def test_phrase_matcher_deprecated(en_vocab):
matcher = PhraseMatcher(en_vocab)
matcher.add("TEST", [Doc(en_vocab, words=["helllo"])])
doc = Doc(en_vocab, words=["hello", "world"])
with pytest.warns(DeprecationWarning) as record:
for _ in matcher.pipe([doc]):
pass
assert record.list
assert "spaCy v3.0" in str(record.list[0].message)
def test_issue3410():
texts = ["Hello world", "This is a test"]
nlp = English()
matcher = Matcher(nlp.vocab)
phrasematcher = PhraseMatcher(nlp.vocab)
with pytest.deprecated_call():
docs = list(nlp.pipe(texts, n_threads=4))
with pytest.deprecated_call():
docs = list(nlp.tokenizer.pipe(texts, n_threads=4))
with pytest.deprecated_call():
list(matcher.pipe(docs, n_threads=4))
with pytest.deprecated_call():
list(phrasematcher.pipe(docs, n_threads=4))
def test_issue3410():
texts = ["Hello world", "This is a test"]
nlp = English()
matcher = Matcher(nlp.vocab)
phrasematcher = PhraseMatcher(nlp.vocab)
with pytest.deprecated_call():
docs = list(nlp.pipe(texts, n_threads=4))
with pytest.deprecated_call():
docs = list(nlp.tokenizer.pipe(texts, n_threads=4))
with pytest.deprecated_call():
list(matcher.pipe(docs, n_threads=4))
with pytest.deprecated_call():
list(phrasematcher.pipe(docs, n_threads=4))
def trim_segments(all_doc_per):
'''Assumes all_doc_per is a dictionary of person names and segments.
Returns a new dictionary of person names and trimmed segments.'''
matcher = PhraseMatcher(nlp.vocab)
patterns = [nlp.make_doc(name) for name in all_doc_per.keys()]
matcher.add('Name', None, *patterns)
all_segments = nlp.pipe(list(all_doc_per.values()), n_threads=4)
for doc_i, doc in enumerate(matcher.pipe(all_segments)):
matches = matcher(doc)
persons = [(doc[start:end], start) for matcher_id, start, end in matches]
if len(persons) == 0:
del all_doc_per[patterns[doc_i].text]
elif len(persons) == 1:
seg5 = doc.text
all_doc_per[patterns[doc_i].text] = seg5
else:
sentences = list(doc.sents)
persons_remove = [per for per in persons if per[1] > sentences[0].end]
if not persons_remove:
seg5 = doc.text
all_doc_per[patterns[doc_i].text] = seg5
else:
i = 1
sent = sentences[i]
while persons_remove[0][1] > sent.end:
i += 1
sent = sentences[i]
else:
seg5 = sentences[:i]
seg5 = ' '.join([s.text for s in seg5])
all_doc_per[patterns[doc_i].text] = seg5
return all_doc_per
