Whitespace normalization.

This commit is contained in:
Tim Peters 2005-12-25 23:18:31 +00:00
parent 83a8c393b0
commit 536cf99536
82 changed files with 33875 additions and 33923 deletions

View File

@ -253,10 +253,10 @@ class SimpleXMLRPCDispatcher:
response = self._dispatch(method, params)
# wrap response in a singleton tuple
response = (response,)
response = xmlrpclib.dumps(response, methodresponse=1,
response = xmlrpclib.dumps(response, methodresponse=1,
allow_none=self.allow_none, encoding=self.encoding)
except Fault, fault:
response = xmlrpclib.dumps(fault, allow_none=self.allow_none,
response = xmlrpclib.dumps(fault, allow_none=self.allow_none,
encoding=self.encoding)
except:
# report exception back to server
@ -427,8 +427,8 @@ class SimpleXMLRPCRequestHandler(BaseHTTPServer.BaseHTTPRequestHandler):
"""
try:
# Get arguments by reading body of request.
# We read this in chunks to avoid straining
# Get arguments by reading body of request.
# We read this in chunks to avoid straining
# socket.read(); around the 10 or 15Mb mark, some platforms
# begin to have problems (bug #792570).
max_chunk_size = 10*1024*1024
@ -490,8 +490,8 @@ class SimpleXMLRPCServer(SocketServer.TCPServer,
SimpleXMLRPCDispatcher.__init__(self, allow_none, encoding)
SocketServer.TCPServer.__init__(self, addr, requestHandler)
# [Bug #1222790] If possible, set close-on-exec flag; if a
# method spawns a subprocess, the subprocess shouldn't have
# [Bug #1222790] If possible, set close-on-exec flag; if a
# method spawns a subprocess, the subprocess shouldn't have
# the listening socket open.
if hasattr(fcntl, 'FD_CLOEXEC'):
flags = fcntl.fcntl(self.fileno(), fcntl.F_GETFD)

View File

@ -269,7 +269,7 @@ class StreamReader(Codec):
if self.linebuffer:
self.charbuffer = "".join(self.linebuffer)
self.linebuffer = None
# read until we get the required number of characters (if available)
while True:
# can the request can be satisfied from the character buffer?
@ -335,7 +335,7 @@ class StreamReader(Codec):
if not keepends:
line = line.splitlines(False)[0]
return line
readsize = size or 72
line = ""
# If size is given, we call read() only once

View File

@ -1528,7 +1528,7 @@ class CookieJar:
for cookie in cookies:
if cookie.version == 1:
cookie.rfc2109 = True
if rfc2109_as_ns:
if rfc2109_as_ns:
# treat 2109 cookies as Netscape cookies rather than
# as RFC2965 cookies
cookie.version = 0

