优化项目结构、优化 maven 结构

This commit is contained in:
chenkailing
2021-02-10 00:58:13 +08:00
parent 28d3e05ca9
commit 2542a24675
3610 changed files with 77 additions and 180 deletions

View File

@@ -0,0 +1,157 @@
""" Standard "encodings" Package
Standard Python encoding modules are stored in this package
directory.
Codec modules must have names corresponding to normalized encoding
names as defined in the normalize_encoding() function below, e.g.
'utf-8' must be implemented by the module 'utf_8.py'.
Each codec module must export the following interface:
* getregentry() -> codecs.CodecInfo object
The getregentry() API must a CodecInfo object with encoder, decoder,
incrementalencoder, incrementaldecoder, streamwriter and streamreader
atttributes which adhere to the Python Codec Interface Standard.
In addition, a module may optionally also define the following
APIs which are then used by the package's codec search function:
* getaliases() -> sequence of encoding name strings to use as aliases
Alias names returned by getaliases() must be normalized encoding
names as defined by normalize_encoding().
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
import codecs
from encodings import aliases
import __builtin__
_cache = {}
_unknown = '--unknown--'
_import_tail = ['*']
_norm_encoding_map = (' . '
'0123456789 ABCDEFGHIJKLMNOPQRSTUVWXYZ '
' abcdefghijklmnopqrstuvwxyz '
' '
' '
' ')
_aliases = aliases.aliases
class CodecRegistryError(LookupError, SystemError):
pass
def normalize_encoding(encoding):
""" Normalize an encoding name.
Normalization works as follows: all non-alphanumeric
characters except the dot used for Python package names are
collapsed and replaced with a single underscore, e.g. ' -;#'
becomes '_'. Leading and trailing underscores are removed.
Note that encoding names should be ASCII only; if they do use
non-ASCII characters, these must be Latin-1 compatible.
"""
# Make sure we have an 8-bit string, because .translate() works
# differently for Unicode strings.
if hasattr(__builtin__, "unicode") and isinstance(encoding, unicode):
# Note that .encode('latin-1') does *not* use the codec
# registry, so this call doesn't recurse. (See unicodeobject.c
# PyUnicode_AsEncodedString() for details)
encoding = encoding.encode('latin-1')
return '_'.join(encoding.translate(_norm_encoding_map).split())
def search_function(encoding):
# Cache lookup
entry = _cache.get(encoding, _unknown)
if entry is not _unknown:
return entry
# Import the module:
#
# First try to find an alias for the normalized encoding
# name and lookup the module using the aliased name, then try to
# lookup the module using the standard import scheme, i.e. first
# try in the encodings package, then at top-level.
#
norm_encoding = normalize_encoding(encoding)
aliased_encoding = _aliases.get(norm_encoding) or \
_aliases.get(norm_encoding.replace('.', '_'))
if aliased_encoding is not None:
modnames = [aliased_encoding,
norm_encoding]
else:
modnames = [norm_encoding]
for modname in modnames:
if not modname or '.' in modname:
continue
try:
# Import is absolute to prevent the possibly malicious import of a
# module with side-effects that is not in the 'encodings' package.
mod = __import__('encodings.' + modname, fromlist=_import_tail,
level=0)
except ImportError:
pass
else:
break
else:
mod = None
try:
getregentry = mod.getregentry
except AttributeError:
# Not a codec module
mod = None
if mod is None:
# Cache misses
_cache[encoding] = None
return None
# Now ask the module for the registry entry
entry = getregentry()
if not isinstance(entry, codecs.CodecInfo):
if not 4 <= len(entry) <= 7:
raise CodecRegistryError,\
'module "%s" (%s) failed to register' % \
(mod.__name__, mod.__file__)
if not hasattr(entry[0], '__call__') or \
not hasattr(entry[1], '__call__') or \
(entry[2] is not None and not hasattr(entry[2], '__call__')) or \
(entry[3] is not None and not hasattr(entry[3], '__call__')) or \
(len(entry) > 4 and entry[4] is not None and not hasattr(entry[4], '__call__')) or \
(len(entry) > 5 and entry[5] is not None and not hasattr(entry[5], '__call__')):
raise CodecRegistryError,\
'incompatible codecs in module "%s" (%s)' % \
(mod.__name__, mod.__file__)
if len(entry)<7 or entry[6] is None:
entry += (None,)*(6-len(entry)) + (mod.__name__.split(".", 1)[1],)
entry = codecs.CodecInfo(*entry)
# Cache the codec registry entry
_cache[encoding] = entry
# Register its aliases (without overwriting previously registered
# aliases)
try:
codecaliases = mod.getaliases()
except AttributeError:
pass
else:
for alias in codecaliases:
if alias not in _aliases:
_aliases[alias] = modname
# Return the registry entry
return entry
# Register the search_function in the Python codec registry
codecs.register(search_function)

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,50 @@
""" Python 'ascii' Codec
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""
import codecs
### Codec APIs
class Codec(codecs.Codec):
# Note: Binding these as C functions will result in the class not
# converting them to methods. This is intended.
encode = codecs.ascii_encode
decode = codecs.ascii_decode
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
return codecs.ascii_encode(input, self.errors)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
return codecs.ascii_decode(input, self.errors)[0]
class StreamWriter(Codec,codecs.StreamWriter):
pass
class StreamReader(Codec,codecs.StreamReader):
pass
class StreamConverter(StreamWriter,StreamReader):
encode = codecs.ascii_decode
decode = codecs.ascii_encode
### encodings module API
def getregentry():
return codecs.CodecInfo(
name='ascii',
encode=Codec.encode,
decode=Codec.decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamwriter=StreamWriter,
streamreader=StreamReader,
)

View File

@@ -0,0 +1,79 @@
""" Python 'base64_codec' Codec - base64 content transfer encoding
Unlike most of the other codecs which target Unicode, this codec
will return Python string objects for both encode and decode.
Written by Marc-Andre Lemburg (mal@lemburg.com).
"""
import codecs, base64
### Codec APIs
def base64_encode(input,errors='strict'):
""" Encodes the object input and returns a tuple (output
object, length consumed).
errors defines the error handling to apply. It defaults to
'strict' handling which is the only currently supported
error handling for this codec.
"""
assert errors == 'strict'
output = base64.encodestring(input)
return (output, len(input))
def base64_decode(input,errors='strict'):
""" Decodes the object input and returns a tuple (output
object, length consumed).
input must be an object which provides the bf_getreadbuf
buffer slot. Python strings, buffer objects and memory
mapped files are examples of objects providing this slot.
errors defines the error handling to apply. It defaults to
'strict' handling which is the only currently supported
error handling for this codec.
"""
assert errors == 'strict'
output = base64.decodestring(input)
return (output, 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.encodestring(input)
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
assert self.errors == 'strict'
return base64.decodestring(input)
class StreamWriter(Codec,codecs.StreamWriter):
pass
class StreamReader(Codec,codecs.StreamReader):
pass
### encodings module API
def getregentry():
return codecs.CodecInfo(
name='base64',
encode=base64_encode,
decode=base64_decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamwriter=StreamWriter,
streamreader=StreamReader,
)

View File

@@ -0,0 +1,39 @@
#
# big5.py: Python Unicode Codec for BIG5
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_tw, codecs
import _multibytecodec as mbc
codec = _codecs_tw.getcodec('big5')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='big5',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)

View File

@@ -0,0 +1,39 @@
#
# big5hkscs.py: Python Unicode Codec for BIG5HKSCS
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_hk, codecs
import _multibytecodec as mbc
codec = _codecs_hk.getcodec('big5hkscs')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='big5hkscs',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)

View File

@@ -0,0 +1,102 @@
""" Python 'bz2_codec' Codec - bz2 compression encoding
Unlike most of the other codecs which target Unicode, this codec
will return Python string objects for both encode and decode.
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'):
""" Encodes the object input and returns a tuple (output
object, length consumed).
errors defines the error handling to apply. It defaults to
'strict' handling which is the only currently supported
error handling for this codec.
"""
assert errors == 'strict'
output = bz2.compress(input)
return (output, len(input))
def bz2_decode(input,errors='strict'):
""" Decodes the object input and returns a tuple (output
object, length consumed).
input must be an object which provides the bf_getreadbuf
buffer slot. Python strings, buffer objects and memory
mapped files are examples of objects providing this slot.
errors defines the error handling to apply. It defaults to
'strict' handling which is the only currently supported
error handling for this codec.
"""
assert errors == 'strict'
output = bz2.decompress(input)
return (output, 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):
pass
class StreamReader(Codec,codecs.StreamReader):
pass
### encodings module API
def getregentry():
return codecs.CodecInfo(
name="bz2",
encode=bz2_encode,
decode=bz2_decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamwriter=StreamWriter,
streamreader=StreamReader,
)

