| @@ -0,0 +1,307 @@ | ||
| """ Python Character Mapping Codec cp1006 generated from 'MAPPINGS/VENDORS/MISC/CP1006.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='cp1006', | ||
| 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 | ||
| '\x80' # 0x80 -> <control> | ||
| '\x81' # 0x81 -> <control> | ||
| '\x82' # 0x82 -> <control> | ||
| '\x83' # 0x83 -> <control> | ||
| '\x84' # 0x84 -> <control> | ||
| '\x85' # 0x85 -> <control> | ||
| '\x86' # 0x86 -> <control> | ||
| '\x87' # 0x87 -> <control> | ||
| '\x88' # 0x88 -> <control> | ||
| '\x89' # 0x89 -> <control> | ||
| '\x8a' # 0x8A -> <control> | ||
| '\x8b' # 0x8B -> <control> | ||
| '\x8c' # 0x8C -> <control> | ||
| '\x8d' # 0x8D -> <control> | ||
| '\x8e' # 0x8E -> <control> | ||
| '\x8f' # 0x8F -> <control> | ||
| '\x90' # 0x90 -> <control> | ||
| '\x91' # 0x91 -> <control> | ||
| '\x92' # 0x92 -> <control> | ||
| '\x93' # 0x93 -> <control> | ||
| '\x94' # 0x94 -> <control> | ||
| '\x95' # 0x95 -> <control> | ||
| '\x96' # 0x96 -> <control> | ||
| '\x97' # 0x97 -> <control> | ||
| '\x98' # 0x98 -> <control> | ||
| '\x99' # 0x99 -> <control> | ||
| '\x9a' # 0x9A -> <control> | ||
| '\x9b' # 0x9B -> <control> | ||
| '\x9c' # 0x9C -> <control> | ||
| '\x9d' # 0x9D -> <control> | ||
| '\x9e' # 0x9E -> <control> | ||
| '\x9f' # 0x9F -> <control> | ||
| '\xa0' # 0xA0 -> NO-BREAK SPACE | ||
| '\u06f0' # 0xA1 -> EXTENDED ARABIC-INDIC DIGIT ZERO | ||
| '\u06f1' # 0xA2 -> EXTENDED ARABIC-INDIC DIGIT ONE | ||
| '\u06f2' # 0xA3 -> EXTENDED ARABIC-INDIC DIGIT TWO | ||
| '\u06f3' # 0xA4 -> EXTENDED ARABIC-INDIC DIGIT THREE | ||
| '\u06f4' # 0xA5 -> EXTENDED ARABIC-INDIC DIGIT FOUR | ||
| '\u06f5' # 0xA6 -> EXTENDED ARABIC-INDIC DIGIT FIVE | ||
| '\u06f6' # 0xA7 -> EXTENDED ARABIC-INDIC DIGIT SIX | ||
| '\u06f7' # 0xA8 -> EXTENDED ARABIC-INDIC DIGIT SEVEN | ||
| '\u06f8' # 0xA9 -> EXTENDED ARABIC-INDIC DIGIT EIGHT | ||
| '\u06f9' # 0xAA -> EXTENDED ARABIC-INDIC DIGIT NINE | ||
| '\u060c' # 0xAB -> ARABIC COMMA | ||
| '\u061b' # 0xAC -> ARABIC SEMICOLON | ||
| '\xad' # 0xAD -> SOFT HYPHEN | ||
| '\u061f' # 0xAE -> ARABIC QUESTION MARK | ||
| '\ufe81' # 0xAF -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM | ||
| '\ufe8d' # 0xB0 -> ARABIC LETTER ALEF ISOLATED FORM | ||
| '\ufe8e' # 0xB1 -> ARABIC LETTER ALEF FINAL FORM | ||
| '\ufe8e' # 0xB2 -> ARABIC LETTER ALEF FINAL FORM | ||
| '\ufe8f' # 0xB3 -> ARABIC LETTER BEH ISOLATED FORM | ||
| '\ufe91' # 0xB4 -> ARABIC LETTER BEH INITIAL FORM | ||
| '\ufb56' # 0xB5 -> ARABIC LETTER PEH ISOLATED FORM | ||
| '\ufb58' # 0xB6 -> ARABIC LETTER PEH INITIAL FORM | ||
| '\ufe93' # 0xB7 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM | ||
| '\ufe95' # 0xB8 -> ARABIC LETTER TEH ISOLATED FORM | ||
| '\ufe97' # 0xB9 -> ARABIC LETTER TEH INITIAL FORM | ||
| '\ufb66' # 0xBA -> ARABIC LETTER TTEH ISOLATED FORM | ||
| '\ufb68' # 0xBB -> ARABIC LETTER TTEH INITIAL FORM | ||
| '\ufe99' # 0xBC -> ARABIC LETTER THEH ISOLATED FORM | ||
| '\ufe9b' # 0xBD -> ARABIC LETTER THEH INITIAL FORM | ||
| '\ufe9d' # 0xBE -> ARABIC LETTER JEEM ISOLATED FORM | ||
| '\ufe9f' # 0xBF -> ARABIC LETTER JEEM INITIAL FORM | ||
| '\ufb7a' # 0xC0 -> ARABIC LETTER TCHEH ISOLATED FORM | ||
| '\ufb7c' # 0xC1 -> ARABIC LETTER TCHEH INITIAL FORM | ||
| '\ufea1' # 0xC2 -> ARABIC LETTER HAH ISOLATED FORM | ||
| '\ufea3' # 0xC3 -> ARABIC LETTER HAH INITIAL FORM | ||
| '\ufea5' # 0xC4 -> ARABIC LETTER KHAH ISOLATED FORM | ||
| '\ufea7' # 0xC5 -> ARABIC LETTER KHAH INITIAL FORM | ||
| '\ufea9' # 0xC6 -> ARABIC LETTER DAL ISOLATED FORM | ||
| '\ufb84' # 0xC7 -> ARABIC LETTER DAHAL ISOLATED FORMN | ||
| '\ufeab' # 0xC8 -> ARABIC LETTER THAL ISOLATED FORM | ||
| '\ufead' # 0xC9 -> ARABIC LETTER REH ISOLATED FORM | ||
| '\ufb8c' # 0xCA -> ARABIC LETTER RREH ISOLATED FORM | ||
| '\ufeaf' # 0xCB -> ARABIC LETTER ZAIN ISOLATED FORM | ||
| '\ufb8a' # 0xCC -> ARABIC LETTER JEH ISOLATED FORM | ||
| '\ufeb1' # 0xCD -> ARABIC LETTER SEEN ISOLATED FORM | ||
| '\ufeb3' # 0xCE -> ARABIC LETTER SEEN INITIAL FORM | ||
