iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 17:31:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

revert to using global mecab_tokenize variable

Browse Source 
Former-commit-id: 189a5b9cd6
This commit is contained in:
Joshua Chin 2015-07-07 15:47:37 -04:00
parent 4b398fac65
commit a72b4abb48
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
wordfreq/__init__.py
View File

@ -43,7 +43,7 @@ def simple_tokenize(text):
""" """
return [token.casefold() for token in TOKEN_RE.findall(text)] return [token.casefold() for token in TOKEN_RE.findall(text)]
mecab_tokenize = None
def tokenize(text, lang): def tokenize(text, lang):
""" """
Tokenize this text in a way that's straightforward but appropriate for Tokenize this text in a way that's straightforward but appropriate for
@ -57,7 +57,9 @@ def tokenize(text, lang):
first, so that they can be expected to match the data. first, so that they can be expected to match the data.
""" """
if lang == 'ja': if lang == 'ja':
from wordfreq.mecab import mecab_tokenize global mecab_tokenize
if mecab_tokenize is None:
from wordfreq.mecab import mecab_tokenize
return mecab_tokenize(text) return mecab_tokenize(text)
if lang == 'ar': if lang == 'ar':