mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-05-23 13:52:28 +00:00
python-3.6.zip added from Github
README.cosmo contains the necessary links.
This commit is contained in:
ahgamut
Justine Tunney
parent
75fc601ff5
commit
0c4c56ff39
4219 changed files with 1968626 additions and 0 deletions
53
third_party/python/Tools/unicode/comparecodecs.py
vendored
Executable file
53
third_party/python/Tools/unicode/comparecodecs.py
vendored
Executable file
|
|
@ -0,0 +1,53 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
""" Compare the output of two codecs.
|
||||
|
||||
(c) Copyright 2005, Marc-Andre Lemburg (mal@lemburg.com).
|
||||
|
||||
Licensed to PSF under a Contributor Agreement.
|
||||
|
||||
"""
|
||||
import sys
|
||||
|
||||
def compare_codecs(encoding1, encoding2):
|
||||
|
||||
print('Comparing encoding/decoding of %r and %r' % (encoding1, encoding2))
|
||||
mismatch = 0
|
||||
# Check encoding
|
||||
for i in range(sys.maxunicode+1):
|
||||
u = chr(i)
|
||||
try:
|
||||
c1 = u.encode(encoding1)
|
||||
except UnicodeError as reason:
|
||||
c1 = '<undefined>'
|
||||
try:
|
||||
c2 = u.encode(encoding2)
|
||||
except UnicodeError as reason:
|
||||
c2 = '<undefined>'
|
||||
if c1 != c2:
|
||||
print(' * encoding mismatch for 0x%04X: %-14r != %r' % \
|
||||
(i, c1, c2))
|
||||
mismatch += 1
|
||||
# Check decoding
|
||||
for i in range(256):
|
||||
c = bytes([i])
|
||||
try:
|
||||
u1 = c.decode(encoding1)
|
||||
except UnicodeError:
|
||||
u1 = '<undefined>'
|
||||
try:
|
||||
u2 = c.decode(encoding2)
|
||||
except UnicodeError:
|
||||
u2 = '<undefined>'
|
||||
if u1 != u2:
|
||||
print(' * decoding mismatch for 0x%04X: %-14r != %r' % \
|
||||
(i, u1, u2))
|
||||
mismatch += 1
|
||||
if mismatch:
|
||||
print()
|
||||
print('Found %i mismatches' % mismatch)
|
||||
else:
|
||||
print('-> Codecs are identical.')
|
||||
|
||||
if __name__ == '__main__':
|
||||
compare_codecs(sys.argv[1], sys.argv[2])
|
||||
68
third_party/python/Tools/unicode/gencjkcodecs.py
vendored
Normal file
68
third_party/python/Tools/unicode/gencjkcodecs.py
vendored
Normal file
|
|
@ -0,0 +1,68 @@
|
|||
import os, string
|
||||
|
||||
codecs = {
|
||||
'cn': ('gb2312', 'gbk', 'gb18030', 'hz'),
|
||||
'tw': ('big5', 'cp950'),
|
||||
'hk': ('big5hkscs',),
|
||||
'jp': ('cp932', 'shift_jis', 'euc_jp', 'euc_jisx0213', 'shift_jisx0213',
|
||||
'euc_jis_2004', 'shift_jis_2004'),
|
||||
'kr': ('cp949', 'euc_kr', 'johab'),
|
||||
'iso2022': ('iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2',
|
||||
'iso2022_jp_2004', 'iso2022_jp_3', 'iso2022_jp_ext',
|
||||
'iso2022_kr'),
|
||||
}
|
||||
|
||||
TEMPLATE = string.Template("""\
|
||||
#
|
||||
# $encoding.py: Python Unicode Codec for $ENCODING
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_$owner, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_$owner.getcodec('$encoding')
|
||||
|
||||
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='$encoding',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
""")
|
||||
|
||||
def gencodecs(prefix):
|
||||
for loc, encodings in codecs.items():
|
||||
for enc in encodings:
|
||||
code = TEMPLATE.substitute(ENCODING=enc.upper(),
|
||||
encoding=enc.lower(),
|
||||
owner=loc)
|
||||
codecpath = os.path.join(prefix, enc + '.py')
|
||||
open(codecpath, 'w').write(code)
|
||||
|
||||
if __name__ == '__main__':
|
||||
import sys
|
||||
gencodecs(sys.argv[1])
|
||||
429
third_party/python/Tools/unicode/gencodec.py
vendored
Normal file
429
third_party/python/Tools/unicode/gencodec.py
vendored
Normal file
|
|
@ -0,0 +1,429 @@
|
|||
""" Unicode Mapping Parser and Codec Generator.
|
||||
|
||||
This script parses Unicode mapping files as available from the Unicode
|
||||
site (ftp://ftp.unicode.org/Public/MAPPINGS/) and creates Python codec
|
||||
modules from them. The codecs use the standard character mapping codec
|
||||
to actually apply the mapping.
|
||||
|
||||
Synopsis: gencodec.py dir codec_prefix
|
||||
|
||||
All files in dir are scanned and those producing non-empty mappings
|
||||
will be written to <codec_prefix><mapname>.py with <mapname> being the
|
||||
first part of the map's filename ('a' in a.b.c.txt) converted to
|
||||
lowercase with hyphens replaced by underscores.
|
||||
|
||||
The tool also writes marshalled versions of the mapping tables to the
|
||||
same location (with .mapping extension).
|
||||
|
||||
Written by Marc-Andre Lemburg (mal@lemburg.com).
|
||||
|
||||
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
||||
(c) Copyright Guido van Rossum, 2000.
|
||||
|
||||
Table generation:
|
||||
(c) Copyright Marc-Andre Lemburg, 2005.
|
||||
Licensed to PSF under a Contributor Agreement.
|
||||
|
||||
"""#"
|
||||
|
||||
import re, os, marshal, codecs
|
||||
|
||||
# Maximum allowed size of charmap tables
|
||||
MAX_TABLE_SIZE = 8192
|
||||
|
||||
# Standard undefined Unicode code point
|
||||
UNI_UNDEFINED = chr(0xFFFE)
|
||||
|
||||
# Placeholder for a missing code point
|
||||
MISSING_CODE = -1
|
||||
|
||||
mapRE = re.compile(r'((?:0x[0-9a-fA-F]+\+?)+)'
|
||||
r'\s+'
|
||||
r'((?:(?:0x[0-9a-fA-Z]+|<[A-Za-z]+>)\+?)*)'
|
||||
r'\s*'
|
||||
r'(#.+)?')
|
||||
|
||||
def parsecodes(codes, len=len, range=range):
|
||||
|
||||
""" Converts code combinations to either a single code integer
|
||||
or a tuple of integers.
|
||||
|
||||
meta-codes (in angular brackets, e.g. <LR> and <RL>) are
|
||||
ignored.
|
||||
|
||||
Empty codes or illegal ones are returned as None.
|
||||
|
||||
"""
|
||||
if not codes:
|
||||
return MISSING_CODE
|
||||
l = codes.split('+')
|
||||
if len(l) == 1:
|
||||
return int(l[0],16)
|
||||
for i in range(len(l)):
|
||||
try:
|
||||
l[i] = int(l[i],16)
|
||||
except ValueError:
|
||||
l[i] = MISSING_CODE
|
||||
l = [x for x in l if x != MISSING_CODE]
|
||||
if len(l) == 1:
|
||||
return l[0]
|
||||
else:
|
||||
return tuple(l)
|
||||
|
||||
def readmap(filename):
|
||||
|
||||
f = open(filename,'r')
|
||||
lines = f.readlines()
|
||||
f.close()
|
||||
enc2uni = {}
|
||||
identity = []
|
||||
unmapped = list(range(256))
|
||||
|
||||
# UTC mapping tables per convention don't include the identity
|
||||
# mappings for code points 0x00 - 0x1F and 0x7F, unless these are
|
||||
# explicitly mapped to different characters or undefined
|
||||
for i in list(range(32)) + [127]:
|
||||
identity.append(i)
|
||||
unmapped.remove(i)
|
||||
enc2uni[i] = (i, 'CONTROL CHARACTER')
|
||||
|
||||
for line in lines:
|
||||
line = line.strip()
|
||||
if not line or line[0] == '#':
|
||||
continue
|
||||
m = mapRE.match(line)
|
||||
if not m:
|
||||
#print '* not matched: %s' % repr(line)
|
||||
continue
|
||||
enc,uni,comment = m.groups()
|
||||
enc = parsecodes(enc)
|
||||
uni = parsecodes(uni)
|
||||
if comment is None:
|
||||
comment = ''
|
||||
else:
|
||||
comment = comment[1:].strip()
|
||||
if not isinstance(enc, tuple) and enc < 256:
|
||||
if enc in unmapped:
|
||||
unmapped.remove(enc)
|
||||
if enc == uni:
|
||||
identity.append(enc)
|
||||
enc2uni[enc] = (uni,comment)
|
||||
else:
|
||||
enc2uni[enc] = (uni,comment)
|
||||
|
||||
# If there are more identity-mapped entries than unmapped entries,
|
||||
# it pays to generate an identity dictionary first, and add explicit
|
||||
# mappings to None for the rest
|
||||
if len(identity) >= len(unmapped):
|
||||
for enc in unmapped:
|
||||
enc2uni[enc] = (MISSING_CODE, "")
|
||||
enc2uni['IDENTITY'] = 256
|
||||
|
||||
return enc2uni
|
||||
|
||||
def hexrepr(t, precision=4):
|
||||
|
||||
if t is None:
|
||||
return 'None'
|
||||
try:
|
||||
len(t)
|
||||
except TypeError:
|
||||
return '0x%0*X' % (precision, t)
|
||||
try:
|
||||
return '(' + ', '.join(['0x%0*X' % (precision, item)
|
||||
for item in t]) + ')'
|
||||
except TypeError as why:
|
||||
print('* failed to convert %r: %s' % (t, why))
|
||||
raise
|
||||
|
||||
def python_mapdef_code(varname, map, comments=1, precisions=(2, 4)):
|
||||
|
||||
l = []
|
||||
append = l.append
|
||||
if "IDENTITY" in map:
|
||||
append("%s = codecs.make_identity_dict(range(%d))" %
|
||||
(varname, map["IDENTITY"]))
|
||||
append("%s.update({" % varname)
|
||||
splits = 1
|
||||
del map["IDENTITY"]
|
||||
identity = 1
|
||||
else:
|
||||
append("%s = {" % varname)
|
||||
splits = 0
|
||||
identity = 0
|
||||
|
||||
mappings = sorted(map.items())
|
||||
i = 0
|
||||
key_precision, value_precision = precisions
|
||||
for mapkey, mapvalue in mappings:
|
||||
mapcomment = ''
|
||||
if isinstance(mapkey, tuple):
|
||||
(mapkey, mapcomment) = mapkey
|
||||
if isinstance(mapvalue, tuple):
|
||||
(mapvalue, mapcomment) = mapvalue
|
||||
if mapkey is None:
|
||||
continue
|
||||
if (identity and
|
||||
mapkey == mapvalue and
|
||||
mapkey < 256):
