CYRILLIC CAPITAL LETTER YERU '\u0417' # 0xFA -> CYRILLIC CAPITAL LETTER ZE '\u0428' # 0xFB -> CYRILLIC CAPITAL LETTER SHA '\u042d' # 0xFC -> CYRILLIC CAPITAL LETTER E '\u0429' # 0xFD -> CYRILLIC CAPITAL LETTER SHCHA '\u0427' # 0xFE -> CYRILLIC CAPITAL LETTER CHE '\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) base64_codec.py 0000644 00000002775 15030477433 0007360 0 ustar 00 """Python 'base64_codec' Codec - base64 content transfer encoding. This codec de/encodes from bytes to bytes. Written by Marc-Andre Lemburg (mal@lemburg.com). """ import codecs import base64 ### Codec APIs def base64_encode(input, errors='strict'): assert errors == 'strict' return (base64.encodebytes(input), len(input)) def base64_decode(input, errors='strict'): assert errors == 'strict' return (base64.decodebytes(input), len(input)) class Codec(codecs.Codec): def encode(self, input, errors='strict'): return base64_encode(input, errors) def decode(self, input, errors='strict'): return base64_decode(input, errors) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): assert self.errors == 'strict' return base64.encodebytes(input) class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): assert self.errors == 'strict' return base64.decodebytes(input) class StreamWriter(Codec, codecs.StreamWriter): charbuffertype = bytes class StreamReader(Codec, codecs.StreamReader): charbuffertype = bytes ### encodings module API def getregentry(): return codecs.CodecInfo( name='base64', encode=base64_encode, decode=base64_decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, _is_text_encoding=False, ) cp861.py 0000644 00000103511 15030477433 0005766 0 ustar 00 """ Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP861.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp861', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x008b: 0x00d0, # LATIN CAPITAL LETTER ETH 0x008c: 0x00f0, # LATIN SMALL LETTER ETH 0x008d: 0x00de, # LATIN CAPITAL LETTER THORN 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x0095: 0x00fe, # LATIN SMALL LETTER THORN 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x0097: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE 0x0098: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE 0x009e: 0x20a7, # PESETA SIGN 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE 0x00a5: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE 0x00a6: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00a7: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x2310, # REVERSED NOT SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x00e3: 0x03c0, # GREEK SMALL LETTER PI 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA 0x00ec: 0x221e, # INFINITY 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON 0x00ef: 0x2229, # INTERSECTION 0x00f0: 0x2261, # IDENTICAL TO 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO 0x00f4: 0x2320, # TOP HALF INTEGRAL 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x2248, # ALMOST EQUAL TO 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( '\x00' # 0x0000 -> NULL '\x01' # 0x0001 -> START OF HEADING '\x02' # 0x0002 -> START OF TEXT '\x03' # 0x0003 -> END OF TEXT '\x04' # 0x0004 -> END OF TRANSMISSION '\x05' # 0x0005 -> ENQUIRY '\x06' # 0x0006 -> ACKNOWLEDGE '\x07' # 0x0007 -> BELL '\x08' # 0x0008 -> BACKSPACE '\t' # 0x0009 -> HORIZONTAL TABULATION '\n' # 0x000a -> LINE FEED '\x0b' # 0x000b -> VERTICAL TABULATION '\x0c' # 0x000c -> FORM FEED '\r' # 0x000d -> CARRIAGE RETURN '\x0e' # 0x000e -> SHIFT OUT '\x0f' # 0x000f -> SHIFT IN '\x10' # 0x0010 -> DATA LINK ESCAPE '\x11' # 0x0011 -> DEVICE CONTROL ONE '\x12' # 0x0012 -> DEVICE CONTROL TWO '\x13' # 0x0013 -> DEVICE CONTROL THREE '\x14' # 0x0014 -> DEVICE CONTROL FOUR '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE '\x16' # 0x0016 -> SYNCHRONOUS IDLE '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK '\x18' # 0x0018 -> CANCEL '\x19' # 0x0019 -> END OF MEDIUM '\x1a' # 0x001a -> SUBSTITUTE '\x1b' # 0x001b -> ESCAPE '\x1c' # 0x001c -> FILE SEPARATOR '\x1d' # 0x001d -> GROUP SEPARATOR '\x1e' # 0x001e -> RECORD SEPARATOR '\x1f' # 0x001f -> UNIT SEPARATOR ' ' # 0x0020 -> SPACE '!' # 0x0021 -> EXCLAMATION MARK '"' # 0x0022 -> QUOTATION MARK '#' # 0x0023 -> NUMBER SIGN '$' # 0x0024 -> DOLLAR SIGN '%' # 0x0025 -> PERCENT SIGN '&' # 0x0026 -> AMPERSAND "'" # 0x0027 -> APOSTROPHE '(' # 0x0028 -> LEFT PARENTHESIS ')' # 0x0029 -> RIGHT PARENTHESIS '*' # 0x002a -> ASTERISK '+' # 0x002b -> PLUS SIGN ',' # 0x002c -> COMMA '-' # 0x002d -> HYPHEN-MINUS '.' # 0x002e -> FULL STOP '/' # 0x002f -> SOLIDUS '0' # 0x0030 -> DIGIT ZERO '1' # 0x0031 -> DIGIT ONE '2' # 0x0032 -> DIGIT TWO '3' # 0x0033 -> DIGIT THREE '4' # 0x0034 -> DIGIT FOUR '5' # 0x0035 -> DIGIT FIVE '6' # 0x0036 -> DIGIT SIX '7' # 0x0037 -> DIGIT SEVEN '8' # 0x0038 -> DIGIT EIGHT '9' # 0x0039 -> DIGIT NINE ':' # 0x003a -> COLON ';' # 0x003b -> SEMICOLON '<' # 0x003c -> LESS-THAN SIGN '=' # 0x003d -> EQUALS SIGN '>' # 0x003e -> GREATER-THAN SIGN '?' # 0x003f -> QUESTION MARK '@' # 0x0040 -> COMMERCIAL AT 'A' # 0x0041 -> LATIN CAPITAL LETTER A 'B' # 0x0042 -> LATIN CAPITAL LETTER B 'C' # 0x0043 -> LATIN CAPITAL LETTER C 'D' # 0x0044 -> LATIN CAPITAL LETTER D 'E' # 0x0045 -> LATIN CAPITAL LETTER E 'F' # 0x0046 -> LATIN CAPITAL LETTER F 'G' # 0x0047 -> LATIN CAPITAL LETTER G 'H' # 0x0048 -> LATIN CAPITAL LETTER H 'I' # 0x0049 -> LATIN CAPITAL LETTER I 'J' # 0x004a -> LATIN CAPITAL LETTER J 'K' # 0x004b -> LATIN CAPITAL LETTER K 'L' # 0x004c -> LATIN CAPITAL LETTER L 'M' # 0x004d -> LATIN CAPITAL LETTER M 'N' # 0x004e -> LATIN CAPITAL LETTER N 'O' # 0x004f -> LATIN CAPITAL LETTER O 'P' # 0x0050 -> LATIN CAPITAL LETTER P 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q 'R' # 0x0052 -> LATIN CAPITAL LETTER R 'S' # 0x0053 -> LATIN CAPITAL LETTER S 'T' # 0x0054 -> LATIN CAPITAL LETTER T 'U' # 0x0055 -> LATIN CAPITAL LETTER U 'V' # 0x0056 -> LATIN CAPITAL LETTER V 'W' # 0x0057 -> LATIN CAPITAL LETTER W 'X' # 0x0058 -> LATIN CAPITAL LETTER X 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y 'Z' # 0x005a -> LATIN CAPITAL LETTER Z '[' # 0x005b -> LEFT SQUARE BRACKET '\\' # 0x005c -> REVERSE SOLIDUS ']' # 0x005d -> RIGHT SQUARE BRACKET '^' # 0x005e -> CIRCUMFLEX ACCENT '_' # 0x005f -> LOW LINE '`' # 0x0060 -> GRAVE ACCENT 'a' # 0x0061 -> LATIN SMALL LETTER A 'b' # 0x0062 -> LATIN SMALL LETTER B 'c' # 0x0063 -> LATIN SMALL LETTER C 'd' # 0x0064 -> LATIN SMALL LETTER D 'e' # 0x0065 -> LATIN SMALL LETTER E 'f' # 0x0066 -> LATIN SMALL LETTER F 'g' # 0x0067 -> LATIN SMALL LETTER G 'h' # 0x0068 -> LATIN SMALL LETTER H 'i' # 0x0069 -> LATIN SMALL LETTER I 'j' # 0x006a -> LATIN SMALL LETTER J 'k' # 0x006b -> LATIN SMALL LETTER K 'l' # 0x006c -> LATIN SMALL LETTER L 'm' # 0x006d -> LATIN SMALL LETTER M 'n' # 0x006e -> LATIN SMALL LETTER N 'o' # 0x006f -> LATIN SMALL LETTER O 'p' # 0x0070 -> LATIN SMALL LETTER P 'q' # 0x0071 -> LATIN SMALL LETTER Q 'r' # 0x0072 -> LATIN SMALL LETTER R 's' # 0x0073 -> LATIN SMALL LETTER S 't' # 0x0074 -> LATIN SMALL LETTER T 'u' # 0x0075 -> LATIN SMALL LETTER U 'v' # 0x0076 -> LATIN SMALL LETTER V 'w' # 0x0077 -> LATIN SMALL LETTER W 'x' # 0x0078 -> LATIN SMALL LETTER X 'y' # 0x0079 -> LATIN SMALL LETTER Y 'z' # 0x007a -> LATIN SMALL LETTER Z '{' # 0x007b -> LEFT CURLY BRACKET '|' # 0x007c -> VERTICAL LINE '}' # 0x007d -> RIGHT CURLY BRACKET '~' # 0x007e -> TILDE '\x7f' # 0x007f -> DELETE '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE '\xd0' # 0x008b -> LATIN CAPITAL LETTER ETH '\xf0' # 0x008c -> LATIN SMALL LETTER ETH '\xde' # 0x008d -> LATIN CAPITAL LETTER THORN '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS '\xfe' # 0x0095 -> LATIN SMALL LETTER THORN '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX '\xdd' # 0x0097 -> LATIN CAPITAL LETTER Y WITH ACUTE '\xfd' # 0x0098 -> LATIN SMALL LETTER Y WITH ACUTE '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE '\xa3' # 0x009c -> POUND SIGN '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE '\u20a7' # 0x009e -> PESETA SIGN '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE '\xc1' # 0x00a4 -> LATIN CAPITAL LETTER A WITH ACUTE '\xcd' # 0x00a5 -> LATIN CAPITAL LETTER I WITH ACUTE '\xd3' # 0x00a6 -> LATIN CAPITAL LETTER O WITH ACUTE '\xda' # 0x00a7 -> LATIN CAPITAL LETTER U WITH ACUTE '\xbf' # 0x00a8 -> INVERTED QUESTION MARK '\u2310' # 0x00a9 -> REVERSED NOT SIGN '\xac' # 0x00aa -> NOT SIGN '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK '\u2591' # 0x00b0 -> LIGHT SHADE '\u2592' # 0x00b1 -> MEDIUM SHADE '\u2593' # 0x00b2 -> DARK SHADE '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT '\u2588' # 0x00db -> FULL BLOCK '\u2584' # 0x00dc -> LOWER HALF BLOCK '\u258c' # 0x00dd -> LEFT HALF BLOCK '\u2590' # 0x00de -> RIGHT HALF BLOCK '\u2580' # 0x00df -> UPPER HALF BLOCK '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA '\xb5' # 0x00e6 -> MICRO SIGN '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA '\u221e' # 0x00ec -> INFINITY '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON '\u2229' # 0x00ef -> INTERSECTION '\u2261' # 0x00f0 -> IDENTICAL TO '\xb1' # 0x00f1 -> PLUS-MINUS SIGN '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO '\u2320' # 0x00f4 -> TOP HALF INTEGRAL '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL '\xf7' # 0x00f6 -> DIVISION SIGN '\u2248' # 0x00f7 -> ALMOST EQUAL TO '\xb0' # 0x00f8 -> DEGREE SIGN '\u2219' # 0x00f9 -> BULLET OPERATOR '\xb7' # 0x00fa -> MIDDLE DOT '\u221a' # 0x00fb -> SQUARE ROOT '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N '\xb2' # 0x00fd -> SUPERSCRIPT TWO '\u25a0' # 0x00fe -> BLACK SQUARE '\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a3: 0x009c, # POUND SIGN 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b5: 0x00e6, # MICRO SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00c1: 0x00a4, # LATIN CAPITAL LETTER A WITH ACUTE 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00cd: 0x00a5, # LATIN CAPITAL LETTER I WITH ACUTE 0x00d0: 0x008b, # LATIN CAPITAL LETTER ETH 0x00d3: 0x00a6, # LATIN CAPITAL LETTER O WITH ACUTE 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE 0x00da: 0x00a7, # LATIN CAPITAL LETTER U WITH ACUTE 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00dd: 0x0097, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00de: 0x008d, # LATIN CAPITAL LETTER THORN 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00f0: 0x008c, # LATIN SMALL LETTER ETH 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x00f6, # DIVISION SIGN 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x00fd: 0x0098, # LATIN SMALL LETTER Y WITH ACUTE 0x00fe: 0x0095, # LATIN SMALL LETTER THORN 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON 0x03c0: 0x00e3, # GREEK SMALL LETTER PI 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N 0x20a7: 0x009e, # PESETA SIGN 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x221e: 0x00ec, # INFINITY 0x2229: 0x00ef, # INTERSECTION 0x2248: 0x00f7, # ALMOST EQUAL TO 0x2261: 0x00f0, # IDENTICAL TO 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO 0x2310: 0x00a9, # REVERSED NOT SIGN 0x2320: 0x00f4, # TOP HALF INTEGRAL 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } iso2022_kr.py 0000644 00000002035 15030477433 0006720 0 ustar 00 # # iso2022_kr.py: Python Unicode Codec for ISO2022_KR # # Written by Hye-Shik Chang <perky@FreeBSD.org> # import _codecs_iso2022, codecs import _multibytecodec as mbc codec = _codecs_iso2022.getcodec('iso2022_kr') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='iso2022_kr', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) utf_32.py 0000644 00000012011 15030477433 0006221 0 ustar 00 """ Python 'utf-32' Codec """ import codecs, sys ### Codec APIs encode = codecs.utf_32_encode def decode(input, errors='strict'): return codecs.utf_32_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def __init__(self, errors='strict'): codecs.IncrementalEncoder.__init__(self, errors) self.encoder = None def encode(self, input, final=False): if self.encoder is None: result = codecs.utf_32_encode(input, self.errors)[0] if sys.byteorder == 'little': self.encoder = codecs.utf_32_le_encode else: self.encoder = codecs.utf_32_be_encode return result return self.encoder(input, self.errors)[0] def reset(self): codecs.IncrementalEncoder.reset(self) self.encoder = None def getstate(self): # state info we return to the caller: # 0: stream is in natural order for this platform # 2: endianness hasn't been determined yet # (we're never writing in unnatural order) return (2 if self.encoder is None else 0) def setstate(self, state): if state: self.encoder = None else: if sys.byteorder == 'little': self.encoder = codecs.utf_32_le_encode else: self.encoder = codecs.utf_32_be_encode class IncrementalDecoder(codecs.BufferedIncrementalDecoder): def __init__(self, errors='strict'): codecs.BufferedIncrementalDecoder.__init__(self, errors) self.decoder = None def _buffer_decode(self, input, errors, final): if self.decoder is None: (output, consumed, byteorder) = \ codecs.utf_32_ex_decode(input, errors, 0, final) if byteorder == -1: self.decoder = codecs.utf_32_le_decode elif byteorder == 1: self.decoder = codecs.utf_32_be_decode elif consumed >= 4: raise UnicodeError("UTF-32 stream does not start with BOM") return (output, consumed) return self.decoder(input, self.errors, final) def reset(self): codecs.BufferedIncrementalDecoder.reset(self) self.decoder = None def getstate(self): # additional state info from the base class must be None here, # as it isn't passed along to the caller state = codecs.BufferedIncrementalDecoder.getstate(self)[0] # additional state info we pass to the caller: # 0: stream is in natural order for this platform # 1: stream is in unnatural order # 2: endianness hasn't been determined yet if self.decoder is None: return (state, 2) addstate = int((sys.byteorder == "big") != (self.decoder is codecs.utf_32_be_decode)) return (state, addstate) def setstate(self, state): # state[1] will be ignored by BufferedIncrementalDecoder.setstate() codecs.BufferedIncrementalDecoder.setstate(self, state) state = state[1] if state == 0: self.decoder = (codecs.utf_32_be_decode if sys.byteorder == "big" else codecs.utf_32_le_decode) elif state == 1: self.decoder = (codecs.utf_32_le_decode if sys.byteorder == "big" else codecs.utf_32_be_decode) else: self.decoder = None class StreamWriter(codecs.StreamWriter): def __init__(self, stream, errors='strict'): self.encoder = None codecs.StreamWriter.__init__(self, stream, errors) def reset(self): codecs.StreamWriter.reset(self) self.encoder = None def encode(self, input, errors='strict'): if self.encoder is None: result = codecs.utf_32_encode(input, errors) if sys.byteorder == 'little': self.encoder = codecs.utf_32_le_encode else: self.encoder = codecs.utf_32_be_encode return result else: return self.encoder(input, errors) class StreamReader(codecs.StreamReader): def reset(self): codecs.StreamReader.reset(self) try: del self.decode except AttributeError: pass def decode(self, input, errors='strict'): (object, consumed, byteorder) = \ codecs.utf_32_ex_decode(input, errors, 0, False) if byteorder == -1: self.decode = codecs.utf_32_le_decode elif byteorder == 1: self.decode = codecs.utf_32_be_decode elif consumed>=4: raise UnicodeError("UTF-32 stream does not start with BOM") return (object, consumed) ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-32', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) euc_jp.py 0000644 00000002003 15030477433 0006364 0 ustar 00 # # euc_jp.py: Python Unicode Codec for EUC_JP # # Written by Hye-Shik Chang <perky@FreeBSD.org> # import _codecs_jp, codecs import _multibytecodec as mbc codec = _codecs_jp.getcodec('euc_jp') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='euc_jp', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) cp037.py 0000644 