| '\ufeb5' # 0xCF -> ARABIC LETTER SHEEN ISOLATED FORM | ||
| '\ufeb7' # 0xD0 -> ARABIC LETTER SHEEN INITIAL FORM | ||
| '\ufeb9' # 0xD1 -> ARABIC LETTER SAD ISOLATED FORM | ||
| '\ufebb' # 0xD2 -> ARABIC LETTER SAD INITIAL FORM | ||
| '\ufebd' # 0xD3 -> ARABIC LETTER DAD ISOLATED FORM | ||
| '\ufebf' # 0xD4 -> ARABIC LETTER DAD INITIAL FORM | ||
| '\ufec1' # 0xD5 -> ARABIC LETTER TAH ISOLATED FORM | ||
| '\ufec5' # 0xD6 -> ARABIC LETTER ZAH ISOLATED FORM | ||
| '\ufec9' # 0xD7 -> ARABIC LETTER AIN ISOLATED FORM | ||
| '\ufeca' # 0xD8 -> ARABIC LETTER AIN FINAL FORM | ||
| '\ufecb' # 0xD9 -> ARABIC LETTER AIN INITIAL FORM | ||
| '\ufecc' # 0xDA -> ARABIC LETTER AIN MEDIAL FORM | ||
| '\ufecd' # 0xDB -> ARABIC LETTER GHAIN ISOLATED FORM | ||
| '\ufece' # 0xDC -> ARABIC LETTER GHAIN FINAL FORM | ||
| '\ufecf' # 0xDD -> ARABIC LETTER GHAIN INITIAL FORM | ||
| '\ufed0' # 0xDE -> ARABIC LETTER GHAIN MEDIAL FORM | ||
| '\ufed1' # 0xDF -> ARABIC LETTER FEH ISOLATED FORM | ||
| '\ufed3' # 0xE0 -> ARABIC LETTER FEH INITIAL FORM | ||
| '\ufed5' # 0xE1 -> ARABIC LETTER QAF ISOLATED FORM | ||
| '\ufed7' # 0xE2 -> ARABIC LETTER QAF INITIAL FORM | ||
| '\ufed9' # 0xE3 -> ARABIC LETTER KAF ISOLATED FORM | ||
| '\ufedb' # 0xE4 -> ARABIC LETTER KAF INITIAL FORM | ||
| '\ufb92' # 0xE5 -> ARABIC LETTER GAF ISOLATED FORM | ||
| '\ufb94' # 0xE6 -> ARABIC LETTER GAF INITIAL FORM | ||
| '\ufedd' # 0xE7 -> ARABIC LETTER LAM ISOLATED FORM | ||
| '\ufedf' # 0xE8 -> ARABIC LETTER LAM INITIAL FORM | ||
| '\ufee0' # 0xE9 -> ARABIC LETTER LAM MEDIAL FORM | ||
| '\ufee1' # 0xEA -> ARABIC LETTER MEEM ISOLATED FORM | ||
| '\ufee3' # 0xEB -> ARABIC LETTER MEEM INITIAL FORM | ||
| '\ufb9e' # 0xEC -> ARABIC LETTER NOON GHUNNA ISOLATED FORM | ||
| '\ufee5' # 0xED -> ARABIC LETTER NOON ISOLATED FORM | ||
| '\ufee7' # 0xEE -> ARABIC LETTER NOON INITIAL FORM | ||
| '\ufe85' # 0xEF -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM | ||
| '\ufeed' # 0xF0 -> ARABIC LETTER WAW ISOLATED FORM | ||
| '\ufba6' # 0xF1 -> ARABIC LETTER HEH GOAL ISOLATED FORM | ||
| '\ufba8' # 0xF2 -> ARABIC LETTER HEH GOAL INITIAL FORM | ||
| '\ufba9' # 0xF3 -> ARABIC LETTER HEH GOAL MEDIAL FORM | ||
| '\ufbaa' # 0xF4 -> ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM | ||
| '\ufe80' # 0xF5 -> ARABIC LETTER HAMZA ISOLATED FORM | ||
| '\ufe89' # 0xF6 -> ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM | ||
| '\ufe8a' # 0xF7 -> ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM | ||
| '\ufe8b' # 0xF8 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM | ||
| '\ufef1' # 0xF9 -> ARABIC LETTER YEH ISOLATED FORM | ||
| '\ufef2' # 0xFA -> ARABIC LETTER YEH FINAL FORM | ||
| '\ufef3' # 0xFB -> ARABIC LETTER YEH INITIAL FORM | ||
| '\ufbb0' # 0xFC -> ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM | ||
| '\ufbae' # 0xFD -> ARABIC LETTER YEH BARREE ISOLATED FORM | ||
| '\ufe7c' # 0xFE -> ARABIC SHADDA ISOLATED FORM | ||
| '\ufe7d' # 0xFF -> ARABIC SHADDA MEDIAL FORM | ||
| ) | ||
|
|
||
| ### Encoding table | ||
| encoding_table=codecs.charmap_build(decoding_table) |
| @@ -0,0 +1,307 @@ | ||
| """ Python Character Mapping Codec cp1026 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.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='cp1026', | ||
| 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 | ||
| '{' # 0x48 -> LEFT CURLY BRACKET | ||
| '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE | ||
| '\xc7' # 0x4A -> LATIN CAPITAL LETTER C WITH CEDILLA | ||
| '.' # 0x4B -> FULL STOP | ||
| '<' # 0x4C -> LESS-THAN SIGN | ||
| '(' # 0x4D -> LEFT PARENTHESIS | ||
| '+' # 0x4E -> PLUS SIGN | ||
| '!' # 0x4F -> EXCLAMATION MARK | ||
| '&' # 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) | ||
| '\u011e' # 0x5A -> LATIN CAPITAL LETTER G WITH BREVE | ||
| '\u0130' # 0x5B -> LATIN CAPITAL LETTER I WITH DOT ABOVE | ||
| '*' # 0x5C -> ASTERISK | ||
| ')' # 0x5D -> RIGHT PARENTHESIS | ||
| ';' # 0x5E -> SEMICOLON | ||
| '^' # 0x5F -> CIRCUMFLEX ACCENT | ||
| '-' # 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 | ||
| '[' # 0x68 -> LEFT SQUARE BRACKET | ||
| '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE | ||
| '\u015f' # 0x6A -> LATIN SMALL LETTER S WITH CEDILLA | ||
| ',' # 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 | ||
| '\u0131' # 0x79 -> LATIN SMALL LETTER DOTLESS I | ||
| ':' # 0x7A -> COLON | ||
| '\xd6' # 0x7B -> LATIN CAPITAL LETTER O WITH DIAERESIS | ||
| '\u015e' # 0x7C -> LATIN CAPITAL LETTER S WITH CEDILLA | ||
| "'" # 0x7D -> APOSTROPHE | ||
| '=' # 0x7E -> EQUALS SIGN | ||
| '\xdc' # 0x7F -> LATIN CAPITAL LETTER U WITH DIAERESIS | ||
| '\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 | ||
| '}' # 0x8C -> RIGHT CURLY BRACKET | ||
| '`' # 0x8D -> GRAVE ACCENT | ||
| '\xa6' # 0x8E -> BROKEN BAR | ||
| '\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 | ||
| '\xf6' # 0xA1 -> LATIN SMALL LETTER O WITH DIAERESIS | ||
| '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 | ||
| ']' # 0xAC -> RIGHT SQUARE BRACKET | ||
| '$' # 0xAD -> DOLLAR SIGN | ||
| '@' # 0xAE -> COMMERCIAL AT | ||
| '\xae' # 0xAF -> REGISTERED SIGN | ||
| '\xa2' # 0xB0 -> CENT SIGN | ||
| '\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 | ||
| '\xac' # 0xBA -> NOT SIGN | ||
| '|' # 0xBB -> VERTICAL LINE | ||
| '\xaf' # 0xBC -> MACRON | ||
| '\xa8' # 0xBD -> DIAERESIS | ||
| '\xb4' # 0xBE -> ACUTE ACCENT | ||
| '\xd7' # 0xBF -> MULTIPLICATION SIGN | ||
| '\xe7' # 0xC0 -> LATIN SMALL LETTER C WITH CEDILLA | ||
| '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 | ||
| '~' # 0xCC -> TILDE | ||
| '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE | ||
| '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE | ||
| '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE | ||
| '\u011f' # 0xD0 -> LATIN SMALL LETTER G WITH BREVE | ||
| '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 | ||
| '\\' # 0xDC -> REVERSE SOLIDUS | ||
| '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE | ||
| '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE | ||
| '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS | ||
| '\xfc' # 0xE0 -> LATIN SMALL LETTER U WITH DIAERESIS | ||
| '\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 | ||
| '#' # 0xEC -> NUMBER SIGN | ||
| '\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 | ||
| '"' # 0xFC -> QUOTATION MARK | ||
| '\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) |
| @@ -0,0 +1,307 @@ | ||
| """ Python Character Mapping Codec cp1140 generated from 'python-mappings/CP1140.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='cp1140', | ||
| 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 | ||
| '\u20ac' # 0x9F -> EURO 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) |
| @@ -0,0 +1,307 @@ | ||
| """ Python Character Mapping Codec cp1250 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.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='cp1250', | ||
| 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 | ||
| '\ufffe' # 0x83 -> UNDEFINED | ||
| '\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 | ||
| '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON | ||
| '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK | ||
| '\u015a' # 0x8C -> LATIN CAPITAL LETTER S WITH ACUTE | ||
| '\u0164' # 0x8D -> LATIN CAPITAL LETTER T WITH CARON | ||
| '\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON | ||
| '\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE | ||
| '\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 | ||
| '\ufffe' # 0x98 -> UNDEFINED | ||
| '\u2122' # 0x99 -> TRADE MARK SIGN | ||
| '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON | ||
| '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK | ||
| '\u015b' # 0x9C -> LATIN SMALL LETTER S WITH ACUTE | ||
| '\u0165' # 0x9D -> LATIN SMALL LETTER T WITH CARON | ||
| '\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON | ||
| '\u017a' # 0x9F -> LATIN SMALL LETTER Z WITH ACUTE | ||
| '\xa0' # 0xA0 -> NO-BREAK SPACE | ||
| '\u02c7' # 0xA1 -> CARON | ||
| '\u02d8' # 0xA2 -> BREVE | ||
| '\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE | ||
| '\xa4' # 0xA4 -> CURRENCY SIGN | ||
| '\u0104' # 0xA5 -> LATIN CAPITAL LETTER A WITH OGONEK | ||
| '\xa6' # 0xA6 -> BROKEN BAR | ||
| '\xa7' # 0xA7 -> SECTION SIGN | ||
| '\xa8' # 0xA8 -> DIAERESIS | ||
| '\xa9' # 0xA9 -> COPYRIGHT SIGN | ||
| '\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA | ||
| '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK | ||
| '\xac' # 0xAC -> NOT SIGN | ||
| '\xad' # 0xAD -> SOFT HYPHEN | ||
| '\xae' # 0xAE -> REGISTERED SIGN | ||
| '\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE | ||
| '\xb0' # 0xB0 -> DEGREE SIGN | ||
| '\xb1' # 0xB1 -> PLUS-MINUS SIGN | ||
| '\u02db' # 0xB2 -> OGONEK | ||
| '\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE | ||
| '\xb4' # 0xB4 -> ACUTE ACCENT | ||
| '\xb5' # 0xB5 -> MICRO SIGN | ||
| '\xb6' # 0xB6 -> PILCROW SIGN | ||
| '\xb7' # 0xB7 -> MIDDLE DOT | ||
| '\xb8' # 0xB8 -> CEDILLA | ||
| '\u0105' # 0xB9 -> LATIN SMALL LETTER A WITH OGONEK | ||
| '\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA | ||
| '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK | ||
| '\u013d' # 0xBC -> LATIN CAPITAL LETTER L WITH CARON | ||
| '\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT | ||
| '\u013e' # 0xBE -> LATIN SMALL LETTER L WITH CARON | ||
| '\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE | ||
| '\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE | ||
| '\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 | ||
| '\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE | ||
| '\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE | ||
| '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA | ||
| '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON | ||
| '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE | ||
| '\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK | ||
| '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS | ||
| '\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON | ||
| '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE | ||
| '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX | ||
| '\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON | ||
| '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE | ||
| '\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE | ||
| '\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON | ||
| '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE | ||
| '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX | ||
| '\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE | ||
| '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS | ||
| '\xd7' # 0xD7 -> MULTIPLICATION SIGN | ||
| '\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON | ||
| '\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE | ||
| '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE | ||
| '\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE | ||
| '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS | ||
| '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE | ||
| '\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA | ||
| '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S | ||
| '\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE | ||
| '\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 | ||
| '\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE | ||
| '\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE | ||
| '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA | ||
| '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON | ||
| '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE | ||
| '\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK | ||
| '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS | ||
| '\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON | ||
| '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE | ||
| '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX | ||
| '\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON | ||
| '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE | ||
| '\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE | ||
| '\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON | ||
| '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE | ||
| '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX | ||
| '\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE | ||
| '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS | ||
| '\xf7' # 0xF7 -> DIVISION SIGN | ||
| '\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON | ||
| '\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE | ||
| '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE | ||
| '\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE | ||
| '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS | ||
| '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE | ||
| '\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA | ||
| '\u02d9' # 0xFF -> DOT ABOVE | ||
| ) | ||
|
|
||
| ### Encoding table | ||
| encoding_table=codecs.charmap_build(decoding_table) |
| @@ -0,0 +1,307 @@ | ||
| """ Python Character Mapping Codec cp1251 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.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='cp1251', | ||
| 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 | ||
| '\u040c' # 0x8D -> CYRILLIC CAPITAL LETTER KJE | ||
| '\u040b' # 0x8E -> CYRILLIC CAPITAL LETTER TSHE | ||
| '\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 | ||
| '\u045c' # 0x9D -> CYRILLIC SMALL LETTER KJE | ||
| '\u045b' # 0x9E -> CYRILLIC SMALL LETTER TSHE | ||
| '\u045f' # 0x9F -> CYRILLIC SMALL LETTER DZHE | ||
| '\xa0' # 0xA0 -> NO-BREAK SPACE | ||
| '\u040e' # 0xA1 -> CYRILLIC CAPITAL LETTER SHORT U | ||
| '\u045e' # 0xA2 -> CYRILLIC SMALL LETTER SHORT U | ||
| '\u0408' # 0xA3 -> CYRILLIC CAPITAL LETTER JE | ||
| '\xa4' # 0xA4 -> CURRENCY SIGN | ||
| '\u0490' # 0xA5 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN | ||
| '\xa6' # 0xA6 -> BROKEN BAR | ||
| '\xa7' # 0xA7 -> SECTION SIGN | ||
| '\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO | ||
| '\xa9' # 0xA9 -> COPYRIGHT SIGN | ||
| '\u0404' # 0xAA -> CYRILLIC CAPITAL LETTER UKRAINIAN IE | ||
| '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK | ||
| '\xac' # 0xAC -> NOT SIGN | ||
| '\xad' # 0xAD -> SOFT HYPHEN | ||
| '\xae' # 0xAE -> REGISTERED SIGN | ||
| '\u0407' # 0xAF -> CYRILLIC CAPITAL LETTER YI | ||
| '\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 | ||
| '\u0491' # 0xB4 -> CYRILLIC SMALL LETTER GHE WITH UPTURN | ||
| '\xb5' # 0xB5 -> MICRO SIGN | ||
| '\xb6' # 0xB6 -> PILCROW SIGN | ||
| '\xb7' # 0xB7 -> MIDDLE DOT | ||
| '\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO | ||
| '\u2116' # 0xB9 -> NUMERO SIGN | ||
| '\u0454' # 0xBA -> CYRILLIC SMALL LETTER UKRAINIAN IE | ||
| '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK | ||
| '\u0458' # 0xBC -> CYRILLIC SMALL LETTER JE | ||
| '\u0405' # 0xBD -> CYRILLIC CAPITAL LETTER DZE | ||
| '\u0455' # 0xBE -> CYRILLIC SMALL LETTER DZE | ||
| '\u0457' # 0xBF -> CYRILLIC SMALL LETTER YI | ||
| '\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) |
| @@ -0,0 +1,307 @@ | ||
| """ Python Character Mapping Codec cp1252 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.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='cp1252', | ||
| 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 | ||
| '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON | ||
| '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK | ||
| '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE | ||
| '\ufffe' # 0x8D -> UNDEFINED | ||
| '\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON | ||
| '\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 | ||
| '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON | ||
| '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK | ||
| '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE | ||
| '\ufffe' # 0x9D -> UNDEFINED | ||
| '\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON | ||
| '\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 | ||
| '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE | ||
| '\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 | ||
| '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE | ||
| '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE | ||
| '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX | ||
| '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS | ||
| '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH | ||
| '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE | ||
| '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE | ||
| '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE | ||
| '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX | ||
| '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE | ||
| '\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 | ||
| '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE | ||
| '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN | ||
| '\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 | ||
| '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE | ||
| '\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 | ||
| '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE | ||
| '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE | ||
| '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX | ||
| '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS | ||
| '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH | ||
| '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE | ||
| '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE | ||
| '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE | ||
| '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX | ||
| '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE | ||
| '\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 | ||
| '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE | ||
| '\xfe' # 0xFE -> LATIN SMALL LETTER THORN | ||
| '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS | ||
| ) | ||
|
|
||
| ### Encoding table | ||
| encoding_table=codecs.charmap_build(decoding_table) |
| @@ -0,0 +1,307 @@ | ||
| """ Python Character Mapping Codec cp1253 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.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='cp1253', | ||
| 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 | ||
| '\ufffe' # 0x88 -> UNDEFINED | ||
| '\u2030' # 0x89 -> PER MILLE SIGN | ||
| '\ufffe' # 0x8A -> UNDEFINED | ||
| '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK | ||
| '\ufffe' # 0x8C -> UNDEFINED | ||
| '\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 | ||
| '\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 | ||
| '\xa0' # 0xA0 -> NO-BREAK SPACE | ||
| '\u0385' # 0xA1 -> GREEK DIALYTIKA TONOS | ||
| '\u0386' # 0xA2 -> GREEK CAPITAL LETTER ALPHA WITH TONOS | ||
| '\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 | ||
| '\ufffe' # 0xAA -> UNDEFINED | ||
| '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK | ||
| '\xac' # 0xAC -> NOT SIGN | ||
| '\xad' # 0xAD -> SOFT HYPHEN | ||
| '\xae' # 0xAE -> REGISTERED SIGN | ||
| '\u2015' # 0xAF -> HORIZONTAL BAR | ||
| '\xb0' # 0xB0 -> DEGREE SIGN | ||
| '\xb1' # 0xB1 -> PLUS-MINUS SIGN | ||
| '\xb2' # 0xB2 -> SUPERSCRIPT TWO | ||
| '\xb3' # 0xB3 -> SUPERSCRIPT THREE | ||
| '\u0384' # 0xB4 -> GREEK TONOS | ||
| '\xb5' # 0xB5 -> MICRO SIGN | ||
| '\xb6' # 0xB6 -> PILCROW SIGN | ||
| '\xb7' # 0xB7 -> MIDDLE DOT | ||
| '\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS | ||
| '\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS | ||
| '\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS | ||
| '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK | ||
| '\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS | ||
| '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF | ||
| '\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS | ||
| '\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS | ||
