Commit 0f00ba8b authored by Marc-André Lemburg's avatar Marc-André Lemburg

Replace the old EBCDIC codecs with new ones using the decoding table.

parent 7797be7b
""" Python Character Mapping Codec generated from 'CP037.TXT' with gencodec.py. """ Python Character Mapping Codec generated from 'VENDORS/MICSFT/EBCDIC/CP037.TXT' with gencodec.py.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
(c) Copyright 2000 Guido van Rossum.
"""#" """#"
...@@ -19,7 +14,7 @@ class Codec(codecs.Codec): ...@@ -19,7 +14,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'): def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_map) return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter): class StreamWriter(Codec,codecs.StreamWriter):
pass pass
...@@ -275,6 +270,524 @@ decoding_map.update({ ...@@ -275,6 +270,524 @@ decoding_map.update({
0x00ff: 0x009f, # CONTROL 0x00ff: 0x009f, # CONTROL
}) })
### Decoding Table
decoding_table = (
u'\x00' # 0x0000 -> NULL
u'\x01' # 0x0001 -> START OF HEADING
u'\x02' # 0x0002 -> START OF TEXT
u'\x03' # 0x0003 -> END OF TEXT
u'\x9c' # 0x0004 -> CONTROL
u'\t' # 0x0005 -> HORIZONTAL TABULATION
u'\x86' # 0x0006 -> CONTROL
u'\x7f' # 0x0007 -> DELETE
u'\x97' # 0x0008 -> CONTROL
u'\x8d' # 0x0009 -> CONTROL
u'\x8e' # 0x000a -> CONTROL
u'\x0b' # 0x000b -> VERTICAL TABULATION
u'\x0c' # 0x000c -> FORM FEED
u'\r' # 0x000d -> CARRIAGE RETURN
u'\x0e' # 0x000e -> SHIFT OUT
u'\x0f' # 0x000f -> SHIFT IN
u'\x10' # 0x0010 -> DATA LINK ESCAPE
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
u'\x9d' # 0x0014 -> CONTROL
u'\x85' # 0x0015 -> CONTROL
u'\x08' # 0x0016 -> BACKSPACE
u'\x87' # 0x0017 -> CONTROL
u'\x18' # 0x0018 -> CANCEL
u'\x19' # 0x0019 -> END OF MEDIUM
u'\x92' # 0x001a -> CONTROL
u'\x8f' # 0x001b -> CONTROL
u'\x1c' # 0x001c -> FILE SEPARATOR
u'\x1d' # 0x001d -> GROUP SEPARATOR
u'\x1e' # 0x001e -> RECORD SEPARATOR
u'\x1f' # 0x001f -> UNIT SEPARATOR
u'\x80' # 0x0020 -> CONTROL
u'\x81' # 0x0021 -> CONTROL
u'\x82' # 0x0022 -> CONTROL
u'\x83' # 0x0023 -> CONTROL
u'\x84' # 0x0024 -> CONTROL
u'\n' # 0x0025 -> LINE FEED
u'\x17' # 0x0026 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x0027 -> ESCAPE
u'\x88' # 0x0028 -> CONTROL
u'\x89' # 0x0029 -> CONTROL
u'\x8a' # 0x002a -> CONTROL
u'\x8b' # 0x002b -> CONTROL
u'\x8c' # 0x002c -> CONTROL
u'\x05' # 0x002d -> ENQUIRY
u'\x06' # 0x002e -> ACKNOWLEDGE
u'\x07' # 0x002f -> BELL
u'\x90' # 0x0030 -> CONTROL
u'\x91' # 0x0031 -> CONTROL
u'\x16' # 0x0032 -> SYNCHRONOUS IDLE
u'\x93' # 0x0033 -> CONTROL
u'\x94' # 0x0034 -> CONTROL
u'\x95' # 0x0035 -> CONTROL
u'\x96' # 0x0036 -> CONTROL
u'\x04' # 0x0037 -> END OF TRANSMISSION
u'\x98' # 0x0038 -> CONTROL
u'\x99' # 0x0039 -> CONTROL
u'\x9a' # 0x003a -> CONTROL
u'\x9b' # 0x003b -> CONTROL
u'\x14' # 0x003c -> DEVICE CONTROL FOUR
u'\x15' # 0x003d -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x003e -> CONTROL
u'\x1a' # 0x003f -> SUBSTITUTE
u' ' # 0x0040 -> SPACE
u'\xa0' # 0x0041 -> NO-BREAK SPACE
u'\xe2' # 0x0042 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\xe4' # 0x0043 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe0' # 0x0044 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0x0045 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe3' # 0x0046 -> LATIN SMALL LETTER A WITH TILDE
u'\xe5' # 0x0047 -> LATIN SMALL LETTER A WITH RING ABOVE
u'\xe7' # 0x0048 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xf1' # 0x0049 -> LATIN SMALL LETTER N WITH TILDE
u'\xa2' # 0x004a -> CENT SIGN
u'.' # 0x004b -> FULL STOP
u'<' # 0x004c -> LESS-THAN SIGN
u'(' # 0x004d -> LEFT PARENTHESIS
u'+' # 0x004e -> PLUS SIGN
u'|' # 0x004f -> VERTICAL LINE
u'&' # 0x0050 -> AMPERSAND
u'\xe9' # 0x0051 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0x0052 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0x0053 -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xe8' # 0x0054 -> LATIN SMALL LETTER E WITH GRAVE
u'\xed' # 0x0055 -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0x0056 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0x0057 -> LATIN SMALL LETTER I WITH DIAERESIS
u'\xec' # 0x0058 -> LATIN SMALL LETTER I WITH GRAVE
u'\xdf' # 0x0059 -> LATIN SMALL LETTER SHARP S (GERMAN)
u'!' # 0x005a -> EXCLAMATION MARK
u'$' # 0x005b -> DOLLAR SIGN
u'*' # 0x005c -> ASTERISK
u')' # 0x005d -> RIGHT PARENTHESIS
u';' # 0x005e -> SEMICOLON
u'\xac' # 0x005f -> NOT SIGN
u'-' # 0x0060 -> HYPHEN-MINUS
u'/' # 0x0061 -> SOLIDUS
u'\xc2' # 0x0062 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\xc4' # 0x0063 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc0' # 0x0064 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0x0065 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc3' # 0x0066 -> LATIN CAPITAL LETTER A WITH TILDE
u'\xc5' # 0x0067 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'\xc7' # 0x0068 -> LATIN CAPITAL LETTER C WITH CEDILLA
u'\xd1' # 0x0069 -> LATIN CAPITAL LETTER N WITH TILDE
u'\xa6' # 0x006a -> BROKEN BAR
u',' # 0x006b -> COMMA
u'%' # 0x006c -> PERCENT SIGN
u'_' # 0x006d -> LOW LINE
u'>' # 0x006e -> GREATER-THAN SIGN
u'?' # 0x006f -> QUESTION MARK
u'\xf8' # 0x0070 -> LATIN SMALL LETTER O WITH STROKE
u'\xc9' # 0x0071 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0x0072 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0x0073 -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\xc8' # 0x0074 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xcd' # 0x0075 -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0x0076 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0x0077 -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\xcc' # 0x0078 -> LATIN CAPITAL LETTER I WITH GRAVE
u'`' # 0x0079 -> GRAVE ACCENT
u':' # 0x007a -> COLON
u'#' # 0x007b -> NUMBER SIGN
u'@' # 0x007c -> COMMERCIAL AT
u"'" # 0x007d -> APOSTROPHE
u'=' # 0x007e -> EQUALS SIGN
u'"' # 0x007f -> QUOTATION MARK
u'\xd8' # 0x0080 -> LATIN CAPITAL LETTER O WITH STROKE
u'a' # 0x0081 -> LATIN SMALL LETTER A
u'b' # 0x0082 -> LATIN SMALL LETTER B
u'c' # 0x0083 -> LATIN SMALL LETTER C
u'd' # 0x0084 -> LATIN SMALL LETTER D
u'e' # 0x0085 -> LATIN SMALL LETTER E
u'f' # 0x0086 -> LATIN SMALL LETTER F
u'g' # 0x0087 -> LATIN SMALL LETTER G
u'h' # 0x0088 -> LATIN SMALL LETTER H
u'i' # 0x0089 -> LATIN SMALL LETTER I
u'\xab' # 0x008a -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbb' # 0x008b -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xf0' # 0x008c -> LATIN SMALL LETTER ETH (ICELANDIC)
u'\xfd' # 0x008d -> LATIN SMALL LETTER Y WITH ACUTE
u'\xfe' # 0x008e -> LATIN SMALL LETTER THORN (ICELANDIC)
u'\xb1' # 0x008f -> PLUS-MINUS SIGN
u'\xb0' # 0x0090 -> DEGREE SIGN
u'j' # 0x0091 -> LATIN SMALL LETTER J
u'k' # 0x0092 -> LATIN SMALL LETTER K
u'l' # 0x0093 -> LATIN SMALL LETTER L
u'm' # 0x0094 -> LATIN SMALL LETTER M
u'n' # 0x0095 -> LATIN SMALL LETTER N
u'o' # 0x0096 -> LATIN SMALL LETTER O
u'p' # 0x0097 -> LATIN SMALL LETTER P
u'q' # 0x0098 -> LATIN SMALL LETTER Q
u'r' # 0x0099 -> LATIN SMALL LETTER R
u'\xaa' # 0x009a -> FEMININE ORDINAL INDICATOR
u'\xba' # 0x009b -> MASCULINE ORDINAL INDICATOR
u'\xe6' # 0x009c -> LATIN SMALL LIGATURE AE
u'\xb8' # 0x009d -> CEDILLA
u'\xc6' # 0x009e -> LATIN CAPITAL LIGATURE AE
u'\xa4' # 0x009f -> CURRENCY SIGN
u'\xb5' # 0x00a0 -> MICRO SIGN
u'~' # 0x00a1 -> TILDE
u's' # 0x00a2 -> LATIN SMALL LETTER S
u't' # 0x00a3 -> LATIN SMALL LETTER T
u'u' # 0x00a4 -> LATIN SMALL LETTER U
u'v' # 0x00a5 -> LATIN SMALL LETTER V
u'w' # 0x00a6 -> LATIN SMALL LETTER W
u'x' # 0x00a7 -> LATIN SMALL LETTER X
u'y' # 0x00a8 -> LATIN SMALL LETTER Y
u'z' # 0x00a9 -> LATIN SMALL LETTER Z
u'\xa1' # 0x00aa -> INVERTED EXCLAMATION MARK
u'\xbf' # 0x00ab -> INVERTED QUESTION MARK
u'\xd0' # 0x00ac -> LATIN CAPITAL LETTER ETH (ICELANDIC)
u'\xdd' # 0x00ad -> LATIN CAPITAL LETTER Y WITH ACUTE
u'\xde' # 0x00ae -> LATIN CAPITAL LETTER THORN (ICELANDIC)
u'\xae' # 0x00af -> REGISTERED SIGN
u'^' # 0x00b0 -> CIRCUMFLEX ACCENT
u'\xa3' # 0x00b1 -> POUND SIGN
u'\xa5' # 0x00b2 -> YEN SIGN
u'\xb7' # 0x00b3 -> MIDDLE DOT
u'\xa9' # 0x00b4 -> COPYRIGHT SIGN
u'\xa7' # 0x00b5 -> SECTION SIGN
u'\xb6' # 0x00b6 -> PILCROW SIGN
u'\xbc' # 0x00b7 -> VULGAR FRACTION ONE QUARTER
u'\xbd' # 0x00b8 -> VULGAR FRACTION ONE HALF
u'\xbe' # 0x00b9 -> VULGAR FRACTION THREE QUARTERS
u'[' # 0x00ba -> LEFT SQUARE BRACKET
u']' # 0x00bb -> RIGHT SQUARE BRACKET
u'\xaf' # 0x00bc -> MACRON
u'\xa8' # 0x00bd -> DIAERESIS
u'\xb4' # 0x00be -> ACUTE ACCENT
u'\xd7' # 0x00bf -> MULTIPLICATION SIGN
u'{' # 0x00c0 -> LEFT CURLY BRACKET
u'A' # 0x00c1 -> LATIN CAPITAL LETTER A
u'B' # 0x00c2 -> LATIN CAPITAL LETTER B
u'C' # 0x00c3 -> LATIN CAPITAL LETTER C
u'D' # 0x00c4 -> LATIN CAPITAL LETTER D
u'E' # 0x00c5 -> LATIN CAPITAL LETTER E
u'F' # 0x00c6 -> LATIN CAPITAL LETTER F
u'G' # 0x00c7 -> LATIN CAPITAL LETTER G
u'H' # 0x00c8 -> LATIN CAPITAL LETTER H
u'I' # 0x00c9 -> LATIN CAPITAL LETTER I
u'\xad' # 0x00ca -> SOFT HYPHEN
u'\xf4' # 0x00cb -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\xf6' # 0x00cc -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf2' # 0x00cd -> LATIN SMALL LETTER O WITH GRAVE
u'\xf3' # 0x00ce -> LATIN SMALL LETTER O WITH ACUTE
u'\xf5' # 0x00cf -> LATIN SMALL LETTER O WITH TILDE
u'}' # 0x00d0 -> RIGHT CURLY BRACKET
u'J' # 0x00d1 -> LATIN CAPITAL LETTER J
u'K' # 0x00d2 -> LATIN CAPITAL LETTER K
u'L' # 0x00d3 -> LATIN CAPITAL LETTER L
u'M' # 0x00d4 -> LATIN CAPITAL LETTER M
u'N' # 0x00d5 -> LATIN CAPITAL LETTER N
u'O' # 0x00d6 -> LATIN CAPITAL LETTER O
u'P' # 0x00d7 -> LATIN CAPITAL LETTER P
u'Q' # 0x00d8 -> LATIN CAPITAL LETTER Q
u'R' # 0x00d9 -> LATIN CAPITAL LETTER R
u'\xb9' # 0x00da -> SUPERSCRIPT ONE
u'\xfb' # 0x00db -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xfc' # 0x00dc -> LATIN SMALL LETTER U WITH DIAERESIS
u'\xf9' # 0x00dd -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0x00de -> LATIN SMALL LETTER U WITH ACUTE
u'\xff' # 0x00df -> LATIN SMALL LETTER Y WITH DIAERESIS
u'\\' # 0x00e0 -> REVERSE SOLIDUS
u'\xf7' # 0x00e1 -> DIVISION SIGN
u'S' # 0x00e2 -> LATIN CAPITAL LETTER S
u'T' # 0x00e3 -> LATIN CAPITAL LETTER T
u'U' # 0x00e4 -> LATIN CAPITAL LETTER U
u'V' # 0x00e5 -> LATIN CAPITAL LETTER V
u'W' # 0x00e6 -> LATIN CAPITAL LETTER W
u'X' # 0x00e7 -> LATIN CAPITAL LETTER X
u'Y' # 0x00e8 -> LATIN CAPITAL LETTER Y
u'Z' # 0x00e9 -> LATIN CAPITAL LETTER Z
u'\xb2' # 0x00ea -> SUPERSCRIPT TWO
u'\xd4' # 0x00eb -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'\xd6' # 0x00ec -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd2' # 0x00ed -> LATIN CAPITAL LETTER O WITH GRAVE
u'\xd3' # 0x00ee -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd5' # 0x00ef -> LATIN CAPITAL LETTER O WITH TILDE
u'0' # 0x00f0 -> DIGIT ZERO
u'1' # 0x00f1 -> DIGIT ONE
u'2' # 0x00f2 -> DIGIT TWO
u'3' # 0x00f3 -> DIGIT THREE
u'4' # 0x00f4 -> DIGIT FOUR
u'5' # 0x00f5 -> DIGIT FIVE