|
||||
# No need to include identity mappings, since these
|
||||
# are already set for the first 256 code points.
|
||||
continue
|
||||
key = hexrepr(mapkey, key_precision)
|
||||
value = hexrepr(mapvalue, value_precision)
|
||||
if mapcomment and comments:
|
||||
append(' %s: %s,\t# %s' % (key, value, mapcomment))
|
||||
else:
|
||||
append(' %s: %s,' % (key, value))
|
||||
i += 1
|
||||
if i == 4096:
|
||||
# Split the definition into parts to that the Python
|
||||
# parser doesn't dump core
|
||||
if splits == 0:
|
||||
append('}')
|
||||
else:
|
||||
append('})')
|
||||
append('%s.update({' % varname)
|
||||
i = 0
|
||||
splits = splits + 1
|
||||
if splits == 0:
|
||||
append('}')
|
||||
else:
|
||||
append('})')
|
||||
|
||||
return l
|
||||
|
||||
def python_tabledef_code(varname, map, comments=1, key_precision=2):
|
||||
|
||||
l = []
|
||||
append = l.append
|
||||
append('%s = (' % varname)
|
||||
|
||||
# Analyze map and create table dict
|
||||
mappings = sorted(map.items())
|
||||
table = {}
|
||||
maxkey = 255
|
||||
if 'IDENTITY' in map:
|
||||
for key in range(256):
|
||||
table[key] = (key, '')
|
||||
del map['IDENTITY']
|
||||
for mapkey, mapvalue in mappings:
|
||||
mapcomment = ''
|
||||
if isinstance(mapkey, tuple):
|
||||
(mapkey, mapcomment) = mapkey
|
||||
if isinstance(mapvalue, tuple):
|
||||
(mapvalue, mapcomment) = mapvalue
|
||||
if mapkey == MISSING_CODE:
|
||||
continue
|
||||
table[mapkey] = (mapvalue, mapcomment)
|
||||
if mapkey > maxkey:
|
||||
maxkey = mapkey
|
||||
if maxkey > MAX_TABLE_SIZE:
|
||||
# Table too large
|
||||
return None
|
||||
|
||||
# Create table code
|
||||
maxchar = 0
|
||||
for key in range(maxkey + 1):
|
||||
if key not in table:
|
||||
mapvalue = MISSING_CODE
|
||||
mapcomment = 'UNDEFINED'
|
||||
else:
|
||||
mapvalue, mapcomment = table[key]
|
||||
if mapvalue == MISSING_CODE:
|
||||
mapchar = UNI_UNDEFINED
|
||||
else:
|
||||
if isinstance(mapvalue, tuple):
|
||||
# 1-n mappings not supported
|
||||
return None
|
||||
else:
|
||||
mapchar = chr(mapvalue)
|
||||
maxchar = max(maxchar, ord(mapchar))
|
||||
if mapcomment and comments:
|
||||
append(' %a \t# %s -> %s' % (mapchar,
|
||||
hexrepr(key, key_precision),
|
||||
mapcomment))
|
||||
else:
|
||||
append(' %a' % mapchar)
|
||||
|
||||
if maxchar < 256:
|
||||
append(' %a \t## Widen to UCS2 for optimization' % UNI_UNDEFINED)
|
||||
append(')')
|
||||
return l
|
||||
|
||||
def codegen(name, map, encodingname, comments=1):
|
||||
|
||||
""" Returns Python source for the given map.
|
||||
|
||||
Comments are included in the source, if comments is true (default).
|
||||
|
||||
"""
|
||||
# Generate code
|
||||
decoding_map_code = python_mapdef_code(
|
||||
'decoding_map',
|
||||
map,
|
||||
comments=comments)
|
||||
decoding_table_code = python_tabledef_code(
|
||||
'decoding_table',
|
||||
map,
|
||||
comments=comments)
|
||||
encoding_map_code = python_mapdef_code(
|
||||
'encoding_map',
|
||||
codecs.make_encoding_map(map),
|
||||
comments=comments,
|
||||
precisions=(4, 2))
|
||||
|
||||
if decoding_table_code:
|
||||
suffix = 'table'
|
||||
else:
|
||||
suffix = 'map'
|
||||
|
||||
l = [
|
||||
'''\
|
||||
""" Python Character Mapping Codec %s generated from '%s' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self, input, errors='strict'):
|
||||
return codecs.charmap_encode(input, errors, encoding_%s)
|
||||
|
||||
def decode(self, input, errors='strict'):
|
||||
return codecs.charmap_decode(input, errors, decoding_%s)
|
||||
''' % (encodingname, name, suffix, suffix)]
|
||||
l.append('''\
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input, self.errors, encoding_%s)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input, self.errors, decoding_%s)[0]''' %
|
||||
(suffix, suffix))
|
||||
|
||||
l.append('''
|
||||
class StreamWriter(Codec, codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec, codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name=%r,
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
''' % encodingname.replace('_', '-'))
|
||||
|
||||
# Add decoding table or map (with preference to the table)
|
||||
if not decoding_table_code:
|
||||
l.append('''
|
||||
### Decoding Map
|
||||
''')
|
||||
l.extend(decoding_map_code)
|
||||
else:
|
||||
l.append('''
|
||||
### Decoding Table
|
||||
''')
|
||||
l.extend(decoding_table_code)
|
||||
|
||||
# Add encoding map
|
||||
if decoding_table_code:
|
||||
l.append('''
|
||||
### Encoding table
|
||||
encoding_table = codecs.charmap_build(decoding_table)
|
||||
''')
|
||||
else:
|
||||
l.append('''
|
||||
### Encoding Map
|
||||
''')
|
||||
l.extend(encoding_map_code)
|
||||
|
||||
# Final new-line
|
||||
l.append('')
|
||||
|
||||
return '\n'.join(l).expandtabs()
|
||||
|
||||
def pymap(name,map,pyfile,encodingname,comments=1):
|
||||
|
||||
code = codegen(name,map,encodingname,comments)
|
||||
f = open(pyfile,'w')
|
||||
f.write(code)
|
||||
f.close()
|
||||
|
||||
def marshalmap(name,map,marshalfile):
|
||||
|
||||
d = {}
|
||||
for e,(u,c) in map.items():
|
||||
d[e] = (u,c)
|
||||
f = open(marshalfile,'wb')
|
||||
marshal.dump(d,f)
|
||||
f.close()
|
||||
|
||||
def convertdir(dir, dirprefix='', nameprefix='', comments=1):
|
||||
|
||||
mapnames = os.listdir(dir)
|
||||
for mapname in mapnames:
|
||||
mappathname = os.path.join(dir, mapname)
|
||||
if not os.path.isfile(mappathname):
|
||||
continue
|
||||
name = os.path.split(mapname)[1]
|
||||
name = name.replace('-','_')
|
||||
name = name.split('.')[0]
|
||||
name = name.lower()
|
||||
name = nameprefix + name
|
||||
codefile = name + '.py'
|
||||
marshalfile = name + '.mapping'
|
||||
print('converting %s to %s and %s' % (mapname,
|
||||
dirprefix + codefile,
|
||||
dirprefix + marshalfile))
|
||||
try:
|
||||
map = readmap(os.path.join(dir,mapname))
|
||||
if not map:
|
||||
print('* map is empty; skipping')
|
||||
else:
|
||||
pymap(mappathname, map, dirprefix + codefile,name,comments)
|
||||
marshalmap(mappathname, map, dirprefix + marshalfile)
|
||||
except ValueError as why:
|
||||
print('* conversion failed: %s' % why)
|
||||
raise
|
||||
|
||||
def rewritepythondir(dir, dirprefix='', comments=1):
|
||||
|
||||
mapnames = os.listdir(dir)
|
||||
for mapname in mapnames:
|
||||
if not mapname.endswith('.mapping'):
|
||||
continue
|
||||
name = mapname[:-len('.mapping')]
|
||||
codefile = name + '.py'
|
||||
print('converting %s to %s' % (mapname,
|
||||
dirprefix + codefile))
|
||||
try:
|
||||
map = marshal.load(open(os.path.join(dir,mapname),
|
||||
'rb'))
|
||||
if not map:
|
||||
print('* map is empty; skipping')
|
||||
else:
|
||||
pymap(mapname, map, dirprefix + codefile,name,comments)
|
||||
except ValueError as why:
|
||||
print('* conversion failed: %s' % why)
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
import sys
|
||||
if 1:
|
||||
convertdir(*sys.argv[1:])
|
||||
else:
|
||||
rewritepythondir(*sys.argv[1:])
|
||||
61
third_party/python/Tools/unicode/genwincodec.py
vendored
Normal file
61
third_party/python/Tools/unicode/genwincodec.py
vendored
Normal file
|
|
@ -0,0 +1,61 @@
|
|||
"""This script generates a Python codec module from a Windows Code Page.
|
||||
|
||||
It uses the function MultiByteToWideChar to generate a decoding table.
