1
0
mirror of https://github.com/moparisthebest/SickRage synced 2024-12-25 09:18:50 -05:00
SickRage/lib/unidecode/__init__.py
echel0n 0d9fbc1ad7 Welcome to our SickBeard-TVRage Edition ...
This version of SickBeard uses both TVDB and TVRage to search and gather it's series data from allowing you to now have access to and download shows that you couldn't before because of being locked into only what TheTVDB had to offer.

Also this edition is based off the code we used in our XEM editon so it does come with scene numbering support as well as all the other features our XEM edition has to offer.

Please before using this with your existing database (sickbeard.db) please make a backup copy of it and delete any other database files such as cache.db and failed.db if present, we HIGHLY recommend starting out with no database files at all to make this a fresh start but the choice is at your own risk!

Enjoy!
2014-03-09 22:39:12 -07:00

64 lines
1.8 KiB
Python

# -*- 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'
"""
import warnings
from sys import version_info
Cache = {}
def unidecode(string):
"""Transliterate an Unicode object into an ASCII string
>>> unidecode(u"\u5317\u4EB0")
"Bei Jing "
"""
if version_info[0] < 3 and not isinstance(string, unicode):
warnings.warn( "Argument %r is not an unicode object. "
"Passing an encoded string will likely have "
"unexpected results." % (type(string),),
RuntimeWarning, 2)
retval = []
for char in string:
codepoint = ord(char)
if codepoint < 0x80: # Basic ASCII
retval.append(str(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)