summaryrefslogtreecommitdiff
path: root/Lib/encodings/cp424.py
diff options
context:
space:
mode:
authorMarc-André Lemburg <mal@egenix.com>2005-10-21 13:49:12 +0000
committerMarc-André Lemburg <mal@egenix.com>2005-10-21 13:49:12 +0000
commita1129f4b9bdf655e8b5b9565b87ead5f32f4b574 (patch)
treedb7cf3de8872e250c8c9153a1b0dec559f869ecb /Lib/encodings/cp424.py
parent92b201debcb7c796a68df372f3660e02b2c85d40 (diff)
downloadcpython-git-a1129f4b9bdf655e8b5b9565b87ead5f32f4b574.tar.gz
Replace the old charmap codecs with new ones generated from the current
mapping tables available at ftp.unicode.org. These new codecs include and use character decoding tables which speeds up decoding by a few factors.
Diffstat (limited to 'Lib/encodings/cp424.py')
-rw-r--r--Lib/encodings/cp424.py965
1 files changed, 720 insertions, 245 deletions
diff --git a/Lib/encodings/cp424.py b/Lib/encodings/cp424.py
index 6a532333fb..1f4480dff7 100644
--- a/Lib/encodings/cp424.py
+++ b/Lib/encodings/cp424.py
@@ -1,9 +1,4 @@
-""" Python Character Mapping Codec generated from 'CP424.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.
+""" Python Character Mapping Codec generated from 'VENDORS/MISC/CP424.TXT' with gencodec.py.
"""#"
@@ -19,8 +14,8 @@ class Codec(codecs.Codec):
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):
pass
@@ -37,244 +32,724 @@ def getregentry():
decoding_map = codecs.make_identity_dict(range(256))
decoding_map.update({
- 0x0004: 0x009c, # SELECT
- 0x0005: 0x0009, # HORIZONTAL TABULATION
- 0x0006: 0x0086, # REQUIRED NEW LINE
- 0x0007: 0x007f, # DELETE
- 0x0008: 0x0097, # GRAPHIC ESCAPE
- 0x0009: 0x008d, # SUPERSCRIPT
- 0x000a: 0x008e, # REPEAT
- 0x0014: 0x009d, # RESTORE/ENABLE PRESENTATION
- 0x0015: 0x0085, # NEW LINE
- 0x0016: 0x0008, # BACKSPACE
- 0x0017: 0x0087, # PROGRAM OPERATOR COMMUNICATION
- 0x001a: 0x0092, # UNIT BACK SPACE
- 0x001b: 0x008f, # CUSTOMER USE ONE
- 0x0020: 0x0080, # DIGIT SELECT
- 0x0021: 0x0081, # START OF SIGNIFICANCE
- 0x0022: 0x0082, # FIELD SEPARATOR
- 0x0023: 0x0083, # WORD UNDERSCORE
- 0x0024: 0x0084, # BYPASS OR INHIBIT PRESENTATION
- 0x0025: 0x000a, # LINE FEED
- 0x0026: 0x0017, # END OF TRANSMISSION BLOCK
- 0x0027: 0x001b, # ESCAPE
- 0x0028: 0x0088, # SET ATTRIBUTE
- 0x0029: 0x0089, # START FIELD EXTENDED
- 0x002a: 0x008a, # SET MODE OR SWITCH
- 0x002b: 0x008b, # CONTROL SEQUENCE PREFIX
- 0x002c: 0x008c, # MODIFY FIELD ATTRIBUTE
- 0x002d: 0x0005, # ENQUIRY
- 0x002e: 0x0006, # ACKNOWLEDGE
- 0x002f: 0x0007, # BELL
- 0x0030: 0x0090, # <reserved>
- 0x0031: 0x0091, # <reserved>
- 0x0032: 0x0016, # SYNCHRONOUS IDLE
- 0x0033: 0x0093, # INDEX RETURN
- 0x0034: 0x0094, # PRESENTATION POSITION
- 0x0035: 0x0095, # TRANSPARENT
- 0x0036: 0x0096, # NUMERIC BACKSPACE
- 0x0037: 0x0004, # END OF TRANSMISSION
- 0x0038: 0x0098, # SUBSCRIPT
- 0x0039: 0x0099, # INDENT TABULATION
- 0x003a: 0x009a, # REVERSE FORM FEED
- 0x003b: 0x009b, # CUSTOMER USE THREE
- 0x003c: 0x0014, # DEVICE CONTROL FOUR
- 0x003d: 0x0015, # NEGATIVE ACKNOWLEDGE
- 0x003e: 0x009e, # <reserved>
- 0x003f: 0x001a, # SUBSTITUTE
- 0x0040: 0x0020, # SPACE
- 0x0041: 0x05d0, # HEBREW LETTER ALEF
- 0x0042: 0x05d1, # HEBREW LETTER BET
- 0x0043: 0x05d2, # HEBREW LETTER GIMEL
- 0x0044: 0x05d3, # HEBREW LETTER DALET
- 0x0045: 0x05d4, # HEBREW LETTER HE