|
||||
"""
|
||||
|
||||
import ctypes
|
||||
from ctypes import wintypes
|
||||
from gencodec import codegen
|
||||
import unicodedata
|
||||
|
||||
def genwinmap(codepage):
|
||||
MultiByteToWideChar = ctypes.windll.kernel32.MultiByteToWideChar
|
||||
MultiByteToWideChar.argtypes = [wintypes.UINT, wintypes.DWORD,
|
||||
wintypes.LPCSTR, ctypes.c_int,
|
||||
wintypes.LPWSTR, ctypes.c_int]
|
||||
MultiByteToWideChar.restype = ctypes.c_int
|
||||
|
||||
enc2uni = {}
|
||||
|
||||
for i in list(range(32)) + [127]:
|
||||
enc2uni[i] = (i, 'CONTROL CHARACTER')
|
||||
|
||||
for i in range(256):
|
||||
buf = ctypes.create_unicode_buffer(2)
|
||||
ret = MultiByteToWideChar(
|
||||
codepage, 0,
|
||||
bytes([i]), 1,
|
||||
buf, 2)
|
||||
assert ret == 1, "invalid code page"
|
||||
assert buf[1] == '\x00'
|
||||
try:
|
||||
name = unicodedata.name(buf[0])
|
||||
except ValueError:
|
||||
try:
|
||||
name = enc2uni[i][1]
|
||||
except KeyError:
|
||||
name = ''
|
||||
|
||||
enc2uni[i] = (ord(buf[0]), name)
|
||||
|
||||
return enc2uni
|
||||
|
||||
def genwincodec(codepage):
|
||||
import platform
|
||||
map = genwinmap(codepage)
|
||||
encodingname = 'cp%d' % codepage
|
||||
code = codegen("", map, encodingname)
|
||||
# Replace first lines with our own docstring
|
||||
code = '''\
|
||||
"""Python Character Mapping Codec %s generated on Windows:
|
||||
%s with the command:
|
||||
python Tools/unicode/genwincodec.py %s
|
||||
"""#"
|
||||
''' % (encodingname, ' '.join(platform.win32_ver()), codepage
|
||||
) + code.split('"""#"', 1)[1]
|
||||
|
||||
print(code)
|
||||
|
||||
if __name__ == '__main__':
|
||||
import sys
|
||||
genwincodec(int(sys.argv[1]))
|
||||
7
third_party/python/Tools/unicode/genwincodecs.bat
vendored
Normal file
7
third_party/python/Tools/unicode/genwincodecs.bat
vendored
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
@rem Recreate some python charmap codecs from the Windows function
|
||||
@rem MultiByteToWideChar.
|
||||
|
||||
@cd /d %~dp0
|
||||
@mkdir build
|
||||
@rem Arabic DOS code page
|
||||
c:\python30\python genwincodec.py 720 > build/cp720.py
|
||||
41
third_party/python/Tools/unicode/listcodecs.py
vendored
Normal file
41
third_party/python/Tools/unicode/listcodecs.py
vendored
Normal file
|
|
@ -0,0 +1,41 @@
|
|||
""" List all available codec modules.
|
||||
|
||||
(c) Copyright 2005, Marc-Andre Lemburg (mal@lemburg.com).
|
||||
|
||||
Licensed to PSF under a Contributor Agreement.
|
||||
|
||||
"""
|
||||
|
||||
import os, codecs, encodings
|
||||
|
||||
_debug = 0
|
||||
|
||||
def listcodecs(dir):
|
||||
names = []
|
||||
for filename in os.listdir(dir):
|
||||
if filename[-3:] != '.py':
|
||||
continue
|
||||
name = filename[:-3]
|
||||
# Check whether we've found a true codec
|
||||
try:
|
||||
codecs.lookup(name)
|
||||
except LookupError:
|
||||
# Codec not found
|
||||
continue
|
||||
except Exception as reason:
|
||||
# Probably an error from importing the codec; still it's
|
||||
# a valid code name
|
||||
if _debug:
|
||||
print('* problem importing codec %r: %s' % \
|
||||
(name, reason))
|
||||
names.append(name)
|
||||
return names
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
names = listcodecs(encodings.__path__[0])
|
||||
names.sort()
|
||||
print('all_codecs = [')
|
||||
for name in names:
|
||||
print(' %r,' % name)
|
||||
print(']')
|
||||
1345
third_party/python/Tools/unicode/makeunicodedata.py
vendored
Normal file
1345
third_party/python/Tools/unicode/makeunicodedata.py
vendored
Normal file
File diff suppressed because it is too large
Load diff
431
third_party/python/Tools/unicode/mkstringprep.py
vendored
Normal file
431
third_party/python/Tools/unicode/mkstringprep.py
vendored
Normal file
|
|
@ -0,0 +1,431 @@
|
|||
import re, sys
|
||||
from unicodedata import ucd_3_2_0 as unicodedata
|
||||
|
||||
if sys.maxunicode == 65535:
|
||||
raise RuntimeError("need UCS-4 Python")
|
||||
|
||||
def gen_category(cats):
|
||||
for i in range(0, 0x110000):
|
||||
if unicodedata.category(chr(i)) in cats:
|
||||
yield(i)
|
||||
|
||||
def gen_bidirectional(cats):
|
||||
for i in range(0, 0x110000):
|
||||
if unicodedata.bidirectional(chr(i)) in cats:
|
||||
yield(i)
|
||||
|
||||
def compact_set(l):
|
||||
single = []
|
||||
tuple = []
|
||||
prev = None
|
||||
span = 0
|
||||
for e in l:
|
||||
if prev is None:
|
||||
prev = e
|
||||
span = 0
|
||||
continue
|
||||
if prev+span+1 != e:
|
||||
if span > 2:
|
||||
tuple.append((prev,prev+span+1))
|
||||
else:
|
||||
for i in range(prev, prev+span+1):
|
||||
single.append(i)
|
||||
prev = e
|
||||
span = 0
|
||||
else:
|
||||
span += 1
|
||||
if span:
|
||||
tuple.append((prev,prev+span+1))
|
||||
else:
|
||||
single.append(prev)
|
||||
if not single and len(tuple) == 1:
|
||||
tuple = "range(%d,%d)" % tuple[0]
|
||||
else:
|
||||
tuple = " + ".join("list(range(%d,%d))" % t for t in tuple)
|
||||
if not single:
|
||||
return "set(%s)" % tuple
|
||||
if not tuple:
|
||||
return "set(%r)" % (single,)
|
||||
return "set(%r + %s)" % (single, tuple)
|
||||
|
||||
############## Read the tables in the RFC #######################
|
||||
|
||||
with open("rfc3454.txt") as f:
|
||||
data = f.readlines()
|
||||
|
||||
tables = []
|
||||
curname = None
|
||||
for l in data:
|
||||
l = l.strip()
|
||||
if not l:
|
||||
continue
|
||||
# Skip RFC page breaks
|
||||
if l.startswith(("Hoffman & Blanchet", "RFC 3454")):
|
||||
continue
|
||||
# Find start/end lines
|
||||
m = re.match("----- (Start|End) Table ([A-Z](.[0-9])+) -----", l)
|
||||
if m:
|
||||
if m.group(1) == "Start":
|
||||
if curname:
|
||||
raise RuntimeError("Double Start", (curname, l))
|
||||
curname = m.group(2)
|
||||
table = {}
|
||||
tables.append((curname, table))
|
||||
continue
|
||||
else:
|
||||
if not curname:
|
||||
raise RuntimeError("End without start", l)
|
||||
if curname != m.group(2):
|
||||
raise RuntimeError("Unexpected end", l)
|
||||
curname = None
|
||||
continue
|
||||
if not curname:
|
||||
continue
|
||||
# Now we are in a table
|
||||
fields = l.split(";")
|
||||
if len(fields) > 1:
|
||||
# Drop comment field
|
||||
fields = fields[:-1]
|
||||
if len(fields) == 1:
|
||||
fields = fields[0].split("-")
|
||||
if len(fields) > 1:
|
||||
# range
|
||||
try:
|
||||
start, end = fields
|
||||
except ValueError:
|
||||
raise RuntimeError("Unpacking problem", l)
|
||||
else:
|
||||
start = end = fields[0]
|
||||
start = int(start, 16)
|
||||
end = int(end, 16)
|
||||
for i in range(start, end+1):
|
||||
table[i] = i
|
||||
else:
|
||||
code, value = fields
|
||||
value = value.strip()
|
||||
if value:
|
||||
value = [int(v, 16) for v in value.split(" ")]
|
||||
else:
|
||||
# table B.1
|
||||
value = None
|
||||
table[int(code, 16)] = value
|
||||
|
||||
########### Generate compact Python versions of the tables #############
|
||||
|
||||
print("""# This file is generated by mkstringprep.py. DO NOT EDIT.
|
||||
\"\"\"Library that exposes various tables found in the StringPrep RFC 3454.
|
||||
|
||||
There are two kinds of tables: sets, for which a member test is provided,
|
||||
and mappings, for which a mapping function is provided.
|
||||
\"\"\"
|
||||
|
||||
from unicodedata import ucd_3_2_0 as unicodedata
|
||||
""")
|
||||
|
||||
print("assert unicodedata.unidata_version == %r" % (unicodedata.unidata_version,))
|
||||
|
||||
# A.1 is the table of unassigned characters
|
||||
# XXX Plane 15 PUA is listed as unassigned in Python.
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "A.1"
|
||||
table = set(table.keys())
|
||||
Cn = set(gen_category(["Cn"]))
|
||||
|
||||
# FDD0..FDEF are process internal codes
|
||||
Cn -= set(range(0xFDD0, 0xFDF0))
|
||||
# not a character
|
||||
Cn -= set(range(0xFFFE, 0x110000, 0x10000))
|
||||
Cn -= set(range(0xFFFF, 0x110000, 0x10000))
|
||||
|
||||
# assert table == Cn
|
||||
|
||||
print("""
|
||||
def in_table_a1(code):
|
||||
if unicodedata.category(code) != 'Cn': return False
|
||||
c = ord(code)
|
||||
if 0xFDD0 <= c < 0xFDF0: return False
|
||||
return (c & 0xFFFF) not in (0xFFFE, 0xFFFF)
|
||||
""")
|
||||
|
||||
# B.1 cannot easily be derived
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "B.1"
|
||||
table = sorted(table.keys())
|
||||
print("""
|
||||
b1_set = """ + compact_set(table) + """
|
||||
def in_table_b1(code):
|
||||
return ord(code) in b1_set
|
||||
""")
|
||||
|
||||
# B.2 and B.3 is case folding.
|
||||
# It takes CaseFolding.txt into account, which is
|
||||
# not available in the Python database. Since
|
||||
# B.2 is derived from B.3, we process B.3 first.
|
||||
# B.3 supposedly *is* CaseFolding-3.2.0.txt.
|
||||
|
||||
name, table_b2 = tables[0]
|
||||
del tables[0]
|
||||
assert name == "B.2"
|
||||
|
||||
name, table_b3 = tables[0]
|
||||
del tables[0]
|
||||
assert name == "B.3"