View File

@@ -0,0 +1,69 @@
""" Generic Python Character Mapping Codec.
Use this codec directly rather than through the automatic
conversion mechanisms supplied by unicode() and .encode().
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
# Note: Binding these as C functions will result in the class not
# converting them to methods. This is intended.
encode = codecs.charmap_encode
decode = codecs.charmap_decode
class IncrementalEncoder(codecs.IncrementalEncoder):
def __init__(self, errors='strict', mapping=None):
codecs.IncrementalEncoder.__init__(self, errors)
self.mapping = mapping
def encode(self, input, final=False):
return codecs.charmap_encode(input, self.errors, self.mapping)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def __init__(self, errors='strict', mapping=None):
codecs.IncrementalDecoder.__init__(self, errors)
self.mapping = mapping
def decode(self, input, final=False):
return codecs.charmap_decode(input, self.errors, self.mapping)[0]
class StreamWriter(Codec,codecs.StreamWriter):
def __init__(self,stream,errors='strict',mapping=None):
codecs.StreamWriter.__init__(self,stream,errors)
self.mapping = mapping
def encode(self,input,errors='strict'):
return Codec.encode(input,errors,self.mapping)
class StreamReader(Codec,codecs.StreamReader):
def __init__(self,stream,errors='strict',mapping=None):
codecs.StreamReader.__init__(self,stream,errors)
self.mapping = mapping
def decode(self,input,errors='strict'):
return Codec.decode(input,errors,self.mapping)
### encodings module API
def getregentry():
return codecs.CodecInfo(
name='charmap',
encode=Codec.encode,
decode=Codec.decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamwriter=StreamWriter,
streamreader=StreamReader,
)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp037 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp037',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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 -> CONTROL
u'\t' # 0x05 -> HORIZONTAL TABULATION
u'\x86' # 0x06 -> CONTROL
u'\x7f' # 0x07 -> DELETE
u'\x97' # 0x08 -> CONTROL
u'\x8d' # 0x09 -> CONTROL
u'\x8e' # 0x0A -> CONTROL
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 -> CONTROL
u'\x85' # 0x15 -> CONTROL
u'\x08' # 0x16 -> BACKSPACE
u'\x87' # 0x17 -> CONTROL
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x92' # 0x1A -> CONTROL
u'\x8f' # 0x1B -> CONTROL
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u'\x80' # 0x20 -> CONTROL
u'\x81' # 0x21 -> CONTROL
u'\x82' # 0x22 -> CONTROL
u'\x83' # 0x23 -> CONTROL
u'\x84' # 0x24 -> CONTROL
u'\n' # 0x25 -> LINE FEED
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x27 -> ESCAPE
u'\x88' # 0x28 -> CONTROL
u'\x89' # 0x29 -> CONTROL
u'\x8a' # 0x2A -> CONTROL
u'\x8b' # 0x2B -> CONTROL
u'\x8c' # 0x2C -> CONTROL
u'\x05' # 0x2D -> ENQUIRY
u'\x06' # 0x2E -> ACKNOWLEDGE
u'\x07' # 0x2F -> BELL
u'\x90' # 0x30 -> CONTROL
u'\x91' # 0x31 -> CONTROL
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
u'\x93' # 0x33 -> CONTROL
u'\x94' # 0x34 -> CONTROL
u'\x95' # 0x35 -> CONTROL
u'\x96' # 0x36 -> CONTROL
u'\x04' # 0x37 -> END OF TRANSMISSION
u'\x98' # 0x38 -> CONTROL
u'\x99' # 0x39 -> CONTROL
u'\x9a' # 0x3A -> CONTROL
u'\x9b' # 0x3B -> CONTROL
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x3E -> CONTROL
u'\x1a' # 0x3F -> SUBSTITUTE
u' ' # 0x40 -> SPACE
u'\xa0' # 0x41 -> NO-BREAK SPACE
u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
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'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
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'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
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'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
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'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
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'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC)
u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC)
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'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
u'\xb8' # 0x9D -> CEDILLA
u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
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'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
u'\xbf' # 0xAB -> INVERTED QUESTION MARK
u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC)
u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC)
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'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
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'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
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'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
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'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
u'\x9f' # 0xFF -> CONTROL
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1006 generated from 'MAPPINGS/VENDORS/MISC/CP1006.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1006',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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'\u06f0' # 0xA1 -> EXTENDED ARABIC-INDIC DIGIT ZERO
u'\u06f1' # 0xA2 -> EXTENDED ARABIC-INDIC DIGIT ONE
u'\u06f2' # 0xA3 -> EXTENDED ARABIC-INDIC DIGIT TWO
u'\u06f3' # 0xA4 -> EXTENDED ARABIC-INDIC DIGIT THREE
u'\u06f4' # 0xA5 -> EXTENDED ARABIC-INDIC DIGIT FOUR
u'\u06f5' # 0xA6 -> EXTENDED ARABIC-INDIC DIGIT FIVE
u'\u06f6' # 0xA7 -> EXTENDED ARABIC-INDIC DIGIT SIX
u'\u06f7' # 0xA8 -> EXTENDED ARABIC-INDIC DIGIT SEVEN
u'\u06f8' # 0xA9 -> EXTENDED ARABIC-INDIC DIGIT EIGHT
u'\u06f9' # 0xAA -> EXTENDED ARABIC-INDIC DIGIT NINE
u'\u060c' # 0xAB -> ARABIC COMMA
u'\u061b' # 0xAC -> ARABIC SEMICOLON
u'\xad' # 0xAD -> SOFT HYPHEN
u'\u061f' # 0xAE -> ARABIC QUESTION MARK
u'\ufe81' # 0xAF -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
u'\ufe8d' # 0xB0 -> ARABIC LETTER ALEF ISOLATED FORM
u'\ufe8e' # 0xB1 -> ARABIC LETTER ALEF FINAL FORM
u'\ufe8e' # 0xB2 -> ARABIC LETTER ALEF FINAL FORM
u'\ufe8f' # 0xB3 -> ARABIC LETTER BEH ISOLATED FORM
u'\ufe91' # 0xB4 -> ARABIC LETTER BEH INITIAL FORM
u'\ufb56' # 0xB5 -> ARABIC LETTER PEH ISOLATED FORM
u'\ufb58' # 0xB6 -> ARABIC LETTER PEH INITIAL FORM
u'\ufe93' # 0xB7 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM
u'\ufe95' # 0xB8 -> ARABIC LETTER TEH ISOLATED FORM
u'\ufe97' # 0xB9 -> ARABIC LETTER TEH INITIAL FORM
u'\ufb66' # 0xBA -> ARABIC LETTER TTEH ISOLATED FORM
u'\ufb68' # 0xBB -> ARABIC LETTER TTEH INITIAL FORM
u'\ufe99' # 0xBC -> ARABIC LETTER THEH ISOLATED FORM
u'\ufe9b' # 0xBD -> ARABIC LETTER THEH INITIAL FORM
u'\ufe9d' # 0xBE -> ARABIC LETTER JEEM ISOLATED FORM
u'\ufe9f' # 0xBF -> ARABIC LETTER JEEM INITIAL FORM
u'\ufb7a' # 0xC0 -> ARABIC LETTER TCHEH ISOLATED FORM
u'\ufb7c' # 0xC1 -> ARABIC LETTER TCHEH INITIAL FORM
u'\ufea1' # 0xC2 -> ARABIC LETTER HAH ISOLATED FORM
u'\ufea3' # 0xC3 -> ARABIC LETTER HAH INITIAL FORM
u'\ufea5' # 0xC4 -> ARABIC LETTER KHAH ISOLATED FORM
u'\ufea7' # 0xC5 -> ARABIC LETTER KHAH INITIAL FORM
u'\ufea9' # 0xC6 -> ARABIC LETTER DAL ISOLATED FORM
u'\ufb84' # 0xC7 -> ARABIC LETTER DAHAL ISOLATED FORMN
u'\ufeab' # 0xC8 -> ARABIC LETTER THAL ISOLATED FORM
u'\ufead' # 0xC9 -> ARABIC LETTER REH ISOLATED FORM
u'\ufb8c' # 0xCA -> ARABIC LETTER RREH ISOLATED FORM
u'\ufeaf' # 0xCB -> ARABIC LETTER ZAIN ISOLATED FORM
u'\ufb8a' # 0xCC -> ARABIC LETTER JEH ISOLATED FORM
u'\ufeb1' # 0xCD -> ARABIC LETTER SEEN ISOLATED FORM
u'\ufeb3' # 0xCE -> ARABIC LETTER SEEN INITIAL FORM
u'\ufeb5' # 0xCF -> ARABIC LETTER SHEEN ISOLATED FORM
u'\ufeb7' # 0xD0 -> ARABIC LETTER SHEEN INITIAL FORM
u'\ufeb9' # 0xD1 -> ARABIC LETTER SAD ISOLATED FORM
u'\ufebb' # 0xD2 -> ARABIC LETTER SAD INITIAL FORM
u'\ufebd' # 0xD3 -> ARABIC LETTER DAD ISOLATED FORM
u'\ufebf' # 0xD4 -> ARABIC LETTER DAD INITIAL FORM
u'\ufec1' # 0xD5 -> ARABIC LETTER TAH ISOLATED FORM
u'\ufec5' # 0xD6 -> ARABIC LETTER ZAH ISOLATED FORM
u'\ufec9' # 0xD7 -> ARABIC LETTER AIN ISOLATED FORM
u'\ufeca' # 0xD8 -> ARABIC LETTER AIN FINAL FORM
u'\ufecb' # 0xD9 -> ARABIC LETTER AIN INITIAL FORM
u'\ufecc' # 0xDA -> ARABIC LETTER AIN MEDIAL FORM
u'\ufecd' # 0xDB -> ARABIC LETTER GHAIN ISOLATED FORM
u'\ufece' # 0xDC -> ARABIC LETTER GHAIN FINAL FORM
u'\ufecf' # 0xDD -> ARABIC LETTER GHAIN INITIAL FORM
u'\ufed0' # 0xDE -> ARABIC LETTER GHAIN MEDIAL FORM
u'\ufed1' # 0xDF -> ARABIC LETTER FEH ISOLATED FORM
u'\ufed3' # 0xE0 -> ARABIC LETTER FEH INITIAL FORM
u'\ufed5' # 0xE1 -> ARABIC LETTER QAF ISOLATED FORM
u'\ufed7' # 0xE2 -> ARABIC LETTER QAF INITIAL FORM
u'\ufed9' # 0xE3 -> ARABIC LETTER KAF ISOLATED FORM
u'\ufedb' # 0xE4 -> ARABIC LETTER KAF INITIAL FORM
u'\ufb92' # 0xE5 -> ARABIC LETTER GAF ISOLATED FORM
u'\ufb94' # 0xE6 -> ARABIC LETTER GAF INITIAL FORM
u'\ufedd' # 0xE7 -> ARABIC LETTER LAM ISOLATED FORM
u'\ufedf' # 0xE8 -> ARABIC LETTER LAM INITIAL FORM
u'\ufee0' # 0xE9 -> ARABIC LETTER LAM MEDIAL FORM
u'\ufee1' # 0xEA -> ARABIC LETTER MEEM ISOLATED FORM
u'\ufee3' # 0xEB -> ARABIC LETTER MEEM INITIAL FORM
u'\ufb9e' # 0xEC -> ARABIC LETTER NOON GHUNNA ISOLATED FORM
u'\ufee5' # 0xED -> ARABIC LETTER NOON ISOLATED FORM
u'\ufee7' # 0xEE -> ARABIC LETTER NOON INITIAL FORM
u'\ufe85' # 0xEF -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
u'\ufeed' # 0xF0 -> ARABIC LETTER WAW ISOLATED FORM