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -15,7 +15,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter):
pass
@ -32,499 +32,498 @@ def getregentry():
### Decoding Table
decoding_table = (
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\u20ac' # 0x80 -> EURO SIGN
u'\ufffe' # 0x81 -> UNDEFINED
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
u'\u2020' # 0x86 -> DAGGER
u'\u2021' # 0x87 -> DOUBLE DAGGER
u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
u'\u2030' # 0x89 -> PER MILLE SIGN
u'\ufffe' # 0x8A -> UNDEFINED
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
u'\ufffe' # 0x8C -> UNDEFINED
u'\ufffe' # 0x8D -> UNDEFINED
u'\ufffe' # 0x8E -> UNDEFINED
u'\ufffe' # 0x8F -> UNDEFINED
u'\ufffe' # 0x90 -> UNDEFINED
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
u'\u2022' # 0x95 -> BULLET
u'\u2013' # 0x96 -> EN DASH
u'\u2014' # 0x97 -> EM DASH
u'\u02dc' # 0x98 -> SMALL TILDE
u'\u2122' # 0x99 -> TRADE MARK SIGN
u'\ufffe' # 0x9A -> UNDEFINED
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
u'\ufffe' # 0x9C -> UNDEFINED
u'\ufffe' # 0x9D -> UNDEFINED
u'\ufffe' # 0x9E -> UNDEFINED
u'\ufffe' # 0x9F -> UNDEFINED
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
u'\xa2' # 0xA2 -> CENT SIGN
u'\xa3' # 0xA3 -> POUND SIGN
u'\u20aa' # 0xA4 -> NEW SHEQEL SIGN
u'\xa5' # 0xA5 -> YEN SIGN
u'\xa6' # 0xA6 -> BROKEN BAR
u'\xa7' # 0xA7 -> SECTION SIGN
u'\xa8' # 0xA8 -> DIAERESIS
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
u'\xd7' # 0xAA -> MULTIPLICATION SIGN
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xac' # 0xAC -> NOT SIGN
u'\xad' # 0xAD -> SOFT HYPHEN
u'\xae' # 0xAE -> REGISTERED SIGN
u'\xaf' # 0xAF -> MACRON
u'\xb0' # 0xB0 -> DEGREE SIGN
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
u'\xb4' # 0xB4 -> ACUTE ACCENT
u'\xb5' # 0xB5 -> MICRO SIGN
u'\xb6' # 0xB6 -> PILCROW SIGN
u'\xb7' # 0xB7 -> MIDDLE DOT
u'\xb8' # 0xB8 -> CEDILLA
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
u'\xf7' # 0xBA -> DIVISION SIGN
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
u'\xbf' # 0xBF -> INVERTED QUESTION MARK
u'\u05b0' # 0xC0 -> HEBREW POINT SHEVA
u'\u05b1' # 0xC1 -> HEBREW POINT HATAF SEGOL
u'\u05b2' # 0xC2 -> HEBREW POINT HATAF PATAH
u'\u05b3' # 0xC3 -> HEBREW POINT HATAF QAMATS
u'\u05b4' # 0xC4 -> HEBREW POINT HIRIQ
u'\u05b5' # 0xC5 -> HEBREW POINT TSERE
u'\u05b6' # 0xC6 -> HEBREW POINT SEGOL
u'\u05b7' # 0xC7 -> HEBREW POINT PATAH
u'\u05b8' # 0xC8 -> HEBREW POINT QAMATS
u'\u05b9' # 0xC9 -> HEBREW POINT HOLAM
u'\ufffe' # 0xCA -> UNDEFINED
u'\u05bb' # 0xCB -> HEBREW POINT QUBUTS
u'\u05bc' # 0xCC -> HEBREW POINT DAGESH OR MAPIQ
u'\u05bd' # 0xCD -> HEBREW POINT METEG
u'\u05be' # 0xCE -> HEBREW PUNCTUATION MAQAF
u'\u05bf' # 0xCF -> HEBREW POINT RAFE
u'\u05c0' # 0xD0 -> HEBREW PUNCTUATION PASEQ
u'\u05c1' # 0xD1 -> HEBREW POINT SHIN DOT
u'\u05c2' # 0xD2 -> HEBREW POINT SIN DOT
u'\u05c3' # 0xD3 -> HEBREW PUNCTUATION SOF PASUQ
u'\u05f0' # 0xD4 -> HEBREW LIGATURE YIDDISH DOUBLE VAV
u'\u05f1' # 0xD5 -> HEBREW LIGATURE YIDDISH VAV YOD
u'\u05f2' # 0xD6 -> HEBREW LIGATURE YIDDISH DOUBLE YOD
u'\u05f3' # 0xD7 -> HEBREW PUNCTUATION GERESH
u'\u05f4' # 0xD8 -> HEBREW PUNCTUATION GERSHAYIM
u'\ufffe' # 0xD9 -> UNDEFINED
u'\ufffe' # 0xDA -> UNDEFINED
u'\ufffe' # 0xDB -> UNDEFINED
u'\ufffe' # 0xDC -> UNDEFINED
u'\ufffe' # 0xDD -> UNDEFINED
u'\ufffe' # 0xDE -> UNDEFINED
u'\ufffe' # 0xDF -> UNDEFINED
u'\u05d0' # 0xE0 -> HEBREW LETTER ALEF
u'\u05d1' # 0xE1 -> HEBREW LETTER BET
u'\u05d2' # 0xE2 -> HEBREW LETTER GIMEL
u'\u05d3' # 0xE3 -> HEBREW LETTER DALET
u'\u05d4' # 0xE4 -> HEBREW LETTER HE
u'\u05d5' # 0xE5 -> HEBREW LETTER VAV
u'\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN
u'\u05d7' # 0xE7 -> HEBREW LETTER HET
u'\u05d8' # 0xE8 -> HEBREW LETTER TET
u'\u05d9' # 0xE9 -> HEBREW LETTER YOD
u'\u05da' # 0xEA -> HEBREW LETTER FINAL KAF
u'\u05db' # 0xEB -> HEBREW LETTER KAF
u'\u05dc' # 0xEC -> HEBREW LETTER LAMED
u'\u05dd' # 0xED -> HEBREW LETTER FINAL MEM
u'\u05de' # 0xEE -> HEBREW LETTER MEM
u'\u05df' # 0xEF -> HEBREW LETTER FINAL NUN
u'\u05e0' # 0xF0 -> HEBREW LETTER NUN
u'\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH
u'\u05e2' # 0xF2 -> HEBREW LETTER AYIN
u'\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE
u'\u05e4' # 0xF4 -> HEBREW LETTER PE
u'\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI
u'\u05e6' # 0xF6 -> HEBREW LETTER TSADI
u'\u05e7' # 0xF7 -> HEBREW LETTER QOF
u'\u05e8' # 0xF8 -> HEBREW LETTER RESH
u'\u05e9' # 0xF9 -> HEBREW LETTER SHIN
u'\u05ea' # 0xFA -> HEBREW LETTER TAV
u'\ufffe' # 0xFB -> UNDEFINED
u'\ufffe' # 0xFC -> UNDEFINED
u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK
u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK
u'\ufffe' # 0xFF -> UNDEFINED
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\u20ac' # 0x80 -> EURO SIGN
u'\ufffe' # 0x81 -> UNDEFINED
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
u'\u2020' # 0x86 -> DAGGER
u'\u2021' # 0x87 -> DOUBLE DAGGER
u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
u'\u2030' # 0x89 -> PER MILLE SIGN
u'\ufffe' # 0x8A -> UNDEFINED
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
u'\ufffe' # 0x8C -> UNDEFINED
u'\ufffe' # 0x8D -> UNDEFINED
u'\ufffe' # 0x8E -> UNDEFINED
u'\ufffe' # 0x8F -> UNDEFINED
u'\ufffe' # 0x90 -> UNDEFINED
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
u'\u2022' # 0x95 -> BULLET
u'\u2013' # 0x96 -> EN DASH
u'\u2014' # 0x97 -> EM DASH
u'\u02dc' # 0x98 -> SMALL TILDE
u'\u2122' # 0x99 -> TRADE MARK SIGN
u'\ufffe' # 0x9A -> UNDEFINED
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
u'\ufffe' # 0x9C -> UNDEFINED
u'\ufffe' # 0x9D -> UNDEFINED
u'\ufffe' # 0x9E -> UNDEFINED
u'\ufffe' # 0x9F -> UNDEFINED
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
u'\xa2' # 0xA2 -> CENT SIGN
u'\xa3' # 0xA3 -> POUND SIGN
u'\u20aa' # 0xA4 -> NEW SHEQEL SIGN
u'\xa5' # 0xA5 -> YEN SIGN
u'\xa6' # 0xA6 -> BROKEN BAR
u'\xa7' # 0xA7 -> SECTION SIGN
u'\xa8' # 0xA8 -> DIAERESIS
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
u'\xd7' # 0xAA -> MULTIPLICATION SIGN
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xac' # 0xAC -> NOT SIGN
u'\xad' # 0xAD -> SOFT HYPHEN
u'\xae' # 0xAE -> REGISTERED SIGN
u'\xaf' # 0xAF -> MACRON
u'\xb0' # 0xB0 -> DEGREE SIGN
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
u'\xb4' # 0xB4 -> ACUTE ACCENT
u'\xb5' # 0xB5 -> MICRO SIGN
u'\xb6' # 0xB6 -> PILCROW SIGN
u'\xb7' # 0xB7 -> MIDDLE DOT
u'\xb8' # 0xB8 -> CEDILLA
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
u'\xf7' # 0xBA -> DIVISION SIGN
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
u'\xbf' # 0xBF -> INVERTED QUESTION MARK
u'\u05b0' # 0xC0 -> HEBREW POINT SHEVA
u'\u05b1' # 0xC1 -> HEBREW POINT HATAF SEGOL
u'\u05b2' # 0xC2 -> HEBREW POINT HATAF PATAH
u'\u05b3' # 0xC3 -> HEBREW POINT HATAF QAMATS
u'\u05b4' # 0xC4 -> HEBREW POINT HIRIQ
u'\u05b5' # 0xC5 -> HEBREW POINT TSERE
u'\u05b6' # 0xC6 -> HEBREW POINT SEGOL
u'\u05b7' # 0xC7 -> HEBREW POINT PATAH
u'\u05b8' # 0xC8 -> HEBREW POINT QAMATS
u'\u05b9' # 0xC9 -> HEBREW POINT HOLAM
u'\ufffe' # 0xCA -> UNDEFINED
u'\u05bb' # 0xCB -> HEBREW POINT QUBUTS
u'\u05bc' # 0xCC -> HEBREW POINT DAGESH OR MAPIQ
u'\u05bd' # 0xCD -> HEBREW POINT METEG
u'\u05be' # 0xCE -> HEBREW PUNCTUATION MAQAF
u'\u05bf' # 0xCF -> HEBREW POINT RAFE
u'\u05c0' # 0xD0 -> HEBREW PUNCTUATION PASEQ
u'\u05c1' # 0xD1 -> HEBREW POINT SHIN DOT
u'\u05c2' # 0xD2 -> HEBREW POINT SIN DOT
u'\u05c3' # 0xD3 -> HEBREW PUNCTUATION SOF PASUQ
u'\u05f0' # 0xD4 -> HEBREW LIGATURE YIDDISH DOUBLE VAV
u'\u05f1' # 0xD5 -> HEBREW LIGATURE YIDDISH VAV YOD
u'\u05f2' # 0xD6 -> HEBREW LIGATURE YIDDISH DOUBLE YOD
u'\u05f3' # 0xD7 -> HEBREW PUNCTUATION GERESH
u'\u05f4' # 0xD8 -> HEBREW PUNCTUATION GERSHAYIM
u'\ufffe' # 0xD9 -> UNDEFINED
u'\ufffe' # 0xDA -> UNDEFINED
u'\ufffe' # 0xDB -> UNDEFINED
u'\ufffe' # 0xDC -> UNDEFINED
u'\ufffe' # 0xDD -> UNDEFINED
u'\ufffe' # 0xDE -> UNDEFINED
u'\ufffe' # 0xDF -> UNDEFINED
u'\u05d0' # 0xE0 -> HEBREW LETTER ALEF
u'\u05d1' # 0xE1 -> HEBREW LETTER BET
u'\u05d2' # 0xE2 -> HEBREW LETTER GIMEL
u'\u05d3' # 0xE3 -> HEBREW LETTER DALET
u'\u05d4' # 0xE4 -> HEBREW LETTER HE
u'\u05d5' # 0xE5 -> HEBREW LETTER VAV
u'\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN
u'\u05d7' # 0xE7 -> HEBREW LETTER HET
u'\u05d8' # 0xE8 -> HEBREW LETTER TET
u'\u05d9' # 0xE9 -> HEBREW LETTER YOD
u'\u05da' # 0xEA -> HEBREW LETTER FINAL KAF
u'\u05db' # 0xEB -> HEBREW LETTER KAF
u'\u05dc' # 0xEC -> HEBREW LETTER LAMED
u'\u05dd' # 0xED -> HEBREW LETTER FINAL MEM
u'\u05de' # 0xEE -> HEBREW LETTER MEM
u'\u05df' # 0xEF -> HEBREW LETTER FINAL NUN
u'\u05e0' # 0xF0 -> HEBREW LETTER NUN
u'\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH
u'\u05e2' # 0xF2 -> HEBREW LETTER AYIN
u'\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE
u'\u05e4' # 0xF4 -> HEBREW LETTER PE
u'\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI
u'\u05e6' # 0xF6 -> HEBREW LETTER TSADI
u'\u05e7' # 0xF7 -> HEBREW LETTER QOF
u'\u05e8' # 0xF8 -> HEBREW LETTER RESH
u'\u05e9' # 0xF9 -> HEBREW LETTER SHIN
u'\u05ea' # 0xFA -> HEBREW LETTER TAV
u'\ufffe' # 0xFB -> UNDEFINED
u'\ufffe' # 0xFC -> UNDEFINED
u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK
u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK
u'\ufffe' # 0xFF -> UNDEFINED
)
### Encoding Map
encoding_map = {
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x00A0: 0xA0, # NO-BREAK SPACE
0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
0x00A2: 0xA2, # CENT SIGN
0x00A3: 0xA3, # POUND SIGN
0x00A5: 0xA5, # YEN SIGN
0x00A6: 0xA6, # BROKEN BAR
0x00A7: 0xA7, # SECTION SIGN
0x00A8: 0xA8, # DIAERESIS
0x00A9: 0xA9, # COPYRIGHT SIGN
0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC: 0xAC, # NOT SIGN
0x00AD: 0xAD, # SOFT HYPHEN
0x00AE: 0xAE, # REGISTERED SIGN
0x00AF: 0xAF, # MACRON
0x00B0: 0xB0, # DEGREE SIGN
0x00B1: 0xB1, # PLUS-MINUS SIGN
0x00B2: 0xB2, # SUPERSCRIPT TWO
0x00B3: 0xB3, # SUPERSCRIPT THREE
0x00B4: 0xB4, # ACUTE ACCENT
0x00B5: 0xB5, # MICRO SIGN
0x00B6: 0xB6, # PILCROW SIGN
0x00B7: 0xB7, # MIDDLE DOT
0x00B8: 0xB8, # CEDILLA
0x00B9: 0xB9, # SUPERSCRIPT ONE
0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
0x00BF: 0xBF, # INVERTED QUESTION MARK
0x00D7: 0xAA, # MULTIPLICATION SIGN
0x00F7: 0xBA, # DIVISION SIGN
0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK
0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT
0x02DC: 0x98, # SMALL TILDE
0x05B0: 0xC0, # HEBREW POINT SHEVA
0x05B1: 0xC1, # HEBREW POINT HATAF SEGOL
0x05B2: 0xC2, # HEBREW POINT HATAF PATAH
0x05B3: 0xC3, # HEBREW POINT HATAF QAMATS
0x05B4: 0xC4, # HEBREW POINT HIRIQ
0x05B5: 0xC5, # HEBREW POINT TSERE
0x05B6: 0xC6, # HEBREW POINT SEGOL
0x05B7: 0xC7, # HEBREW POINT PATAH
0x05B8: 0xC8, # HEBREW POINT QAMATS
0x05B9: 0xC9, # HEBREW POINT HOLAM
0x05BB: 0xCB, # HEBREW POINT QUBUTS
0x05BC: 0xCC, # HEBREW POINT DAGESH OR MAPIQ
0x05BD: 0xCD, # HEBREW POINT METEG
0x05BE: 0xCE, # HEBREW PUNCTUATION MAQAF
0x05BF: 0xCF, # HEBREW POINT RAFE
0x05C0: 0xD0, # HEBREW PUNCTUATION PASEQ
0x05C1: 0xD1, # HEBREW POINT SHIN DOT
0x05C2: 0xD2, # HEBREW POINT SIN DOT
0x05C3: 0xD3, # HEBREW PUNCTUATION SOF PASUQ
0x05D0: 0xE0, # HEBREW LETTER ALEF
0x05D1: 0xE1, # HEBREW LETTER BET
0x05D2: 0xE2, # HEBREW LETTER GIMEL
0x05D3: 0xE3, # HEBREW LETTER DALET
0x05D4: 0xE4, # HEBREW LETTER HE
0x05D5: 0xE5, # HEBREW LETTER VAV
0x05D6: 0xE6, # HEBREW LETTER ZAYIN
0x05D7: 0xE7, # HEBREW LETTER HET
0x05D8: 0xE8, # HEBREW LETTER TET
0x05D9: 0xE9, # HEBREW LETTER YOD
0x05DA: 0xEA, # HEBREW LETTER FINAL KAF
0x05DB: 0xEB, # HEBREW LETTER KAF
0x05DC: 0xEC, # HEBREW LETTER LAMED
0x05DD: 0xED, # HEBREW LETTER FINAL MEM
0x05DE: 0xEE, # HEBREW LETTER MEM
0x05DF: 0xEF, # HEBREW LETTER FINAL NUN
0x05E0: 0xF0, # HEBREW LETTER NUN
0x05E1: 0xF1, # HEBREW LETTER SAMEKH
0x05E2: 0xF2, # HEBREW LETTER AYIN
0x05E3: 0xF3, # HEBREW LETTER FINAL PE
0x05E4: 0xF4, # HEBREW LETTER PE
0x05E5: 0xF5, # HEBREW LETTER FINAL TSADI
0x05E6: 0xF6, # HEBREW LETTER TSADI
0x05E7: 0xF7, # HEBREW LETTER QOF
0x05E8: 0xF8, # HEBREW LETTER RESH
0x05E9: 0xF9, # HEBREW LETTER SHIN
0x05EA: 0xFA, # HEBREW LETTER TAV
0x05F0: 0xD4, # HEBREW LIGATURE YIDDISH DOUBLE VAV
0x05F1: 0xD5, # HEBREW LIGATURE YIDDISH VAV YOD
0x05F2: 0xD6, # HEBREW LIGATURE YIDDISH DOUBLE YOD
0x05F3: 0xD7, # HEBREW PUNCTUATION GERESH
0x05F4: 0xD8, # HEBREW PUNCTUATION GERSHAYIM
0x200E: 0xFD, # LEFT-TO-RIGHT MARK
0x200F: 0xFE, # RIGHT-TO-LEFT MARK
0x2013: 0x96, # EN DASH
0x2014: 0x97, # EM DASH
0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
0x2020: 0x86, # DAGGER
0x2021: 0x87, # DOUBLE DAGGER
0x2022: 0x95, # BULLET
0x2026: 0x85, # HORIZONTAL ELLIPSIS
0x2030: 0x89, # PER MILLE SIGN
0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x20AA: 0xA4, # NEW SHEQEL SIGN
0x20AC: 0x80, # EURO SIGN
0x2122: 0x99, # TRADE MARK SIGN
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x00A0: 0xA0, # NO-BREAK SPACE
0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
0x00A2: 0xA2, # CENT SIGN
0x00A3: 0xA3, # POUND SIGN
0x00A5: 0xA5, # YEN SIGN
0x00A6: 0xA6, # BROKEN BAR
0x00A7: 0xA7, # SECTION SIGN
0x00A8: 0xA8, # DIAERESIS
0x00A9: 0xA9, # COPYRIGHT SIGN
0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC: 0xAC, # NOT SIGN
0x00AD: 0xAD, # SOFT HYPHEN
0x00AE: 0xAE, # REGISTERED SIGN
0x00AF: 0xAF, # MACRON
0x00B0: 0xB0, # DEGREE SIGN
0x00B1: 0xB1, # PLUS-MINUS SIGN
0x00B2: 0xB2, # SUPERSCRIPT TWO
0x00B3: 0xB3, # SUPERSCRIPT THREE
0x00B4: 0xB4, # ACUTE ACCENT
0x00B5: 0xB5, # MICRO SIGN
0x00B6: 0xB6, # PILCROW SIGN
0x00B7: 0xB7, # MIDDLE DOT
0x00B8: 0xB8, # CEDILLA
0x00B9: 0xB9, # SUPERSCRIPT ONE
0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
0x00BF: 0xBF, # INVERTED QUESTION MARK
0x00D7: 0xAA, # MULTIPLICATION SIGN
0x00F7: 0xBA, # DIVISION SIGN
0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK
0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT
0x02DC: 0x98, # SMALL TILDE
0x05B0: 0xC0, # HEBREW POINT SHEVA
0x05B1: 0xC1, # HEBREW POINT HATAF SEGOL
0x05B2: 0xC2, # HEBREW POINT HATAF PATAH
0x05B3: 0xC3, # HEBREW POINT HATAF QAMATS
0x05B4: 0xC4, # HEBREW POINT HIRIQ
0x05B5: 0xC5, # HEBREW POINT TSERE
0x05B6: 0xC6, # HEBREW POINT SEGOL
0x05B7: 0xC7, # HEBREW POINT PATAH
0x05B8: 0xC8, # HEBREW POINT QAMATS
0x05B9: 0xC9, # HEBREW POINT HOLAM
0x05BB: 0xCB, # HEBREW POINT QUBUTS
0x05BC: 0xCC, # HEBREW POINT DAGESH OR MAPIQ
0x05BD: 0xCD, # HEBREW POINT METEG
0x05BE: 0xCE, # HEBREW PUNCTUATION MAQAF
0x05BF: 0xCF, # HEBREW POINT RAFE
0x05C0: 0xD0, # HEBREW PUNCTUATION PASEQ
0x05C1: 0xD1, # HEBREW POINT SHIN DOT
0x05C2: 0xD2, # HEBREW POINT SIN DOT
0x05C3: 0xD3, # HEBREW PUNCTUATION SOF PASUQ
0x05D0: 0xE0, # HEBREW LETTER ALEF
0x05D1: 0xE1, # HEBREW LETTER BET
0x05D2: 0xE2, # HEBREW LETTER GIMEL
0x05D3: 0xE3, # HEBREW LETTER DALET
0x05D4: 0xE4, # HEBREW LETTER HE
0x05D5: 0xE5, # HEBREW LETTER VAV
0x05D6: 0xE6, # HEBREW LETTER ZAYIN
0x05D7: 0xE7, # HEBREW LETTER HET
0x05D8: 0xE8, # HEBREW LETTER TET
0x05D9: 0xE9, # HEBREW LETTER YOD
0x05DA: 0xEA, # HEBREW LETTER FINAL KAF
0x05DB: 0xEB, # HEBREW LETTER KAF
0x05DC: 0xEC, # HEBREW LETTER LAMED
0x05DD: 0xED, # HEBREW LETTER FINAL MEM
0x05DE: 0xEE, # HEBREW LETTER MEM
0x05DF: 0xEF, # HEBREW LETTER FINAL NUN
0x05E0: 0xF0, # HEBREW LETTER NUN
0x05E1: 0xF1, # HEBREW LETTER SAMEKH
0x05E2: 0xF2, # HEBREW LETTER AYIN
0x05E3: 0xF3, # HEBREW LETTER FINAL PE
0x05E4: 0xF4, # HEBREW LETTER PE
0x05E5: 0xF5, # HEBREW LETTER FINAL TSADI
0x05E6: 0xF6, # HEBREW LETTER TSADI
0x05E7: 0xF7, # HEBREW LETTER QOF
0x05E8: 0xF8, # HEBREW LETTER RESH
0x05E9: 0xF9, # HEBREW LETTER SHIN
0x05EA: 0xFA, # HEBREW LETTER TAV
0x05F0: 0xD4, # HEBREW LIGATURE YIDDISH DOUBLE VAV
0x05F1: 0xD5, # HEBREW LIGATURE YIDDISH VAV YOD
0x05F2: 0xD6, # HEBREW LIGATURE YIDDISH DOUBLE YOD
0x05F3: 0xD7, # HEBREW PUNCTUATION GERESH
0x05F4: 0xD8, # HEBREW PUNCTUATION GERSHAYIM
0x200E: 0xFD, # LEFT-TO-RIGHT MARK
0x200F: 0xFE, # RIGHT-TO-LEFT MARK
0x2013: 0x96, # EN DASH
0x2014: 0x97, # EM DASH
0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
0x2020: 0x86, # DAGGER
0x2021: 0x87, # DOUBLE DAGGER
0x2022: 0x95, # BULLET
0x2026: 0x85, # HORIZONTAL ELLIPSIS
0x2030: 0x89, # PER MILLE SIGN
0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x20AA: 0xA4, # NEW SHEQEL SIGN
0x20AC: 0x80, # EURO SIGN
0x2122: 0x99, # TRADE MARK SIGN
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -15,7 +15,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter):
pass
@ -32,484 +32,483 @@ def getregentry():
### Decoding Table
decoding_table = (
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x9c' # 0x04 -> SELECT
u'\t' # 0x05 -> HORIZONTAL TABULATION
u'\x86' # 0x06 -> REQUIRED NEW LINE
u'\x7f' # 0x07 -> DELETE
u'\x97' # 0x08 -> GRAPHIC ESCAPE
u'\x8d' # 0x09 -> SUPERSCRIPT
u'\x8e' # 0x0A -> REPEAT
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x9d' # 0x14 -> RESTORE/ENABLE PRESENTATION
u'\x85' # 0x15 -> NEW LINE
u'\x08' # 0x16 -> BACKSPACE
u'\x87' # 0x17 -> PROGRAM OPERATOR COMMUNICATION
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x92' # 0x1A -> UNIT BACK SPACE
u'\x8f' # 0x1B -> CUSTOMER USE ONE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u'\x80' # 0x20 -> DIGIT SELECT
u'\x81' # 0x21 -> START OF SIGNIFICANCE
u'\x82' # 0x22 -> FIELD SEPARATOR
u'\x83' # 0x23 -> WORD UNDERSCORE
u'\x84' # 0x24 -> BYPASS OR INHIBIT PRESENTATION
u'\n' # 0x25 -> LINE FEED
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x27 -> ESCAPE
u'\x88' # 0x28 -> SET ATTRIBUTE
u'\x89' # 0x29 -> START FIELD EXTENDED
u'\x8a' # 0x2A -> SET MODE OR SWITCH
u'\x8b' # 0x2B -> CONTROL SEQUENCE PREFIX
u'\x8c' # 0x2C -> MODIFY FIELD ATTRIBUTE
u'\x05' # 0x2D -> ENQUIRY
u'\x06' # 0x2E -> ACKNOWLEDGE
u'\x07' # 0x2F -> BELL
u'\x90' # 0x30 -> <reserved>
u'\x91' # 0x31 -> <reserved>
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
u'\x93' # 0x33 -> INDEX RETURN
u'\x94' # 0x34 -> PRESENTATION POSITION
u'\x95' # 0x35 -> TRANSPARENT
u'\x96' # 0x36 -> NUMERIC BACKSPACE
u'\x04' # 0x37 -> END OF TRANSMISSION
u'\x98' # 0x38 -> SUBSCRIPT
u'\x99' # 0x39 -> INDENT TABULATION
u'\x9a' # 0x3A -> REVERSE FORM FEED
u'\x9b' # 0x3B -> CUSTOMER USE THREE
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x3E -> <reserved>
u'\x1a' # 0x3F -> SUBSTITUTE
u' ' # 0x40 -> SPACE
u'\u05d0' # 0x41 -> HEBREW LETTER ALEF
u'\u05d1' # 0x42 -> HEBREW LETTER BET
u'\u05d2' # 0x43 -> HEBREW LETTER GIMEL
u'\u05d3' # 0x44 -> HEBREW LETTER DALET
u'\u05d4' # 0x45 -> HEBREW LETTER HE
u'\u05d5' # 0x46 -> HEBREW LETTER VAV
u'\u05d6' # 0x47 -> HEBREW LETTER ZAYIN
u'\u05d7' # 0x48 -> HEBREW LETTER HET
u'\u05d8' # 0x49 -> HEBREW LETTER TET
u'\xa2' # 0x4A -> CENT SIGN
u'.' # 0x4B -> FULL STOP
u'<' # 0x4C -> LESS-THAN SIGN
u'(' # 0x4D -> LEFT PARENTHESIS
u'+' # 0x4E -> PLUS SIGN
u'|' # 0x4F -> VERTICAL LINE
u'&' # 0x50 -> AMPERSAND
u'\u05d9' # 0x51 -> HEBREW LETTER YOD
u'\u05da' # 0x52 -> HEBREW LETTER FINAL KAF
u'\u05db' # 0x53 -> HEBREW LETTER KAF