|
||||
|
||||
# B.3 is mostly Python's .lower, except for a number
|
||||
# of special cases, e.g. considering canonical forms.
|
||||
|
||||
b3_exceptions = {}
|
||||
|
||||
for k,v in table_b2.items():
|
||||
if list(map(ord, chr(k).lower())) != v:
|
||||
b3_exceptions[k] = "".join(map(chr,v))
|
||||
|
||||
b3 = sorted(b3_exceptions.items())
|
||||
|
||||
print("""
|
||||
b3_exceptions = {""")
|
||||
for i, kv in enumerate(b3):
|
||||
print("0x%x:%a," % kv, end=' ')
|
||||
if i % 4 == 3:
|
||||
print()
|
||||
print("}")
|
||||
|
||||
print("""
|
||||
def map_table_b3(code):
|
||||
r = b3_exceptions.get(ord(code))
|
||||
if r is not None: return r
|
||||
return code.lower()
|
||||
""")
|
||||
|
||||
def map_table_b3(code):
|
||||
r = b3_exceptions.get(ord(code))
|
||||
if r is not None: return r
|
||||
return code.lower()
|
||||
|
||||
# B.2 is case folding for NFKC. This is the same as B.3,
|
||||
# except where NormalizeWithKC(Fold(a)) !=
|
||||
# NormalizeWithKC(Fold(NormalizeWithKC(Fold(a))))
|
||||
|
||||
def map_table_b2(a):
|
||||
al = map_table_b3(a)
|
||||
b = unicodedata.normalize("NFKC", al)
|
||||
bl = "".join([map_table_b3(ch) for ch in b])
|
||||
c = unicodedata.normalize("NFKC", bl)
|
||||
if b != c:
|
||||
return c
|
||||
else:
|
||||
return al
|
||||
|
||||
specials = {}
|
||||
for k,v in table_b2.items():
|
||||
if list(map(ord, map_table_b2(chr(k)))) != v:
|
||||
specials[k] = v
|
||||
|
||||
# B.3 should not add any additional special cases
|
||||
assert specials == {}
|
||||
|
||||
print("""
|
||||
def map_table_b2(a):
|
||||
al = map_table_b3(a)
|
||||
b = unicodedata.normalize("NFKC", al)
|
||||
bl = "".join([map_table_b3(ch) for ch in b])
|
||||
c = unicodedata.normalize("NFKC", bl)
|
||||
if b != c:
|
||||
return c
|
||||
else:
|
||||
return al
|
||||
""")
|
||||
|
||||
# C.1.1 is a table with a single character
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.1.1"
|
||||
assert table == {0x20:0x20}
|
||||
|
||||
print("""
|
||||
def in_table_c11(code):
|
||||
return code == " "
|
||||
""")
|
||||
|
||||
# C.1.2 is the rest of all space characters
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.1.2"
|
||||
|
||||
# table = set(table.keys())
|
||||
# Zs = set(gen_category(["Zs"])) - {0x20}
|
||||
# assert Zs == table
|
||||
|
||||
print("""
|
||||
def in_table_c12(code):
|
||||
return unicodedata.category(code) == "Zs" and code != " "
|
||||
|
||||
def in_table_c11_c12(code):
|
||||
return unicodedata.category(code) == "Zs"
|
||||
""")
|
||||
|
||||
# C.2.1 ASCII control characters
|
||||
name, table_c21 = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.2.1"
|
||||
|
||||
Cc = set(gen_category(["Cc"]))
|
||||
Cc_ascii = Cc & set(range(128))
|
||||
table_c21 = set(table_c21.keys())
|
||||
assert Cc_ascii == table_c21
|
||||
|
||||
print("""
|
||||
def in_table_c21(code):
|
||||
return ord(code) < 128 and unicodedata.category(code) == "Cc"
|
||||
""")
|
||||
|
||||
# C.2.2 Non-ASCII control characters. It also includes
|
||||
# a number of characters in category Cf.
|
||||
name, table_c22 = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.2.2"
|
||||
|
||||
Cc_nonascii = Cc - Cc_ascii
|
||||
table_c22 = set(table_c22.keys())
|
||||
assert len(Cc_nonascii - table_c22) == 0
|
||||
|
||||
specials = list(table_c22 - Cc_nonascii)
|
||||
specials.sort()
|
||||
|
||||
print("""c22_specials = """ + compact_set(specials) + """
|
||||
def in_table_c22(code):
|
||||
c = ord(code)
|
||||
if c < 128: return False
|
||||
if unicodedata.category(code) == "Cc": return True
|
||||
return c in c22_specials
|
||||
|
||||
def in_table_c21_c22(code):
|
||||
return unicodedata.category(code) == "Cc" or \\
|
||||
ord(code) in c22_specials
|
||||
""")
|
||||
|
||||
# C.3 Private use
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.3"
|
||||
|
||||
Co = set(gen_category(["Co"]))
|
||||
assert set(table.keys()) == Co
|
||||
|
||||
print("""
|
||||
def in_table_c3(code):
|
||||
return unicodedata.category(code) == "Co"
|
||||
""")
|
||||
|
||||
# C.4 Non-character code points, xFFFE, xFFFF
|
||||
# plus process internal codes
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.4"
|
||||
|
||||
nonchar = set(range(0xFDD0,0xFDF0))
|
||||
nonchar.update(range(0xFFFE,0x110000,0x10000))
|
||||
nonchar.update(range(0xFFFF,0x110000,0x10000))
|
||||
table = set(table.keys())
|
||||
assert table == nonchar
|
||||
|
||||
print("""
|
||||
def in_table_c4(code):
|
||||
c = ord(code)
|
||||
if c < 0xFDD0: return False
|
||||
if c < 0xFDF0: return True
|
||||
return (ord(code) & 0xFFFF) in (0xFFFE, 0xFFFF)
|
||||
""")
|
||||
|
||||
# C.5 Surrogate codes
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.5"
|
||||
|
||||
Cs = set(gen_category(["Cs"]))
|
||||
assert set(table.keys()) == Cs
|
||||
|
||||
print("""
|
||||
def in_table_c5(code):
|
||||
return unicodedata.category(code) == "Cs"
|
||||
""")
|
||||
|
||||
# C.6 Inappropriate for plain text
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.6"
|
||||
|
||||
table = sorted(table.keys())
|
||||
|
||||
print("""
|
||||
c6_set = """ + compact_set(table) + """
|
||||
def in_table_c6(code):
|
||||
return ord(code) in c6_set
|
||||
""")
|
||||
|
||||
# C.7 Inappropriate for canonical representation
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.7"
|
||||
|
||||
table = sorted(table.keys())
|
||||
|
||||
print("""
|
||||
c7_set = """ + compact_set(table) + """
|
||||
def in_table_c7(code):
|
||||
return ord(code) in c7_set
|
||||
""")
|
||||
|
||||
# C.8 Change display properties or are deprecated
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.8"
|
||||
|
||||
table = sorted(table.keys())
|
||||
|
||||
print("""
|
||||
c8_set = """ + compact_set(table) + """
|
||||
def in_table_c8(code):
|
||||
return ord(code) in c8_set
|
||||
""")
|
||||
|
||||
# C.9 Tagging characters
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "C.9"
|
||||
|
||||
table = sorted(table.keys())
|
||||
|
||||
print("""
|
||||
c9_set = """ + compact_set(table) + """
|
||||
def in_table_c9(code):
|
||||
return ord(code) in c9_set
|
||||
""")
|
||||
|
||||
# D.1 Characters with bidirectional property "R" or "AL"
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "D.1"
|
||||
|
||||
RandAL = set(gen_bidirectional(["R","AL"]))
|
||||
assert set(table.keys()) == RandAL
|
||||
|
||||
print("""
|
||||
def in_table_d1(code):
|
||||
return unicodedata.bidirectional(code) in ("R","AL")
|
||||
""")
|
||||
|
||||
# D.2 Characters with bidirectional property "L"
|
||||
name, table = tables[0]
|
||||
del tables[0]
|
||||
assert name == "D.2"
|
||||
|
||||
L = set(gen_bidirectional(["L"]))
|
||||
assert set(table.keys()) == L
|
||||
|
||||
print("""
|
||||
def in_table_d2(code):
|
||||
return unicodedata.bidirectional(code) == "L"
|
||||
""")
|
||||
291
third_party/python/Tools/unicode/python-mappings/CP1140.TXT
vendored
Normal file
291
third_party/python/Tools/unicode/python-mappings/CP1140.TXT
vendored
Normal file
|
|
@ -0,0 +1,291 @@
|
|||
#
|
||||
# Name: CP1140
|
||||
# Unicode version: 3.2
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 2005-10-25
|
||||
# Authors: Marc-Andre Lemburg <mal@egenix.com>
|
||||
#
|
||||
# This encoding is a modified CP037 encoding (with added Euro
|
||||
# currency sign).
|
||||
#
|
||||
# (c) Copyright Marc-Andre Lemburg, 2005.
|
||||
# Licensed to PSF under a Contributor Agreement.
|
||||
#
|
||||
# Based on the file
|
||||
# ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT
|
||||
# which is:
|
||||
#
|
||||
# Copyright (c) 2002 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x009C #CONTROL
|
||||
0x05 0x0009 #HORIZONTAL TABULATION
|
||||
0x06 0x0086 #CONTROL
|
||||
0x07 0x007F #DELETE
|
||||
0x08 0x0097 #CONTROL
|
||||
0x09 0x008D #CONTROL
|
||||
0x0A 0x008E #CONTROL
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x009D #CONTROL
|
||||
0x15 0x0085 #CONTROL
|
||||
0x16 0x0008 #BACKSPACE
|
||||
0x17 0x0087 #CONTROL
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x0092 #CONTROL
|
||||
0x1B 0x008F #CONTROL
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0080 #CONTROL
|
||||
0x21 0x0081 #CONTROL
|
||||
0x22 0x0082 #CONTROL
|
||||
0x23 0x0083 #CONTROL
|
||||
0x24 0x0084 #CONTROL
|
||||
0x25 0x000A #LINE FEED
|
||||
0x26 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x27 0x001B #ESCAPE
|
||||
0x28 0x0088 #CONTROL
|
||||
0x29 0x0089 #CONTROL
|
||||
0x2A 0x008A #CONTROL
|
||||
0x2B 0x008B #CONTROL
|
||||
0x2C 0x008C #CONTROL
|
||||
0x2D 0x0005 #ENQUIRY
|
||||
0x2E 0x0006 #ACKNOWLEDGE
|
||||
0x2F 0x0007 #BELL
|
||||
0x30 0x0090 #CONTROL
|
||||
0x31 0x0091 #CONTROL
|
||||
0x32 0x0016 #SYNCHRONOUS IDLE
|
||||
0x33 0x0093 #CONTROL
|
||||
0x34 0x0094 #CONTROL
|
||||
0x35 0x0095 #CONTROL
|
||||
0x36 0x0096 #CONTROL
|
||||
0x37 0x0004 #END OF TRANSMISSION
|
||||
0x38 0x0098 #CONTROL
|
||||
0x39 0x0099 #CONTROL
|
||||
0x3A 0x009A #CONTROL
|
||||
0x3B 0x009B #CONTROL
|
||||
0x3C 0x0014 #DEVICE CONTROL FOUR
|
||||
0x3D 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x3E 0x009E #CONTROL
|
||||
0x3F 0x001A #SUBSTITUTE
|
||||
0x40 0x0020 #SPACE
|
||||
0x41 0x00A0 #NO-BREAK SPACE
|
||||
0x42 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x43 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x44 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0x45 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
|
||||
0x46 0x00E3 #LATIN SMALL LETTER A WITH TILDE
|
||||
0x47 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x48 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x49 0x00F1 #LATIN SMALL LETTER N WITH TILDE
|
||||
0x4A 0x00A2 #CENT SIGN
|
||||
0x4B 0x002E #FULL STOP
|
||||
0x4C 0x003C #LESS-THAN SIGN
|
||||
0x4D 0x0028 #LEFT PARENTHESIS
|
||||
0x4E 0x002B #PLUS SIGN
|
||||
0x4F 0x007C #VERTICAL LINE
|
||||
0x50 0x0026 #AMPERSAND
|
||||
0x51 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0x52 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x53 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x54 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0x55 0x00ED #LATIN SMALL LETTER I WITH ACUTE
|
||||
0x56 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x57 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x58 0x00EC #LATIN SMALL LETTER I WITH GRAVE
|
||||
0x59 0x00DF #LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
0x5A 0x0021 #EXCLAMATION MARK
|
||||
0x5B 0x0024 #DOLLAR SIGN
|
||||
0x5C 0x002A #ASTERISK
|
||||
0x5D 0x0029 #RIGHT PARENTHESIS
|
||||
0x5E 0x003B #SEMICOLON
|
||||
0x5F 0x00AC #NOT SIGN
|
||||
0x60 0x002D #HYPHEN-MINUS
|
||||
0x61 0x002F #SOLIDUS
|
||||
0x62 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x63 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x64 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x65 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x66 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x67 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x68 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x69 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x6A 0x00A6 #BROKEN BAR
|
||||
0x6B 0x002C #COMMA
|
||||
0x6C 0x0025 #PERCENT SIGN
|
||||
0x6D 0x005F #LOW LINE
|
||||
0x6E 0x003E #GREATER-THAN SIGN
|
||||
0x6F 0x003F #QUESTION MARK
|
||||
0x70 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0x71 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x72 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x73 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x74 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x75 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x76 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x77 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x78 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x79 0x0060 #GRAVE ACCENT
|
||||
0x7A 0x003A #COLON
|
||||
0x7B 0x0023 #NUMBER SIGN
|
||||
0x7C 0x0040 #COMMERCIAL AT
|
||||
0x7D 0x0027 #APOSTROPHE
|
||||
0x7E 0x003D #EQUALS SIGN
|
||||
0x7F 0x0022 #QUOTATION MARK
|
||||
0x80 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x81 0x0061 #LATIN SMALL LETTER A
|
||||
0x82 0x0062 #LATIN SMALL LETTER B
|
||||
0x83 0x0063 #LATIN SMALL LETTER C
|
||||
0x84 0x0064 #LATIN SMALL LETTER D
|
||||
0x85 0x0065 #LATIN SMALL LETTER E
|
||||
0x86 0x0066 #LATIN SMALL LETTER F
|
||||
0x87 0x0067 #LATIN SMALL LETTER G
|
||||
0x88 0x0068 #LATIN SMALL LETTER H
|
||||
0x89 0x0069 #LATIN SMALL LETTER I
|
||||
0x8A 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x8B 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x8C 0x00F0 #LATIN SMALL LETTER ETH (ICELANDIC)
|
||||
0x8D 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x8E 0x00FE #LATIN SMALL LETTER THORN (ICELANDIC)
|
||||
0x8F 0x00B1 #PLUS-MINUS SIGN
|
||||
0x90 0x00B0 #DEGREE SIGN
|
||||
0x91 0x006A #LATIN SMALL LETTER J
|
||||
0x92 0x006B #LATIN SMALL LETTER K
|
||||
0x93 0x006C #LATIN SMALL LETTER L
|
||||
0x94 0x006D #LATIN SMALL LETTER M
|
||||
0x95 0x006E #LATIN SMALL LETTER N
|
||||
0x96 0x006F #LATIN SMALL LETTER O
|
||||
0x97 0x0070 #LATIN SMALL LETTER P
|
||||
0x98 0x0071 #LATIN SMALL LETTER Q
|
||||
0x99 0x0072 #LATIN SMALL LETTER R
|
||||
0x9A 0x00AA #FEMININE ORDINAL INDICATOR
|
||||
0x9B 0x00BA #MASCULINE ORDINAL INDICATOR
|
||||
0x9C 0x00E6 #LATIN SMALL LIGATURE AE
|
||||
0x9D 0x00B8 #CEDILLA
|
||||
0x9E 0x00C6 #LATIN CAPITAL LIGATURE AE
|
||||
#0x9F 0x00A4 #CURRENCY SIGN
|
||||
0x9F 0x20AC # EURO SIGN
|
||||
0xA0 0x00B5 #MICRO SIGN
|
||||
0xA1 0x007E #TILDE
|
||||
0xA2 0x0073 #LATIN SMALL LETTER S
|
||||
0xA3 0x0074 #LATIN SMALL LETTER T
|
||||
0xA4 0x0075 #LATIN SMALL LETTER U
|
||||
0xA5 0x0076 #LATIN SMALL LETTER V
|
||||
0xA6 0x0077 #LATIN SMALL LETTER W
|
||||
0xA7 0x0078 #LATIN SMALL LETTER X
|
||||
0xA8 0x0079 #LATIN SMALL LETTER Y
|
||||
0xA9 0x007A #LATIN SMALL LETTER Z
|
||||
0xAA 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xAB 0x00BF #INVERTED QUESTION MARK
|
||||
0xAC 0x00D0 #LATIN CAPITAL LETTER ETH (ICELANDIC)
|
||||
0xAD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0xAE 0x00DE #LATIN CAPITAL LETTER THORN (ICELANDIC)
|
||||
0xAF 0x00AE #REGISTERED SIGN
|
||||
0xB0 0x005E #CIRCUMFLEX ACCENT
|
||||
0xB1 0x00A3 #POUND SIGN
|
||||
0xB2 0x00A5 #YEN SIGN
|
||||
0xB3 0x00B7 #MIDDLE DOT
|
||||
0xB4 0x00A9 #COPYRIGHT SIGN
|
||||
0xB5 0x00A7 #SECTION SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xB8 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xB9 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBA 0x005B #LEFT SQUARE BRACKET
|
||||
0xBB 0x005D #RIGHT SQUARE BRACKET
|
||||
0xBC 0x00AF #MACRON
|
||||
0xBD 0x00A8 #DIAERESIS
|
||||
0xBE 0x00B4 #ACUTE ACCENT
|
||||
0xBF 0x00D7 #MULTIPLICATION SIGN
|
||||
0xC0 0x007B #LEFT CURLY BRACKET
|
||||
0xC1 0x0041 #LATIN CAPITAL LETTER A
|
||||
0xC2 0x0042 #LATIN CAPITAL LETTER B
|
||||
0xC3 0x0043 #LATIN CAPITAL LETTER C
|
||||
0xC4 0x0044 #LATIN CAPITAL LETTER D
|
||||
0xC5 0x0045 #LATIN CAPITAL LETTER E
|
||||
0xC6 0x0046 #LATIN CAPITAL LETTER F
|
||||
0xC7 0x0047 #LATIN CAPITAL LETTER G
|
||||
0xC8 0x0048 #LATIN CAPITAL LETTER H
|
||||
0xC9 0x0049 #LATIN CAPITAL LETTER I
|
||||
0xCA 0x00AD #SOFT HYPHEN
|
||||
0xCB 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xCC 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xCD 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
|
||||
0xCE 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xCF 0x00F5 #LATIN SMALL LETTER O WITH TILDE
|
||||
0xD0 0x007D #RIGHT CURLY BRACKET
|
||||
0xD1 0x004A #LATIN CAPITAL LETTER J
|
||||
0xD2 0x004B #LATIN CAPITAL LETTER K
|
||||
0xD3 0x004C #LATIN CAPITAL LETTER L
|
||||
0xD4 0x004D #LATIN CAPITAL LETTER M
|
||||
0xD5 0x004E #LATIN CAPITAL LETTER N
|
||||
0xD6 0x004F #LATIN CAPITAL LETTER O
|
||||
0xD7 0x0050 #LATIN CAPITAL LETTER P
|
||||
0xD8 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0xD9 0x0052 #LATIN CAPITAL LETTER R
|
||||
0xDA 0x00B9 #SUPERSCRIPT ONE
|
||||
0xDB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xDD 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0xDE 0x00FA #LATIN SMALL LETTER U WITH ACUTE
|
||||
0xDF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0xE0 0x005C #REVERSE SOLIDUS
|
||||
0xE1 0x00F7 #DIVISION SIGN
|
||||
0xE2 0x0053 #LATIN CAPITAL LETTER S
|
||||
0xE3 0x0054 #LATIN CAPITAL LETTER T
|
||||
0xE4 0x0055 #LATIN CAPITAL LETTER U
|
||||
0xE5 0x0056 #LATIN CAPITAL LETTER V
|
||||
0xE6 0x0057 #LATIN CAPITAL LETTER W
|
||||
0xE7 0x0058 #LATIN CAPITAL LETTER X
|
||||
0xE8 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0xE9 0x005A #LATIN CAPITAL LETTER Z
|
||||
0xEA 0x00B2 #SUPERSCRIPT TWO
|
||||
0xEB 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xEC 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xED 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xEF 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xF0 0x0030 #DIGIT ZERO
|
||||
0xF1 0x0031 #DIGIT ONE
|
||||
0xF2 0x0032 #DIGIT TWO
|
||||
0xF3 0x0033 #DIGIT THREE
|
||||
0xF4 0x0034 #DIGIT FOUR
|
||||
0xF5 0x0035 #DIGIT FIVE
|
||||
0xF6 0x0036 #DIGIT SIX
|
||||
0xF7 0x0037 #DIGIT SEVEN
|
||||
0xF8 0x0038 #DIGIT EIGHT
|
||||
0xF9 0x0039 #DIGIT NINE
|
||||
0xFA 0x00B3 #SUPERSCRIPT THREE
|
||||
0xFB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xFD 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xFE 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xFF 0x009F #CONTROL
|
||||
258
third_party/python/Tools/unicode/python-mappings/CP273.TXT
vendored
Normal file
258
third_party/python/Tools/unicode/python-mappings/CP273.TXT
vendored
Normal file
|
|
@ -0,0 +1,258 @@
|
|||
0x00 0x0000 #NULL (NUL)
|
||||
0x01 0x0001 #START OF HEADING (SOH)
|
||||
0x02 0x0002 #START OF TEXT (STX)
|
||||
0x03 0x0003 #END OF TEXT (ETX)
|
||||
0x04 0x009C #STRING TERMINATOR (ST)
|
||||
0x05 0x0009 #CHARACTER TABULATION (HT)
|
||||
0x06 0x0086 #START OF SELECTED AREA (SSA)
|
||||
0x07 0x007F #DELETE (DEL)
|
||||
0x08 0x0097 #END OF GUARDED AREA (EPA)
|
||||
0x09 0x008D #REVERSE LINE FEED (RI)
|
||||
0x0A 0x008E #SINGLE-SHIFT TWO (SS2)
|
||||
0x0B 0x000B #LINE TABULATION (VT)
|
||||
0x0C 0x000C #FORM FEED (FF)
|
||||
0x0D 0x000D #CARRIAGE RETURN (CR)
|
||||
0x0E 0x000E #SHIFT OUT (SO)
|
||||
0x0F 0x000F #SHIFT IN (SI)
|
||||
0x10 0x0010 #DATALINK ESCAPE (DLE)
|
||||
0x11 0x0011 #DEVICE CONTROL ONE (DC1)
|
||||
0x12 0x0012 #DEVICE CONTROL TWO (DC2)
|
||||
0x13 0x0013 #DEVICE CONTROL THREE (DC3)
|
||||
0x14 0x009D #OPERATING SYSTEM COMMAND (OSC)
|
||||
0x15 0x0085 #NEXT LINE (NEL)
|
||||
0x16 0x0008 #BACKSPACE (BS)
|
||||
0x17 0x0087 #END OF SELECTED AREA (ESA)
|
||||
0x18 0x0018 #CANCEL (CAN)
|
||||
0x19 0x0019 #END OF MEDIUM (EM)
|
||||
0x1A 0x0092 #PRIVATE USE TWO (PU2)
|
||||
0x1B 0x008F #SINGLE-SHIFT THREE (SS3)
|
||||
0x1C 0x001C #FILE SEPARATOR (IS4)
|
||||
0x1D 0x001D #GROUP SEPARATOR (IS3)
|
||||
0x1E 0x001E #RECORD SEPARATOR (IS2)
|
||||
0x1F 0x001F #UNIT SEPARATOR (IS1)
|
||||
0x20 0x0080 #PADDING CHARACTER (PAD)
|
||||
0x21 0x0081 #HIGH OCTET PRESET (HOP)
|
||||
0x22 0x0082 #BREAK PERMITTED HERE (BPH)
|
||||
0x23 0x0083 #NO BREAK HERE (NBH)
|
||||
0x24 0x0084 #INDEX (IND)
|
||||
0x25 0x000A #LINE FEED (LF)
|
||||
0x26 0x0017 #END OF TRANSMISSION BLOCK (ETB)
|
||||
0x27 0x001B #ESCAPE (ESC)
|
||||
0x28 0x0088 #CHARACTER TABULATION SET (HTS)
|
||||
0x29 0x0089 #CHARACTER TABULATION WITH JUSTIFICATION (HTJ)
|
||||
0x2A 0x008A #LINE TABULATION SET (VTS)
|
||||
0x2B 0x008B #PARTIAL LINE FORWARD (PLD)
|
||||
0x2C 0x008C #PARTIAL LINE BACKWARD (PLU)
|
||||
0x2D 0x0005 #ENQUIRY (ENQ)
|
||||
0x2E 0x0006 #ACKNOWLEDGE (ACK)
|
||||
0x2F 0x0007 #BELL (BEL)
|
||||
0x30 0x0090 #DEVICE CONTROL STRING (DCS)
|
||||
0x31 0x0091 #PRIVATE USE ONE (PU1)
|
||||
0x32 0x0016 #SYNCHRONOUS IDLE (SYN)
|
||||
0x33 0x0093 #SET TRANSMIT STATE (STS)
|
||||
0x34 0x0094 #CANCEL CHARACTER (CCH)
|
||||
0x35 0x0095 #MESSAGE WAITING (MW)
|
||||
0x36 0x0096 #START OF GUARDED AREA (SPA)
|
||||
0x37 0x0004 #END OF TRANSMISSION (EOT)
|
||||
0x38 0x0098 #START OF STRING (SOS)
|
||||
0x39 0x0099 #SINGLE GRAPHIC CHARACTER INTRODUCER (SGCI)
|
||||
0x3A 0x009A #SINGLE CHARACTER INTRODUCER (SCI)
|
||||
0x3B 0x009B #CONTROL SEQUENCE INTRODUCER (CSI)
|
||||
0x3C 0x0014 #DEVICE CONTROL FOUR (DC4)
|
||||
0x3D 0x0015 #NEGATIVE ACKNOWLEDGE (NAK)
|
||||
0x3E 0x009E #PRIVACY MESSAGE (PM)
|
||||
0x3F 0x001A #SUBSTITUTE (SUB)
|
||||
0x40 0x0020 #SPACE
|
||||
0x41 0x00A0 #NO-BREAK SPACE
|
||||
0x42 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x43 0x007B #LEFT CURLY BRACKET
|
||||
0x44 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0x45 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
|
||||
0x46 0x00E3 #LATIN SMALL LETTER A WITH TILDE
|
||||
0x47 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x48 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x49 0x00F1 #LATIN SMALL LETTER N WITH TILDE
|
||||
0x4A 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x4B 0x002E #FULL STOP
|
||||
0x4C 0x003C #LESS-THAN SIGN
|
||||
0x4D 0x0028 #LEFT PARENTHESIS
|
||||
0x4E 0x002B #PLUS SIGN
|
||||
0x4F 0x0021 #EXCLAMATION MARK
|
||||
0x50 0x0026 #AMPERSAND
|
||||
0x51 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0x52 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x53 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x54 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0x55 0x00ED #LATIN SMALL LETTER I WITH ACUTE
|
||||
0x56 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x57 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x58 0x00EC #LATIN SMALL LETTER I WITH GRAVE
|
||||
0x59 0x007E #TILDE
|
||||
0x5A 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x5B 0x0024 #DOLLAR SIGN
|
||||
0x5C 0x002A #ASTERISK
|
||||
0x5D 0x0029 #RIGHT PARENTHESIS
|
||||
0x5E 0x003B #SEMICOLON
|
||||
0x5F 0x005E #CIRCUMFLEX ACCENT
|
||||
0x60 0x002D #HYPHEN-MINUS
|
||||
0x61 0x002F #SOLIDUS
|
||||
0x62 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x63 0x005B #LEFT SQUARE BRACKET
|
||||
0x64 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x65 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x66 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x67 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x68 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x69 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x6A 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x6B 0x002C #COMMA
|
||||
0x6C 0x0025 #PERCENT SIGN
|
||||
0x6D 0x005F #LOW LINE
|
||||
0x6E 0x003E #GREATER-THAN SIGN
|
||||
0x6F 0x003F #QUESTION MARK
|
||||
0x70 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0x71 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x72 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x73 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x74 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x75 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x76 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x77 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x78 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x79 0x0060 #GRAVE ACCENT
|
||||
0x7A 0x003A #COLON
|
||||
0x7B 0x0023 #NUMBER SIGN
|
||||
0x7C 0x00A7 #SECTION SIGN
|
||||
0x7D 0x0027 #APOSTROPHE
|
||||
0x7E 0x003D #EQUALS SIGN
|
||||
0x7F 0x0022 #QUOTATION MARK
|
||||
0x80 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x81 0x0061 #LATIN SMALL LETTER A
|
||||
0x82 0x0062 #LATIN SMALL LETTER B
|
||||
0x83 0x0063 #LATIN SMALL LETTER C
|
||||
0x84 0x0064 #LATIN SMALL LETTER D
|
||||
0x85 0x0065 #LATIN SMALL LETTER E
|
||||
0x86 0x0066 #LATIN SMALL LETTER F
|
||||
0x87 0x0067 #LATIN SMALL LETTER G
|
||||
0x88 0x0068 #LATIN SMALL LETTER H
|
||||
0x89 0x0069 #LATIN SMALL LETTER I
|
||||
0x8A 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x8B 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x8C 0x00F0 #LATIN SMALL LETTER ETH (Icelandic)
|
||||
0x8D 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x8E 0x00FE #LATIN SMALL LETTER THORN (Icelandic)
|
||||
0x8F 0x00B1 #PLUS-MINUS SIGN
|
||||
0x90 0x00B0 #DEGREE SIGN
|
||||
0x91 0x006A #LATIN SMALL LETTER J
|
||||
0x92 0x006B #LATIN SMALL LETTER K
|
||||
0x93 0x006C #LATIN SMALL LETTER L
|
||||
0x94 0x006D #LATIN SMALL LETTER M
|
||||
