summaryrefslogtreecommitdiff
path: root/Lib/encodings
diff options
context:
space:
mode:
Diffstat (limited to 'Lib/encodings')
-rw-r--r--Lib/encodings/__init__.py2
-rw-r--r--Lib/encodings/aliases.py8
-rw-r--r--Lib/encodings/base64_codec.py55
-rw-r--r--Lib/encodings/bz2_codec.py77
-rw-r--r--Lib/encodings/cp720.py309
-rw-r--r--Lib/encodings/cp858.py698
-rw-r--r--Lib/encodings/hex_codec.py55
-rw-r--r--Lib/encodings/punycode.py1
-rw-r--r--Lib/encodings/quopri_codec.py56
-rwxr-xr-xLib/encodings/rot_13.py113
-rw-r--r--Lib/encodings/uu_codec.py99
-rw-r--r--Lib/encodings/zlib_codec.py77
12 files changed, 1547 insertions, 3 deletions
diff --git a/Lib/encodings/__init__.py b/Lib/encodings/__init__.py
index d72eae9328..b189bd9793 100644
--- a/Lib/encodings/__init__.py
+++ b/Lib/encodings/__init__.py
@@ -10,7 +10,7 @@
Each codec module must export the following interface:
* getregentry() -> codecs.CodecInfo object
- The getregentry() API must a CodecInfo object with encoder, decoder,
+ The getregentry() API must return a CodecInfo object with encoder, decoder,
incrementalencoder, incrementaldecoder, streamwriter and streamreader
atttributes which adhere to the Python Codec Interface Standard.
diff --git a/Lib/encodings/aliases.py b/Lib/encodings/aliases.py
index 4c35588c88..235deb5c30 100644
--- a/Lib/encodings/aliases.py
+++ b/Lib/encodings/aliases.py
@@ -146,6 +146,11 @@ aliases = {
'csibm857' : 'cp857',
'ibm857' : 'cp857',
+ # cp858 codec
+ '858' : 'cp858',
+ 'csibm858' : 'cp858',
+ 'ibm858' : 'cp858',
+
# cp860 codec
'860' : 'cp860',
'csibm860' : 'cp860',
@@ -430,6 +435,7 @@ aliases = {
'maclatin2' : 'mac_latin2',
# mac_roman codec
+ 'macintosh' : 'mac_roman',
'macroman' : 'mac_roman',
# mac_turkish codec
@@ -442,7 +448,7 @@ aliases = {
'csptcp154' : 'ptcp154',
'pt154' : 'ptcp154',
'cp154' : 'ptcp154',
- 'cyrillic-asian' : 'ptcp154',
+ 'cyrillic_asian' : 'ptcp154',
## quopri_codec codec
#'quopri' : 'quopri_codec',
diff --git a/Lib/encodings/base64_codec.py b/Lib/encodings/base64_codec.py
new file mode 100644
index 0000000000..321a961782
--- /dev/null
+++ b/Lib/encodings/base64_codec.py
@@ -0,0 +1,55 @@
+"""Python 'base64_codec' Codec - base64 content transfer encoding.
+
+This codec de/encodes from bytes to bytes and is therefore usable with
+bytes.transform() and bytes.untransform().
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+"""
+
+import codecs
+import base64
+
+### Codec APIs
+
+def base64_encode(input, errors='strict'):
+ assert errors == 'strict'
+ return (base64.encodebytes(input), len(input))
+
+def base64_decode(input, errors='strict'):
+ assert errors == 'strict'
+ return (base64.decodebytes(input), len(input))
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return base64_encode(input, errors)
+ def decode(self, input, errors='strict'):
+ return base64_decode(input, errors)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ assert self.errors == 'strict'
+ return base64.encodebytes(input)
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ assert self.errors == 'strict'
+ return base64.decodebytes(input)
+
+class StreamWriter(Codec, codecs.StreamWriter):
+ charbuffertype = bytes
+
+class StreamReader(Codec, codecs.StreamReader):
+ charbuffertype = bytes
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='base64',
+ encode=base64_encode,
+ decode=base64_decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ )
diff --git a/Lib/encodings/bz2_codec.py b/Lib/encodings/bz2_codec.py
new file mode 100644
index 0000000000..e65d226bfd
--- /dev/null
+++ b/Lib/encodings/bz2_codec.py
@@ -0,0 +1,77 @@
+"""Python 'bz2_codec' Codec - bz2 compression encoding.
