mirror of
https://github.com/fxsjy/jieba.git
synced 2025-07-10 00:01:33 +08:00
32 lines
744 B
Python
32 lines
744 B
Python
# -*- coding: utf-8 -*-
|
|
import sys
|
|
|
|
PY2 = sys.version_info[0] == 2
|
|
|
|
default_encoding = sys.getfilesystemencoding()
|
|
|
|
if PY2:
|
|
text_type = unicode
|
|
string_types = (str, unicode)
|
|
|
|
iterkeys = lambda d: d.iterkeys()
|
|
itervalues = lambda d: d.itervalues()
|
|
iteritems = lambda d: d.iteritems()
|
|
|
|
else:
|
|
text_type = str
|
|
string_types = (str,)
|
|
xrange = range
|
|
|
|
iterkeys = lambda d: iter(d.keys())
|
|
itervalues = lambda d: iter(d.values())
|
|
iteritems = lambda d: iter(d.items())
|
|
|
|
def strdecode(sentence):
|
|
if not isinstance(sentence, text_type):
|
|
try:
|
|
sentence = sentence.decode('utf-8')
|
|
except UnicodeDecodeError:
|
|
sentence = sentence.decode('gbk', 'ignore')
|
|
return sentence
|