00000031501 15030477433 0005760 0 ustar 00 """ Python Character Mapping Codec cp037 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp037', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( '\x00' # 0x00 -> NULL '\x01' # 0x01 -> START OF HEADING '\x02' # 0x02 -> START OF TEXT '\x03' # 0x03 -> END OF TEXT '\x9c' # 0x04 -> CONTROL '\t' # 0x05 -> HORIZONTAL TABULATION '\x86' # 0x06 -> CONTROL '\x7f' # 0x07 -> DELETE '\x97' # 0x08 -> CONTROL '\x8d' # 0x09 -> CONTROL '\x8e' # 0x0A -> CONTROL '\x0b' # 0x0B -> VERTICAL TABULATION '\x0c' # 0x0C -> FORM FEED '\r' # 0x0D -> CARRIAGE RETURN '\x0e' # 0x0E -> SHIFT OUT '\x0f' # 0x0F -> SHIFT IN '\x10' # 0x10 -> DATA LINK ESCAPE '\x11' # 0x11 -> DEVICE CONTROL ONE '\x12' # 0x12 -> DEVICE CONTROL TWO '\x13' # 0x13 -> DEVICE CONTROL THREE '\x9d' # 0x14 -> CONTROL '\x85' # 0x15 -> CONTROL '\x08' # 0x16 -> BACKSPACE '\x87' # 0x17 -> CONTROL '\x18' # 0x18 -> CANCEL '\x19' # 0x19 -> END OF MEDIUM '\x92' # 0x1A -> CONTROL '\x8f' # 0x1B -> CONTROL '\x1c' # 0x1C -> FILE SEPARATOR '\x1d' # 0x1D -> GROUP SEPARATOR '\x1e' # 0x1E -> RECORD SEPARATOR '\x1f' # 0x1F -> UNIT SEPARATOR '\x80' # 0x20 -> CONTROL '\x81' # 0x21 -> CONTROL '\x82' # 0x22 -> CONTROL '\x83' # 0x23 -> CONTROL '\x84' # 0x24 -> CONTROL '\n' # 0x25 -> LINE FEED '\x17' # 0x26 -> END OF TRANSMISSION BLOCK '\x1b' # 0x27 -> ESCAPE '\x88' # 0x28 -> CONTROL '\x89' # 0x29 -> CONTROL '\x8a' # 0x2A -> CONTROL '\x8b' # 0x2B -> CONTROL '\x8c' # 0x2C -> CONTROL '\x05' # 0x2D -> ENQUIRY '\x06' # 0x2E -> ACKNOWLEDGE '\x07' # 0x2F -> BELL '\x90' # 0x30 -> CONTROL '\x91' # 0x31 -> CONTROL '\x16' # 0x32 -> SYNCHRONOUS IDLE '\x93' # 0x33 -> CONTROL '\x94' # 0x34 -> CONTROL '\x95' # 0x35 -> CONTROL '\x96' # 0x36 -> CONTROL '\x04' # 0x37 -> END OF TRANSMISSION '\x98' # 0x38 -> CONTROL '\x99' # 0x39 -> CONTROL '\x9a' # 0x3A -> CONTROL '\x9b' # 0x3B -> CONTROL '\x14' # 0x3C -> DEVICE CONTROL FOUR '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE '\x9e' # 0x3E -> CONTROL '\x1a' # 0x3F -> SUBSTITUTE ' ' # 0x40 -> SPACE '\xa0' # 0x41 -> NO-BREAK SPACE '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX '\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE '\xa2' # 0x4A -> CENT SIGN '.' # 0x4B -> FULL STOP '<' # 0x4C -> LESS-THAN SIGN '(' # 0x4D -> LEFT PARENTHESIS '+' # 0x4E -> PLUS SIGN '|' # 0x4F -> VERTICAL LINE '&' # 0x50 -> AMPERSAND '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE '\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) '!' # 0x5A -> EXCLAMATION MARK '$' # 0x5B -> DOLLAR SIGN '*' # 0x5C -> ASTERISK ')' # 0x5D -> RIGHT PARENTHESIS ';' # 0x5E -> SEMICOLON '\xac' # 0x5F -> NOT SIGN '-' # 0x60 -> HYPHEN-MINUS '/' # 0x61 -> SOLIDUS '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX '\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE '\xa6' # 0x6A -> BROKEN BAR ',' # 0x6B -> COMMA '%' # 0x6C -> PERCENT SIGN '_' # 0x6D -> LOW LINE '>' # 0x6E -> GREATER-THAN SIGN '?' # 0x6F -> QUESTION MARK '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE '`' # 0x79 -> GRAVE ACCENT ':' # 0x7A -> COLON '#' # 0x7B -> NUMBER SIGN '@' # 0x7C -> COMMERCIAL AT "'" # 0x7D -> APOSTROPHE '=' # 0x7E -> EQUALS SIGN '"' # 0x7F -> QUOTATION MARK '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE 'a' # 0x81 -> LATIN SMALL LETTER A 'b' # 0x82 -> LATIN SMALL LETTER B 'c' # 0x83 -> LATIN SMALL LETTER C 'd' # 0x84 -> LATIN SMALL LETTER D 'e' # 0x85 -> LATIN SMALL LETTER E 'f' # 0x86 -> LATIN SMALL LETTER F 'g' # 0x87 -> LATIN SMALL LETTER G 'h' # 0x88 -> LATIN SMALL LETTER H 'i' # 0x89 -> LATIN SMALL LETTER I '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) '\xb1' # 0x8F -> PLUS-MINUS SIGN '\xb0' # 0x90 -> DEGREE SIGN 'j' # 0x91 -> LATIN SMALL LETTER J 'k' # 0x92 -> LATIN SMALL LETTER K 'l' # 0x93 -> LATIN SMALL LETTER L 'm' # 0x94 -> LATIN SMALL LETTER M 'n' # 0x95 -> LATIN SMALL LETTER N 'o' # 0x96 -> LATIN SMALL LETTER O 'p' # 0x97 -> LATIN SMALL LETTER P 'q' # 0x98 -> LATIN SMALL LETTER Q 'r' # 0x99 -> LATIN SMALL LETTER R '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR '\xe6' # 0x9C -> LATIN SMALL LIGATURE AE '\xb8' # 0x9D -> CEDILLA '\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE '\xa4' # 0x9F -> CURRENCY SIGN '\xb5' # 0xA0 -> MICRO SIGN '~' # 0xA1 -> TILDE 's' # 0xA2 -> LATIN SMALL LETTER S 't' # 0xA3 -> LATIN SMALL LETTER T 'u' # 0xA4 -> LATIN SMALL LETTER U 'v' # 0xA5 -> LATIN SMALL LETTER V 'w' # 0xA6 -> LATIN SMALL LETTER W 'x' # 0xA7 -> LATIN SMALL LETTER X 'y' # 0xA8 -> LATIN SMALL LETTER Y 'z' # 0xA9 -> LATIN SMALL LETTER Z '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK '\xbf' # 0xAB -> INVERTED QUESTION MARK '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) '\xae' # 0xAF -> REGISTERED SIGN '^' # 0xB0 -> CIRCUMFLEX ACCENT '\xa3' # 0xB1 -> POUND SIGN '\xa5' # 0xB2 -> YEN SIGN '\xb7' # 0xB3 -> MIDDLE DOT '\xa9' # 0xB4 -> COPYRIGHT SIGN '\xa7' # 0xB5 -> SECTION SIGN '\xb6' # 0xB6 -> PILCROW SIGN '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS '[' # 0xBA -> LEFT SQUARE BRACKET ']' # 0xBB -> RIGHT SQUARE BRACKET '\xaf' # 0xBC -> MACRON '\xa8' # 0xBD -> DIAERESIS '\xb4' # 0xBE -> ACUTE ACCENT '\xd7' # 0xBF -> MULTIPLICATION SIGN '{' # 0xC0 -> LEFT CURLY BRACKET 'A' # 0xC1 -> LATIN CAPITAL LETTER A 'B' # 0xC2 -> LATIN CAPITAL LETTER B 'C' # 0xC3 -> LATIN CAPITAL LETTER C 'D' # 0xC4 -> LATIN CAPITAL LETTER D 'E' # 0xC5 -> LATIN CAPITAL LETTER E 'F' # 0xC6 -> LATIN CAPITAL LETTER F 'G' # 0xC7 -> LATIN CAPITAL LETTER G 'H' # 0xC8 -> LATIN CAPITAL LETTER H 'I' # 0xC9 -> LATIN CAPITAL LETTER I '\xad' # 0xCA -> SOFT HYPHEN '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX '\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE '}' # 0xD0 -> RIGHT CURLY BRACKET 'J' # 0xD1 -> LATIN CAPITAL LETTER J 'K' # 0xD2 -> LATIN CAPITAL LETTER K 'L' # 0xD3 -> LATIN CAPITAL LETTER L 'M' # 0xD4 -> LATIN CAPITAL LETTER M 'N' # 0xD5 -> LATIN CAPITAL LETTER N 'O' # 0xD6 -> LATIN CAPITAL LETTER O 'P' # 0xD7 -> LATIN CAPITAL LETTER P 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q 'R' # 0xD9 -> LATIN CAPITAL LETTER R '\xb9' # 0xDA -> SUPERSCRIPT ONE '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX '\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS '\\' # 0xE0 -> REVERSE SOLIDUS '\xf7' # 0xE1 -> DIVISION SIGN 'S' # 0xE2 -> LATIN CAPITAL LETTER S 'T' # 0xE3 -> LATIN CAPITAL LETTER T 'U' # 0xE4 -> LATIN CAPITAL LETTER U 'V' # 0xE5 -> LATIN CAPITAL LETTER V 'W' # 0xE6 -> LATIN CAPITAL LETTER W 'X' # 0xE7 -> LATIN CAPITAL LETTER X 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z '\xb2' # 0xEA -> SUPERSCRIPT TWO '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX '\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE '0' # 0xF0 -> DIGIT ZERO '1' # 0xF1 -> DIGIT ONE '2' # 0xF2 -> DIGIT TWO '3' # 0xF3 -> DIGIT THREE '4' # 0xF4 -> DIGIT FOUR '5' # 0xF5 -> DIGIT FIVE '6' # 0xF6 -> DIGIT SIX '7' # 0xF7 -> DIGIT SEVEN '8' # 0xF8 -> DIGIT EIGHT '9' # 0xF9 -> DIGIT NINE '\xb3' # 0xFA -> SUPERSCRIPT THREE '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX '\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE '\x9f' # 0xFF -> CONTROL ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) mac_arabic.py 0000644 00000107163 15030477433 0007175 0 ustar 00 """ Python Character Mapping Codec generated from 'VENDORS/APPLE/ARABIC.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-arabic', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x0081: 0x00a0, # NO-BREAK SPACE, right-left 0x0082: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0083: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0084: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x0085: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x0086: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x0087: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x0088: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0089: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x008a: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x008b: 0x06ba, # ARABIC LETTER NOON GHUNNA 0x008c: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left 0x008d: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x008e: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x008f: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x0090: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0091: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x0092: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x0093: 0x2026, # HORIZONTAL ELLIPSIS, right-left 0x0094: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x0095: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS 0x0096: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x0097: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x0098: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left 0x0099: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x009a: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x009b: 0x00f7, # DIVISION SIGN, right-left 0x009c: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x009d: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x009e: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x009f: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x00a0: 0x0020, # SPACE, right-left 0x00a1: 0x0021, # EXCLAMATION MARK, right-left 0x00a2: 0x0022, # QUOTATION MARK, right-left 0x00a3: 0x0023, # NUMBER SIGN, right-left 0x00a4: 0x0024, # DOLLAR SIGN, right-left 0x00a5: 0x066a, # ARABIC PERCENT SIGN 0x00a6: 0x0026, # AMPERSAND, right-left 0x00a7: 0x0027, # APOSTROPHE, right-left 0x00a8: 0x0028, # LEFT PARENTHESIS, right-left 0x00a9: 0x0029, # RIGHT PARENTHESIS, right-left 0x00aa: 0x002a, # ASTERISK, right-left 0x00ab: 0x002b, # PLUS SIGN, right-left 0x00ac: 0x060c, # ARABIC COMMA 0x00ad: 0x002d, # HYPHEN-MINUS, right-left 0x00ae: 0x002e, # FULL STOP, right-left 0x00af: 0x002f, # SOLIDUS, right-left 0x00b0: 0x0660, # ARABIC-INDIC DIGIT ZERO, right-left (need override) 0x00b1: 0x0661, # ARABIC-INDIC DIGIT ONE, right-left (need override) 0x00b2: 0x0662, # ARABIC-INDIC DIGIT TWO, right-left (need override) 0x00b3: 0x0663, # ARABIC-INDIC DIGIT THREE, right-left (need override) 0x00b4: 0x0664, # ARABIC-INDIC DIGIT FOUR, right-left (need override) 0x00b5: 0x0665, # ARABIC-INDIC DIGIT FIVE, right-left (need override) 0x00b6: 0x0666, # ARABIC-INDIC DIGIT SIX, right-left (need override) 0x00b7: 0x0667, # ARABIC-INDIC DIGIT SEVEN, right-left (need override) 0x00b8: 0x0668, # ARABIC-INDIC DIGIT EIGHT, right-left (need override) 0x00b9: 0x0669, # ARABIC-INDIC DIGIT NINE, right-left (need override) 0x00ba: 0x003a, # COLON, right-left 0x00bb: 0x061b, # ARABIC SEMICOLON 0x00bc: 0x003c, # LESS-THAN SIGN, right-left 0x00bd: 0x003d, # EQUALS SIGN, right-left 0x00be: 0x003e, # GREATER-THAN SIGN, right-left 0x00bf: 0x061f, # ARABIC QUESTION MARK 0x00c0: 0x274a, # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left 0x00c1: 0x0621, # ARABIC LETTER HAMZA 0x00c2: 0x0622, # ARABIC LETTER ALEF WITH MADDA ABOVE 0x00c3: 0x0623, # ARABIC LETTER ALEF WITH HAMZA ABOVE 0x00c4: 0x0624, # ARABIC LETTER WAW WITH HAMZA ABOVE 0x00c5: 0x0625, # ARABIC LETTER ALEF WITH HAMZA BELOW 0x00c6: 0x0626, # ARABIC LETTER YEH WITH HAMZA ABOVE 0x00c7: 0x0627, # ARABIC LETTER ALEF 0x00c8: 0x0628, # ARABIC LETTER BEH 0x00c9: 0x0629, # ARABIC LETTER TEH MARBUTA 0x00ca: 0x062a, # ARABIC LETTER TEH 0x00cb: 0x062b, # ARABIC LETTER THEH 0x00cc: 0x062c, # ARABIC LETTER JEEM 0x00cd: 0x062d, # ARABIC LETTER HAH 0x00ce: 0x062e, # ARABIC LETTER KHAH 0x00cf: 0x062f, # ARABIC LETTER DAL 0x00d0: 0x0630, # ARABIC LETTER THAL 0x00d1: 0x0631, # ARABIC LETTER REH 0x00d2: 0x0632, # ARABIC LETTER ZAIN 0x00d3: 0x0633, # ARABIC LETTER SEEN 0x00d4: 0x0634, # ARABIC LETTER SHEEN 0x00d5: 0x0635, # ARABIC LETTER SAD 0x00d6: 0x0636, # ARABIC LETTER DAD 0x00d7: 0x0637, # ARABIC LETTER TAH 0x00d8: 0x0638, # ARABIC LETTER ZAH 0x00d9: 0x0639, # ARABIC LETTER AIN 0x00da: 0x063a, # ARABIC LETTER GHAIN 0x00db: 0x005b, # LEFT SQUARE BRACKET, right-left 0x00dc: 0x005c, # REVERSE SOLIDUS, right-left 0x00dd: 0x005d, # RIGHT SQUARE BRACKET, right-left 0x00de: 0x005e, # CIRCUMFLEX ACCENT, right-left 0x00df: 0x005f, # LOW LINE, right-left 0x00e0: 0x0640, # ARABIC TATWEEL 0x00e1: 0x0641, # ARABIC LETTER FEH 0x00e2: 0x0642, # ARABIC LETTER QAF 0x00e3: 0x0643, # ARABIC LETTER KAF 0x00e4: 0x0644, # ARABIC LETTER LAM 0x00e5: 0x0645, # ARABIC LETTER MEEM 0x00e6: 0x0646, # ARABIC LETTER NOON 0x00e7: 0x0647, # ARABIC LETTER HEH 0x00e8: 0x0648, # ARABIC LETTER WAW 0x00e9: 0x0649, # ARABIC LETTER ALEF MAKSURA 0x00ea: 0x064a, # ARABIC LETTER YEH 0x00eb: 0x064b, # ARABIC FATHATAN 0x00ec: 0x064c, # ARABIC DAMMATAN 0x00ed: 0x064d, # ARABIC KASRATAN 0x00ee: 0x064e, # ARABIC FATHA 0x00ef: 0x064f, # ARABIC DAMMA 0x00f0: 0x0650, # ARABIC KASRA 0x00f1: 0x0651, # ARABIC SHADDA 0x00f2: 0x0652, # ARABIC SUKUN 0x00f3: 0x067e, # ARABIC LETTER PEH 0x00f4: 0x0679, # ARABIC LETTER TTEH 0x00f5: 0x0686, # ARABIC LETTER TCHEH 0x00f6: 0x06d5, # ARABIC LETTER AE 0x00f7: 0x06a4, # ARABIC LETTER VEH 0x00f8: 0x06af, # ARABIC LETTER GAF 0x00f9: 0x0688, # ARABIC LETTER DDAL 0x00fa: 0x0691, # ARABIC LETTER RREH 0x00fb: 0x007b, # LEFT CURLY BRACKET, right-left 0x00fc: 0x007c, # VERTICAL LINE, right-left 0x00fd: 0x007d, # RIGHT CURLY BRACKET, right-left 0x00fe: 0x0698, # ARABIC LETTER JEH 0x00ff: 0x06d2, # ARABIC LETTER YEH BARREE }) ### Decoding Table decoding_table = ( '\x00' # 0x0000 -> CONTROL CHARACTER '\x01' # 0x0001 -> CONTROL CHARACTER '\x02' # 0x0002 -> CONTROL CHARACTER '\x03' # 0x0003 -> CONTROL CHARACTER '\x04' # 0x0004 -> CONTROL CHARACTER '\x05' # 0x0005 -> CONTROL CHARACTER '\x06' # 0x0006 -> CONTROL CHARACTER '\x07' # 0x0007 -> CONTROL CHARACTER '\x08' # 0x0008 -> CONTROL CHARACTER '\t' # 0x0009 -> CONTROL CHARACTER '\n' # 0x000a -> CONTROL CHARACTER '\x0b' # 0x000b -> CONTROL CHARACTER '\x0c' # 0x000c -> CONTROL CHARACTER '\r' # 0x000d -> CONTROL CHARACTER '\x0e' # 0x000e -> CONTROL CHARACTER '\x0f' # 0x000f -> CONTROL CHARACTER '\x10' # 0x0010 -> CONTROL CHARACTER '\x11' # 0x0011 -> CONTROL CHARACTER '\x12' # 0x0012 -> CONTROL CHARACTER '\x13' # 0x0013 -> CONTROL CHARACTER '\x14' # 0x0014 -> CONTROL CHARACTER '\x15' # 0x0015 -> CONTROL CHARACTER '\x16' # 0x0016 -> CONTROL CHARACTER '\x17' # 0x0017 -> CONTROL CHARACTER '\x18' # 0x0018 -> CONTROL CHARACTER '\x19' # 0x0019 -> CONTROL CHARACTER '\x1a' # 0x001a -> CONTROL CHARACTER '\x1b' # 0x001b -> CONTROL CHARACTER '\x1c' # 0x001c -> CONTROL CHARACTER '\x1d' # 0x001d -> CONTROL CHARACTER '\x1e' # 0x001e -> CONTROL CHARACTER '\x1f' # 0x001f -> CONTROL CHARACTER ' ' # 0x0020 -> SPACE, left-right '!' # 0x0021 -> EXCLAMATION MARK, left-right '"' # 0x0022 -> QUOTATION MARK, left-right '#' # 0x0023 -> NUMBER SIGN, left-right '$' # 0x0024 -> DOLLAR SIGN, left-right '%' # 0x0025 -> PERCENT SIGN, left-right '&' # 0x0026 -> AMPERSAND, left-right "'" # 0x0027 -> APOSTROPHE, left-right '(' # 0x0028 -> LEFT PARENTHESIS, left-right ')' # 0x0029 -> RIGHT PARENTHESIS, left-right '*' # 0x002a -> ASTERISK, left-right '+' # 0x002b -> PLUS SIGN, left-right ',' # 0x002c -> COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR '-' # 0x002d -> HYPHEN-MINUS, left-right '.' # 0x002e -> FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR '/' # 0x002f -> SOLIDUS, left-right '0' # 0x0030 -> DIGIT ZERO; in Arabic-script context, displayed as 0x0660 ARABIC-INDIC DIGIT ZERO '1' # 0x0031 -> DIGIT ONE; in Arabic-script context, displayed as 0x0661 ARABIC-INDIC DIGIT ONE '2' # 0x0032 -> DIGIT TWO; in Arabic-script context, displayed as 0x0662 ARABIC-INDIC DIGIT TWO '3' # 0x0033 -> DIGIT THREE; in Arabic-script context, displayed as 0x0663 ARABIC-INDIC DIGIT THREE '4' # 0x0034 -> DIGIT FOUR; in Arabic-script context, displayed as 0x0664 ARABIC-INDIC DIGIT FOUR '5' # 0x0035 -> DIGIT FIVE; in Arabic-script context, displayed as 