u'6' # 0x00f6 -> DIGIT SIX
u'7' # 0x00f7 -> DIGIT SEVEN
u'8' # 0x00f8 -> DIGIT EIGHT
u'9' # 0x00f9 -> DIGIT NINE
u'\xb3' # 0x00fa -> SUPERSCRIPT THREE
u'\xdb' # 0x00fb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'\xdc' # 0x00fc -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\xd9' # 0x00fd -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0x00fe -> LATIN CAPITAL LETTER U WITH ACUTE
u'\x9f' # 0x00ff -> CONTROL
)
### Encoding Map ### Encoding Map
encoding_map = codecs.make_encoding_map(decoding_map) encoding_map = {
0x0000: 0x0000, # NULL
0x0001: 0x0001, # START OF HEADING
0x0002: 0x0002, # START OF TEXT
0x0003: 0x0003, # END OF TEXT
0x0004: 0x0037, # END OF TRANSMISSION
0x0005: 0x002d, # ENQUIRY
0x0006: 0x002e, # ACKNOWLEDGE
0x0007: 0x002f, # BELL
0x0008: 0x0016, # BACKSPACE
0x0009: 0x0005, # HORIZONTAL TABULATION
0x000a: 0x0025, # LINE FEED
0x000b: 0x000b, # VERTICAL TABULATION
0x000c: 0x000c, # FORM FEED
0x000d: 0x000d, # CARRIAGE RETURN
0x000e: 0x000e, # SHIFT OUT
0x000f: 0x000f, # SHIFT IN
0x0010: 0x0010, # DATA LINK ESCAPE
0x0011: 0x0011, # DEVICE CONTROL ONE
0x0012: 0x0012, # DEVICE CONTROL TWO
0x0013: 0x0013, # DEVICE CONTROL THREE
0x0014: 0x003c, # DEVICE CONTROL FOUR
0x0015: 0x003d, # NEGATIVE ACKNOWLEDGE
0x0016: 0x0032, # SYNCHRONOUS IDLE
0x0017: 0x0026, # END OF TRANSMISSION BLOCK
0x0018: 0x0018, # CANCEL
0x0019: 0x0019, # END OF MEDIUM
0x001a: 0x003f, # SUBSTITUTE
0x001b: 0x0027, # ESCAPE
0x001c: 0x001c, # FILE SEPARATOR
0x001d: 0x001d, # GROUP SEPARATOR
0x001e: 0x001e, # RECORD SEPARATOR
0x001f: 0x001f, # UNIT SEPARATOR
0x0020: 0x0040, # SPACE
0x0021: 0x005a, # EXCLAMATION MARK
0x0022: 0x007f, # QUOTATION MARK
0x0023: 0x007b, # NUMBER SIGN
0x0024: 0x005b, # DOLLAR SIGN
0x0025: 0x006c, # PERCENT SIGN
0x0026: 0x0050, # AMPERSAND
0x0027: 0x007d, # APOSTROPHE
0x0028: 0x004d, # LEFT PARENTHESIS
0x0029: 0x005d, # RIGHT PARENTHESIS
0x002a: 0x005c, # ASTERISK
0x002b: 0x004e, # PLUS SIGN
0x002c: 0x006b, # COMMA
0x002d: 0x0060, # HYPHEN-MINUS
0x002e: 0x004b, # FULL STOP
0x002f: 0x0061, # SOLIDUS
0x0030: 0x00f0, # DIGIT ZERO
0x0031: 0x00f1, # DIGIT ONE
0x0032: 0x00f2, # DIGIT TWO
0x0033: 0x00f3, # DIGIT THREE
0x0034: 0x00f4, # DIGIT FOUR
0x0035: 0x00f5, # DIGIT FIVE
0x0036: 0x00f6, # DIGIT SIX
0x0037: 0x00f7, # DIGIT SEVEN
0x0038: 0x00f8, # DIGIT EIGHT
0x0039: 0x00f9, # DIGIT NINE
0x003a: 0x007a, # COLON
0x003b: 0x005e, # SEMICOLON
0x003c: 0x004c, # LESS-THAN SIGN
0x003d: 0x007e, # EQUALS SIGN
0x003e: 0x006e, # GREATER-THAN SIGN
0x003f: 0x006f, # QUESTION MARK
0x0040: 0x007c, # COMMERCIAL AT
0x0041: 0x00c1, # LATIN CAPITAL LETTER A
0x0042: 0x00c2, # LATIN CAPITAL LETTER B
0x0043: 0x00c3, # LATIN CAPITAL LETTER C
0x0044: 0x00c4, # LATIN CAPITAL LETTER D
0x0045: 0x00c5, # LATIN CAPITAL LETTER E
0x0046: 0x00c6, # LATIN CAPITAL LETTER F
0x0047: 0x00c7, # LATIN CAPITAL LETTER G
0x0048: 0x00c8, # LATIN CAPITAL LETTER H
0x0049: 0x00c9, # LATIN CAPITAL LETTER I
0x004a: 0x00d1, # LATIN CAPITAL LETTER J
0x004b: 0x00d2, # LATIN CAPITAL LETTER K
0x004c: 0x00d3, # LATIN CAPITAL LETTER L
0x004d: 0x00d4, # LATIN CAPITAL LETTER M
0x004e: 0x00d5, # LATIN CAPITAL LETTER N
0x004f: 0x00d6, # LATIN CAPITAL LETTER O
0x0050: 0x00d7, # LATIN CAPITAL LETTER P
0x0051: 0x00d8, # LATIN CAPITAL LETTER Q
0x0052: 0x00d9, # LATIN CAPITAL LETTER R
0x0053: 0x00e2, # LATIN CAPITAL LETTER S
0x0054: 0x00e3, # LATIN CAPITAL LETTER T
0x0055: 0x00e4, # LATIN CAPITAL LETTER U
0x0056: 0x00e5, # LATIN CAPITAL LETTER V
0x0057: 0x00e6, # LATIN CAPITAL LETTER W
0x0058: 0x00e7, # LATIN CAPITAL LETTER X
0x0059: 0x00e8, # LATIN CAPITAL LETTER Y
0x005a: 0x00e9, # LATIN CAPITAL LETTER Z
0x005b: 0x00ba, # LEFT SQUARE BRACKET
0x005c: 0x00e0, # REVERSE SOLIDUS
0x005d: 0x00bb, # RIGHT SQUARE BRACKET
0x005e: 0x00b0, # CIRCUMFLEX ACCENT
0x005f: 0x006d, # LOW LINE
0x0060: 0x0079, # GRAVE ACCENT
0x0061: 0x0081, # LATIN SMALL LETTER A
0x0062: 0x0082, # LATIN SMALL LETTER B
0x0063: 0x0083, # LATIN SMALL LETTER C
0x0064: 0x0084, # LATIN SMALL LETTER D
0x0065: 0x0085, # LATIN SMALL LETTER E
0x0066: 0x0086, # LATIN SMALL LETTER F
0x0067: 0x0087, # LATIN SMALL LETTER G
0x0068: 0x0088, # LATIN SMALL LETTER H
0x0069: 0x0089, # LATIN SMALL LETTER I
0x006a: 0x0091, # LATIN SMALL LETTER J
0x006b: 0x0092, # LATIN SMALL LETTER K
0x006c: 0x0093, # LATIN SMALL LETTER L
0x006d: 0x0094, # LATIN SMALL LETTER M
0x006e: 0x0095, # LATIN SMALL LETTER N
0x006f: 0x0096, # LATIN SMALL LETTER O
0x0070: 0x0097, # LATIN SMALL LETTER P
0x0071: 0x0098, # LATIN SMALL LETTER Q
0x0072: 0x0099, # LATIN SMALL LETTER R
0x0073: 0x00a2, # LATIN SMALL LETTER S
0x0074: 0x00a3, # LATIN SMALL LETTER T
0x0075: 0x00a4, # LATIN SMALL LETTER U
0x0076: 0x00a5, # LATIN SMALL LETTER V
0x0077: 0x00a6, # LATIN SMALL LETTER W
0x0078: 0x00a7, # LATIN SMALL LETTER X
0x0079: 0x00a8, # LATIN SMALL LETTER Y
0x007a: 0x00a9, # LATIN SMALL LETTER Z
0x007b: 0x00c0, # LEFT CURLY BRACKET
0x007c: 0x004f, # VERTICAL LINE
0x007d: 0x00d0, # RIGHT CURLY BRACKET
0x007e: 0x00a1, # TILDE
0x007f: 0x0007, # DELETE
0x0080: 0x0020, # CONTROL
0x0081: 0x0021, # CONTROL
0x0082: 0x0022, # CONTROL
0x0083: 0x0023, # CONTROL
0x0084: 0x0024, # CONTROL
0x0085: 0x0015, # CONTROL
0x0086: 0x0006, # CONTROL
0x0087: 0x0017, # CONTROL
0x0088: 0x0028, # CONTROL
0x0089: 0x0029, # CONTROL
0x008a: 0x002a, # CONTROL
0x008b: 0x002b, # CONTROL
0x008c: 0x002c, # CONTROL
0x008d: 0x0009, # CONTROL
0x008e: 0x000a, # CONTROL
0x008f: 0x001b, # CONTROL
0x0090: 0x0030, # CONTROL
0x0091: 0x0031, # CONTROL
0x0092: 0x001a, # CONTROL
0x0093: 0x0033, # CONTROL
0x0094: 0x0034, # CONTROL
0x0095: 0x0035, # CONTROL
0x0096: 0x0036, # CONTROL
0x0097: 0x0008, # CONTROL
0x0098: 0x0038, # CONTROL
0x0099: 0x0039, # CONTROL
0x009a: 0x003a, # CONTROL
0x009b: 0x003b, # CONTROL
0x009c: 0x0004, # CONTROL
0x009d: 0x0014, # CONTROL
0x009e: 0x003e, # CONTROL
0x009f: 0x00ff, # CONTROL
0x00a0: 0x0041, # NO-BREAK SPACE
0x00a1: 0x00aa, # INVERTED EXCLAMATION MARK
0x00a2: 0x004a, # CENT SIGN
0x00a3: 0x00b1, # POUND SIGN
0x00a4: 0x009f, # CURRENCY SIGN
0x00a5: 0x00b2, # YEN SIGN
0x00a6: 0x006a, # BROKEN BAR
0x00a7: 0x00b5, # SECTION SIGN
0x00a8: 0x00bd, # DIAERESIS
0x00a9: 0x00b4, # COPYRIGHT SIGN
0x00aa: 0x009a, # FEMININE ORDINAL INDICATOR
0x00ab: 0x008a, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00ac: 0x005f, # NOT SIGN
0x00ad: 0x00ca, # SOFT HYPHEN
0x00ae: 0x00af, # REGISTERED SIGN
0x00af: 0x00bc, # MACRON
0x00b0: 0x0090, # DEGREE SIGN
0x00b1: 0x008f, # PLUS-MINUS SIGN
0x00b2: 0x00ea, # SUPERSCRIPT TWO
0x00b3: 0x00fa, # SUPERSCRIPT THREE
0x00b4: 0x00be, # ACUTE ACCENT
0x00b5: 0x00a0, # MICRO SIGN
0x00b6: 0x00b6, # PILCROW SIGN
0x00b7: 0x00b3, # MIDDLE DOT
0x00b8: 0x009d, # CEDILLA
0x00b9: 0x00da, # SUPERSCRIPT ONE
0x00ba: 0x009b, # MASCULINE ORDINAL INDICATOR
0x00bb: 0x008b, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00bc: 0x00b7, # VULGAR FRACTION ONE QUARTER
0x00bd: 0x00b8, # VULGAR FRACTION ONE HALF
0x00be: 0x00b9, # VULGAR FRACTION THREE QUARTERS
0x00bf: 0x00ab, # INVERTED QUESTION MARK
0x00c0: 0x0064, # LATIN CAPITAL LETTER A WITH GRAVE
0x00c1: 0x0065, # LATIN CAPITAL LETTER A WITH ACUTE
0x00c2: 0x0062, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x00c3: 0x0066, # LATIN CAPITAL LETTER A WITH TILDE
0x00c4: 0x0063, # LATIN CAPITAL LETTER A WITH DIAERESIS
0x00c5: 0x0067, # LATIN CAPITAL LETTER A WITH RING ABOVE
0x00c6: 0x009e, # LATIN CAPITAL LIGATURE AE
0x00c7: 0x0068, # LATIN CAPITAL LETTER C WITH CEDILLA
0x00c8: 0x0074, # LATIN CAPITAL LETTER E WITH GRAVE
0x00c9: 0x0071, # LATIN CAPITAL LETTER E WITH ACUTE
0x00ca: 0x0072, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x00cb: 0x0073, # LATIN CAPITAL LETTER E WITH DIAERESIS
0x00cc: 0x0078, # LATIN CAPITAL LETTER I WITH GRAVE
0x00cd: 0x0075, # LATIN CAPITAL LETTER I WITH ACUTE
0x00ce: 0x0076, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0x00cf: 0x0077, # LATIN CAPITAL LETTER I WITH DIAERESIS
0x00d0: 0x00ac, # LATIN CAPITAL LETTER ETH (ICELANDIC)
0x00d1: 0x0069, # LATIN CAPITAL LETTER N WITH TILDE
0x00d2: 0x00ed, # LATIN CAPITAL LETTER O WITH GRAVE
0x00d3: 0x00ee, # LATIN CAPITAL LETTER O WITH ACUTE
0x00d4: 0x00eb, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0x00d5: 0x00ef, # LATIN CAPITAL LETTER O WITH TILDE
0x00d6: 0x00ec, # LATIN CAPITAL LETTER O WITH DIAERESIS
0x00d7: 0x00bf, # MULTIPLICATION SIGN
0x00d8: 0x0080, # LATIN CAPITAL LETTER O WITH STROKE
0x00d9: 0x00fd, # LATIN CAPITAL LETTER U WITH GRAVE
0x00da: 0x00fe, # LATIN CAPITAL LETTER U WITH ACUTE
0x00db: 0x00fb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0x00dc: 0x00fc, # LATIN CAPITAL LETTER U WITH DIAERESIS
0x00dd: 0x00ad, # LATIN CAPITAL LETTER Y WITH ACUTE
0x00de: 0x00ae, # LATIN CAPITAL LETTER THORN (ICELANDIC)
0x00df: 0x0059, # LATIN SMALL LETTER SHARP S (GERMAN)
0x00e0: 0x0044, # LATIN SMALL LETTER A WITH GRAVE
0x00e1: 0x0045, # LATIN SMALL LETTER A WITH ACUTE
0x00e2: 0x0042, # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x00e3: 0x0046, # LATIN SMALL LETTER A WITH TILDE
0x00e4: 0x0043, # LATIN SMALL LETTER A WITH DIAERESIS
0x00e5: 0x0047, # LATIN SMALL LETTER A WITH RING ABOVE
0x00e6: 0x009c, # LATIN SMALL LIGATURE AE
0x00e7: 0x0048, # LATIN SMALL LETTER C WITH CEDILLA
0x00e8: 0x0054, # LATIN SMALL LETTER E WITH GRAVE
0x00e9: 0x0051, # LATIN SMALL LETTER E WITH ACUTE
0x00ea: 0x0052, # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x00eb: 0x0053, # LATIN SMALL LETTER E WITH DIAERESIS
0x00ec: 0x0058, # LATIN SMALL LETTER I WITH GRAVE
0x00ed: 0x0055, # LATIN SMALL LETTER I WITH ACUTE
0x00ee: 0x0056, # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x00ef: 0x0057, # LATIN SMALL LETTER I WITH DIAERESIS
0x00f0: 0x008c, # LATIN SMALL LETTER ETH (ICELANDIC)
0x00f1: 0x0049, # LATIN SMALL LETTER N WITH TILDE
0x00f2: 0x00cd, # LATIN SMALL LETTER O WITH GRAVE
0x00f3: 0x00ce, # LATIN SMALL LETTER O WITH ACUTE
0x00f4: 0x00cb, # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x00f5: 0x00cf, # LATIN SMALL LETTER O WITH TILDE
0x00f6: 0x00cc, # LATIN SMALL LETTER O WITH DIAERESIS
0x00f7: 0x00e1, # DIVISION SIGN
0x00f8: 0x0070, # LATIN SMALL LETTER O WITH STROKE
0x00f9: 0x00dd, # LATIN SMALL LETTER U WITH GRAVE
0x00fa: 0x00de, # LATIN SMALL LETTER U WITH ACUTE
0x00fb: 0x00db, # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x00fc: 0x00dc, # LATIN SMALL LETTER U WITH DIAERESIS
0x00fd: 0x008d, # LATIN SMALL LETTER Y WITH ACUTE
0x00fe: 0x008e, # LATIN SMALL LETTER THORN (ICELANDIC)
0x00ff: 0x00df, # LATIN SMALL LETTER Y WITH DIAERESIS
}
\ No newline at end of file
""" Python Character Mapping Codec generated from 'CP1026.TXT' with gencodec.py. """ Python Character Mapping Codec generated from 'VENDORS/MICSFT/EBCDIC/CP1026.TXT' with gencodec.py.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
(c) Copyright 2000 Guido van Rossum.