u'\u05dc' # 0x54 -> HEBREW LETTER LAMED
u'\u05dd' # 0x55 -> HEBREW LETTER FINAL MEM
u'\u05de' # 0x56 -> HEBREW LETTER MEM
u'\u05df' # 0x57 -> HEBREW LETTER FINAL NUN
u'\u05e0' # 0x58 -> HEBREW LETTER NUN
u'\u05e1' # 0x59 -> HEBREW LETTER SAMEKH
u'!' # 0x5A -> EXCLAMATION MARK
u'$' # 0x5B -> DOLLAR SIGN
u'*' # 0x5C -> ASTERISK
u')' # 0x5D -> RIGHT PARENTHESIS
u';' # 0x5E -> SEMICOLON
u'\xac' # 0x5F -> NOT SIGN
u'-' # 0x60 -> HYPHEN-MINUS
u'/' # 0x61 -> SOLIDUS
u'\u05e2' # 0x62 -> HEBREW LETTER AYIN
u'\u05e3' # 0x63 -> HEBREW LETTER FINAL PE
u'\u05e4' # 0x64 -> HEBREW LETTER PE
u'\u05e5' # 0x65 -> HEBREW LETTER FINAL TSADI
u'\u05e6' # 0x66 -> HEBREW LETTER TSADI
u'\u05e7' # 0x67 -> HEBREW LETTER QOF
u'\u05e8' # 0x68 -> HEBREW LETTER RESH
u'\u05e9' # 0x69 -> HEBREW LETTER SHIN
u'\xa6' # 0x6A -> BROKEN BAR
u',' # 0x6B -> COMMA
u'%' # 0x6C -> PERCENT SIGN
u'_' # 0x6D -> LOW LINE
u'>' # 0x6E -> GREATER-THAN SIGN
u'?' # 0x6F -> QUESTION MARK
u'\ufffe' # 0x70 -> UNDEFINED
u'\u05ea' # 0x71 -> HEBREW LETTER TAV
u'\ufffe' # 0x72 -> UNDEFINED
u'\ufffe' # 0x73 -> UNDEFINED
u'\xa0' # 0x74 -> NO-BREAK SPACE
u'\ufffe' # 0x75 -> UNDEFINED
u'\ufffe' # 0x76 -> UNDEFINED
u'\ufffe' # 0x77 -> UNDEFINED
u'\u2017' # 0x78 -> DOUBLE LOW LINE
u'`' # 0x79 -> GRAVE ACCENT
u':' # 0x7A -> COLON
u'#' # 0x7B -> NUMBER SIGN
u'@' # 0x7C -> COMMERCIAL AT
u"'" # 0x7D -> APOSTROPHE
u'=' # 0x7E -> EQUALS SIGN
u'"' # 0x7F -> QUOTATION MARK
u'\ufffe' # 0x80 -> UNDEFINED
u'a' # 0x81 -> LATIN SMALL LETTER A
u'b' # 0x82 -> LATIN SMALL LETTER B
u'c' # 0x83 -> LATIN SMALL LETTER C
u'd' # 0x84 -> LATIN SMALL LETTER D
u'e' # 0x85 -> LATIN SMALL LETTER E
u'f' # 0x86 -> LATIN SMALL LETTER F
u'g' # 0x87 -> LATIN SMALL LETTER G
u'h' # 0x88 -> LATIN SMALL LETTER H
u'i' # 0x89 -> LATIN SMALL LETTER I
u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\ufffe' # 0x8C -> UNDEFINED
u'\ufffe' # 0x8D -> UNDEFINED
u'\ufffe' # 0x8E -> UNDEFINED
u'\xb1' # 0x8F -> PLUS-MINUS SIGN
u'\xb0' # 0x90 -> DEGREE SIGN
u'j' # 0x91 -> LATIN SMALL LETTER J
u'k' # 0x92 -> LATIN SMALL LETTER K
u'l' # 0x93 -> LATIN SMALL LETTER L
u'm' # 0x94 -> LATIN SMALL LETTER M
u'n' # 0x95 -> LATIN SMALL LETTER N
u'o' # 0x96 -> LATIN SMALL LETTER O
u'p' # 0x97 -> LATIN SMALL LETTER P
u'q' # 0x98 -> LATIN SMALL LETTER Q
u'r' # 0x99 -> LATIN SMALL LETTER R
u'\ufffe' # 0x9A -> UNDEFINED
u'\ufffe' # 0x9B -> UNDEFINED
u'\ufffe' # 0x9C -> UNDEFINED
u'\xb8' # 0x9D -> CEDILLA
u'\ufffe' # 0x9E -> UNDEFINED
u'\xa4' # 0x9F -> CURRENCY SIGN
u'\xb5' # 0xA0 -> MICRO SIGN
u'~' # 0xA1 -> TILDE
u's' # 0xA2 -> LATIN SMALL LETTER S
u't' # 0xA3 -> LATIN SMALL LETTER T
u'u' # 0xA4 -> LATIN SMALL LETTER U
u'v' # 0xA5 -> LATIN SMALL LETTER V
u'w' # 0xA6 -> LATIN SMALL LETTER W
u'x' # 0xA7 -> LATIN SMALL LETTER X
u'y' # 0xA8 -> LATIN SMALL LETTER Y
u'z' # 0xA9 -> LATIN SMALL LETTER Z
u'\ufffe' # 0xAA -> UNDEFINED
u'\ufffe' # 0xAB -> UNDEFINED
u'\ufffe' # 0xAC -> UNDEFINED
u'\ufffe' # 0xAD -> UNDEFINED
u'\ufffe' # 0xAE -> UNDEFINED
u'\xae' # 0xAF -> REGISTERED SIGN
u'^' # 0xB0 -> CIRCUMFLEX ACCENT
u'\xa3' # 0xB1 -> POUND SIGN
u'\xa5' # 0xB2 -> YEN SIGN
u'\xb7' # 0xB3 -> MIDDLE DOT
u'\xa9' # 0xB4 -> COPYRIGHT SIGN
u'\xa7' # 0xB5 -> SECTION SIGN
u'\xb6' # 0xB6 -> PILCROW SIGN
u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
u'[' # 0xBA -> LEFT SQUARE BRACKET
u']' # 0xBB -> RIGHT SQUARE BRACKET
u'\xaf' # 0xBC -> MACRON
u'\xa8' # 0xBD -> DIAERESIS
u'\xb4' # 0xBE -> ACUTE ACCENT
u'\xd7' # 0xBF -> MULTIPLICATION SIGN
u'{' # 0xC0 -> LEFT CURLY BRACKET
u'A' # 0xC1 -> LATIN CAPITAL LETTER A
u'B' # 0xC2 -> LATIN CAPITAL LETTER B
u'C' # 0xC3 -> LATIN CAPITAL LETTER C
u'D' # 0xC4 -> LATIN CAPITAL LETTER D
u'E' # 0xC5 -> LATIN CAPITAL LETTER E
u'F' # 0xC6 -> LATIN CAPITAL LETTER F
u'G' # 0xC7 -> LATIN CAPITAL LETTER G
u'H' # 0xC8 -> LATIN CAPITAL LETTER H
u'I' # 0xC9 -> LATIN CAPITAL LETTER I
u'\xad' # 0xCA -> SOFT HYPHEN
u'\ufffe' # 0xCB -> UNDEFINED
u'\ufffe' # 0xCC -> UNDEFINED
u'\ufffe' # 0xCD -> UNDEFINED
u'\ufffe' # 0xCE -> UNDEFINED
u'\ufffe' # 0xCF -> UNDEFINED
u'}' # 0xD0 -> RIGHT CURLY BRACKET
u'J' # 0xD1 -> LATIN CAPITAL LETTER J
u'K' # 0xD2 -> LATIN CAPITAL LETTER K
u'L' # 0xD3 -> LATIN CAPITAL LETTER L
u'M' # 0xD4 -> LATIN CAPITAL LETTER M
u'N' # 0xD5 -> LATIN CAPITAL LETTER N
u'O' # 0xD6 -> LATIN CAPITAL LETTER O
u'P' # 0xD7 -> LATIN CAPITAL LETTER P
u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
u'R' # 0xD9 -> LATIN CAPITAL LETTER R
u'\xb9' # 0xDA -> SUPERSCRIPT ONE
u'\ufffe' # 0xDB -> UNDEFINED
u'\ufffe' # 0xDC -> UNDEFINED
u'\ufffe' # 0xDD -> UNDEFINED
u'\ufffe' # 0xDE -> UNDEFINED
u'\ufffe' # 0xDF -> UNDEFINED
u'\\' # 0xE0 -> REVERSE SOLIDUS
u'\xf7' # 0xE1 -> DIVISION SIGN
u'S' # 0xE2 -> LATIN CAPITAL LETTER S
u'T' # 0xE3 -> LATIN CAPITAL LETTER T
u'U' # 0xE4 -> LATIN CAPITAL LETTER U
u'V' # 0xE5 -> LATIN CAPITAL LETTER V
u'W' # 0xE6 -> LATIN CAPITAL LETTER W
u'X' # 0xE7 -> LATIN CAPITAL LETTER X
u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
u'\xb2' # 0xEA -> SUPERSCRIPT TWO
u'\ufffe' # 0xEB -> UNDEFINED
u'\ufffe' # 0xEC -> UNDEFINED
u'\ufffe' # 0xED -> UNDEFINED
u'\ufffe' # 0xEE -> UNDEFINED
u'\ufffe' # 0xEF -> UNDEFINED
u'0' # 0xF0 -> DIGIT ZERO
u'1' # 0xF1 -> DIGIT ONE
u'2' # 0xF2 -> DIGIT TWO
u'3' # 0xF3 -> DIGIT THREE
u'4' # 0xF4 -> DIGIT FOUR
u'5' # 0xF5 -> DIGIT FIVE
u'6' # 0xF6 -> DIGIT SIX
u'7' # 0xF7 -> DIGIT SEVEN
u'8' # 0xF8 -> DIGIT EIGHT
u'9' # 0xF9 -> DIGIT NINE
u'\xb3' # 0xFA -> SUPERSCRIPT THREE
u'\ufffe' # 0xFB -> UNDEFINED
u'\ufffe' # 0xFC -> UNDEFINED
u'\ufffe' # 0xFD -> UNDEFINED
u'\ufffe' # 0xFE -> UNDEFINED
u'\x9f' # 0xFF -> EIGHT ONES
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x9c' # 0x04 -> SELECT
u'\t' # 0x05 -> HORIZONTAL TABULATION
u'\x86' # 0x06 -> REQUIRED NEW LINE
u'\x7f' # 0x07 -> DELETE
u'\x97' # 0x08 -> GRAPHIC ESCAPE
u'\x8d' # 0x09 -> SUPERSCRIPT
u'\x8e' # 0x0A -> REPEAT
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x9d' # 0x14 -> RESTORE/ENABLE PRESENTATION
u'\x85' # 0x15 -> NEW LINE
u'\x08' # 0x16 -> BACKSPACE
u'\x87' # 0x17 -> PROGRAM OPERATOR COMMUNICATION
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x92' # 0x1A -> UNIT BACK SPACE
u'\x8f' # 0x1B -> CUSTOMER USE ONE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u'\x80' # 0x20 -> DIGIT SELECT
u'\x81' # 0x21 -> START OF SIGNIFICANCE
u'\x82' # 0x22 -> FIELD SEPARATOR
u'\x83' # 0x23 -> WORD UNDERSCORE
u'\x84' # 0x24 -> BYPASS OR INHIBIT PRESENTATION
u'\n' # 0x25 -> LINE FEED
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x27 -> ESCAPE
u'\x88' # 0x28 -> SET ATTRIBUTE
u'\x89' # 0x29 -> START FIELD EXTENDED
u'\x8a' # 0x2A -> SET MODE OR SWITCH
u'\x8b' # 0x2B -> CONTROL SEQUENCE PREFIX
u'\x8c' # 0x2C -> MODIFY FIELD ATTRIBUTE
u'\x05' # 0x2D -> ENQUIRY
u'\x06' # 0x2E -> ACKNOWLEDGE
u'\x07' # 0x2F -> BELL
u'\x90' # 0x30 -> <reserved>
u'\x91' # 0x31 -> <reserved>
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
u'\x93' # 0x33 -> INDEX RETURN
u'\x94' # 0x34 -> PRESENTATION POSITION
u'\x95' # 0x35 -> TRANSPARENT
u'\x96' # 0x36 -> NUMERIC BACKSPACE
u'\x04' # 0x37 -> END OF TRANSMISSION
u'\x98' # 0x38 -> SUBSCRIPT
u'\x99' # 0x39 -> INDENT TABULATION
u'\x9a' # 0x3A -> REVERSE FORM FEED
u'\x9b' # 0x3B -> CUSTOMER USE THREE
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x3E -> <reserved>
u'\x1a' # 0x3F -> SUBSTITUTE
u' ' # 0x40 -> SPACE
u'\u05d0' # 0x41 -> HEBREW LETTER ALEF
u'\u05d1' # 0x42 -> HEBREW LETTER BET
u'\u05d2' # 0x43 -> HEBREW LETTER GIMEL
u'\u05d3' # 0x44 -> HEBREW LETTER DALET
u'\u05d4' # 0x45 -> HEBREW LETTER HE
u'\u05d5' # 0x46 -> HEBREW LETTER VAV
u'\u05d6' # 0x47 -> HEBREW LETTER ZAYIN
u'\u05d7' # 0x48 -> HEBREW LETTER HET
u'\u05d8' # 0x49 -> HEBREW LETTER TET
u'\xa2' # 0x4A -> CENT SIGN
u'.' # 0x4B -> FULL STOP
u'<' # 0x4C -> LESS-THAN SIGN
u'(' # 0x4D -> LEFT PARENTHESIS
u'+' # 0x4E -> PLUS SIGN
u'|' # 0x4F -> VERTICAL LINE
u'&' # 0x50 -> AMPERSAND
u'\u05d9' # 0x51 -> HEBREW LETTER YOD
u'\u05da' # 0x52 -> HEBREW LETTER FINAL KAF
u'\u05db' # 0x53 -> HEBREW LETTER KAF
u'\u05dc' # 0x54 -> HEBREW LETTER LAMED
u'\u05dd' # 0x55 -> HEBREW LETTER FINAL MEM
u'\u05de' # 0x56 -> HEBREW LETTER MEM
u'\u05df' # 0x57 -> HEBREW LETTER FINAL NUN
u'\u05e0' # 0x58 -> HEBREW LETTER NUN
u'\u05e1' # 0x59 -> HEBREW LETTER SAMEKH
u'!' # 0x5A -> EXCLAMATION MARK
u'$' # 0x5B -> DOLLAR SIGN
u'*' # 0x5C -> ASTERISK
u')' # 0x5D -> RIGHT PARENTHESIS
u';' # 0x5E -> SEMICOLON
u'\xac' # 0x5F -> NOT SIGN
u'-' # 0x60 -> HYPHEN-MINUS
u'/' # 0x61 -> SOLIDUS
u'\u05e2' # 0x62 -> HEBREW LETTER AYIN
u'\u05e3' # 0x63 -> HEBREW LETTER FINAL PE
u'\u05e4' # 0x64 -> HEBREW LETTER PE
u'\u05e5' # 0x65 -> HEBREW LETTER FINAL TSADI
u'\u05e6' # 0x66 -> HEBREW LETTER TSADI
u'\u05e7' # 0x67 -> HEBREW LETTER QOF
u'\u05e8' # 0x68 -> HEBREW LETTER RESH
u'\u05e9' # 0x69 -> HEBREW LETTER SHIN
u'\xa6' # 0x6A -> BROKEN BAR
u',' # 0x6B -> COMMA
u'%' # 0x6C -> PERCENT SIGN
u'_' # 0x6D -> LOW LINE
u'>' # 0x6E -> GREATER-THAN SIGN
u'?' # 0x6F -> QUESTION MARK
u'\ufffe' # 0x70 -> UNDEFINED
u'\u05ea' # 0x71 -> HEBREW LETTER TAV
u'\ufffe' # 0x72 -> UNDEFINED
u'\ufffe' # 0x73 -> UNDEFINED
u'\xa0' # 0x74 -> NO-BREAK SPACE
u'\ufffe' # 0x75 -> UNDEFINED
u'\ufffe' # 0x76 -> UNDEFINED
u'\ufffe' # 0x77 -> UNDEFINED
u'\u2017' # 0x78 -> DOUBLE LOW LINE
u'`' # 0x79 -> GRAVE ACCENT
u':' # 0x7A -> COLON
u'#' # 0x7B -> NUMBER SIGN
u'@' # 0x7C -> COMMERCIAL AT
u"'" # 0x7D -> APOSTROPHE
u'=' # 0x7E -> EQUALS SIGN
u'"' # 0x7F -> QUOTATION MARK
u'\ufffe' # 0x80 -> UNDEFINED
u'a' # 0x81 -> LATIN SMALL LETTER A
u'b' # 0x82 -> LATIN SMALL LETTER B
u'c' # 0x83 -> LATIN SMALL LETTER C
u'd' # 0x84 -> LATIN SMALL LETTER D
u'e' # 0x85 -> LATIN SMALL LETTER E
u'f' # 0x86 -> LATIN SMALL LETTER F
u'g' # 0x87 -> LATIN SMALL LETTER G
u'h' # 0x88 -> LATIN SMALL LETTER H
u'i' # 0x89 -> LATIN SMALL LETTER I
u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\ufffe' # 0x8C -> UNDEFINED
u'\ufffe' # 0x8D -> UNDEFINED
u'\ufffe' # 0x8E -> UNDEFINED
u'\xb1' # 0x8F -> PLUS-MINUS SIGN
u'\xb0' # 0x90 -> DEGREE SIGN
u'j' # 0x91 -> LATIN SMALL LETTER J
u'k' # 0x92 -> LATIN SMALL LETTER K
u'l' # 0x93 -> LATIN SMALL LETTER L
u'm' # 0x94 -> LATIN SMALL LETTER M
u'n' # 0x95 -> LATIN SMALL LETTER N
u'o' # 0x96 -> LATIN SMALL LETTER O
u'p' # 0x97 -> LATIN SMALL LETTER P
u'q' # 0x98 -> LATIN SMALL LETTER Q
u'r' # 0x99 -> LATIN SMALL LETTER R
u'\ufffe' # 0x9A -> UNDEFINED
u'\ufffe' # 0x9B -> UNDEFINED
u'\ufffe' # 0x9C -> UNDEFINED
u'\xb8' # 0x9D -> CEDILLA
u'\ufffe' # 0x9E -> UNDEFINED
u'\xa4' # 0x9F -> CURRENCY SIGN
u'\xb5' # 0xA0 -> MICRO SIGN
u'~' # 0xA1 -> TILDE
u's' # 0xA2 -> LATIN SMALL LETTER S
u't' # 0xA3 -> LATIN SMALL LETTER T
u'u' # 0xA4 -> LATIN SMALL LETTER U
u'v' # 0xA5 -> LATIN SMALL LETTER V
u'w' # 0xA6 -> LATIN SMALL LETTER W
u'x' # 0xA7 -> LATIN SMALL LETTER X
u'y' # 0xA8 -> LATIN SMALL LETTER Y
u'z' # 0xA9 -> LATIN SMALL LETTER Z
u'\ufffe' # 0xAA -> UNDEFINED
u'\ufffe' # 0xAB -> UNDEFINED
u'\ufffe' # 0xAC -> UNDEFINED
u'\ufffe' # 0xAD -> UNDEFINED
u'\ufffe' # 0xAE -> UNDEFINED
u'\xae' # 0xAF -> REGISTERED SIGN
u'^' # 0xB0 -> CIRCUMFLEX ACCENT
u'\xa3' # 0xB1 -> POUND SIGN
u'\xa5' # 0xB2 -> YEN SIGN
u'\xb7' # 0xB3 -> MIDDLE DOT
u'\xa9' # 0xB4 -> COPYRIGHT SIGN
u'\xa7' # 0xB5 -> SECTION SIGN
u'\xb6' # 0xB6 -> PILCROW SIGN
u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
u'[' # 0xBA -> LEFT SQUARE BRACKET
u']' # 0xBB -> RIGHT SQUARE BRACKET
u'\xaf' # 0xBC -> MACRON
u'\xa8' # 0xBD -> DIAERESIS
u'\xb4' # 0xBE -> ACUTE ACCENT
u'\xd7' # 0xBF -> MULTIPLICATION SIGN
u'{' # 0xC0 -> LEFT CURLY BRACKET
u'A' # 0xC1 -> LATIN CAPITAL LETTER A
u'B' # 0xC2 -> LATIN CAPITAL LETTER B
u'C' # 0xC3 -> LATIN CAPITAL LETTER C
u'D' # 0xC4 -> LATIN CAPITAL LETTER D
u'E' # 0xC5 -> LATIN CAPITAL LETTER E
u'F' # 0xC6 -> LATIN CAPITAL LETTER F
u'G' # 0xC7 -> LATIN CAPITAL LETTER G
u'H' # 0xC8 -> LATIN CAPITAL LETTER H
u'I' # 0xC9 -> LATIN CAPITAL LETTER I
u'\xad' # 0xCA -> SOFT HYPHEN
u'\ufffe' # 0xCB -> UNDEFINED
u'\ufffe' # 0xCC -> UNDEFINED
u'\ufffe' # 0xCD -> UNDEFINED
u'\ufffe' # 0xCE -> UNDEFINED
u'\ufffe' # 0xCF -> UNDEFINED
u'}' # 0xD0 -> RIGHT CURLY BRACKET
u'J' # 0xD1 -> LATIN CAPITAL LETTER J
u'K' # 0xD2 -> LATIN CAPITAL LETTER K
u'L' # 0xD3 -> LATIN CAPITAL LETTER L
u'M' # 0xD4 -> LATIN CAPITAL LETTER M
u'N' # 0xD5 -> LATIN CAPITAL LETTER N
u'O' # 0xD6 -> LATIN CAPITAL LETTER O
u'P' # 0xD7 -> LATIN CAPITAL LETTER P
u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
u'R' # 0xD9 -> LATIN CAPITAL LETTER R
u'\xb9' # 0xDA -> SUPERSCRIPT ONE
u'\ufffe' # 0xDB -> UNDEFINED
u'\ufffe' # 0xDC -> UNDEFINED
u'\ufffe' # 0xDD -> UNDEFINED
u'\ufffe' # 0xDE -> UNDEFINED
u'\ufffe' # 0xDF -> UNDEFINED
u'\\' # 0xE0 -> REVERSE SOLIDUS
u'\xf7' # 0xE1 -> DIVISION SIGN
u'S' # 0xE2 -> LATIN CAPITAL LETTER S
u'T' # 0xE3 -> LATIN CAPITAL LETTER T
u'U' # 0xE4 -> LATIN CAPITAL LETTER U
u'V' # 0xE5 -> LATIN CAPITAL LETTER V
u'W' # 0xE6 -> LATIN CAPITAL LETTER W
u'X' # 0xE7 -> LATIN CAPITAL LETTER X
u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
u'\xb2' # 0xEA -> SUPERSCRIPT TWO
u'\ufffe' # 0xEB -> UNDEFINED
u'\ufffe' # 0xEC -> UNDEFINED
u'\ufffe' # 0xED -> UNDEFINED
u'\ufffe' # 0xEE -> UNDEFINED
u'\ufffe' # 0xEF -> UNDEFINED
u'0' # 0xF0 -> DIGIT ZERO
u'1' # 0xF1 -> DIGIT ONE
u'2' # 0xF2 -> DIGIT TWO
u'3' # 0xF3 -> DIGIT THREE
u'4' # 0xF4 -> DIGIT FOUR
u'5' # 0xF5 -> DIGIT FIVE
u'6' # 0xF6 -> DIGIT SIX
u'7' # 0xF7 -> DIGIT SEVEN
u'8' # 0xF8 -> DIGIT EIGHT
u'9' # 0xF9 -> DIGIT NINE
u'\xb3' # 0xFA -> SUPERSCRIPT THREE
u'\ufffe' # 0xFB -> UNDEFINED
u'\ufffe' # 0xFC -> UNDEFINED
u'\ufffe' # 0xFD -> UNDEFINED
u'\ufffe' # 0xFE -> UNDEFINED
u'\x9f' # 0xFF -> EIGHT ONES
)
### Encoding Map
encoding_map = {
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x37, # END OF TRANSMISSION
0x0005: 0x2D, # ENQUIRY
0x0006: 0x2E, # ACKNOWLEDGE
0x0007: 0x2F, # BELL
0x0008: 0x16, # BACKSPACE
0x0009: 0x05, # HORIZONTAL TABULATION
0x000A: 0x25, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x3C, # DEVICE CONTROL FOUR
0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE
0x0016: 0x32, # SYNCHRONOUS IDLE
0x0017: 0x26, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x3F, # SUBSTITUTE
0x001B: 0x27, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x40, # SPACE
0x0021: 0x5A, # EXCLAMATION MARK
0x0022: 0x7F, # QUOTATION MARK
0x0023: 0x7B, # NUMBER SIGN
0x0024: 0x5B, # DOLLAR SIGN
0x0025: 0x6C, # PERCENT SIGN
0x0026: 0x50, # AMPERSAND
0x0027: 0x7D, # APOSTROPHE
0x0028: 0x4D, # LEFT PARENTHESIS
0x0029: 0x5D, # RIGHT PARENTHESIS
0x002A: 0x5C, # ASTERISK
0x002B: 0x4E, # PLUS SIGN
0x002C: 0x6B, # COMMA
0x002D: 0x60, # HYPHEN-MINUS
0x002E: 0x4B, # FULL STOP
0x002F: 0x61, # SOLIDUS
0x0030: 0xF0, # DIGIT ZERO
0x0031: 0xF1, # DIGIT ONE
0x0032: 0xF2, # DIGIT TWO
0x0033: 0xF3, # DIGIT THREE
0x0034: 0xF4, # DIGIT FOUR
0x0035: 0xF5, # DIGIT FIVE
0x0036: 0xF6, # DIGIT SIX
0x0037: 0xF7, # DIGIT SEVEN
0x0038: 0xF8, # DIGIT EIGHT
0x0039: 0xF9, # DIGIT NINE
0x003A: 0x7A, # COLON
0x003B: 0x5E, # SEMICOLON
0x003C: 0x4C, # LESS-THAN SIGN
0x003D: 0x7E, # EQUALS SIGN
0x003E: 0x6E, # GREATER-THAN SIGN
0x003F: 0x6F, # QUESTION MARK
0x0040: 0x7C, # COMMERCIAL AT
0x0041: 0xC1, # LATIN CAPITAL LETTER A
0x0042: 0xC2, # LATIN CAPITAL LETTER B
0x0043: 0xC3, # LATIN CAPITAL LETTER C
0x0044: 0xC4, # LATIN CAPITAL LETTER D
0x0045: 0xC5, # LATIN CAPITAL LETTER E
0x0046: 0xC6, # LATIN CAPITAL LETTER F
0x0047: 0xC7, # LATIN CAPITAL LETTER G
0x0048: 0xC8, # LATIN CAPITAL LETTER H
0x0049: 0xC9, # LATIN CAPITAL LETTER I
0x004A: 0xD1, # LATIN CAPITAL LETTER J
0x004B: 0xD2, # LATIN CAPITAL LETTER K
0x004C: 0xD3, # LATIN CAPITAL LETTER L
0x004D: 0xD4, # LATIN CAPITAL LETTER M
0x004E: 0xD5, # LATIN CAPITAL LETTER N
0x004F: 0xD6, # LATIN CAPITAL LETTER O
0x0050: 0xD7, # LATIN CAPITAL LETTER P
0x0051: 0xD8, # LATIN CAPITAL LETTER Q
0x0052: 0xD9, # LATIN CAPITAL LETTER R
0x0053: 0xE2, # LATIN CAPITAL LETTER S
0x0054: 0xE3, # LATIN CAPITAL LETTER T
0x0055: 0xE4, # LATIN CAPITAL LETTER U
0x0056: 0xE5, # LATIN CAPITAL LETTER V
0x0057: 0xE6, # LATIN CAPITAL LETTER W
0x0058: 0xE7, # LATIN CAPITAL LETTER X
0x0059: 0xE8, # LATIN CAPITAL LETTER Y
0x005A: 0xE9, # LATIN CAPITAL LETTER Z
0x005B: 0xBA, # LEFT SQUARE BRACKET
0x005C: 0xE0, # REVERSE SOLIDUS
0x005D: 0xBB, # RIGHT SQUARE BRACKET
0x005E: 0xB0, # CIRCUMFLEX ACCENT
0x005F: 0x6D, # LOW LINE
0x0060: 0x79, # GRAVE ACCENT
0x0061: 0x81, # LATIN SMALL LETTER A
0x0062: 0x82, # LATIN SMALL LETTER B
0x0063: 0x83, # LATIN SMALL LETTER C
0x0064: 0x84, # LATIN SMALL LETTER D
0x0065: 0x85, # LATIN SMALL LETTER E
0x0066: 0x86, # LATIN SMALL LETTER F
0x0067: 0x87, # LATIN SMALL LETTER G
0x0068: 0x88, # LATIN SMALL LETTER H
0x0069: 0x89, # LATIN SMALL LETTER I
0x006A: 0x91, # LATIN SMALL LETTER J
0x006B: 0x92, # LATIN SMALL LETTER K
0x006C: 0x93, # LATIN SMALL LETTER L
0x006D: 0x94, # LATIN SMALL LETTER M
0x006E: 0x95, # LATIN SMALL LETTER N
0x006F: 0x96, # LATIN SMALL LETTER O
0x0070: 0x97, # LATIN SMALL LETTER P
0x0071: 0x98, # LATIN SMALL LETTER Q
0x0072: 0x99, # LATIN SMALL LETTER R
0x0073: 0xA2, # LATIN SMALL LETTER S
0x0074: 0xA3, # LATIN SMALL LETTER T
0x0075: 0xA4, # LATIN SMALL LETTER U
0x0076: 0xA5, # LATIN SMALL LETTER V
0x0077: 0xA6, # LATIN SMALL LETTER W
0x0078: 0xA7, # LATIN SMALL LETTER X
0x0079: 0xA8, # LATIN SMALL LETTER Y
0x007A: 0xA9, # LATIN SMALL LETTER Z
0x007B: 0xC0, # LEFT CURLY BRACKET
0x007C: 0x4F, # VERTICAL LINE
0x007D: 0xD0, # RIGHT CURLY BRACKET
0x007E: 0xA1, # TILDE
0x007F: 0x07, # DELETE
0x0080: 0x20, # DIGIT SELECT
0x0081: 0x21, # START OF SIGNIFICANCE
0x0082: 0x22, # FIELD SEPARATOR
0x0083: 0x23, # WORD UNDERSCORE
0x0084: 0x24, # BYPASS OR INHIBIT PRESENTATION
0x0085: 0x15, # NEW LINE
0x0086: 0x06, # REQUIRED NEW LINE
0x0087: 0x17, # PROGRAM OPERATOR COMMUNICATION
0x0088: 0x28, # SET ATTRIBUTE
0x0089: 0x29, # START FIELD EXTENDED
0x008A: 0x2A, # SET MODE OR SWITCH
0x008B: 0x2B, # CONTROL SEQUENCE PREFIX
0x008C: 0x2C, # MODIFY FIELD ATTRIBUTE
0x008D: 0x09, # SUPERSCRIPT
0x008E: 0x0A, # REPEAT
0x008F: 0x1B, # CUSTOMER USE ONE
0x0090: 0x30, # <reserved>
0x0091: 0x31, # <reserved>
0x0092: 0x1A, # UNIT BACK SPACE
0x0093: 0x33, # INDEX RETURN
0x0094: 0x34, # PRESENTATION POSITION
0x0095: 0x35, # TRANSPARENT
0x0096: 0x36, # NUMERIC BACKSPACE
0x0097: 0x08, # GRAPHIC ESCAPE
0x0098: 0x38, # SUBSCRIPT
0x0099: 0x39, # INDENT TABULATION
0x009A: 0x3A, # REVERSE FORM FEED
0x009B: 0x3B, # CUSTOMER USE THREE
0x009C: 0x04, # SELECT
0x009D: 0x14, # RESTORE/ENABLE PRESENTATION
0x009E: 0x3E, # <reserved>
0x009F: 0xFF, # EIGHT ONES
0x00A0: 0x74, # NO-BREAK SPACE
0x00A2: 0x4A, # CENT SIGN
0x00A3: 0xB1, # POUND SIGN
0x00A4: 0x9F, # CURRENCY SIGN
0x00A5: 0xB2, # YEN SIGN
0x00A6: 0x6A, # BROKEN BAR
0x00A7: 0xB5, # SECTION SIGN
0x00A8: 0xBD, # DIAERESIS
0x00A9: 0xB4, # COPYRIGHT SIGN
0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC: 0x5F, # NOT SIGN
0x00AD: 0xCA, # SOFT HYPHEN
0x00AE: 0xAF, # REGISTERED SIGN
0x00AF: 0xBC, # MACRON
0x00B0: 0x90, # DEGREE SIGN