0x0665 ARABIC-INDIC DIGIT FIVE '6' # 0x0036 -> DIGIT SIX; in Arabic-script context, displayed as 0x0666 ARABIC-INDIC DIGIT SIX '7' # 0x0037 -> DIGIT SEVEN; in Arabic-script context, displayed as 0x0667 ARABIC-INDIC DIGIT SEVEN '8' # 0x0038 -> DIGIT EIGHT; in Arabic-script context, displayed as 0x0668 ARABIC-INDIC DIGIT EIGHT '9' # 0x0039 -> DIGIT NINE; in Arabic-script context, displayed as 0x0669 ARABIC-INDIC DIGIT NINE ':' # 0x003a -> COLON, left-right ';' # 0x003b -> SEMICOLON, left-right '<' # 0x003c -> LESS-THAN SIGN, left-right '=' # 0x003d -> EQUALS SIGN, left-right '>' # 0x003e -> GREATER-THAN SIGN, left-right '?' # 0x003f -> QUESTION MARK, left-right '@' # 0x0040 -> COMMERCIAL AT 'A' # 0x0041 -> LATIN CAPITAL LETTER A 'B' # 0x0042 -> LATIN CAPITAL LETTER B 'C' # 0x0043 -> LATIN CAPITAL LETTER C 'D' # 0x0044 -> LATIN CAPITAL LETTER D 'E' # 0x0045 -> LATIN CAPITAL LETTER E 'F' # 0x0046 -> LATIN CAPITAL LETTER F 'G' # 0x0047 -> LATIN CAPITAL LETTER G 'H' # 0x0048 -> LATIN CAPITAL LETTER H 'I' # 0x0049 -> LATIN CAPITAL LETTER I 'J' # 0x004a -> LATIN CAPITAL LETTER J 'K' # 0x004b -> LATIN CAPITAL LETTER K 'L' # 0x004c -> LATIN CAPITAL LETTER L 'M' # 0x004d -> LATIN CAPITAL LETTER M 'N' # 0x004e -> LATIN CAPITAL LETTER N 'O' # 0x004f -> LATIN CAPITAL LETTER O 'P' # 0x0050 -> LATIN CAPITAL LETTER P 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q 'R' # 0x0052 -> LATIN CAPITAL LETTER R 'S' # 0x0053 -> LATIN CAPITAL LETTER S 'T' # 0x0054 -> LATIN CAPITAL LETTER T 'U' # 0x0055 -> LATIN CAPITAL LETTER U 'V' # 0x0056 -> LATIN CAPITAL LETTER V 'W' # 0x0057 -> LATIN CAPITAL LETTER W 'X' # 0x0058 -> LATIN CAPITAL LETTER X 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y 'Z' # 0x005a -> LATIN CAPITAL LETTER Z '[' # 0x005b -> LEFT SQUARE BRACKET, left-right '\\' # 0x005c -> REVERSE SOLIDUS, left-right ']' # 0x005d -> RIGHT SQUARE BRACKET, left-right '^' # 0x005e -> CIRCUMFLEX ACCENT, left-right '_' # 0x005f -> LOW LINE, left-right '`' # 0x0060 -> GRAVE ACCENT 'a' # 0x0061 -> LATIN SMALL LETTER A 'b' # 0x0062 -> LATIN SMALL LETTER B 'c' # 0x0063 -> LATIN SMALL LETTER C 'd' # 0x0064 -> LATIN SMALL LETTER D 'e' # 0x0065 -> LATIN SMALL LETTER E 'f' # 0x0066 -> LATIN SMALL LETTER F 'g' # 0x0067 -> LATIN SMALL LETTER G 'h' # 0x0068 -> LATIN SMALL LETTER H 'i' # 0x0069 -> LATIN SMALL LETTER I 'j' # 0x006a -> LATIN SMALL LETTER J 'k' # 0x006b -> LATIN SMALL LETTER K 'l' # 0x006c -> LATIN SMALL LETTER L 'm' # 0x006d -> LATIN SMALL LETTER M 'n' # 0x006e -> LATIN SMALL LETTER N 'o' # 0x006f -> LATIN SMALL LETTER O 'p' # 0x0070 -> LATIN SMALL LETTER P 'q' # 0x0071 -> LATIN SMALL LETTER Q 'r' # 0x0072 -> LATIN SMALL LETTER R 's' # 0x0073 -> LATIN SMALL LETTER S 't' # 0x0074 -> LATIN SMALL LETTER T 'u' # 0x0075 -> LATIN SMALL LETTER U 'v' # 0x0076 -> LATIN SMALL LETTER V 'w' # 0x0077 -> LATIN SMALL LETTER W 'x' # 0x0078 -> LATIN SMALL LETTER X 'y' # 0x0079 -> LATIN SMALL LETTER Y 'z' # 0x007a -> LATIN SMALL LETTER Z '{' # 0x007b -> LEFT CURLY BRACKET, left-right '|' # 0x007c -> VERTICAL LINE, left-right '}' # 0x007d -> RIGHT CURLY BRACKET, left-right '~' # 0x007e -> TILDE '\x7f' # 0x007f -> CONTROL CHARACTER '\xc4' # 0x0080 -> LATIN CAPITAL LETTER A WITH DIAERESIS '\xa0' # 0x0081 -> NO-BREAK SPACE, right-left '\xc7' # 0x0082 -> LATIN CAPITAL LETTER C WITH CEDILLA '\xc9' # 0x0083 -> LATIN CAPITAL LETTER E WITH ACUTE '\xd1' # 0x0084 -> LATIN CAPITAL LETTER N WITH TILDE '\xd6' # 0x0085 -> LATIN CAPITAL LETTER O WITH DIAERESIS '\xdc' # 0x0086 -> LATIN CAPITAL LETTER U WITH DIAERESIS '\xe1' # 0x0087 -> LATIN SMALL LETTER A WITH ACUTE '\xe0' # 0x0088 -> LATIN SMALL LETTER A WITH GRAVE '\xe2' # 0x0089 -> LATIN SMALL LETTER A WITH CIRCUMFLEX '\xe4' # 0x008a -> LATIN SMALL LETTER A WITH DIAERESIS '\u06ba' # 0x008b -> ARABIC LETTER NOON GHUNNA '\xab' # 0x008c -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left '\xe7' # 0x008d -> LATIN SMALL LETTER C WITH CEDILLA '\xe9' # 0x008e -> LATIN SMALL LETTER E WITH ACUTE '\xe8' # 0x008f -> LATIN SMALL LETTER E WITH GRAVE '\xea' # 0x0090 -> LATIN SMALL LETTER E WITH CIRCUMFLEX '\xeb' # 0x0091 -> LATIN SMALL LETTER E WITH DIAERESIS '\xed' # 0x0092 -> LATIN SMALL LETTER I WITH ACUTE '\u2026' # 0x0093 -> HORIZONTAL ELLIPSIS, right-left '\xee' # 0x0094 -> LATIN SMALL LETTER I WITH CIRCUMFLEX '\xef' # 0x0095 -> LATIN SMALL LETTER I WITH DIAERESIS '\xf1' # 0x0096 -> LATIN SMALL LETTER N WITH TILDE '\xf3' # 0x0097 -> LATIN SMALL LETTER O WITH ACUTE '\xbb' # 0x0098 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left '\xf4' # 0x0099 -> LATIN SMALL LETTER O WITH CIRCUMFLEX '\xf6' # 0x009a -> LATIN SMALL LETTER O WITH DIAERESIS '\xf7' # 0x009b -> DIVISION SIGN, right-left '\xfa' # 0x009c -> LATIN SMALL LETTER U WITH ACUTE '\xf9' # 0x009d -> LATIN SMALL LETTER U WITH GRAVE '\xfb' # 0x009e -> LATIN SMALL LETTER U WITH CIRCUMFLEX '\xfc' # 0x009f -> LATIN SMALL LETTER U WITH DIAERESIS ' ' # 0x00a0 -> SPACE, right-left '!' # 0x00a1 -> EXCLAMATION MARK, right-left '"' # 0x00a2 -> QUOTATION MARK, right-left '#' # 0x00a3 -> NUMBER SIGN, right-left '$' # 0x00a4 -> DOLLAR SIGN, right-left '\u066a' # 0x00a5 -> ARABIC PERCENT SIGN '&' # 0x00a6 -> AMPERSAND, right-left "'" # 0x00a7 -> APOSTROPHE, right-left '(' # 0x00a8 -> LEFT PARENTHESIS, right-left ')' # 0x00a9 -> RIGHT PARENTHESIS, right-left '*' # 0x00aa -> ASTERISK, right-left '+' # 0x00ab -> PLUS SIGN, right-left '\u060c' # 0x00ac -> ARABIC COMMA '-' # 0x00ad -> HYPHEN-MINUS, right-left '.' # 0x00ae -> FULL STOP, right-left '/' # 0x00af -> SOLIDUS, right-left '\u0660' # 0x00b0 -> ARABIC-INDIC DIGIT ZERO, right-left (need override) '\u0661' # 0x00b1 -> ARABIC-INDIC DIGIT ONE, right-left (need override) '\u0662' # 0x00b2 -> ARABIC-INDIC DIGIT TWO, right-left (need override) '\u0663' # 0x00b3 -> ARABIC-INDIC DIGIT THREE, right-left (need override) '\u0664' # 0x00b4 -> ARABIC-INDIC DIGIT FOUR, right-left (need override) '\u0665' # 0x00b5 -> ARABIC-INDIC DIGIT FIVE, right-left (need override) '\u0666' # 0x00b6 -> ARABIC-INDIC DIGIT SIX, right-left (need override) '\u0667' # 0x00b7 -> ARABIC-INDIC DIGIT SEVEN, right-left (need override) '\u0668' # 0x00b8 -> ARABIC-INDIC DIGIT EIGHT, right-left (need override) '\u0669' # 0x00b9 -> ARABIC-INDIC DIGIT NINE, right-left (need override) ':' # 0x00ba -> COLON, right-left '\u061b' # 0x00bb -> ARABIC SEMICOLON '<' # 0x00bc -> LESS-THAN SIGN, right-left '=' # 0x00bd -> EQUALS SIGN, right-left '>' # 0x00be -> GREATER-THAN SIGN, right-left '\u061f' # 0x00bf -> ARABIC QUESTION MARK '\u274a' # 0x00c0 -> EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left '\u0621' # 0x00c1 -> ARABIC LETTER HAMZA '\u0622' # 0x00c2 -> ARABIC LETTER ALEF WITH MADDA ABOVE '\u0623' # 0x00c3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE '\u0624' # 0x00c4 -> ARABIC LETTER WAW WITH HAMZA ABOVE '\u0625' # 0x00c5 -> ARABIC LETTER ALEF WITH HAMZA BELOW '\u0626' # 0x00c6 -> ARABIC LETTER YEH WITH HAMZA ABOVE '\u0627' # 0x00c7 -> ARABIC LETTER ALEF '\u0628' # 0x00c8 -> ARABIC LETTER BEH '\u0629' # 0x00c9 -> ARABIC LETTER TEH MARBUTA '\u062a' # 0x00ca -> ARABIC LETTER TEH '\u062b' # 0x00cb -> ARABIC LETTER THEH '\u062c' # 0x00cc -> ARABIC LETTER JEEM '\u062d' # 0x00cd -> ARABIC LETTER HAH '\u062e' # 0x00ce -> ARABIC LETTER KHAH '\u062f' # 0x00cf -> ARABIC LETTER DAL '\u0630' # 0x00d0 -> ARABIC LETTER THAL '\u0631' # 0x00d1 -> ARABIC LETTER REH '\u0632' # 0x00d2 -> ARABIC LETTER ZAIN '\u0633' # 0x00d3 -> ARABIC LETTER SEEN '\u0634' # 0x00d4 -> ARABIC LETTER SHEEN '\u0635' # 0x00d5 -> ARABIC LETTER SAD '\u0636' # 0x00d6 -> ARABIC LETTER DAD '\u0637' # 0x00d7 -> ARABIC LETTER TAH '\u0638' # 0x00d8 -> ARABIC LETTER ZAH '\u0639' # 0x00d9 -> ARABIC LETTER AIN '\u063a' # 0x00da -> ARABIC LETTER GHAIN '[' # 0x00db -> LEFT SQUARE BRACKET, right-left '\\' # 0x00dc -> REVERSE SOLIDUS, right-left ']' # 0x00dd -> RIGHT SQUARE BRACKET, right-left '^' # 0x00de -> CIRCUMFLEX ACCENT, right-left '_' # 