"""#" """#"
...@@ -19,7 +14,7 @@ class Codec(codecs.Codec): ...@@ -19,7 +14,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'): def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_map) return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter): class StreamWriter(Codec,codecs.StreamWriter):
pass pass
...@@ -275,6 +270,524 @@ decoding_map.update({ ...@@ -275,6 +270,524 @@ decoding_map.update({
0x00ff: 0x009f, # CONTROL 0x00ff: 0x009f, # CONTROL
}) })
### Decoding Table
decoding_table = (
u'\x00' # 0x0000 -> NULL
u'\x01' # 0x0001 -> START OF HEADING
u'\x02' # 0x0002 -> START OF TEXT
u'\x03' # 0x0003 -> END OF TEXT
u'\x9c' # 0x0004 -> CONTROL
u'\t' # 0x0005 -> HORIZONTAL TABULATION
u'\x86' # 0x0006 -> CONTROL
u'\x7f' # 0x0007 -> DELETE
u'\x97' # 0x0008 -> CONTROL
u'\x8d' # 0x0009 -> CONTROL
u'\x8e' # 0x000a -> CONTROL
u'\x0b' # 0x000b -> VERTICAL TABULATION
u'\x0c' # 0x000c -> FORM FEED
u'\r' # 0x000d -> CARRIAGE RETURN
u'\x0e' # 0x000e -> SHIFT OUT
u'\x0f' # 0x000f -> SHIFT IN
u'\x10' # 0x0010 -> DATA LINK ESCAPE
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
u'\x9d' # 0x0014 -> CONTROL
u'\x85' # 0x0015 -> CONTROL
u'\x08' # 0x0016 -> BACKSPACE
u'\x87' # 0x0017 -> CONTROL
u'\x18' # 0x0018 -> CANCEL
u'\x19' # 0x0019 -> END OF MEDIUM
u'\x92' # 0x001a -> CONTROL
u'\x8f' # 0x001b -> CONTROL
u'\x1c' # 0x001c -> FILE SEPARATOR
u'\x1d' # 0x001d -> GROUP SEPARATOR
u'\x1e' # 0x001e -> RECORD SEPARATOR
u'\x1f' # 0x001f -> UNIT SEPARATOR
u'\x80' # 0x0020 -> CONTROL
u'\x81' # 0x0021 -> CONTROL
u'\x82' # 0x0022 -> CONTROL
u'\x83' # 0x0023 -> CONTROL
u'\x84' # 0x0024 -> CONTROL
u'\n' # 0x0025 -> LINE FEED
u'\x17' # 0x0026 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x0027 -> ESCAPE
u'\x88' # 0x0028 -> CONTROL
u'\x89' # 0x0029 -> CONTROL
u'\x8a' # 0x002a -> CONTROL
u'\x8b' # 0x002b -> CONTROL
u'\x8c' # 0x002c -> CONTROL
u'\x05' # 0x002d -> ENQUIRY
u'\x06' # 0x002e -> ACKNOWLEDGE
u'\x07' # 0x002f -> BELL
u'\x90' # 0x0030 -> CONTROL
u'\x91' # 0x0031 -> CONTROL
u'\x16' # 0x0032 -> SYNCHRONOUS IDLE
u'\x93' # 0x0033 -> CONTROL
u'\x94' # 0x0034 -> CONTROL
u'\x95' # 0x0035 -> CONTROL
u'\x96' # 0x0036 -> CONTROL
u'\x04' # 0x0037 -> END OF TRANSMISSION
u'\x98' # 0x0038 -> CONTROL
u'\x99' # 0x0039 -> CONTROL
u'\x9a' # 0x003a -> CONTROL
u'\x9b' # 0x003b -> CONTROL
u'\x14' # 0x003c -> DEVICE CONTROL FOUR
u'\x15' # 0x003d -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x003e -> CONTROL
u'\x1a' # 0x003f -> SUBSTITUTE
u' ' # 0x0040 -> SPACE
u'\xa0' # 0x0041 -> NO-BREAK SPACE
u'\xe2' # 0x0042 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\xe4' # 0x0043 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe0' # 0x0044 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0x0045 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe3' # 0x0046 -> LATIN SMALL LETTER A WITH TILDE
u'\xe5' # 0x0047 -> LATIN SMALL LETTER A WITH RING ABOVE
u'{' # 0x0048 -> LEFT CURLY BRACKET
u'\xf1' # 0x0049 -> LATIN SMALL LETTER N WITH TILDE
u'\xc7' # 0x004a -> LATIN CAPITAL LETTER C WITH CEDILLA
u'.' # 0x004b -> FULL STOP
u'<' # 0x004c -> LESS-THAN SIGN
u'(' # 0x004d -> LEFT PARENTHESIS
u'+' # 0x004e -> PLUS SIGN
u'!' # 0x004f -> EXCLAMATION MARK
u'&' # 0x0050 -> AMPERSAND
u'\xe9' # 0x0051 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0x0052 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0x0053 -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xe8' # 0x0054 -> LATIN SMALL LETTER E WITH GRAVE
u'\xed' # 0x0055 -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0x0056 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0x0057 -> LATIN SMALL LETTER I WITH DIAERESIS
u'\xec' # 0x0058 -> LATIN SMALL LETTER I WITH GRAVE
u'\xdf' # 0x0059 -> LATIN SMALL LETTER SHARP S (GERMAN)
u'\u011e' # 0x005a -> LATIN CAPITAL LETTER G WITH BREVE
u'\u0130' # 0x005b -> LATIN CAPITAL LETTER I WITH DOT ABOVE
u'*' # 0x005c -> ASTERISK
u')' # 0x005d -> RIGHT PARENTHESIS
u';' # 0x005e -> SEMICOLON
u'^' # 0x005f -> CIRCUMFLEX ACCENT
u'-' # 0x0060 -> HYPHEN-MINUS
u'/' # 0x0061 -> SOLIDUS
u'\xc2' # 0x0062 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\xc4' # 0x0063 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc0' # 0x0064 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0x0065 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc3' # 0x0066 -> LATIN CAPITAL LETTER A WITH TILDE
u'\xc5' # 0x0067 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'[' # 0x0068 -> LEFT SQUARE BRACKET
u'\xd1' # 0x0069 -> LATIN CAPITAL LETTER N WITH TILDE
u'\u015f' # 0x006a -> LATIN SMALL LETTER S WITH CEDILLA
u',' # 0x006b -> COMMA
u'%' # 0x006c -> PERCENT SIGN
u'_' # 0x006d -> LOW LINE
u'>' # 0x006e -> GREATER-THAN SIGN
u'?' # 0x006f -> QUESTION MARK
u'\xf8' # 0x0070 -> LATIN SMALL LETTER O WITH STROKE
u'\xc9' # 0x0071 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0x0072 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0x0073 -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\xc8' # 0x0074 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xcd' # 0x0075 -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0x0076 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0x0077 -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\xcc' # 0x0078 -> LATIN CAPITAL LETTER I WITH GRAVE
u'\u0131' # 0x0079 -> LATIN SMALL LETTER DOTLESS I
u':' # 0x007a -> COLON
u'\xd6' # 0x007b -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\u015e' # 0x007c -> LATIN CAPITAL LETTER S WITH CEDILLA
u"'" # 0x007d -> APOSTROPHE
u'=' # 0x007e -> EQUALS SIGN
u'\xdc' # 0x007f -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\xd8' # 0x0080 -> LATIN CAPITAL LETTER O WITH STROKE
u'a' # 0x0081 -> LATIN SMALL LETTER A
u'b' # 0x0082 -> LATIN SMALL LETTER B
u'c' # 0x0083 -> LATIN SMALL LETTER C
u'd' # 0x0084 -> LATIN SMALL LETTER D
u'e' # 0x0085 -> LATIN SMALL LETTER E
u'f' # 0x0086 -> LATIN SMALL LETTER F
u'g' # 0x0087 -> LATIN SMALL LETTER G
u'h' # 0x0088 -> LATIN SMALL LETTER H
u'i' # 0x0089 -> LATIN SMALL LETTER I
u'\xab' # 0x008a -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbb' # 0x008b -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'}' # 0x008c -> RIGHT CURLY BRACKET
u'`' # 0x008d -> GRAVE ACCENT
u'\xa6' # 0x008e -> BROKEN BAR
u'\xb1' # 0x008f -> PLUS-MINUS SIGN
u'\xb0' # 0x0090 -> DEGREE SIGN
u'j' # 0x0091 -> LATIN SMALL LETTER J
u'k' # 0x0092 -> LATIN SMALL LETTER K
u'l' # 0x0093 -> LATIN SMALL LETTER L
u'm' # 0x0094 -> LATIN SMALL LETTER M
u'n' # 0x0095 -> LATIN SMALL LETTER N
u'o' # 0x0096 -> LATIN SMALL LETTER O
u'p' # 0x0097 -> LATIN SMALL LETTER P
u'q' # 0x0098 -> LATIN SMALL LETTER Q
u'r' # 0x0099 -> LATIN SMALL LETTER R
u'\xaa' # 0x009a -> FEMININE ORDINAL INDICATOR
u'\xba' # 0x009b -> MASCULINE ORDINAL INDICATOR
u'\xe6' # 0x009c -> LATIN SMALL LIGATURE AE
u'\xb8' # 0x009d -> CEDILLA
u'\xc6' # 0x009e -> LATIN CAPITAL LIGATURE AE
u'\xa4' # 0x009f -> CURRENCY SIGN
u'\xb5' # 0x00a0 -> MICRO SIGN
u'\xf6' # 0x00a1 -> LATIN SMALL LETTER O WITH DIAERESIS
u's' # 0x00a2 -> LATIN SMALL LETTER S
u't' # 0x00a3 -> LATIN SMALL LETTER T
u'u' # 0x00a4 -> LATIN SMALL LETTER U
u'v' # 0x00a5 -> LATIN SMALL LETTER V
u'w' # 0x00a6 -> LATIN SMALL LETTER W
u'x' # 0x00a7 -> LATIN SMALL LETTER X
u'y' # 0x00a8 -> LATIN SMALL LETTER Y
u'z' # 0x00a9 -> LATIN SMALL LETTER Z
u'\xa1' # 0x00aa -> INVERTED EXCLAMATION MARK
u'\xbf' # 0x00ab -> INVERTED QUESTION MARK
u']' # 0x00ac -> RIGHT SQUARE BRACKET
u'$' # 0x00ad -> DOLLAR SIGN
u'@' # 0x00ae -> COMMERCIAL AT
u'\xae' # 0x00af -> REGISTERED SIGN
u'\xa2' # 0x00b0 -> CENT SIGN
u'\xa3' # 0x00b1 -> POUND SIGN
u'\xa5' # 0x00b2 -> YEN SIGN
u'\xb7' # 0x00b3 -> MIDDLE DOT
u'\xa9' # 0x00b4 -> COPYRIGHT SIGN
u'\xa7' # 0x00b5 -> SECTION SIGN
u'\xb6' # 0x00b6 -> PILCROW SIGN
u'\xbc' # 0x00b7 -> VULGAR FRACTION ONE QUARTER
u'\xbd' # 0x00b8 -> VULGAR FRACTION ONE HALF
u'\xbe' # 0x00b9 -> VULGAR FRACTION THREE QUARTERS
u'\xac' # 0x00ba -> NOT SIGN
u'|' # 0x00bb -> VERTICAL LINE
u'\xaf' # 0x00bc -> MACRON
u'\xa8' # 0x00bd -> DIAERESIS
u'\xb4' # 0x00be -> ACUTE ACCENT
u'\xd7' # 0x00bf -> MULTIPLICATION SIGN
u'\xe7' # 0x00c0 -> LATIN SMALL LETTER C WITH CEDILLA
u'A' # 0x00c1 -> LATIN CAPITAL LETTER A
u'B' # 0x00c2 -> LATIN CAPITAL LETTER B
u'C' # 0x00c3 -> LATIN CAPITAL LETTER C
u'D' # 0x00c4 -> LATIN CAPITAL LETTER D
u'E' # 0x00c5 -> LATIN CAPITAL LETTER E
u'F' # 0x00c6 -> LATIN CAPITAL LETTER F
u'G' # 0x00c7 -> LATIN CAPITAL LETTER G
u'H' # 0x00c8 -> LATIN CAPITAL LETTER H
u'I' # 0x00c9 -> LATIN CAPITAL LETTER I
u'\xad' # 0x00ca -> SOFT HYPHEN
u'\xf4' # 0x00cb -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'~' # 0x00cc -> TILDE
u'\xf2' # 0x00cd -> LATIN SMALL LETTER O WITH GRAVE
u'\xf3' # 0x00ce -> LATIN SMALL LETTER O WITH ACUTE
u'\xf5' # 0x00cf -> LATIN SMALL LETTER O WITH TILDE
u'\u011f' # 0x00d0 -> LATIN SMALL LETTER G WITH BREVE
u'J' # 0x00d1 -> LATIN CAPITAL LETTER J
u'K' # 0x00d2 -> LATIN CAPITAL LETTER K
u'L' # 0x00d3 -> LATIN CAPITAL LETTER L
u'M' # 0x00d4 -> LATIN CAPITAL LETTER M
u'N' # 0x00d5 -> LATIN CAPITAL LETTER N
u'O' # 0x00d6 -> LATIN CAPITAL LETTER O
u'P' # 0x00d7 -> LATIN CAPITAL LETTER P
u'Q' # 0x00d8 -> LATIN CAPITAL LETTER Q
u'R' # 0x00d9 -> LATIN CAPITAL LETTER R
u'\xb9' # 0x00da -> SUPERSCRIPT ONE
u'\xfb' # 0x00db -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\\' # 0x00dc -> REVERSE SOLIDUS
u'\xf9' # 0x00dd -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0x00de -> LATIN SMALL LETTER U WITH ACUTE
u'\xff' # 0x00df -> LATIN SMALL LETTER Y WITH DIAERESIS
u'\xfc' # 0x00e0 -> LATIN SMALL LETTER U WITH DIAERESIS
u'\xf7' # 0x00e1 -> DIVISION SIGN
u'S' # 0x00e2 -> LATIN CAPITAL LETTER S
u'T' # 0x00e3 -> LATIN CAPITAL LETTER T
u'U' # 0x00e4 -> LATIN CAPITAL LETTER U
u'V' # 0x00e5 -> LATIN CAPITAL LETTER V
u'W' # 0x00e6 -> LATIN CAPITAL LETTER W
u'X' # 0x00e7 -> LATIN CAPITAL LETTER X
u'Y' # 0x00e8 -> LATIN CAPITAL LETTER Y
u'Z' # 0x00e9 -> LATIN CAPITAL LETTER Z
u'\xb2' # 0x00ea -> SUPERSCRIPT TWO
u'\xd4' # 0x00eb -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'#' # 0x00ec -> NUMBER SIGN
u'\xd2' # 0x00ed -> LATIN CAPITAL LETTER O WITH GRAVE
u'\xd3' # 0x00ee -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd5' # 0x00ef -> LATIN CAPITAL LETTER O WITH TILDE
u'0' # 0x00f0 -> DIGIT ZERO
u'1' # 0x00f1 -> DIGIT ONE
u'2' # 0x00f2 -> DIGIT TWO
u'3' # 0x00f3 -> DIGIT THREE
u'4' # 0x00f4 -> DIGIT FOUR
u'5' # 0x00f5 -> DIGIT FIVE
u'6' # 0x00f6 -> DIGIT SIX
u'7' # 0x00f7 -> DIGIT SEVEN
u'8' # 0x00f8 -> DIGIT EIGHT
u'9' # 0x00f9 -> DIGIT NINE
u'\xb3' # 0x00fa -> SUPERSCRIPT THREE