+
+This codec de/encodes from bytes to bytes and is therefore usable with
+bytes.transform() and bytes.untransform().
+
+Adapted by Raymond Hettinger from zlib_codec.py which was written
+by Marc-Andre Lemburg (mal@lemburg.com).
+"""
+
+import codecs
+import bz2 # this codec needs the optional bz2 module !
+
+### Codec APIs
+
+def bz2_encode(input, errors='strict'):
+ assert errors == 'strict'
+ return (bz2.compress(input), len(input))
+
+def bz2_decode(input, errors='strict'):
+ assert errors == 'strict'
+ return (bz2.decompress(input), len(input))
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return bz2_encode(input, errors)
+ def decode(self, input, errors='strict'):
+ return bz2_decode(input, errors)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def __init__(self, errors='strict'):
+ assert errors == 'strict'
+ self.errors = errors
+ self.compressobj = bz2.BZ2Compressor()
+
+ def encode(self, input, final=False):
+ if final:
+ c = self.compressobj.compress(input)
+ return c + self.compressobj.flush()
+ else:
+ return self.compressobj.compress(input)
+
+ def reset(self):
+ self.compressobj = bz2.BZ2Compressor()
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def __init__(self, errors='strict'):
+ assert errors == 'strict'
+ self.errors = errors
+ self.decompressobj = bz2.BZ2Decompressor()
+
+ def decode(self, input, final=False):
+ try:
+ return self.decompressobj.decompress(input)
+ except EOFError:
+ return ''
+
+ def reset(self):
+ self.decompressobj = bz2.BZ2Decompressor()
+
+class StreamWriter(Codec, codecs.StreamWriter):
+ charbuffertype = bytes
+
+class StreamReader(Codec, codecs.StreamReader):
+ charbuffertype = bytes
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name="bz2",
+ encode=bz2_encode,
+ decode=bz2_decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ )
diff --git a/Lib/encodings/cp720.py b/Lib/encodings/cp720.py
new file mode 100644
index 0000000000..96d609616c
--- /dev/null
+++ b/Lib/encodings/cp720.py
@@ -0,0 +1,309 @@
+"""Python Character Mapping Codec cp720 generated on Windows:
+Vista 6.0.6002 SP2 Multiprocessor Free with the command:
+ python Tools/unicode/genwincodec.py 720
+"""#"
+
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp720',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> CONTROL CHARACTER
+ '\x01' # 0x01 -> CONTROL CHARACTER
+ '\x02' # 0x02 -> CONTROL CHARACTER
+ '\x03' # 0x03 -> CONTROL CHARACTER
+ '\x04' # 0x04 -> CONTROL CHARACTER
+ '\x05' # 0x05 -> CONTROL CHARACTER
+ '\x06' # 0x06 -> CONTROL CHARACTER
+ '\x07' # 0x07 -> CONTROL CHARACTER
+ '\x08' # 0x08 -> CONTROL CHARACTER
+ '\t' # 0x09 -> CONTROL CHARACTER
+ '\n' # 0x0A -> CONTROL CHARACTER
+ '\x0b' # 0x0B -> CONTROL CHARACTER
+ '\x0c' # 0x0C -> CONTROL CHARACTER
+ '\r' # 0x0D -> CONTROL CHARACTER
+ '\x0e' # 0x0E -> CONTROL CHARACTER
+ '\x0f' # 0x0F -> CONTROL CHARACTER
+ '\x10' # 0x10 -> CONTROL CHARACTER
+ '\x11' # 0x11 -> CONTROL CHARACTER
+ '\x12' # 0x12 -> CONTROL CHARACTER
+ '\x13' # 0x13 -> CONTROL CHARACTER
+ '\x14' # 0x14 -> CONTROL CHARACTER
+ '\x15' # 0x15 -> CONTROL CHARACTER
+ '\x16' # 0x16 -> CONTROL CHARACTER
+ '\x17' # 0x17 -> CONTROL CHARACTER
+ '\x18' # 0x18 -> CONTROL CHARACTER
+ '\x19' # 0x19 -> CONTROL CHARACTER
+ '\x1a' # 0x1A -> CONTROL CHARACTER
+ '\x1b' # 0x1B -> CONTROL CHARACTER
+ '\x1c' # 0x1C -> CONTROL CHARACTER
+ '\x1d' # 0x1D -> CONTROL CHARACTER
+ '\x1e' # 0x1E -> CONTROL CHARACTER
+ '\x1f' # 0x1F -> CONTROL CHARACTER
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> CONTROL CHARACTER
+ '\x80'
+ '\x81'
+ '\xe9' # 0x82 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x83 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\x84'
+ '\xe0' # 0x85 -> LATIN SMALL LETTER A WITH GRAVE
+ '\x86'
+ '\xe7' # 0x87 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x88 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x89 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x8A -> LATIN SMALL LETTER E WITH GRAVE
+ '\xef' # 0x8B -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xee' # 0x8C -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\x8d'