u'\ufba6' # 0xF1 -> ARABIC LETTER HEH GOAL ISOLATED FORM
u'\ufba8' # 0xF2 -> ARABIC LETTER HEH GOAL INITIAL FORM
u'\ufba9' # 0xF3 -> ARABIC LETTER HEH GOAL MEDIAL FORM
u'\ufbaa' # 0xF4 -> ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM
u'\ufe80' # 0xF5 -> ARABIC LETTER HAMZA ISOLATED FORM
u'\ufe89' # 0xF6 -> ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM
u'\ufe8a' # 0xF7 -> ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM
u'\ufe8b' # 0xF8 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
u'\ufef1' # 0xF9 -> ARABIC LETTER YEH ISOLATED FORM
u'\ufef2' # 0xFA -> ARABIC LETTER YEH FINAL FORM
u'\ufef3' # 0xFB -> ARABIC LETTER YEH INITIAL FORM
u'\ufbb0' # 0xFC -> ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM
u'\ufbae' # 0xFD -> ARABIC LETTER YEH BARREE ISOLATED FORM
u'\ufe7c' # 0xFE -> ARABIC SHADDA ISOLATED FORM
u'\ufe7d' # 0xFF -> ARABIC SHADDA MEDIAL FORM
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1026 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1026',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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 -> CONTROL
u'\t' # 0x05 -> HORIZONTAL TABULATION
u'\x86' # 0x06 -> CONTROL
u'\x7f' # 0x07 -> DELETE
u'\x97' # 0x08 -> CONTROL
u'\x8d' # 0x09 -> CONTROL
u'\x8e' # 0x0A -> CONTROL
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 -> CONTROL
u'\x85' # 0x15 -> CONTROL
u'\x08' # 0x16 -> BACKSPACE
u'\x87' # 0x17 -> CONTROL
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x92' # 0x1A -> CONTROL
u'\x8f' # 0x1B -> CONTROL
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u'\x80' # 0x20 -> CONTROL
u'\x81' # 0x21 -> CONTROL
u'\x82' # 0x22 -> CONTROL
u'\x83' # 0x23 -> CONTROL
u'\x84' # 0x24 -> CONTROL
u'\n' # 0x25 -> LINE FEED
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x27 -> ESCAPE
u'\x88' # 0x28 -> CONTROL
u'\x89' # 0x29 -> CONTROL
u'\x8a' # 0x2A -> CONTROL
u'\x8b' # 0x2B -> CONTROL
u'\x8c' # 0x2C -> CONTROL
u'\x05' # 0x2D -> ENQUIRY
u'\x06' # 0x2E -> ACKNOWLEDGE
u'\x07' # 0x2F -> BELL
u'\x90' # 0x30 -> CONTROL
u'\x91' # 0x31 -> CONTROL
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
u'\x93' # 0x33 -> CONTROL
u'\x94' # 0x34 -> CONTROL
u'\x95' # 0x35 -> CONTROL
u'\x96' # 0x36 -> CONTROL
u'\x04' # 0x37 -> END OF TRANSMISSION
u'\x98' # 0x38 -> CONTROL
u'\x99' # 0x39 -> CONTROL
u'\x9a' # 0x3A -> CONTROL
u'\x9b' # 0x3B -> CONTROL
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x3E -> CONTROL
u'\x1a' # 0x3F -> SUBSTITUTE
u' ' # 0x40 -> SPACE
u'\xa0' # 0x41 -> NO-BREAK SPACE
u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
u'{' # 0x48 -> LEFT CURLY BRACKET
u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
u'\xc7' # 0x4A -> LATIN CAPITAL LETTER C WITH CEDILLA
u'.' # 0x4B -> FULL STOP
u'<' # 0x4C -> LESS-THAN SIGN
u'(' # 0x4D -> LEFT PARENTHESIS
u'+' # 0x4E -> PLUS SIGN
u'!' # 0x4F -> EXCLAMATION MARK
u'&' # 0x50 -> AMPERSAND
u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
u'\u011e' # 0x5A -> LATIN CAPITAL LETTER G WITH BREVE
u'\u0130' # 0x5B -> LATIN CAPITAL LETTER I WITH DOT ABOVE
u'*' # 0x5C -> ASTERISK
u')' # 0x5D -> RIGHT PARENTHESIS
u';' # 0x5E -> SEMICOLON
u'^' # 0x5F -> CIRCUMFLEX ACCENT
u'-' # 0x60 -> HYPHEN-MINUS
u'/' # 0x61 -> SOLIDUS
u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'[' # 0x68 -> LEFT SQUARE BRACKET
u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
u'\u015f' # 0x6A -> LATIN SMALL LETTER S WITH CEDILLA
u',' # 0x6B -> COMMA
u'%' # 0x6C -> PERCENT SIGN
u'_' # 0x6D -> LOW LINE
u'>' # 0x6E -> GREATER-THAN SIGN
u'?' # 0x6F -> QUESTION MARK
u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
u'\u0131' # 0x79 -> LATIN SMALL LETTER DOTLESS I
u':' # 0x7A -> COLON
u'\xd6' # 0x7B -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\u015e' # 0x7C -> LATIN CAPITAL LETTER S WITH CEDILLA
u"'" # 0x7D -> APOSTROPHE
u'=' # 0x7E -> EQUALS SIGN
u'\xdc' # 0x7F -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
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'}' # 0x8C -> RIGHT CURLY BRACKET
u'`' # 0x8D -> GRAVE ACCENT
u'\xa6' # 0x8E -> BROKEN BAR
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'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
u'\xb8' # 0x9D -> CEDILLA
u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
u'\xa4' # 0x9F -> CURRENCY SIGN
u'\xb5' # 0xA0 -> MICRO SIGN
u'\xf6' # 0xA1 -> LATIN SMALL LETTER O WITH DIAERESIS
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'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
u'\xbf' # 0xAB -> INVERTED QUESTION MARK
u']' # 0xAC -> RIGHT SQUARE BRACKET
u'$' # 0xAD -> DOLLAR SIGN
u'@' # 0xAE -> COMMERCIAL AT
u'\xae' # 0xAF -> REGISTERED SIGN
u'\xa2' # 0xB0 -> CENT SIGN
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'\xac' # 0xBA -> NOT SIGN
u'|' # 0xBB -> VERTICAL LINE
u'\xaf' # 0xBC -> MACRON
u'\xa8' # 0xBD -> DIAERESIS
u'\xb4' # 0xBE -> ACUTE ACCENT
u'\xd7' # 0xBF -> MULTIPLICATION SIGN
u'\xe7' # 0xC0 -> LATIN SMALL LETTER C WITH CEDILLA
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'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'~' # 0xCC -> TILDE
u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
u'\u011f' # 0xD0 -> LATIN SMALL LETTER G WITH BREVE
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'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\\' # 0xDC -> REVERSE SOLIDUS
u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
u'\xfc' # 0xE0 -> LATIN SMALL LETTER U WITH DIAERESIS
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'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'#' # 0xEC -> NUMBER SIGN
u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
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'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'"' # 0xFC -> QUOTATION MARK
u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
u'\x9f' # 0xFF -> CONTROL
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1140 generated from 'python-mappings/CP1140.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1140',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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 -> CONTROL
u'\t' # 0x05 -> HORIZONTAL TABULATION
u'\x86' # 0x06 -> CONTROL
u'\x7f' # 0x07 -> DELETE
u'\x97' # 0x08 -> CONTROL
u'\x8d' # 0x09 -> CONTROL
u'\x8e' # 0x0A -> CONTROL
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 -> CONTROL
u'\x85' # 0x15 -> CONTROL
u'\x08' # 0x16 -> BACKSPACE
u'\x87' # 0x17 -> CONTROL
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x92' # 0x1A -> CONTROL
u'\x8f' # 0x1B -> CONTROL
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u'\x80' # 0x20 -> CONTROL
u'\x81' # 0x21 -> CONTROL
u'\x82' # 0x22 -> CONTROL
u'\x83' # 0x23 -> CONTROL
u'\x84' # 0x24 -> CONTROL
u'\n' # 0x25 -> LINE FEED
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x27 -> ESCAPE
u'\x88' # 0x28 -> CONTROL
u'\x89' # 0x29 -> CONTROL
u'\x8a' # 0x2A -> CONTROL
u'\x8b' # 0x2B -> CONTROL
u'\x8c' # 0x2C -> CONTROL
u'\x05' # 0x2D -> ENQUIRY
u'\x06' # 0x2E -> ACKNOWLEDGE
u'\x07' # 0x2F -> BELL
u'\x90' # 0x30 -> CONTROL
u'\x91' # 0x31 -> CONTROL
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
u'\x93' # 0x33 -> CONTROL
u'\x94' # 0x34 -> CONTROL
u'\x95' # 0x35 -> CONTROL
u'\x96' # 0x36 -> CONTROL
u'\x04' # 0x37 -> END OF TRANSMISSION
u'\x98' # 0x38 -> CONTROL
u'\x99' # 0x39 -> CONTROL
u'\x9a' # 0x3A -> CONTROL
u'\x9b' # 0x3B -> CONTROL
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x3E -> CONTROL
u'\x1a' # 0x3F -> SUBSTITUTE
u' ' # 0x40 -> SPACE
u'\xa0' # 0x41 -> NO-BREAK SPACE
u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
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'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
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'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
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'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
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'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
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'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC)
u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC)
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'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
u'\xb8' # 0x9D -> CEDILLA
u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
u'\u20ac' # 0x9F -> EURO 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'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
u'\xbf' # 0xAB -> INVERTED QUESTION MARK
u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC)
u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC)
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'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
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'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
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'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
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'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
u'\x9f' # 0xFF -> CONTROL
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1250 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1250',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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'\ufffe' # 0x83 -> UNDEFINED