u'\xdb' # 0x00fb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'"' # 0x00fc -> QUOTATION MARK
u'\xd9' # 0x00fd -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0x00fe -> LATIN CAPITAL LETTER U WITH ACUTE
u'\x9f' # 0x00ff -> CONTROL
)
### Encoding Map ### Encoding Map
encoding_map = codecs.make_encoding_map(decoding_map) encoding_map = {
0x0000: 0x0000, # NULL
0x0001: 0x0001, # START OF HEADING
0x0002: 0x0002, # START OF TEXT
0x0003: 0x0003, # END OF TEXT
0x0004: 0x0037, # END OF TRANSMISSION
0x0005: 0x002d, # ENQUIRY
0x0006: 0x002e, # ACKNOWLEDGE
0x0007: 0x002f, # BELL
0x0008: 0x0016, # BACKSPACE
0x0009: 0x0005, # HORIZONTAL TABULATION
0x000a: 0x0025, # LINE FEED
0x000b: 0x000b, # VERTICAL TABULATION
0x000c: 0x000c, # FORM FEED
0x000d: 0x000d, # CARRIAGE RETURN
0x000e: 0x000e, # SHIFT OUT
0x000f: 0x000f, # SHIFT IN
0x0010: 0x0010, # DATA LINK ESCAPE
0x0011: 0x0011, # DEVICE CONTROL ONE
0x0012: 0x0012, # DEVICE CONTROL TWO
0x0013: 0x0013, # DEVICE CONTROL THREE
0x0014: 0x003c, # DEVICE CONTROL FOUR
0x0015: 0x003d, # NEGATIVE ACKNOWLEDGE
0x0016: 0x0032, # SYNCHRONOUS IDLE
0x0017: 0x0026, # END OF TRANSMISSION BLOCK
0x0018: 0x0018, # CANCEL
0x0019: 0x0019, # END OF MEDIUM
0x001a: 0x003f, # SUBSTITUTE
0x001b: 0x0027, # ESCAPE
0x001c: 0x001c, # FILE SEPARATOR
0x001d: 0x001d, # GROUP SEPARATOR
0x001e: 0x001e, # RECORD SEPARATOR
0x001f: 0x001f, # UNIT SEPARATOR
0x0020: 0x0040, # SPACE
0x0021: 0x004f, # EXCLAMATION MARK
0x0022: 0x00fc, # QUOTATION MARK
0x0023: 0x00ec, # NUMBER SIGN
0x0024: 0x00ad, # DOLLAR SIGN
0x0025: 0x006c, # PERCENT SIGN
0x0026: 0x0050, # AMPERSAND
0x0027: 0x007d, # APOSTROPHE
0x0028: 0x004d, # LEFT PARENTHESIS
0x0029: 0x005d, # RIGHT PARENTHESIS
0x002a: 0x005c, # ASTERISK
0x002b: 0x004e, # PLUS SIGN
0x002c: 0x006b, # COMMA
0x002d: 0x0060, # HYPHEN-MINUS
0x002e: 0x004b, # FULL STOP
0x002f: 0x0061, # SOLIDUS
0x0030: 0x00f0, # DIGIT ZERO
0x0031: 0x00f1, # DIGIT ONE
0x0032: 0x00f2, # DIGIT TWO
0x0033: 0x00f3, # DIGIT THREE
0x0034: 0x00f4, # DIGIT FOUR
0x0035: 0x00f5, # DIGIT FIVE
0x0036: 0x00f6, # DIGIT SIX
0x0037: 0x00f7, # DIGIT SEVEN
0x0038: 0x00f8, # DIGIT EIGHT
0x0039: 0x00f9, # DIGIT NINE
0x003a: 0x007a, # COLON
0x003b: 0x005e, # SEMICOLON
0x003c: 0x004c, # LESS-THAN SIGN
0x003d: 0x007e, # EQUALS SIGN
0x003e: 0x006e, # GREATER-THAN SIGN
0x003f: 0x006f, # QUESTION MARK
0x0040: 0x00ae, # COMMERCIAL AT
0x0041: 0x00c1, # LATIN CAPITAL LETTER A
0x0042: 0x00c2, # LATIN CAPITAL LETTER B
0x0043: 0x00c3, # LATIN CAPITAL LETTER C
0x0044: 0x00c4, # LATIN CAPITAL LETTER D
0x0045: 0x00c5, # LATIN CAPITAL LETTER E
0x0046: 0x00c6, # LATIN CAPITAL LETTER F
0x0047: 0x00c7, # LATIN CAPITAL LETTER G
0x0048: 0x00c8, # LATIN CAPITAL LETTER H
0x0049: 0x00c9, # LATIN CAPITAL LETTER I
0x004a: 0x00d1, # LATIN CAPITAL LETTER J
0x004b: 0x00d2, # LATIN CAPITAL LETTER K
0x004c: 0x00d3, # LATIN CAPITAL LETTER L
0x004d: 0x00d4, # LATIN CAPITAL LETTER M
0x004e: 0x00d5, # LATIN CAPITAL LETTER N
0x004f: 0x00d6, # LATIN CAPITAL LETTER O
0x0050: 0x00d7, # LATIN CAPITAL LETTER P
0x0051: 0x00d8, # LATIN CAPITAL LETTER Q
0x0052: 0x00d9, # LATIN CAPITAL LETTER R
0x0053: 0x00e2, # LATIN CAPITAL LETTER S
0x0054: 0x00e3, # LATIN CAPITAL LETTER T
0x0055: 0x00e4, # LATIN CAPITAL LETTER U
0x0056: 0x00e5, # LATIN CAPITAL LETTER V
0x0057: 0x00e6, # LATIN CAPITAL LETTER W
0x0058: 0x00e7, # LATIN CAPITAL LETTER X
0x0059: 0x00e8, # LATIN CAPITAL LETTER Y
0x005a: 0x00e9, # LATIN CAPITAL LETTER Z
0x005b: 0x0068, # LEFT SQUARE BRACKET
0x005c: 0x00dc, # REVERSE SOLIDUS
0x005d: 0x00ac, # RIGHT SQUARE BRACKET
0x005e: 0x005f, # CIRCUMFLEX ACCENT
0x005f: 0x006d, # LOW LINE
0x0060: 0x008d, # GRAVE ACCENT
0x0061: 0x0081, # LATIN SMALL LETTER A
0x0062: 0x0082, # LATIN SMALL LETTER B
0x0063: 0x0083, # LATIN SMALL LETTER C
0x0064: 0x0084, # LATIN SMALL LETTER D
0x0065: 0x0085, # LATIN SMALL LETTER E
0x0066: 0x0086, # LATIN SMALL LETTER F
0x0067: 0x0087, # LATIN SMALL LETTER G
0x0068: 0x0088, # LATIN SMALL LETTER H
0x0069: 0x0089, # LATIN SMALL LETTER I
0x006a: 0x0091, # LATIN SMALL LETTER J
0x006b: 0x0092, # LATIN SMALL LETTER K
0x006c: 0x0093, # LATIN SMALL LETTER L
0x006d: 0x0094, # LATIN SMALL LETTER M
0x006e: 0x0095, # LATIN SMALL LETTER N
0x006f: 0x0096, # LATIN SMALL LETTER O
0x0070: 0x0097, # LATIN SMALL LETTER P
0x0071: 0x0098, # LATIN SMALL LETTER Q
0x0072: 0x0099, # LATIN SMALL LETTER R
0x0073: 0x00a2, # LATIN SMALL LETTER S
0x0074: 0x00a3, # LATIN SMALL LETTER T
0x0075: 0x00a4, # LATIN SMALL LETTER U
0x0076: 0x00a5, # LATIN SMALL LETTER V
0x0077: 0x00a6, # LATIN SMALL LETTER W
0x0078: 0x00a7, # LATIN SMALL LETTER X
0x0079: 0x00a8, # LATIN SMALL LETTER Y
0x007a: 0x00a9, # LATIN SMALL LETTER Z
0x007b: 0x0048, # LEFT CURLY BRACKET
0x007c: 0x00bb, # VERTICAL LINE
0x007d: 0x008c, # RIGHT CURLY BRACKET
0x007e: 0x00cc, # TILDE
0x007f: 0x0007, # DELETE
0x0080: 0x0020, # CONTROL
0x0081: 0x0021, # CONTROL
0x0082: 0x0022, # CONTROL
0x0083: 0x0023, # CONTROL
0x0084: 0x0024, # CONTROL
0x0085: 0x0015, # CONTROL
0x0086: 0x0006, # CONTROL
0x0087: 0x0017, # CONTROL
0x0088: 0x0028, # CONTROL
0x0089: 0x0029, # CONTROL
0x008a: 0x002a, # CONTROL
0x008b: 0x002b, # CONTROL
0x008c: 0x002c, # CONTROL
0x008d: 0x0009, # CONTROL
0x008e: 0x000a, # CONTROL
0x008f: 0x001b, # CONTROL
0x0090: 0x0030, # CONTROL
0x0091: 0x0031, # CONTROL
0x0092: 0x001a, # CONTROL
0x0093: 0x0033, # CONTROL
0x0094: 0x0034, # CONTROL
0x0095: 0x0035, # CONTROL
0x0096: 0x0036, # CONTROL
0x0097: 0x0008, # CONTROL
0x0098: 0x0038, # CONTROL
0x0099: 0x0039, # CONTROL
0x009a: 0x003a, # CONTROL
0x009b: 0x003b, # CONTROL
0x009c: 0x0004, # CONTROL
0x009d: 0x0014, # CONTROL
0x009e: 0x003e, # CONTROL
0x009f: 0x00ff, # CONTROL
0x00a0: 0x0041, # NO-BREAK SPACE
0x00a1: 0x00aa, # INVERTED EXCLAMATION MARK
0x00a2: 0x00b0, # CENT SIGN
0x00a3: 0x00b1, # POUND SIGN
0x00a4: 0x009f, # CURRENCY SIGN
0x00a5: 0x00b2, # YEN SIGN
0x00a6: 0x008e, # BROKEN BAR
0x00a7: 0x00b5, # SECTION SIGN
0x00a8: 0x00bd, # DIAERESIS
0x00a9: 0x00b4, # COPYRIGHT SIGN
0x00aa: 0x009a, # FEMININE ORDINAL INDICATOR
0x00ab: 0x008a, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00ac: 0x00ba, # NOT SIGN
0x00ad: 0x00ca, # SOFT HYPHEN
0x00ae: 0x00af, # REGISTERED SIGN
0x00af: 0x00bc, # MACRON
0x00b0: 0x0090, # DEGREE SIGN
0x00b1: 0x008f, # PLUS-MINUS SIGN
0x00b2: 0x00ea, # SUPERSCRIPT TWO
0x00b3: 0x00fa, # SUPERSCRIPT THREE
0x00b4: 0x00be, # ACUTE ACCENT
0x00b5: 0x00a0, # MICRO SIGN
0x00b6: 0x00b6, # PILCROW SIGN
0x00b7: 0x00b3, # MIDDLE DOT
0x00b8: 0x009d, # CEDILLA
0x00b9: 0x00da, # SUPERSCRIPT ONE
0x00ba: 0x009b, # MASCULINE ORDINAL INDICATOR
0x00bb: 0x008b, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00bc: 0x00b7, # VULGAR FRACTION ONE QUARTER
0x00bd: 0x00b8, # VULGAR FRACTION ONE HALF
0x00be: 0x00b9, # VULGAR FRACTION THREE QUARTERS
0x00bf: 0x00ab, # INVERTED QUESTION MARK
0x00c0: 0x0064, # LATIN CAPITAL LETTER A WITH GRAVE
0x00c1: 0x0065, # LATIN CAPITAL LETTER A WITH ACUTE
0x00c2: 0x0062, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x00c3: 0x0066, # LATIN CAPITAL LETTER A WITH TILDE
0x00c4: 0x0063, # LATIN CAPITAL LETTER A WITH DIAERESIS
0x00c5: 0x0067, # LATIN CAPITAL LETTER A WITH RING ABOVE
0x00c6: 0x009e, # LATIN CAPITAL LIGATURE AE
0x00c7: 0x004a, # LATIN CAPITAL LETTER C WITH CEDILLA
0x00c8: 0x0074, # LATIN CAPITAL LETTER E WITH GRAVE
0x00c9: 0x0071, # LATIN CAPITAL LETTER E WITH ACUTE
0x00ca: 0x0072, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x00cb: 0x0073, # LATIN CAPITAL LETTER E WITH DIAERESIS
0x00cc: 0x0078, # LATIN CAPITAL LETTER I WITH GRAVE
0x00cd: 0x0075, # LATIN CAPITAL LETTER I WITH ACUTE
0x00ce: 0x0076, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0x00cf: 0x0077, # LATIN CAPITAL LETTER I WITH DIAERESIS
0x00d1: 0x0069, # LATIN CAPITAL LETTER N WITH TILDE
0x00d2: 0x00ed, # LATIN CAPITAL LETTER O WITH GRAVE
0x00d3: 0x00ee, # LATIN CAPITAL LETTER O WITH ACUTE
0x00d4: 0x00eb, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0x00d5: 0x00ef, # LATIN CAPITAL LETTER O WITH TILDE
0x00d6: 0x007b, # LATIN CAPITAL LETTER O WITH DIAERESIS
0x00d7: 0x00bf, # MULTIPLICATION SIGN
0x00d8: 0x0080, # LATIN CAPITAL LETTER O WITH STROKE
0x00d9: 0x00fd, # LATIN CAPITAL LETTER U WITH GRAVE
0x00da: 0x00fe, # LATIN CAPITAL LETTER U WITH ACUTE
0x00db: 0x00fb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0x00dc: 0x007f, # LATIN CAPITAL LETTER U WITH DIAERESIS
0x00df: 0x0059, # LATIN SMALL LETTER SHARP S (GERMAN)
0x00e0: 0x0044, # LATIN SMALL LETTER A WITH GRAVE
0x00e1: 0x0045, # LATIN SMALL LETTER A WITH ACUTE
0x00e2: 0x0042, # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x00e3: 0x0046, # LATIN SMALL LETTER A WITH TILDE
0x00e4: 0x0043, # LATIN SMALL LETTER A WITH DIAERESIS
0x00e5: 0x0047, # LATIN SMALL LETTER A WITH RING ABOVE
0x00e6: 0x009c, # LATIN SMALL LIGATURE AE
0x00e7: 0x00c0, # LATIN SMALL LETTER C WITH CEDILLA
0x00e8: 0x0054, # LATIN SMALL LETTER E WITH GRAVE
0x00e9: 0x0051, # LATIN SMALL LETTER E WITH ACUTE
0x00ea: 0x0052, # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x00eb: 0x0053, # LATIN SMALL LETTER E WITH DIAERESIS
0x00ec: 0x0058, # LATIN SMALL LETTER I WITH GRAVE
0x00ed: 0x0055, # LATIN SMALL LETTER I WITH ACUTE
0x00ee: 0x0056, # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x00ef: 0x0057, # LATIN SMALL LETTER I WITH DIAERESIS
0x00f1: 0x0049, # LATIN SMALL LETTER N WITH TILDE
0x00f2: 0x00cd, # LATIN SMALL LETTER O WITH GRAVE
0x00f3: 0x00ce, # LATIN SMALL LETTER O WITH ACUTE
0x00f4: 0x00cb, # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x00f5: 0x00cf, # LATIN SMALL LETTER O WITH TILDE
0x00f6: 0x00a1, # LATIN SMALL LETTER O WITH DIAERESIS
0x00f7: 0x00e1, # DIVISION SIGN
0x00f8: 0x0070, # LATIN SMALL LETTER O WITH STROKE
0x00f9: 0x00dd, # LATIN SMALL LETTER U WITH GRAVE
0x00fa: 0x00de, # LATIN SMALL LETTER U WITH ACUTE
0x00fb: 0x00db, # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x00fc: 0x00e0, # LATIN SMALL LETTER U WITH DIAERESIS
0x00ff: 0x00df, # LATIN SMALL LETTER Y WITH DIAERESIS
0x011e: 0x005a, # LATIN CAPITAL LETTER G WITH BREVE
0x011f: 0x00d0, # LATIN SMALL LETTER G WITH BREVE
0x0130: 0x005b, # LATIN CAPITAL LETTER I WITH DOT ABOVE
0x0131: 0x0079, # LATIN SMALL LETTER DOTLESS I
0x015e: 0x007c, # LATIN CAPITAL LETTER S WITH CEDILLA
0x015f: 0x006a, # LATIN SMALL LETTER S WITH CEDILLA
}
\ No newline at end of file
""" Python Character Mapping Codec generated from 'CP500.TXT' with gencodec.py. """ Python Character Mapping Codec generated from 'VENDORS/MICSFT/EBCDIC/CP500.TXT' with gencodec.py.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
(c) Copyright 2000 Guido van Rossum.
