mirror of
https://github.com/python/cpython.git
synced 2025-07-24 11:44:31 +00:00

Replaced the tis_620, cp1140 and koi8_u codecs with new ones based on custom mapping files.
552 lines
No EOL
24 KiB
Python
552 lines
No EOL
24 KiB
Python
""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/CENTEURO.TXT' with gencodec.py.
|
|
|
|
"""#"
|
|
|
|
import codecs
|
|
|
|
### Codec APIs
|
|
|
|
class Codec(codecs.Codec):
|
|
|
|
def encode(self,input,errors='strict'):
|
|
|
|
return codecs.charmap_encode(input,errors,encoding_map)
|
|
|
|
def decode(self,input,errors='strict'):
|
|
|
|
return codecs.charmap_decode(input,errors,decoding_table)
|
|
|
|
class StreamWriter(Codec,codecs.StreamWriter):
|
|
pass
|
|
|
|
class StreamReader(Codec,codecs.StreamReader):
|
|
pass
|
|
|
|
### encodings module API
|
|
|
|
def getregentry():
|
|
|
|
return (Codec().encode,Codec().decode,StreamReader,StreamWriter)
|
|
|
|
|
|
### Decoding Table
|
|
|
|
decoding_table = (
|
|
u'\x00' # 0x00 -> CONTROL CHARACTER
|
|
u'\x01' # 0x01 -> CONTROL CHARACTER
|
|
u'\x02' # 0x02 -> CONTROL CHARACTER
|
|
u'\x03' # 0x03 -> CONTROL CHARACTER
|
|
u'\x04' # 0x04 -> CONTROL CHARACTER
|
|
u'\x05' # 0x05 -> CONTROL CHARACTER
|
|
u'\x06' # 0x06 -> CONTROL CHARACTER
|
|
u'\x07' # 0x07 -> CONTROL CHARACTER
|
|
u'\x08' # 0x08 -> CONTROL CHARACTER
|
|
u'\t' # 0x09 -> CONTROL CHARACTER
|
|
u'\n' # 0x0a -> CONTROL CHARACTER
|
|
u'\x0b' # 0x0b -> CONTROL CHARACTER
|
|
u'\x0c' # 0x0c -> CONTROL CHARACTER
|
|
u'\r' # 0x0d -> CONTROL CHARACTER
|
|
u'\x0e' # 0x0e -> CONTROL CHARACTER
|
|
u'\x0f' # 0x0f -> CONTROL CHARACTER
|
|
u'\x10' # 0x10 -> CONTROL CHARACTER
|
|
u'\x11' # 0x11 -> CONTROL CHARACTER
|
|
u'\x12' # 0x12 -> CONTROL CHARACTER
|
|
u'\x13' # 0x13 -> CONTROL CHARACTER
|
|
u'\x14' # 0x14 -> CONTROL CHARACTER
|
|
u'\x15' # 0x15 -> CONTROL CHARACTER
|
|
u'\x16' # 0x16 -> CONTROL CHARACTER
|
|
u'\x17' # 0x17 -> CONTROL CHARACTER
|
|
u'\x18' # 0x18 -> CONTROL CHARACTER
|
|
u'\x19' # 0x19 -> CONTROL CHARACTER
|
|
u'\x1a' # 0x1a -> CONTROL CHARACTER
|
|
u'\x1b' # 0x1b -> CONTROL CHARACTER
|
|
u'\x1c' # 0x1c -> CONTROL CHARACTER
|
|
u'\x1d' # 0x1d -> CONTROL CHARACTER
|
|
u'\x1e' # 0x1e -> CONTROL CHARACTER
|
|
u'\x1f' # 0x1f -> CONTROL CHARACTER
|
|
u' ' # 0x20 -> SPACE
|
|
u'!' # 0x21 -> EXCLAMATION MARK
|
|
u'"' # 0x22 -> QUOTATION MARK
|
|
u'#' # 0x23 -> NUMBER SIGN
|
|
u'$' # 0x24 -> DOLLAR SIGN
|
|
u'%' # 0x25 -> PERCENT SIGN
|
|
u'&' # 0x26 -> AMPERSAND
|
|
u"'" # 0x27 -> APOSTROPHE
|
|
u'(' # 0x28 -> LEFT PARENTHESIS
|
|
u')' # 0x29 -> RIGHT PARENTHESIS
|
|
u'*' # 0x2a -> ASTERISK
|
|
u'+' # 0x2b -> PLUS SIGN
|
|
u',' # 0x2c -> COMMA
|
|
u'-' # 0x2d -> HYPHEN-MINUS
|
|
u'.' # 0x2e -> FULL STOP
|
|
u'/' # 0x2f -> SOLIDUS
|
|
u'0' # 0x30 -> DIGIT ZERO
|
|
u'1' # 0x31 -> DIGIT ONE
|
|
u'2' # 0x32 -> DIGIT TWO
|
|
u'3' # 0x33 -> DIGIT THREE
|
|
u'4' # 0x34 -> DIGIT FOUR
|
|
u'5' # 0x35 -> DIGIT FIVE
|
|
u'6' # 0x36 -> DIGIT SIX
|
|
u'7' # 0x37 -> DIGIT SEVEN
|
|
u'8' # 0x38 -> DIGIT EIGHT
|
|
u'9' # 0x39 -> DIGIT NINE
|
|
u':' # 0x3a -> COLON
|
|