- 0x0046: 0x05d5, # HEBREW LETTER VAV
- 0x0047: 0x05d6, # HEBREW LETTER ZAYIN
- 0x0048: 0x05d7, # HEBREW LETTER HET
- 0x0049: 0x05d8, # HEBREW LETTER TET
- 0x004a: 0x00a2, # CENT SIGN
- 0x004b: 0x002e, # FULL STOP
- 0x004c: 0x003c, # LESS-THAN SIGN
- 0x004d: 0x0028, # LEFT PARENTHESIS
- 0x004e: 0x002b, # PLUS SIGN
- 0x004f: 0x007c, # VERTICAL LINE
- 0x0050: 0x0026, # AMPERSAND
- 0x0051: 0x05d9, # HEBREW LETTER YOD
- 0x0052: 0x05da, # HEBREW LETTER FINAL KAF
- 0x0053: 0x05db, # HEBREW LETTER KAF
- 0x0054: 0x05dc, # HEBREW LETTER LAMED
- 0x0055: 0x05dd, # HEBREW LETTER FINAL MEM
- 0x0056: 0x05de, # HEBREW LETTER MEM
- 0x0057: 0x05df, # HEBREW LETTER FINAL NUN
- 0x0058: 0x05e0, # HEBREW LETTER NUN
- 0x0059: 0x05e1, # HEBREW LETTER SAMEKH
- 0x005a: 0x0021, # EXCLAMATION MARK
- 0x005b: 0x0024, # DOLLAR SIGN
- 0x005c: 0x002a, # ASTERISK
- 0x005d: 0x0029, # RIGHT PARENTHESIS
- 0x005e: 0x003b, # SEMICOLON
- 0x005f: 0x00ac, # NOT SIGN
- 0x0060: 0x002d, # HYPHEN-MINUS
- 0x0061: 0x002f, # SOLIDUS
- 0x0062: 0x05e2, # HEBREW LETTER AYIN
- 0x0063: 0x05e3, # HEBREW LETTER FINAL PE
- 0x0064: 0x05e4, # HEBREW LETTER PE
- 0x0065: 0x05e5, # HEBREW LETTER FINAL TSADI
- 0x0066: 0x05e6, # HEBREW LETTER TSADI
- 0x0067: 0x05e7, # HEBREW LETTER QOF
- 0x0068: 0x05e8, # HEBREW LETTER RESH
- 0x0069: 0x05e9, # HEBREW LETTER SHIN
- 0x006a: 0x00a6, # BROKEN BAR
- 0x006b: 0x002c, # COMMA
- 0x006c: 0x0025, # PERCENT SIGN
- 0x006d: 0x005f, # LOW LINE
- 0x006e: 0x003e, # GREATER-THAN SIGN
- 0x006f: 0x003f, # QUESTION MARK
- 0x0070: None, # UNDEFINED
- 0x0071: 0x05ea, # HEBREW LETTER TAV
- 0x0072: None, # UNDEFINED
- 0x0073: None, # UNDEFINED
- 0x0074: 0x00a0, # NO-BREAK SPACE
- 0x0075: None, # UNDEFINED
- 0x0076: None, # UNDEFINED
- 0x0077: None, # UNDEFINED
- 0x0078: 0x2017, # DOUBLE LOW LINE
- 0x0079: 0x0060, # GRAVE ACCENT
- 0x007a: 0x003a, # COLON
- 0x007b: 0x0023, # NUMBER SIGN
- 0x007c: 0x0040, # COMMERCIAL AT
- 0x007d: 0x0027, # APOSTROPHE
- 0x007e: 0x003d, # EQUALS SIGN
- 0x007f: 0x0022, # QUOTATION MARK
- 0x0080: None, # UNDEFINED
- 0x0081: 0x0061, # LATIN SMALL LETTER A
- 0x0082: 0x0062, # LATIN SMALL LETTER B
- 0x0083: 0x0063, # LATIN SMALL LETTER C
- 0x0084: 0x0064, # LATIN SMALL LETTER D
- 0x0085: 0x0065, # LATIN SMALL LETTER E
- 0x0086: 0x0066, # LATIN SMALL LETTER F
- 0x0087: 0x0067, # LATIN SMALL LETTER G
- 0x0088: 0x0068, # LATIN SMALL LETTER H
- 0x0089: 0x0069, # LATIN SMALL LETTER I
- 0x008a: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x008b: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
- 0x008c: None, # UNDEFINED
- 0x008d: None, # UNDEFINED
- 0x008e: None, # UNDEFINED
- 0x008f: 0x00b1, # PLUS-MINUS SIGN
- 0x0090: 0x00b0, # DEGREE SIGN
- 0x0091: 0x006a, # LATIN SMALL LETTER J
- 0x0092: 0x006b, # LATIN SMALL LETTER K
- 0x0093: 0x006c, # LATIN SMALL LETTER L
- 0x0094: 0x006d, # LATIN SMALL LETTER M
- 0x0095: 0x006e, # LATIN SMALL LETTER N
- 0x0096: 0x006f, # LATIN SMALL LETTER O
- 0x0097: 0x0070, # LATIN SMALL LETTER P
- 0x0098: 0x0071, # LATIN SMALL LETTER Q
- 0x0099: 0x0072, # LATIN SMALL LETTER R
- 0x009a: None, # UNDEFINED
- 0x009b: None, # UNDEFINED
- 0x009c: None, # UNDEFINED
- 0x009d: 0x00b8, # CEDILLA
- 0x009e: None, # UNDEFINED
- 0x009f: 0x00a4, # CURRENCY SIGN
- 0x00a0: 0x00b5, # MICRO SIGN
- 0x00a1: 0x007e, # TILDE