"""#" """#"
...@@ -19,7 +14,7 @@ class Codec(codecs.Codec): ...@@ -19,7 +14,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'): def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_map) return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter): class StreamWriter(Codec,codecs.StreamWriter):
pass pass
...@@ -275,6 +270,524 @@ decoding_map.update({ ...@@ -275,6 +270,524 @@ decoding_map.update({
0x00ff: 0x009f, # CONTROL 0x00ff: 0x009f, # CONTROL
}) })
### Decoding Table
decoding_table = (
u'\x00' # 0x0000 -> NULL
u'\x01' # 0x0001 -> START OF HEADING
u'\x02' # 0x0002 -> START OF TEXT
u'\x03' # 0x0003 -> END OF TEXT
u'\x9c' # 0x0004 -> CONTROL
u'\t' # 0x0005 -> HORIZONTAL TABULATION
u'\x86' # 0x0006 -> CONTROL
u'\x7f' # 0x0007 -> DELETE
u'\x97' # 0x0008 -> CONTROL
u'\x8d' # 0x0009 -> CONTROL
u'\x8e' # 0x000a -> CONTROL
u'\x0b' # 0x000b -> VERTICAL TABULATION
u'\x0c' # 0x000c -> FORM FEED
u'\r' # 0x000d -> CARRIAGE RETURN
u'\x0e' # 0x000e -> SHIFT OUT
u'\x0f' # 0x000f -> SHIFT IN
u'\x10' # 0x0010 -> DATA LINK ESCAPE
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
u'\x9d' # 0x0014 -> CONTROL
u'\x85' # 0x0015 -> CONTROL
u'\x08' # 0x0016 -> BACKSPACE
u'\x87' # 0x0017 -> CONTROL
u'\x18' # 0x0018 -> CANCEL
u'\x19' # 0x0019 -> END OF MEDIUM
u'\x92' # 0x001a -> CONTROL
u'\x8f' # 0x001b -> CONTROL
u'\x1c' # 0x001c -> FILE SEPARATOR
u'\x1d' # 0x001d -> GROUP SEPARATOR
u'\x1e' # 0x001e -> RECORD SEPARATOR
u'\x1f' # 0x001f -> UNIT SEPARATOR
u'\x80' # 0x0020 -> CONTROL
u'\x81' # 0x0021 -> CONTROL
u'\x82' # 0x0022 -> CONTROL
u'\x83' # 0x0023 -> CONTROL
u'\x84' # 0x0024 -> CONTROL
u'\n' # 0x0025 -> LINE FEED
u'\x17' # 0x0026 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x0027 -> ESCAPE
u'\x88' # 0x0028 -> CONTROL
u'\x89' # 0x0029 -> CONTROL
u'\x8a' # 0x002a -> CONTROL
u'\x8b' # 0x002b -> CONTROL
u'\x8c' # 0x002c -> CONTROL
u'\x05' # 0x002d -> ENQUIRY
u'\x06' # 0x002e -> ACKNOWLEDGE
u'\x07' # 0x002f -> BELL
u'\x90' # 0x0030 -> CONTROL
u'\x91' # 0x0031 -> CONTROL
u'\x16' # 0x0032 -> SYNCHRONOUS IDLE
u'\x93' # 0x0033 -> CONTROL
u'\x94' # 0x0034 -> CONTROL
u'\x95' # 0x0035 -> CONTROL
u'\x96' # 0x0036 -> CONTROL
u'\x04' # 0x0037 -> END OF TRANSMISSION
u'\x98' # 0x0038 -> CONTROL
u'\x99' # 0x0039 -> CONTROL
u'\x9a' # 0x003a -> CONTROL
u'\x9b' # 0x003b -> CONTROL
u'\x14' # 0x003c -> DEVICE CONTROL FOUR
u'\x15' # 0x003d -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x003e -> CONTROL
u'\x1a' # 0x003f -> SUBSTITUTE
u' ' # 0x0040 -> SPACE
u'\xa0' # 0x0041 -> NO-BREAK SPACE
u'\xe2' # 0x0042 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\xe4' # 0x0043 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe0' # 0x0044 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0x0045 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe3' # 0x0046 -> LATIN SMALL LETTER A WITH TILDE
u'\xe5' # 0x0047 -> LATIN SMALL LETTER A WITH RING ABOVE
u'\xe7' # 0x0048 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xf1' # 0x0049 -> LATIN SMALL LETTER N WITH TILDE
u'[' # 0x004a -> LEFT SQUARE BRACKET
u'.' # 0x004b -> FULL STOP
u'<' # 0x004c -> LESS-THAN SIGN
u'(' # 0x004d -> LEFT PARENTHESIS
u'+' # 0x004e -> PLUS SIGN
u'!' # 0x004f -> EXCLAMATION MARK
u'&' # 0x0050 -> AMPERSAND
u'\xe9' # 0x0051 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0x0052 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0x0053 -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xe8' # 0x0054 -> LATIN SMALL LETTER E WITH GRAVE
u'\xed' # 0x0055 -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0x0056 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0x0057 -> LATIN SMALL LETTER I WITH DIAERESIS
u'\xec' # 0x0058 -> LATIN SMALL LETTER I WITH GRAVE
u'\xdf' # 0x0059 -> LATIN SMALL LETTER SHARP S (GERMAN)
u']' # 0x005a -> RIGHT SQUARE BRACKET
u'$' # 0x005b -> DOLLAR SIGN
u'*' # 0x005c -> ASTERISK
u')' # 0x005d -> RIGHT PARENTHESIS
u';' # 0x005e -> SEMICOLON
u'^' # 0x005f -> CIRCUMFLEX ACCENT
u'-' # 0x0060 -> HYPHEN-MINUS
u'/' # 0x0061 -> SOLIDUS
u'\xc2' # 0x0062 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\xc4' # 0x0063 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc0' # 0x0064 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0x0065 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc3' # 0x0066 -> LATIN CAPITAL LETTER A WITH TILDE
u'\xc5' # 0x0067 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'\xc7' # 0x0068 -> LATIN CAPITAL LETTER C WITH CEDILLA
u'\xd1' # 0x0069 -> LATIN CAPITAL LETTER N WITH TILDE
u'\xa6' # 0x006a -> BROKEN BAR
u',' # 0x006b -> COMMA
u'%' # 0x006c -> PERCENT SIGN
u'_' # 0x006d -> LOW LINE
u'>' # 0x006e -> GREATER-THAN SIGN
u'?' # 0x006f -> QUESTION MARK
u'\xf8' # 0x0070 -> LATIN SMALL LETTER O WITH STROKE
u'\xc9' # 0x0071 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0x0072 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0x0073 -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\xc8' # 0x0074 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xcd' # 0x0075 -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0x0076 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0x0077 -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\xcc' # 0x0078 -> LATIN CAPITAL LETTER I WITH GRAVE
u'`' # 0x0079 -> GRAVE ACCENT
u':' # 0x007a -> COLON
u'#' # 0x007b -> NUMBER SIGN
u'@' # 0x007c -> COMMERCIAL AT
u"'" # 0x007d -> APOSTROPHE
u'=' # 0x007e -> EQUALS SIGN
u'"' # 0x007f -> QUOTATION MARK
u'\xd8' # 0x0080 -> LATIN CAPITAL LETTER O WITH STROKE
u'a' # 0x0081 -> LATIN SMALL LETTER A
u'b' # 0x0082 -> LATIN SMALL LETTER B
u'c' # 0x0083 -> LATIN SMALL LETTER C
u'd' # 0x0084 -> LATIN SMALL LETTER D
u'e' # 0x0085 -> LATIN SMALL LETTER E
u'f' # 0x0086 -> LATIN SMALL LETTER F
u'g' # 0x0087 -> LATIN SMALL LETTER G
u'h' # 0x0088 -> LATIN SMALL LETTER H
u'i' # 0x0089 -> LATIN SMALL LETTER I
u'\xab' # 0x008a -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbb' # 0x008b -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xf0' # 0x008c -> LATIN SMALL LETTER ETH (ICELANDIC)
u'\xfd' # 0x008d -> LATIN SMALL LETTER Y WITH ACUTE
u'\xfe' # 0x008e -> LATIN SMALL LETTER THORN (ICELANDIC)
u'\xb1' # 0x008f -> PLUS-MINUS SIGN
u'\xb0' # 0x0090 -> DEGREE SIGN
u'j' # 0x0091 -> LATIN SMALL LETTER J
u'k' # 0x0092 -> LATIN SMALL LETTER K
u'l' # 0x0093 -> LATIN SMALL LETTER L
u'm' # 0x0094 -> LATIN SMALL LETTER M
u'n' # 0x0095 -> LATIN SMALL LETTER N
u'o' # 0x0096 -> LATIN SMALL LETTER O
u'p' # 0x0097 -> LATIN SMALL LETTER P
u'q' # 0x0098 -> LATIN SMALL LETTER Q
u'r' # 0x0099 -> LATIN SMALL LETTER R
u'\xaa' # 0x009a -> FEMININE ORDINAL INDICATOR
u'\xba' # 0x009b -> MASCULINE ORDINAL INDICATOR
u'\xe6' # 0x009c -> LATIN SMALL LIGATURE AE
u'\xb8' # 0x009d -> CEDILLA
u'\xc6' # 0x009e -> LATIN CAPITAL LIGATURE AE
u'\xa4' # 0x009f -> CURRENCY SIGN
u'\xb5' # 0x00a0 -> MICRO SIGN
u'~' # 0x00a1 -> TILDE
u's' # 0x00a2 -> LATIN SMALL LETTER S
u't' # 0x00a3 -> LATIN SMALL LETTER T
u'u' # 0x00a4 -> LATIN SMALL LETTER U
u'v' # 0x00a5 -> LATIN SMALL LETTER V
u'w' # 0x00a6 -> LATIN SMALL LETTER W
u'x' # 0x00a7 -> LATIN SMALL LETTER X
u'y' # 0x00a8 -> LATIN SMALL LETTER Y
u'z' # 0x00a9 -> LATIN SMALL LETTER Z
u'\xa1' # 0x00aa -> INVERTED EXCLAMATION MARK
u'\xbf' # 0x00ab -> INVERTED QUESTION MARK
u'\xd0' # 0x00ac -> LATIN CAPITAL LETTER ETH (ICELANDIC)
u'\xdd' # 0x00ad -> LATIN CAPITAL LETTER Y WITH ACUTE
u'\xde' # 0x00ae -> LATIN CAPITAL LETTER THORN (ICELANDIC)
u'\xae' # 0x00af -> REGISTERED SIGN
u'\xa2' # 0x00b0 -> CENT SIGN
u'\xa3' # 0x00b1 -> POUND SIGN
u'\xa5' # 0x00b2 -> YEN SIGN
u'\xb7' # 0x00b3 -> MIDDLE DOT
u'\xa9' # 0x00b4 -> COPYRIGHT SIGN
u'\xa7' # 0x00b5 -> SECTION SIGN
u'\xb6' # 0x00b6 -> PILCROW SIGN
u'\xbc' # 0x00b7 -> VULGAR FRACTION ONE QUARTER
u'\xbd' # 0x00b8 -> VULGAR FRACTION ONE HALF
u'\xbe' # 0x00b9 -> VULGAR FRACTION THREE QUARTERS
u'\xac' # 0x00ba -> NOT SIGN
u'|' # 0x00bb -> VERTICAL LINE
u'\xaf' # 0x00bc -> MACRON
u'\xa8' # 0x00bd -> DIAERESIS
u'\xb4' # 0x00be -> ACUTE ACCENT
u'\xd7' # 0x00bf -> MULTIPLICATION SIGN
u'{' # 0x00c0 -> LEFT CURLY BRACKET
u'A' # 0x00c1 -> LATIN CAPITAL LETTER A
u'B' # 0x00c2 -> LATIN CAPITAL LETTER B
u'C' # 0x00c3 -> LATIN CAPITAL LETTER C
u'D' # 0x00c4 -> LATIN CAPITAL LETTER D
u'E' # 0x00c5 -> LATIN CAPITAL LETTER E
u'F' # 0x00c6 -> LATIN CAPITAL LETTER F
u'G' # 0x00c7 -> LATIN CAPITAL LETTER G
u'H' # 0x00c8 -> LATIN CAPITAL LETTER H
u'I' # 0x00c9 -> LATIN CAPITAL LETTER I
u'\xad' # 0x00ca -> SOFT HYPHEN
u'\xf4' # 0x00cb -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\xf6' # 0x00cc -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf2' # 0x00cd -> LATIN SMALL LETTER O WITH GRAVE
u'\xf3' # 0x00ce -> LATIN SMALL LETTER O WITH ACUTE
u'\xf5' # 0x00cf -> LATIN SMALL LETTER O WITH TILDE
u'}' # 0x00d0 -> RIGHT CURLY BRACKET
u'J' # 0x00d1 -> LATIN CAPITAL LETTER J
u'K' # 0x00d2 -> LATIN CAPITAL LETTER K
u'L' # 0x00d3 -> LATIN CAPITAL LETTER L
u'M' # 0x00d4 -> LATIN CAPITAL LETTER M
u'N' # 0x00d5 -> LATIN CAPITAL LETTER N
u'O' # 0x00d6 -> LATIN CAPITAL LETTER O
u'P' # 0x00d7 -> LATIN CAPITAL LETTER P
u'Q' # 0x00d8 -> LATIN CAPITAL LETTER Q
u'R' # 0x00d9 -> LATIN CAPITAL LETTER R
u'\xb9' # 0x00da -> SUPERSCRIPT ONE
u'\xfb' # 0x00db -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xfc' # 0x00dc -> LATIN SMALL LETTER U WITH DIAERESIS
u'\xf9' # 0x00dd -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0x00de -> LATIN SMALL LETTER U WITH ACUTE
u'\xff' # 0x00df -> LATIN SMALL LETTER Y WITH DIAERESIS
u'\\' # 0x00e0 -> REVERSE SOLIDUS
u'\xf7' # 0x00e1 -> DIVISION SIGN
u'S' # 0x00e2 -> LATIN CAPITAL LETTER S
u'T' # 0x00e3 -> LATIN CAPITAL LETTER T
u'U' # 0x00e4 -> LATIN CAPITAL LETTER U
u'V' # 0x00e5 -> LATIN CAPITAL LETTER V
u'W' # 0x00e6 -> LATIN CAPITAL LETTER W
u'X' # 0x00e7 -> LATIN CAPITAL LETTER X
u'Y' # 0x00e8 -> LATIN CAPITAL LETTER Y
u'Z' # 0x00e9 -> LATIN CAPITAL LETTER Z
u'\xb2' # 0x00ea -> SUPERSCRIPT TWO
u'\xd4' # 0x00eb -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'\xd6' # 0x00ec -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd2' # 0x00ed -> LATIN CAPITAL LETTER O WITH GRAVE
u'\xd3' # 0x00ee -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd5' # 0x00ef -> LATIN CAPITAL LETTER O WITH TILDE
u'0' # 0x00f0 -> DIGIT ZERO
u'1' # 0x00f1 -> DIGIT ONE
u'2' # 0x00f2 -> DIGIT TWO
u'3' # 0x00f3 -> DIGIT THREE
u'4' # 0x00f4 -> DIGIT FOUR
u'5' # 0x00f5 -> DIGIT FIVE
u'6' # 0x00f6 -> DIGIT SIX
u'7' # 0x00f7 -> DIGIT SEVEN
u'8' # 0x00f8 -> DIGIT EIGHT
u'9' # 0x00f9 -> DIGIT NINE
u'\xb3' # 0x00fa -> SUPERSCRIPT THREE