u';' # 0x3b -> SEMICOLON
|
|
u'<' # 0x3c -> LESS-THAN SIGN
|
|
u'=' # 0x3d -> EQUALS SIGN
|
|
u'>' # 0x3e -> GREATER-THAN SIGN
|
|
u'?' # 0x3f -> QUESTION MARK
|
|
u'@' # 0x40 -> COMMERCIAL AT
|
|
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
|
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
|
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
|
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
|
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
|
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
|
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
|
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
|
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
|
u'J' # 0x4a -> LATIN CAPITAL LETTER J
|
|
u'K' # 0x4b -> LATIN CAPITAL LETTER K
|
|
u'L' # 0x4c -> LATIN CAPITAL LETTER L
|
|
u'M' # 0x4d -> LATIN CAPITAL LETTER M
|
|
u'N' # 0x4e -> LATIN CAPITAL LETTER N
|
|
u'O' # 0x4f -> LATIN CAPITAL LETTER O
|
|
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
|
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
|
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
|
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
|
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
|
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
|
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
|
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
|
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
|
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
|
u'Z' # 0x5a -> LATIN CAPITAL LETTER Z
|
|
u'[' # 0x5b -> LEFT SQUARE BRACKET
|
|
u'\\' # 0x5c -> REVERSE SOLIDUS
|
|
u']' # 0x5d -> RIGHT SQUARE BRACKET
|
|
u'^' # 0x5e -> CIRCUMFLEX ACCENT
|
|
u'_' # 0x5f -> LOW LINE
|
|
u'`' # 0x60 -> GRAVE ACCENT
|
|
u'a' # 0x61 -> LATIN SMALL LETTER A
|
|
u'b' # 0x62 -> LATIN SMALL LETTER B
|
|
u'c' # 0x63 -> LATIN SMALL LETTER C
|
|
u'd' # 0x64 -> LATIN SMALL LETTER D
|
|
u'e' # 0x65 -> LATIN SMALL LETTER E
|
|
u'f' # 0x66 -> LATIN SMALL LETTER F
|
|
u'g' # 0x67 -> LATIN SMALL LETTER G
|
|
u'h' # 0x68 -> LATIN SMALL LETTER H
|
|
u'i' # 0x69 -> LATIN SMALL LETTER I
|
|
u'j' # 0x6a -> LATIN SMALL LETTER J
|
|
u'k' # 0x6b -> LATIN SMALL LETTER K
|
|
u'l' # 0x6c -> LATIN SMALL LETTER L
|
|
u'm' # 0x6d -> LATIN SMALL LETTER M
|
|
u'n' # 0x6e -> LATIN SMALL LETTER N
|
|
u'o' # 0x6f -> LATIN SMALL LETTER O
|
|
u'p' # 0x70 -> LATIN SMALL LETTER P
|
|
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
|
u'r' # 0x72 -> LATIN SMALL LETTER R
|
|
u's' # 0x73 -> LATIN SMALL LETTER S
|
|
u't' # 0x74 -> LATIN SMALL LETTER T
|
|
u'u' # 0x75 -> LATIN SMALL LETTER U
|
|
u'v' # 0x76 -> LATIN SMALL LETTER V
|
|
u'w' # 0x77 -> LATIN SMALL LETTER W
|
|
u'x' # 0x78 -> LATIN SMALL LETTER X
|
|
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
|
u'z' # 0x7a -> LATIN SMALL LETTER Z
|
|
u'{' # 0x7b -> LEFT CURLY BRACKET
|
|
u'|' # 0x7c -> VERTICAL LINE
|
|
u'}' # 0x7d -> RIGHT CURLY BRACKET
|
|
u'~' # 0x7e -> TILDE
|
|
u'\x7f' # 0x7f -> CONTROL CHARACTER
|
|
u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