0x00df -> LOW LINE, right-left '\u0640' # 0x00e0 -> ARABIC TATWEEL '\u0641' # 0x00e1 -> ARABIC LETTER FEH '\u0642' # 0x00e2 -> ARABIC LETTER QAF '\u0643' # 0x00e3 -> ARABIC LETTER KAF '\u0644' # 0x00e4 -> ARABIC LETTER LAM '\u0645' # 0x00e5 -> ARABIC LETTER MEEM '\u0646' # 0x00e6 -> ARABIC LETTER NOON '\u0647' # 0x00e7 -> ARABIC LETTER HEH '\u0648' # 0x00e8 -> ARABIC LETTER WAW '\u0649' # 0x00e9 -> ARABIC LETTER ALEF MAKSURA '\u064a' # 0x00ea -> ARABIC LETTER YEH '\u064b' # 0x00eb -> ARABIC FATHATAN '\u064c' # 0x00ec -> ARABIC DAMMATAN '\u064d' # 0x00ed -> ARABIC KASRATAN '\u064e' # 0x00ee -> ARABIC FATHA '\u064f' # 0x00ef -> ARABIC DAMMA '\u0650' # 0x00f0 -> ARABIC KASRA '\u0651' # 0x00f1 -> ARABIC SHADDA '\u0652' # 0x00f2 -> ARABIC SUKUN '\u067e' # 0x00f3 -> ARABIC LETTER PEH '\u0679' # 0x00f4 -> ARABIC LETTER TTEH '\u0686' # 0x00f5 -> ARABIC LETTER TCHEH '\u06d5' # 0x00f6 -> ARABIC LETTER AE '\u06a4' # 0x00f7 -> ARABIC LETTER VEH '\u06af' # 0x00f8 -> ARABIC LETTER GAF '\u0688' # 0x00f9 -> ARABIC LETTER DDAL '\u0691' # 0x00fa -> ARABIC LETTER RREH '{' # 0x00fb -> LEFT CURLY BRACKET, right-left '|' # 0x00fc -> VERTICAL LINE, right-left '}' # 0x00fd -> RIGHT CURLY BRACKET, right-left '\u0698' # 0x00fe -> ARABIC LETTER JEH '\u06d2' # 0x00ff -> ARABIC LETTER YEH BARREE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # CONTROL CHARACTER 0x0001: 0x0001, # CONTROL CHARACTER 0x0002: 0x0002, # CONTROL CHARACTER 0x0003: 0x0003, # CONTROL CHARACTER 0x0004: 0x0004, # CONTROL CHARACTER 0x0005: 0x0005, # CONTROL CHARACTER 0x0006: 0x0006, # CONTROL CHARACTER 0x0007: 0x0007, # CONTROL CHARACTER 0x0008: 0x0008, # CONTROL CHARACTER 0x0009: 0x0009, # CONTROL CHARACTER 0x000a: 0x000a, # CONTROL CHARACTER 0x000b: 0x000b, # CONTROL CHARACTER 0x000c: 0x000c, # CONTROL CHARACTER 0x000d: 0x000d, # CONTROL CHARACTER 0x000e: 0x000e, # CONTROL CHARACTER 0x000f: 0x000f, # CONTROL CHARACTER 0x0010: 0x0010, # CONTROL CHARACTER 0x0011: 0x0011, # CONTROL CHARACTER 0x0012: 0x0012, # CONTROL CHARACTER 0x0013: 0x0013, # CONTROL CHARACTER 0x0014: 0x0014, # CONTROL CHARACTER 0x0015: 0x0015, # CONTROL CHARACTER 0x0016: 0x0016, # CONTROL CHARACTER 0x0017: 0x0017, # CONTROL CHARACTER 0x0018: 0x0018, # CONTROL CHARACTER 0x0019: 0x0019, # CONTROL CHARACTER 0x001a: 0x001a, # CONTROL CHARACTER 0x001b: 0x001b, # CONTROL CHARACTER 0x001c: 0x001c, # CONTROL CHARACTER 0x001d: 0x001d, # CONTROL CHARACTER 0x001e: 0x001e, # CONTROL CHARACTER 0x001f: 0x001f, # CONTROL CHARACTER 0x0020: 0x0020, # SPACE, left-right 0x0020: 0x00a0, # SPACE, right-left 0x0021: 0x0021, # EXCLAMATION MARK, left-right 0x0021: 0x00a1, # EXCLAMATION MARK, right-left 0x0022: 0x0022, # QUOTATION MARK, left-right 0x0022: 0x00a2, # QUOTATION MARK, right-left 0x0023: 0x0023, # NUMBER SIGN, left-right 0x0023: 0x00a3, # NUMBER SIGN, right-left 0x0024: 0x0024, # DOLLAR SIGN, left-right 0x0024: 0x00a4, # DOLLAR SIGN, right-left 0x0025: 0x0025, # PERCENT SIGN, left-right 0x0026: 0x0026, # AMPERSAND, left-right 0x0026: 0x00a6, # AMPERSAND, right-left 0x0027: 0x0027, # APOSTROPHE, left-right 0x0027: 0x00a7, # APOSTROPHE, right-left 0x0028: 0x0028, # LEFT PARENTHESIS, left-right 0x0028: 0x00a8, # LEFT PARENTHESIS, right-left 0x0029: 0x0029, # RIGHT PARENTHESIS, left-right 0x0029: 0x00a9, # RIGHT PARENTHESIS, right-left 0x002a: 0x002a, # ASTERISK, left-right 0x002a: 0x00aa, # ASTERISK, right-left 0x002b: 0x002b, # PLUS SIGN, left-right 0x002b: 0x00ab, # PLUS SIGN, right-left 0x002c: 0x002c, # COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR 0x002d: 0x002d, # HYPHEN-MINUS, left-right 0x002d: 0x00ad, # HYPHEN-MINUS, right-left 0x002e: 0x002e, # FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR 0x002e: 0x00ae, # FULL STOP, right-left 0x002f: 0x002f, # SOLIDUS, left-right 0x002f: 0x00af, # SOLIDUS, right-left 0x0030: 0x0030, # DIGIT ZERO; in Arabic-script context, displayed as 0x0660 ARABIC-INDIC DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE; in Arabic-script context, displayed as 0x0661 ARABIC-INDIC DIGIT ONE 0x0032: 0x0032, # DIGIT TWO; in Arabic-script context, displayed as 0x0662 ARABIC-INDIC DIGIT TWO 0x0033: 0x0033, # DIGIT THREE; in Arabic-script context, displayed as 0x0663 ARABIC-INDIC DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR; in Arabic-script context, displayed as 0x0664 ARABIC-INDIC DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE; in Arabic-script context, displayed as 0x0665 ARABIC-INDIC DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX; in Arabic-script context, displayed as 0x0666 ARABIC-INDIC DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN; in Arabic-script context, displayed as 0x0667 ARABIC-INDIC DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT; in Arabic-script context, displayed as 0x0668 ARABIC-INDIC DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE; in Arabic-script context, displayed as 0x0669 ARABIC-INDIC DIGIT NINE 0x003a: 0x003a, # COLON, left-right 0x003a: 0x00ba, # COLON, right-left 0x003b: 0x003b, # SEMICOLON, left-right 0x003c: 0x003c, # LESS-THAN SIGN, left-right 0x003c: 0x00bc, # LESS-THAN SIGN, right-left 0x003d: 0x003d, # EQUALS SIGN, left-right 0x003d: 0x00bd, # EQUALS SIGN, right-left 0x003e: 0x003e, # GREATER-THAN SIGN, left-right 0x003e: 0x00be, # GREATER-THAN SIGN, right-left 0x003f: 0x003f, # QUESTION MARK, left-right 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET, left-right 0x005b: 0x00db, # LEFT SQUARE BRACKET, right-left 0x005c: 0x005c, # REVERSE SOLIDUS, left-right 0x005c: 0x00dc, # REVERSE SOLIDUS, right-left 0x005d: 0x005d, # RIGHT SQUARE BRACKET, left-right 0x005d: 0x00dd, # RIGHT SQUARE BRACKET, right-left 0x005e: 0x005e, # CIRCUMFLEX ACCENT, left-right 0x005e: 0x00de, # CIRCUMFLEX ACCENT, right-left 0x005f: 0x005f, # LOW LINE, left-right 0x005f: 0x00df, # LOW LINE, right-left 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET, left-right 0x007b: 0x00fb, # LEFT CURLY BRACKET, right-left 0x007c: 0x007c, # VERTICAL LINE, left-right 0x007c: 0x00fc, # VERTICAL LINE, right-left 0x007d: 0x007d, # RIGHT CURLY BRACKET, left-right 0x007d: 0x00fd, # RIGHT CURLY BRACKET, right-left 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # CONTROL CHARACTER 0x00a0: 0x0081, # NO-BREAK SPACE, right-left 0x00ab: 0x008c, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left 0x00bb: 0x0098, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left 0x00c4: 0x0080, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c7: 0x0082, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c9: 0x0083, # LATIN CAPITAL LETTER E WITH ACUTE 0x00d1: 0x0084, # LATIN CAPITAL LETTER N WITH TILDE 0x00d6: 0x0085, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00dc: 0x0086, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00e0: 0x0088, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x0087, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0089, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e4: 0x008a, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e7: 0x008d, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008f, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x008e, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0090, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0091, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ed: 0x0092, # LATIN SMALL LETTER I WITH ACUTE 0x00ee: 0x0094, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00ef: 0x0095, # LATIN SMALL LETTER I WITH DIAERESIS 0x00f1: 0x0096, # LATIN SMALL LETTER N WITH TILDE 0x00f3: 0x0097, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0099, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f6: 0x009a, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x009b, # DIVISION SIGN, right-left 0x00f9: 0x009d, # LATIN SMALL LETTER U WITH GRAVE 0x00fa: 0x009c, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x009e, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x009f, # LATIN