0x00B1: 0x8F, # PLUS-MINUS SIGN
0x00B2: 0xEA, # SUPERSCRIPT TWO
0x00B3: 0xFA, # SUPERSCRIPT THREE
0x00B4: 0xBE, # ACUTE ACCENT
0x00B5: 0xA0, # MICRO SIGN
0x00B6: 0xB6, # PILCROW SIGN
0x00B7: 0xB3, # MIDDLE DOT
0x00B8: 0x9D, # CEDILLA
0x00B9: 0xDA, # SUPERSCRIPT ONE
0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER
0x00BD: 0xB8, # VULGAR FRACTION ONE HALF
0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS
0x00D7: 0xBF, # MULTIPLICATION SIGN
0x00F7: 0xE1, # DIVISION SIGN
0x05D0: 0x41, # HEBREW LETTER ALEF
0x05D1: 0x42, # HEBREW LETTER BET
0x05D2: 0x43, # HEBREW LETTER GIMEL
0x05D3: 0x44, # HEBREW LETTER DALET
0x05D4: 0x45, # HEBREW LETTER HE
0x05D5: 0x46, # HEBREW LETTER VAV
0x05D6: 0x47, # HEBREW LETTER ZAYIN
0x05D7: 0x48, # HEBREW LETTER HET
0x05D8: 0x49, # HEBREW LETTER TET
0x05D9: 0x51, # HEBREW LETTER YOD
0x05DA: 0x52, # HEBREW LETTER FINAL KAF
0x05DB: 0x53, # HEBREW LETTER KAF
0x05DC: 0x54, # HEBREW LETTER LAMED
0x05DD: 0x55, # HEBREW LETTER FINAL MEM
0x05DE: 0x56, # HEBREW LETTER MEM
0x05DF: 0x57, # HEBREW LETTER FINAL NUN
0x05E0: 0x58, # HEBREW LETTER NUN
0x05E1: 0x59, # HEBREW LETTER SAMEKH
0x05E2: 0x62, # HEBREW LETTER AYIN
0x05E3: 0x63, # HEBREW LETTER FINAL PE
0x05E4: 0x64, # HEBREW LETTER PE
0x05E5: 0x65, # HEBREW LETTER FINAL TSADI
0x05E6: 0x66, # HEBREW LETTER TSADI
0x05E7: 0x67, # HEBREW LETTER QOF
0x05E8: 0x68, # HEBREW LETTER RESH
0x05E9: 0x69, # HEBREW LETTER SHIN
0x05EA: 0x71, # HEBREW LETTER TAV
0x2017: 0x78, # DOUBLE LOW LINE
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x37, # END OF TRANSMISSION
0x0005: 0x2D, # ENQUIRY
0x0006: 0x2E, # ACKNOWLEDGE
0x0007: 0x2F, # BELL
0x0008: 0x16, # BACKSPACE
0x0009: 0x05, # HORIZONTAL TABULATION
0x000A: 0x25, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x3C, # DEVICE CONTROL FOUR
0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE
0x0016: 0x32, # SYNCHRONOUS IDLE
0x0017: 0x26, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x3F, # SUBSTITUTE
0x001B: 0x27, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x40, # SPACE
0x0021: 0x5A, # EXCLAMATION MARK
0x0022: 0x7F, # QUOTATION MARK
0x0023: 0x7B, # NUMBER SIGN
0x0024: 0x5B, # DOLLAR SIGN
0x0025: 0x6C, # PERCENT SIGN
0x0026: 0x50, # AMPERSAND
0x0027: 0x7D, # APOSTROPHE
0x0028: 0x4D, # LEFT PARENTHESIS
0x0029: 0x5D, # RIGHT PARENTHESIS
0x002A: 0x5C, # ASTERISK
0x002B: 0x4E, # PLUS SIGN
0x002C: 0x6B, # COMMA
0x002D: 0x60, # HYPHEN-MINUS
0x002E: 0x4B, # FULL STOP
0x002F: 0x61, # SOLIDUS
0x0030: 0xF0, # DIGIT ZERO
0x0031: 0xF1, # DIGIT ONE
0x0032: 0xF2, # DIGIT TWO
0x0033: 0xF3, # DIGIT THREE
0x0034: 0xF4, # DIGIT FOUR
0x0035: 0xF5, # DIGIT FIVE
0x0036: 0xF6, # DIGIT SIX
0x0037: 0xF7, # DIGIT SEVEN
0x0038: 0xF8, # DIGIT EIGHT
0x0039: 0xF9, # DIGIT NINE
0x003A: 0x7A, # COLON
0x003B: 0x5E, # SEMICOLON
0x003C: 0x4C, # LESS-THAN SIGN
0x003D: 0x7E, # EQUALS SIGN
0x003E: 0x6E, # GREATER-THAN SIGN
0x003F: 0x6F, # QUESTION MARK
0x0040: 0x7C, # COMMERCIAL AT
0x0041: 0xC1, # LATIN CAPITAL LETTER A
0x0042: 0xC2, # LATIN CAPITAL LETTER B
0x0043: 0xC3, # LATIN CAPITAL LETTER C
0x0044: 0xC4, # LATIN CAPITAL LETTER D
0x0045: 0xC5, # LATIN CAPITAL LETTER E
0x0046: 0xC6, # LATIN CAPITAL LETTER F
0x0047: 0xC7, # LATIN CAPITAL LETTER G
0x0048: 0xC8, # LATIN CAPITAL LETTER H
0x0049: 0xC9, # LATIN CAPITAL LETTER I
0x004A: 0xD1, # LATIN CAPITAL LETTER J
0x004B: 0xD2, # LATIN CAPITAL LETTER K
0x004C: 0xD3, # LATIN CAPITAL LETTER L
0x004D: 0xD4, # LATIN CAPITAL LETTER M
0x004E: 0xD5, # LATIN CAPITAL LETTER N
0x004F: 0xD6, # LATIN CAPITAL LETTER O
0x0050: 0xD7, # LATIN CAPITAL LETTER P
0x0051: 0xD8, # LATIN CAPITAL LETTER Q
0x0052: 0xD9, # LATIN CAPITAL LETTER R
0x0053: 0xE2, # LATIN CAPITAL LETTER S
0x0054: 0xE3, # LATIN CAPITAL LETTER T
0x0055: 0xE4, # LATIN CAPITAL LETTER U
0x0056: 0xE5, # LATIN CAPITAL LETTER V
0x0057: 0xE6, # LATIN CAPITAL LETTER W
0x0058: 0xE7, # LATIN CAPITAL LETTER X
0x0059: 0xE8, # LATIN CAPITAL LETTER Y
0x005A: 0xE9, # LATIN CAPITAL LETTER Z
0x005B: 0xBA, # LEFT SQUARE BRACKET
0x005C: 0xE0, # REVERSE SOLIDUS
0x005D: 0xBB, # RIGHT SQUARE BRACKET
0x005E: 0xB0, # CIRCUMFLEX ACCENT
0x005F: 0x6D, # LOW LINE
0x0060: 0x79, # GRAVE ACCENT
0x0061: 0x81, # LATIN SMALL LETTER A
0x0062: 0x82, # LATIN SMALL LETTER B
0x0063: 0x83, # LATIN SMALL LETTER C
0x0064: 0x84, # LATIN SMALL LETTER D
0x0065: 0x85, # LATIN SMALL LETTER E
0x0066: 0x86, # LATIN SMALL LETTER F
0x0067: 0x87, # LATIN SMALL LETTER G
0x0068: 0x88, # LATIN SMALL LETTER H
0x0069: 0x89, # LATIN SMALL LETTER I
0x006A: 0x91, # LATIN SMALL LETTER J
0x006B: 0x92, # LATIN SMALL LETTER K
0x006C: 0x93, # LATIN SMALL LETTER L
0x006D: 0x94, # LATIN SMALL LETTER M
0x006E: 0x95, # LATIN SMALL LETTER N
0x006F: 0x96, # LATIN SMALL LETTER O
0x0070: 0x97, # LATIN SMALL LETTER P
0x0071: 0x98, # LATIN SMALL LETTER Q
0x0072: 0x99, # LATIN SMALL LETTER R
0x0073: 0xA2, # LATIN SMALL LETTER S
0x0074: 0xA3, # LATIN SMALL LETTER T
0x0075: 0xA4, # LATIN SMALL LETTER U
0x0076: 0xA5, # LATIN SMALL LETTER V
0x0077: 0xA6, # LATIN SMALL LETTER W
0x0078: 0xA7, # LATIN SMALL LETTER X
0x0079: 0xA8, # LATIN SMALL LETTER Y
0x007A: 0xA9, # LATIN SMALL LETTER Z
0x007B: 0xC0, # LEFT CURLY BRACKET
0x007C: 0x4F, # VERTICAL LINE
0x007D: 0xD0, # RIGHT CURLY BRACKET
0x007E: 0xA1, # TILDE
0x007F: 0x07, # DELETE
0x0080: 0x20, # DIGIT SELECT
0x0081: 0x21, # START OF SIGNIFICANCE
0x0082: 0x22, # FIELD SEPARATOR
0x0083: 0x23, # WORD UNDERSCORE
0x0084: 0x24, # BYPASS OR INHIBIT PRESENTATION
0x0085: 0x15, # NEW LINE
0x0086: 0x06, # REQUIRED NEW LINE
0x0087: 0x17, # PROGRAM OPERATOR COMMUNICATION
0x0088: 0x28, # SET ATTRIBUTE
0x0089: 0x29, # START FIELD EXTENDED
0x008A: 0x2A, # SET MODE OR SWITCH
0x008B: 0x2B, # CONTROL SEQUENCE PREFIX
0x008C: 0x2C, # MODIFY FIELD ATTRIBUTE
0x008D: 0x09, # SUPERSCRIPT
0x008E: 0x0A, # REPEAT
0x008F: 0x1B, # CUSTOMER USE ONE
0x0090: 0x30, # <reserved>
0x0091: 0x31, # <reserved>
0x0092: 0x1A, # UNIT BACK SPACE
0x0093: 0x33, # INDEX RETURN
0x0094: 0x34, # PRESENTATION POSITION
0x0095: 0x35, # TRANSPARENT
0x0096: 0x36, # NUMERIC BACKSPACE
0x0097: 0x08, # GRAPHIC ESCAPE
0x0098: 0x38, # SUBSCRIPT
0x0099: 0x39, # INDENT TABULATION
0x009A: 0x3A, # REVERSE FORM FEED
0x009B: 0x3B, # CUSTOMER USE THREE
0x009C: 0x04, # SELECT
0x009D: 0x14, # RESTORE/ENABLE PRESENTATION
0x009E: 0x3E, # <reserved>
0x009F: 0xFF, # EIGHT ONES
0x00A0: 0x74, # NO-BREAK SPACE
0x00A2: 0x4A, # CENT SIGN
0x00A3: 0xB1, # POUND SIGN
0x00A4: 0x9F, # CURRENCY SIGN
0x00A5: 0xB2, # YEN SIGN
0x00A6: 0x6A, # BROKEN BAR
0x00A7: 0xB5, # SECTION SIGN
0x00A8: 0xBD, # DIAERESIS
0x00A9: 0xB4, # COPYRIGHT SIGN
0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC: 0x5F, # NOT SIGN
0x00AD: 0xCA, # SOFT HYPHEN
0x00AE: 0xAF, # REGISTERED SIGN
0x00AF: 0xBC, # MACRON
0x00B0: 0x90, # DEGREE SIGN
0x00B1: 0x8F, # PLUS-MINUS SIGN
0x00B2: 0xEA, # SUPERSCRIPT TWO
0x00B3: 0xFA, # SUPERSCRIPT THREE
0x00B4: 0xBE, # ACUTE ACCENT
0x00B5: 0xA0, # MICRO SIGN
0x00B6: 0xB6, # PILCROW SIGN
0x00B7: 0xB3, # MIDDLE DOT
0x00B8: 0x9D, # CEDILLA
0x00B9: 0xDA, # SUPERSCRIPT ONE
0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER
0x00BD: 0xB8, # VULGAR FRACTION ONE HALF
0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS
0x00D7: 0xBF, # MULTIPLICATION SIGN
0x00F7: 0xE1, # DIVISION SIGN
0x05D0: 0x41, # HEBREW LETTER ALEF
0x05D1: 0x42, # HEBREW LETTER BET
0x05D2: 0x43, # HEBREW LETTER GIMEL
0x05D3: 0x44, # HEBREW LETTER DALET
0x05D4: 0x45, # HEBREW LETTER HE
0x05D5: 0x46, # HEBREW LETTER VAV
0x05D6: 0x47, # HEBREW LETTER ZAYIN
0x05D7: 0x48, # HEBREW LETTER HET
0x05D8: 0x49, # HEBREW LETTER TET
0x05D9: 0x51, # HEBREW LETTER YOD
0x05DA: 0x52, # HEBREW LETTER FINAL KAF
0x05DB: 0x53, # HEBREW LETTER KAF
0x05DC: 0x54, # HEBREW LETTER LAMED
0x05DD: 0x55, # HEBREW LETTER FINAL MEM
0x05DE: 0x56, # HEBREW LETTER MEM
0x05DF: 0x57, # HEBREW LETTER FINAL NUN
0x05E0: 0x58, # HEBREW LETTER NUN
0x05E1: 0x59, # HEBREW LETTER SAMEKH
0x05E2: 0x62, # HEBREW LETTER AYIN
0x05E3: 0x63, # HEBREW LETTER FINAL PE
0x05E4: 0x64, # HEBREW LETTER PE
0x05E5: 0x65, # HEBREW LETTER FINAL TSADI
0x05E6: 0x66, # HEBREW LETTER TSADI
0x05E7: 0x67, # HEBREW LETTER QOF
0x05E8: 0x68, # HEBREW LETTER RESH
0x05E9: 0x69, # HEBREW LETTER SHIN
0x05EA: 0x71, # HEBREW LETTER TAV
0x2017: 0x78, # DOUBLE LOW LINE
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -15,7 +15,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter):
pass
@ -32,481 +32,480 @@ def getregentry():
### Decoding Table
decoding_table = (
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\u05d0' # 0x80 -> HEBREW LETTER ALEF
u'\u05d1' # 0x81 -> HEBREW LETTER BET
u'\u05d2' # 0x82 -> HEBREW LETTER GIMEL
u'\u05d3' # 0x83 -> HEBREW LETTER DALET
u'\u05d4' # 0x84 -> HEBREW LETTER HE
u'\u05d5' # 0x85 -> HEBREW LETTER VAV
u'\u05d6' # 0x86 -> HEBREW LETTER ZAYIN
u'\u05d7' # 0x87 -> HEBREW LETTER HET
u'\u05d8' # 0x88 -> HEBREW LETTER TET
u'\u05d9' # 0x89 -> HEBREW LETTER YOD
u'\u05da' # 0x8A -> HEBREW LETTER FINAL KAF
u'\u05db' # 0x8B -> HEBREW LETTER KAF
u'\u05dc' # 0x8C -> HEBREW LETTER LAMED
u'\u05dd' # 0x8D -> HEBREW LETTER FINAL MEM
u'\u05de' # 0x8E -> HEBREW LETTER MEM
u'\u05df' # 0x8F -> HEBREW LETTER FINAL NUN
u'\u05e0' # 0x90 -> HEBREW LETTER NUN
u'\u05e1' # 0x91 -> HEBREW LETTER SAMEKH
u'\u05e2' # 0x92 -> HEBREW LETTER AYIN
u'\u05e3' # 0x93 -> HEBREW LETTER FINAL PE
u'\u05e4' # 0x94 -> HEBREW LETTER PE
u'\u05e5' # 0x95 -> HEBREW LETTER FINAL TSADI
u'\u05e6' # 0x96 -> HEBREW LETTER TSADI
u'\u05e7' # 0x97 -> HEBREW LETTER QOF
u'\u05e8' # 0x98 -> HEBREW LETTER RESH
u'\u05e9' # 0x99 -> HEBREW LETTER SHIN
u'\u05ea' # 0x9A -> HEBREW LETTER TAV
u'\ufffe' # 0x9B -> UNDEFINED
u'\xa3' # 0x9C -> POUND SIGN
u'\ufffe' # 0x9D -> UNDEFINED
u'\xd7' # 0x9E -> MULTIPLICATION SIGN
u'\ufffe' # 0x9F -> UNDEFINED
u'\ufffe' # 0xA0 -> UNDEFINED
u'\ufffe' # 0xA1 -> UNDEFINED
u'\ufffe' # 0xA2 -> UNDEFINED
u'\ufffe' # 0xA3 -> UNDEFINED
u'\ufffe' # 0xA4 -> UNDEFINED
u'\ufffe' # 0xA5 -> UNDEFINED
u'\ufffe' # 0xA6 -> UNDEFINED
u'\ufffe' # 0xA7 -> UNDEFINED
u'\ufffe' # 0xA8 -> UNDEFINED
u'\xae' # 0xA9 -> REGISTERED SIGN
u'\xac' # 0xAA -> NOT SIGN
u'\xbd' # 0xAB -> VULGAR FRACTION ONE HALF
u'\xbc' # 0xAC -> VULGAR FRACTION ONE QUARTER
u'\ufffe' # 0xAD -> UNDEFINED
u'\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\u2591' # 0xB0 -> LIGHT SHADE
u'\u2592' # 0xB1 -> MEDIUM SHADE
u'\u2593' # 0xB2 -> DARK SHADE
u'\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL
u'\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
u'\ufffe' # 0xB5 -> UNDEFINED
u'\ufffe' # 0xB6 -> UNDEFINED
u'\ufffe' # 0xB7 -> UNDEFINED
u'\xa9' # 0xB8 -> COPYRIGHT SIGN
u'\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
u'\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL
u'\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT
u'\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT
u'\xa2' # 0xBD -> CENT SIGN
u'\xa5' # 0xBE -> YEN SIGN
u'\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT
u'\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT
u'\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
u'\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
u'\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
u'\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL
u'\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
u'\ufffe' # 0xC6 -> UNDEFINED
u'\ufffe' # 0xC7 -> UNDEFINED
u'\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
u'\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
u'\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
u'\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
u'\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
u'\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL
u'\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
u'\xa4' # 0xCF -> CURRENCY SIGN
u'\ufffe' # 0xD0 -> UNDEFINED
u'\ufffe' # 0xD1 -> UNDEFINED
u'\ufffe' # 0xD2 -> UNDEFINED
u'\ufffe' # 0xD3 -> UNDEFINEDS
u'\ufffe' # 0xD4 -> UNDEFINED
u'\ufffe' # 0xD5 -> UNDEFINED
u'\ufffe' # 0xD6 -> UNDEFINEDE
u'\ufffe' # 0xD7 -> UNDEFINED
u'\ufffe' # 0xD8 -> UNDEFINED
u'\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT
u'\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT
u'\u2588' # 0xDB -> FULL BLOCK
u'\u2584' # 0xDC -> LOWER HALF BLOCK
u'\xa6' # 0xDD -> BROKEN BAR
u'\ufffe' # 0xDE -> UNDEFINED
u'\u2580' # 0xDF -> UPPER HALF BLOCK
u'\ufffe' # 0xE0 -> UNDEFINED
u'\ufffe' # 0xE1 -> UNDEFINED
u'\ufffe' # 0xE2 -> UNDEFINED
u'\ufffe' # 0xE3 -> UNDEFINED
u'\ufffe' # 0xE4 -> UNDEFINED
u'\ufffe' # 0xE5 -> UNDEFINED
u'\xb5' # 0xE6 -> MICRO SIGN
u'\ufffe' # 0xE7 -> UNDEFINED
u'\ufffe' # 0xE8 -> UNDEFINED
u'\ufffe' # 0xE9 -> UNDEFINED
u'\ufffe' # 0xEA -> UNDEFINED
u'\ufffe' # 0xEB -> UNDEFINED
u'\ufffe' # 0xEC -> UNDEFINED
u'\ufffe' # 0xED -> UNDEFINED
u'\xaf' # 0xEE -> MACRON
u'\xb4' # 0xEF -> ACUTE ACCENT
u'\xad' # 0xF0 -> SOFT HYPHEN
u'\xb1' # 0xF1 -> PLUS-MINUS SIGN
u'\u2017' # 0xF2 -> DOUBLE LOW LINE
u'\xbe' # 0xF3 -> VULGAR FRACTION THREE QUARTERS
u'\xb6' # 0xF4 -> PILCROW SIGN
u'\xa7' # 0xF5 -> SECTION SIGN
u'\xf7' # 0xF6 -> DIVISION SIGN
u'\xb8' # 0xF7 -> CEDILLA
u'\xb0' # 0xF8 -> DEGREE SIGN
u'\xa8' # 0xF9 -> DIAERESIS
u'\xb7' # 0xFA -> MIDDLE DOT
u'\xb9' # 0xFB -> SUPERSCRIPT ONE
u'\xb3' # 0xFC -> SUPERSCRIPT THREE
u'\xb2' # 0xFD -> SUPERSCRIPT TWO
u'\u25a0' # 0xFE -> BLACK SQUARE
u'\xa0' # 0xFF -> NO-BREAK SPACE
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\u05d0' # 0x80 -> HEBREW LETTER ALEF
u'\u05d1' # 0x81 -> HEBREW LETTER BET
u'\u05d2' # 0x82 -> HEBREW LETTER GIMEL
u'\u05d3' # 0x83 -> HEBREW LETTER DALET
u'\u05d4' # 0x84 -> HEBREW LETTER HE
u'\u05d5' # 0x85 -> HEBREW LETTER VAV
u'\u05d6' # 0x86 -> HEBREW LETTER ZAYIN
u'\u05d7' # 0x87 -> HEBREW LETTER HET
u'\u05d8' # 0x88 -> HEBREW LETTER TET
u'\u05d9' # 0x89 -> HEBREW LETTER YOD
u'\u05da' # 0x8A -> HEBREW LETTER FINAL KAF
u'\u05db' # 0x8B -> HEBREW LETTER KAF
u'\u05dc' # 0x8C -> HEBREW LETTER LAMED
u'\u05dd' # 0x8D -> HEBREW LETTER FINAL MEM
u'\u05de' # 0x8E -> HEBREW LETTER MEM
u'\u05df' # 0x8F -> HEBREW LETTER FINAL NUN
u'\u05e0' # 0x90 -> HEBREW LETTER NUN
u'\u05e1' # 0x91 -> HEBREW LETTER SAMEKH
u'\u05e2' # 0x92 -> HEBREW LETTER AYIN
u'\u05e3' # 0x93 -> HEBREW LETTER FINAL PE
u'\u05e4' # 0x94 -> HEBREW LETTER PE
u'\u05e5' # 0x95 -> HEBREW LETTER FINAL TSADI
u'\u05e6' # 0x96 -> HEBREW LETTER TSADI
u'\u05e7' # 0x97 -> HEBREW LETTER QOF
u'\u05e8' # 0x98 -> HEBREW LETTER RESH
u'\u05e9' # 0x99 -> HEBREW LETTER SHIN
u'\u05ea' # 0x9A -> HEBREW LETTER TAV
u'\ufffe' # 0x9B -> UNDEFINED
u'\xa3' # 0x9C -> POUND SIGN
u'\ufffe' # 0x9D -> UNDEFINED
u'\xd7' # 0x9E -> MULTIPLICATION SIGN
u'\ufffe' # 0x9F -> UNDEFINED
u'\ufffe' # 0xA0 -> UNDEFINED
u'\ufffe' # 0xA1 -> UNDEFINED
u'\ufffe' # 0xA2 -> UNDEFINED
u'\ufffe' # 0xA3 -> UNDEFINED
u'\ufffe' # 0xA4 -> UNDEFINED
u'\ufffe' # 0xA5 -> UNDEFINED
u'\ufffe' # 0xA6 -> UNDEFINED
u'\ufffe' # 0xA7 -> UNDEFINED
u'\ufffe' # 0xA8 -> UNDEFINED
u'\xae' # 0xA9 -> REGISTERED SIGN
u'\xac' # 0xAA -> NOT SIGN
u'\xbd' # 0xAB -> VULGAR FRACTION ONE HALF
u'\xbc' # 0xAC -> VULGAR FRACTION ONE QUARTER
u'\ufffe' # 0xAD -> UNDEFINED
u'\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\u2591' # 0xB0 -> LIGHT SHADE
u'\u2592' # 0xB1 -> MEDIUM SHADE
u'\u2593' # 0xB2 -> DARK SHADE
u'\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL
u'\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
u'\ufffe' # 0xB5 -> UNDEFINED
u'\ufffe' # 0xB6 -> UNDEFINED
u'\ufffe' # 0xB7 -> UNDEFINED
u'\xa9' # 0xB8 -> COPYRIGHT SIGN
u'\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
u'\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL
u'\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT
u'\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT
u'\xa2' # 0xBD -> CENT SIGN
u'\xa5' # 0xBE -> YEN SIGN
u'\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT
u'\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT
u'\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
u'\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
u'\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
u'\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL
u'\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
u'\ufffe' # 0xC6 -> UNDEFINED
u'\ufffe' # 0xC7 -> UNDEFINED
u'\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
u'\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
u'\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
u'\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
u'\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
u'\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL
u'\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
u'\xa4' # 0xCF -> CURRENCY SIGN
u'\ufffe' # 0xD0 -> UNDEFINED
u'\ufffe' # 0xD1 -> UNDEFINED
u'\ufffe' # 0xD2 -> UNDEFINED
u'\ufffe' # 0xD3 -> UNDEFINEDS
u'\ufffe' # 0xD4 -> UNDEFINED
u'\ufffe' # 0xD5 -> UNDEFINED
u'\ufffe' # 0xD6 -> UNDEFINEDE
u'\ufffe' # 0xD7 -> UNDEFINED
u'\ufffe' # 0xD8 -> UNDEFINED
u'\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT
u'\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT
u'\u2588' # 0xDB -> FULL BLOCK
u'\u2584' # 0xDC -> LOWER HALF BLOCK
u'\xa6' # 0xDD -> BROKEN BAR
u'\ufffe' # 0xDE -> UNDEFINED
u'\u2580' # 0xDF -> UPPER HALF BLOCK
u'\ufffe' # 0xE0 -> UNDEFINED
u'\ufffe' # 0xE1 -> UNDEFINED
u'\ufffe' # 0xE2 -> UNDEFINED
u'\ufffe' # 0xE3 -> UNDEFINED
u'\ufffe' # 0xE4 -> UNDEFINED
u'\ufffe' # 0xE5 -> UNDEFINED
u'\xb5' # 0xE6 -> MICRO SIGN
u'\ufffe' # 0xE7 -> UNDEFINED
u'\ufffe' # 0xE8 -> UNDEFINED
u'\ufffe' # 0xE9 -> UNDEFINED
u'\ufffe' # 0xEA -> UNDEFINED
u'\ufffe' # 0xEB -> UNDEFINED
u'\ufffe' # 0xEC -> UNDEFINED
u'\ufffe' # 0xED -> UNDEFINED
u'\xaf' # 0xEE -> MACRON
u'\xb4' # 0xEF -> ACUTE ACCENT
u'\xad' # 0xF0 -> SOFT HYPHEN
u'\xb1' # 0xF1 -> PLUS-MINUS SIGN
u'\u2017' # 0xF2 -> DOUBLE LOW LINE
u'\xbe' # 0xF3 -> VULGAR FRACTION THREE QUARTERS
u'\xb6' # 0xF4 -> PILCROW SIGN
u'\xa7' # 0xF5 -> SECTION SIGN
u'\xf7' # 0xF6 -> DIVISION SIGN
u'\xb8' # 0xF7 -> CEDILLA
u'\xb0' # 0xF8 -> DEGREE SIGN
u'\xa8' # 0xF9 -> DIAERESIS
u'\xb7' # 0xFA -> MIDDLE DOT
u'\xb9' # 0xFB -> SUPERSCRIPT ONE
u'\xb3' # 0xFC -> SUPERSCRIPT THREE
u'\xb2' # 0xFD -> SUPERSCRIPT TWO
u'\u25a0' # 0xFE -> BLACK SQUARE
u'\xa0' # 0xFF -> NO-BREAK SPACE
)
### Encoding Map
encoding_map = {
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x00A0: 0xFF, # NO-BREAK SPACE
0x00A2: 0xBD, # CENT SIGN
0x00A3: 0x9C, # POUND SIGN
0x00A4: 0xCF, # CURRENCY SIGN
0x00A5: 0xBE, # YEN SIGN
0x00A6: 0xDD, # BROKEN BAR
0x00A7: 0xF5, # SECTION SIGN
0x00A8: 0xF9, # DIAERESIS
0x00A9: 0xB8, # COPYRIGHT SIGN
0x00AB: 0xAE, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC: 0xAA, # NOT SIGN
0x00AD: 0xF0, # SOFT HYPHEN
0x00AE: 0xA9, # REGISTERED SIGN
0x00AF: 0xEE, # MACRON
0x00B0: 0xF8, # DEGREE SIGN
0x00B1: 0xF1, # PLUS-MINUS SIGN
0x00B2: 0xFD, # SUPERSCRIPT TWO
0x00B3: 0xFC, # SUPERSCRIPT THREE
0x00B4: 0xEF, # ACUTE ACCENT
0x00B5: 0xE6, # MICRO SIGN
0x00B6: 0xF4, # PILCROW SIGN
0x00B7: 0xFA, # MIDDLE DOT
0x00B8: 0xF7, # CEDILLA
0x00B9: 0xFB, # SUPERSCRIPT ONE
0x00BB: 0xAF, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC: 0xAC, # VULGAR FRACTION ONE QUARTER
0x00BD: 0xAB, # VULGAR FRACTION ONE HALF
0x00BE: 0xF3, # VULGAR FRACTION THREE QUARTERS
0x00D7: 0x9E, # MULTIPLICATION SIGN
0x00F7: 0xF6, # DIVISION SIGN
0x05D0: 0x80, # HEBREW LETTER ALEF
0x05D1: 0x81, # HEBREW LETTER BET
0x05D2: 0x82, # HEBREW LETTER GIMEL
0x05D3: 0x83, # HEBREW LETTER DALET
0x05D4: 0x84, # HEBREW LETTER HE
0x05D5: 0x85, # HEBREW LETTER VAV
0x05D6: 0x86, # HEBREW LETTER ZAYIN
0x05D7: 0x87, # HEBREW LETTER HET
0x05D8: 0x88, # HEBREW LETTER TET
0x05D9: 0x89, # HEBREW LETTER YOD
0x05DA: 0x8A, # HEBREW LETTER FINAL KAF
0x05DB: 0x8B, # HEBREW LETTER KAF
0x05DC: 0x8C, # HEBREW LETTER LAMED
0x05DD: 0x8D, # HEBREW LETTER FINAL MEM
0x05DE: 0x8E, # HEBREW LETTER MEM
0x05DF: 0x8F, # HEBREW LETTER FINAL NUN
0x05E0: 0x90, # HEBREW LETTER NUN
0x05E1: 0x91, # HEBREW LETTER SAMEKH
0x05E2: 0x92, # HEBREW LETTER AYIN
0x05E3: 0x93, # HEBREW LETTER FINAL PE
0x05E4: 0x94, # HEBREW LETTER PE
0x05E5: 0x95, # HEBREW LETTER FINAL TSADI
0x05E6: 0x96, # HEBREW LETTER TSADI
0x05E7: 0x97, # HEBREW LETTER QOF
0x05E8: 0x98, # HEBREW LETTER RESH
0x05E9: 0x99, # HEBREW LETTER SHIN
0x05EA: 0x9A, # HEBREW LETTER TAV
0x2017: 0xF2, # DOUBLE LOW LINE
0x2500: 0xC4, # BOX DRAWINGS LIGHT HORIZONTAL
0x2502: 0xB3, # BOX DRAWINGS LIGHT VERTICAL
0x250C: 0xDA, # BOX DRAWINGS LIGHT DOWN AND RIGHT
0x2510: 0xBF, # BOX DRAWINGS LIGHT DOWN AND LEFT
0x2514: 0xC0, # BOX DRAWINGS LIGHT UP AND RIGHT
0x2518: 0xD9, # BOX DRAWINGS LIGHT UP AND LEFT
0x251C: 0xC3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0x2524: 0xB4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
0x252C: 0xC2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0x2534: 0xC1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
0x253C: 0xC5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0x2550: 0xCD, # BOX DRAWINGS DOUBLE HORIZONTAL
0x2551: 0xBA, # BOX DRAWINGS DOUBLE VERTICAL
0x2554: 0xC9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
0x2557: 0xBB, # BOX DRAWINGS DOUBLE DOWN AND LEFT
0x255A: 0xC8, # BOX DRAWINGS DOUBLE UP AND RIGHT
0x255D: 0xBC, # BOX DRAWINGS DOUBLE UP AND LEFT
0x2560: 0xCC, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0x2563: 0xB9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0x2566: 0xCB, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0x2569: 0xCA, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0x256C: 0xCE, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0x2580: 0xDF, # UPPER HALF BLOCK
0x2584: 0xDC, # LOWER HALF BLOCK
0x2588: 0xDB, # FULL BLOCK
0x2591: 0xB0, # LIGHT SHADE
0x2592: 0xB1, # MEDIUM SHADE
0x2593: 0xB2, # DARK SHADE
0x25A0: 0xFE, # BLACK SQUARE
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x00A0: 0xFF, # NO-BREAK SPACE
0x00A2: 0xBD, # CENT SIGN
0x00A3: 0x9C, # POUND SIGN
0x00A4: 0xCF, # CURRENCY SIGN
0x00A5: 0xBE, # YEN SIGN
0x00A6: 0xDD, # BROKEN BAR
0x00A7: 0xF5, # SECTION SIGN
0x00A8: 0xF9, # DIAERESIS
0x00A9: 0xB8, # COPYRIGHT SIGN
0x00AB: 0xAE, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC: 0xAA, # NOT SIGN
0x00AD: 0xF0, # SOFT HYPHEN
0x00AE: 0xA9, # REGISTERED SIGN
0x00AF: 0xEE, # MACRON
0x00B0: 0xF8, # DEGREE SIGN
0x00B1: 0xF1, # PLUS-MINUS SIGN
0x00B2: 0xFD, # SUPERSCRIPT TWO
0x00B3: 0xFC, # SUPERSCRIPT THREE
0x00B4: 0xEF, # ACUTE ACCENT
0x00B5: 0xE6, # MICRO SIGN
0x00B6: 0xF4, # PILCROW SIGN
0x00B7: 0xFA, # MIDDLE DOT
0x00B8: 0xF7, # CEDILLA
0x00B9: 0xFB, # SUPERSCRIPT ONE
0x00BB: 0xAF, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC: 0xAC, # VULGAR FRACTION ONE QUARTER
0x00BD: 0xAB, # VULGAR FRACTION ONE HALF
0x00BE: 0xF3, # VULGAR FRACTION THREE QUARTERS
0x00D7: 0x9E, # MULTIPLICATION SIGN
0x00F7: 0xF6, # DIVISION SIGN
0x05D0: 0x80, # HEBREW LETTER ALEF
0x05D1: 0x81, # HEBREW LETTER BET
0x05D2: 0x82, # HEBREW LETTER GIMEL
0x05D3: 0x83, # HEBREW LETTER DALET
0x05D4: 0x84, # HEBREW LETTER HE
0x05D5: 0x85, # HEBREW LETTER VAV
0x05D6: 0x86, # HEBREW LETTER ZAYIN
0x05D7: 0x87, # HEBREW LETTER HET
0x05D8: 0x88, # HEBREW LETTER TET
0x05D9: 0x89, # HEBREW LETTER YOD
0x05DA: 0x8A, # HEBREW LETTER FINAL KAF
0x05DB: 0x8B, # HEBREW LETTER KAF
0x05DC: 0x8C, # HEBREW LETTER LAMED
0x05DD: 0x8D, # HEBREW LETTER FINAL MEM
0x05DE: 0x8E, # HEBREW LETTER MEM
0x05DF: 0x8F, # HEBREW LETTER FINAL NUN
0x05E0: 0x90, # HEBREW LETTER NUN
0x05E1: 0x91, # HEBREW LETTER SAMEKH
0x05E2: 0x92, # HEBREW LETTER AYIN
0x05E3: 0x93, # HEBREW LETTER FINAL PE
0x05E4: 0x94, # HEBREW LETTER PE
0x05E5: 0x95, # HEBREW LETTER FINAL TSADI
0x05E6: 0x96, # HEBREW LETTER TSADI
0x05E7: 0x97, # HEBREW LETTER QOF
0x05E8: 0x98, # HEBREW LETTER RESH
0x05E9: 0x99, # HEBREW LETTER SHIN
0x05EA: 0x9A, # HEBREW LETTER TAV
0x2017: 0xF2, # DOUBLE LOW LINE
0x2500: 0xC4, # BOX DRAWINGS LIGHT HORIZONTAL
0x2502: 0xB3, # BOX DRAWINGS LIGHT VERTICAL
0x250C: 0xDA, # BOX DRAWINGS LIGHT DOWN AND RIGHT
0x2510: 0xBF, # BOX DRAWINGS LIGHT DOWN AND LEFT
0x2514: 0xC0, # BOX DRAWINGS LIGHT UP AND RIGHT
0x2518: 0xD9, # BOX DRAWINGS LIGHT UP AND LEFT
0x251C: 0xC3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
0x2524: 0xB4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
0x252C: 0xC2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
0x2534: 0xC1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
0x253C: 0xC5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
0x2550: 0xCD, # BOX DRAWINGS DOUBLE HORIZONTAL
0x2551: 0xBA, # BOX DRAWINGS DOUBLE VERTICAL
0x2554: 0xC9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
0x2557: 0xBB, # BOX DRAWINGS DOUBLE DOWN AND LEFT
0x255A: 0xC8, # BOX DRAWINGS DOUBLE UP AND RIGHT
0x255D: 0xBC, # BOX DRAWINGS DOUBLE UP AND LEFT
0x2560: 0xCC, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
0x2563: 0xB9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
0x2566: 0xCB, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
0x2569: 0xCA, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
0x256C: 0xCE, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
0x2580: 0xDF, # UPPER HALF BLOCK
0x2584: 0xDC, # LOWER HALF BLOCK
0x2588: 0xDB, # FULL BLOCK
0x2591: 0xB0, # LIGHT SHADE
0x2592: 0xB1, # MEDIUM SHADE
0x2593: 0xB2, # DARK SHADE
0x25A0: 0xFE, # BLACK SQUARE
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -15,7 +15,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter):
pass
@ -32,491 +32,490 @@ def getregentry():
### Decoding Table
decoding_table = (
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\u20ac' # 0x80 -> EURO SIGN
u'\ufffe' # 0x81 -> UNDEFINED
u'\ufffe' # 0x82 -> UNDEFINED
u'\ufffe' # 0x83 -> UNDEFINED
u'\ufffe' # 0x84 -> UNDEFINED
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
u'\ufffe' # 0x86 -> UNDEFINED
u'\ufffe' # 0x87 -> UNDEFINED
u'\ufffe' # 0x88 -> UNDEFINED
u'\ufffe' # 0x89 -> UNDEFINED
u'\ufffe' # 0x8A -> UNDEFINED
u'\ufffe' # 0x8B -> UNDEFINED
u'\ufffe' # 0x8C -> UNDEFINED
u'\ufffe' # 0x8D -> UNDEFINED
u'\ufffe' # 0x8E -> UNDEFINED
u'\ufffe' # 0x8F -> UNDEFINED
u'\ufffe' # 0x90 -> UNDEFINED
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
u'\u2022' # 0x95 -> BULLET
u'\u2013' # 0x96 -> EN DASH
u'\u2014' # 0x97 -> EM DASH
u'\ufffe' # 0x98 -> UNDEFINED
u'\ufffe' # 0x99 -> UNDEFINED
u'\ufffe' # 0x9A -> UNDEFINED
u'\ufffe' # 0x9B -> UNDEFINED
u'\ufffe' # 0x9C -> UNDEFINED
u'\ufffe' # 0x9D -> UNDEFINED
u'\ufffe' # 0x9E -> UNDEFINED
u'\ufffe' # 0x9F -> UNDEFINED
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI
u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI
u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT
u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI
u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON
u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG
u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU
u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN
u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING
u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG
u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO
u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE
u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING
u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA
u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK
u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN
u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO
u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO
u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN
u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK
u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO
u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG
u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN
u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG
u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU
u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI
u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA
u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG
u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA
u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN
u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN
u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO
u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA
u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK
u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA
u'\u0e24' # 0xC4 -> THAI CHARACTER RU
u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING
u'\u0e26' # 0xC6 -> THAI CHARACTER LU
u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN
u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA
u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI
u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA
u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP
u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA
u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG
u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK
u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI
u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A
u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT
u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA
u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM
u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I
u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II
u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE
u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE
u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U
u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU
u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU
u'\ufffe' # 0xDB -> UNDEFINED
u'\ufffe' # 0xDC -> UNDEFINED
u'\ufffe' # 0xDD -> UNDEFINED
u'\ufffe' # 0xDE -> UNDEFINED
u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT
u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E
u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE
u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O
u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN
u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI
u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO
u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK
u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU
u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK
u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO
u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI
u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA
u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT
u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT
u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN
u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN
u'\u0e50' # 0xF0 -> THAI DIGIT ZERO
u'\u0e51' # 0xF1 -> THAI DIGIT ONE
u'\u0e52' # 0xF2 -> THAI DIGIT TWO
u'\u0e53' # 0xF3 -> THAI DIGIT THREE
u'\u0e54' # 0xF4 -> THAI DIGIT FOUR
u'\u0e55' # 0xF5 -> THAI DIGIT FIVE
u'\u0e56' # 0xF6 -> THAI DIGIT SIX
u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN
u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT
u'\u0e59' # 0xF9 -> THAI DIGIT NINE
u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU
u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT
u'\ufffe' # 0xFC -> UNDEFINED
u'\ufffe' # 0xFD -> UNDEFINED
u'\ufffe' # 0xFE -> UNDEFINED
u'\ufffe' # 0xFF -> UNDEFINED
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\u20ac' # 0x80 -> EURO SIGN
u'\ufffe' # 0x81 -> UNDEFINED
u'\ufffe' # 0x82 -> UNDEFINED
u'\ufffe' # 0x83 -> UNDEFINED
u'\ufffe' # 0x84 -> UNDEFINED
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
u'\ufffe' # 0x86 -> UNDEFINED
u'\ufffe' # 0x87 -> UNDEFINED
u'\ufffe' # 0x88 -> UNDEFINED
u'\ufffe' # 0x89 -> UNDEFINED
u'\ufffe' # 0x8A -> UNDEFINED
u'\ufffe' # 0x8B -> UNDEFINED
u'\ufffe' # 0x8C -> UNDEFINED
u'\ufffe' # 0x8D -> UNDEFINED
u'\ufffe' # 0x8E -> UNDEFINED
u'\ufffe' # 0x8F -> UNDEFINED
u'\ufffe' # 0x90 -> UNDEFINED
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
u'\u2022' # 0x95 -> BULLET
u'\u2013' # 0x96 -> EN DASH
u'\u2014' # 0x97 -> EM DASH
u'\ufffe' # 0x98 -> UNDEFINED
u'\ufffe' # 0x99 -> UNDEFINED
u'\ufffe' # 0x9A -> UNDEFINED
u'\ufffe' # 0x9B -> UNDEFINED
u'\ufffe' # 0x9C -> UNDEFINED
u'\ufffe' # 0x9D -> UNDEFINED
u'\ufffe' # 0x9E -> UNDEFINED
u'\ufffe' # 0x9F -> UNDEFINED
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI
u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI
u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT
u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI
u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON
u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG
u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU
u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN
u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING
u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG
u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO
u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE
u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING
u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA
u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK
u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN
u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO
u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO
u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN
u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK
u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO
u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG
u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN
u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG
u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU
u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI
u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA
u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG
u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA
u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN
u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN
u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO
u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA
u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK
u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA
u'\u0e24' # 0xC4 -> THAI CHARACTER RU
u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING
u'\u0e26' # 0xC6 -> THAI CHARACTER LU
u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN
u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA
u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI
u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA
u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP
u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA
u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG
u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK
u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI
u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A
u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT
u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA
u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM
u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I
u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II
u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE
u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE
u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U
u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU
u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU
u'\ufffe' # 0xDB -> UNDEFINED
u'\ufffe' # 0xDC -> UNDEFINED
u'\ufffe' # 0xDD -> UNDEFINED
u'\ufffe' # 0xDE -> UNDEFINED
u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT
u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E
u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE
u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O
u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN
u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI
u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO
u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK
u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU
u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK
u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO
u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI
u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA
u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT
u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT
u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN
u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN
u'\u0e50' # 0xF0 -> THAI DIGIT ZERO
u'\u0e51' # 0xF1 -> THAI DIGIT ONE
u'\u0e52' # 0xF2 -> THAI DIGIT TWO
u'\u0e53' # 0xF3 -> THAI DIGIT THREE
u'\u0e54' # 0xF4 -> THAI DIGIT FOUR
u'\u0e55' # 0xF5 -> THAI DIGIT FIVE
u'\u0e56' # 0xF6 -> THAI DIGIT SIX
u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN
u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT
u'\u0e59' # 0xF9 -> THAI DIGIT NINE
u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU
u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT
u'\ufffe' # 0xFC -> UNDEFINED
u'\ufffe' # 0xFD -> UNDEFINED
u'\ufffe' # 0xFE -> UNDEFINED
u'\ufffe' # 0xFF -> UNDEFINED
)
### Encoding Map
encoding_map = {
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x00A0: 0xA0, # NO-BREAK SPACE
0x0E01: 0xA1, # THAI CHARACTER KO KAI
0x0E02: 0xA2, # THAI CHARACTER KHO KHAI
0x0E03: 0xA3, # THAI CHARACTER KHO KHUAT
0x0E04: 0xA4, # THAI CHARACTER KHO KHWAI
0x0E05: 0xA5, # THAI CHARACTER KHO KHON
0x0E06: 0xA6, # THAI CHARACTER KHO RAKHANG
0x0E07: 0xA7, # THAI CHARACTER NGO NGU
0x0E08: 0xA8, # THAI CHARACTER CHO CHAN
0x0E09: 0xA9, # THAI CHARACTER CHO CHING
0x0E0A: 0xAA, # THAI CHARACTER CHO CHANG
0x0E0B: 0xAB, # THAI CHARACTER SO SO
0x0E0C: 0xAC, # THAI CHARACTER CHO CHOE
0x0E0D: 0xAD, # THAI CHARACTER YO YING
0x0E0E: 0xAE, # THAI CHARACTER DO CHADA
0x0E0F: 0xAF, # THAI CHARACTER TO PATAK
0x0E10: 0xB0, # THAI CHARACTER THO THAN
0x0E11: 0xB1, # THAI CHARACTER THO NANGMONTHO
0x0E12: 0xB2, # THAI CHARACTER THO PHUTHAO
0x0E13: 0xB3, # THAI CHARACTER NO NEN
0x0E14: 0xB4, # THAI CHARACTER DO DEK
0x0E15: 0xB5, # THAI CHARACTER TO TAO
0x0E16: 0xB6, # THAI CHARACTER THO THUNG
0x0E17: 0xB7, # THAI CHARACTER THO THAHAN
0x0E18: 0xB8, # THAI CHARACTER THO THONG
0x0E19: 0xB9, # THAI CHARACTER NO NU
0x0E1A: 0xBA, # THAI CHARACTER BO BAIMAI
0x0E1B: 0xBB, # THAI CHARACTER PO PLA
0x0E1C: 0xBC, # THAI CHARACTER PHO PHUNG
0x0E1D: 0xBD, # THAI CHARACTER FO FA
0x0E1E: 0xBE, # THAI CHARACTER PHO PHAN
0x0E1F: 0xBF, # THAI CHARACTER FO FAN
0x0E20: 0xC0, # THAI CHARACTER PHO SAMPHAO
0x0E21: 0xC1, # THAI CHARACTER MO MA
0x0E22: 0xC2, # THAI CHARACTER YO YAK
0x0E23: 0xC3, # THAI CHARACTER RO RUA
0x0E24: 0xC4, # THAI CHARACTER RU
0x0E25: 0xC5, # THAI CHARACTER LO LING
0x0E26: 0xC6, # THAI CHARACTER LU
0x0E27: 0xC7, # THAI CHARACTER WO WAEN
0x0E28: 0xC8, # THAI CHARACTER SO SALA
0x0E29: 0xC9, # THAI CHARACTER SO RUSI
0x0E2A: 0xCA, # THAI CHARACTER SO SUA
0x0E2B: 0xCB, # THAI CHARACTER HO HIP
0x0E2C: 0xCC, # THAI CHARACTER LO CHULA
0x0E2D: 0xCD, # THAI CHARACTER O ANG
0x0E2E: 0xCE, # THAI CHARACTER HO NOKHUK
0x0E2F: 0xCF, # THAI CHARACTER PAIYANNOI
0x0E30: 0xD0, # THAI CHARACTER SARA A
0x0E31: 0xD1, # THAI CHARACTER MAI HAN-AKAT
0x0E32: 0xD2, # THAI CHARACTER SARA AA
0x0E33: 0xD3, # THAI CHARACTER SARA AM
0x0E34: 0xD4, # THAI CHARACTER SARA I
0x0E35: 0xD5, # THAI CHARACTER SARA II
0x0E36: 0xD6, # THAI CHARACTER SARA UE
0x0E37: 0xD7, # THAI CHARACTER SARA UEE
0x0E38: 0xD8, # THAI CHARACTER SARA U
0x0E39: 0xD9, # THAI CHARACTER SARA UU
0x0E3A: 0xDA, # THAI CHARACTER PHINTHU
0x0E3F: 0xDF, # THAI CURRENCY SYMBOL BAHT
0x0E40: 0xE0, # THAI CHARACTER SARA E
0x0E41: 0xE1, # THAI CHARACTER SARA AE
0x0E42: 0xE2, # THAI CHARACTER SARA O
0x0E43: 0xE3, # THAI CHARACTER SARA AI MAIMUAN
0x0E44: 0xE4, # THAI CHARACTER SARA AI MAIMALAI
0x0E45: 0xE5, # THAI CHARACTER LAKKHANGYAO
0x0E46: 0xE6, # THAI CHARACTER MAIYAMOK
0x0E47: 0xE7, # THAI CHARACTER MAITAIKHU
0x0E48: 0xE8, # THAI CHARACTER MAI EK
0x0E49: 0xE9, # THAI CHARACTER MAI THO
0x0E4A: 0xEA, # THAI CHARACTER MAI TRI
0x0E4B: 0xEB, # THAI CHARACTER MAI CHATTAWA
0x0E4C: 0xEC, # THAI CHARACTER THANTHAKHAT
0x0E4D: 0xED, # THAI CHARACTER NIKHAHIT
0x0E4E: 0xEE, # THAI CHARACTER YAMAKKAN
0x0E4F: 0xEF, # THAI CHARACTER FONGMAN
0x0E50: 0xF0, # THAI DIGIT ZERO
0x0E51: 0xF1, # THAI DIGIT ONE
0x0E52: 0xF2, # THAI DIGIT TWO
0x0E53: 0xF3, # THAI DIGIT THREE
0x0E54: 0xF4, # THAI DIGIT FOUR
0x0E55: 0xF5, # THAI DIGIT FIVE
0x0E56: 0xF6, # THAI DIGIT SIX
0x0E57: 0xF7, # THAI DIGIT SEVEN
0x0E58: 0xF8, # THAI DIGIT EIGHT
0x0E59: 0xF9, # THAI DIGIT NINE
0x0E5A: 0xFA, # THAI CHARACTER ANGKHANKHU
0x0E5B: 0xFB, # THAI CHARACTER KHOMUT
0x2013: 0x96, # EN DASH
0x2014: 0x97, # EM DASH
0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
0x2022: 0x95, # BULLET
0x2026: 0x85, # HORIZONTAL ELLIPSIS
0x20AC: 0x80, # EURO SIGN
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x00A0: 0xA0, # NO-BREAK SPACE
0x0E01: 0xA1, # THAI CHARACTER KO KAI
0x0E02: 0xA2, # THAI CHARACTER KHO KHAI
0x0E03: 0xA3, # THAI CHARACTER KHO KHUAT
0x0E04: 0xA4, # THAI CHARACTER KHO KHWAI
0x0E05: 0xA5, # THAI CHARACTER KHO KHON
0x0E06: 0xA6, # THAI CHARACTER KHO RAKHANG
0x0E07: 0xA7, # THAI CHARACTER NGO NGU
0x0E08: 0xA8, # THAI CHARACTER CHO CHAN
0x0E09: 0xA9, # THAI CHARACTER CHO CHING
0x0E0A: 0xAA, # THAI CHARACTER CHO CHANG
0x0E0B: 0xAB, # THAI CHARACTER SO SO
0x0E0C: 0xAC, # THAI CHARACTER CHO CHOE
0x0E0D: 0xAD, # THAI CHARACTER YO YING
0x0E0E: 0xAE, # THAI CHARACTER DO CHADA
0x0E0F: 0xAF, # THAI CHARACTER TO PATAK
0x0E10: 0xB0, # THAI CHARACTER THO THAN
0x0E11: 0xB1, # THAI CHARACTER THO NANGMONTHO
0x0E12: 0xB2, # THAI CHARACTER THO PHUTHAO
0x0E13: 0xB3, # THAI CHARACTER NO NEN
0x0E14: 0xB4, # THAI CHARACTER DO DEK
0x0E15: 0xB5, # THAI CHARACTER TO TAO
0x0E16: 0xB6, # THAI CHARACTER THO THUNG
0x0E17: 0xB7, # THAI CHARACTER THO THAHAN
0x0E18: 0xB8, # THAI CHARACTER THO THONG
0x0E19: 0xB9, # THAI CHARACTER NO NU
0x0E1A: 0xBA, # THAI CHARACTER BO BAIMAI
0x0E1B: 0xBB, # THAI CHARACTER PO PLA
0x0E1C: 0xBC, # THAI CHARACTER PHO PHUNG
0x0E1D: 0xBD, # THAI CHARACTER FO FA
0x0E1E: 0xBE, # THAI CHARACTER PHO PHAN
0x0E1F: 0xBF, # THAI CHARACTER FO FAN
0x0E20: 0xC0, # THAI CHARACTER PHO SAMPHAO
0x0E21: 0xC1, # THAI CHARACTER MO MA
0x0E22: 0xC2, # THAI CHARACTER YO YAK
0x0E23: 0xC3, # THAI CHARACTER RO RUA
0x0E24: 0xC4, # THAI CHARACTER RU
0x0E25: 0xC5, # THAI CHARACTER LO LING
0x0E26: 0xC6, # THAI CHARACTER LU
0x0E27: 0xC7, # THAI CHARACTER WO WAEN
0x0E28: 0xC8, # THAI CHARACTER SO SALA
0x0E29: 0xC9, # THAI CHARACTER SO RUSI
0x0E2A: 0xCA, # THAI CHARACTER SO SUA
0x0E2B: 0xCB, # THAI CHARACTER HO HIP
0x0E2C: 0xCC, # THAI CHARACTER LO CHULA
0x0E2D: 0xCD, # THAI CHARACTER O ANG
0x0E2E: 0xCE, # THAI CHARACTER HO NOKHUK
0x0E2F: 0xCF, # THAI CHARACTER PAIYANNOI
0x0E30: 0xD0, # THAI CHARACTER SARA A
0x0E31: 0xD1, # THAI CHARACTER MAI HAN-AKAT
0x0E32: 0xD2, # THAI CHARACTER SARA AA
0x0E33: 0xD3, # THAI CHARACTER SARA AM
0x0E34: 0xD4, # THAI CHARACTER SARA I
0x0E35: 0xD5, # THAI CHARACTER SARA II
0x0E36: 0xD6, # THAI CHARACTER SARA UE
0x0E37: 0xD7, # THAI CHARACTER SARA UEE
0x0E38: 0xD8, # THAI CHARACTER SARA U
0x0E39: 0xD9, # THAI CHARACTER SARA UU
0x0E3A: 0xDA, # THAI CHARACTER PHINTHU
0x0E3F: 0xDF, # THAI CURRENCY SYMBOL BAHT
0x0E40: 0xE0, # THAI CHARACTER SARA E
0x0E41: 0xE1, # THAI CHARACTER SARA AE
0x0E42: 0xE2, # THAI CHARACTER SARA O
0x0E43: 0xE3, # THAI CHARACTER SARA AI MAIMUAN
0x0E44: 0xE4, # THAI CHARACTER SARA AI MAIMALAI
0x0E45: 0xE5, # THAI CHARACTER LAKKHANGYAO
0x0E46: 0xE6, # THAI CHARACTER MAIYAMOK
0x0E47: 0xE7, # THAI CHARACTER MAITAIKHU
0x0E48: 0xE8, # THAI CHARACTER MAI EK
0x0E49: 0xE9, # THAI CHARACTER MAI THO
0x0E4A: 0xEA, # THAI CHARACTER MAI TRI
0x0E4B: 0xEB, # THAI CHARACTER MAI CHATTAWA
0x0E4C: 0xEC, # THAI CHARACTER THANTHAKHAT
0x0E4D: 0xED, # THAI CHARACTER NIKHAHIT
0x0E4E: 0xEE, # THAI CHARACTER YAMAKKAN
0x0E4F: 0xEF, # THAI CHARACTER FONGMAN
0x0E50: 0xF0, # THAI DIGIT ZERO
0x0E51: 0xF1, # THAI DIGIT ONE
0x0E52: 0xF2, # THAI DIGIT TWO
0x0E53: 0xF3, # THAI DIGIT THREE
0x0E54: 0xF4, # THAI DIGIT FOUR
0x0E55: 0xF5, # THAI DIGIT FIVE
0x0E56: 0xF6, # THAI DIGIT SIX
0x0E57: 0xF7, # THAI DIGIT SEVEN
0x0E58: 0xF8, # THAI DIGIT EIGHT
0x0E59: 0xF9, # THAI DIGIT NINE
0x0E5A: 0xFA, # THAI CHARACTER ANGKHANKHU
0x0E5B: 0xFB, # THAI CHARACTER KHOMUT
0x2013: 0x96, # EN DASH
0x2014: 0x97, # EM DASH
0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
0x2022: 0x95, # BULLET
0x2026: 0x85, # HORIZONTAL ELLIPSIS
0x20AC: 0x80, # EURO SIGN
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -15,7 +15,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter):
pass
@ -32,171 +32,171 @@ def getregentry():
### Decoding Table
decoding_table = (
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\x80' # 0x80 -> <control>
u'\x81' # 0x81 -> <control>
u'\x82' # 0x82 -> <control>
u'\x83' # 0x83 -> <control>
u'\x84' # 0x84 -> <control>
u'\x85' # 0x85 -> <control>
u'\x86' # 0x86 -> <control>
u'\x87' # 0x87 -> <control>
u'\x88' # 0x88 -> <control>
u'\x89' # 0x89 -> <control>
u'\x8a' # 0x8A -> <control>
u'\x8b' # 0x8B -> <control>
u'\x8c' # 0x8C -> <control>
u'\x8d' # 0x8D -> <control>
u'\x8e' # 0x8E -> <control>
u'\x8f' # 0x8F -> <control>
u'\x90' # 0x90 -> <control>
u'\x91' # 0x91 -> <control>
u'\x92' # 0x92 -> <control>
u'\x93' # 0x93 -> <control>
u'\x94' # 0x94 -> <control>
u'\x95' # 0x95 -> <control>
u'\x96' # 0x96 -> <control>
u'\x97' # 0x97 -> <control>
u'\x98' # 0x98 -> <control>
u'\x99' # 0x99 -> <control>
u'\x9a' # 0x9A -> <control>
u'\x9b' # 0x9B -> <control>
u'\x9c' # 0x9C -> <control>
u'\x9d' # 0x9D -> <control>
u'\x9e' # 0x9E -> <control>
u'\x9f' # 0x9F -> <control>
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\x80' # 0x80 -> <control>
u'\x81' # 0x81 -> <control>
u'\x82' # 0x82 -> <control>
u'\x83' # 0x83 -> <control>
u'\x84' # 0x84 -> <control>
u'\x85' # 0x85 -> <control>
u'\x86' # 0x86 -> <control>
u'\x87' # 0x87 -> <control>
u'\x88' # 0x88 -> <control>
u'\x89' # 0x89 -> <control>
u'\x8a' # 0x8A -> <control>
u'\x8b' # 0x8B -> <control>
u'\x8c' # 0x8C -> <control>
u'\x8d' # 0x8D -> <control>
u'\x8e' # 0x8E -> <control>
u'\x8f' # 0x8F -> <control>
u'\x90' # 0x90 -> <control>
u'\x91' # 0x91 -> <control>
u'\x92' # 0x92 -> <control>
u'\x93' # 0x93 -> <control>
u'\x94' # 0x94 -> <control>
u'\x95' # 0x95 -> <control>
u'\x96' # 0x96 -> <control>
u'\x97' # 0x97 -> <control>
u'\x98' # 0x98 -> <control>
u'\x99' # 0x99 -> <control>
u'\x9a' # 0x9A -> <control>
u'\x9b' # 0x9B -> <control>
u'\x9c' # 0x9C -> <control>
u'\x9d' # 0x9D -> <control>
u'\x9e' # 0x9E -> <control>
u'\x9f' # 0x9F -> <control>
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\ufffe'
u'\ufffe'
u'\ufffe'
u'\xa4' # 0xA4 -> CURRENCY SIGN
u'\xa4' # 0xA4 -> CURRENCY SIGN
u'\ufffe'
u'\ufffe'
u'\ufffe'
@ -204,8 +204,8 @@ decoding_table = (
u'\ufffe'
u'\ufffe'
u'\ufffe'
u'\u060c' # 0xAC -> ARABIC COMMA
u'\xad' # 0xAD -> SOFT HYPHEN
u'\u060c' # 0xAC -> ARABIC COMMA
u'\xad' # 0xAD -> SOFT HYPHEN
u'\ufffe'
u'\ufffe'
u'\ufffe'
@ -219,62 +219,62 @@ decoding_table = (
u'\ufffe'
u'\ufffe'
u'\ufffe'
u'\u061b' # 0xBB -> ARABIC SEMICOLON
u'\u061b' # 0xBB -> ARABIC SEMICOLON
u'\ufffe'
u'\ufffe'
u'\ufffe'
u'\u061f' # 0xBF -> ARABIC QUESTION MARK
u'\u061f' # 0xBF -> ARABIC QUESTION MARK
u'\ufffe'
u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA
u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE
u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE
u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE
u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW
u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE
u'\u0627' # 0xC7 -> ARABIC LETTER ALEF
u'\u0628' # 0xC8 -> ARABIC LETTER BEH
u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA
u'\u062a' # 0xCA -> ARABIC LETTER TEH
u'\u062b' # 0xCB -> ARABIC LETTER THEH
u'\u062c' # 0xCC -> ARABIC LETTER JEEM
u'\u062d' # 0xCD -> ARABIC LETTER HAH
u'\u062e' # 0xCE -> ARABIC LETTER KHAH
u'\u062f' # 0xCF -> ARABIC LETTER DAL
u'\u0630' # 0xD0 -> ARABIC LETTER THAL
u'\u0631' # 0xD1 -> ARABIC LETTER REH
u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN
u'\u0633' # 0xD3 -> ARABIC LETTER SEEN
u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN
u'\u0635' # 0xD5 -> ARABIC LETTER SAD
u'\u0636' # 0xD6 -> ARABIC LETTER DAD
u'\u0637' # 0xD7 -> ARABIC LETTER TAH
u'\u0638' # 0xD8 -> ARABIC LETTER ZAH
u'\u0639' # 0xD9 -> ARABIC LETTER AIN
u'\u063a' # 0xDA -> ARABIC LETTER GHAIN
u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA
u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE
u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE
u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE
u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW
u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE
u'\u0627' # 0xC7 -> ARABIC LETTER ALEF
u'\u0628' # 0xC8 -> ARABIC LETTER BEH
u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA
u'\u062a' # 0xCA -> ARABIC LETTER TEH
u'\u062b' # 0xCB -> ARABIC LETTER THEH
u'\u062c' # 0xCC -> ARABIC LETTER JEEM
u'\u062d' # 0xCD -> ARABIC LETTER HAH
u'\u062e' # 0xCE -> ARABIC LETTER KHAH
u'\u062f' # 0xCF -> ARABIC LETTER DAL
u'\u0630' # 0xD0 -> ARABIC LETTER THAL
u'\u0631' # 0xD1 -> ARABIC LETTER REH
u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN
u'\u0633' # 0xD3 -> ARABIC LETTER SEEN
u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN
u'\u0635' # 0xD5 -> ARABIC LETTER SAD
u'\u0636' # 0xD6 -> ARABIC LETTER DAD
u'\u0637' # 0xD7 -> ARABIC LETTER TAH
u'\u0638' # 0xD8 -> ARABIC LETTER ZAH
u'\u0639' # 0xD9 -> ARABIC LETTER AIN
u'\u063a' # 0xDA -> ARABIC LETTER GHAIN
u'\ufffe'
u'\ufffe'
u'\ufffe'
u'\ufffe'
u'\ufffe'
u'\u0640' # 0xE0 -> ARABIC TATWEEL
u'\u0641' # 0xE1 -> ARABIC LETTER FEH
u'\u0642' # 0xE2 -> ARABIC LETTER QAF
u'\u0643' # 0xE3 -> ARABIC LETTER KAF
u'\u0644' # 0xE4 -> ARABIC LETTER LAM
u'\u0645' # 0xE5 -> ARABIC LETTER MEEM
u'\u0646' # 0xE6 -> ARABIC LETTER NOON
u'\u0647' # 0xE7 -> ARABIC LETTER HEH
u'\u0648' # 0xE8 -> ARABIC LETTER WAW
u'\u0649' # 0xE9 -> ARABIC LETTER ALEF MAKSURA
u'\u064a' # 0xEA -> ARABIC LETTER YEH
u'\u064b' # 0xEB -> ARABIC FATHATAN
u'\u064c' # 0xEC -> ARABIC DAMMATAN
u'\u064d' # 0xED -> ARABIC KASRATAN
u'\u064e' # 0xEE -> ARABIC FATHA
u'\u064f' # 0xEF -> ARABIC DAMMA
u'\u0650' # 0xF0 -> ARABIC KASRA
u'\u0651' # 0xF1 -> ARABIC SHADDA
u'\u0652' # 0xF2 -> ARABIC SUKUN
u'\u0640' # 0xE0 -> ARABIC TATWEEL
u'\u0641' # 0xE1 -> ARABIC LETTER FEH
u'\u0642' # 0xE2 -> ARABIC LETTER QAF
u'\u0643' # 0xE3 -> ARABIC LETTER KAF
u'\u0644' # 0xE4 -> ARABIC LETTER LAM
u'\u0645' # 0xE5 -> ARABIC LETTER MEEM
u'\u0646' # 0xE6 -> ARABIC LETTER NOON
u'\u0647' # 0xE7 -> ARABIC LETTER HEH
u'\u0648' # 0xE8 -> ARABIC LETTER WAW
u'\u0649' # 0xE9 -> ARABIC LETTER ALEF MAKSURA
u'\u064a' # 0xEA -> ARABIC LETTER YEH
u'\u064b' # 0xEB -> ARABIC FATHATAN
u'\u064c' # 0xEC -> ARABIC DAMMATAN
u'\u064d' # 0xED -> ARABIC KASRATAN
u'\u064e' # 0xEE -> ARABIC FATHA
u'\u064f' # 0xEF -> ARABIC DAMMA
u'\u0650' # 0xF0 -> ARABIC KASRA
u'\u0651' # 0xF1 -> ARABIC SHADDA
u'\u0652' # 0xF2 -> ARABIC SUKUN
u'\ufffe'
u'\ufffe'
u'\ufffe'
@ -293,216 +293,215 @@ decoding_table = (
### Encoding Map
encoding_map = {
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x0080: 0x80, # <control>
0x0081: 0x81, # <control>
0x0082: 0x82, # <control>
0x0083: 0x83, # <control>
0x0084: 0x84, # <control>
0x0085: 0x85, # <control>
0x0086: 0x86, # <control>
0x0087: 0x87, # <control>
0x0088: 0x88, # <control>
0x0089: 0x89, # <control>
0x008A: 0x8A, # <control>
0x008B: 0x8B, # <control>
0x008C: 0x8C, # <control>
0x008D: 0x8D, # <control>
0x008E: 0x8E, # <control>
0x008F: 0x8F, # <control>
0x0090: 0x90, # <control>
0x0091: 0x91, # <control>
0x0092: 0x92, # <control>
0x0093: 0x93, # <control>
0x0094: 0x94, # <control>
0x0095: 0x95, # <control>
0x0096: 0x96, # <control>
0x0097: 0x97, # <control>
0x0098: 0x98, # <control>
0x0099: 0x99, # <control>
0x009A: 0x9A, # <control>
0x009B: 0x9B, # <control>
0x009C: 0x9C, # <control>
0x009D: 0x9D, # <control>
0x009E: 0x9E, # <control>
0x009F: 0x9F, # <control>
0x00A0: 0xA0, # NO-BREAK SPACE
0x00A4: 0xA4, # CURRENCY SIGN
0x00AD: 0xAD, # SOFT HYPHEN
0x060C: 0xAC, # ARABIC COMMA
0x061B: 0xBB, # ARABIC SEMICOLON
0x061F: 0xBF, # ARABIC QUESTION MARK
0x0621: 0xC1, # ARABIC LETTER HAMZA
0x0622: 0xC2, # ARABIC LETTER ALEF WITH MADDA ABOVE
0x0623: 0xC3, # ARABIC LETTER ALEF WITH HAMZA ABOVE
0x0624: 0xC4, # ARABIC LETTER WAW WITH HAMZA ABOVE
0x0625: 0xC5, # ARABIC LETTER ALEF WITH HAMZA BELOW
0x0626: 0xC6, # ARABIC LETTER YEH WITH HAMZA ABOVE
0x0627: 0xC7, # ARABIC LETTER ALEF
0x0628: 0xC8, # ARABIC LETTER BEH
0x0629: 0xC9, # ARABIC LETTER TEH MARBUTA
0x062A: 0xCA, # ARABIC LETTER TEH
0x062B: 0xCB, # ARABIC LETTER THEH
0x062C: 0xCC, # ARABIC LETTER JEEM
0x062D: 0xCD, # ARABIC LETTER HAH
0x062E: 0xCE, # ARABIC LETTER KHAH
0x062F: 0xCF, # ARABIC LETTER DAL
0x0630: 0xD0, # ARABIC LETTER THAL
0x0631: 0xD1, # ARABIC LETTER REH
0x0632: 0xD2, # ARABIC LETTER ZAIN
0x0633: 0xD3, # ARABIC LETTER SEEN
0x0634: 0xD4, # ARABIC LETTER SHEEN
0x0635: 0xD5, # ARABIC LETTER SAD
0x0636: 0xD6, # ARABIC LETTER DAD
0x0637: 0xD7, # ARABIC LETTER TAH
0x0638: 0xD8, # ARABIC LETTER ZAH
0x0639: 0xD9, # ARABIC LETTER AIN
0x063A: 0xDA, # ARABIC LETTER GHAIN
0x0640: 0xE0, # ARABIC TATWEEL
0x0641: 0xE1, # ARABIC LETTER FEH
0x0642: 0xE2, # ARABIC LETTER QAF
0x0643: 0xE3, # ARABIC LETTER KAF
0x0644: 0xE4, # ARABIC LETTER LAM
0x0645: 0xE5, # ARABIC LETTER MEEM
0x0646: 0xE6, # ARABIC LETTER NOON
0x0647: 0xE7, # ARABIC LETTER HEH
0x0648: 0xE8, # ARABIC LETTER WAW
0x0649: 0xE9, # ARABIC LETTER ALEF MAKSURA
0x064A: 0xEA, # ARABIC LETTER YEH
0x064B: 0xEB, # ARABIC FATHATAN
0x064C: 0xEC, # ARABIC DAMMATAN
0x064D: 0xED, # ARABIC KASRATAN
0x064E: 0xEE, # ARABIC FATHA
0x064F: 0xEF, # ARABIC DAMMA
0x0650: 0xF0, # ARABIC KASRA
0x0651: 0xF1, # ARABIC SHADDA
0x0652: 0xF2, # ARABIC SUKUN
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x0080: 0x80, # <control>
0x0081: 0x81, # <control>
0x0082: 0x82, # <control>
0x0083: 0x83, # <control>
0x0084: 0x84, # <control>
0x0085: 0x85, # <control>
0x0086: 0x86, # <control>
0x0087: 0x87, # <control>
0x0088: 0x88, # <control>
0x0089: 0x89, # <control>
0x008A: 0x8A, # <control>
0x008B: 0x8B, # <control>
0x008C: 0x8C, # <control>
0x008D: 0x8D, # <control>
0x008E: 0x8E, # <control>
0x008F: 0x8F, # <control>
0x0090: 0x90, # <control>
0x0091: 0x91, # <control>
0x0092: 0x92, # <control>
0x0093: 0x93, # <control>
0x0094: 0x94, # <control>
0x0095: 0x95, # <control>
0x0096: 0x96, # <control>
0x0097: 0x97, # <control>
0x0098: 0x98, # <control>
0x0099: 0x99, # <control>
0x009A: 0x9A, # <control>
0x009B: 0x9B, # <control>
0x009C: 0x9C, # <control>
0x009D: 0x9D, # <control>
0x009E: 0x9E, # <control>
0x009F: 0x9F, # <control>
0x00A0: 0xA0, # NO-BREAK SPACE
0x00A4: 0xA4, # CURRENCY SIGN
0x00AD: 0xAD, # SOFT HYPHEN
0x060C: 0xAC, # ARABIC COMMA
0x061B: 0xBB, # ARABIC SEMICOLON
0x061F: 0xBF, # ARABIC QUESTION MARK
0x0621: 0xC1, # ARABIC LETTER HAMZA
0x0622: 0xC2, # ARABIC LETTER ALEF WITH MADDA ABOVE
0x0623: 0xC3, # ARABIC LETTER ALEF WITH HAMZA ABOVE
0x0624: 0xC4, # ARABIC LETTER WAW WITH HAMZA ABOVE
0x0625: 0xC5, # ARABIC LETTER ALEF WITH HAMZA BELOW
0x0626: 0xC6, # ARABIC LETTER YEH WITH HAMZA ABOVE
0x0627: 0xC7, # ARABIC LETTER ALEF
0x0628: 0xC8, # ARABIC LETTER BEH
0x0629: 0xC9, # ARABIC LETTER TEH MARBUTA
0x062A: 0xCA, # ARABIC LETTER TEH
0x062B: 0xCB, # ARABIC LETTER THEH
0x062C: 0xCC, # ARABIC LETTER JEEM
0x062D: 0xCD, # ARABIC LETTER HAH
0x062E: 0xCE, # ARABIC LETTER KHAH
0x062F: 0xCF, # ARABIC LETTER DAL
0x0630: 0xD0, # ARABIC LETTER THAL
0x0631: 0xD1, # ARABIC LETTER REH
0x0632: 0xD2, # ARABIC LETTER ZAIN
0x0633: 0xD3, # ARABIC LETTER SEEN
0x0634: 0xD4, # ARABIC LETTER SHEEN
0x0635: 0xD5, # ARABIC LETTER SAD
0x0636: 0xD6, # ARABIC LETTER DAD
0x0637: 0xD7, # ARABIC LETTER TAH
0x0638: 0xD8, # ARABIC LETTER ZAH
0x0639: 0xD9, # ARABIC LETTER AIN
0x063A: 0xDA, # ARABIC LETTER GHAIN
0x0640: 0xE0, # ARABIC TATWEEL
0x0641: 0xE1, # ARABIC LETTER FEH
0x0642: 0xE2, # ARABIC LETTER QAF
0x0643: 0xE3, # ARABIC LETTER KAF
0x0644: 0xE4, # ARABIC LETTER LAM
0x0645: 0xE5, # ARABIC LETTER MEEM
0x0646: 0xE6, # ARABIC LETTER NOON
0x0647: 0xE7, # ARABIC LETTER HEH
0x0648: 0xE8, # ARABIC LETTER WAW
0x0649: 0xE9, # ARABIC LETTER ALEF MAKSURA
0x064A: 0xEA, # ARABIC LETTER YEH
0x064B: 0xEB, # ARABIC FATHATAN
0x064C: 0xEC, # ARABIC DAMMATAN
0x064D: 0xED, # ARABIC KASRATAN
0x064E: 0xEE, # ARABIC FATHA
0x064F: 0xEF, # ARABIC DAMMA
0x0650: 0xF0, # ARABIC KASRA
0x0651: 0xF1, # ARABIC SHADDA
0x0652: 0xF2, # ARABIC SUKUN
}