|
u'\u0100' # 0x81 -> LATIN CAPITAL LETTER A WITH MACRON
|
|
u'\u0101' # 0x82 -> LATIN SMALL LETTER A WITH MACRON
|
|
u'\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE
|
|
u'\u0104' # 0x84 -> LATIN CAPITAL LETTER A WITH OGONEK
|
|
u'\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
|
u'\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
|
u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE
|
|
u'\u0105' # 0x88 -> LATIN SMALL LETTER A WITH OGONEK
|
|
u'\u010c' # 0x89 -> LATIN CAPITAL LETTER C WITH CARON
|
|
u'\xe4' # 0x8a -> LATIN SMALL LETTER A WITH DIAERESIS
|
|
u'\u010d' # 0x8b -> LATIN SMALL LETTER C WITH CARON
|
|
u'\u0106' # 0x8c -> LATIN CAPITAL LETTER C WITH ACUTE
|
|
u'\u0107' # 0x8d -> LATIN SMALL LETTER C WITH ACUTE
|
|
u'\xe9' # 0x8e -> LATIN SMALL LETTER E WITH ACUTE
|
|
u'\u0179' # 0x8f -> LATIN CAPITAL LETTER Z WITH ACUTE
|
|
u'\u017a' # 0x90 -> LATIN SMALL LETTER Z WITH ACUTE
|
|
u'\u010e' # 0x91 -> LATIN CAPITAL LETTER D WITH CARON
|
|
u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE
|
|
u'\u010f' # 0x93 -> LATIN SMALL LETTER D WITH CARON
|
|
u'\u0112' # 0x94 -> LATIN CAPITAL LETTER E WITH MACRON
|
|
u'\u0113' # 0x95 -> LATIN SMALL LETTER E WITH MACRON
|
|
u'\u0116' # 0x96 -> LATIN CAPITAL LETTER E WITH DOT ABOVE
|
|
u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE
|
|
u'\u0117' # 0x98 -> LATIN SMALL LETTER E WITH DOT ABOVE
|
|
u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
|
u'\xf6' # 0x9a -> LATIN SMALL LETTER O WITH DIAERESIS
|
|
u'\xf5' # 0x9b -> LATIN SMALL LETTER O WITH TILDE
|
|
u'\xfa' # 0x9c -> LATIN SMALL LETTER U WITH ACUTE
|
|
u'\u011a' # 0x9d -> LATIN CAPITAL LETTER E WITH CARON
|
|
u'\u011b' # 0x9e -> LATIN SMALL LETTER E WITH CARON
|
|
u'\xfc' # 0x9f -> LATIN SMALL LETTER U WITH DIAERESIS
|
|
u'\u2020' # 0xa0 -> DAGGER
|
|
u'\xb0' # 0xa1 -> DEGREE SIGN
|
|
u'\u0118' # 0xa2 -> LATIN CAPITAL LETTER E WITH OGONEK
|
|
u'\xa3' # 0xa3 -> POUND SIGN
|
|
u'\xa7' # 0xa4 -> SECTION SIGN
|
|
u'\u2022' # 0xa5 -> BULLET
|
|
u'\xb6' # 0xa6 -> PILCROW SIGN
|
|
u'\xdf' # 0xa7 -> LATIN SMALL LETTER SHARP S
|
|
u'\xae' # 0xa8 -> REGISTERED SIGN
|
|
u'\xa9' # 0xa9 -> COPYRIGHT SIGN
|
|
u'\u2122' # 0xaa -> TRADE MARK SIGN
|
|
u'\u0119' # 0xab -> LATIN SMALL LETTER E WITH OGONEK
|
|
u'\xa8' # 0xac -> DIAERESIS
|
|
u'\u2260' # 0xad -> NOT EQUAL TO
|
|
u'\u0123' # 0xae -> LATIN SMALL LETTER G WITH CEDILLA
|
|
u'\u012e' # 0xaf -> LATIN CAPITAL LETTER I WITH OGONEK
|
|
u'\u012f' # 0xb0 -> LATIN SMALL LETTER I WITH OGONEK
|
|
u'\u012a' # 0xb1 -> LATIN CAPITAL LETTER I WITH MACRON
|
|
u'\u2264' # 0xb2 -> LESS-THAN OR EQUAL TO
|
|
u'\u2265' # 0xb3 -> GREATER-THAN OR EQUAL TO
|
|
u'\u012b' # 0xb4 -> LATIN SMALL LETTER I WITH MACRON
|
|
u'\u0136' # 0xb5 -> LATIN CAPITAL LETTER K WITH CEDILLA
|
|
u'\u2202' # 0xb6 -> PARTIAL DIFFERENTIAL
|
|
u'\u2211' # 0xb7 -> N-ARY SUMMATION
|
|
u'\u0142' # 0xb8 -> LATIN SMALL LETTER L WITH STROKE
|
|
u'\u013b' # 0xb9 -> LATIN CAPITAL LETTER L WITH CEDILLA
|
|
u'\u013c' # 0xba -> LATIN SMALL LETTER L WITH CEDILLA
|
|