u'\xdb' # 0x00fb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'\xdc' # 0x00fc -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\xd9' # 0x00fd -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0x00fe -> LATIN CAPITAL LETTER U WITH ACUTE
u'\x9f' # 0x00ff -> CONTROL
)
### Encoding Map ### Encoding Map
encoding_map = codecs.make_encoding_map(decoding_map) encoding_map = {
0x0000: 0x0000, # NULL
0x0001: 0x0001, # START OF HEADING
0x0002: 0x0002, # START OF TEXT
0x0003: 0x0003, # END OF TEXT
0x0004: 0x0037, # END OF TRANSMISSION
0x0005: 0x002d, # ENQUIRY
0x0006: 0x002e, # ACKNOWLEDGE
0x0007: 0x002f, # BELL
0x0008: 0x0016, # BACKSPACE
0x0009: 0x0005, # HORIZONTAL TABULATION
0x000a: 0x0025, # LINE FEED
0x000b: 0x000b, # VERTICAL TABULATION
0x000c: 0x000c, # FORM FEED
0x000d: 0x000d, # CARRIAGE RETURN
0x000e: 0x000e, # SHIFT OUT
0x000f: 0x000f, # SHIFT IN
0x0010: 0x0010, # DATA LINK ESCAPE
0x0011: 0x0011, # DEVICE CONTROL ONE
0x0012: 0x0012, # DEVICE CONTROL TWO
0x0013: 0x0013, # DEVICE CONTROL THREE
0x0014: 0x003c, # DEVICE CONTROL FOUR
0x0015: 0x003d, # NEGATIVE ACKNOWLEDGE
0x0016: 0x0032, # SYNCHRONOUS IDLE
0x0017: 0x0026, # END OF TRANSMISSION BLOCK
0x0018: 0x0018, # CANCEL
0x0019: 0x0019, # END OF MEDIUM
0x001a: 0x003f, # SUBSTITUTE
0x001b: 0x0027, # ESCAPE
0x001c: 0x001c, # FILE SEPARATOR
0x001d: 0x001d, # GROUP SEPARATOR
0x001e: 0x001e, # RECORD SEPARATOR
0x001f: 0x001f, # UNIT SEPARATOR
0x0020: 0x0040, # SPACE
0x0021: 0x004f, # EXCLAMATION MARK
0x0022: 0x007f, # QUOTATION MARK
0x0023: 0x007b, # NUMBER SIGN
0x0024: 0x005b, # DOLLAR SIGN
0x0025: 0x006c, # PERCENT SIGN
0x0026: 0x0050, # AMPERSAND
0x0027: 0x007d, # APOSTROPHE
0x0028: 0x004d, # LEFT PARENTHESIS
0x0029: 0x005d, # RIGHT PARENTHESIS
0x002a: 0x005c, # ASTERISK
0x002b: 0x004e, # PLUS SIGN
0x002c: 0x006b, # COMMA
0x002d: 0x0060, # HYPHEN-MINUS
0x002e: 0x004b, # FULL STOP
0x002f: 0x0061, # SOLIDUS
0x0030: 0x00f0, # DIGIT ZERO
0x0031: 0x00f1, # DIGIT ONE
0x0032: 0x00f2, # DIGIT TWO
0x0033: 0x00f3, # DIGIT THREE
0x0034: 0x00f4, # DIGIT FOUR
0x0035: 0x00f5, # DIGIT FIVE
0x0036: 0x00f6, # DIGIT SIX
0x0037: 0x00f7, # DIGIT SEVEN
0x0038: 0x00f8, # DIGIT EIGHT
0x0039: 0x00f9, # DIGIT NINE
0x003a: 0x007a, # COLON
0x003b: 0x005e, # SEMICOLON
0x003c: 0x004c, # LESS-THAN SIGN
0x003d: 0x007e, # EQUALS SIGN
0x003e: 0x006e, # GREATER-THAN SIGN
0x003f: 0x006f, # QUESTION MARK
0x0040: 0x007c, # COMMERCIAL AT
0x0041: 0x00c1, # LATIN CAPITAL LETTER A
0x0042: 0x00c2, # LATIN CAPITAL LETTER B
0x0043: 0x00c3, # LATIN CAPITAL LETTER C
0x0044: 0x00c4, # LATIN CAPITAL LETTER D
0x0045: 0x00c5, # LATIN CAPITAL LETTER E
0x0046: 0x00c6, # LATIN CAPITAL LETTER F
0x0047: 0x00c7, # LATIN CAPITAL LETTER G
0x0048: 0x00c8, # LATIN CAPITAL LETTER H
0x0049: 0x00c9, # LATIN CAPITAL LETTER I
0x004a: 0x00d1, # LATIN CAPITAL LETTER J
0x004b: 0x00d2, # LATIN CAPITAL LETTER K
0x004c: 0x00d3, # LATIN CAPITAL LETTER L
0x004d: 0x00d4, # LATIN CAPITAL LETTER M
0x004e: 0x00d5, # LATIN CAPITAL LETTER N
0x004f: 0x00d6, # LATIN CAPITAL LETTER O
0x0050: 0x00d7, # LATIN CAPITAL LETTER P
0x0051: 0x00d8, # LATIN CAPITAL LETTER Q
0x0052: 0x00d9, # LATIN CAPITAL LETTER R
0x0053: 0x00e2, # LATIN CAPITAL LETTER S
0x0054: 0x00e3, # LATIN CAPITAL LETTER T
0x0055: 0x00e4, # LATIN CAPITAL LETTER U
0x0056: 0x00e5, # LATIN CAPITAL LETTER V
0x0057: 0x00e6, # LATIN CAPITAL LETTER W
0x0058: 0x00e7, # LATIN CAPITAL LETTER X
0x0059: 0x00e8, # LATIN CAPITAL LETTER Y
0x005a: 0x00e9, # LATIN CAPITAL LETTER Z
0x005b: 0x004a, # LEFT SQUARE BRACKET
0x005c: 0x00e0, # REVERSE SOLIDUS
0x005d: 0x005a, # RIGHT SQUARE BRACKET
0x005e: 0x005f, # CIRCUMFLEX ACCENT
0x005f: 0x006d, # LOW LINE
0x0060: 0x0079, # GRAVE ACCENT
0x0061: 0x0081, # LATIN SMALL LETTER A
0x0062: 0x0082, # LATIN SMALL LETTER B
0x0063: 0x0083, # LATIN SMALL LETTER C
0x0064: 0x0084, # LATIN SMALL LETTER D
0x0065: 0x0085, # LATIN SMALL LETTER E
0x0066: 0x0086, # LATIN SMALL LETTER F
0x0067: 0x0087, # LATIN SMALL LETTER G
0x0068: 0x0088, # LATIN SMALL LETTER H
0x0069: 0x0089, # LATIN SMALL LETTER I
0x006a: 0x0091, # LATIN SMALL LETTER J
0x006b: 0x0092, # LATIN SMALL LETTER K
0x006c: 0x0093, # LATIN SMALL LETTER L
0x006d: 0x0094, # LATIN SMALL LETTER M
0x006e: 0x0095, # LATIN SMALL LETTER N
0x006f: 0x0096, # LATIN SMALL LETTER O
0x0070: 0x0097, # LATIN SMALL LETTER P
0x0071: 0x0098, # LATIN SMALL LETTER Q
0x0072: 0x0099, # LATIN SMALL LETTER R
0x0073: 0x00a2, # LATIN SMALL LETTER S
0x0074: 0x00a3, # LATIN SMALL LETTER T
0x0075: 0x00a4, # LATIN SMALL LETTER U
0x0076: 0x00a5, # LATIN SMALL LETTER V
0x0077: 0x00a6, # LATIN SMALL LETTER W
0x0078: 0x00a7, # LATIN SMALL LETTER X
0x0079: 0x00a8, # LATIN SMALL LETTER Y
0x007a: 0x00a9, # LATIN SMALL LETTER Z
0x007b: 0x00c0, # LEFT CURLY BRACKET
0x007c: 0x00bb, # VERTICAL LINE
0x007d: 0x00d0, # RIGHT CURLY BRACKET
0x007e: 0x00a1, # TILDE
0x007f: 0x0007, # DELETE
0x0080: 0x0020, # CONTROL
0x0081: 0x0021, # CONTROL
0x0082: 0x0022, # CONTROL
0x0083: 0x0023, # CONTROL
0x0084: 0x0024, # CONTROL
0x0085: 0x0015, # CONTROL
0x0086: 0x0006, # CONTROL
0x0087: 0x0017, # CONTROL
0x0088: 0x0028, # CONTROL
0x0089: 0x0029, # CONTROL
0x008a: 0x002a, # CONTROL
0x008b: 0x002b, # CONTROL
0x008c: 0x002c, # CONTROL
0x008d: 0x0009, # CONTROL
0x008e: 0x000a, # CONTROL
0x008f: 0x001b, # CONTROL
0x0090: 0x0030, # CONTROL
0x0091: 0x0031, # CONTROL
0x0092: 0x001a, # CONTROL
0x0093: 0x0033, # CONTROL
0x0094: 0x0034, # CONTROL
0x0095: 0x0035, # CONTROL
0x0096: 0x0036, # CONTROL
0x0097: 0x0008, # CONTROL
0x0098: 0x0038, # CONTROL
0x0099: 0x0039, # CONTROL
0x009a: 0x003a, # CONTROL
0x009b: 0x003b, # CONTROL
0x009c: 0x0004, # CONTROL
0x009d: 0x0014, # CONTROL
0x009e: 0x003e, # CONTROL
0x009f: 0x00ff, # CONTROL
0x00a0: 0x0041, # NO-BREAK SPACE
0x00a1: 0x00aa, # INVERTED EXCLAMATION MARK
0x00a2: 0x00b0, # CENT SIGN
0x00a3: 0x00b1, # POUND SIGN
0x00a4: 0x009f, # CURRENCY SIGN
0x00a5: 0x00b2, # YEN SIGN
0x00a6: 0x006a, # BROKEN BAR
0x00a7: 0x00b5, # SECTION SIGN
0x00a8: 0x00bd, # DIAERESIS
0x00a9: 0x00b4, # COPYRIGHT SIGN
0x00aa: 0x009a, # FEMININE ORDINAL INDICATOR
0x00ab: 0x008a, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00ac: 0x00ba, # NOT SIGN
0x00ad: 0x00ca, # SOFT HYPHEN
0x00ae: 0x00af, # REGISTERED SIGN
0x00af: 0x00bc, # MACRON
0x00b0: 0x0090, # DEGREE SIGN
0x00b1: 0x008f, # PLUS-MINUS SIGN
0x00b2: 0x00ea, # SUPERSCRIPT TWO
0x00b3: 0x00fa, # SUPERSCRIPT THREE
0x00b4: 0x00be, # ACUTE ACCENT
0x00b5: 0x00a0, # MICRO SIGN
0x00b6: 0x00b6, # PILCROW SIGN
0x00b7: 0x00b3, # MIDDLE DOT
0x00b8: 0x009d, # CEDILLA
0x00b9: 0x00da, # SUPERSCRIPT ONE
0x00ba: 0x009b, # MASCULINE ORDINAL INDICATOR
0x00bb: 0x008b, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00bc: 0x00b7, # VULGAR FRACTION ONE QUARTER
0x00bd: 0x00b8, # VULGAR FRACTION ONE HALF
0x00be: 0x00b9, # VULGAR FRACTION THREE QUARTERS
0x00bf: 0x00ab, # INVERTED QUESTION MARK
0x00c0: 0x0064, # LATIN CAPITAL LETTER A WITH GRAVE
0x00c1: 0x0065, # LATIN CAPITAL LETTER A WITH ACUTE
0x00c2: 0x0062, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x00c3: 0x0066, # LATIN CAPITAL LETTER A WITH TILDE
0x00c4: 0x0063, # LATIN CAPITAL LETTER A WITH DIAERESIS
0x00c5: 0x0067, # LATIN CAPITAL LETTER A WITH RING ABOVE
0x00c6: 0x009e, # LATIN CAPITAL LIGATURE AE
0x00c7: 0x0068, # LATIN CAPITAL LETTER C WITH CEDILLA
0x00c8: 0x0074, # LATIN CAPITAL LETTER E WITH GRAVE
0x00c9: 0x0071, # LATIN CAPITAL LETTER E WITH ACUTE
0x00ca: 0x0072, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x00cb: 0x0073, # LATIN CAPITAL LETTER E WITH DIAERESIS
0x00cc: 0x0078, # LATIN CAPITAL LETTER I WITH GRAVE
0x00cd: 0x0075, # LATIN CAPITAL LETTER I WITH ACUTE
0x00ce: 0x0076, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0x00cf: 0x0077, # LATIN CAPITAL LETTER I WITH DIAERESIS
0x00d0: 0x00ac, # LATIN CAPITAL LETTER ETH (ICELANDIC)
0x00d1: 0x0069, # LATIN CAPITAL LETTER N WITH TILDE
0x00d2: 0x00ed, # LATIN CAPITAL LETTER O WITH GRAVE
0x00d3: 0x00ee, # LATIN CAPITAL LETTER O WITH ACUTE
0x00d4: 0x00eb, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0x00d5: 0x00ef, # LATIN CAPITAL LETTER O WITH TILDE
0x00d6: 0x00ec, # LATIN CAPITAL LETTER O WITH DIAERESIS
0x00d7: 0x00bf, # MULTIPLICATION SIGN
0x00d8: 0x0080, # LATIN CAPITAL LETTER O WITH STROKE
0x00d9: 0x00fd, # LATIN CAPITAL LETTER U WITH GRAVE
0x00da: 0x00fe, # LATIN CAPITAL LETTER U WITH ACUTE
0x00db: 0x00fb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0x00dc: 0x00fc, # LATIN CAPITAL LETTER U WITH DIAERESIS
0x00dd: 0x00ad, # LATIN CAPITAL LETTER Y WITH ACUTE
0x00de: 0x00ae, # LATIN CAPITAL LETTER THORN (ICELANDIC)
0x00df: 0x0059, # LATIN SMALL LETTER SHARP S (GERMAN)
0x00e0: 0x0044, # LATIN SMALL LETTER A WITH GRAVE
0x00e1: 0x0045, # LATIN SMALL LETTER A WITH ACUTE
0x00e2: 0x0042, # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x00e3: 0x0046, # LATIN SMALL LETTER A WITH TILDE
0x00e4: 0x0043, # LATIN SMALL LETTER A WITH DIAERESIS
0x00e5: 0x0047, # LATIN SMALL LETTER A WITH RING ABOVE
0x00e6: 0x009c, # LATIN SMALL LIGATURE AE
0x00e7: 0x0048, # LATIN SMALL LETTER C WITH CEDILLA
0x00e8: 0x0054, # LATIN SMALL LETTER E WITH GRAVE
0x00e9: 0x0051, # LATIN SMALL LETTER E WITH ACUTE
0x00ea: 0x0052, # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x00eb: 0x0053, # LATIN SMALL LETTER E WITH DIAERESIS
0x00ec: 0x0058, # LATIN SMALL LETTER I WITH GRAVE
0x00ed: 0x0055, # LATIN SMALL LETTER I WITH ACUTE
0x00ee: 0x0056, # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x00ef: 0x0057, # LATIN SMALL LETTER I WITH DIAERESIS
0x00f0: 0x008c, # LATIN SMALL LETTER ETH (ICELANDIC)
0x00f1: 0x0049, # LATIN SMALL LETTER N WITH TILDE
0x00f2: 0x00cd, # LATIN SMALL LETTER O WITH GRAVE
0x00f3: 0x00ce, # LATIN SMALL LETTER O WITH ACUTE
0x00f4: 0x00cb, # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x00f5: 0x00cf, # LATIN SMALL LETTER O WITH TILDE
0x00f6: 0x00cc, # LATIN SMALL LETTER O WITH DIAERESIS
0x00f7: 0x00e1, # DIVISION SIGN
0x00f8: 0x0070, # LATIN SMALL LETTER O WITH STROKE
0x00f9: 0x00dd, # LATIN SMALL LETTER U WITH GRAVE
0x00fa: 0x00de, # LATIN SMALL LETTER U WITH ACUTE
0x00fb: 0x00db, # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x00fc: 0x00dc, # LATIN SMALL LETTER U WITH DIAERESIS
0x00fd: 0x008d, # LATIN SMALL LETTER Y WITH ACUTE
0x00fe: 0x008e, # LATIN SMALL LETTER THORN (ICELANDIC)
0x00ff: 0x00df, # LATIN SMALL LETTER Y WITH DIAERESIS
}
\ No newline at end of file
""" Python Character Mapping Codec generated from 'CP875.TXT' with gencodec.py. """ Python Character Mapping Codec generated from 'VENDORS/MICSFT/EBCDIC/CP875.TXT' with gencodec.py.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
(c) Copyright 2000 Guido van Rossum.