File diff suppressed because it is too large Load Diff

View File

@ -15,7 +15,7 @@ class Codec(codecs.Codec):
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class StreamWriter(Codec,codecs.StreamWriter):
pass
@ -32,197 +32,197 @@ def getregentry():
### Decoding Table
decoding_table = (
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\x80' # 0x80 -> <control>
u'\x81' # 0x81 -> <control>
u'\x82' # 0x82 -> <control>
u'\x83' # 0x83 -> <control>
u'\x84' # 0x84 -> <control>
u'\x85' # 0x85 -> <control>
u'\x86' # 0x86 -> <control>
u'\x87' # 0x87 -> <control>
u'\x88' # 0x88 -> <control>
u'\x89' # 0x89 -> <control>
u'\x8a' # 0x8A -> <control>
u'\x8b' # 0x8B -> <control>
u'\x8c' # 0x8C -> <control>
u'\x8d' # 0x8D -> <control>
u'\x8e' # 0x8E -> <control>
u'\x8f' # 0x8F -> <control>
u'\x90' # 0x90 -> <control>
u'\x91' # 0x91 -> <control>
u'\x92' # 0x92 -> <control>
u'\x93' # 0x93 -> <control>
u'\x94' # 0x94 -> <control>
u'\x95' # 0x95 -> <control>
u'\x96' # 0x96 -> <control>
u'\x97' # 0x97 -> <control>
u'\x98' # 0x98 -> <control>
u'\x99' # 0x99 -> <control>
u'\x9a' # 0x9A -> <control>
u'\x9b' # 0x9B -> <control>
u'\x9c' # 0x9C -> <control>
u'\x9d' # 0x9D -> <control>
u'\x9e' # 0x9E -> <control>
u'\x9f' # 0x9F -> <control>
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\x00' # 0x00 -> NULL
u'\x01' # 0x01 -> START OF HEADING
u'\x02' # 0x02 -> START OF TEXT
u'\x03' # 0x03 -> END OF TEXT
u'\x04' # 0x04 -> END OF TRANSMISSION
u'\x05' # 0x05 -> ENQUIRY
u'\x06' # 0x06 -> ACKNOWLEDGE
u'\x07' # 0x07 -> BELL
u'\x08' # 0x08 -> BACKSPACE
u'\t' # 0x09 -> HORIZONTAL TABULATION
u'\n' # 0x0A -> LINE FEED
u'\x0b' # 0x0B -> VERTICAL TABULATION
u'\x0c' # 0x0C -> FORM FEED
u'\r' # 0x0D -> CARRIAGE RETURN
u'\x0e' # 0x0E -> SHIFT OUT
u'\x0f' # 0x0F -> SHIFT IN
u'\x10' # 0x10 -> DATA LINK ESCAPE
u'\x11' # 0x11 -> DEVICE CONTROL ONE
u'\x12' # 0x12 -> DEVICE CONTROL TWO
u'\x13' # 0x13 -> DEVICE CONTROL THREE
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x1a' # 0x1A -> SUBSTITUTE
u'\x1b' # 0x1B -> ESCAPE
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> DELETE
u'\x80' # 0x80 -> <control>
u'\x81' # 0x81 -> <control>
u'\x82' # 0x82 -> <control>
u'\x83' # 0x83 -> <control>
u'\x84' # 0x84 -> <control>
u'\x85' # 0x85 -> <control>
u'\x86' # 0x86 -> <control>
u'\x87' # 0x87 -> <control>
u'\x88' # 0x88 -> <control>
u'\x89' # 0x89 -> <control>
u'\x8a' # 0x8A -> <control>
u'\x8b' # 0x8B -> <control>
u'\x8c' # 0x8C -> <control>
u'\x8d' # 0x8D -> <control>
u'\x8e' # 0x8E -> <control>
u'\x8f' # 0x8F -> <control>
u'\x90' # 0x90 -> <control>
u'\x91' # 0x91 -> <control>
u'\x92' # 0x92 -> <control>
u'\x93' # 0x93 -> <control>
u'\x94' # 0x94 -> <control>
u'\x95' # 0x95 -> <control>
u'\x96' # 0x96 -> <control>
u'\x97' # 0x97 -> <control>
u'\x98' # 0x98 -> <control>
u'\x99' # 0x99 -> <control>
u'\x9a' # 0x9A -> <control>
u'\x9b' # 0x9B -> <control>
u'\x9c' # 0x9C -> <control>
u'\x9d' # 0x9D -> <control>
u'\x9e' # 0x9E -> <control>
u'\x9f' # 0x9F -> <control>
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\ufffe'
u'\xa2' # 0xA2 -> CENT SIGN
u'\xa3' # 0xA3 -> POUND SIGN
u'\xa4' # 0xA4 -> CURRENCY SIGN
u'\xa5' # 0xA5 -> YEN SIGN
u'\xa6' # 0xA6 -> BROKEN BAR
u'\xa7' # 0xA7 -> SECTION SIGN
u'\xa8' # 0xA8 -> DIAERESIS
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
u'\xd7' # 0xAA -> MULTIPLICATION SIGN
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xac' # 0xAC -> NOT SIGN
u'\xad' # 0xAD -> SOFT HYPHEN
u'\xae' # 0xAE -> REGISTERED SIGN
u'\xaf' # 0xAF -> MACRON
u'\xb0' # 0xB0 -> DEGREE SIGN
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
u'\xb4' # 0xB4 -> ACUTE ACCENT
u'\xb5' # 0xB5 -> MICRO SIGN
u'\xb6' # 0xB6 -> PILCROW SIGN
u'\xb7' # 0xB7 -> MIDDLE DOT
u'\xb8' # 0xB8 -> CEDILLA
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
u'\xf7' # 0xBA -> DIVISION SIGN
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
u'\xa2' # 0xA2 -> CENT SIGN
u'\xa3' # 0xA3 -> POUND SIGN
u'\xa4' # 0xA4 -> CURRENCY SIGN
u'\xa5' # 0xA5 -> YEN SIGN
u'\xa6' # 0xA6 -> BROKEN BAR
u'\xa7' # 0xA7 -> SECTION SIGN
u'\xa8' # 0xA8 -> DIAERESIS
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
u'\xd7' # 0xAA -> MULTIPLICATION SIGN
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xac' # 0xAC -> NOT SIGN
u'\xad' # 0xAD -> SOFT HYPHEN
u'\xae' # 0xAE -> REGISTERED SIGN
u'\xaf' # 0xAF -> MACRON
u'\xb0' # 0xB0 -> DEGREE SIGN
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
u'\xb4' # 0xB4 -> ACUTE ACCENT
u'\xb5' # 0xB5 -> MICRO SIGN
u'\xb6' # 0xB6 -> PILCROW SIGN
u'\xb7' # 0xB7 -> MIDDLE DOT
u'\xb8' # 0xB8 -> CEDILLA
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
u'\xf7' # 0xBA -> DIVISION SIGN
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
u'\ufffe'
u'\ufffe'
u'\ufffe'
@ -255,263 +255,262 @@ decoding_table = (
u'\ufffe'
u'\ufffe'
u'\ufffe'
u'\u2017' # 0xDF -> DOUBLE LOW LINE
u'\u05d0' # 0xE0 -> HEBREW LETTER ALEF
u'\u05d1' # 0xE1 -> HEBREW LETTER BET
u'\u05d2' # 0xE2 -> HEBREW LETTER GIMEL
u'\u05d3' # 0xE3 -> HEBREW LETTER DALET
u'\u05d4' # 0xE4 -> HEBREW LETTER HE
u'\u05d5' # 0xE5 -> HEBREW LETTER VAV
u'\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN
u'\u05d7' # 0xE7 -> HEBREW LETTER HET
u'\u05d8' # 0xE8 -> HEBREW LETTER TET
u'\u05d9' # 0xE9 -> HEBREW LETTER YOD
u'\u05da' # 0xEA -> HEBREW LETTER FINAL KAF
u'\u05db' # 0xEB -> HEBREW LETTER KAF
u'\u05dc' # 0xEC -> HEBREW LETTER LAMED
u'\u05dd' # 0xED -> HEBREW LETTER FINAL MEM
u'\u05de' # 0xEE -> HEBREW LETTER MEM
u'\u05df' # 0xEF -> HEBREW LETTER FINAL NUN
u'\u05e0' # 0xF0 -> HEBREW LETTER NUN
u'\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH
u'\u05e2' # 0xF2 -> HEBREW LETTER AYIN
u'\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE
u'\u05e4' # 0xF4 -> HEBREW LETTER PE
u'\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI
u'\u05e6' # 0xF6 -> HEBREW LETTER TSADI
u'\u05e7' # 0xF7 -> HEBREW LETTER QOF
u'\u05e8' # 0xF8 -> HEBREW LETTER RESH
u'\u05e9' # 0xF9 -> HEBREW LETTER SHIN
u'\u05ea' # 0xFA -> HEBREW LETTER TAV
u'\u2017' # 0xDF -> DOUBLE LOW LINE
u'\u05d0' # 0xE0 -> HEBREW LETTER ALEF
u'\u05d1' # 0xE1 -> HEBREW LETTER BET
u'\u05d2' # 0xE2 -> HEBREW LETTER GIMEL
u'\u05d3' # 0xE3 -> HEBREW LETTER DALET
u'\u05d4' # 0xE4 -> HEBREW LETTER HE
u'\u05d5' # 0xE5 -> HEBREW LETTER VAV
u'\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN
u'\u05d7' # 0xE7 -> HEBREW LETTER HET
u'\u05d8' # 0xE8 -> HEBREW LETTER TET
u'\u05d9' # 0xE9 -> HEBREW LETTER YOD
u'\u05da' # 0xEA -> HEBREW LETTER FINAL KAF
u'\u05db' # 0xEB -> HEBREW LETTER KAF
u'\u05dc' # 0xEC -> HEBREW LETTER LAMED
u'\u05dd' # 0xED -> HEBREW LETTER FINAL MEM
u'\u05de' # 0xEE -> HEBREW LETTER MEM
u'\u05df' # 0xEF -> HEBREW LETTER FINAL NUN
u'\u05e0' # 0xF0 -> HEBREW LETTER NUN
u'\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH
u'\u05e2' # 0xF2 -> HEBREW LETTER AYIN
u'\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE
u'\u05e4' # 0xF4 -> HEBREW LETTER PE
u'\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI
u'\u05e6' # 0xF6 -> HEBREW LETTER TSADI
u'\u05e7' # 0xF7 -> HEBREW LETTER QOF
u'\u05e8' # 0xF8 -> HEBREW LETTER RESH
u'\u05e9' # 0xF9 -> HEBREW LETTER SHIN
u'\u05ea' # 0xFA -> HEBREW LETTER TAV
u'\ufffe'
u'\ufffe'
u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK
u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK
u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK
u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK
u'\ufffe'
)
### Encoding Map
encoding_map = {
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x0080: 0x80, # <control>
0x0081: 0x81, # <control>
0x0082: 0x82, # <control>
0x0083: 0x83, # <control>
0x0084: 0x84, # <control>
0x0085: 0x85, # <control>
0x0086: 0x86, # <control>
0x0087: 0x87, # <control>
0x0088: 0x88, # <control>
0x0089: 0x89, # <control>
0x008A: 0x8A, # <control>
0x008B: 0x8B, # <control>
0x008C: 0x8C, # <control>
0x008D: 0x8D, # <control>
0x008E: 0x8E, # <control>
0x008F: 0x8F, # <control>
0x0090: 0x90, # <control>
0x0091: 0x91, # <control>
0x0092: 0x92, # <control>
0x0093: 0x93, # <control>
0x0094: 0x94, # <control>
0x0095: 0x95, # <control>
0x0096: 0x96, # <control>
0x0097: 0x97, # <control>
0x0098: 0x98, # <control>
0x0099: 0x99, # <control>
0x009A: 0x9A, # <control>
0x009B: 0x9B, # <control>
0x009C: 0x9C, # <control>
0x009D: 0x9D, # <control>
0x009E: 0x9E, # <control>
0x009F: 0x9F, # <control>
0x00A0: 0xA0, # NO-BREAK SPACE
0x00A2: 0xA2, # CENT SIGN
0x00A3: 0xA3, # POUND SIGN
0x00A4: 0xA4, # CURRENCY SIGN
0x00A5: 0xA5, # YEN SIGN
0x00A6: 0xA6, # BROKEN BAR
0x00A7: 0xA7, # SECTION SIGN
0x00A8: 0xA8, # DIAERESIS
0x00A9: 0xA9, # COPYRIGHT SIGN
0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC: 0xAC, # NOT SIGN
0x00AD: 0xAD, # SOFT HYPHEN
0x00AE: 0xAE, # REGISTERED SIGN
0x00AF: 0xAF, # MACRON
0x00B0: 0xB0, # DEGREE SIGN
0x00B1: 0xB1, # PLUS-MINUS SIGN
0x00B2: 0xB2, # SUPERSCRIPT TWO
0x00B3: 0xB3, # SUPERSCRIPT THREE
0x00B4: 0xB4, # ACUTE ACCENT
0x00B5: 0xB5, # MICRO SIGN
0x00B6: 0xB6, # PILCROW SIGN
0x00B7: 0xB7, # MIDDLE DOT
0x00B8: 0xB8, # CEDILLA
0x00B9: 0xB9, # SUPERSCRIPT ONE
0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
0x00D7: 0xAA, # MULTIPLICATION SIGN
0x00F7: 0xBA, # DIVISION SIGN
0x05D0: 0xE0, # HEBREW LETTER ALEF
0x05D1: 0xE1, # HEBREW LETTER BET
0x05D2: 0xE2, # HEBREW LETTER GIMEL
0x05D3: 0xE3, # HEBREW LETTER DALET
0x05D4: 0xE4, # HEBREW LETTER HE
0x05D5: 0xE5, # HEBREW LETTER VAV
0x05D6: 0xE6, # HEBREW LETTER ZAYIN
0x05D7: 0xE7, # HEBREW LETTER HET
0x05D8: 0xE8, # HEBREW LETTER TET
0x05D9: 0xE9, # HEBREW LETTER YOD
0x05DA: 0xEA, # HEBREW LETTER FINAL KAF
0x05DB: 0xEB, # HEBREW LETTER KAF
0x05DC: 0xEC, # HEBREW LETTER LAMED
0x05DD: 0xED, # HEBREW LETTER FINAL MEM
0x05DE: 0xEE, # HEBREW LETTER MEM
0x05DF: 0xEF, # HEBREW LETTER FINAL NUN
0x05E0: 0xF0, # HEBREW LETTER NUN
0x05E1: 0xF1, # HEBREW LETTER SAMEKH
0x05E2: 0xF2, # HEBREW LETTER AYIN
0x05E3: 0xF3, # HEBREW LETTER FINAL PE
0x05E4: 0xF4, # HEBREW LETTER PE
0x05E5: 0xF5, # HEBREW LETTER FINAL TSADI
0x05E6: 0xF6, # HEBREW LETTER TSADI
0x05E7: 0xF7, # HEBREW LETTER QOF
0x05E8: 0xF8, # HEBREW LETTER RESH
0x05E9: 0xF9, # HEBREW LETTER SHIN
0x05EA: 0xFA, # HEBREW LETTER TAV
0x200E: 0xFD, # LEFT-TO-RIGHT MARK
0x200F: 0xFE, # RIGHT-TO-LEFT MARK
0x2017: 0xDF, # DOUBLE LOW LINE
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x0080: 0x80, # <control>
0x0081: 0x81, # <control>
0x0082: 0x82, # <control>
0x0083: 0x83, # <control>
0x0084: 0x84, # <control>
0x0085: 0x85, # <control>
0x0086: 0x86, # <control>
0x0087: 0x87, # <control>
0x0088: 0x88, # <control>
0x0089: 0x89, # <control>
0x008A: 0x8A, # <control>
0x008B: 0x8B, # <control>
0x008C: 0x8C, # <control>
0x008D: 0x8D, # <control>
0x008E: 0x8E, # <control>
0x008F: 0x8F, # <control>
0x0090: 0x90, # <control>
0x0091: 0x91, # <control>
0x0092: 0x92, # <control>
0x0093: 0x93, # <control>
0x0094: 0x94, # <control>
0x0095: 0x95, # <control>
0x0096: 0x96, # <control>
0x0097: 0x97, # <control>
0x0098: 0x98, # <control>
0x0099: 0x99, # <control>
0x009A: 0x9A, # <control>
0x009B: 0x9B, # <control>
0x009C: 0x9C, # <control>
0x009D: 0x9D, # <control>
0x009E: 0x9E, # <control>
0x009F: 0x9F, # <control>
0x00A0: 0xA0, # NO-BREAK SPACE
0x00A2: 0xA2, # CENT SIGN
0x00A3: 0xA3, # POUND SIGN
0x00A4: 0xA4, # CURRENCY SIGN
0x00A5: 0xA5, # YEN SIGN
0x00A6: 0xA6, # BROKEN BAR
0x00A7: 0xA7, # SECTION SIGN
0x00A8: 0xA8, # DIAERESIS
0x00A9: 0xA9, # COPYRIGHT SIGN
0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC: 0xAC, # NOT SIGN
0x00AD: 0xAD, # SOFT HYPHEN
0x00AE: 0xAE, # REGISTERED SIGN
0x00AF: 0xAF, # MACRON
0x00B0: 0xB0, # DEGREE SIGN
0x00B1: 0xB1, # PLUS-MINUS SIGN
0x00B2: 0xB2, # SUPERSCRIPT TWO
0x00B3: 0xB3, # SUPERSCRIPT THREE
0x00B4: 0xB4, # ACUTE ACCENT
0x00B5: 0xB5, # MICRO SIGN
0x00B6: 0xB6, # PILCROW SIGN
0x00B7: 0xB7, # MIDDLE DOT
0x00B8: 0xB8, # CEDILLA
0x00B9: 0xB9, # SUPERSCRIPT ONE
0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
0x00D7: 0xAA, # MULTIPLICATION SIGN
0x00F7: 0xBA, # DIVISION SIGN
0x05D0: 0xE0, # HEBREW LETTER ALEF
0x05D1: 0xE1, # HEBREW LETTER BET
0x05D2: 0xE2, # HEBREW LETTER GIMEL
0x05D3: 0xE3, # HEBREW LETTER DALET
0x05D4: 0xE4, # HEBREW LETTER HE
0x05D5: 0xE5, # HEBREW LETTER VAV
0x05D6: 0xE6, # HEBREW LETTER ZAYIN
0x05D7: 0xE7, # HEBREW LETTER HET
0x05D8: 0xE8, # HEBREW LETTER TET
0x05D9: 0xE9, # HEBREW LETTER YOD
0x05DA: 0xEA, # HEBREW LETTER FINAL KAF
0x05DB: 0xEB, # HEBREW LETTER KAF
0x05DC: 0xEC, # HEBREW LETTER LAMED
0x05DD: 0xED, # HEBREW LETTER FINAL MEM
0x05DE: 0xEE, # HEBREW LETTER MEM
0x05DF: 0xEF, # HEBREW LETTER FINAL NUN
0x05E0: 0xF0, # HEBREW LETTER NUN
0x05E1: 0xF1, # HEBREW LETTER SAMEKH
0x05E2: 0xF2, # HEBREW LETTER AYIN
0x05E3: 0xF3, # HEBREW LETTER FINAL PE
0x05E4: 0xF4, # HEBREW LETTER PE
0x05E5: 0xF5, # HEBREW LETTER FINAL TSADI
0x05E6: 0xF6, # HEBREW LETTER TSADI
0x05E7: 0xF7, # HEBREW LETTER QOF
0x05E8: 0xF8, # HEBREW LETTER RESH
0x05E9: 0xF9, # HEBREW LETTER SHIN
0x05EA: 0xFA, # HEBREW LETTER TAV
0x200E: 0xFD, # LEFT-TO-RIGHT MARK
0x200F: 0xFE, # RIGHT-TO-LEFT MARK
0x2017: 0xDF, # DOUBLE LOW LINE
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -1,2 +1,2 @@
#coding: utf8
print ''
print ''