u'\u013d' # 0xbb -> LATIN CAPITAL LETTER L WITH CARON
|
|
u'\u013e' # 0xbc -> LATIN SMALL LETTER L WITH CARON
|
|
u'\u0139' # 0xbd -> LATIN CAPITAL LETTER L WITH ACUTE
|
|
u'\u013a' # 0xbe -> LATIN SMALL LETTER L WITH ACUTE
|
|
u'\u0145' # 0xbf -> LATIN CAPITAL LETTER N WITH CEDILLA
|
|
u'\u0146' # 0xc0 -> LATIN SMALL LETTER N WITH CEDILLA
|
|
u'\u0143' # 0xc1 -> LATIN CAPITAL LETTER N WITH ACUTE
|
|
u'\xac' # 0xc2 -> NOT SIGN
|
|
u'\u221a' # 0xc3 -> SQUARE ROOT
|
|
u'\u0144' # 0xc4 -> LATIN SMALL LETTER N WITH ACUTE
|
|
u'\u0147' # 0xc5 -> LATIN CAPITAL LETTER N WITH CARON
|
|
u'\u2206' # 0xc6 -> INCREMENT
|
|
u'\xab' # 0xc7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
|
u'\xbb' # 0xc8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
|
u'\u2026' # 0xc9 -> HORIZONTAL ELLIPSIS
|
|
u'\xa0' # 0xca -> NO-BREAK SPACE
|
|
u'\u0148' # 0xcb -> LATIN SMALL LETTER N WITH CARON
|
|
u'\u0150' # 0xcc -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
|
u'\xd5' # 0xcd -> LATIN CAPITAL LETTER O WITH TILDE
|
|
u'\u0151' # 0xce -> LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
|
u'\u014c' # 0xcf -> LATIN CAPITAL LETTER O WITH MACRON
|
|
u'\u2013' # 0xd0 -> EN DASH
|
|
u'\u2014' # 0xd1 -> EM DASH
|
|
u'\u201c' # 0xd2 -> LEFT DOUBLE QUOTATION MARK
|
|
u'\u201d' # 0xd3 -> RIGHT DOUBLE QUOTATION MARK
|
|
u'\u2018' # 0xd4 -> LEFT SINGLE QUOTATION MARK
|
|
u'\u2019' # 0xd5 -> RIGHT SINGLE QUOTATION MARK
|
|
u'\xf7' # 0xd6 -> DIVISION SIGN
|
|
u'\u25ca' # 0xd7 -> LOZENGE
|
|
u'\u014d' # 0xd8 -> LATIN SMALL LETTER O WITH MACRON
|
|
u'\u0154' # 0xd9 -> LATIN CAPITAL LETTER R WITH ACUTE
|
|
u'\u0155' # 0xda -> LATIN SMALL LETTER R WITH ACUTE
|
|
u'\u0158' # 0xdb -> LATIN CAPITAL LETTER R WITH CARON
|
|
u'\u2039' # 0xdc -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
|
u'\u203a' # 0xdd -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
|
u'\u0159' # 0xde -> LATIN SMALL LETTER R WITH CARON
|
|
u'\u0156' # 0xdf -> LATIN CAPITAL LETTER R WITH CEDILLA
|
|
u'\u0157' # 0xe0 -> LATIN SMALL LETTER R WITH CEDILLA
|
|
u'\u0160' # 0xe1 -> LATIN CAPITAL LETTER S WITH CARON
|
|
u'\u201a' # 0xe2 -> SINGLE LOW-9 QUOTATION MARK
|
|
u'\u201e' # 0xe3 -> DOUBLE LOW-9 QUOTATION MARK
|
|
u'\u0161' # 0xe4 -> LATIN SMALL LETTER S WITH CARON
|
|
u'\u015a' # 0xe5 -> LATIN CAPITAL LETTER S WITH ACUTE
|
|
u'\u015b' # 0xe6 -> LATIN SMALL LETTER S WITH ACUTE
|
|
u'\xc1' # 0xe7 -> LATIN CAPITAL LETTER A WITH ACUTE
|
|
u'\u0164' # 0xe8 -> LATIN CAPITAL LETTER T WITH CARON
|
|
u'\u0165' # 0xe9 -> LATIN SMALL LETTER T WITH CARON
|
|
u'\xcd' # 0xea -> LATIN CAPITAL LETTER I WITH ACUTE
|
|
u'\u017d' # 0xeb -> LATIN CAPITAL LETTER Z WITH CARON
|
|
u'\u017e' # 0xec -> LATIN SMALL LETTER Z WITH CARON
|
|
u'\u016a' # 0xed -> LATIN CAPITAL LETTER U WITH MACRON
|
|
u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE
|
|
u'\xd4' # 0xef -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
|
u'\u016b' # 0xf0 -> LATIN SMALL LETTER U WITH MACRON
|
|
u'\u016e' # 0xf1 -> LATIN CAPITAL LETTER U WITH RING ABOVE
|
|
u'\xda' # 0xf2 -> LATIN CAPITAL LETTER U WITH ACUTE
|
|
u'\u016f' # 0xf3 -> LATIN SMALL LETTER U WITH RING ABOVE
|
|
u'\u0170' # 0xf4 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
|
u'\u0171' # 0xf5 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
|
u'\u0172' # 0xf6 -> LATIN CAPITAL LETTER U WITH OGONEK
|
|
u'\u0173' # 0xf7 -> LATIN SMALL LETTER U WITH OGONEK
|
|
u'\xdd' # 0xf8 -> LATIN CAPITAL LETTER Y WITH ACUTE
|
|
u'\xfd' # 0xf9 -> LATIN SMALL LETTER Y WITH ACUTE
|
|
u'\u0137' # 0xfa -> LATIN SMALL LETTER K WITH CEDILLA
|
|
u'\u017b' # 0xfb -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
|
u'\u0141' # 0xfc -> LATIN CAPITAL LETTER L WITH STROKE
|
|
u'\u017c' # 0xfd -> LATIN SMALL LETTER Z WITH DOT ABOVE
|
|
u'\u0122' # 0xfe -> LATIN CAPITAL LETTER G WITH CEDILLA
|
|
u'\u02c7' # 0xff -> CARON
|
|
)
|
|
|
|
### Encoding Map
|
|
|
|
encoding_map = {
|
|
0x0000: 0x00, # CONTROL CHARACTER
|
|
0x0001: 0x01, # CONTROL CHARACTER
|
|
0x0002: 0x02, # CONTROL CHARACTER
|
|
0x0003: 0x03, # CONTROL CHARACTER
|
|
0x0004: 0x04, # CONTROL CHARACTER
|
|
0x0005: 0x05, # CONTROL CHARACTER
|
|
0x0006: 0x06, # CONTROL CHARACTER
|
|
0x0007: 0x07, # CONTROL CHARACTER
|
|
0x0008: 0x08, # CONTROL CHARACTER
|
|
0x0009: 0x09, # CONTROL CHARACTER
|
|
0x000a: 0x0a, # CONTROL CHARACTER
|
|
0x000b: 0x0b, # CONTROL CHARACTER
|
|
0x000c: 0x0c, # CONTROL CHARACTER
|
|
0x000d: 0x0d, # CONTROL CHARACTER
|
|
0x000e: 0x0e, # CONTROL CHARACTER
|
|
0x000f: 0x0f, # CONTROL CHARACTER
|
|
0x0010: 0x10, # CONTROL CHARACTER
|
|
0x0011: 0x11, # CONTROL CHARACTER
|
|
0x0012: 0x12, # CONTROL CHARACTER
|
|
0x0013: 0x13, # CONTROL CHARACTER
|
|
0x0014: 0x14, # CONTROL CHARACTER
|
|
0x0015: 0x15, # CONTROL CHARACTER
|
|
0x0016: 0x16, # CONTROL CHARACTER
|
|
0x0017: 0x17, # CONTROL CHARACTER
|
|
0x0018: 0x18, # CONTROL CHARACTER
|
|
0x0019: 0x19, # CONTROL CHARACTER
|
|
0x001a: 0x1a, # CONTROL CHARACTER
|
|
0x001b: 0x1b, # CONTROL CHARACTER
|
|
0x001c: 0x1c, # CONTROL CHARACTER
|
|
0x001d: 0x1d, # CONTROL CHARACTER
|
|
0x001e: 0x1e, # CONTROL CHARACTER
|
|
0x001f: 0x1f, # CONTROL CHARACTER
|
|
0x0020: 0x20, # SPACE
|
|
0x0021: 0x21, # EXCLAMATION MARK
|
|
0x0022: 0x22, # QUOTATION MARK
|
|
0x0023: 0x23, # NUMBER SIGN
|
|
0x0024: 0x24, # DOLLAR SIGN
|
|
0x0025: 0x25, # PERCENT SIGN
|
|
0x0026: 0x26, # AMPERSAND
|
|
0x0027: 0x27, # APOSTROPHE
|
|
0x0028: 0x28, # LEFT PARENTHESIS
|
|
0x0029: 0x29, # RIGHT PARENTHESIS
|
|
0x002a: 0x2a, # ASTERISK
|
|
0x002b: 0x2b, # PLUS SIGN
|
|
0x002c: 0x2c, # COMMA
|
|
0x002d: 0x2d, # HYPHEN-MINUS
|
|
0x002e: 0x2e, # FULL STOP
|
|
0x002f: 0x2f, # SOLIDUS
|
|
0x0030: 0x30, # DIGIT ZERO
|
|
0x0031: 0x31, # DIGIT ONE
|
|
0x0032: 0x32, # DIGIT TWO
|
|
0x0033: 0x33, # DIGIT THREE
|
|
0x0034: 0x34, # DIGIT FOUR
|
|
0x0035: 0x35, # DIGIT FIVE
|
|
0x0036: 0x36, # DIGIT SIX
|
|
0x0037: 0x37, # DIGIT SEVEN
|
|
0x0038: 0x38, # DIGIT EIGHT
|
|
0x0039: 0x39, # DIGIT NINE
|
|
0x003a: 0x3a, # COLON
|
|
0x003b: 0x3b, # SEMICOLON
|
|
0x003c: 0x3c, # LESS-THAN SIGN
|
|
0x003d: 0x3d, # EQUALS SIGN
|
|
0x003e: 0x3e, # GREATER-THAN SIGN
|
|