- 0x00a2: 0x0073, # LATIN SMALL LETTER S
- 0x00a3: 0x0074, # LATIN SMALL LETTER T
- 0x00a4: 0x0075, # LATIN SMALL LETTER U
- 0x00a5: 0x0076, # LATIN SMALL LETTER V
- 0x00a6: 0x0077, # LATIN SMALL LETTER W
- 0x00a7: 0x0078, # LATIN SMALL LETTER X
- 0x00a8: 0x0079, # LATIN SMALL LETTER Y
- 0x00a9: 0x007a, # LATIN SMALL LETTER Z
- 0x00aa: None, # UNDEFINED
- 0x00ab: None, # UNDEFINED
- 0x00ac: None, # UNDEFINED
- 0x00ad: None, # UNDEFINED
- 0x00ae: None, # UNDEFINED
- 0x00af: 0x00ae, # REGISTERED SIGN
- 0x00b0: 0x005e, # CIRCUMFLEX ACCENT
- 0x00b1: 0x00a3, # POUND SIGN
- 0x00b2: 0x00a5, # YEN SIGN
- 0x00b3: 0x00b7, # MIDDLE DOT
- 0x00b4: 0x00a9, # COPYRIGHT SIGN
- 0x00b5: 0x00a7, # SECTION SIGN
- 0x00b7: 0x00bc, # VULGAR FRACTION ONE QUARTER
- 0x00b8: 0x00bd, # VULGAR FRACTION ONE HALF
- 0x00b9: 0x00be, # VULGAR FRACTION THREE QUARTERS
- 0x00ba: 0x005b, # LEFT SQUARE BRACKET
- 0x00bb: 0x005d, # RIGHT SQUARE BRACKET
- 0x00bc: 0x00af, # MACRON
- 0x00bd: 0x00a8, # DIAERESIS
- 0x00be: 0x00b4, # ACUTE ACCENT
- 0x00bf: 0x00d7, # MULTIPLICATION SIGN
- 0x00c0: 0x007b, # LEFT CURLY BRACKET
- 0x00c1: 0x0041, # LATIN CAPITAL LETTER A
- 0x00c2: 0x0042, # LATIN CAPITAL LETTER B
- 0x00c3: 0x0043, # LATIN CAPITAL LETTER C
- 0x00c4: 0x0044, # LATIN CAPITAL LETTER D
- 0x00c5: 0x0045, # LATIN CAPITAL LETTER E
- 0x00c6: 0x0046, # LATIN CAPITAL LETTER F
- 0x00c7: 0x0047, # LATIN CAPITAL LETTER G
- 0x00c8: 0x0048, # LATIN CAPITAL LETTER H
- 0x00c9: 0x0049, # LATIN CAPITAL LETTER I
- 0x00ca: 0x00ad, # SOFT HYPHEN
- 0x00cb: None, # UNDEFINED
- 0x00cc: None, # UNDEFINED
- 0x00cd: None, # UNDEFINED
- 0x00ce: None, # UNDEFINED
- 0x00cf: None, # UNDEFINED
- 0x00d0: 0x007d, # RIGHT CURLY BRACKET
- 0x00d1: 0x004a, # LATIN CAPITAL LETTER J
- 0x00d2: 0x004b, # LATIN CAPITAL LETTER K
- 0x00d3: 0x004c, # LATIN CAPITAL LETTER L
- 0x00d4: 0x004d, # LATIN CAPITAL LETTER M
- 0x00d5: 0x004e, # LATIN CAPITAL LETTER N
- 0x00d6: 0x004f, # LATIN CAPITAL LETTER O
- 0x00d7: 0x0050, # LATIN CAPITAL LETTER P
- 0x00d8: 0x0051, # LATIN CAPITAL LETTER Q
- 0x00d9: 0x0052, # LATIN CAPITAL LETTER R
- 0x00da: 0x00b9, # SUPERSCRIPT ONE
- 0x00db: None, # UNDEFINED
- 0x00dc: None, # UNDEFINED
- 0x00dd: None, # UNDEFINED
- 0x00de: None, # UNDEFINED
- 0x00df: None, # UNDEFINED
- 0x00e0: 0x005c, # REVERSE SOLIDUS
- 0x00e1: 0x00f7, # DIVISION SIGN
- 0x00e2: 0x0053, # LATIN CAPITAL LETTER S
- 0x00e3: 0x0054, # LATIN CAPITAL LETTER T
- 0x00e4: 0x0055, # LATIN CAPITAL LETTER U
- 0x00e5: 0x0056, # LATIN CAPITAL LETTER V
- 0x00e6: 0x0057, # LATIN CAPITAL LETTER W
- 0x00e7: 0x0058, # LATIN CAPITAL LETTER X
- 0x00e8: 0x0059, # LATIN CAPITAL LETTER Y
- 0x00e9: 0x005a, # LATIN CAPITAL LETTER Z
- 0x00ea: 0x00b2, # SUPERSCRIPT TWO
- 0x00eb: None, # UNDEFINED
- 0x00ec: None, # UNDEFINED
- 0x00ed: None, # UNDEFINED
- 0x00ee: None, # UNDEFINED
- 0x00ef: None, # UNDEFINED
- 0x00f0: 0x0030, # DIGIT ZERO
- 0x00f1: 0x0031, # DIGIT ONE
- 0x00f2: 0x0032, # DIGIT TWO
- 0x00f3: 0x0033, # DIGIT THREE
- 0x00f4: 0x0034, # DIGIT FOUR
- 0x00f5: 0x0035, # DIGIT FIVE
- 0x00f6: 0x0036, # DIGIT SIX
- 0x00f7: 0x0037, # DIGIT SEVEN
- 0x00f8: 0x0038, # DIGIT EIGHT
- 0x00f9: 0x0039, # DIGIT NINE
- 0x00fa: 0x00b3, # SUPERSCRIPT THREE
- 0x00fb: None, # UNDEFINED
- 0x00fc: None, # UNDEFINED
- 0x00fd: None, # UNDEFINED
- 0x00fe: None, # UNDEFINED
