spaCy/spacy/tests/lang/en/test_sbd.py
Lj Miranda 7d50804644
Migrate regression tests into the main test suite (#9655)
* 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
2021-12-04 20:34:48 +01:00

46 lines
1.7 KiB
Python

import pytest
from spacy.tokens import Doc
from ...util import apply_transition_sequence
@pytest.mark.issue(309)
def test_issue309(en_vocab):
"""Test Issue #309: SBD fails on empty string"""
doc = Doc(en_vocab, words=[" "], heads=[0], deps=["ROOT"])
assert len(doc) == 1
sents = list(doc.sents)
assert len(sents) == 1
@pytest.mark.parametrize("words", [["A", "test", "sentence"]])
@pytest.mark.parametrize("punct", [".", "!", "?", ""])
def test_en_sbd_single_punct(en_vocab, words, punct):
heads = [2, 2, 2, 2] if punct else [2, 2, 2]
deps = ["dep"] * len(heads)
words = [*words, punct] if punct else words
doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
assert len(doc) == 4 if punct else 3
assert len(list(doc.sents)) == 1
assert sum(len(sent) for sent in doc.sents) == len(doc)
@pytest.mark.skip(
reason="The step_through API was removed (but should be brought back)"
)
def test_en_sentence_breaks(en_vocab, en_parser):
# fmt: off
words = ["This", "is", "a", "sentence", ".", "This", "is", "another", "one", "."]
heads = [1, 1, 3, 1, 1, 6, 6, 8, 6, 6]
deps = ["nsubj", "ROOT", "det", "attr", "punct", "nsubj", "ROOT", "det",
"attr", "punct"]
transition = ["L-nsubj", "S", "L-det", "R-attr", "D", "R-punct", "B-ROOT",
"L-nsubj", "S", "L-attr", "R-attr", "D", "R-punct"]
# fmt: on
doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
apply_transition_sequence(en_parser, doc, transition)
assert len(list(doc.sents)) == 2
for token in doc:
assert token.dep != 0 or token.is_space
assert [token.head.i for token in doc] == [1, 1, 3, 1, 1, 6, 6, 8, 6, 6]