0x95 0x006E #LATIN SMALL LETTER N
|
||||
0x96 0x006F #LATIN SMALL LETTER O
|
||||
0x97 0x0070 #LATIN SMALL LETTER P
|
||||
0x98 0x0071 #LATIN SMALL LETTER Q
|
||||
0x99 0x0072 #LATIN SMALL LETTER R
|
||||
0x9A 0x00AA #FEMININE ORDINAL INDICATOR
|
||||
0x9B 0x00BA #MASCULINE ORDINAL INDICATOR
|
||||
0x9C 0x00E6 #LATIN SMALL LETTER AE
|
||||
0x9D 0x00B8 #CEDILLA
|
||||
0x9E 0x00C6 #LATIN CAPITAL LETTER AE
|
||||
0x9F 0x00A4 #CURRENCY SIGN
|
||||
0xA0 0x00B5 #MICRO SIGN
|
||||
0xA1 0x00DF #LATIN SMALL LETTER SHARP S (German)
|
||||
0xA2 0x0073 #LATIN SMALL LETTER S
|
||||
0xA3 0x0074 #LATIN SMALL LETTER T
|
||||
0xA4 0x0075 #LATIN SMALL LETTER U
|
||||
0xA5 0x0076 #LATIN SMALL LETTER V
|
||||
0xA6 0x0077 #LATIN SMALL LETTER W
|
||||
0xA7 0x0078 #LATIN SMALL LETTER X
|
||||
0xA8 0x0079 #LATIN SMALL LETTER Y
|
||||
0xA9 0x007A #LATIN SMALL LETTER Z
|
||||
0xAA 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xAB 0x00BF #INVERTED QUESTION MARK
|
||||
0xAC 0x00D0 #LATIN CAPITAL LETTER ETH (Icelandic)
|
||||
0xAD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0xAE 0x00DE #LATIN CAPITAL LETTER THORN (Icelandic)
|
||||
0xAF 0x00AE #REGISTERED SIGN
|
||||
0xB0 0x00A2 #CENT SIGN
|
||||
0xB1 0x00A3 #POUND SIGN
|
||||
0xB2 0x00A5 #YEN SIGN
|
||||
0xB3 0x00B7 #MIDDLE DOT
|
||||
0xB4 0x00A9 #COPYRIGHT SIGN
|
||||
0xB5 0x0040 #COMMERCIAL AT
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xB8 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xB9 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBA 0x00AC #NOT SIGN
|
||||
0xBB 0x007C #VERTICAL LINE
|
||||
0xBC 0x203E #OVERLINE
|
||||
0xBD 0x00A8 #DIAERESIS
|
||||
0xBE 0x00B4 #ACUTE ACCENT
|
||||
0xBF 0x00D7 #MULTIPLICATION SIGN
|
||||
0xC0 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xC1 0x0041 #LATIN CAPITAL LETTER A
|
||||
0xC2 0x0042 #LATIN CAPITAL LETTER B
|
||||
0xC3 0x0043 #LATIN CAPITAL LETTER C
|
||||
0xC4 0x0044 #LATIN CAPITAL LETTER D
|
||||
0xC5 0x0045 #LATIN CAPITAL LETTER E
|
||||
0xC6 0x0046 #LATIN CAPITAL LETTER F
|
||||
0xC7 0x0047 #LATIN CAPITAL LETTER G
|
||||
0xC8 0x0048 #LATIN CAPITAL LETTER H
|
||||
0xC9 0x0049 #LATIN CAPITAL LETTER I
|
||||
0xCA 0x00AD #SOFT HYPHEN
|
||||
0xCB 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xCC 0x00A6 #BROKEN BAR
|
||||
0xCD 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
|
||||
0xCE 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xCF 0x00F5 #LATIN SMALL LETTER O WITH TILDE
|
||||
0xD0 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xD1 0x004A #LATIN CAPITAL LETTER J
|
||||
0xD2 0x004B #LATIN CAPITAL LETTER K
|
||||
0xD3 0x004C #LATIN CAPITAL LETTER L
|
||||
0xD4 0x004D #LATIN CAPITAL LETTER M
|
||||
0xD5 0x004E #LATIN CAPITAL LETTER N
|
||||
0xD6 0x004F #LATIN CAPITAL LETTER O
|
||||
0xD7 0x0050 #LATIN CAPITAL LETTER P
|
||||
0xD8 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0xD9 0x0052 #LATIN CAPITAL LETTER R
|
||||
0xDA 0x00B9 #SUPERSCRIPT ONE
|
||||
0xDB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x007D #RIGHT CURLY BRACKET
|
||||
0xDD 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0xDE 0x00FA #LATIN SMALL LETTER U WITH ACUTE
|
||||
0xDF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0xE0 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xE1 0x00F7 #DIVISION SIGN
|
||||
0xE2 0x0053 #LATIN CAPITAL LETTER S
|
||||
0xE3 0x0054 #LATIN CAPITAL LETTER T
|
||||
0xE4 0x0055 #LATIN CAPITAL LETTER U
|
||||
0xE5 0x0056 #LATIN CAPITAL LETTER V
|
||||
0xE6 0x0057 #LATIN CAPITAL LETTER W
|
||||
0xE7 0x0058 #LATIN CAPITAL LETTER X
|
||||
0xE8 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0xE9 0x005A #LATIN CAPITAL LETTER Z
|
||||
0xEA 0x00B2 #SUPERSCRIPT TWO
|
||||
0xEB 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xEC 0x005C #REVERSE SOLIDUS
|
||||
0xED 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xEF 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xF0 0x0030 #DIGIT ZERO
|
||||
0xF1 0x0031 #DIGIT ONE
|
||||
0xF2 0x0032 #DIGIT TWO
|
||||
0xF3 0x0033 #DIGIT THREE
|
||||
0xF4 0x0034 #DIGIT FOUR
|
||||
0xF5 0x0035 #DIGIT FIVE
|
||||
0xF6 0x0036 #DIGIT SIX
|
||||
0xF7 0x0037 #DIGIT SEVEN
|
||||
0xF8 0x0038 #DIGIT EIGHT
|
||||
0xF9 0x0039 #DIGIT NINE
|
||||
0xFA 0x00B3 #SUPERSCRIPT THREE
|
||||
0xFB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x005D #RIGHT SQUARE BRACKET
|
||||
0xFD 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xFE 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xFF 0x009F #APPLICATION PROGRAM COMMAND (APC)
|
||||
|
||||
|
||||
298
third_party/python/Tools/unicode/python-mappings/KOI8-U.TXT
vendored
Normal file
298
third_party/python/Tools/unicode/python-mappings/KOI8-U.TXT
vendored
Normal file
|
|
@ -0,0 +1,298 @@
|
|||
#
|
||||
# Name: KOI8-U (RFC2319) to Unicode
|
||||
# Unicode version: 3.2
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 2005-10-25
|
||||
# Authors: Marc-Andre Lemburg <mal@egenix.com>
|
||||
#
|
||||
# See RFC2319 for details. This encoding is a modified KOI8-R
|
||||
# encoding.
|
||||
#
|
||||
# (c) Copyright Marc-Andre Lemburg, 2005.
|
||||
# Licensed to PSF under a Contributor Agreement.
|
||||
#
|
||||
# Based on the file
|
||||
# ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-R.TXT
|
||||
# which is:
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x8B 0x2580 # UPPER HALF BLOCK
|
||||
0x8C 0x2584 # LOWER HALF BLOCK
|
||||
0x8D 0x2588 # FULL BLOCK
|
||||
0x8E 0x258C # LEFT HALF BLOCK
|
||||
0x8F 0x2590 # RIGHT HALF BLOCK
|
||||
0x90 0x2591 # LIGHT SHADE
|
||||
0x91 0x2592 # MEDIUM SHADE
|
||||
0x92 0x2593 # DARK SHADE
|
||||
0x93 0x2320 # TOP HALF INTEGRAL
|
||||
0x94 0x25A0 # BLACK SQUARE
|
||||
0x95 0x2219 # BULLET OPERATOR
|
||||
0x96 0x221A # SQUARE ROOT
|
||||
0x97 0x2248 # ALMOST EQUAL TO
|
||||
0x98 0x2264 # LESS-THAN OR EQUAL TO
|
||||
0x99 0x2265 # GREATER-THAN OR EQUAL TO
|
||||
0x9A 0x00A0 # NO-BREAK SPACE
|
||||
0x9B 0x2321 # BOTTOM HALF INTEGRAL
|
||||
0x9C 0x00B0 # DEGREE SIGN
|
||||
0x9D 0x00B2 # SUPERSCRIPT TWO
|
||||
0x9E 0x00B7 # MIDDLE DOT
|
||||
0x9F 0x00F7 # DIVISION SIGN
|
||||
0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0xA3 0x0451 # CYRILLIC SMALL LETTER IO
|
||||
#0xA4 0x2553 # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0xA4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
#0xA6 0x2555 # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0xA6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
#0xA7 0x2556 # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0xA7 0x0457 # CYRILLIC SMALL LETTER YI (UKRAINIAN)
|
||||
0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
#0xAD 0x255C # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0xAD 0x0491 # CYRILLIC SMALL LETTER UKRAINIAN GHE WITH UPTURN
|
||||
0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO
|
||||
#0xB4 0x2562 # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0xB4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
#0xB6 0x2564 # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0xB6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
#0xB7 0x2565 # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0xB7 0x0407 # CYRILLIC CAPITAL LETTER YI (UKRAINIAN)
|
||||
0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
#0xBD 0x256B # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0xBD 0x0490 # CYRILLIC CAPITAL LETTER UKRAINIAN GHE WITH UPTURN
|
||||
0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0xBF 0x00A9 # COPYRIGHT SIGN
|
||||
0xC0 0x044E # CYRILLIC SMALL LETTER YU
|
||||
0xC1 0x0430 # CYRILLIC SMALL LETTER A
|
||||
0xC2 0x0431 # CYRILLIC SMALL LETTER BE
|
||||
0xC3 0x0446 # CYRILLIC SMALL LETTER TSE
|
||||
0xC4 0x0434 # CYRILLIC SMALL LETTER DE
|
||||
0xC5 0x0435 # CYRILLIC SMALL LETTER IE
|
||||
0xC6 0x0444 # CYRILLIC SMALL LETTER EF
|
||||
0xC7 0x0433 # CYRILLIC SMALL LETTER GHE
|
||||
0xC8 0x0445 # CYRILLIC SMALL LETTER HA
|
||||
0xC9 0x0438 # CYRILLIC SMALL LETTER I
|
||||
0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I
|
||||
0xCB 0x043A # CYRILLIC SMALL LETTER KA
|
||||
0xCC 0x043B # CYRILLIC SMALL LETTER EL
|
||||
0xCD 0x043C # CYRILLIC SMALL LETTER EM
|
||||
0xCE 0x043D # CYRILLIC SMALL LETTER EN
|
||||
0xCF 0x043E # CYRILLIC SMALL LETTER O
|
||||
0xD0 0x043F # CYRILLIC SMALL LETTER PE
|
||||
0xD1 0x044F # CYRILLIC SMALL LETTER YA
|
||||
0xD2 0x0440 # CYRILLIC SMALL LETTER ER
|
||||
0xD3 0x0441 # CYRILLIC SMALL LETTER ES
|
||||
0xD4 0x0442 # CYRILLIC SMALL LETTER TE
|
||||
0xD5 0x0443 # CYRILLIC SMALL LETTER U
|
||||
0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE
|
||||
0xD7 0x0432 # CYRILLIC SMALL LETTER VE
|
||||
0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0xD9 0x044B # CYRILLIC SMALL LETTER YERU