"""#" """#"
...@@ -19,7 +14,7 @@ class Codec(codecs.Codec): ...@@ -19,7 +14,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'): def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_map) return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter): class StreamWriter(Codec,codecs.StreamWriter):
pass pass
...@@ -276,6 +271,518 @@ decoding_map.update({ ...@@ -276,6 +271,518 @@ decoding_map.update({
0x00ff: 0x009f, # CONTROL 0x00ff: 0x009f, # CONTROL
}) })
### Decoding Table
decoding_table = (
u'\x00' # 0x0000 -> NULL
u'\x01' # 0x0001 -> START OF HEADING
u'\x02' # 0x0002 -> START OF TEXT
u'\x03' # 0x0003 -> END OF TEXT
u'\x9c' # 0x0004 -> CONTROL
u'\t' # 0x0005 -> HORIZONTAL TABULATION
u'\x86' # 0x0006 -> CONTROL
u'\x7f' # 0x0007 -> DELETE
u'\x97' # 0x0008 -> CONTROL
u'\x8d' # 0x0009 -> CONTROL
u'\x8e' # 0x000a -> CONTROL
u'\x0b' # 0x000b -> VERTICAL TABULATION
u'\x0c' # 0x000c -> FORM FEED
u'\r' # 0x000d -> CARRIAGE RETURN
u'\x0e' # 0x000e -> SHIFT OUT
u'\x0f' # 0x000f -> SHIFT IN
u'\x10' # 0x0010 -> DATA LINK ESCAPE
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
u'\x9d' # 0x0014 -> CONTROL
u'\x85' # 0x0015 -> CONTROL
u'\x08' # 0x0016 -> BACKSPACE
u'\x87' # 0x0017 -> CONTROL
u'\x18' # 0x0018 -> CANCEL
u'\x19' # 0x0019 -> END OF MEDIUM
u'\x92' # 0x001a -> CONTROL
u'\x8f' # 0x001b -> CONTROL
u'\x1c' # 0x001c -> FILE SEPARATOR
u'\x1d' # 0x001d -> GROUP SEPARATOR
u'\x1e' # 0x001e -> RECORD SEPARATOR
u'\x1f' # 0x001f -> UNIT SEPARATOR
u'\x80' # 0x0020 -> CONTROL
u'\x81' # 0x0021 -> CONTROL
u'\x82' # 0x0022 -> CONTROL
u'\x83' # 0x0023 -> CONTROL
u'\x84' # 0x0024 -> CONTROL
u'\n' # 0x0025 -> LINE FEED
u'\x17' # 0x0026 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x0027 -> ESCAPE
u'\x88' # 0x0028 -> CONTROL
u'\x89' # 0x0029 -> CONTROL
u'\x8a' # 0x002a -> CONTROL
u'\x8b' # 0x002b -> CONTROL
u'\x8c' # 0x002c -> CONTROL
u'\x05' # 0x002d -> ENQUIRY
u'\x06' # 0x002e -> ACKNOWLEDGE
u'\x07' # 0x002f -> BELL
u'\x90' # 0x0030 -> CONTROL
u'\x91' # 0x0031 -> CONTROL
u'\x16' # 0x0032 -> SYNCHRONOUS IDLE
u'\x93' # 0x0033 -> CONTROL
u'\x94' # 0x0034 -> CONTROL
u'\x95' # 0x0035 -> CONTROL
u'\x96' # 0x0036 -> CONTROL
u'\x04' # 0x0037 -> END OF TRANSMISSION
u'\x98' # 0x0038 -> CONTROL
u'\x99' # 0x0039 -> CONTROL
u'\x9a' # 0x003a -> CONTROL
u'\x9b' # 0x003b -> CONTROL
u'\x14' # 0x003c -> DEVICE CONTROL FOUR
u'\x15' # 0x003d -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x003e -> CONTROL
u'\x1a' # 0x003f -> SUBSTITUTE
u' ' # 0x0040 -> SPACE
u'\u0391' # 0x0041 -> GREEK CAPITAL LETTER ALPHA
u'\u0392' # 0x0042 -> GREEK CAPITAL LETTER BETA
u'\u0393' # 0x0043 -> GREEK CAPITAL LETTER GAMMA
u'\u0394' # 0x0044 -> GREEK CAPITAL LETTER DELTA
u'\u0395' # 0x0045 -> GREEK CAPITAL LETTER EPSILON
u'\u0396' # 0x0046 -> GREEK CAPITAL LETTER ZETA
u'\u0397' # 0x0047 -> GREEK CAPITAL LETTER ETA
u'\u0398' # 0x0048 -> GREEK CAPITAL LETTER THETA
u'\u0399' # 0x0049 -> GREEK CAPITAL LETTER IOTA
u'[' # 0x004a -> LEFT SQUARE BRACKET
u'.' # 0x004b -> FULL STOP
u'<' # 0x004c -> LESS-THAN SIGN
u'(' # 0x004d -> LEFT PARENTHESIS
u'+' # 0x004e -> PLUS SIGN
u'!' # 0x004f -> EXCLAMATION MARK
u'&' # 0x0050 -> AMPERSAND
u'\u039a' # 0x0051 -> GREEK CAPITAL LETTER KAPPA
u'\u039b' # 0x0052 -> GREEK CAPITAL LETTER LAMDA
u'\u039c' # 0x0053 -> GREEK CAPITAL LETTER MU
u'\u039d' # 0x0054 -> GREEK CAPITAL LETTER NU
u'\u039e' # 0x0055 -> GREEK CAPITAL LETTER XI
u'\u039f' # 0x0056 -> GREEK CAPITAL LETTER OMICRON
u'\u03a0' # 0x0057 -> GREEK CAPITAL LETTER PI
u'\u03a1' # 0x0058 -> GREEK CAPITAL LETTER RHO
u'\u03a3' # 0x0059 -> GREEK CAPITAL LETTER SIGMA
u']' # 0x005a -> RIGHT SQUARE BRACKET
u'$' # 0x005b -> DOLLAR SIGN
u'*' # 0x005c -> ASTERISK
u')' # 0x005d -> RIGHT PARENTHESIS
u';' # 0x005e -> SEMICOLON
u'^' # 0x005f -> CIRCUMFLEX ACCENT
u'-' # 0x0060 -> HYPHEN-MINUS
u'/' # 0x0061 -> SOLIDUS
u'\u03a4' # 0x0062 -> GREEK CAPITAL LETTER TAU
u'\u03a5' # 0x0063 -> GREEK CAPITAL LETTER UPSILON
u'\u03a6' # 0x0064 -> GREEK CAPITAL LETTER PHI
u'\u03a7' # 0x0065 -> GREEK CAPITAL LETTER CHI
u'\u03a8' # 0x0066 -> GREEK CAPITAL LETTER PSI
u'\u03a9' # 0x0067 -> GREEK CAPITAL LETTER OMEGA
u'\u03aa' # 0x0068 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
u'\u03ab' # 0x0069 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
u'|' # 0x006a -> VERTICAL LINE
u',' # 0x006b -> COMMA
u'%' # 0x006c -> PERCENT SIGN
u'_' # 0x006d -> LOW LINE
u'>' # 0x006e -> GREATER-THAN SIGN
u'?' # 0x006f -> QUESTION MARK
u'\xa8' # 0x0070 -> DIAERESIS
u'\u0386' # 0x0071 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
u'\u0388' # 0x0072 -> GREEK CAPITAL LETTER EPSILON WITH TONOS
u'\u0389' # 0x0073 -> GREEK CAPITAL LETTER ETA WITH TONOS
u'\xa0' # 0x0074 -> NO-BREAK SPACE
u'\u038a' # 0x0075 -> GREEK CAPITAL LETTER IOTA WITH TONOS
u'\u038c' # 0x0076 -> GREEK CAPITAL LETTER OMICRON WITH TONOS
u'\u038e' # 0x0077 -> GREEK CAPITAL LETTER UPSILON WITH TONOS
u'\u038f' # 0x0078 -> GREEK CAPITAL LETTER OMEGA WITH TONOS
u'`' # 0x0079 -> GRAVE ACCENT
u':' # 0x007a -> COLON
u'#' # 0x007b -> NUMBER SIGN
u'@' # 0x007c -> COMMERCIAL AT
u"'" # 0x007d -> APOSTROPHE
u'=' # 0x007e -> EQUALS SIGN
u'"' # 0x007f -> QUOTATION MARK
u'\u0385' # 0x0080 -> GREEK DIALYTIKA TONOS
u'a' # 0x0081 -> LATIN SMALL LETTER A
u'b' # 0x0082 -> LATIN SMALL LETTER B
u'c' # 0x0083 -> LATIN SMALL LETTER C
u'd' # 0x0084 -> LATIN SMALL LETTER D
u'e' # 0x0085 -> LATIN SMALL LETTER E
u'f' # 0x0086 -> LATIN SMALL LETTER F
u'g' # 0x0087 -> LATIN SMALL LETTER G
u'h' # 0x0088 -> LATIN SMALL LETTER H
u'i' # 0x0089 -> LATIN SMALL LETTER I
u'\u03b1' # 0x008a -> GREEK SMALL LETTER ALPHA
u'\u03b2' # 0x008b -> GREEK SMALL LETTER BETA
u'\u03b3' # 0x008c -> GREEK SMALL LETTER GAMMA
u'\u03b4' # 0x008d -> GREEK SMALL LETTER DELTA
u'\u03b5' # 0x008e -> GREEK SMALL LETTER EPSILON
u'\u03b6' # 0x008f -> GREEK SMALL LETTER ZETA
u'\xb0' # 0x0090 -> DEGREE SIGN
u'j' # 0x0091 -> LATIN SMALL LETTER J
u'k' # 0x0092 -> LATIN SMALL LETTER K
u'l' # 0x0093 -> LATIN SMALL LETTER L
u'm' # 0x0094 -> LATIN SMALL LETTER M
u'n' # 0x0095 -> LATIN SMALL LETTER N
u'o' # 0x0096 -> LATIN SMALL LETTER O
u'p' # 0x0097 -> LATIN SMALL LETTER P
u'q' # 0x0098 -> LATIN SMALL LETTER Q
u'r' # 0x0099 -> LATIN SMALL LETTER R
u'\u03b7' # 0x009a -> GREEK SMALL LETTER ETA
u'\u03b8' # 0x009b -> GREEK SMALL LETTER THETA
u'\u03b9' # 0x009c -> GREEK SMALL LETTER IOTA
u'\u03ba' # 0x009d -> GREEK SMALL LETTER KAPPA
u'\u03bb' # 0x009e -> GREEK SMALL LETTER LAMDA
u'\u03bc' # 0x009f -> GREEK SMALL LETTER MU
u'\xb4' # 0x00a0 -> ACUTE ACCENT
u'~' # 0x00a1 -> TILDE
u's' # 0x00a2 -> LATIN SMALL LETTER S
u't' # 0x00a3 -> LATIN SMALL LETTER T
u'u' # 0x00a4 -> LATIN SMALL LETTER U
u'v' # 0x00a5 -> LATIN SMALL LETTER V
u'w' # 0x00a6 -> LATIN SMALL LETTER W
u'x' # 0x00a7 -> LATIN SMALL LETTER X
u'y' # 0x00a8 -> LATIN SMALL LETTER Y
u'z' # 0x00a9 -> LATIN SMALL LETTER Z
u'\u03bd' # 0x00aa -> GREEK SMALL LETTER NU
u'\u03be' # 0x00ab -> GREEK SMALL LETTER XI
u'\u03bf' # 0x00ac -> GREEK SMALL LETTER OMICRON
u'\u03c0' # 0x00ad -> GREEK SMALL LETTER PI
u'\u03c1' # 0x00ae -> GREEK SMALL LETTER RHO
u'\u03c3' # 0x00af -> GREEK SMALL LETTER SIGMA
u'\xa3' # 0x00b0 -> POUND SIGN
u'\u03ac' # 0x00b1 -> GREEK SMALL LETTER ALPHA WITH TONOS
u'\u03ad' # 0x00b2 -> GREEK SMALL LETTER EPSILON WITH TONOS
u'\u03ae' # 0x00b3 -> GREEK SMALL LETTER ETA WITH TONOS
u'\u03ca' # 0x00b4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
u'\u03af' # 0x00b5 -> GREEK SMALL LETTER IOTA WITH TONOS
u'\u03cc' # 0x00b6 -> GREEK SMALL LETTER OMICRON WITH TONOS
u'\u03cd' # 0x00b7 -> GREEK SMALL LETTER UPSILON WITH TONOS
u'\u03cb' # 0x00b8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
u'\u03ce' # 0x00b9 -> GREEK SMALL LETTER OMEGA WITH TONOS
u'\u03c2' # 0x00ba -> GREEK SMALL LETTER FINAL SIGMA
u'\u03c4' # 0x00bb -> GREEK SMALL LETTER TAU
u'\u03c5' # 0x00bc -> GREEK SMALL LETTER UPSILON
u'\u03c6' # 0x00bd -> GREEK SMALL LETTER PHI
u'\u03c7' # 0x00be -> GREEK SMALL LETTER CHI
u'\u03c8' # 0x00bf -> GREEK SMALL LETTER PSI
u'{' # 0x00c0 -> LEFT CURLY BRACKET
u'A' # 0x00c1 -> LATIN CAPITAL LETTER A
u'B' # 0x00c2 -> LATIN CAPITAL LETTER B
u'C' # 0x00c3 -> LATIN CAPITAL LETTER C
u'D' # 0x00c4 -> LATIN CAPITAL LETTER D
u'E' # 0x00c5 -> LATIN CAPITAL LETTER E
u'F' # 0x00c6 -> LATIN CAPITAL LETTER F
u'G' # 0x00c7 -> LATIN CAPITAL LETTER G
u'H' # 0x00c8 -> LATIN CAPITAL LETTER H
u'I' # 0x00c9 -> LATIN CAPITAL LETTER I
u'\xad' # 0x00ca -> SOFT HYPHEN
u'\u03c9' # 0x00cb -> GREEK SMALL LETTER OMEGA
u'\u0390' # 0x00cc -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
u'\u03b0' # 0x00cd -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
u'\u2018' # 0x00ce -> LEFT SINGLE QUOTATION MARK
u'\u2015' # 0x00cf -> HORIZONTAL BAR
u'}' # 0x00d0 -> RIGHT CURLY BRACKET
u'J' # 0x00d1 -> LATIN CAPITAL LETTER J
u'K' # 0x00d2 -> LATIN CAPITAL LETTER K
u'L' # 0x00d3 -> LATIN CAPITAL LETTER L
u'M' # 0x00d4 -> LATIN CAPITAL LETTER M
u'N' # 0x00d5 -> LATIN CAPITAL LETTER N
u'O' # 0x00d6 -> LATIN CAPITAL LETTER O
u'P' # 0x00d7 -> LATIN CAPITAL LETTER P
u'Q' # 0x00d8 -> LATIN CAPITAL LETTER Q
u'R' # 0x00d9 -> LATIN CAPITAL LETTER R
u'\xb1' # 0x00da -> PLUS-MINUS SIGN
u'\xbd' # 0x00db -> VULGAR FRACTION ONE HALF
u'\x1a' # 0x00dc -> SUBSTITUTE
u'\u0387' # 0x00dd -> GREEK ANO TELEIA
u'\u2019' # 0x00de -> RIGHT SINGLE QUOTATION MARK
u'\xa6' # 0x00df -> BROKEN BAR
u'\\' # 0x00e0 -> REVERSE SOLIDUS
u'\x1a' # 0x00e1 -> SUBSTITUTE
u'S' # 0x00e2 -> LATIN CAPITAL LETTER S
u'T' # 0x00e3 -> LATIN CAPITAL LETTER T
u'U' # 0x00e4 -> LATIN CAPITAL LETTER U
u'V' # 0x00e5 -> LATIN CAPITAL LETTER V
u'W' # 0x00e6 -> LATIN CAPITAL LETTER W
u'X' # 0x00e7 -> LATIN CAPITAL LETTER X
u'Y' # 0x00e8 -> LATIN CAPITAL LETTER Y
u'Z' # 0x00e9 -> LATIN CAPITAL LETTER Z
u'\xb2' # 0x00ea -> SUPERSCRIPT TWO
u'\xa7' # 0x00eb -> SECTION SIGN
u'\x1a' # 0x00ec -> SUBSTITUTE
u'\x1a' # 0x00ed -> SUBSTITUTE
u'\xab' # 0x00ee -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xac' # 0x00ef -> NOT SIGN
u'0' # 0x00f0 -> DIGIT ZERO
u'1' # 0x00f1 -> DIGIT ONE
u'2' # 0x00f2 -> DIGIT TWO
