Returns the best encoding scheme for the system, based on
locale.getpreferredencoding() and some further tweaks.
"""
- def yield_preferredencoding():
- try:
- pref = locale.getpreferredencoding()
- u'TEST'.encode(pref)
- except:
- pref = 'UTF-8'
- while True:
- yield pref
- return yield_preferredencoding().next()
+ try:
+ pref = locale.getpreferredencoding()
+ u'TEST'.encode(pref)
+ except:
+ pref = 'UTF-8'
+
+ return pref
def htmlentity_transform(matchobj):
elif char == ':':
return '_-' if restricted else ' -'
elif char in '\\/|*<>':
- return '-'
- if restricted and (char in '&\'' or char.isspace()):
+ return '_'
+ if restricted and (char in '!&\'' or char.isspace()):
+ return '_'
+ if restricted and ord(char) > 127:
return '_'
return char
result = u''.join(map(replace_insane, s))
- while '--' in result:
- result = result.replace('--', '-')
- return result.strip('-')
+ while '__' in result:
+ result = result.replace('__', '_')
+ result = result.strip('_')
+ # Common case of "Foreign band name - English song title"
+ if restricted and result.startswith('-_'):
+ result = result[2:]
+ if not result:
+ result = '_'
+ return result
def orderedSet(iterable):
""" Remove all duplicates from the input iterable """
class Trouble(Exception):
"""Trouble helper exception
-
+
This is an exception to be handled with
FileDownloader.trouble
"""