explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-22 10:02:01 +03:00
Code Issues Packages Projects Releases Wiki Activity

black format

Browse Source
This commit is contained in:
sani 2023-05-08 01:04:03 +08:00
parent 82ce3cc3f0
commit c1b4b6d5c6
3 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/lang/ms/examples.py
View File

@ -11,8 +11,7 @@ sentences = [
"Berapa banyak pelajar yang akan menghadiri majlis perpisahan sekolah?",
"Pengeluaran makanan berasal dari beberapa lokasi termasuk Cameron Highlands, Johor Bahru, dan Kuching.",
"Syarikat XYZ telah menghasilkan 20,000 unit produk baharu dalam setahun terakhir",
"Kuala Lumpur merupakan ibu negara Malaysia."
"Kau berada di mana semalam?",
"Kuala Lumpur merupakan ibu negara Malaysia." "Kau berada di mana semalam?",
"Siapa yang akan memimpin projek itu?",
"Siapa perdana menteri Malaysia sekarang?",
]

2
spacy/lang/ms/lex_attrs.py
View File

@ -30,7 +30,7 @@ _num_words = [
"septilion",
"oktilion",
"nonilion",
"desilion"
"desilion",
]

4
spacy/tests/lang/ms/test_prefix_suffix_infix.py
View File

@ -1,5 +1,6 @@
import pytest
@pytest.mark.parametrize("text", ["(Ma'arif)"])
def test_ms_tokenizer_splits_no_special(id_tokenizer, text):
tokens = id_tokenizer(text)
@ -61,7 +62,8 @@ def test_ms_tokenizer_splits_uneven_wrap_interact(id_tokenizer, text):
@pytest.mark.parametrize(
"text,length", [("kerana", 1), ("Mahathir-Anwar", 3), ("Tun Dr. Ismail-Abdul Rahman", 6)]
"text,length",
[("kerana", 1), ("Mahathir-Anwar", 3), ("Tun Dr. Ismail-Abdul Rahman", 6)],
)
def test_my_tokenizer_splits_hyphens(ms_tokenizer, text, length):
tokens = ms_tokenizer(text)