u'3' # 0x00f3 -> DIGIT THREE
u'4' # 0x00f4 -> DIGIT FOUR
u'5' # 0x00f5 -> DIGIT FIVE
u'6' # 0x00f6 -> DIGIT SIX
u'7' # 0x00f7 -> DIGIT SEVEN
u'8' # 0x00f8 -> DIGIT EIGHT
u'9' # 0x00f9 -> DIGIT NINE
u'\xb3' # 0x00fa -> SUPERSCRIPT THREE
u'\xa9' # 0x00fb -> COPYRIGHT SIGN
u'\x1a' # 0x00fc -> SUBSTITUTE
u'\x1a' # 0x00fd -> SUBSTITUTE
u'\xbb' # 0x00fe -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\x9f' # 0x00ff -> CONTROL
)
### Encoding Map ### Encoding Map
encoding_map = codecs.make_encoding_map(decoding_map) encoding_map = {
0x0000: 0x0000, # NULL
0x0001: 0x0001, # START OF HEADING
0x0002: 0x0002, # START OF TEXT
0x0003: 0x0003, # END OF TEXT
0x0004: 0x0037, # END OF TRANSMISSION
0x0005: 0x002d, # ENQUIRY
0x0006: 0x002e, # ACKNOWLEDGE
0x0007: 0x002f, # BELL
0x0008: 0x0016, # BACKSPACE
0x0009: 0x0005, # HORIZONTAL TABULATION
0x000a: 0x0025, # LINE FEED
0x000b: 0x000b, # VERTICAL TABULATION
0x000c: 0x000c, # FORM FEED
0x000d: 0x000d, # CARRIAGE RETURN
0x000e: 0x000e, # SHIFT OUT
0x000f: 0x000f, # SHIFT IN
0x0010: 0x0010, # DATA LINK ESCAPE
0x0011: 0x0011, # DEVICE CONTROL ONE
0x0012: 0x0012, # DEVICE CONTROL TWO
0x0013: 0x0013, # DEVICE CONTROL THREE
0x0014: 0x003c, # DEVICE CONTROL FOUR
0x0015: 0x003d, # NEGATIVE ACKNOWLEDGE
0x0016: 0x0032, # SYNCHRONOUS IDLE
0x0017: 0x0026, # END OF TRANSMISSION BLOCK
0x0018: 0x0018, # CANCEL
0x0019: 0x0019, # END OF MEDIUM
0x001a: None, # SUBSTITUTE
0x001b: 0x0027, # ESCAPE
0x001c: 0x001c, # FILE SEPARATOR
0x001d: 0x001d, # GROUP SEPARATOR
0x001e: 0x001e, # RECORD SEPARATOR
0x001f: 0x001f, # UNIT SEPARATOR
0x0020: 0x0040, # SPACE
0x0021: 0x004f, # EXCLAMATION MARK
0x0022: 0x007f, # QUOTATION MARK
0x0023: 0x007b, # NUMBER SIGN
0x0024: 0x005b, # DOLLAR SIGN
0x0025: 0x006c, # PERCENT SIGN
0x0026: 0x0050, # AMPERSAND
0x0027: 0x007d, # APOSTROPHE
0x0028: 0x004d, # LEFT PARENTHESIS
0x0029: 0x005d, # RIGHT PARENTHESIS
0x002a: 0x005c, # ASTERISK
0x002b: 0x004e, # PLUS SIGN
0x002c: 0x006b, # COMMA
0x002d: 0x0060, # HYPHEN-MINUS
0x002e: 0x004b, # FULL STOP
0x002f: 0x0061, # SOLIDUS
0x0030: 0x00f0, # DIGIT ZERO
0x0031: 0x00f1, # DIGIT ONE
0x0032: 0x00f2, # DIGIT TWO
0x0033: 0x00f3, # DIGIT THREE
0x0034: 0x00f4, # DIGIT FOUR
0x0035: 0x00f5, # DIGIT FIVE
0x0036: 0x00f6, # DIGIT SIX
0x0037: 0x00f7, # DIGIT SEVEN
0x0038: 0x00f8, # DIGIT EIGHT
0x0039: 0x00f9, # DIGIT NINE
0x003a: 0x007a, # COLON
0x003b: 0x005e, # SEMICOLON
0x003c: 0x004c, # LESS-THAN SIGN
0x003d: 0x007e, # EQUALS SIGN
0x003e: 0x006e, # GREATER-THAN SIGN
0x003f: 0x006f, # QUESTION MARK
0x0040: 0x007c, # COMMERCIAL AT
0x0041: 0x00c1, # LATIN CAPITAL LETTER A
0x0042: 0x00c2, # LATIN CAPITAL LETTER B
0x0043: 0x00c3, # LATIN CAPITAL LETTER C
0x0044: 0x00c4, # LATIN CAPITAL LETTER D
0x0045: 0x00c5, # LATIN CAPITAL LETTER E
0x0046: 0x00c6, # LATIN CAPITAL LETTER F
0x0047: 0x00c7, # LATIN CAPITAL LETTER G
0x0048: 0x00c8, # LATIN CAPITAL LETTER H
0x0049: 0x00c9, # LATIN CAPITAL LETTER I
0x004a: 0x00d1, # LATIN CAPITAL LETTER J
0x004b: 0x00d2, # LATIN CAPITAL LETTER K
0x004c: 0x00d3, # LATIN CAPITAL LETTER L
0x004d: 0x00d4, # LATIN CAPITAL LETTER M
0x004e: 0x00d5, # LATIN CAPITAL LETTER N
0x004f: 0x00d6, # LATIN CAPITAL LETTER O
0x0050: 0x00d7, # LATIN CAPITAL LETTER P
0x0051: 0x00d8, # LATIN CAPITAL LETTER Q
0x0052: 0x00d9, # LATIN CAPITAL LETTER R
0x0053: 0x00e2, # LATIN CAPITAL LETTER S
0x0054: 0x00e3, # LATIN CAPITAL LETTER T
0x0055: 0x00e4, # LATIN CAPITAL LETTER U
0x0056: 0x00e5, # LATIN CAPITAL LETTER V
0x0057: 0x00e6, # LATIN CAPITAL LETTER W
0x0058: 0x00e7, # LATIN CAPITAL LETTER X
0x0059: 0x00e8, # LATIN CAPITAL LETTER Y
0x005a: 0x00e9, # LATIN CAPITAL LETTER Z
0x005b: 0x004a, # LEFT SQUARE BRACKET
0x005c: 0x00e0, # REVERSE SOLIDUS
0x005d: 0x005a, # RIGHT SQUARE BRACKET
0x005e: 0x005f, # CIRCUMFLEX ACCENT
0x005f: 0x006d, # LOW LINE
0x0060: 0x0079, # GRAVE ACCENT
0x0061: 0x0081, # LATIN SMALL LETTER A
0x0062: 0x0082, # LATIN SMALL LETTER B
0x0063: 0x0083, # LATIN SMALL LETTER C
0x0064: 0x0084, # LATIN SMALL LETTER D
0x0065: 0x0085, # LATIN SMALL LETTER E
0x0066: 0x0086, # LATIN SMALL LETTER F
0x0067: 0x0087, # LATIN SMALL LETTER G
0x0068: 0x0088, # LATIN SMALL LETTER H
0x0069: 0x0089, # LATIN SMALL LETTER I
0x006a: 0x0091, # LATIN SMALL LETTER J
0x006b: 0x0092, # LATIN SMALL LETTER K
0x006c: 0x0093, # LATIN SMALL LETTER L
0x006d: 0x0094, # LATIN SMALL LETTER M
0x006e: 0x0095, # LATIN SMALL LETTER N
0x006f: 0x0096, # LATIN SMALL LETTER O
0x0070: 0x0097, # LATIN SMALL LETTER P
0x0071: 0x0098, # LATIN SMALL LETTER Q
0x0072: 0x0099, # LATIN SMALL LETTER R
0x0073: 0x00a2, # LATIN SMALL LETTER S
0x0074: 0x00a3, # LATIN SMALL LETTER T
0x0075: 0x00a4, # LATIN SMALL LETTER U
0x0076: 0x00a5, # LATIN SMALL LETTER V
0x0077: 0x00a6, # LATIN SMALL LETTER W
0x0078: 0x00a7, # LATIN SMALL LETTER X
0x0079: 0x00a8, # LATIN SMALL LETTER Y
0x007a: 0x00a9, # LATIN SMALL LETTER Z
0x007b: 0x00c0, # LEFT CURLY BRACKET
0x007c: 0x006a, # VERTICAL LINE
0x007d: 0x00d0, # RIGHT CURLY BRACKET
0x007e: 0x00a1, # TILDE
0x007f: 0x0007, # DELETE
0x0080: 0x0020, # CONTROL
0x0081: 0x0021, # CONTROL
0x0082: 0x0022, # CONTROL
0x0083: 0x0023, # CONTROL
0x0084: 0x0024, # CONTROL
0x0085: 0x0015, # CONTROL
0x0086: 0x0006, # CONTROL
0x0087: 0x0017, # CONTROL
0x0088: 0x0028, # CONTROL
0x0089: 0x0029, # CONTROL
0x008a: 0x002a, # CONTROL
0x008b: 0x002b, # CONTROL
0x008c: 0x002c, # CONTROL
0x008d: 0x0009, # CONTROL
0x008e: 0x000a, # CONTROL
0x008f: 0x001b, # CONTROL
0x0090: 0x0030, # CONTROL
0x0091: 0x0031, # CONTROL
0x0092: 0x001a, # CONTROL
0x0093: 0x0033, # CONTROL
0x0094: 0x0034, # CONTROL
0x0095: 0x0035, # CONTROL
0x0096: 0x0036, # CONTROL
0x0097: 0x0008, # CONTROL
0x0098: 0x0038, # CONTROL
0x0099: 0x0039, # CONTROL
0x009a: 0x003a, # CONTROL
0x009b: 0x003b, # CONTROL
0x009c: 0x0004, # CONTROL
0x009d: 0x0014, # CONTROL
0x009e: 0x003e, # CONTROL
0x009f: 0x00ff, # CONTROL
0x00a0: 0x0074, # NO-BREAK SPACE
0x00a3: 0x00b0, # POUND SIGN
0x00a6: 0x00df, # BROKEN BAR
0x00a7: 0x00eb, # SECTION SIGN
0x00a8: 0x0070, # DIAERESIS
0x00a9: 0x00fb, # COPYRIGHT SIGN
0x00ab: 0x00ee, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00ac: 0x00ef, # NOT SIGN
0x00ad: 0x00ca, # SOFT HYPHEN
0x00b0: 0x0090, # DEGREE SIGN
0x00b1: 0x00da, # PLUS-MINUS SIGN
0x00b2: 0x00ea, # SUPERSCRIPT TWO
0x00b3: 0x00fa, # SUPERSCRIPT THREE
0x00b4: 0x00a0, # ACUTE ACCENT
0x00bb: 0x00fe, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00bd: 0x00db, # VULGAR FRACTION ONE HALF
0x0385: 0x0080, # GREEK DIALYTIKA TONOS
0x0386: 0x0071, # GREEK CAPITAL LETTER ALPHA WITH TONOS
0x0387: 0x00dd, # GREEK ANO TELEIA
0x0388: 0x0072, # GREEK CAPITAL LETTER EPSILON WITH TONOS
0x0389: 0x0073, # GREEK CAPITAL LETTER ETA WITH TONOS
0x038a: 0x0075, # GREEK CAPITAL LETTER IOTA WITH TONOS
0x038c: 0x0076, # GREEK CAPITAL LETTER OMICRON WITH TONOS
0x038e: 0x0077, # GREEK CAPITAL LETTER UPSILON WITH TONOS
0x038f: 0x0078, # GREEK CAPITAL LETTER OMEGA WITH TONOS
0x0390: 0x00cc, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
0x0391: 0x0041, # GREEK CAPITAL LETTER ALPHA
0x0392: 0x0042, # GREEK CAPITAL LETTER BETA
0x0393: 0x0043, # GREEK CAPITAL LETTER GAMMA
0x0394: 0x0044, # GREEK CAPITAL LETTER DELTA
0x0395: 0x0045, # GREEK CAPITAL LETTER EPSILON
0x0396: 0x0046, # GREEK CAPITAL LETTER ZETA
0x0397: 0x0047, # GREEK CAPITAL LETTER ETA
0x0398: 0x0048, # GREEK CAPITAL LETTER THETA
0x0399: 0x0049, # GREEK CAPITAL LETTER IOTA
0x039a: 0x0051, # GREEK CAPITAL LETTER KAPPA
0x039b: 0x0052, # GREEK CAPITAL LETTER LAMDA
0x039c: 0x0053, # GREEK CAPITAL LETTER MU
0x039d: 0x0054, # GREEK CAPITAL LETTER NU
0x039e: 0x0055, # GREEK CAPITAL LETTER XI
0x039f: 0x0056, # GREEK CAPITAL LETTER OMICRON
0x03a0: 0x0057, # GREEK CAPITAL LETTER PI
0x03a1: 0x0058, # GREEK CAPITAL LETTER RHO
0x03a3: 0x0059, # GREEK CAPITAL LETTER SIGMA
0x03a4: 0x0062, # GREEK CAPITAL LETTER TAU
0x03a5: 0x0063, # GREEK CAPITAL LETTER UPSILON
0x03a6: 0x0064, # GREEK CAPITAL LETTER PHI
0x03a7: 0x0065, # GREEK CAPITAL LETTER CHI
0x03a8: 0x0066, # GREEK CAPITAL LETTER PSI
0x03a9: 0x0067, # GREEK CAPITAL LETTER OMEGA
0x03aa: 0x0068, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
0x03ab: 0x0069, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
0x03ac: 0x00b1, # GREEK SMALL LETTER ALPHA WITH TONOS
0x03ad: 0x00b2, # GREEK SMALL LETTER EPSILON WITH TONOS
0x03ae: 0x00b3, # GREEK SMALL LETTER ETA WITH TONOS
0x03af: 0x00b5, # GREEK SMALL LETTER IOTA WITH TONOS
0x03b0: 0x00cd, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
0x03b1: 0x008a, # GREEK SMALL LETTER ALPHA
0x03b2: 0x008b, # GREEK SMALL LETTER BETA
0x03b3: 0x008c, # GREEK SMALL LETTER GAMMA
0x03b4: 0x008d, # GREEK SMALL LETTER DELTA
0x03b5: 0x008e, # GREEK SMALL LETTER EPSILON
0x03b6: 0x008f, # GREEK SMALL LETTER ZETA
0x03b7: 0x009a, # GREEK SMALL LETTER ETA
0x03b8: 0x009b, # GREEK SMALL LETTER THETA
0x03b9: 0x009c, # GREEK SMALL LETTER IOTA
0x03ba: 0x009d, # GREEK SMALL LETTER KAPPA
0x03bb: 0x009e, # GREEK SMALL LETTER LAMDA
0x03bc: 0x009f, # GREEK SMALL LETTER MU
0x03bd: 0x00aa, # GREEK SMALL LETTER NU
0x03be: 0x00ab, # GREEK SMALL LETTER XI
0x03bf: 0x00ac, # GREEK SMALL LETTER OMICRON
0x03c0: 0x00ad, # GREEK SMALL LETTER PI
0x03c1: 0x00ae, # GREEK SMALL LETTER RHO
0x03c2: 0x00ba, # GREEK SMALL LETTER FINAL SIGMA
0x03c3: 0x00af, # GREEK SMALL LETTER SIGMA
0x03c4: 0x00bb, # GREEK SMALL LETTER TAU
0x03c5: 0x00bc, # GREEK SMALL LETTER UPSILON
0x03c6: 0x00bd, # GREEK SMALL LETTER PHI
0x03c7: 0x00be, # GREEK SMALL LETTER CHI
0x03c8: 0x00bf, # GREEK SMALL LETTER PSI
0x03c9: 0x00cb, # GREEK SMALL LETTER OMEGA
0x03ca: 0x00b4, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
0x03cb: 0x00b8, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
0x03cc: 0x00b6, # GREEK SMALL LETTER OMICRON WITH TONOS
0x03cd: 0x00b7, # GREEK SMALL LETTER UPSILON WITH TONOS
0x03ce: 0x00b9, # GREEK SMALL LETTER OMEGA WITH TONOS
0x2015: 0x00cf, # HORIZONTAL BAR
0x2018: 0x00ce, # LEFT SINGLE QUOTATION MARK
0x2019: 0x00de, # RIGHT SINGLE QUOTATION MARK
}
\ No newline at end of file
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment