iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-24 18:01:38 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

changed mecab_tokenize to a global variable

Browse Source 
Former-commit-id: 5fc448bc60
This commit is contained in:
Joshua Chin 2015-06-25 13:58:30 -04:00
parent d372f29757
commit 6765bead18
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
wordfreq/__init__.py
View File

@ -124,7 +124,7 @@ def simple_tokenize(text):
"""
return [token.lower() for token in TOKEN_RE.findall(text)]
mecab_tokenize = None
def tokenize(text, lang):
"""
Tokenize this text in a way that's straightforward but appropriate for
@ -138,11 +138,10 @@ def tokenize(text, lang):
first, so that they can be expected to match the data.
"""
if lang == 'ja':
try:
return mecab_tokenize(text)
except NameError:
global mecab_tokenize
if mecab_tokenize is None:
from wordfreq.mecab import mecab_tokenize
return mecab_tokenize(text)
return mecab_tokenize(text)
elif lang == 'ar':
tokens = simple_tokenize(text)
tokens = [token.replace('ـ', '') for token in tokens] # remove arabic commas