0x003f: 0x3f, # QUESTION MARK
|
|
0x0040: 0x40, # COMMERCIAL AT
|
|
0x0041: 0x41, # LATIN CAPITAL LETTER A
|
|
0x0042: 0x42, # LATIN CAPITAL LETTER B
|
|
0x0043: 0x43, # LATIN CAPITAL LETTER C
|
|
0x0044: 0x44, # LATIN CAPITAL LETTER D
|
|
0x0045: 0x45, # LATIN CAPITAL LETTER E
|
|
0x0046: 0x46, # LATIN CAPITAL LETTER F
|
|
0x0047: 0x47, # LATIN CAPITAL LETTER G
|
|
0x0048: 0x48, # LATIN CAPITAL LETTER H
|
|
0x0049: 0x49, # LATIN CAPITAL LETTER I
|
|
0x004a: 0x4a, # LATIN CAPITAL LETTER J
|
|
0x004b: 0x4b, # LATIN CAPITAL LETTER K
|
|
0x004c: 0x4c, # LATIN CAPITAL LETTER L
|
|
0x004d: 0x4d, # LATIN CAPITAL LETTER M
|
|
0x004e: 0x4e, # LATIN CAPITAL LETTER N
|
|
0x004f: 0x4f, # LATIN CAPITAL LETTER O
|
|
0x0050: 0x50, # LATIN CAPITAL LETTER P
|
|
0x0051: 0x51, # LATIN CAPITAL LETTER Q
|
|
0x0052: 0x52, # LATIN CAPITAL LETTER R
|
|
0x0053: 0x53, # LATIN CAPITAL LETTER S
|
|
0x0054: 0x54, # LATIN CAPITAL LETTER T
|
|
0x0055: 0x55, # LATIN CAPITAL LETTER U
|
|
0x0056: 0x56, # LATIN CAPITAL LETTER V
|
|
0x0057: 0x57, # LATIN CAPITAL LETTER W
|
|
0x0058: 0x58, # LATIN CAPITAL LETTER X
|
|
0x0059: 0x59, # LATIN CAPITAL LETTER Y
|
|
0x005a: 0x5a, # LATIN CAPITAL LETTER Z
|
|
0x005b: 0x5b, # LEFT SQUARE BRACKET
|
|
0x005c: 0x5c, # REVERSE SOLIDUS
|
|
0x005d: 0x5d, # RIGHT SQUARE BRACKET
|
|
0x005e: 0x5e, # CIRCUMFLEX ACCENT
|
|
0x005f: 0x5f, # LOW LINE
|
|
0x0060: 0x60, # GRAVE ACCENT
|
|
0x0061: 0x61, # LATIN SMALL LETTER A
|
|
0x0062: 0x62, # LATIN SMALL LETTER B
|
|
0x0063: 0x63, # LATIN SMALL LETTER C
|
|
0x0064: 0x64, # LATIN SMALL LETTER D
|
|
0x0065: 0x65, # LATIN SMALL LETTER E
|
|
0x0066: 0x66, # LATIN SMALL LETTER F
|
|
0x0067: 0x67, # LATIN SMALL LETTER G
|
|
0x0068: 0x68, # LATIN SMALL LETTER H
|
|
0x0069: 0x69, # LATIN SMALL LETTER I
|
|
0x006a: 0x6a, # LATIN SMALL LETTER J
|
|
0x006b: 0x6b, # LATIN SMALL LETTER K
|
|
0x006c: 0x6c, # LATIN SMALL LETTER L
|
|
0x006d: 0x6d, # LATIN SMALL LETTER M
|
|
0x006e: 0x6e, # LATIN SMALL LETTER N
|
|
0x006f: 0x6f, # LATIN SMALL LETTER O
|
|
0x0070: 0x70, # LATIN SMALL LETTER P
|
|
0x0071: 0x71, # LATIN SMALL LETTER Q
|
|
0x0072: 0x72, # LATIN SMALL LETTER R
|
|
0x0073: 0x73, # LATIN SMALL LETTER S
|
|
0x0074: 0x74, # LATIN SMALL LETTER T
|
|
0x0075: 0x75, # LATIN SMALL LETTER U
|
|
0x0076: 0x76, # LATIN SMALL LETTER V
|
|
0x0077: 0x77, # LATIN SMALL LETTER W
|
|
0x0078: 0x78, # LATIN SMALL LETTER X
|
|
0x0079: 0x79, # LATIN SMALL LETTER Y
|
|
0x007a: 0x7a, # LATIN SMALL LETTER Z
|
|
0x007b: 0x7b, # LEFT CURLY BRACKET
|
|
0x007c: 0x7c, # VERTICAL LINE
|
|
0x007d: 0x7d, # RIGHT CURLY BRACKET
|
|
0x007e: 0x7e, # TILDE
|
|
0x007f: 0x7f, # CONTROL CHARACTER
|
|
0x00a0: 0xca, # NO-BREAK SPACE
|
|
0x00a3: 0xa3, # POUND SIGN
|
|
0x00a7: 0xa4, # SECTION SIGN
|
|
0x00a8: 0xac, # DIAERESIS
|
|
0x00a9: 0xa9, # COPYRIGHT SIGN
|
|
0x00ab: 0xc7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
|
0x00ac: 0xc2, # NOT SIGN
|
|
0x00ae: 0xa8, # REGISTERED SIGN
|
|
0x00b0: 0xa1, # DEGREE SIGN
|
|
0x00b6: 0xa6, # PILCROW SIGN
|
|
0x00bb: 0xc8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
