Skip to content

Fix sent_tokenize(engine="whitespace") return value to be a list of string #957

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Nov 1, 2024
Merged

Fix sent_tokenize(engine="whitespace") return value to be a list of string #957

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
690fbc8
Fixed #954
wannaphong Nov 1, 2024
79278f3
Merge pull request #959 from PyThaiNLP/dev
bact Nov 1, 2024
3d1bd1a
Move more sent_tokenize test
bact Nov 1, 2024
f5bddb4
Merge pull request #961 from bact/mv-sent-tokenize-test
bact Nov 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pythainlp/tokenize/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -538,7 +538,7 @@ def sent_tokenize(
result = map_indices_to_words(word_indices, segments)
return result
else:
return [segments]
return segments


def paragraph_tokenize(
Expand Down
12 changes: 0 additions & 12 deletions tests/test_tokenize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,18 +225,6 @@ def test_sent_tokenize(self):
sent_tokenize("รักน้ำ รักปลา ", engine="whitespace+newline"),
["รักน้ำ", "รักปลา"],
)
self.assertEqual(
sent_tokenize(SENT_1),
SENT_1_TOKS,
)
self.assertEqual(
sent_tokenize(SENT_2),
SENT_2_TOKS,
)
self.assertEqual(
sent_tokenize(SENT_3),
SENT_3_TOKS,
)
self.assertIsNotNone(
sent_tokenize(
SENT_1,
Expand Down
32 changes: 17 additions & 15 deletions tests/testx_tokenize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,31 +92,35 @@ def testx_sent_tokenize(self):
# Use default engine (crfcut)
self.assertEqual(sent_tokenize(None), [])
self.assertEqual(sent_tokenize(""), [])

self.assertEqual(
sent_tokenize(SENT_1, engine="crfcut"),
sent_tokenize(SENT_1),
SENT_1_TOKS,
)
self.assertEqual(
sent_tokenize(SENT_2, engine="crfcut"),
sent_tokenize(SENT_2),
SENT_2_TOKS,
)
self.assertEqual(
sent_tokenize(SENT_3, engine="crfcut"),
sent_tokenize(SENT_3),
SENT_3_TOKS,
)

self.assertEqual(
sent_tokenize(SENT_1),
sent_tokenize(SENT_1, engine="crfcut"),
SENT_1_TOKS,
)
self.assertEqual(
sent_tokenize(SENT_2),
sent_tokenize(SENT_2, engine="crfcut"),
SENT_2_TOKS,
)
self.assertEqual(
sent_tokenize(SENT_3),
sent_tokenize(SENT_3, engine="crfcut"),
SENT_3_TOKS,
)
self.assertEqual(
sent_tokenize(SENT_4, engine="crfcut"),
[["ผม", "กิน", "ข้าว", " ", "\n", "เธอ", "เล่น", "เกม"]],
)
self.assertIsNotNone(
sent_tokenize(
SENT_1,
Expand All @@ -135,6 +139,7 @@ def testx_sent_tokenize(self):
engine="tltk",
),
)

self.assertIsNotNone(
sent_tokenize(
SENT_1,
Expand All @@ -153,6 +158,11 @@ def testx_sent_tokenize(self):
engine="thaisum",
),
)
self.assertEqual(
sent_tokenize(SENT_4, engine="thaisum"),
[["ผม", "กิน", "ข้าว", " ", "เธอ", "เล่น", "เกม"]],
)

self.assertIsNotNone(
sent_tokenize(
SENT_3,
Expand All @@ -177,14 +187,6 @@ def testx_sent_tokenize(self):
# engine="wtp-large",
# ),
# )
self.assertEqual(
sent_tokenize(SENT_4, engine="crfcut"),
[["ผม", "กิน", "ข้าว", " ", "\n", "เธอ", "เล่น", "เกม"]],
)
self.assertEqual(
sent_tokenize(SENT_4, engine="thaisum"),
[["ผม", "กิน", "ข้าว", " ", "เธอ", "เล่น", "เกม"]],
)

def testx_word_tokenize(self):
self.assertIsNotNone(word_tokenize(TEXT_1, engine="nlpo3"))
Expand Down
Loading