mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 01:48:04 +03:00
7d50804644
* Migrate regressions 1-1000 * Move serialize test to correct file * Remove tests that won't work in v3 * Migrate regressions 1000-1500 Removed regression test 1250 because v3 doesn't support the old LEX scheme anymore. * Add missing imports in serializer tests * Migrate tests 1500-2000 * Migrate regressions from 2000-2500 * Migrate regressions from 2501-3000 * Migrate regressions from 3000-3501 * Migrate regressions from 3501-4000 * Migrate regressions from 4001-4500 * Migrate regressions from 4501-5000 * Migrate regressions from 5001-5501 * Migrate regressions from 5501 to 7000 * Migrate regressions from 7001 to 8000 * Migrate remaining regression tests * Fixing missing imports * Update docs with new system [ci skip] * Update CONTRIBUTING.md - Fix formatting - Update wording * Remove lemmatizer tests in el lang * Move a few tests into the general tokenizer * Separate Doc and DocBin tests
15 lines
411 B
Python
15 lines
411 B
Python
import pytest
|
|
|
|
|
|
@pytest.mark.issue(2822)
|
|
def test_issue2822(it_tokenizer):
|
|
"""Test that the abbreviation of poco is kept as one word."""
|
|
doc = it_tokenizer("Vuoi un po' di zucchero?")
|
|
assert len(doc) == 6
|
|
assert doc[0].text == "Vuoi"
|
|
assert doc[1].text == "un"
|
|
assert doc[2].text == "po'"
|
|
assert doc[3].text == "di"
|
|
assert doc[4].text == "zucchero"
|
|
assert doc[5].text == "?"
|