|
||||
0xDA 0x0437 # CYRILLIC SMALL LETTER ZE
|
||||
0xDB 0x0448 # CYRILLIC SMALL LETTER SHA
|
||||
0xDC 0x044D # CYRILLIC SMALL LETTER E
|
||||
0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA
|
||||
0xDE 0x0447 # CYRILLIC SMALL LETTER CHE
|
||||
0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN
|
||||
0xE0 0x042E # CYRILLIC CAPITAL LETTER YU
|
||||
0xE1 0x0410 # CYRILLIC CAPITAL LETTER A
|
||||
0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE
|
||||
0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE
|
||||
0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE
|
||||
0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE
|
||||
0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF
|
||||
0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE
|
||||
0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA
|
||||
0xE9 0x0418 # CYRILLIC CAPITAL LETTER I
|
||||
0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
|
||||
0xEB 0x041A # CYRILLIC CAPITAL LETTER KA
|
||||
0xEC 0x041B # CYRILLIC CAPITAL LETTER EL
|
||||
0xED 0x041C # CYRILLIC CAPITAL LETTER EM
|
||||
0xEE 0x041D # CYRILLIC CAPITAL LETTER EN
|
||||
0xEF 0x041E # CYRILLIC CAPITAL LETTER O
|
||||
0xF0 0x041F # CYRILLIC CAPITAL LETTER PE
|
||||
0xF1 0x042F # CYRILLIC CAPITAL LETTER YA
|
||||
0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER
|
||||
0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES
|
||||
0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE
|
||||
0xF5 0x0423 # CYRILLIC CAPITAL LETTER U
|
||||
0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE
|
||||
0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE
|
||||
0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU
|
||||
0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE
|
||||
0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA
|
||||
0xFC 0x042D # CYRILLIC CAPITAL LETTER E
|
||||
0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
|
||||
0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE
|
||||
0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
284
third_party/python/Tools/unicode/python-mappings/TIS-620.TXT
vendored
Normal file
284
third_party/python/Tools/unicode/python-mappings/TIS-620.TXT
vendored
Normal file
|
|
@ -0,0 +1,284 @@
|
|||
#
|
||||
# Name: TIS-620
|
||||
# Unicode version: 3.2
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 2005-10-25
|
||||
# Authors: Marc-Andre Lemburg <mal@egenix.com>
|
||||
#
|
||||
# According to
|
||||
# ftp://ftp.unicode.org/Public/MAPPINGS/ISO8859/8859-11.TXT the
|
||||
# TIS-620 is the identical to ISO_8859-11 with the 0xA0
|
||||
# (no-break space) mapping removed.
|
||||
#
|
||||
# (c) Copyright Marc-Andre Lemburg, 2005.
|
||||
# Licensed to PSF under a Contributor Agreement.
|
||||
#
|
||||
# Based on the file
|
||||
# ftp://ftp.unicode.org/Public/MAPPINGS/ISO8859/8859-11.TXT
|
||||
# which is:
|
||||
#
|
||||
# Copyright (c) 2002 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
#0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x0E01 # THAI CHARACTER KO KAI
|
||||
0xA2 0x0E02 # THAI CHARACTER KHO KHAI
|
||||
0xA3 0x0E03 # THAI CHARACTER KHO KHUAT
|
||||
0xA4 0x0E04 # THAI CHARACTER KHO KHWAI
|
||||
0xA5 0x0E05 # THAI CHARACTER KHO KHON
|
||||
0xA6 0x0E06 # THAI CHARACTER KHO RAKHANG
|
||||
0xA7 0x0E07 # THAI CHARACTER NGO NGU
|
||||
0xA8 0x0E08 # THAI CHARACTER CHO CHAN
|
||||
0xA9 0x0E09 # THAI CHARACTER CHO CHING
|
||||
0xAA 0x0E0A # THAI CHARACTER CHO CHANG
|
||||
0xAB 0x0E0B # THAI CHARACTER SO SO
|
||||
0xAC 0x0E0C # THAI CHARACTER CHO CHOE
|
||||
0xAD 0x0E0D # THAI CHARACTER YO YING
|
||||
0xAE 0x0E0E # THAI CHARACTER DO CHADA
|
||||
0xAF 0x0E0F # THAI CHARACTER TO PATAK
|
||||
0xB0 0x0E10 # THAI CHARACTER THO THAN
|
||||
0xB1 0x0E11 # THAI CHARACTER THO NANGMONTHO
|
||||
0xB2 0x0E12 # THAI CHARACTER THO PHUTHAO
|
||||
0xB3 0x0E13 # THAI CHARACTER NO NEN
|
||||
0xB4 0x0E14 # THAI CHARACTER DO DEK
|
||||
0xB5 0x0E15 # THAI CHARACTER TO TAO
|
||||
0xB6 0x0E16 # THAI CHARACTER THO THUNG
|
||||
0xB7 0x0E17 # THAI CHARACTER THO THAHAN
|
||||
0xB8 0x0E18 # THAI CHARACTER THO THONG
|
||||
0xB9 0x0E19 # THAI CHARACTER NO NU
|
||||
0xBA 0x0E1A # THAI CHARACTER BO BAIMAI
|
||||
0xBB 0x0E1B # THAI CHARACTER PO PLA
|
||||
0xBC 0x0E1C # THAI CHARACTER PHO PHUNG
|
||||
0xBD 0x0E1D # THAI CHARACTER FO FA
|
||||
0xBE 0x0E1E # THAI CHARACTER PHO PHAN
|
||||
0xBF 0x0E1F # THAI CHARACTER FO FAN
|
||||
0xC0 0x0E20 # THAI CHARACTER PHO SAMPHAO
|
||||
0xC1 0x0E21 # THAI CHARACTER MO MA
|
||||
0xC2 0x0E22 # THAI CHARACTER YO YAK
|
||||
0xC3 0x0E23 # THAI CHARACTER RO RUA
|
||||
0xC4 0x0E24 # THAI CHARACTER RU
|
||||
0xC5 0x0E25 # THAI CHARACTER LO LING
|
||||
0xC6 0x0E26 # THAI CHARACTER LU
|
||||
0xC7 0x0E27 # THAI CHARACTER WO WAEN
|
||||
0xC8 0x0E28 # THAI CHARACTER SO SALA
|
||||
0xC9 0x0E29 # THAI CHARACTER SO RUSI
|
||||
0xCA 0x0E2A # THAI CHARACTER SO SUA
|
||||
0xCB 0x0E2B # THAI CHARACTER HO HIP
|
||||
0xCC 0x0E2C # THAI CHARACTER LO CHULA
|
||||
0xCD 0x0E2D # THAI CHARACTER O ANG
|
||||
0xCE 0x0E2E # THAI CHARACTER HO NOKHUK
|
||||
0xCF 0x0E2F # THAI CHARACTER PAIYANNOI
|
||||
0xD0 0x0E30 # THAI CHARACTER SARA A
|
||||
0xD1 0x0E31 # THAI CHARACTER MAI HAN-AKAT
|
||||
0xD2 0x0E32 # THAI CHARACTER SARA AA
|
||||
0xD3 0x0E33 # THAI CHARACTER SARA AM
|
||||
0xD4 0x0E34 # THAI CHARACTER SARA I
|
||||
0xD5 0x0E35 # THAI CHARACTER SARA II
|
||||
0xD6 0x0E36 # THAI CHARACTER SARA UE
|
||||
0xD7 0x0E37 # THAI CHARACTER SARA UEE
|
||||
0xD8 0x0E38 # THAI CHARACTER SARA U
|
||||
0xD9 0x0E39 # THAI CHARACTER SARA UU
|
||||
0xDA 0x0E3A # THAI CHARACTER PHINTHU
|
||||
0xDF 0x0E3F # THAI CURRENCY SYMBOL BAHT
|
||||
0xE0 0x0E40 # THAI CHARACTER SARA E
|
||||
0xE1 0x0E41 # THAI CHARACTER SARA AE
|
||||
0xE2 0x0E42 # THAI CHARACTER SARA O
|
||||
0xE3 0x0E43 # THAI CHARACTER SARA AI MAIMUAN
|
||||
0xE4 0x0E44 # THAI CHARACTER SARA AI MAIMALAI
|
||||
0xE5 0x0E45 # THAI CHARACTER LAKKHANGYAO
|
||||
0xE6 0x0E46 # THAI CHARACTER MAIYAMOK
|
||||
0xE7 0x0E47 # THAI CHARACTER MAITAIKHU
|
||||
0xE8 0x0E48 # THAI CHARACTER MAI EK
|
||||
0xE9 0x0E49 # THAI CHARACTER MAI THO
|
||||
0xEA 0x0E4A # THAI CHARACTER MAI TRI
|
||||
0xEB 0x0E4B # THAI CHARACTER MAI CHATTAWA
|
||||
0xEC 0x0E4C # THAI CHARACTER THANTHAKHAT
|
||||
0xED 0x0E4D # THAI CHARACTER NIKHAHIT
|
||||
0xEE 0x0E4E # THAI CHARACTER YAMAKKAN
|
||||
0xEF 0x0E4F # THAI CHARACTER FONGMAN
|
||||
0xF0 0x0E50 # THAI DIGIT ZERO
|
||||
0xF1 0x0E51 # THAI DIGIT ONE
|
||||
0xF2 0x0E52 # THAI DIGIT TWO
|
||||
0xF3 0x0E53 # THAI DIGIT THREE
|
||||
0xF4 0x0E54 # THAI DIGIT FOUR
|
||||
0xF5 0x0E55 # THAI DIGIT FIVE
|
||||
0xF6 0x0E56 # THAI DIGIT SIX
|
||||
0xF7 0x0E57 # THAI DIGIT SEVEN
|
||||
0xF8 0x0E58 # THAI DIGIT EIGHT
|
||||
0xF9 0x0E59 # THAI DIGIT NINE
|
||||
0xFA 0x0E5A # THAI CHARACTER ANGKHANKHU
|
||||
0xFB 0x0E5B # THAI CHARACTER KHOMUT
|
||||
Loading…
Add table
Add a link
Reference in a new issue