- 0x00ff: 0x009f, # EIGHT ONES
+ 0x0004: 0x009c, # SELECT
+ 0x0005: 0x0009, # HORIZONTAL TABULATION
+ 0x0006: 0x0086, # REQUIRED NEW LINE
+ 0x0007: 0x007f, # DELETE
+ 0x0008: 0x0097, # GRAPHIC ESCAPE
+ 0x0009: 0x008d, # SUPERSCRIPT
+ 0x000a: 0x008e, # REPEAT
+ 0x0014: 0x009d, # RESTORE/ENABLE PRESENTATION
+ 0x0015: 0x0085, # NEW LINE
+ 0x0016: 0x0008, # BACKSPACE
+ 0x0017: 0x0087, # PROGRAM OPERATOR COMMUNICATION
+ 0x001a: 0x0092, # UNIT BACK SPACE
+ 0x001b: 0x008f, # CUSTOMER USE ONE
+ 0x0020: 0x0080, # DIGIT SELECT
+ 0x0021: 0x0081, # START OF SIGNIFICANCE
+ 0x0022: 0x0082, # FIELD SEPARATOR
+ 0x0023: 0x0083, # WORD UNDERSCORE
+ 0x0024: 0x0084, # BYPASS OR INHIBIT PRESENTATION
+ 0x0025: 0x000a, # LINE FEED
+ 0x0026: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0027: 0x001b, # ESCAPE
+ 0x0028: 0x0088, # SET ATTRIBUTE
+ 0x0029: 0x0089, # START FIELD EXTENDED
+ 0x002a: 0x008a, # SET MODE OR SWITCH
+ 0x002b: 0x008b, # CONTROL SEQUENCE PREFIX
+ 0x002c: 0x008c, # MODIFY FIELD ATTRIBUTE
+ 0x002d: 0x0005, # ENQUIRY
+ 0x002e: 0x0006, # ACKNOWLEDGE
+ 0x002f: 0x0007, # BELL
+ 0x0030: 0x0090, # <reserved>
+ 0x0031: 0x0091, # <reserved>
+ 0x0032: 0x0016, # SYNCHRONOUS IDLE
+ 0x0033: 0x0093, # INDEX RETURN
+ 0x0034: 0x0094, # PRESENTATION POSITION
+ 0x0035: 0x0095, # TRANSPARENT
+ 0x0036: 0x0096, # NUMERIC BACKSPACE
+ 0x0037: 0x0004, # END OF TRANSMISSION
+ 0x0038: 0x0098, # SUBSCRIPT
+ 0x0039: 0x0099, # INDENT TABULATION
+ 0x003a: 0x009a, # REVERSE FORM FEED
+ 0x003b: 0x009b, # CUSTOMER USE THREE
+ 0x003c: 0x0014, # DEVICE CONTROL FOUR
+ 0x003d: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x003e: 0x009e, # <reserved>
+ 0x003f: 0x001a, # SUBSTITUTE
+ 0x0040: 0x0020, # SPACE
+ 0x0041: 0x05d0, # HEBREW LETTER ALEF
+ 0x0042: 0x05d1, # HEBREW LETTER BET
+ 0x0043: 0x05d2, # HEBREW LETTER GIMEL
+ 0x0044: 0x05d3, # HEBREW LETTER DALET
+ 0x0045: 0x05d4, # HEBREW LETTER HE
+ 0x0046: 0x05d5, # HEBREW LETTER VAV
+ 0x0047: 0x05d6, # HEBREW LETTER ZAYIN
+ 0x0048: 0x05d7, # HEBREW LETTER HET
+ 0x0049: 0x05d8, # HEBREW LETTER TET
+ 0x004a: 0x00a2, # CENT SIGN
+ 0x004b: 0x002e, # FULL STOP
+ 0x004c: 0x003c, # LESS-THAN SIGN
+ 0x004d: 0x0028, # LEFT PARENTHESIS
+ 0x004e: 0x002b, # PLUS SIGN
+ 0x004f: 0x007c, # VERTICAL LINE
+ 0x0050: 0x0026, # AMPERSAND
+ 0x0051: 0x05d9, # HEBREW LETTER YOD
+ 0x0052: 0x05da, # HEBREW LETTER FINAL KAF
+ 0x0053: 0x05db, # HEBREW LETTER KAF
+ 0x0054: 0x05dc, # HEBREW LETTER LAMED
+ 0x0055: 0x05dd, # HEBREW LETTER FINAL MEM
+ 0x0056: 0x05de, # HEBREW LETTER MEM
+ 0x0057: 0x05df, # HEBREW LETTER FINAL NUN
+ 0x0058: 0x05e0, # HEBREW LETTER NUN
+ 0x0059: 0x05e1, # HEBREW LETTER SAMEKH
+ 0x005a: 0x0021, # EXCLAMATION MARK
+ 0x005b: 0x0024, # DOLLAR SIGN
+ 0x005c: 0x002a, # ASTERISK
+ 0x005d: 0x0029, # RIGHT PARENTHESIS
+ 0x005e: 0x003b, # SEMICOLON
+ 0x005f: 0x00ac, # NOT SIGN
+ 0x0060: 0x002d, # HYPHEN-MINUS
+ 0x0061: 0x002f, # SOLIDUS
+ 0x0062: 0x05e2, # HEBREW LETTER AYIN
+ 0x0063: 0x05e3, # HEBREW LETTER FINAL PE
+ 0x0064: 0x05e4, # HEBREW LETTER PE
+ 0x0065: 0x05e5, # HEBREW LETTER FINAL TSADI
+ 0x0066: 0x05e6, # HEBREW LETTER TSADI
+ 0x0067: 0x05e7, # HEBREW LETTER QOF
+ 0x0068: 0x05e8, # HEBREW LETTER RESH
+ 0x0069: 0x05e9, # HEBREW LETTER SHIN
+ 0x006a: 0x00a6, # BROKEN BAR
+ 0x006b: 0x002c, # COMMA
