iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 09:21:37 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

add tests for French apostrophe tokenization

Browse Source
This commit is contained in:
Robyn Speer 2016-12-05 18:42:16 -05:00
parent 596368ac6e
commit ff5a8f2a65
1 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
tests/test_french.py Normal file
View File

@ -0,0 +1,19 @@
from nose.tools import eq_, assert_almost_equal
from wordfreq import tokenize, word_frequency
def test_apostrophes():
for lang in ('fr', 'ca', 'oc'):
eq_(tokenize("langues d'oïl", lang),
['langues', "d", 'oïl'])
eq_(tokenize("langues d'oïl", lang, include_punctuation=True),
['langues', "d'", 'oïl'])
eq_(tokenize("l'heure", lang),
['l', 'heure'])
eq_(tokenize("l'heure", lang, include_punctuation=True),
["l'", 'heure'])
eq_(tokenize("L'Hôpital", lang, include_punctuation=True),
["l'", 'hôpital'])
eq_(tokenize("This isn't French", lang),
['this', "isn't", 'french'])