View File

@ -33,7 +33,7 @@ consts: ('None',)
... b = x - y
... c = a * b
... return c
...
...
>>> dump(h.func_code)
name: h
argcount: 2

View File

@ -1,180 +1,180 @@
from test.test_support import run_unittest
import unittest
class ExceptionTestCase(unittest.TestCase):
def test_try_except_else_finally(self):
hit_except = False
hit_else = False
hit_finally = False
try:
raise Exception, 'nyaa!'
except:
hit_except = True
else:
hit_else = True
finally:
hit_finally = True
self.assertTrue(hit_except)
self.assertTrue(hit_finally)
self.assertFalse(hit_else)
def test_try_except_else_finally_no_exception(self):
hit_except = False
hit_else = False
hit_finally = False
try:
pass
except:
hit_except = True
else:
hit_else = True
finally:
hit_finally = True
self.assertFalse(hit_except)
self.assertTrue(hit_finally)
self.assertTrue(hit_else)
def test_try_except_finally(self):
hit_except = False
hit_finally = False
try:
raise Exception, 'yarr!'
except:
hit_except = True
finally:
hit_finally = True
self.assertTrue(hit_except)
self.assertTrue(hit_finally)
def test_try_except_finally_no_exception(self):
hit_except = False
hit_finally = False
try:
pass
except:
hit_except = True
finally:
hit_finally = True
self.assertFalse(hit_except)
self.assertTrue(hit_finally)
def test_try_except(self):
hit_except = False
try:
raise Exception, 'ahoy!'
except:
hit_except = True
self.assertTrue(hit_except)
def test_try_except_no_exception(self):
hit_except = False
try:
pass
except:
hit_except = True
self.assertFalse(hit_except)
def test_try_except_else(self):
hit_except = False
hit_else = False
try:
raise Exception, 'foo!'
except:
hit_except = True
else:
hit_else = True
self.assertFalse(hit_else)
self.assertTrue(hit_except)
def test_try_except_else_no_exception(self):
hit_except = False
hit_else = False
try:
pass
except:
hit_except = True
else:
hit_else = True
self.assertFalse(hit_except)
self.assertTrue(hit_else)
def test_try_finally_no_exception(self):
hit_finally = False
try:
pass
finally:
hit_finally = True
self.assertTrue(hit_finally)
def test_nested(self):
hit_finally = False
hit_inner_except = False
hit_inner_finally = False
try:
try:
raise Exception, 'inner exception'
except:
hit_inner_except = True
finally:
hit_inner_finally = True
finally:
hit_finally = True
self.assertTrue(hit_inner_except)
self.assertTrue(hit_inner_finally)
self.assertTrue(hit_finally)
def test_nested_else(self):
hit_else = False
hit_finally = False
hit_except = False
hit_inner_except = False
hit_inner_else = False
try:
try:
pass
except:
hit_inner_except = True
else:
hit_inner_else = True
raise Exception, 'outer exception'
except:
hit_except = True
else:
hit_else = True
finally:
hit_finally = True
self.assertFalse(hit_inner_except)
self.assertTrue(hit_inner_else)
self.assertFalse(hit_else)
self.assertTrue(hit_finally)
self.assertTrue(hit_except)
def test_main():
run_unittest(ExceptionTestCase)
if __name__ == '__main__':
test_main()
from test.test_support import run_unittest
import unittest
class ExceptionTestCase(unittest.TestCase):
def test_try_except_else_finally(self):
hit_except = False
hit_else = False
hit_finally = False
try:
raise Exception, 'nyaa!'
except:
hit_except = True
else:
hit_else = True
finally:
hit_finally = True
self.assertTrue(hit_except)
self.assertTrue(hit_finally)
self.assertFalse(hit_else)
def test_try_except_else_finally_no_exception(self):
hit_except = False
hit_else = False
hit_finally = False
try:
pass
except:
hit_except = True
else:
hit_else = True
finally:
hit_finally = True
self.assertFalse(hit_except)
self.assertTrue(hit_finally)
self.assertTrue(hit_else)
def test_try_except_finally(self):
hit_except = False
hit_finally = False
try:
raise Exception, 'yarr!'
except:
hit_except = True
finally:
hit_finally = True
self.assertTrue(hit_except)
self.assertTrue(hit_finally)
def test_try_except_finally_no_exception(self):
hit_except = False
hit_finally = False
try:
pass
except:
hit_except = True
finally:
hit_finally = True
self.assertFalse(hit_except)
self.assertTrue(hit_finally)
def test_try_except(self):
hit_except = False
try:
raise Exception, 'ahoy!'
except:
hit_except = True
self.assertTrue(hit_except)
def test_try_except_no_exception(self):
hit_except = False
try:
pass
except:
hit_except = True
self.assertFalse(hit_except)
def test_try_except_else(self):
hit_except = False
hit_else = False
try:
raise Exception, 'foo!'
except:
hit_except = True
else:
hit_else = True
self.assertFalse(hit_else)
self.assertTrue(hit_except)
def test_try_except_else_no_exception(self):
hit_except = False
hit_else = False
try:
pass
except:
hit_except = True
else:
hit_else = True
self.assertFalse(hit_except)
self.assertTrue(hit_else)
def test_try_finally_no_exception(self):
hit_finally = False
try:
pass
finally:
hit_finally = True
self.assertTrue(hit_finally)
def test_nested(self):
hit_finally = False
hit_inner_except = False
hit_inner_finally = False
try:
try:
raise Exception, 'inner exception'
except:
hit_inner_except = True
finally:
hit_inner_finally = True
finally:
hit_finally = True
self.assertTrue(hit_inner_except)
self.assertTrue(hit_inner_finally)
self.assertTrue(hit_finally)
def test_nested_else(self):
hit_else = False
hit_finally = False
hit_except = False
hit_inner_except = False
hit_inner_else = False
try:
try:
pass
except:
hit_inner_except = True
else:
hit_inner_else = True
raise Exception, 'outer exception'
except:
hit_except = True
else:
hit_else = True
finally:
hit_finally = True
self.assertFalse(hit_inner_except)
self.assertTrue(hit_inner_else)
self.assertFalse(hit_else)
self.assertTrue(hit_finally)
self.assertTrue(hit_except)
def test_main():
run_unittest(ExceptionTestCase)
if __name__ == '__main__':
test_main()

View File

@ -774,7 +774,7 @@ These are fine:
... try:
... 1//0
... except ZeroDivisionError:
... yield 666
... yield 666
... except:
... pass
... finally:

View File

@ -1137,9 +1137,9 @@ def testPatch1094164 ():
# Check that replacing a child with itself leaves the tree unchanged
elem.replaceChild(e, e)
confirm(e.parentNode is elem, "After replaceChild()")
def testReplaceWholeText():
def setup():
doc = parseString("<doc>a<e/>d</doc>")

View File

@ -185,7 +185,7 @@ def test_poll3():
if x != 5:
print 'Overflow must have occurred'
print 'Poll test 3 complete'
test_poll1()
test_poll2()

View File

@ -175,18 +175,18 @@ zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz''')
self.assert_(quopri.decodestring(e, header=True) == p)
def test_scriptencode(self):
(p, e) = self.STRINGS[-1]
(cin, cout) = os.popen2("%s -mquopri" % sys.executable)
cin.write(p)
cin.close()
self.assert_(cout.read() == e)
(p, e) = self.STRINGS[-1]
(cin, cout) = os.popen2("%s -mquopri" % sys.executable)
cin.write(p)
cin.close()
self.assert_(cout.read() == e)
def test_scriptdecode(self):
(p, e) = self.STRINGS[-1]
(cin, cout) = os.popen2("%s -mquopri -d" % sys.executable)
cin.write(e)
cin.close()
self.assert_(cout.read() == p)
(p, e) = self.STRINGS[-1]
(cin, cout) = os.popen2("%s -mquopri -d" % sys.executable)
cin.write(e)
cin.close()
self.assert_(cout.read() == p)
def test_main():
test_support.run_unittest(QuopriTestCase)

View File

@ -78,7 +78,7 @@ class XMLRPCTestCase(unittest.TestCase):
def test_bug_1164912 (self):
d = xmlrpclib.DateTime()
((new_d,), dummy) = xmlrpclib.loads(xmlrpclib.dumps((d,),
((new_d,), dummy) = xmlrpclib.loads(xmlrpclib.dumps((d,),
methodresponse=True))
self.assert_(isinstance(new_d.value, str))

View File

@ -96,7 +96,7 @@ def _synthesize(browser, update_tryorder=1):
if sys.platform[:3] == "win":
def _isexecutable(cmd):
cmd = cmd.lower()
if os.path.isfile(cmd) and (cmd.endswith(".exe") or
if os.path.isfile(cmd) and (cmd.endswith(".exe") or
cmd.endswith(".bat")):
return True
for ext in ".exe", ".bat":
@ -134,7 +134,7 @@ class BaseBrowser(object):
def __init__(self, name=""):
self.name = name
self.basename = name
def open(self, url, new=0, autoraise=1):
raise NotImplementedError

View File

@ -141,4 +141,3 @@ def include(elem, loader=None):
else:
include(e, loader)
i = i + 1

View File

@ -196,4 +196,3 @@ def findtext(element, path, default=None):
def findall(element, path):
return _compile(path).findall(element)

View File

@ -142,7 +142,7 @@ class ASDLParser(spark.GenericParser, object):
def p_product(self, (_0, fields, _1)):
" product ::= ( fields ) "
# XXX can't I just construct things in the right order?
fields.reverse()
fields.reverse()
return Product(fields)
def p_sum_0(self, (constructor,)):
@ -164,7 +164,7 @@ class ASDLParser(spark.GenericParser, object):
def p_constructor_1(self, (id, _0, fields, _1)):
" constructor ::= Id ( fields ) "
# XXX can't I just construct things in the right order?
fields.reverse()
fields.reverse()
return Constructor(id, fields)
def p_fields_0(self, (field,)):
@ -355,7 +355,7 @@ def check(mod):
v.errors += 1
uses = ", ".join(v.types[t])
print "Undefined type %s, used in %s" % (t, uses)
return not v.errors
def parse(file):
@ -380,7 +380,7 @@ if __name__ == "__main__":
else:
testdir = "tests"
files = glob.glob(testdir + "/*.asdl")
for file in files:
print file
mod = parse(file)

View File

@ -439,7 +439,7 @@ class FreeVisitor(PickleVisitor):
self.emit("", 0)
self.emit("free(o);", 1)
self.func_end()
def visitConstructor(self, cons, enum, name):
self.emit("case %s_kind:" % cons.name, 1)
for f in cons.fields:
@ -487,76 +487,76 @@ class FreeVisitor(PickleVisitor):
else:
ctype = get_c_type(field.type)
self.emit("free_%s((%s)%s);" % (field.type, ctype, value), depth)
class MarshalUtilVisitor(StaticVisitor):
CODE = '''
#define CHECKSIZE(BUF, OFF, MIN) { \\
int need = *(OFF) + MIN; \\
if (need >= PyString_GET_SIZE(*(BUF))) { \\
int newsize = PyString_GET_SIZE(*(BUF)) * 2; \\
if (newsize < need) \\
newsize = need; \\
if (_PyString_Resize((BUF), newsize) < 0) \\
return 0; \\
} \\
}
int need = *(OFF) + MIN; \\
if (need >= PyString_GET_SIZE(*(BUF))) { \\
int newsize = PyString_GET_SIZE(*(BUF)) * 2; \\
if (newsize < need) \\
newsize = need; \\
if (_PyString_Resize((BUF), newsize) < 0) \\
return 0; \\
} \\
}
static int
static int
marshal_write_int(PyObject **buf, int *offset, int x)
{
char *s;
char *s;
CHECKSIZE(buf, offset, 4)
s = PyString_AS_STRING(*buf) + (*offset);
s[0] = (x & 0xff);
s[1] = (x >> 8) & 0xff;
s[2] = (x >> 16) & 0xff;
s[3] = (x >> 24) & 0xff;
*offset += 4;
return 1;
CHECKSIZE(buf, offset, 4)
s = PyString_AS_STRING(*buf) + (*offset);
s[0] = (x & 0xff);
s[1] = (x >> 8) & 0xff;
s[2] = (x >> 16) & 0xff;
s[3] = (x >> 24) & 0xff;
*offset += 4;
return 1;
}
static int
static int
marshal_write_bool(PyObject **buf, int *offset, bool b)
{
if (b)
marshal_write_int(buf, offset, 1);
else
marshal_write_int(buf, offset, 0);
return 1;
if (b)
marshal_write_int(buf, offset, 1);
else
marshal_write_int(buf, offset, 0);
return 1;
}
static int
static int
marshal_write_identifier(PyObject **buf, int *offset, identifier id)
{
int l = PyString_GET_SIZE(id);
marshal_write_int(buf, offset, l);
CHECKSIZE(buf, offset, l);
memcpy(PyString_AS_STRING(*buf) + *offset,
PyString_AS_STRING(id), l);
*offset += l;
return 1;
int l = PyString_GET_SIZE(id);
marshal_write_int(buf, offset, l);
CHECKSIZE(buf, offset, l);
memcpy(PyString_AS_STRING(*buf) + *offset,
PyString_AS_STRING(id), l);
*offset += l;
return 1;
}
static int
static int
marshal_write_string(PyObject **buf, int *offset, string s)
{
int len = PyString_GET_SIZE(s);
marshal_write_int(buf, offset, len);
CHECKSIZE(buf, offset, len);
memcpy(PyString_AS_STRING(*buf) + *offset,
PyString_AS_STRING(s), len);
*offset += len;
return 1;
int len = PyString_GET_SIZE(s);
marshal_write_int(buf, offset, len);
CHECKSIZE(buf, offset, len);
memcpy(PyString_AS_STRING(*buf) + *offset,
PyString_AS_STRING(s), len);
*offset += len;
return 1;
}
static int
static int
marshal_write_object(PyObject **buf, int *offset, object s)
{
/* XXX */
return 0;
/* XXX */
return 0;
}
'''
@ -575,7 +575,7 @@ class MarshalFunctionVisitor(PickleVisitor):
self.emit("return 1;", 1)
self.emit("}", 0)
self.emit("", 0)
def visitSum(self, sum, name):
self.func_begin(name, has_sequence(sum.types, False))
simple = is_simple(sum)
@ -594,7 +594,7 @@ class MarshalFunctionVisitor(PickleVisitor):
for field in prod.fields:
self.visitField(field, name, 1, 1)
self.func_end()
def visitConstructor(self, cons, enum, name, simple):
if simple:
self.emit("case %s:" % cons.name, 1)

File diff suppressed because it is too large Load Diff

View File

@ -218,10 +218,10 @@ class FunctionGenerator(BaseFunctionGenerator):
def beginallowthreads(self):
pass
def endallowthreads(self):
pass
def callit(self):
args = ""
s = "%s%s(" % (self.getrvforcallit(), self.callname)

View File

@ -111,10 +111,10 @@ class VarVarHeapOutputBufferType(VarHeapOutputBufferType):
def passOutput(self, name):
return "%s__out__, %s__len__, &%s__len__" % (name, name, name)
class MallocHeapOutputBufferType(HeapOutputBufferType):
"""Output buffer allocated by the called function -- passed as (&buffer, &size).
Instantiate without parameters.
Call from Python without parameters.
"""
@ -124,7 +124,7 @@ class MallocHeapOutputBufferType(HeapOutputBufferType):
def getAuxDeclarations(self, name):
return []
def passOutput(self, name):
return "&%s__out__, &%s__len__" % (name, name)
@ -133,10 +133,9 @@ class MallocHeapOutputBufferType(HeapOutputBufferType):
def getargsArgs(self, name):
return None
def mkvalueFormat(self):
return "z#"
def cleanup(self, name):
Output("if( %s__out__ ) free(%s__out__);", name, name)

View File

@ -43,5 +43,5 @@ if __name__ == "__main__":
buf = open(filename).read()
co = compile(buf, filename, "exec")
walk(co)
else:
else:
load(filename, codename)

View File

@ -295,8 +295,8 @@ class Codec(codecs.Codec):
else:
l.append('''\
return codecs.charmap_decode(input,errors,decoding_map)''')
l.append('''
l.append('''
class StreamWriter(Codec,codecs.StreamWriter):
pass
@ -330,7 +330,7 @@ def getregentry():
# Final new-line
l.append('\n')
return '\n'.join(l)
def pymap(name,map,pyfile,comments=1):