SMALL LETTER U WITH DIAERESIS 0x060c: 0x00ac, # ARABIC COMMA 0x061b: 0x00bb, # ARABIC SEMICOLON 0x061f: 0x00bf, # ARABIC QUESTION MARK 0x0621: 0x00c1, # ARABIC LETTER HAMZA 0x0622: 0x00c2, # ARABIC LETTER ALEF WITH MADDA ABOVE 0x0623: 0x00c3, # ARABIC LETTER ALEF WITH HAMZA ABOVE 0x0624: 0x00c4, # ARABIC LETTER WAW WITH HAMZA ABOVE 0x0625: 0x00c5, # ARABIC LETTER ALEF WITH HAMZA BELOW 0x0626: 0x00c6, # ARABIC LETTER YEH WITH HAMZA ABOVE 0x0627: 0x00c7, # ARABIC LETTER ALEF 0x0628: 0x00c8, # ARABIC LETTER BEH 0x0629: 0x00c9, # ARABIC LETTER TEH MARBUTA 0x062a: 0x00ca, # ARABIC LETTER TEH 0x062b: 0x00cb, # ARABIC LETTER THEH 0x062c: 0x00cc, # ARABIC LETTER JEEM 0x062d: 0x00cd, # ARABIC LETTER HAH 0x062e: 0x00ce, # ARABIC LETTER KHAH 0x062f: 0x00cf, # ARABIC LETTER DAL 0x0630: 0x00d0, # ARABIC LETTER THAL 0x0631: 0x00d1, # ARABIC LETTER REH 0x0632: 0x00d2, # ARABIC LETTER ZAIN 0x0633: 0x00d3, # ARABIC LETTER SEEN 0x0634: 0x00d4, # ARABIC LETTER SHEEN 0x0635: 0x00d5, # ARABIC LETTER SAD 0x0636: 0x00d6, # ARABIC LETTER DAD 0x0637: 0x00d7, # ARABIC LETTER TAH 0x0638: 0x00d8, # ARABIC LETTER ZAH 0x0639: 0x00d9, # ARABIC LETTER AIN 0x063a: 0x00da, # ARABIC LETTER GHAIN 0x0640: 0x00e0, # ARABIC TATWEEL 0x0641: 0x00e1, # ARABIC LETTER FEH 0x0642: 0x00e2, # ARABIC LETTER QAF 0x0643: 0x00e3, # ARABIC LETTER KAF 0x0644: 0x00e4, # ARABIC LETTER LAM 0x0645: 0x00e5, # ARABIC LETTER MEEM 0x0646: 0x00e6, # ARABIC LETTER NOON 0x0647: 0x00e7, # ARABIC LETTER HEH 0x0648: 0x00e8, # ARABIC LETTER WAW 0x0649: 0x00e9, # ARABIC LETTER ALEF MAKSURA 0x064a: 0x00ea, # ARABIC LETTER YEH 0x064b: 0x00eb, # ARABIC FATHATAN 0x064c: 0x00ec, # ARABIC DAMMATAN 0x064d: 0x00ed, # ARABIC KASRATAN 0x064e: 0x00ee, # ARABIC FATHA 0x064f: 0x00ef, # ARABIC DAMMA 0x0650: 0x00f0, # ARABIC KASRA 0x0651: 0x00f1, # ARABIC SHADDA 0x0652: 0x00f2, # ARABIC SUKUN 0x0660: 0x00b0, # ARABIC-INDIC DIGIT ZERO, right-left (need override) 0x0661: 0x00b1, # ARABIC-INDIC DIGIT ONE, right-left (need override) 0x0662: 0x00b2, # ARABIC-INDIC DIGIT TWO, right-left (need override) 0x0663: 0x00b3, # ARABIC-INDIC DIGIT THREE, right-left (need override) 0x0664: 0x00b4, # ARABIC-INDIC DIGIT FOUR, right-left (need override) 0x0665: 0x00b5, # ARABIC-INDIC DIGIT FIVE, right-left (need override) 0x0666: 0x00b6, # ARABIC-INDIC DIGIT SIX, right-left (need override) 0x0667: 0x00b7, # ARABIC-INDIC DIGIT SEVEN, right-left (need override) 0x0668: 0x00b8, # ARABIC-INDIC DIGIT EIGHT, right-left (need override) 0x0669: 0x00b9, # ARABIC-INDIC DIGIT NINE, right-left (need override) 0x066a: 0x00a5, # ARABIC PERCENT SIGN 0x0679: 0x00f4, # ARABIC LETTER TTEH 0x067e: 0x00f3, # ARABIC LETTER PEH 0x0686: 0x00f5, # ARABIC LETTER TCHEH 0x0688: 0x00f9, # ARABIC LETTER DDAL 0x0691: 0x00fa, # ARABIC LETTER RREH 0x0698: 0x00fe, # ARABIC LETTER JEH 0x06a4: 0x00f7, # ARABIC LETTER VEH 0x06af: 0x00f8, # ARABIC LETTER GAF 0x06ba: 0x008b, # ARABIC LETTER NOON GHUNNA 0x06d2: 0x00ff, # ARABIC LETTER YEH BARREE 0x06d5: 0x00f6, # ARABIC LETTER AE 0x2026: 0x0093, # HORIZONTAL ELLIPSIS, right-left 0x274a: 0x00c0, # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left } iso2022_jp_ext.py 0000644 00000002055 15030477433 0007577 0 ustar 00 # # iso2022_jp_ext.py: Python Unicode Codec for ISO2022_JP_EXT # # Written by Hye-Shik Chang <perky@FreeBSD.org> # import _codecs_iso2022, codecs import _multibytecodec as mbc codec = _codecs_iso2022.getcodec('iso2022_jp_ext') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='iso2022_jp_ext', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) cp862.py 0000644 00000101132 15030477433 0005764 0 ustar 00 """ Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP862.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp862', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x05d0, # HEBREW LETTER ALEF 0x0081: 0x05d1, # HEBREW LETTER BET 0x0082: 0x05d2, # HEBREW LETTER GIMEL 0x0083: 0x05d3, # HEBREW LETTER DALET 0x0084: 0x05d4, # HEBREW LETTER HE 0x0085: 0x05d5, # HEBREW LETTER VAV 0x0086: 0x05d6, # HEBREW LETTER ZAYIN 0x0087: 0x05d7, # HEBREW LETTER HET 0x0088: 0x05d8, # HEBREW LETTER TET 0x0089: 0x05d9, # HEBREW LETTER YOD 0x008a: 0x05da, # HEBREW LETTER FINAL KAF 0x008b: 0x05db, # HEBREW LETTER KAF 0x008c: 0x05dc, # HEBREW LETTER LAMED 0x008d: 0x05dd, # HEBREW LETTER FINAL MEM 0x008e: 0x05de, # HEBREW LETTER MEM 0x008f: 0x05df, # HEBREW LETTER FINAL NUN 0x0090: 0x05e0, # HEBREW LETTER NUN 0x0091: 0x05e1, # HEBREW LETTER SAMEKH 0x0092: 0x05e2, # HEBREW LETTER AYIN 0x0093: 0x05e3, # HEBREW LETTER FINAL PE 0x0094: 0x05e4, # HEBREW LETTER PE 0x0095: 0x05e5, # HEBREW LETTER FINAL TSADI 0x0096: 0x05e6, # HEBREW LETTER TSADI 0x0097: 0x05e7, # HEBREW LETTER QOF 0x0098: 0x05e8, # HEBREW LETTER RESH 0x0099: 0x05e9, # HEBREW LETTER SHIN 0x009a: 0x05ea, # HEBREW LETTER TAV 0x009b: 0x00a2, # CENT SIGN 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00a5, # YEN SIGN 0x009e: 0x20a7, # PESETA SIGN 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x2310, # REVERSED NOT SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN) 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x00e3: 0x03c0, # GREEK SMALL LETTER PI 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA 0x00ec: 0x221e, # INFINITY 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON 0x00ef: 0x2229, # INTERSECTION 0x00f0: 0x2261, # IDENTICAL TO 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO 0x00f4: 0x2320, # TOP HALF INTEGRAL 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x2248, # ALMOST EQUAL TO 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( '\x00' # 0x0000 -> NULL '\x01' # 0x0001 -> START OF HEADING '\x02' # 0x0002 -> START OF TEXT '\x03' # 0x0003 -> END OF TEXT '\x04' # 0x0004 -> END OF TRANSMISSION '\x05' # 0x0005 -> ENQUIRY '\x06' # 0x0006 -> ACKNOWLEDGE '\x07' # 0x0007 -> BELL '\x08' # 0x0008 -> BACKSPACE '\t' # 0x0009 -> HORIZONTAL TABULATION '\n' # 0x000a -> LINE FEED '\x0b' # 0x000b -> VERTICAL TABULATION '\x0c' # 0x000c -> FORM FEED '\r' # 0x000d -> CARRIAGE RETURN '\x0e' # 0x000e -> SHIFT OUT '\x0f' # 0x000f -> SHIFT IN '\x10' # 0x0010 -> DATA LINK ESCAPE '\x11' # 0x0011 -> DEVICE CONTROL ONE '\x12' # 0x0012 -> DEVICE CONTROL TWO '\x13' # 0x0013 -> DEVICE CONTROL THREE '\x14' # 0x0014 -> DEVICE CONTROL FOUR '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE '\x16' # 0x0016 -> SYNCHRONOUS IDLE '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK '\x18' # 0x0018 -> CANCEL '\x19' # 0x0019 -> END OF MEDIUM '\x1a' # 0x001a -> SUBSTITUTE '\x1b' # 0x001b -> ESCAPE '\x1c' # 0x001c -> FILE SEPARATOR '\x1d' # 0x001d -> GROUP SEPARATOR '\x1e' # 0x001e -> RECORD SEPARATOR '\x1f' # 0x001f -> UNIT SEPARATOR ' ' # 0x0020 -> SPACE '!' # 0x0021 -> EXCLAMATION MARK '"' # 0x0022 -> QUOTATION MARK '#' # 0x0023 -> NUMBER SIGN '$' # 0x0024 -> DOLLAR SIGN '%' # 0x0025 -> PERCENT SIGN '&' # 0x0026 -> AMPERSAND "'" # 0x0027 -> APOSTROPHE '(' # 0x0028 -> LEFT PARENTHESIS ')' # 0x0029 -> RIGHT PARENTHESIS '*' # 0x002a -> ASTERISK '+' # 0x002b -> PLUS SIGN ',' # 0x002c -> COMMA '-' # 0x002d -> HYPHEN-MINUS '.' # 0x002e -> FULL STOP '/' # 0x002f -> SOLIDUS '0' # 0x0030 -> DIGIT ZERO '1' # 0x0031 -> DIGIT ONE '2' # 0x0032 -> DIGIT TWO '3' # 0x0033 -> DIGIT THREE '4' # 0x0034 -> DIGIT FOUR '5' # 0x0035 -> DIGIT FIVE '6' # 0x0036 -> DIGIT SIX '7' # 0x0037 -> DIGIT SEVEN '8' # 0x0038 -> DIGIT EIGHT '9' # 0x0039 -> DIGIT NINE ':' # 0x003a -> COLON ';' # 0x003b -> SEMICOLON '<' # 0x003c -> LESS-THAN SIGN '=' # 0x003d -> EQUALS SIGN '>' # 0x003e -> GREATER-THAN SIGN '?' # 0x003f -> QUESTION MARK '@' # 0x0040 -> COMMERCIAL AT 'A' # 0x0041 -> LATIN CAPITAL LETTER A 'B' # 0x0042 -> LATIN CAPITAL LETTER B 'C' # 0x0043 -> LATIN CAPITAL LETTER C 'D' # 0x0044 -> LATIN CAPITAL LETTER D 'E' # 0x0045 -> LATIN CAPITAL LETTER E 'F' # 0x0046 -> LATIN CAPITAL LETTER F 'G' # 0x0047 -> LATIN CAPITAL LETTER G 'H' # 0x0048 -> LATIN CAPITAL LETTER H 'I' # 