|
0x00c1: 0xe7, # LATIN CAPITAL LETTER A WITH ACUTE
|
|
0x00c4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
|
0x00c9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE
|
|
0x00cd: 0xea, # LATIN CAPITAL LETTER I WITH ACUTE
|
|
0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE
|
|
0x00d4: 0xef, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
|
0x00d5: 0xcd, # LATIN CAPITAL LETTER O WITH TILDE
|
|
0x00d6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
|
0x00da: 0xf2, # LATIN CAPITAL LETTER U WITH ACUTE
|
|
0x00dc: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
|
0x00dd: 0xf8, # LATIN CAPITAL LETTER Y WITH ACUTE
|
|
0x00df: 0xa7, # LATIN SMALL LETTER SHARP S
|
|
0x00e1: 0x87, # LATIN SMALL LETTER A WITH ACUTE
|
|
0x00e4: 0x8a, # LATIN SMALL LETTER A WITH DIAERESIS
|
|
0x00e9: 0x8e, # LATIN SMALL LETTER E WITH ACUTE
|
|
0x00ed: 0x92, # LATIN SMALL LETTER I WITH ACUTE
|
|
0x00f3: 0x97, # LATIN SMALL LETTER O WITH ACUTE
|
|
0x00f4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
|
0x00f5: 0x9b, # LATIN SMALL LETTER O WITH TILDE
|
|
0x00f6: 0x9a, # LATIN SMALL LETTER O WITH DIAERESIS
|
|
0x00f7: 0xd6, # DIVISION SIGN
|
|
0x00fa: 0x9c, # LATIN SMALL LETTER U WITH ACUTE
|
|
0x00fc: 0x9f, # LATIN SMALL LETTER U WITH DIAERESIS
|
|
0x00fd: 0xf9, # LATIN SMALL LETTER Y WITH ACUTE
|
|
0x0100: 0x81, # LATIN CAPITAL LETTER A WITH MACRON
|
|
0x0101: 0x82, # LATIN SMALL LETTER A WITH MACRON
|
|
0x0104: 0x84, # LATIN CAPITAL LETTER A WITH OGONEK
|
|
0x0105: 0x88, # LATIN SMALL LETTER A WITH OGONEK
|
|
0x0106: 0x8c, # LATIN CAPITAL LETTER C WITH ACUTE
|
|
0x0107: 0x8d, # LATIN SMALL LETTER C WITH ACUTE
|
|
0x010c: 0x89, # LATIN CAPITAL LETTER C WITH CARON
|
|
0x010d: 0x8b, # LATIN SMALL LETTER C WITH CARON
|
|
0x010e: 0x91, # LATIN CAPITAL LETTER D WITH CARON
|
|
0x010f: 0x93, # LATIN SMALL LETTER D WITH CARON
|
|
0x0112: 0x94, # LATIN CAPITAL LETTER E WITH MACRON
|
|
0x0113: 0x95, # LATIN SMALL LETTER E WITH MACRON
|
|
0x0116: 0x96, # LATIN CAPITAL LETTER E WITH DOT ABOVE
|
|
0x0117: 0x98, # LATIN SMALL LETTER E WITH DOT ABOVE
|
|
0x0118: 0xa2, # LATIN CAPITAL LETTER E WITH OGONEK
|
|
0x0119: 0xab, # LATIN SMALL LETTER E WITH OGONEK
|
|
0x011a: 0x9d, # LATIN CAPITAL LETTER E WITH CARON
|
|
0x011b: 0x9e, # LATIN SMALL LETTER E WITH CARON
|
|
0x0122: 0xfe, # LATIN CAPITAL LETTER G WITH CEDILLA
|
|
0x0123: 0xae, # LATIN SMALL LETTER G WITH CEDILLA
|
|
0x012a: 0xb1, # LATIN CAPITAL LETTER I WITH MACRON
|
|
0x012b: 0xb4, # LATIN SMALL LETTER I WITH MACRON
|
|
0x012e: 0xaf, # LATIN CAPITAL LETTER I WITH OGONEK
|
|
0x012f: 0xb0, # LATIN SMALL LETTER I WITH OGONEK
|
|
0x0136: 0xb5, # LATIN CAPITAL LETTER K WITH CEDILLA
|
|
0x0137: 0xfa, # LATIN SMALL LETTER K WITH CEDILLA
|
|
0x0139: 0xbd, # LATIN CAPITAL LETTER L WITH ACUTE
|
|
0x013a: 0xbe, # LATIN SMALL LETTER L WITH ACUTE
|
|
0x013b: 0xb9, # LATIN CAPITAL LETTER L WITH CEDILLA
|
|
0x013c: 0xba, # LATIN SMALL LETTER L WITH CEDILLA
|
|
0x013d: 0xbb, # LATIN CAPITAL LETTER L WITH CARON
|
|
0x013e: 0xbc, # LATIN SMALL LETTER L WITH CARON
