mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +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]
67 lines
2.0 KiB
Python
67 lines
2.0 KiB
Python
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["ca.", "m.a.o.", "Jan.", "Dec.", "kr.", "jf."])
|
|
def test_da_tokenizer_handles_abbr(da_tokenizer, text):
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["Jul.", "jul.", "Tor.", "Tors."])
|
|
def test_da_tokenizer_handles_ambiguous_abbr(da_tokenizer, text):
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 2
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["1.", "10.", "31."])
|
|
def test_da_tokenizer_handles_dates(da_tokenizer, text):
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
|
|
|
|
def test_da_tokenizer_handles_exc_in_text(da_tokenizer):
|
|
text = "Det er bl.a. ikke meningen"
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 5
|
|
assert tokens[2].text == "bl.a."
|
|
|
|
|
|
def test_da_tokenizer_handles_custom_base_exc(da_tokenizer):
|
|
text = "Her er noget du kan kigge i."
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == 8
|
|
assert tokens[6].text == "i"
|
|
assert tokens[7].text == "."
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,norm", [("akvarium", "akvarie"), ("bedstemoder", "bedstemor")]
|
|
)
|
|
def test_da_tokenizer_norm_exceptions(da_tokenizer, text, norm):
|
|
tokens = da_tokenizer(text)
|
|
assert tokens[0].norm_ == norm
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,n_tokens",
|
|
[
|
|
("Godt og/eller skidt", 3),
|
|
("Kør 4 km/t på vejen", 5),
|
|
("Det blæser 12 m/s.", 5),
|
|
("Det blæser 12 m/sek. på havnen", 6),
|
|
("Windows 8/Windows 10", 5),
|
|
("Billeten virker til bus/tog/metro", 8),
|
|
("26/02/2019", 1),
|
|
("Kristiansen c/o Madsen", 3),
|
|
("Sprogteknologi a/s", 2),
|
|
("De boede i A/B Bellevue", 5),
|
|
("Rotorhastigheden er 3400 o/m.", 5),
|
|
("Jeg købte billet t/r.", 5),
|
|
("Murerarbejdsmand m/k søges", 3),
|
|
("Netværket kører over TCP/IP", 4),
|
|
],
|
|
)
|
|
def test_da_tokenizer_slash(da_tokenizer, text, n_tokens):
|
|
tokens = da_tokenizer(text)
|
|
assert len(tokens) == n_tokens
|