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
u'\u2020' # 0x86 -> DAGGER
u'\u2021' # 0x87 -> DOUBLE DAGGER
u'\ufffe' # 0x88 -> UNDEFINED
u'\u2030' # 0x89 -> PER MILLE SIGN
u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
u'\u015a' # 0x8C -> LATIN CAPITAL LETTER S WITH ACUTE
u'\u0164' # 0x8D -> LATIN CAPITAL LETTER T WITH CARON
u'\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON
u'\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE
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'\u2122' # 0x99 -> TRADE MARK SIGN
u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
u'\u015b' # 0x9C -> LATIN SMALL LETTER S WITH ACUTE
u'\u0165' # 0x9D -> LATIN SMALL LETTER T WITH CARON
u'\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON
u'\u017a' # 0x9F -> LATIN SMALL LETTER Z WITH ACUTE
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\u02c7' # 0xA1 -> CARON
u'\u02d8' # 0xA2 -> BREVE
u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE
u'\xa4' # 0xA4 -> CURRENCY SIGN
u'\u0104' # 0xA5 -> LATIN CAPITAL LETTER A WITH OGONEK
u'\xa6' # 0xA6 -> BROKEN BAR
u'\xa7' # 0xA7 -> SECTION SIGN
u'\xa8' # 0xA8 -> DIAERESIS
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA
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'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
u'\xb0' # 0xB0 -> DEGREE SIGN
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
u'\u02db' # 0xB2 -> OGONEK
u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE
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'\u0105' # 0xB9 -> LATIN SMALL LETTER A WITH OGONEK
u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\u013d' # 0xBC -> LATIN CAPITAL LETTER L WITH CARON
u'\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT
u'\u013e' # 0xBE -> LATIN SMALL LETTER L WITH CARON
u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE
u'\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE
u'\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON
u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE
u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE
u'\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
u'\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON
u'\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
u'\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
u'\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
u'\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE
u'\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
u'\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON
u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE
u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE
u'\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf7' # 0xF7 -> DIVISION SIGN
u'\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON
u'\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
u'\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
u'\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA
u'\u02d9' # 0xFF -> DOT ABOVE
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1251 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1251',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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'\u0402' # 0x80 -> CYRILLIC CAPITAL LETTER DJE
u'\u0403' # 0x81 -> CYRILLIC CAPITAL LETTER GJE
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
u'\u0453' # 0x83 -> CYRILLIC SMALL LETTER GJE
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
u'\u2020' # 0x86 -> DAGGER
u'\u2021' # 0x87 -> DOUBLE DAGGER
u'\u20ac' # 0x88 -> EURO SIGN
u'\u2030' # 0x89 -> PER MILLE SIGN
u'\u0409' # 0x8A -> CYRILLIC CAPITAL LETTER LJE
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
u'\u040a' # 0x8C -> CYRILLIC CAPITAL LETTER NJE
u'\u040c' # 0x8D -> CYRILLIC CAPITAL LETTER KJE
u'\u040b' # 0x8E -> CYRILLIC CAPITAL LETTER TSHE
u'\u040f' # 0x8F -> CYRILLIC CAPITAL LETTER DZHE
u'\u0452' # 0x90 -> CYRILLIC SMALL LETTER DJE
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'\u2122' # 0x99 -> TRADE MARK SIGN
u'\u0459' # 0x9A -> CYRILLIC SMALL LETTER LJE
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
u'\u045a' # 0x9C -> CYRILLIC SMALL LETTER NJE
u'\u045c' # 0x9D -> CYRILLIC SMALL LETTER KJE
u'\u045b' # 0x9E -> CYRILLIC SMALL LETTER TSHE
u'\u045f' # 0x9F -> CYRILLIC SMALL LETTER DZHE
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\u040e' # 0xA1 -> CYRILLIC CAPITAL LETTER SHORT U
u'\u045e' # 0xA2 -> CYRILLIC SMALL LETTER SHORT U
u'\u0408' # 0xA3 -> CYRILLIC CAPITAL LETTER JE
u'\xa4' # 0xA4 -> CURRENCY SIGN
u'\u0490' # 0xA5 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN
u'\xa6' # 0xA6 -> BROKEN BAR
u'\xa7' # 0xA7 -> SECTION SIGN
u'\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
u'\u0404' # 0xAA -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
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'\u0407' # 0xAF -> CYRILLIC CAPITAL LETTER YI
u'\xb0' # 0xB0 -> DEGREE SIGN
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
u'\u0406' # 0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
u'\u0456' # 0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
u'\u0491' # 0xB4 -> CYRILLIC SMALL LETTER GHE WITH UPTURN
u'\xb5' # 0xB5 -> MICRO SIGN
u'\xb6' # 0xB6 -> PILCROW SIGN
u'\xb7' # 0xB7 -> MIDDLE DOT
u'\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO
u'\u2116' # 0xB9 -> NUMERO SIGN
u'\u0454' # 0xBA -> CYRILLIC SMALL LETTER UKRAINIAN IE
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\u0458' # 0xBC -> CYRILLIC SMALL LETTER JE
u'\u0405' # 0xBD -> CYRILLIC CAPITAL LETTER DZE
u'\u0455' # 0xBE -> CYRILLIC SMALL LETTER DZE
u'\u0457' # 0xBF -> CYRILLIC SMALL LETTER YI
u'\u0410' # 0xC0 -> CYRILLIC CAPITAL LETTER A
u'\u0411' # 0xC1 -> CYRILLIC CAPITAL LETTER BE
u'\u0412' # 0xC2 -> CYRILLIC CAPITAL LETTER VE
u'\u0413' # 0xC3 -> CYRILLIC CAPITAL LETTER GHE
u'\u0414' # 0xC4 -> CYRILLIC CAPITAL LETTER DE
u'\u0415' # 0xC5 -> CYRILLIC CAPITAL LETTER IE
u'\u0416' # 0xC6 -> CYRILLIC CAPITAL LETTER ZHE
u'\u0417' # 0xC7 -> CYRILLIC CAPITAL LETTER ZE
u'\u0418' # 0xC8 -> CYRILLIC CAPITAL LETTER I
u'\u0419' # 0xC9 -> CYRILLIC CAPITAL LETTER SHORT I
u'\u041a' # 0xCA -> CYRILLIC CAPITAL LETTER KA
u'\u041b' # 0xCB -> CYRILLIC CAPITAL LETTER EL
u'\u041c' # 0xCC -> CYRILLIC CAPITAL LETTER EM
u'\u041d' # 0xCD -> CYRILLIC CAPITAL LETTER EN
u'\u041e' # 0xCE -> CYRILLIC CAPITAL LETTER O
u'\u041f' # 0xCF -> CYRILLIC CAPITAL LETTER PE
u'\u0420' # 0xD0 -> CYRILLIC CAPITAL LETTER ER
u'\u0421' # 0xD1 -> CYRILLIC CAPITAL LETTER ES
u'\u0422' # 0xD2 -> CYRILLIC CAPITAL LETTER TE
u'\u0423' # 0xD3 -> CYRILLIC CAPITAL LETTER U
u'\u0424' # 0xD4 -> CYRILLIC CAPITAL LETTER EF
u'\u0425' # 0xD5 -> CYRILLIC CAPITAL LETTER HA
u'\u0426' # 0xD6 -> CYRILLIC CAPITAL LETTER TSE
u'\u0427' # 0xD7 -> CYRILLIC CAPITAL LETTER CHE
u'\u0428' # 0xD8 -> CYRILLIC CAPITAL LETTER SHA
u'\u0429' # 0xD9 -> CYRILLIC CAPITAL LETTER SHCHA
u'\u042a' # 0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN
u'\u042b' # 0xDB -> CYRILLIC CAPITAL LETTER YERU
u'\u042c' # 0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN
u'\u042d' # 0xDD -> CYRILLIC CAPITAL LETTER E
u'\u042e' # 0xDE -> CYRILLIC CAPITAL LETTER YU
u'\u042f' # 0xDF -> CYRILLIC CAPITAL LETTER YA
u'\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A
u'\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE
u'\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE
u'\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE
u'\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE
u'\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE
u'\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE
u'\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE
u'\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I
u'\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I
u'\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA
u'\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL
u'\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM
u'\u043d' # 0xED -> CYRILLIC SMALL LETTER EN
u'\u043e' # 0xEE -> CYRILLIC SMALL LETTER O
u'\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE
u'\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER
u'\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES
u'\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE
u'\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U
u'\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF
u'\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA
u'\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE
u'\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE
u'\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA
u'\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA
u'\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN
u'\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU
u'\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN
u'\u044d' # 0xFD -> CYRILLIC SMALL LETTER E
u'\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU
u'\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1252 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1252',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
u'\ufffe' # 0x8D -> UNDEFINED
u'\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON
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'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
u'\ufffe' # 0x9D -> UNDEFINED
u'\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON
u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
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'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
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'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
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'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf7' # 0xF7 -> DIVISION SIGN
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1253 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1253',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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'\ufffe' # 0x88 -> UNDEFINED
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'\ufffe' # 0x98 -> UNDEFINED
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'\u0385' # 0xA1 -> GREEK DIALYTIKA TONOS
u'\u0386' # 0xA2 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
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'\ufffe' # 0xAA -> UNDEFINED
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'\u2015' # 0xAF -> HORIZONTAL BAR
u'\xb0' # 0xB0 -> DEGREE SIGN
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
u'\u0384' # 0xB4 -> GREEK TONOS
u'\xb5' # 0xB5 -> MICRO SIGN
u'\xb6' # 0xB6 -> PILCROW SIGN
u'\xb7' # 0xB7 -> MIDDLE DOT
u'\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS
u'\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS
u'\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
u'\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS
u'\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS
u'\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
u'\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA
u'\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA
u'\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA
u'\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA
u'\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON
u'\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA
u'\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA
u'\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA
u'\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA
u'\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA
u'\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA
u'\u039c' # 0xCC -> GREEK CAPITAL LETTER MU
u'\u039d' # 0xCD -> GREEK CAPITAL LETTER NU
u'\u039e' # 0xCE -> GREEK CAPITAL LETTER XI
u'\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON
u'\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI
u'\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO
u'\ufffe' # 0xD2 -> UNDEFINED
u'\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA
u'\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU
u'\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON
u'\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI
u'\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI
u'\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI
u'\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA
u'\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
u'\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
u'\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS
u'\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS
u'\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS
u'\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS
u'\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
u'\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA
u'\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA
u'\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA
u'\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA
u'\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON
u'\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA
u'\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA
u'\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA
u'\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA
u'\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA
u'\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA
u'\u03bc' # 0xEC -> GREEK SMALL LETTER MU
u'\u03bd' # 0xED -> GREEK SMALL LETTER NU
u'\u03be' # 0xEE -> GREEK SMALL LETTER XI
u'\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON
u'\u03c0' # 0xF0 -> GREEK SMALL LETTER PI
u'\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO
u'\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA
u'\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA
u'\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU
u'\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON
u'\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI
u'\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI
u'\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI
u'\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA
u'\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
u'\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
u'\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS
u'\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS
u'\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS
u'\ufffe' # 0xFF -> UNDEFINED
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1254 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1254',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
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'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
u'\ufffe' # 0x9D -> UNDEFINED
u'\ufffe' # 0x9E -> UNDEFINED
u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
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'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
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'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
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'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\u011e' # 0xD0 -> LATIN CAPITAL LETTER G WITH BREVE
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\u0130' # 0xDD -> LATIN CAPITAL LETTER I WITH DOT ABOVE
u'\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
u'\u011f' # 0xF0 -> LATIN SMALL LETTER G WITH BREVE
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf7' # 0xF7 -> DIVISION SIGN
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
u'\u0131' # 0xFD -> LATIN SMALL LETTER DOTLESS I
u'\u015f' # 0xFE -> LATIN SMALL LETTER S WITH CEDILLA
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1255 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1255',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1256 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1256',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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'\u067e' # 0x81 -> ARABIC LETTER PEH
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'\u0679' # 0x8A -> ARABIC LETTER TTEH
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
u'\u0686' # 0x8D -> ARABIC LETTER TCHEH
u'\u0698' # 0x8E -> ARABIC LETTER JEH
u'\u0688' # 0x8F -> ARABIC LETTER DDAL
u'\u06af' # 0x90 -> ARABIC LETTER GAF
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'\u06a9' # 0x98 -> ARABIC LETTER KEHEH
u'\u2122' # 0x99 -> TRADE MARK SIGN
u'\u0691' # 0x9A -> ARABIC LETTER RREH
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
u'\u200c' # 0x9D -> ZERO WIDTH NON-JOINER
u'\u200d' # 0x9E -> ZERO WIDTH JOINER
u'\u06ba' # 0x9F -> ARABIC LETTER NOON GHUNNA
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\u060c' # 0xA1 -> ARABIC COMMA
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'\u06be' # 0xAA -> ARABIC LETTER HEH DOACHASHMEE
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'\u061b' # 0xBA -> ARABIC SEMICOLON
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'\u061f' # 0xBF -> ARABIC QUESTION MARK
u'\u06c1' # 0xC0 -> ARABIC LETTER HEH GOAL
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'\xd7' # 0xD7 -> MULTIPLICATION SIGN
u'\u0637' # 0xD8 -> ARABIC LETTER TAH
u'\u0638' # 0xD9 -> ARABIC LETTER ZAH
u'\u0639' # 0xDA -> ARABIC LETTER AIN
u'\u063a' # 0xDB -> ARABIC LETTER GHAIN
u'\u0640' # 0xDC -> ARABIC TATWEEL
u'\u0641' # 0xDD -> ARABIC LETTER FEH
u'\u0642' # 0xDE -> ARABIC LETTER QAF
u'\u0643' # 0xDF -> ARABIC LETTER KAF
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
u'\u0644' # 0xE1 -> ARABIC LETTER LAM
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\u0645' # 0xE3 -> ARABIC LETTER MEEM
u'\u0646' # 0xE4 -> ARABIC LETTER NOON
u'\u0647' # 0xE5 -> ARABIC LETTER HEH
u'\u0648' # 0xE6 -> ARABIC LETTER WAW
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
u'\u0649' # 0xEC -> ARABIC LETTER ALEF MAKSURA
u'\u064a' # 0xED -> ARABIC LETTER YEH
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
u'\u064b' # 0xF0 -> ARABIC FATHATAN
u'\u064c' # 0xF1 -> ARABIC DAMMATAN
u'\u064d' # 0xF2 -> ARABIC KASRATAN
u'\u064e' # 0xF3 -> ARABIC FATHA
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\u064f' # 0xF5 -> ARABIC DAMMA
u'\u0650' # 0xF6 -> ARABIC KASRA
u'\xf7' # 0xF7 -> DIVISION SIGN
u'\u0651' # 0xF8 -> ARABIC SHADDA
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
u'\u0652' # 0xFA -> ARABIC SUKUN
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK
u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK
u'\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1257 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1257',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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'\ufffe' # 0x83 -> UNDEFINED
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
u'\u2020' # 0x86 -> DAGGER
u'\u2021' # 0x87 -> DOUBLE DAGGER
u'\ufffe' # 0x88 -> UNDEFINED
u'\u2030' # 0x89 -> PER MILLE SIGN
u'\ufffe' # 0x8A -> UNDEFINED
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
u'\ufffe' # 0x8C -> UNDEFINED
u'\xa8' # 0x8D -> DIAERESIS
u'\u02c7' # 0x8E -> CARON
u'\xb8' # 0x8F -> CEDILLA
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'\u2122' # 0x99 -> TRADE MARK SIGN
u'\ufffe' # 0x9A -> UNDEFINED
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
u'\ufffe' # 0x9C -> UNDEFINED
u'\xaf' # 0x9D -> MACRON
u'\u02db' # 0x9E -> OGONEK
u'\ufffe' # 0x9F -> UNDEFINED
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\ufffe' # 0xA1 -> UNDEFINED
u'\xa2' # 0xA2 -> CENT SIGN
u'\xa3' # 0xA3 -> POUND SIGN
u'\xa4' # 0xA4 -> CURRENCY SIGN
u'\ufffe' # 0xA5 -> UNDEFINED
u'\xa6' # 0xA6 -> BROKEN BAR
u'\xa7' # 0xA7 -> SECTION SIGN
u'\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
u'\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA
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'\xc6' # 0xAF -> LATIN CAPITAL LETTER AE
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'\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
u'\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA
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'\xe6' # 0xBF -> LATIN SMALL LETTER AE
u'\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK
u'\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK
u'\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON
u'\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK
u'\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON
u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE
u'\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE
u'\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA
u'\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA
u'\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON
u'\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA
u'\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON
u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE
u'\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
u'\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
u'\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK
u'\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE
u'\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE
u'\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
u'\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
u'\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK
u'\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK
u'\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON
u'\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
u'\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK
u'\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON
u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
u'\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE
u'\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE
u'\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA
u'\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA
u'\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON
u'\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA
u'\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON
u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE
u'\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
u'\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf7' # 0xF7 -> DIVISION SIGN
u'\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK
u'\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE
u'\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE
u'\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
u'\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE
u'\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON
u'\u02d9' # 0xFF -> DOT ABOVE
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp1258 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp1258',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
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'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
u'\ufffe' # 0x9D -> UNDEFINED
u'\ufffe' # 0x9E -> UNDEFINED
u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
u'\xa0' # 0xA0 -> NO-BREAK SPACE
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
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'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
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'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
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'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\u0300' # 0xCC -> COMBINING GRAVE ACCENT
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
u'\u0309' # 0xD2 -> COMBINING HOOK ABOVE
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'\u01a0' # 0xD5 -> LATIN CAPITAL LETTER O WITH HORN
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\u01af' # 0xDD -> LATIN CAPITAL LETTER U WITH HORN
u'\u0303' # 0xDE -> COMBINING TILDE
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
u'\u0301' # 0xEC -> COMBINING ACUTE ACCENT
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
u'\u0323' # 0xF2 -> COMBINING DOT BELOW
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\u01a1' # 0xF5 -> LATIN SMALL LETTER O WITH HORN
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf7' # 0xF7 -> DIVISION SIGN
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
u'\u01b0' # 0xFD -> LATIN SMALL LETTER U WITH HORN
u'\u20ab' # 0xFE -> DONG SIGN
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp424 generated from 'MAPPINGS/VENDORS/MISC/CP424.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp424',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp500 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp500',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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 -> CONTROL
u'\t' # 0x05 -> HORIZONTAL TABULATION
u'\x86' # 0x06 -> CONTROL
u'\x7f' # 0x07 -> DELETE
u'\x97' # 0x08 -> CONTROL
u'\x8d' # 0x09 -> CONTROL
u'\x8e' # 0x0A -> CONTROL
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 -> CONTROL
u'\x85' # 0x15 -> CONTROL
u'\x08' # 0x16 -> BACKSPACE
u'\x87' # 0x17 -> CONTROL
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x92' # 0x1A -> CONTROL
u'\x8f' # 0x1B -> CONTROL
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u'\x80' # 0x20 -> CONTROL
u'\x81' # 0x21 -> CONTROL
u'\x82' # 0x22 -> CONTROL
u'\x83' # 0x23 -> CONTROL
u'\x84' # 0x24 -> CONTROL
u'\n' # 0x25 -> LINE FEED
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x27 -> ESCAPE
u'\x88' # 0x28 -> CONTROL
u'\x89' # 0x29 -> CONTROL
u'\x8a' # 0x2A -> CONTROL
u'\x8b' # 0x2B -> CONTROL
u'\x8c' # 0x2C -> CONTROL
u'\x05' # 0x2D -> ENQUIRY
u'\x06' # 0x2E -> ACKNOWLEDGE
u'\x07' # 0x2F -> BELL
u'\x90' # 0x30 -> CONTROL
u'\x91' # 0x31 -> CONTROL
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
u'\x93' # 0x33 -> CONTROL
u'\x94' # 0x34 -> CONTROL
u'\x95' # 0x35 -> CONTROL
u'\x96' # 0x36 -> CONTROL
u'\x04' # 0x37 -> END OF TRANSMISSION
u'\x98' # 0x38 -> CONTROL
u'\x99' # 0x39 -> CONTROL
u'\x9a' # 0x3A -> CONTROL
u'\x9b' # 0x3B -> CONTROL
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x3E -> CONTROL
u'\x1a' # 0x3F -> SUBSTITUTE
u' ' # 0x40 -> SPACE
u'\xa0' # 0x41 -> NO-BREAK SPACE
u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
u'[' # 0x4A -> LEFT SQUARE BRACKET
u'.' # 0x4B -> FULL STOP
u'<' # 0x4C -> LESS-THAN SIGN
u'(' # 0x4D -> LEFT PARENTHESIS
u'+' # 0x4E -> PLUS SIGN
u'!' # 0x4F -> EXCLAMATION MARK
u'&' # 0x50 -> AMPERSAND
u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
u']' # 0x5A -> RIGHT SQUARE BRACKET
u'$' # 0x5B -> DOLLAR SIGN
u'*' # 0x5C -> ASTERISK
u')' # 0x5D -> RIGHT PARENTHESIS
u';' # 0x5E -> SEMICOLON
u'^' # 0x5F -> CIRCUMFLEX ACCENT
u'-' # 0x60 -> HYPHEN-MINUS
u'/' # 0x61 -> SOLIDUS
u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
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'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
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'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
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'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC)
u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC)
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'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
u'\xb8' # 0x9D -> CEDILLA
u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
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'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
u'\xbf' # 0xAB -> INVERTED QUESTION MARK
u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC)
u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC)
u'\xae' # 0xAF -> REGISTERED SIGN
u'\xa2' # 0xB0 -> CENT SIGN
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'\xac' # 0xBA -> NOT SIGN
u'|' # 0xBB -> VERTICAL LINE
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'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
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'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
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'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
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'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
u'\x9f' # 0xFF -> CONTROL
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -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 = (
u'\x00' # 0x00 -> CONTROL CHARACTER
u'\x01' # 0x01 -> CONTROL CHARACTER
u'\x02' # 0x02 -> CONTROL CHARACTER
u'\x03' # 0x03 -> CONTROL CHARACTER
u'\x04' # 0x04 -> CONTROL CHARACTER
u'\x05' # 0x05 -> CONTROL CHARACTER
u'\x06' # 0x06 -> CONTROL CHARACTER
u'\x07' # 0x07 -> CONTROL CHARACTER
u'\x08' # 0x08 -> CONTROL CHARACTER
u'\t' # 0x09 -> CONTROL CHARACTER
u'\n' # 0x0A -> CONTROL CHARACTER
u'\x0b' # 0x0B -> CONTROL CHARACTER
u'\x0c' # 0x0C -> CONTROL CHARACTER
u'\r' # 0x0D -> CONTROL CHARACTER
u'\x0e' # 0x0E -> CONTROL CHARACTER
u'\x0f' # 0x0F -> CONTROL CHARACTER
u'\x10' # 0x10 -> CONTROL CHARACTER
u'\x11' # 0x11 -> CONTROL CHARACTER
u'\x12' # 0x12 -> CONTROL CHARACTER
u'\x13' # 0x13 -> CONTROL CHARACTER
u'\x14' # 0x14 -> CONTROL CHARACTER
u'\x15' # 0x15 -> CONTROL CHARACTER
u'\x16' # 0x16 -> CONTROL CHARACTER
u'\x17' # 0x17 -> CONTROL CHARACTER
u'\x18' # 0x18 -> CONTROL CHARACTER
u'\x19' # 0x19 -> CONTROL CHARACTER
u'\x1a' # 0x1A -> CONTROL CHARACTER
u'\x1b' # 0x1B -> CONTROL CHARACTER
u'\x1c' # 0x1C -> CONTROL CHARACTER
u'\x1d' # 0x1D -> CONTROL CHARACTER
u'\x1e' # 0x1E -> CONTROL CHARACTER
u'\x1f' # 0x1F -> CONTROL CHARACTER
u' ' # 0x20 -> SPACE
u'!' # 0x21 -> EXCLAMATION MARK
u'"' # 0x22 -> QUOTATION MARK
u'#' # 0x23 -> NUMBER SIGN
u'$' # 0x24 -> DOLLAR SIGN
u'%' # 0x25 -> PERCENT SIGN
u'&' # 0x26 -> AMPERSAND
u"'" # 0x27 -> APOSTROPHE
u'(' # 0x28 -> LEFT PARENTHESIS
u')' # 0x29 -> RIGHT PARENTHESIS
u'*' # 0x2A -> ASTERISK
u'+' # 0x2B -> PLUS SIGN
u',' # 0x2C -> COMMA
u'-' # 0x2D -> HYPHEN-MINUS
u'.' # 0x2E -> FULL STOP
u'/' # 0x2F -> SOLIDUS
u'0' # 0x30 -> DIGIT ZERO
u'1' # 0x31 -> DIGIT ONE
u'2' # 0x32 -> DIGIT TWO
u'3' # 0x33 -> DIGIT THREE
u'4' # 0x34 -> DIGIT FOUR
u'5' # 0x35 -> DIGIT FIVE
u'6' # 0x36 -> DIGIT SIX
u'7' # 0x37 -> DIGIT SEVEN
u'8' # 0x38 -> DIGIT EIGHT
u'9' # 0x39 -> DIGIT NINE
u':' # 0x3A -> COLON
u';' # 0x3B -> SEMICOLON
u'<' # 0x3C -> LESS-THAN SIGN
u'=' # 0x3D -> EQUALS SIGN
u'>' # 0x3E -> GREATER-THAN SIGN
u'?' # 0x3F -> QUESTION MARK
u'@' # 0x40 -> COMMERCIAL AT
u'A' # 0x41 -> LATIN CAPITAL LETTER A
u'B' # 0x42 -> LATIN CAPITAL LETTER B
u'C' # 0x43 -> LATIN CAPITAL LETTER C
u'D' # 0x44 -> LATIN CAPITAL LETTER D
u'E' # 0x45 -> LATIN CAPITAL LETTER E
u'F' # 0x46 -> LATIN CAPITAL LETTER F
u'G' # 0x47 -> LATIN CAPITAL LETTER G
u'H' # 0x48 -> LATIN CAPITAL LETTER H
u'I' # 0x49 -> LATIN CAPITAL LETTER I
u'J' # 0x4A -> LATIN CAPITAL LETTER J
u'K' # 0x4B -> LATIN CAPITAL LETTER K
u'L' # 0x4C -> LATIN CAPITAL LETTER L
u'M' # 0x4D -> LATIN CAPITAL LETTER M
u'N' # 0x4E -> LATIN CAPITAL LETTER N
u'O' # 0x4F -> LATIN CAPITAL LETTER O
u'P' # 0x50 -> LATIN CAPITAL LETTER P
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
u'R' # 0x52 -> LATIN CAPITAL LETTER R
u'S' # 0x53 -> LATIN CAPITAL LETTER S
u'T' # 0x54 -> LATIN CAPITAL LETTER T
u'U' # 0x55 -> LATIN CAPITAL LETTER U
u'V' # 0x56 -> LATIN CAPITAL LETTER V
u'W' # 0x57 -> LATIN CAPITAL LETTER W
u'X' # 0x58 -> LATIN CAPITAL LETTER X
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
u'[' # 0x5B -> LEFT SQUARE BRACKET
u'\\' # 0x5C -> REVERSE SOLIDUS
u']' # 0x5D -> RIGHT SQUARE BRACKET
u'^' # 0x5E -> CIRCUMFLEX ACCENT
u'_' # 0x5F -> LOW LINE
u'`' # 0x60 -> GRAVE ACCENT
u'a' # 0x61 -> LATIN SMALL LETTER A
u'b' # 0x62 -> LATIN SMALL LETTER B
u'c' # 0x63 -> LATIN SMALL LETTER C
u'd' # 0x64 -> LATIN SMALL LETTER D
u'e' # 0x65 -> LATIN SMALL LETTER E
u'f' # 0x66 -> LATIN SMALL LETTER F
u'g' # 0x67 -> LATIN SMALL LETTER G
u'h' # 0x68 -> LATIN SMALL LETTER H
u'i' # 0x69 -> LATIN SMALL LETTER I
u'j' # 0x6A -> LATIN SMALL LETTER J
u'k' # 0x6B -> LATIN SMALL LETTER K
u'l' # 0x6C -> LATIN SMALL LETTER L
u'm' # 0x6D -> LATIN SMALL LETTER M
u'n' # 0x6E -> LATIN SMALL LETTER N
u'o' # 0x6F -> LATIN SMALL LETTER O
u'p' # 0x70 -> LATIN SMALL LETTER P
u'q' # 0x71 -> LATIN SMALL LETTER Q
u'r' # 0x72 -> LATIN SMALL LETTER R
u's' # 0x73 -> LATIN SMALL LETTER S
u't' # 0x74 -> LATIN SMALL LETTER T
u'u' # 0x75 -> LATIN SMALL LETTER U
u'v' # 0x76 -> LATIN SMALL LETTER V
u'w' # 0x77 -> LATIN SMALL LETTER W
u'x' # 0x78 -> LATIN SMALL LETTER X
u'y' # 0x79 -> LATIN SMALL LETTER Y
u'z' # 0x7A -> LATIN SMALL LETTER Z
u'{' # 0x7B -> LEFT CURLY BRACKET
u'|' # 0x7C -> VERTICAL LINE
u'}' # 0x7D -> RIGHT CURLY BRACKET
u'~' # 0x7E -> TILDE
u'\x7f' # 0x7F -> CONTROL CHARACTER
u'\x80'
u'\x81'
u'\xe9' # 0x82 -> LATIN SMALL LETTER E WITH ACUTE
u'\xe2' # 0x83 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
u'\x84'
u'\xe0' # 0x85 -> LATIN SMALL LETTER A WITH GRAVE
u'\x86'
u'\xe7' # 0x87 -> LATIN SMALL LETTER C WITH CEDILLA
u'\xea' # 0x88 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
u'\xeb' # 0x89 -> LATIN SMALL LETTER E WITH DIAERESIS
u'\xe8' # 0x8A -> LATIN SMALL LETTER E WITH GRAVE
u'\xef' # 0x8B -> LATIN SMALL LETTER I WITH DIAERESIS
u'\xee' # 0x8C -> LATIN SMALL LETTER I WITH CIRCUMFLEX
u'\x8d'
u'\x8e'
u'\x8f'
u'\x90'
u'\u0651' # 0x91 -> ARABIC SHADDA
u'\u0652' # 0x92 -> ARABIC SUKUN
u'\xf4' # 0x93 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
u'\xa4' # 0x94 -> CURRENCY SIGN
u'\u0640' # 0x95 -> ARABIC TATWEEL
u'\xfb' # 0x96 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
u'\xf9' # 0x97 -> LATIN SMALL LETTER U WITH GRAVE
u'\u0621' # 0x98 -> ARABIC LETTER HAMZA
u'\u0622' # 0x99 -> ARABIC LETTER ALEF WITH MADDA ABOVE
u'\u0623' # 0x9A -> ARABIC LETTER ALEF WITH HAMZA ABOVE
u'\u0624' # 0x9B -> ARABIC LETTER WAW WITH HAMZA ABOVE
u'\xa3' # 0x9C -> POUND SIGN
u'\u0625' # 0x9D -> ARABIC LETTER ALEF WITH HAMZA BELOW
u'\u0626' # 0x9E -> ARABIC LETTER YEH WITH HAMZA ABOVE
u'\u0627' # 0x9F -> ARABIC LETTER ALEF
u'\u0628' # 0xA0 -> ARABIC LETTER BEH
u'\u0629' # 0xA1 -> ARABIC LETTER TEH MARBUTA
u'\u062a' # 0xA2 -> ARABIC LETTER TEH
u'\u062b' # 0xA3 -> ARABIC LETTER THEH
u'\u062c' # 0xA4 -> ARABIC LETTER JEEM
u'\u062d' # 0xA5 -> ARABIC LETTER HAH
u'\u062e' # 0xA6 -> ARABIC LETTER KHAH
u'\u062f' # 0xA7 -> ARABIC LETTER DAL
u'\u0630' # 0xA8 -> ARABIC LETTER THAL
u'\u0631' # 0xA9 -> ARABIC LETTER REH
u'\u0632' # 0xAA -> ARABIC LETTER ZAIN
u'\u0633' # 0xAB -> ARABIC LETTER SEEN
u'\u0634' # 0xAC -> ARABIC LETTER SHEEN
u'\u0635' # 0xAD -> ARABIC LETTER SAD
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'\u2561' # 0xB5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
u'\u2562' # 0xB6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
u'\u2556' # 0xB7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
u'\u2555' # 0xB8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
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'\u255c' # 0xBD -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
u'\u255b' # 0xBE -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
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'\u255e' # 0xC6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
u'\u255f' # 0xC7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
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'\u2567' # 0xCF -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
u'\u2568' # 0xD0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
u'\u2564' # 0xD1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
u'\u2565' # 0xD2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
u'\u2559' # 0xD3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
u'\u2558' # 0xD4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
u'\u2552' # 0xD5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
u'\u2553' # 0xD6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
u'\u256b' # 0xD7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
u'\u256a' # 0xD8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
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'\u258c' # 0xDD -> LEFT HALF BLOCK
u'\u2590' # 0xDE -> RIGHT HALF BLOCK
u'\u2580' # 0xDF -> UPPER HALF BLOCK
u'\u0636' # 0xE0 -> ARABIC LETTER DAD
u'\u0637' # 0xE1 -> ARABIC LETTER TAH
u'\u0638' # 0xE2 -> ARABIC LETTER ZAH
u'\u0639' # 0xE3 -> ARABIC LETTER AIN
u'\u063a' # 0xE4 -> ARABIC LETTER GHAIN
u'\u0641' # 0xE5 -> ARABIC LETTER FEH
u'\xb5' # 0xE6 -> MICRO SIGN
u'\u0642' # 0xE7 -> ARABIC LETTER QAF
u'\u0643' # 0xE8 -> ARABIC LETTER KAF
u'\u0644' # 0xE9 -> ARABIC LETTER LAM
u'\u0645' # 0xEA -> ARABIC LETTER MEEM
u'\u0646' # 0xEB -> ARABIC LETTER NOON
u'\u0647' # 0xEC -> ARABIC LETTER HEH
u'\u0648' # 0xED -> ARABIC LETTER WAW
u'\u0649' # 0xEE -> ARABIC LETTER ALEF MAKSURA
u'\u064a' # 0xEF -> ARABIC LETTER YEH
u'\u2261' # 0xF0 -> IDENTICAL TO
u'\u064b' # 0xF1 -> ARABIC FATHATAN
u'\u064c' # 0xF2 -> ARABIC DAMMATAN
u'\u064d' # 0xF3 -> ARABIC KASRATAN
u'\u064e' # 0xF4 -> ARABIC FATHA
u'\u064f' # 0xF5 -> ARABIC DAMMA
u'\u0650' # 0xF6 -> ARABIC KASRA
u'\u2248' # 0xF7 -> ALMOST EQUAL TO
u'\xb0' # 0xF8 -> DEGREE SIGN
u'\u2219' # 0xF9 -> BULLET OPERATOR
u'\xb7' # 0xFA -> MIDDLE DOT
u'\u221a' # 0xFB -> SQUARE ROOT
u'\u207f' # 0xFC -> SUPERSCRIPT LATIN SMALL LETTER N
u'\xb2' # 0xFD -> SUPERSCRIPT TWO
u'\u25a0' # 0xFE -> BLACK SQUARE
u'\xa0' # 0xFF -> NO-BREAK SPACE
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

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

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp856 generated from 'MAPPINGS/VENDORS/MISC/CP856.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp856',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

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

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp874 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp874',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,307 @@
""" Python Character Mapping Codec cp875 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT' with gencodec.py.
"""#"
import codecs
### Codec APIs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_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='cp875',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
### 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 -> CONTROL
u'\t' # 0x05 -> HORIZONTAL TABULATION
u'\x86' # 0x06 -> CONTROL
u'\x7f' # 0x07 -> DELETE
u'\x97' # 0x08 -> CONTROL
u'\x8d' # 0x09 -> CONTROL
u'\x8e' # 0x0A -> CONTROL
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 -> CONTROL
u'\x85' # 0x15 -> CONTROL
u'\x08' # 0x16 -> BACKSPACE
u'\x87' # 0x17 -> CONTROL
u'\x18' # 0x18 -> CANCEL
u'\x19' # 0x19 -> END OF MEDIUM
u'\x92' # 0x1A -> CONTROL
u'\x8f' # 0x1B -> CONTROL
u'\x1c' # 0x1C -> FILE SEPARATOR
u'\x1d' # 0x1D -> GROUP SEPARATOR
u'\x1e' # 0x1E -> RECORD SEPARATOR
u'\x1f' # 0x1F -> UNIT SEPARATOR
u'\x80' # 0x20 -> CONTROL
u'\x81' # 0x21 -> CONTROL
u'\x82' # 0x22 -> CONTROL
u'\x83' # 0x23 -> CONTROL
u'\x84' # 0x24 -> CONTROL
u'\n' # 0x25 -> LINE FEED
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
u'\x1b' # 0x27 -> ESCAPE
u'\x88' # 0x28 -> CONTROL
u'\x89' # 0x29 -> CONTROL
u'\x8a' # 0x2A -> CONTROL
u'\x8b' # 0x2B -> CONTROL
u'\x8c' # 0x2C -> CONTROL
u'\x05' # 0x2D -> ENQUIRY
u'\x06' # 0x2E -> ACKNOWLEDGE
u'\x07' # 0x2F -> BELL
u'\x90' # 0x30 -> CONTROL
u'\x91' # 0x31 -> CONTROL
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
u'\x93' # 0x33 -> CONTROL
u'\x94' # 0x34 -> CONTROL
u'\x95' # 0x35 -> CONTROL
u'\x96' # 0x36 -> CONTROL
u'\x04' # 0x37 -> END OF TRANSMISSION
u'\x98' # 0x38 -> CONTROL
u'\x99' # 0x39 -> CONTROL
u'\x9a' # 0x3A -> CONTROL
u'\x9b' # 0x3B -> CONTROL
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
u'\x9e' # 0x3E -> CONTROL
u'\x1a' # 0x3F -> SUBSTITUTE
u' ' # 0x40 -> SPACE
u'\u0391' # 0x41 -> GREEK CAPITAL LETTER ALPHA
u'\u0392' # 0x42 -> GREEK CAPITAL LETTER BETA
u'\u0393' # 0x43 -> GREEK CAPITAL LETTER GAMMA
u'\u0394' # 0x44 -> GREEK CAPITAL LETTER DELTA
u'\u0395' # 0x45 -> GREEK CAPITAL LETTER EPSILON
u'\u0396' # 0x46 -> GREEK CAPITAL LETTER ZETA
u'\u0397' # 0x47 -> GREEK CAPITAL LETTER ETA
u'\u0398' # 0x48 -> GREEK CAPITAL LETTER THETA
u'\u0399' # 0x49 -> GREEK CAPITAL LETTER IOTA
u'[' # 0x4A -> LEFT SQUARE BRACKET
u'.' # 0x4B -> FULL STOP
u'<' # 0x4C -> LESS-THAN SIGN
u'(' # 0x4D -> LEFT PARENTHESIS
u'+' # 0x4E -> PLUS SIGN
u'!' # 0x4F -> EXCLAMATION MARK
u'&' # 0x50 -> AMPERSAND
u'\u039a' # 0x51 -> GREEK CAPITAL LETTER KAPPA
u'\u039b' # 0x52 -> GREEK CAPITAL LETTER LAMDA
u'\u039c' # 0x53 -> GREEK CAPITAL LETTER MU
u'\u039d' # 0x54 -> GREEK CAPITAL LETTER NU
u'\u039e' # 0x55 -> GREEK CAPITAL LETTER XI
u'\u039f' # 0x56 -> GREEK CAPITAL LETTER OMICRON
u'\u03a0' # 0x57 -> GREEK CAPITAL LETTER PI
u'\u03a1' # 0x58 -> GREEK CAPITAL LETTER RHO
u'\u03a3' # 0x59 -> GREEK CAPITAL LETTER SIGMA
u']' # 0x5A -> RIGHT SQUARE BRACKET
u'$' # 0x5B -> DOLLAR SIGN
u'*' # 0x5C -> ASTERISK
u')' # 0x5D -> RIGHT PARENTHESIS
u';' # 0x5E -> SEMICOLON
u'^' # 0x5F -> CIRCUMFLEX ACCENT
u'-' # 0x60 -> HYPHEN-MINUS
u'/' # 0x61 -> SOLIDUS
u'\u03a4' # 0x62 -> GREEK CAPITAL LETTER TAU
u'\u03a5' # 0x63 -> GREEK CAPITAL LETTER UPSILON
u'\u03a6' # 0x64 -> GREEK CAPITAL LETTER PHI
u'\u03a7' # 0x65 -> GREEK CAPITAL LETTER CHI
u'\u03a8' # 0x66 -> GREEK CAPITAL LETTER PSI
u'\u03a9' # 0x67 -> GREEK CAPITAL LETTER OMEGA
u'\u03aa' # 0x68 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
u'\u03ab' # 0x69 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
u'|' # 0x6A -> VERTICAL LINE
u',' # 0x6B -> COMMA
u'%' # 0x6C -> PERCENT SIGN
u'_' # 0x6D -> LOW LINE
u'>' # 0x6E -> GREATER-THAN SIGN
u'?' # 0x6F -> QUESTION MARK
u'\xa8' # 0x70 -> DIAERESIS
u'\u0386' # 0x71 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
u'\u0388' # 0x72 -> GREEK CAPITAL LETTER EPSILON WITH TONOS
u'\u0389' # 0x73 -> GREEK CAPITAL LETTER ETA WITH TONOS
u'\xa0' # 0x74 -> NO-BREAK SPACE
u'\u038a' # 0x75 -> GREEK CAPITAL LETTER IOTA WITH TONOS
u'\u038c' # 0x76 -> GREEK CAPITAL LETTER OMICRON WITH TONOS
u'\u038e' # 0x77 -> GREEK CAPITAL LETTER UPSILON WITH TONOS
u'\u038f' # 0x78 -> GREEK CAPITAL LETTER OMEGA WITH TONOS
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'\u0385' # 0x80 -> GREEK DIALYTIKA TONOS
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'\u03b1' # 0x8A -> GREEK SMALL LETTER ALPHA
u'\u03b2' # 0x8B -> GREEK SMALL LETTER BETA
u'\u03b3' # 0x8C -> GREEK SMALL LETTER GAMMA
u'\u03b4' # 0x8D -> GREEK SMALL LETTER DELTA
u'\u03b5' # 0x8E -> GREEK SMALL LETTER EPSILON
u'\u03b6' # 0x8F -> GREEK SMALL LETTER ZETA
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'\u03b7' # 0x9A -> GREEK SMALL LETTER ETA
u'\u03b8' # 0x9B -> GREEK SMALL LETTER THETA
u'\u03b9' # 0x9C -> GREEK SMALL LETTER IOTA
u'\u03ba' # 0x9D -> GREEK SMALL LETTER KAPPA
u'\u03bb' # 0x9E -> GREEK SMALL LETTER LAMDA
u'\u03bc' # 0x9F -> GREEK SMALL LETTER MU
u'\xb4' # 0xA0 -> ACUTE ACCENT
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'\u03bd' # 0xAA -> GREEK SMALL LETTER NU
u'\u03be' # 0xAB -> GREEK SMALL LETTER XI
u'\u03bf' # 0xAC -> GREEK SMALL LETTER OMICRON
u'\u03c0' # 0xAD -> GREEK SMALL LETTER PI
u'\u03c1' # 0xAE -> GREEK SMALL LETTER RHO
u'\u03c3' # 0xAF -> GREEK SMALL LETTER SIGMA
u'\xa3' # 0xB0 -> POUND SIGN
u'\u03ac' # 0xB1 -> GREEK SMALL LETTER ALPHA WITH TONOS
u'\u03ad' # 0xB2 -> GREEK SMALL LETTER EPSILON WITH TONOS
u'\u03ae' # 0xB3 -> GREEK SMALL LETTER ETA WITH TONOS
u'\u03ca' # 0xB4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
u'\u03af' # 0xB5 -> GREEK SMALL LETTER IOTA WITH TONOS
u'\u03cc' # 0xB6 -> GREEK SMALL LETTER OMICRON WITH TONOS
u'\u03cd' # 0xB7 -> GREEK SMALL LETTER UPSILON WITH TONOS
u'\u03cb' # 0xB8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
u'\u03ce' # 0xB9 -> GREEK SMALL LETTER OMEGA WITH TONOS
u'\u03c2' # 0xBA -> GREEK SMALL LETTER FINAL SIGMA
u'\u03c4' # 0xBB -> GREEK SMALL LETTER TAU
u'\u03c5' # 0xBC -> GREEK SMALL LETTER UPSILON
u'\u03c6' # 0xBD -> GREEK SMALL LETTER PHI
u'\u03c7' # 0xBE -> GREEK SMALL LETTER CHI
u'\u03c8' # 0xBF -> GREEK SMALL LETTER PSI
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'\u03c9' # 0xCB -> GREEK SMALL LETTER OMEGA
u'\u0390' # 0xCC -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
u'\u03b0' # 0xCD -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
u'\u2018' # 0xCE -> LEFT SINGLE QUOTATION MARK
u'\u2015' # 0xCF -> HORIZONTAL BAR
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'\xb1' # 0xDA -> PLUS-MINUS SIGN
u'\xbd' # 0xDB -> VULGAR FRACTION ONE HALF
u'\x1a' # 0xDC -> SUBSTITUTE
u'\u0387' # 0xDD -> GREEK ANO TELEIA
u'\u2019' # 0xDE -> RIGHT SINGLE QUOTATION MARK
u'\xa6' # 0xDF -> BROKEN BAR
u'\\' # 0xE0 -> REVERSE SOLIDUS
u'\x1a' # 0xE1 -> SUBSTITUTE
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'\xa7' # 0xEB -> SECTION SIGN
u'\x1a' # 0xEC -> SUBSTITUTE
u'\x1a' # 0xED -> SUBSTITUTE
u'\xab' # 0xEE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\xac' # 0xEF -> NOT SIGN
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'\xa9' # 0xFB -> COPYRIGHT SIGN
u'\x1a' # 0xFC -> SUBSTITUTE
u'\x1a' # 0xFD -> SUBSTITUTE
u'\xbb' # 0xFE -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
u'\x9f' # 0xFF -> CONTROL
)
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)

View File

@@ -0,0 +1,39 @@
#
# cp932.py: Python Unicode Codec for CP932
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_jp, codecs
import _multibytecodec as mbc
codec = _codecs_jp.getcodec('cp932')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='cp932',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)

View File

@@ -0,0 +1,39 @@
#
# cp949.py: Python Unicode Codec for CP949
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_kr, codecs
import _multibytecodec as mbc
codec = _codecs_kr.getcodec('cp949')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='cp949',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)

View File

@@ -0,0 +1,39 @@
#
# cp950.py: Python Unicode Codec for CP950
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_tw, codecs
import _multibytecodec as mbc
codec = _codecs_tw.getcodec('cp950')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='cp950',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)

View File

@@ -0,0 +1,39 @@
#
# euc_jis_2004.py: Python Unicode Codec for EUC_JIS_2004
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_jp, codecs
import _multibytecodec as mbc
codec = _codecs_jp.getcodec('euc_jis_2004')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='euc_jis_2004',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)

View File

@@ -0,0 +1,39 @@
#
# euc_jisx0213.py: Python Unicode Codec for EUC_JISX0213
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_jp, codecs
import _multibytecodec as mbc
codec = _codecs_jp.getcodec('euc_jisx0213')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='euc_jisx0213',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)

View File

@@ -0,0 +1,39 @@
#
# euc_jp.py: Python Unicode Codec for EUC_JP
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_jp, codecs
import _multibytecodec as mbc
codec = _codecs_jp.getcodec('euc_jp')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='euc_jp',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)

View File

@@ -0,0 +1,39 @@
#
# euc_kr.py: Python Unicode Codec for EUC_KR
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_kr, codecs
import _multibytecodec as mbc
codec = _codecs_kr.getcodec('euc_kr')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='euc_kr',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)

Some files were not shown because too many files have changed in this diff Show More