+ '\x8e'
+ '\x8f'
+ '\x90'
+ '\u0651' # 0x91 -> ARABIC SHADDA
+ '\u0652' # 0x92 -> ARABIC SUKUN
+ '\xf4' # 0x93 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xa4' # 0x94 -> CURRENCY SIGN
+ '\u0640' # 0x95 -> ARABIC TATWEEL
+ '\xfb' # 0x96 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xf9' # 0x97 -> LATIN SMALL LETTER U WITH GRAVE
+ '\u0621' # 0x98 -> ARABIC LETTER HAMZA
+ '\u0622' # 0x99 -> ARABIC LETTER ALEF WITH MADDA ABOVE
+ '\u0623' # 0x9A -> ARABIC LETTER ALEF WITH HAMZA ABOVE
+ '\u0624' # 0x9B -> ARABIC LETTER WAW WITH HAMZA ABOVE
+ '\xa3' # 0x9C -> POUND SIGN
+ '\u0625' # 0x9D -> ARABIC LETTER ALEF WITH HAMZA BELOW
+ '\u0626' # 0x9E -> ARABIC LETTER YEH WITH HAMZA ABOVE
+ '\u0627' # 0x9F -> ARABIC LETTER ALEF
+ '\u0628' # 0xA0 -> ARABIC LETTER BEH
+ '\u0629' # 0xA1 -> ARABIC LETTER TEH MARBUTA
+ '\u062a' # 0xA2 -> ARABIC LETTER TEH
+ '\u062b' # 0xA3 -> ARABIC LETTER THEH
+ '\u062c' # 0xA4 -> ARABIC LETTER JEEM
+ '\u062d' # 0xA5 -> ARABIC LETTER HAH
+ '\u062e' # 0xA6 -> ARABIC LETTER KHAH
+ '\u062f' # 0xA7 -> ARABIC LETTER DAL
+ '\u0630' # 0xA8 -> ARABIC LETTER THAL
+ '\u0631' # 0xA9 -> ARABIC LETTER REH
+ '\u0632' # 0xAA -> ARABIC LETTER ZAIN
+ '\u0633' # 0xAB -> ARABIC LETTER SEEN
+ '\u0634' # 0xAC -> ARABIC LETTER SHEEN
+ '\u0635' # 0xAD -> ARABIC LETTER SAD
+ '\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0xB0 -> LIGHT SHADE
+ '\u2592' # 0xB1 -> MEDIUM SHADE
+ '\u2593' # 0xB2 -> DARK SHADE
+ '\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0xB5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0xB6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0xB7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0xB8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0xBD -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0xBE -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0xC6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0xC7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0xCF -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0xD0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0xD1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0xD2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0xD3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0xD4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0xD5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0xD6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0xD7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0xD8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0xDB -> FULL BLOCK
+ '\u2584' # 0xDC -> LOWER HALF BLOCK
+ '\u258c' # 0xDD -> LEFT HALF BLOCK
+ '\u2590' # 0xDE -> RIGHT HALF BLOCK
+ '\u2580' # 0xDF -> UPPER HALF BLOCK
+ '\u0636' # 0xE0 -> ARABIC LETTER DAD
+ '\u0637' # 0xE1 -> ARABIC LETTER TAH
+ '\u0638' # 0xE2 -> ARABIC LETTER ZAH
+ '\u0639' # 0xE3 -> ARABIC LETTER AIN
+ '\u063a' # 0xE4 -> ARABIC LETTER GHAIN
+ '\u0641' # 0xE5 -> ARABIC LETTER FEH
+ '\xb5' # 0xE6 -> MICRO SIGN
+ '\u0642' # 0xE7 -> ARABIC LETTER QAF
+ '\u0643' # 0xE8 -> ARABIC LETTER KAF
+ '\u0644' # 0xE9 -> ARABIC LETTER LAM
+ '\u0645' # 0xEA -> ARABIC LETTER MEEM
+ '\u0646' # 0xEB -> ARABIC LETTER NOON
+ '\u0647' # 0xEC -> ARABIC LETTER HEH
+ '\u0648' # 0xED -> ARABIC LETTER WAW
+ '\u0649' # 0xEE -> ARABIC LETTER ALEF MAKSURA
+ '\u064a' # 0xEF -> ARABIC LETTER YEH
+ '\u2261' # 0xF0 -> IDENTICAL TO
+ '\u064b' # 0xF1 -> ARABIC FATHATAN
+ '\u064c' # 0xF2 -> ARABIC DAMMATAN
+ '\u064d' # 0xF3 -> ARABIC KASRATAN
+ '\u064e' # 0xF4 -> ARABIC FATHA
+ '\u064f' # 0xF5 -> ARABIC DAMMA
+ '\u0650' # 0xF6 -> ARABIC KASRA
+ '\u2248' # 0xF7 -> ALMOST EQUAL TO
+ '\xb0' # 0xF8 -> DEGREE SIGN
+ '\u2219' # 0xF9 -> BULLET OPERATOR
+ '\xb7' # 0xFA -> MIDDLE DOT
+ '\u221a' # 0xFB -> SQUARE ROOT
+ '\u207f' # 0xFC -> SUPERSCRIPT LATIN SMALL LETTER N
+ '\xb2' # 0xFD -> SUPERSCRIPT TWO
+ '\u25a0' # 0xFE -> BLACK SQUARE
+ '\xa0' # 0xFF -> NO-BREAK SPACE
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp858.py b/Lib/encodings/cp858.py
