mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
65 lines
1.8 KiB
Python
65 lines
1.8 KiB
Python
import pytest
|
|
from spacy.lang.en.lex_attrs import like_num
|
|
|
|
|
|
def test_en_tokenizer_handles_long_text(en_tokenizer):
|
|
text = """Tributes pour in for late British Labour Party leader
|
|
|
|
Tributes poured in from around the world Thursday
|
|
to the late Labour Party leader John Smith, who died earlier from a massive
|
|
heart attack aged 55.
|
|
|
|
In Washington, the US State Department issued a statement regretting "the
|
|
untimely death" of the rapier-tongued Scottish barrister and parliamentarian.
|
|
|
|
"Mr. Smith, throughout his distinguished"""
|
|
tokens = en_tokenizer(text)
|
|
assert len(tokens) == 76
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,length",
|
|
[
|
|
("The U.S. Army likes Shock and Awe.", 8),
|
|
("U.N. regulations are not a part of their concern.", 10),
|
|
("“Isn't it?”", 6),
|
|
("""Yes! "I'd rather have a walk", Ms. Comble sighed. """, 15),
|
|
("""'Me too!', Mr. P. Delaware cried. """, 11),
|
|
("They ran about 10km.", 6),
|
|
pytest.param(
|
|
"But then the 6,000-year ice age came...", 10, marks=pytest.mark.xfail()
|
|
),
|
|
],
|
|
)
|
|
def test_en_tokenizer_handles_cnts(en_tokenizer, text, length):
|
|
tokens = en_tokenizer(text)
|
|
assert len(tokens) == length
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,match",
|
|
[
|
|
("10", True),
|
|
("1", True),
|
|
("10,000", True),
|
|
("10,00", True),
|
|
("999.0", True),
|
|
("one", True),
|
|
("two", True),
|
|
("billion", True),
|
|
("dog", False),
|
|
(",", False),
|
|
("1/2", True),
|
|
],
|
|
)
|
|
def test_lex_attrs_like_number(en_tokenizer, text, match):
|
|
tokens = en_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
assert tokens[0].like_num == match
|
|
|
|
|
|
@pytest.mark.parametrize("word", ["eleven"])
|
|
def test_en_lex_attrs_capitals(word):
|
|
assert like_num(word)
|
|
assert like_num(word.upper())
|