+ 0x006c: 0x0025, # PERCENT SIGN
+ 0x006d: 0x005f, # LOW LINE
+ 0x006e: 0x003e, # GREATER-THAN SIGN
+ 0x006f: 0x003f, # QUESTION MARK
+ 0x0070: None, # UNDEFINED
+ 0x0071: 0x05ea, # HEBREW LETTER TAV
+ 0x0072: None, # UNDEFINED
+ 0x0073: None, # UNDEFINED
+ 0x0074: 0x00a0, # NO-BREAK SPACE
+ 0x0075: None, # UNDEFINED
+ 0x0076: None, # UNDEFINED
+ 0x0077: None, # UNDEFINED
+ 0x0078: 0x2017, # DOUBLE LOW LINE
+ 0x0079: 0x0060, # GRAVE ACCENT
+ 0x007a: 0x003a, # COLON
+ 0x007b: 0x0023, # NUMBER SIGN
+ 0x007c: 0x0040, # COMMERCIAL AT
+ 0x007d: 0x0027, # APOSTROPHE
+ 0x007e: 0x003d, # EQUALS SIGN
+ 0x007f: 0x0022, # QUOTATION MARK
+ 0x0080: None, # UNDEFINED
+ 0x0081: 0x0061, # LATIN SMALL LETTER A
+ 0x0082: 0x0062, # LATIN SMALL LETTER B
+ 0x0083: 0x0063, # LATIN SMALL LETTER C
+ 0x0084: 0x0064, # LATIN SMALL LETTER D
+ 0x0085: 0x0065, # LATIN SMALL LETTER E
+ 0x0086: 0x0066, # LATIN SMALL LETTER F
+ 0x0087: 0x0067, # LATIN SMALL LETTER G
+ 0x0088: 0x0068, # LATIN SMALL LETTER H
+ 0x0089: 0x0069, # LATIN SMALL LETTER I
+ 0x008a: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x008b: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x008c: None, # UNDEFINED
+ 0x008d: None, # UNDEFINED
+ 0x008e: None, # UNDEFINED
+ 0x008f: 0x00b1, # PLUS-MINUS SIGN
+ 0x0090: 0x00b0, # DEGREE SIGN
+ 0x0091: 0x006a, # LATIN SMALL LETTER J
+ 0x0092: 0x006b, # LATIN SMALL LETTER K
+ 0x0093: 0x006c, # LATIN SMALL LETTER L
+ 0x0094: 0x006d, # LATIN SMALL LETTER M
+ 0x0095: 0x006e, # LATIN SMALL LETTER N
+ 0x0096: 0x006f, # LATIN SMALL LETTER O
+ 0x0097: 0x0070, # LATIN SMALL LETTER P
+ 0x0098: 0x0071, # LATIN SMALL LETTER Q
+ 0x0099: 0x0072, # LATIN SMALL LETTER R
+ 0x009a: None, # UNDEFINED
+ 0x009b: None, # UNDEFINED
+ 0x009c: None, # UNDEFINED
+ 0x009d: 0x00b8, # CEDILLA
+ 0x009e: None, # UNDEFINED
+ 0x009f: 0x00a4, # CURRENCY SIGN
+ 0x00a0: 0x00b5, # MICRO SIGN
+ 0x00a1: 0x007e, # TILDE
+ 0x00a2: 0x0073, # LATIN SMALL LETTER S
+ 0x00a3: 0x0074, # LATIN SMALL LETTER T
+ 0x00a4: 0x0075, # LATIN SMALL LETTER U
+ 0x00a5: 0x0076, # LATIN SMALL LETTER V
+ 0x00a6: 0x0077, # LATIN SMALL LETTER W
+ 0x00a7: 0x0078, # LATIN SMALL LETTER X
+ 0x00a8: 0x0079, # LATIN SMALL LETTER Y
+ 0x00a9: 0x007a, # LATIN SMALL LETTER Z
+ 0x00aa: None, # UNDEFINED
+ 0x00ab: None, # UNDEFINED
+ 0x00ac: None, # UNDEFINED
+ 0x00ad: None, # UNDEFINED
+ 0x00ae: None, # UNDEFINED
+ 0x00af: 0x00ae, # REGISTERED SIGN
+ 0x00b0: 0x005e, # CIRCUMFLEX ACCENT
+ 0x00b1: 0x00a3, # POUND SIGN
+ 0x00b2: 0x00a5, # YEN SIGN
+ 0x00b3: 0x00b7, # MIDDLE DOT
+ 0x00b4: 0x00a9, # COPYRIGHT SIGN
+ 0x00b5: 0x00a7, # SECTION SIGN
+ 0x00b7: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00b8: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00b9: 0x00be, # VULGAR FRACTION THREE QUARTERS
+ 0x00ba: 0x005b, # LEFT SQUARE BRACKET
+ 0x00bb: 0x005d, # RIGHT SQUARE BRACKET
+ 0x00bc: 0x00af, # MACRON
+ 0x00bd: 0x00a8, # DIAERESIS
+ 0x00be: 0x00b4, # ACUTE ACCENT
+ 0x00bf: 0x00d7, # MULTIPLICATION SIGN
+ 0x00c0: 0x007b, # LEFT CURLY BRACKET
+ 0x00c1: 0x0041, # LATIN CAPITAL LETTER A
+ 0x00c2: 0x0042, # LATIN CAPITAL LETTER B
+ 0x00c3: 0x0043, # LATIN CAPITAL LETTER C
+ 0x00c4: 0x0044, # LATIN CAPITAL LETTER D
+ 0x00c5: 0x0045, # LATIN CAPITAL LETTER E
+ 0x00c6: 0x0046, # LATIN CAPITAL LETTER F
+ 0x00c7: 0x0047, # LATIN CAPITAL LETTER G
+ 0x00c8: 0x0048, # LATIN CAPITAL LETTER H
+ 0x00c9: 0x0049, # LATIN CAPITAL LETTER I
+ 0x00ca: 0x00ad, # SOFT HYPHEN
+ 0x00cb: None, # UNDEFINED
+ 0x00cc: None, # UNDEFINED
+ 0x00cd: None, # UNDEFINED
+ 0x00ce: None, # UNDEFINED
+ 0x00cf: None, # UNDEFINED
+ 0x00d0: 0x007d, # RIGHT CURLY BRACKET
+ 0x00d1: 0x004a, # LATIN CAPITAL LETTER J
+ 0x00d2: 0x004b, # LATIN CAPITAL LETTER K
+ 0x00d3: 0x004c, # LATIN CAPITAL LETTER L
+ 0x00d4: 0x004d, # LATIN CAPITAL LETTER M
+ 0x00d5: 0x004e, # LATIN CAPITAL LETTER N
+ 0x00d6: 0x004f, # LATIN CAPITAL LETTER O
+ 0x00d7: 0x0050, # LATIN CAPITAL LETTER P
+ 0x00d8: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x00d9: 0x0052, # LATIN CAPITAL LETTER R
+ 0x00da: 0x00b9, # SUPERSCRIPT ONE
+ 0x00db: None, # UNDEFINED
+ 0x00dc: None, # UNDEFINED
+ 0x00dd: None, # UNDEFINED
+ 0x00de: None, # UNDEFINED
+ 0x00df: None, # UNDEFINED
+ 0x00e0: 0x005c, # REVERSE SOLIDUS
+ 0x00e1: 0x00f7, # DIVISION SIGN
+ 0x00e2: 0x0053, # LATIN CAPITAL LETTER S
+ 0x00e3: 0x0054, # LATIN CAPITAL LETTER T
+ 0x00e4: 0x0055, # LATIN CAPITAL LETTER U
+ 0x00e5: 0x0056, # LATIN CAPITAL LETTER V
+ 0x00e6: 0x0057, # LATIN CAPITAL LETTER W
+ 0x00e7: 0x0058, # LATIN CAPITAL LETTER X
+ 0x00e8: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x00e9: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x00ea: 0x00b2, # SUPERSCRIPT TWO
+ 0x00eb: None, # UNDEFINED
+ 0x00ec: None, # UNDEFINED
+ 0x00ed: None, # UNDEFINED
+ 0x00ee: None, # UNDEFINED
+ 0x00ef: None, # UNDEFINED
+ 0x00f0: 0x0030, # DIGIT ZERO
+ 0x00f1: 0x0031, # DIGIT ONE
+ 0x00f2: 0x0032, # DIGIT TWO
+ 0x00f3: 0x0033, # DIGIT THREE
+ 0x00f4: 0x0034, # DIGIT FOUR
+ 0x00f5: 0x0035, # DIGIT FIVE
+ 0x00f6: 0x0036, # DIGIT SIX
+ 0x00f7: 0x0037, # DIGIT SEVEN
+ 0x00f8: 0x0038, # DIGIT EIGHT
+ 0x00f9: 0x0039, # DIGIT NINE
+ 0x00fa: 0x00b3, # SUPERSCRIPT THREE
+ 0x00fb: None, # UNDEFINED
+ 0x00fc: None, # UNDEFINED
+ 0x00fd: None, # UNDEFINED
+ 0x00fe: None, # UNDEFINED
+ 0x00ff: 0x009f, # EIGHT ONES
})
+### 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 -> SELECT
+ u'\t' # 0x0005 -> HORIZONTAL TABULATION
+ u'\x86' # 0x0006 -> REQUIRED NEW LINE
+ u'\x7f' # 0x0007 -> DELETE
+ u'\x97' # 0x0008 -> GRAPHIC ESCAPE
+ u'\x8d' # 0x0009 -> SUPERSCRIPT
+ u'\x8e' # 0x000a -> REPEAT
+ 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 -> RESTORE/ENABLE PRESENTATION
+ u'\x85' # 0x0015 -> NEW LINE
+ u'\x08' # 0x0016 -> BACKSPACE
+ u'\x87' # 0x0017 -> PROGRAM OPERATOR COMMUNICATION
+ u'\x18' # 0x0018 -> CANCEL
+ u'\x19' # 0x0019 -> END OF MEDIUM
+ u'\x92' # 0x001a -> UNIT BACK SPACE
+ u'\x8f' # 0x001b -> CUSTOMER USE ONE
+ u'\x1c' # 0x001c -> FILE SEPARATOR
+ u'\x1d' # 0x001d -> GROUP SEPARATOR
+ u'\x1e' # 0x001e -> RECORD SEPARATOR
+ u'\x1f' # 0x001f -> UNIT SEPARATOR
+ u'\x80' # 0x0020 -> DIGIT SELECT
+ u'\x81' # 0x0021 -> START OF SIGNIFICANCE
+ u'\x82' # 0x0022 -> FIELD SEPARATOR
+ u'\x83' # 0x0023 -> WORD UNDERSCORE
+ u'\x84' # 0x0024 -> BYPASS OR INHIBIT PRESENTATION
+ u'\n' # 0x0025 -> LINE FEED
+ u'\x17' # 0x0026 -> END OF TRANSMISSION BLOCK
+ u'\x1b' # 0x0027 -> ESCAPE
+ u'\x88' # 0x0028 -> SET ATTRIBUTE
+ u'\x89' # 0x0029 -> START FIELD EXTENDED
+ u'\x8a' # 0x002a -> SET MODE OR SWITCH
+ u'\x8b' # 0x002b -> CONTROL SEQUENCE PREFIX
+ u'\x8c' # 0x002c -> MODIFY FIELD ATTRIBUTE
+ u'\x05' # 0x002d -> ENQUIRY
+ u'\x06' # 0x002e -> ACKNOWLEDGE
+ u'\x07' # 0x002f -> BELL
+ u'\x90' # 0x0030 -> <reserved>
+ u'\x91' # 0x0031 -> <reserved>
+ u'\x16' # 0x0032 -> SYNCHRONOUS IDLE
+ u'\x93' # 0x0033 -> INDEX RETURN
+ u'\x94' # 0x0034 -> PRESENTATION POSITION
+ u'\x95' # 0x0035 -> TRANSPARENT
+ u'\x96' # 0x0036 -> NUMERIC BACKSPACE
+ u'\x04' # 0x0037 -> END OF TRANSMISSION
+ u'\x98' # 0x0038 -> SUBSCRIPT
+ u'\x99' # 0x0039 -> INDENT TABULATION
+ u'\x9a' # 0x003a -> REVERSE FORM FEED
+ u'\x9b' # 0x003b -> CUSTOMER USE THREE
+ u'\x14' # 0x003c -> DEVICE CONTROL FOUR
+ u'\x15' # 0x003d -> NEGATIVE ACKNOWLEDGE
+ u'\x9e' # 0x003e -> <reserved>
+ u'\x1a' # 0x003f -> SUBSTITUTE
+ u' ' # 0x0040 -> SPACE
+ u'\u05d0' # 0x0041 -> HEBREW LETTER ALEF
+ u'\u05d1' # 0x0042 -> HEBREW LETTER BET
+ u'\u05d2' # 0x0043 -> HEBREW LETTER GIMEL
+ u'\u05d3' # 0x0044 -> HEBREW LETTER DALET
+ u'\u05d4' # 0x0045 -> HEBREW LETTER HE
+ u'\u05d5' # 0x0046 -> HEBREW LETTER VAV
+ u'\u05d6' # 0x0047 -> HEBREW LETTER ZAYIN
+ u'\u05d7' # 0x0048 -> HEBREW LETTER HET
+ u'\u05d8' # 0x0049 -> HEBREW LETTER TET
+ 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'\u05d9' # 0x0051 -> HEBREW LETTER YOD
+ u'\u05da' # 0x0052 -> HEBREW LETTER FINAL KAF
+ u'\u05db' # 0x0053 -> HEBREW LETTER KAF
+ u'\u05dc' # 0x0054 -> HEBREW LETTER LAMED
+ u'\u05dd' # 0x0055 -> HEBREW LETTER FINAL MEM
+ u'\u05de' # 0x0056 -> HEBREW LETTER MEM
+ u'\u05df' # 0x0057 -> HEBREW LETTER FINAL NUN
+ u'\u05e0' # 0x0058 -> HEBREW LETTER NUN
+ u'\u05e1' # 0x0059 -> HEBREW LETTER SAMEKH
+ 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'\u05e2' # 0x0062 -> HEBREW LETTER AYIN
+ u'\u05e3' # 0x0063 -> HEBREW LETTER FINAL PE
+ u'\u05e4' # 0x0064 -> HEBREW LETTER PE
+ u'\u05e5' # 0x0065 -> HEBREW LETTER FINAL TSADI
+ u'\u05e6' # 0x0066 -> HEBREW LETTER TSADI
+ u'\u05e7' # 0x0067 -> HEBREW LETTER QOF
+ u'\u05e8' # 0x0068 -> HEBREW LETTER RESH
+ u'\u05e9' # 0x0069 -> HEBREW LETTER SHIN
+ 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'\ufffe' # 0x0070 -> UNDEFINED
+ u'\u05ea' # 0x0071 -> HEBREW LETTER TAV
+ u'\ufffe' # 0x0072 -> UNDEFINED
+ u'\ufffe' # 0x0073 -> UNDEFINED
+ u'\xa0' # 0x0074 -> NO-BREAK SPACE
+ u'\ufffe' # 0x0075 -> UNDEFINED
+ u'\ufffe' # 0x0076 -> UNDEFINED
+ u'\ufffe' # 0x0077 -> UNDEFINED
+ u'\u2017' # 0x0078 -> DOUBLE LOW LINE
+ 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'\ufffe' # 0x0080 -> UNDEFINED
+ 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'\ufffe' # 0x008c -> UNDEFINED
+ u'\ufffe' # 0x008d -> UNDEFINED
+ u'\ufffe' # 0x008e -> UNDEFINED
+ 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'\ufffe' # 0x009a -> UNDEFINED
+ u'\ufffe' # 0x009b -> UNDEFINED
+ u'\ufffe' # 0x009c -> UNDEFINED
+ u'\xb8' # 0x009d -> CEDILLA
+ u'\ufffe' # 0x009e -> UNDEFINED
+ 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'\ufffe' # 0x00aa -> UNDEFINED
+ u'\ufffe' # 0x00ab -> UNDEFINED
+ u'\ufffe' # 0x00ac -> UNDEFINED
+ u'\ufffe' # 0x00ad -> UNDEFINED
+ u'\ufffe' # 0x00ae -> UNDEFINED
+ 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'\ufffe' # 0x00cb -> UNDEFINED
+ u'\ufffe' # 0x00cc -> UNDEFINED
+ u'\ufffe' # 0x00cd -> UNDEFINED
+ u'\ufffe' # 0x00ce -> UNDEFINED
+ u'\ufffe' # 0x00cf -> UNDEFINED