|
|
0x0141: 0xfc, # LATIN CAPITAL LETTER L WITH STROKE
|
|
0x0142: 0xb8, # LATIN SMALL LETTER L WITH STROKE
|
|
0x0143: 0xc1, # LATIN CAPITAL LETTER N WITH ACUTE
|
|
0x0144: 0xc4, # LATIN SMALL LETTER N WITH ACUTE
|
|
0x0145: 0xbf, # LATIN CAPITAL LETTER N WITH CEDILLA
|
|
0x0146: 0xc0, # LATIN SMALL LETTER N WITH CEDILLA
|
|
0x0147: 0xc5, # LATIN CAPITAL LETTER N WITH CARON
|
|
0x0148: 0xcb, # LATIN SMALL LETTER N WITH CARON
|
|
0x014c: 0xcf, # LATIN CAPITAL LETTER O WITH MACRON
|
|
0x014d: 0xd8, # LATIN SMALL LETTER O WITH MACRON
|
|
0x0150: 0xcc, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
|
0x0151: 0xce, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
|
0x0154: 0xd9, # LATIN CAPITAL LETTER R WITH ACUTE
|
|
0x0155: 0xda, # LATIN SMALL LETTER R WITH ACUTE
|
|
0x0156: 0xdf, # LATIN CAPITAL LETTER R WITH CEDILLA
|
|
0x0157: 0xe0, # LATIN SMALL LETTER R WITH CEDILLA
|
|
0x0158: 0xdb, # LATIN CAPITAL LETTER R WITH CARON
|
|
0x0159: 0xde, # LATIN SMALL LETTER R WITH CARON
|
|
0x015a: 0xe5, # LATIN CAPITAL LETTER S WITH ACUTE
|
|
0x015b: 0xe6, # LATIN SMALL LETTER S WITH ACUTE
|
|
0x0160: 0xe1, # LATIN CAPITAL LETTER S WITH CARON
|
|
0x0161: 0xe4, # LATIN SMALL LETTER S WITH CARON
|
|
0x0164: 0xe8, # LATIN CAPITAL LETTER T WITH CARON
|
|
0x0165: 0xe9, # LATIN SMALL LETTER T WITH CARON
|
|
0x016a: 0xed, # LATIN CAPITAL LETTER U WITH MACRON
|
|
0x016b: 0xf0, # LATIN SMALL LETTER U WITH MACRON
|
|
0x016e: 0xf1, # LATIN CAPITAL LETTER U WITH RING ABOVE
|
|
0x016f: 0xf3, # LATIN SMALL LETTER U WITH RING ABOVE
|
|
0x0170: 0xf4, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
|
0x0171: 0xf5, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
|
0x0172: 0xf6, # LATIN CAPITAL LETTER U WITH OGONEK
|
|
0x0173: 0xf7, # LATIN SMALL LETTER U WITH OGONEK
|
|
0x0179: 0x8f, # LATIN CAPITAL LETTER Z WITH ACUTE
|
|
0x017a: 0x90, # LATIN SMALL LETTER Z WITH ACUTE
|
|
0x017b: 0xfb, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
|
0x017c: 0xfd, # LATIN SMALL LETTER Z WITH DOT ABOVE
|
|
0x017d: 0xeb, # LATIN CAPITAL LETTER Z WITH CARON
|
|
0x017e: 0xec, # LATIN SMALL LETTER Z WITH CARON
|
|
0x02c7: 0xff, # CARON
|
|
0x2013: 0xd0, # EN DASH
|
|
0x2014: 0xd1, # EM DASH
|
|
0x2018: 0xd4, # LEFT SINGLE QUOTATION MARK
|
|
0x2019: 0xd5, # RIGHT SINGLE QUOTATION MARK
|
|
0x201a: 0xe2, # SINGLE LOW-9 QUOTATION MARK
|
|
0x201c: 0xd2, # LEFT DOUBLE QUOTATION MARK
|
|
0x201d: 0xd3, # RIGHT DOUBLE QUOTATION MARK
|
|
0x201e: 0xe3, # DOUBLE LOW-9 QUOTATION MARK
|
|
0x2020: 0xa0, # DAGGER
|
|
0x2022: 0xa5, # BULLET
|
|
0x2026: 0xc9, # HORIZONTAL ELLIPSIS
|
|
0x2039: 0xdc, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
|
0x203a: 0xdd, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
|
0x2122: 0xaa, # TRADE MARK SIGN
|
|
0x2202: 0xb6, # PARTIAL DIFFERENTIAL
|
|
0x2206: 0xc6, # INCREMENT
|
|
0x2211: 0xb7, # N-ARY SUMMATION
|
|
0x221a: 0xc3, # SQUARE ROOT
|
|
0x2260: 0xad, # NOT EQUAL TO
|
|
0x2264: 0xb2, # LESS-THAN OR EQUAL TO
|
|
0x2265: 0xb3, # GREATER-THAN OR EQUAL TO
|
|
0x25ca: 0xd7, # LOZENGE
|
|
} |