0x0049 -> LATIN CAPITAL LETTER I 'J' # 0x004a -> LATIN CAPITAL LETTER J 'K' # 0x004b -> LATIN CAPITAL LETTER K 'L' # 0x004c -> LATIN CAPITAL LETTER L 'M' # 0x004d -> LATIN CAPITAL LETTER M 'N' # 0x004e -> LATIN CAPITAL LETTER N 'O' # 0x004f -> LATIN CAPITAL LETTER O 'P' # 0x0050 -> LATIN CAPITAL LETTER P 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q 'R' # 0x0052 -> LATIN CAPITAL LETTER R 'S' # 0x0053 -> LATIN CAPITAL LETTER S 'T' # 0x0054 -> LATIN CAPITAL LETTER T 'U' # 0x0055 -> LATIN CAPITAL LETTER U 'V' # 0x0056 -> LATIN CAPITAL LETTER V 'W' # 0x0057 -> LATIN CAPITAL LETTER W 'X' # 0x0058 -> LATIN CAPITAL LETTER X 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y 'Z' # 0x005a -> LATIN CAPITAL LETTER Z '[' # 0x005b -> LEFT SQUARE BRACKET '\\' # 0x005c -> REVERSE SOLIDUS ']' # 0x005d -> RIGHT SQUARE BRACKET '^' # 0x005e -> CIRCUMFLEX ACCENT '_' # 0x005f -> LOW LINE '`' # 0x0060 -> GRAVE ACCENT 'a' # 0x0061 -> LATIN SMALL LETTER A 'b' # 0x0062 -> LATIN SMALL LETTER B 'c' # 0x0063 -> LATIN SMALL LETTER C 'd' # 0x0064 -> LATIN SMALL LETTER D 'e' # 0x0065 -> LATIN SMALL LETTER E 'f' # 0x0066 -> LATIN SMALL LETTER F 'g' # 0x0067 -> LATIN SMALL LETTER G 'h' # 0x0068 -> LATIN SMALL LETTER H 'i' # 0x0069 -> LATIN SMALL LETTER I 'j' # 0x006a -> LATIN SMALL LETTER J 'k' # 0x006b -> LATIN SMALL LETTER K 'l' # 0x006c -> LATIN SMALL LETTER L 'm' # 0x006d -> LATIN SMALL LETTER M 'n' # 0x006e -> LATIN SMALL LETTER N 'o' # 0x006f -> LATIN SMALL LETTER O 'p' # 0x0070 -> LATIN SMALL LETTER P 'q' # 0x0071 -> LATIN SMALL LETTER Q 'r' # 0x0072 -> LATIN SMALL LETTER R 's' # 0x0073 -> LATIN SMALL LETTER S 't' # 0x0074 -> LATIN SMALL LETTER T 'u' # 0x0075 -> LATIN SMALL LETTER U 'v' # 0x0076 -> LATIN SMALL LETTER V 'w' # 0x0077 -> LATIN SMALL LETTER W 'x' # 0x0078 -> LATIN SMALL LETTER X 'y' # 0x0079 -> LATIN SMALL LETTER Y 'z' # 0x007a -> LATIN SMALL LETTER Z '{' # 0x007b -> LEFT CURLY BRACKET '|' # 0x007c -> VERTICAL LINE '}' # 0x007d -> RIGHT CURLY BRACKET '~' # 0x007e -> TILDE '\x7f' # 0x007f -> DELETE '\u05d0' # 0x0080 -> HEBREW LETTER ALEF '\u05d1' # 0x0081 -> HEBREW LETTER BET '\u05d2' # 0x0082 -> HEBREW LETTER GIMEL '\u05d3' # 0x0083 -> HEBREW LETTER DALET '\u05d4' # 0x0084 -> HEBREW LETTER HE '\u05d5' # 0x0085 -> HEBREW LETTER VAV '\u05d6' # 0x0086 -> HEBREW LETTER ZAYIN '\u05d7' # 0x0087 -> HEBREW LETTER HET '\u05d8' # 0x0088 -> HEBREW LETTER TET '\u05d9' # 0x0089 -> HEBREW LETTER YOD '\u05da' # 0x008a -> HEBREW LETTER FINAL KAF '\u05db' # 0x008b -> HEBREW LETTER KAF '\u05dc' # 0x008c -> HEBREW LETTER LAMED '\u05dd' # 0x008d -> HEBREW LETTER FINAL MEM '\u05de' # 0x008e -> HEBREW LETTER MEM '\u05df' # 0x008f -> HEBREW LETTER FINAL NUN '\u05e0' # 0x0090 -> HEBREW LETTER NUN '\u05e1' # 0x0091 -> HEBREW LETTER SAMEKH '\u05e2' # 0x0092 -> HEBREW LETTER AYIN '\u05e3' # 0x0093 -> HEBREW LETTER FINAL PE '\u05e4' # 0x0094 -> HEBREW LETTER PE '\u05e5' # 0x0095 -> HEBREW LETTER FINAL TSADI '\u05e6' # 0x0096 -> HEBREW LETTER TSADI '\u05e7' # 0x0097 -> HEBREW LETTER QOF '\u05e8' # 0x0098 -> HEBREW LETTER RESH '\u05e9' # 0x0099 -> HEBREW LETTER SHIN '\u05ea' # 0x009a -> HEBREW LETTER TAV '\xa2' # 0x009b -> CENT SIGN '\xa3' # 0x009c -> POUND SIGN '\xa5' # 0x009d -> YEN SIGN '\u20a7' # 0x009e -> PESETA SIGN '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR '\xbf' # 0x00a8 -> INVERTED QUESTION MARK '\u2310' # 0x00a9 -> REVERSED NOT SIGN '\xac' # 0x00aa -> NOT SIGN '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK '\u2591' # 0x00b0 -> LIGHT SHADE '\u2592' # 0x00b1 -> MEDIUM SHADE '\u2593' # 0x00b2 -> DARK SHADE '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT '\u2588' # 0x00db -> FULL BLOCK '\u2584' # 0x00dc -> LOWER HALF BLOCK '\u258c' # 0x00dd -> LEFT HALF BLOCK '\u2590' # 0x00de -> RIGHT HALF BLOCK '\u2580' # 0x00df -> UPPER HALF BLOCK '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN) '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA '\xb5' # 0x00e6 -> MICRO SIGN '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA '\u221e' # 0x00ec -> INFINITY '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON '\u2229' # 0x00ef -> INTERSECTION '\u2261' # 0x00f0 -> IDENTICAL TO '\xb1' # 0x00f1 -> PLUS-MINUS SIGN '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO '\u2320' # 0x00f4 -> TOP HALF INTEGRAL '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL '\xf7' # 0x00f6 -> DIVISION SIGN '\u2248' # 0x00f7 -> ALMOST EQUAL TO '\xb0' # 0x00f8 -> DEGREE SIGN '\u2219' # 0x00f9 -> BULLET OPERATOR '\xb7' # 0x00fa -> MIDDLE DOT '\u221a' # 0x00fb -> SQUARE ROOT '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N '\xb2' # 0x00fd -> SUPERSCRIPT TWO '\u25a0' # 0x00fe -> BLACK SQUARE '\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a2: 0x009b, # CENT SIGN 0x00a3: 0x009c, # POUND SIGN 0x00a5: 0x009d, # YEN SIGN 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b5: 0x00e6, # MICRO SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S (GERMAN) 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f7: 0x00f6, # DIVISION SIGN 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON 0x03c0: 0x00e3, # GREEK SMALL LETTER PI 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI 0x05d0: 0x0080, # HEBREW LETTER ALEF 0x05d1: 0x0081, # HEBREW LETTER BET 0x05d2: 0x0082, # HEBREW LETTER GIMEL 0x05d3: 0x0083, # HEBREW LETTER DALET 0x05d4: 0x0084, # HEBREW LETTER HE 0x05d5: 0x0085, # HEBREW LETTER VAV 0x05d6: 0x0086, # HEBREW LETTER ZAYIN 0x05d7: 0x0087, # HEBREW LETTER HET 0x05d8: 0x0088, # HEBREW LETTER TET 0x05d9: 0x0089, # HEBREW LETTER YOD 0x05da: 0x008a, # HEBREW LETTER FINAL KAF 0x05db: 0x008b, # HEBREW LETTER KAF 0x05dc: 0x008c, # HEBREW LETTER LAMED 0x05dd: 0x008d, # HEBREW LETTER FINAL MEM 0x05de: 0x008e, # HEBREW LETTER MEM 0x05df: 0x008f, # HEBREW LETTER FINAL NUN 0x05e0: 0x0090, # HEBREW LETTER NUN 0x05e1: 0x0091, # HEBREW LETTER SAMEKH 0x05e2: 0x0092, # HEBREW LETTER AYIN 0x05e3: 0x0093, # HEBREW LETTER FINAL PE 0x05e4: 0x0094, # HEBREW LETTER PE 0x05e5: 0x0095, # HEBREW LETTER FINAL TSADI 0x05e6: 0x0096, # HEBREW LETTER TSADI 0x05e7: 0x0097, # HEBREW LETTER QOF 0x05e8: 0x0098, # HEBREW LETTER RESH 0x05e9: 0x0099, # HEBREW LETTER SHIN 0x05ea: 0x009a, # HEBREW LETTER TAV 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N 0x20a7: 0x009e, # PESETA SIGN 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x221e: 0x00ec, # INFINITY 0x2229: 0x00ef, # INTERSECTION 0x2248: 0x00f7, # ALMOST EQUAL TO 0x2261: 0x00f0, # IDENTICAL TO 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO 0x2310: 0x00a9, # REVERSED NOT SIGN 0x2320: 0x00f4, # TOP HALF INTEGRAL 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } gbk.py 0000644 00000001767 15030477433 0005702 0 ustar 00 # # gbk.py: Python Unicode Codec for GBK # # Written by Hye-Shik Chang <perky@FreeBSD.org> # import _codecs_cn, codecs import _multibytecodec as mbc codec = _codecs_cn.getcodec('gbk') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='gbk', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) __pycache__/cp1253.cpython-310.pyc 0000644 00000004526 15030477433 0012407 0 ustar 00 o }�5h&3 � @ s� d Z ddlZG dd� dej�ZG dd� dej�ZG dd� dej�ZG d d � d eej�ZG dd� deej�Zd d� ZdZe� e�Z dS )zv Python Character Mapping Codec cp1253 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT' with gencodec.py. � Nc @ s e Zd Zddd�Zddd�ZdS )�Codec�strictc C � t �||t�S �N)�codecs�charmap_encode�encoding_table��self�input�errors� r �'/usr/lib/python3.10/encodings/cp1253.py�encode � zCodec.encodec C r r )r �charmap_decode�decoding_tabler r r r �decode r zCodec.decodeN)r )�__name__� __module__�__qualname__r r r r r r r s r c @ � e Zd Zddd�ZdS )�IncrementalEncoderFc C � t �|| jt�d S �Nr )r r r r �r r �finalr r r r � zIncrementalEncoder.encodeN�F)r r r r r r r r r � r c @ r )�IncrementalDecoderFc C r r )r r r r r r r r r r zIncrementalDecoder.decodeNr )r r r r r r r r r r r c @ � e Zd ZdS )�StreamWriterN�r r r r r r r r"