mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 20:09:18 +03:00
cf52510631
* Add Amharic to space * clean up * Add some PRON_LEMMA * add Tigrinya support * remove text_noun_chunks * Tigrinya Support * added some more details for ti * fix unit test * add amharic char range * changes from review * amharic and tigrinya share same unicode block * get rid of _amharic/_tigrinya in char_classes Co-authored-by: Josiah Solomon <jsolomon@meteorcomm.com>
55 lines
2.2 KiB
Python
55 lines
2.2 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.lang.ti.lex_attrs import like_num
|
|
|
|
|
|
def test_ti_tokenizer_handles_long_text(ti_tokenizer):
|
|
text = """ቻንስለር ጀርመን ኣንገላ መርከል ኣብታ ሃገር ቁጽሪ መትሓዝቲ ኮቪድ መዓልታዊ ክብረ መዝገብ ድሕሪ ምህራሙ- ጽኑዕ እገዳ ክግበር ጸዊዓ።
|
|
|
|
መርከል ሎሚ ንታሕታዋይ ባይቶ ሃገራ ክትገልጽ ከላ፡ ኣብ ወሳኒ ምዕራፍ ቃልሲ ኢና ዘለና-ዳሕራዋይ ማዕበል ካብቲ ቀዳማይ ክገድድ ይኽእል`ዩ ኢላ።
|
|
|
|
ትካል ምክልኻል ተላገብቲ ሕማማት ጀርመን፡ ኣብ ዝሓለፈ 24 ሰዓታት ኣብ ምልእቲ ጀርመር 590 ሰባት ብኮቪድ19 ምሟቶም ኣፍሊጡ`ሎ።
|
|
|
|
ቻንስለር ኣንጀላ መርከል ኣብ እዋን በዓላት ልደት ስድራቤታት ክተኣኻኸባ ዝፍቀደለን`ኳ እንተኾነ ድሕሪኡ ኣብ ዘሎ ግዜ ግን እቲ እገዳታት ክትግበር ትደሊ።"""
|
|
tokens = ti_tokenizer(text)
|
|
|
|
assert len(tokens) == 85
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,length",
|
|
[
|
|
("ቻንስለር ጀርመን ኣንገላ መርከል፧", 5),
|
|
("“ስድራቤታት፧”", 4),
|
|
("""ኣብ እዋን በዓላት ልደት ስድራቤታት ክተኣኻኸባ ዝፍቀደለን`ኳ እንተኾነ።""", 9),
|
|
("ብግምት 10ኪ.ሜ. ጎይዩ።", 6),
|
|
("ኣብ ዝሓለፈ 24 ሰዓታት...", 5),
|
|
],
|
|
)
|
|
def test_ti_tokenizer_handles_cnts(ti_tokenizer, text, length):
|
|
tokens = ti_tokenizer(text)
|
|
assert len(tokens) == length
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,match",
|
|
[
|
|
("10", True),
|
|
("1", True),
|
|
("10.000", True),
|
|
("1000", True),
|
|
("999,0", True),
|
|
("ሐደ", True),
|
|
("ክልተ", True),
|
|
("ትሪልዮን", True),
|
|
("ከልቢ", False),
|
|
(",", False),
|
|
("1/2", True),
|
|
],
|
|
)
|
|
def test_lex_attrs_like_number(ti_tokenizer, text, match):
|
|
tokens = ti_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
assert tokens[0].like_num == match |