mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 18:36:36 +03:00
b6e991440c
* Auto-format tests with black * Add flake8 config * Tidy up and remove unused imports * Fix redefinitions of test functions * Replace orths_and_spaces with words and spaces * Fix compatibility with pytest 4.0 * xfail test for now Test was previously overwritten by following test due to naming conflict, so failure wasn't reported * Unfail passing test * Only use fixture via arguments Fixes pytest 4.0 compatibility
18 lines
591 B
Python
18 lines
591 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from spacy.matcher import Matcher
|
|
from spacy.tokens import Span
|
|
|
|
|
|
def test_issue2569(en_tokenizer):
|
|
doc = en_tokenizer("It is May 15, 1993.")
|
|
doc.ents = [Span(doc, 2, 6, label=doc.vocab.strings["DATE"])]
|
|
matcher = Matcher(doc.vocab)
|
|
matcher.add("RULE", None, [{"ENT_TYPE": "DATE", "OP": "+"}])
|
|
matched = [doc[start:end] for _, start, end in matcher(doc)]
|
|
matched = sorted(matched, key=len, reverse=True)
|
|
assert len(matched) == 10
|
|
assert len(matched[0]) == 4
|
|
assert matched[0].text == "May 15, 1993"
|