Skip to content

Add test case for deprecated delete_tone() #393

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 1 commit into from
May 9, 2020
Merged

Add test case for deprecated delete_tone() #393

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 3 additions & 4 deletions pythainlp/util/normalize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -204,6 +204,8 @@ def normalize(text: str) -> str:
If a user wants to customize the selection or the order of rules
to be applied, they can choose to call those functions by themselves.

Note: for Unicode normalization, see unicodedata.normalize().

:param str text: input text
:return: normalized text according to the fules
:rtype: str
Expand All @@ -213,10 +215,7 @@ def normalize(text: str) -> str:

from pythainlp.util import normalize

normalize('สระะน้ำ')
# output: สระน้ำ

normalize('เเปลก')
normalize('เเปลก') # starts with two Sara E
# output: แปลก

normalize('นานาาา')
Expand Down
32 changes: 17 additions & 15 deletions tests/test_util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
bahttext,
collate,
countthai,
delete_tone,
dict_trie,
digit_to_text,
eng_to_thai,
Expand Down Expand Up @@ -278,38 +279,38 @@ def test_trie(self):
def test_normalize(self):
self.assertIsNotNone(normalize("พรรค์จันทร์ab์"))

# sara e + sara e
# normalize sara e + sara e
self.assertEqual(normalize("เเปลก"), "แปลก")

# consonant + follow vowel + tone mark
self.assertEqual(normalize("\u0e01\u0e30\u0e48"), "\u0e01\u0e48\u0e30")

# consonant + nikhahit + sara aa
# normalize consonant + nikhahit + sara aa
self.assertEqual(normalize("นํา"), "นำ")
self.assertEqual(normalize("\u0e01\u0e4d\u0e32"), "\u0e01\u0e33")

# consonant + nikhahit + tone mark + sara aa
# normalize consonant + tone mark + nikhahit + sara aa
self.assertEqual(
normalize("\u0e01\u0e4d\u0e48\u0e32"), "\u0e01\u0e48\u0e33"
normalize("\u0e01\u0e48\u0e4d\u0e32"), "\u0e01\u0e48\u0e33"
)

# consonant + tone mark + nikhahit + sara aa
# reorder consonant + follow vowel + tone mark
self.assertEqual(normalize("\u0e01\u0e30\u0e48"), "\u0e01\u0e48\u0e30")

# reorder consonant + nikhahit + tone mark + sara aa
self.assertEqual(
normalize("\u0e01\u0e48\u0e4d\u0e32"), "\u0e01\u0e48\u0e33"
normalize("\u0e01\u0e4d\u0e48\u0e32"), "\u0e01\u0e48\u0e33"
)

# consonant + follow vowel + tone mark
# reorder consonant + follow vowel + tone mark
self.assertEqual(normalize("\u0e01\u0e32\u0e48"), "\u0e01\u0e48\u0e32")

# repeating following vowels
# remove repeating following vowels
self.assertEqual(normalize("กาา"), "กา")
self.assertEqual(normalize("กา า า า"), "กา")
self.assertEqual(normalize("กา าาะา"), "กาะา")

# repeating tone marks
# remove epeating tone marks
self.assertEqual(normalize("\u0e01\u0e48\u0e48"), "\u0e01\u0e48")

# repeating different ton emarks
# remove repeating different ton emarks
self.assertEqual(normalize("\u0e01\u0e48\u0e49"), "\u0e01\u0e49")
self.assertEqual(
normalize("\u0e01\u0e48\u0e49\u0e48\u0e49"), "\u0e01\u0e49"
Expand All @@ -325,11 +326,12 @@ def test_normalize(self):
self.assertEqual(remove_dup_spaces(" ab c d "), "ab c d")
self.assertEqual(remove_dup_spaces("\nab c \n d \n"), "ab c\nd")

# removing tone marks
# remove tone marks
self.assertEqual(remove_tonemark("จิ้น"), "จิน")
self.assertEqual(remove_tonemark("เก๋า"), "เกา")
self.assertEqual(delete_tone("เจ๋งเป้ง"), remove_tonemark("เจ๋งเป้ง"))

# removing zero width chars
# remove zero width chars
self.assertEqual(remove_zw("กา\u200b"), "กา")
self.assertEqual(remove_zw("ก\u200cา"), "กา")
self.assertEqual(remove_zw("\u200bกา"), "กา")
Expand Down