+ 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'\ufffe' # 0x00db -> UNDEFINED
+ u'\ufffe' # 0x00dc -> UNDEFINED
+ u'\ufffe' # 0x00dd -> UNDEFINED
+ u'\ufffe' # 0x00de -> UNDEFINED
+ u'\ufffe' # 0x00df -> UNDEFINED
+ 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'\ufffe' # 0x00eb -> UNDEFINED
+ u'\ufffe' # 0x00ec -> UNDEFINED
+ u'\ufffe' # 0x00ed -> UNDEFINED
+ u'\ufffe' # 0x00ee -> UNDEFINED
+ u'\ufffe' # 0x00ef -> UNDEFINED
+ 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'\ufffe' # 0x00fb -> UNDEFINED
+ u'\ufffe' # 0x00fc -> UNDEFINED
+ u'\ufffe' # 0x00fd -> UNDEFINED
+ u'\ufffe' # 0x00fe -> UNDEFINED
+ u'\x9f' # 0x00ff -> EIGHT ONES
+)
+
### 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, # DIGIT SELECT
+ 0x0081: 0x0021, # START OF SIGNIFICANCE
+ 0x0082: 0x0022, # FIELD SEPARATOR
+ 0x0083: 0x0023, # WORD UNDERSCORE
+ 0x0084: 0x0024, # BYPASS OR INHIBIT PRESENTATION
+ 0x0085: 0x0015, # NEW LINE
+ 0x0086: 0x0006, # REQUIRED NEW LINE
+ 0x0087: 0x0017, # PROGRAM OPERATOR COMMUNICATION
+ 0x0088: 0x0028, # SET ATTRIBUTE
+ 0x0089: 0x0029, # START FIELD EXTENDED
+ 0x008a: 0x002a, # SET MODE OR SWITCH
+ 0x008b: 0x002b, # CONTROL SEQUENCE PREFIX
+ 0x008c: 0x002c, # MODIFY FIELD ATTRIBUTE
+ 0x008d: 0x0009, # SUPERSCRIPT
+ 0x008e: 0x000a, # REPEAT
+ 0x008f: 0x001b, # CUSTOMER USE ONE
+ 0x0090: 0x0030, # <reserved>
+ 0x0091: 0x0031, # <reserved>
+ 0x0092: 0x001a, # UNIT BACK SPACE
+ 0x0093: 0x0033, # INDEX RETURN
+ 0x0094: 0x0034, # PRESENTATION POSITION
+ 0x0095: 0x0035, # TRANSPARENT
+ 0x0096: 0x0036, # NUMERIC BACKSPACE
+ 0x0097: 0x0008, # GRAPHIC ESCAPE
+ 0x0098: 0x0038, # SUBSCRIPT
+ 0x0099: 0x0039, # INDENT TABULATION
+ 0x009a: 0x003a, # REVERSE FORM FEED
+ 0x009b: 0x003b, # CUSTOMER USE THREE
+ 0x009c: 0x0004, # SELECT
+ 0x009d: 0x0014, # RESTORE/ENABLE PRESENTATION
+ 0x009e: 0x003e, # <reserved>
+ 0x009f: 0x00ff, # EIGHT ONES
+ 0x00a0: 0x0074, # NO-BREAK SPACE
+ 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
+ 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
+ 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
+ 0x00d7: 0x00bf, # MULTIPLICATION SIGN
+ 0x00f7: 0x00e1, # DIVISION SIGN
+ 0x05d0: 0x0041, # HEBREW LETTER ALEF
+ 0x05d1: 0x0042, # HEBREW LETTER BET
+ 0x05d2: 0x0043, # HEBREW LETTER GIMEL
+ 0x05d3: 0x0044, # HEBREW LETTER DALET
+ 0x05d4: 0x0045, # HEBREW LETTER HE
+ 0x05d5: 0x0046, # HEBREW LETTER VAV
+ 0x05d6: 0x0047, # HEBREW LETTER ZAYIN
+ 0x05d7: 0x0048, # HEBREW LETTER HET
+ 0x05d8: 0x0049, # HEBREW LETTER TET
+ 0x05d9: 0x0051, # HEBREW LETTER YOD
+ 0x05da: 0x0052, # HEBREW LETTER FINAL KAF
+ 0x05db: 0x0053, # HEBREW LETTER KAF
+ 0x05dc: 0x0054, # HEBREW LETTER LAMED
+ 0x05dd: 0x0055, # HEBREW LETTER FINAL MEM
+ 0x05de: 0x0056, # HEBREW LETTER MEM
+ 0x05df: 0x0057, # HEBREW LETTER FINAL NUN
+ 0x05e0: 0x0058, # HEBREW LETTER NUN
+ 0x05e1: 0x0059, # HEBREW LETTER SAMEKH
+ 0x05e2: 0x0062, # HEBREW LETTER AYIN
+ 0x05e3: 0x0063, # HEBREW LETTER FINAL PE
+ 0x05e4: 0x0064, # HEBREW LETTER PE
+ 0x05e5: 0x0065, # HEBREW LETTER FINAL TSADI
+ 0x05e6: 0x0066, # HEBREW LETTER TSADI
+ 0x05e7: 0x0067, # HEBREW LETTER QOF
+ 0x05e8: 0x0068, # HEBREW LETTER RESH
+ 0x05e9: 0x0069, # HEBREW LETTER SHIN
+ 0x05ea: 0x0071, # HEBREW LETTER TAV
+ 0x2017: 0x0078, # DOUBLE LOW LINE
+} \ No newline at end of file