blob: 1b045394c33cd0d608f0ca6ebe54cde8f091fc9f (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
|
# -*- coding: utf-8 -*-
"""Transliterate Unicode text into plain 7-bit ASCII.
Example usage:
>>> from unidecode import unidecode:
>>> unidecode(u"\u5317\u4EB0")
"Bei Jing "
The transliteration uses a straightforward map, and doesn't have alternatives
for the same character based on language, position, or anything else.
In Python 3, a standard string object will be returned. If you need bytes, use:
>>> unidecode("Κνωσός").encode("ascii")
b'Knosos'
"""
Cache = {}
def unidecode(string):
"""Transliterate an Unicode object into an ASCII string
>>> unidecode(u"\u5317\u4EB0")
"Bei Jing "
"""
retval = []
for char in string:
codepoint = ord(char)
if codepoint < 0x80: # Basic ASCII
retval.append(char)
continue
if codepoint > 0xeffff:
continue # Characters in Private Use Area and above are ignored
section = codepoint >> 8 # Chop off the last two hex digits
position = codepoint % 256 # Last two hex digits
try:
table = Cache[section]
except KeyError:
try:
mod = __import__('unidecode.x%03x'%(section), [], [], ['data'])
except ImportError:
Cache[section] = None
continue # No match: ignore this character and carry on.
Cache[section] = table = mod.data
if table and len(table) > position:
retval.append( table[position] )
return ''.join(retval)
|