new file mode 100644
index 0000000000..7579f52538
--- /dev/null
+++ b/Lib/encodings/cp858.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec for CP858, modified from cp850.
+
+"""
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp858',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
+ 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
+ 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
+ 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
+ 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
+ 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
+ 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x009e: 0x00d7, # MULTIPLICATION SIGN
+ 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
+ 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
+ 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
+ 0x00a8: 0x00bf, # INVERTED QUESTION MARK
+ 0x00a9: 0x00ae, # REGISTERED SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00b8: 0x00a9, # COPYRIGHT SIGN
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x00a2, # CENT SIGN
+ 0x00be: 0x00a5, # YEN SIGN
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
+ 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x00a4, # CURRENCY SIGN
+ 0x00d0: 0x00f0, # LATIN SMALL LETTER ETH
+ 0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH
+ 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00d5: 0x20ac, # EURO SIGN
+ 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x00a6, # BROKEN BAR
+ 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
+ 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x00fe, # LATIN SMALL LETTER THORN
+ 0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN
+ 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x00ee: 0x00af, # MACRON
+ 0x00ef: 0x00b4, # ACUTE ACCENT
+ 0x00f0: 0x00ad, # SOFT HYPHEN
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2017, # DOUBLE LOW LINE
+ 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
+ 0x00f4: 0x00b6, # PILCROW SIGN
+ 0x00f5: 0x00a7, # SECTION SIGN
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x00b8, # CEDILLA
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x00a8, # DIAERESIS
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x00b9, # SUPERSCRIPT ONE
+ 0x00fc: 0x00b3, # SUPERSCRIPT THREE
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
+ '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
+ '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
+ '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xd7' # 0x009e -> MULTIPLICATION SIGN
+ '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
+ '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
+ '\xbf' # 0x00a8 -> INVERTED QUESTION MARK
+ '\xae' # 0x00a9 -> REGISTERED SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xa9' # 0x00b8 -> COPYRIGHT SIGN
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\xa2' # 0x00bd -> CENT SIGN
+ '\xa5' # 0x00be -> YEN SIGN
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE
+ '\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\xa4' # 0x00cf -> CURRENCY SIGN
+ '\xf0' # 0x00d0 -> LATIN SMALL LETTER ETH
+ '\xd0' # 0x00d1 -> LATIN CAPITAL LETTER ETH
+ '\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\u20ac' # 0x00d5 -> EURO SIGN
+ '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\xa6' # 0x00dd -> BROKEN BAR
+ '\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE
+ '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\xfe' # 0x00e7 -> LATIN SMALL LETTER THORN
+ '\xde' # 0x00e8 -> LATIN CAPITAL LETTER THORN
+ '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xaf' # 0x00ee -> MACRON
+ '\xb4' # 0x00ef -> ACUTE ACCENT
+ '\xad' # 0x00f0 -> SOFT HYPHEN
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2017' # 0x00f2 -> DOUBLE LOW LINE
+ '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
+ '\xb6' # 0x00f4 -> PILCROW SIGN
+ '\xa7' # 0x00f5 -> SECTION SIGN
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\xb8' # 0x00f7 -> CEDILLA
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\xa8' # 0x00f9 -> DIAERESIS
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\xb9' # 0x00fb -> SUPERSCRIPT ONE
+ '\xb3' # 0x00fc -> SUPERSCRIPT THREE
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
+ 0x00a2: 0x00bd, # CENT SIGN
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a4: 0x00cf, # CURRENCY SIGN
+ 0x00a5: 0x00be, # YEN SIGN
+ 0x00a6: 0x00dd, # BROKEN BAR
+ 0x00a7: 0x00f5, # SECTION SIGN
+ 0x00a8: 0x00f9, # DIAERESIS
+ 0x00a9: 0x00b8, # COPYRIGHT SIGN
+ 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00ad: 0x00f0, # SOFT HYPHEN
+ 0x00ae: 0x00a9, # REGISTERED SIGN
+ 0x00af: 0x00ee, # MACRON
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b3: 0x00fc, # SUPERSCRIPT THREE
+ 0x00b4: 0x00ef, # ACUTE ACCENT
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b6: 0x00f4, # PILCROW SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00b8: 0x00f7, # CEDILLA
+ 0x00b9: 0x00fb, # SUPERSCRIPT ONE
+ 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
+ 0x00bf: 0x00a8, # INVERTED QUESTION MARK
+ 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x00d0: 0x00d1, # LATIN CAPITAL LETTER ETH
+ 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x00d7: 0x009e, # MULTIPLICATION SIGN
+ 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x00de: 0x00e8, # LATIN CAPITAL LETTER THORN
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE
+ 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x00f0: 0x00d0, # LATIN SMALL LETTER ETH
+ 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
+ 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE
+ 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
+ 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x00fe: 0x00e7, # LATIN SMALL LETTER THORN
+ 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x20ac: 0x00d5, # EURO SIGN
+ 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
+ 0x2017: 0x00f2, # DOUBLE LOW LINE
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/hex_codec.py b/Lib/encodings/hex_codec.py
new file mode 100644
index 0000000000..e003fc3ff9
--- /dev/null
+++ b/Lib/encodings/hex_codec.py
@@ -0,0 +1,55 @@
+"""Python 'hex_codec' Codec - 2-digit hex content transfer encoding.
+
+This codec de/encodes from bytes to bytes and is therefore usable with
+bytes.transform() and bytes.untransform().
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+"""
+
+import codecs
+import binascii
+
+### Codec APIs
+
+def hex_encode(input, errors='strict'):
+ assert errors == 'strict'
+ return (binascii.b2a_hex(input), len(input))
+
+def hex_decode(input, errors='strict'):
+ assert errors == 'strict'
+ return (binascii.a2b_hex(input), len(input))
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return hex_encode(input, errors)
+ def decode(self, input, errors='strict'):
+ return hex_decode(input, errors)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ assert self.errors == 'strict'
+ return binascii.b2a_hex(input)
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ assert self.errors == 'strict'
+ return binascii.a2b_hex(input)
+
+class StreamWriter(Codec, codecs.StreamWriter):
+ charbuffertype = bytes
+
+class StreamReader(Codec, codecs.StreamReader):
+ charbuffertype = bytes
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='hex',
+ encode=hex_encode,
+ decode=hex_decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ )
diff --git a/Lib/encodings/punycode.py b/Lib/encodings/punycode.py
index 8129af2543..66c51013ea 100644
--- a/Lib/encodings/punycode.py
+++ b/Lib/encodings/punycode.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
""" Codec for the Punicode encoding, as specified in RFC 3492
Written by Martin v. Löwis.
diff --git a/Lib/encodings/quopri_codec.py b/Lib/encodings/quopri_codec.py
new file mode 100644
index 0000000000..9243fc443b
--- /dev/null
+++ b/Lib/encodings/quopri_codec.py
@@ -0,0 +1,56 @@
+"""Codec for quoted-printable encoding.
+
+This codec de/encodes from bytes to bytes and is therefore usable with
+bytes.transform() and bytes.untransform().
