mirror of
https://github.com/python/cpython.git
synced 2024-12-17 05:43:48 +08:00
308 lines
13 KiB
Python
308 lines
13 KiB
Python
""" 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)
|