| '\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS | ||
| '\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA | ||
| '\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA | ||
| '\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA | ||
| '\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA | ||
| '\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON | ||
| '\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA | ||
| '\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA | ||
| '\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA | ||
| '\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA | ||
| '\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA | ||
| '\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA | ||
| '\u039c' # 0xCC -> GREEK CAPITAL LETTER MU | ||
| '\u039d' # 0xCD -> GREEK CAPITAL LETTER NU | ||
| '\u039e' # 0xCE -> GREEK CAPITAL LETTER XI | ||
| '\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON | ||
| '\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI | ||
| '\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO | ||
| '\ufffe' # 0xD2 -> UNDEFINED | ||
| '\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA | ||
| '\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU | ||
| '\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON | ||
| '\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI | ||
| '\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI | ||
| '\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI | ||
| '\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA | ||
| '\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA | ||
| '\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA | ||
| '\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS | ||
| '\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS | ||
| '\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS | ||
| '\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS | ||
| '\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS | ||
| '\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA | ||
| '\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA | ||
| '\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA | ||
| '\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA | ||
| '\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON | ||
| '\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA | ||
| '\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA | ||
| '\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA | ||
| '\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA | ||
| '\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA | ||
| '\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA | ||
| '\u03bc' # 0xEC -> GREEK SMALL LETTER MU | ||
| '\u03bd' # 0xED -> GREEK SMALL LETTER NU | ||
| '\u03be' # 0xEE -> GREEK SMALL LETTER XI | ||
| '\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON | ||
| '\u03c0' # 0xF0 -> GREEK SMALL LETTER PI | ||
| '\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO | ||
| '\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA | ||
| '\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA | ||
| '\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU | ||
| '\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON | ||
| '\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI | ||
| '\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI | ||
| '\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI | ||
| '\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA | ||
| '\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA | ||
| '\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA | ||
| '\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS | ||
| '\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS | ||
| '\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS | ||
| '\ufffe' # 0xFF -> UNDEFINED | ||
| ) | ||
|
|
||
| ### Encoding table | ||
| encoding_table=codecs.charmap_build(decoding_table) |