+"""
+
+import codecs
+import quopri
+from io import BytesIO
+
+def quopri_encode(input, errors='strict'):
+ assert errors == 'strict'
+ f = BytesIO(input)
+ g = BytesIO()
+ quopri.encode(f, g, 1)
+ return (g.getvalue(), len(input))
+
+def quopri_decode(input, errors='strict'):
+ assert errors == 'strict'
+ f = BytesIO(input)
+ g = BytesIO()
+ quopri.decode(f, g)
+ return (g.getvalue(), len(input))
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return quopri_encode(input, errors)
+ def decode(self, input, errors='strict'):
+ return quopri_decode(input, errors)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return quopri_encode(input, self.errors)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return quopri_decode(input, self.errors)[0]
+
+class StreamWriter(Codec, codecs.StreamWriter):
+ charbuffertype = bytes
+
+class StreamReader(Codec, codecs.StreamReader):
+ charbuffertype = bytes
+
+# encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='quopri',
+ encode=quopri_encode,
+ decode=quopri_decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ )
diff --git a/Lib/encodings/rot_13.py b/Lib/encodings/rot_13.py
new file mode 100755
index 0000000000..3140c1432d
--- /dev/null
+++ b/Lib/encodings/rot_13.py
@@ -0,0 +1,113 @@
+#!/usr/bin/env python
+""" Python Character Mapping Codec for ROT13.
+
+This codec de/encodes from str to str and is therefore usable with
+str.transform() and str.untransform().
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+"""
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return (input.translate(rot13_map), len(input))
+
+ def decode(self, input, errors='strict'):
+ return (input.translate(rot13_map), len(input))
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return input.translate(rot13_map)
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return input.translate(rot13_map)
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='rot-13',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ )
+
+### Map
+
+rot13_map = codecs.make_identity_dict(range(256))
+rot13_map.update({
+ 0x0041: 0x004e,
+ 0x0042: 0x004f,
+ 0x0043: 0x0050,
+ 0x0044: 0x0051,
+ 0x0045: 0x0052,
+ 0x0046: 0x0053,
+ 0x0047: 0x0054,
+ 0x0048: 0x0055,
+ 0x0049: 0x0056,
+ 0x004a: 0x0057,
+ 0x004b: 0x0058,
+ 0x004c: 0x0059,
+ 0x004d: 0x005a,
+ 0x004e: 0x0041,
+ 0x004f: 0x0042,
+ 0x0050: 0x0043,
+ 0x0051: 0x0044,
+ 0x0052: 0x0045,
+ 0x0053: 0x0046,
+ 0x0054: 0x0047,
+ 0x0055: 0x0048,
+ 0x0056: 0x0049,
+ 0x0057: 0x004a,
+ 0x0058: 0x004b,
+ 0x0059: 0x004c,
+ 0x005a: 0x004d,
+ 0x0061: 0x006e,
+ 0x0062: 0x006f,
+ 0x0063: 0x0070,
+ 0x0064: 0x0071,
+ 0x0065: 0x0072,
+ 0x0066: 0x0073,
+ 0x0067: 0x0074,
+ 0x0068: 0x0075,
+ 0x0069: 0x0076,
+ 0x006a: 0x0077,
+ 0x006b: 0x0078,
+ 0x006c: 0x0079,
+ 0x006d: 0x007a,
+ 0x006e: 0x0061,
+ 0x006f: 0x0062,
+ 0x0070: 0x0063,
+ 0x0071: 0x0064,
+ 0x0072: 0x0065,
+ 0x0073: 0x0066,
+ 0x0074: 0x0067,
+ 0x0075: 0x0068,
+ 0x0076: 0x0069,
+ 0x0077: 0x006a,
+ 0x0078: 0x006b,
+ 0x0079: 0x006c,
+ 0x007a: 0x006d,
+})
+
+### Filter API
+
+def rot13(infile, outfile):
+ outfile.write(infile.read().encode('rot-13'))
+
+if __name__ == '__main__':
+ import sys
+ rot13(sys.stdin, sys.stdout)
diff --git a/Lib/encodings/uu_codec.py b/Lib/encodings/uu_codec.py
new file mode 100644
index 0000000000..69c6f17c7f
--- /dev/null
+++ b/Lib/encodings/uu_codec.py
@@ -0,0 +1,99 @@
+"""Python 'uu_codec' Codec - UU content transfer encoding.
+
+This codec de/encodes from bytes to bytes and is therefore usable with
+bytes.transform() and bytes.untransform().
+
+Written by Marc-Andre Lemburg (mal@lemburg.com). Some details were
+adapted from uu.py which was written by Lance Ellinghouse and
+modified by Jack Jansen and Fredrik Lundh.
+"""
+
+import codecs
+import binascii
+from io import BytesIO
+
+### Codec APIs
+
+def uu_encode(input, errors='strict', filename='<data>', mode=0o666):
+ assert errors == 'strict'
+ infile = BytesIO(input)
+ outfile = BytesIO()
+ read = infile.read
+ write = outfile.write
+
+ # Encode
+ write(('begin %o %s\n' % (mode & 0o777, filename)).encode('ascii'))
+ chunk = read(45)
+ while chunk:
+ write(binascii.b2a_uu(chunk))
+ chunk = read(45)
+ write(b' \nend\n')
+
+ return (outfile.getvalue(), len(input))
+
+def uu_decode(input, errors='strict'):
+ assert errors == 'strict'
+ infile = BytesIO(input)
+ outfile = BytesIO()
+ readline = infile.readline
+ write = outfile.write
+
+ # Find start of encoded data
+ while 1:
+ s = readline()
+ if not s:
+ raise ValueError('Missing "begin" line in input data')
+ if s[:5] == b'begin':
+ break
+
+ # Decode
+ while True:
+ s = readline()
+ if not s or s == b'end\n':
+ break
+ try:
+ data = binascii.a2b_uu(s)
+ except binascii.Error as v:
+ # Workaround for broken uuencoders by /Fredrik Lundh
+ nbytes = (((ord(s[0])-32) & 63) * 4 + 5) / 3
+ data = binascii.a2b_uu(s[:nbytes])
+ #sys.stderr.write("Warning: %s\n" % str(v))
+ write(data)
+ if not s:
+ raise ValueError('Truncated input data')
+
+ return (outfile.getvalue(), len(input))
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return uu_encode(input, errors)
+
+ def decode(self, input, errors='strict'):
+ return uu_decode(input, errors)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return uu_encode(input, self.errors)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return uu_decode(input, self.errors)[0]
+
+class StreamWriter(Codec, codecs.StreamWriter):
+ charbuffertype = bytes
+
+class StreamReader(Codec, codecs.StreamReader):
+ charbuffertype = bytes
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='uu',
+ encode=uu_encode,
+ decode=uu_decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/zlib_codec.py b/Lib/encodings/zlib_codec.py
new file mode 100644
index 0000000000..e0b9cdadbc
--- /dev/null
+++ b/Lib/encodings/zlib_codec.py
@@ -0,0 +1,77 @@
+"""Python 'zlib_codec' Codec - zlib compression encoding.
+
+This codec de/encodes from bytes to bytes and is therefore usable with
+bytes.transform() and bytes.untransform().
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+"""
+
+import codecs
+import zlib # this codec needs the optional zlib module !
+
+### Codec APIs
+
+def zlib_encode(input, errors='strict'):
+ assert errors == 'strict'
+ return (zlib.compress(input), len(input))
+
+def zlib_decode(input, errors='strict'):
+ assert errors == 'strict'
+ return (zlib.decompress(input), len(input))
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return zlib_encode(input, errors)
+ def decode(self, input, errors='strict'):
+ return zlib_decode(input, errors)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def __init__(self, errors='strict'):
+ assert errors == 'strict'
+ self.errors = errors
+ self.compressobj = zlib.compressobj()
+
+ def encode(self, input, final=False):
+ if final:
+ c = self.compressobj.compress(input)
+ return c + self.compressobj.flush()
+ else:
+ return self.compressobj.compress(input)
+
+ def reset(self):
+ self.compressobj = zlib.compressobj()
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def __init__(self, errors='strict'):
+ assert errors == 'strict'
+ self.errors = errors
+ self.decompressobj = zlib.decompressobj()
+
+ def decode(self, input, final=False):
+ if final:
+ c = self.decompressobj.decompress(input)
+ return c + self.decompressobj.flush()
+ else:
+ return self.decompressobj.decompress(input)
+
+ def reset(self):
+ self.decompressobj = zlib.decompressobj()
+
+class StreamWriter(Codec, codecs.StreamWriter):
+ charbuffertype = bytes
+
+class StreamReader(Codec, codecs.StreamReader):
+ charbuffertype = bytes
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='zlib',
+ encode=zlib_encode,
+ decode=zlib_decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )