Skip to content

Commit 3921e66

Browse files
committed
Update words_th.txt : del ชิชิ
1 parent 69f2319 commit 3921e66

File tree

2 files changed

+7
-1
lines changed

2 files changed

+7
-1
lines changed

pythainlp/corpus/words_th.txt

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -15594,7 +15594,6 @@
1559415594
ชิงไหวชิงพริบ
1559515595
ชิงฮื้อ
1559615596
ชิชะ
15597-
ชิชิ
1559815597
ชิณณะ
1559915598
ชิด
1560015599
ชิดขวา

tests/test_tokenize.py

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -208,6 +208,13 @@ def test_word_tokenize_newmm(self):
208208
self.assertIsNotNone(
209209
word_tokenize(long_danger_text, engine="newmm-safe")
210210
)
211+
text = "ชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิชิ"
212+
self.assertIsNotNone(
213+
word_tokenize(text, engine="newmm")
214+
)
215+
self.assertIsNotNone(
216+
word_tokenize(text, engine="newmm-safe")
217+
)
211218

212219
def test_word_tokenize_attacut(self):
213220
self.assertEqual(attacut.segment(None), [])

0 commit comments

Comments
 (0)