spaCy/spacy/tests/regression/test_issue615.py

32 lines
1.0 KiB
Python
Raw Normal View History

2017-01-10 21:24:10 +03:00
# coding: utf-8
2016-11-24 01:48:41 +03:00
from __future__ import unicode_literals
2017-01-10 21:24:10 +03:00
from ...matcher import Matcher
def test_issue615(en_tokenizer):
def merge_phrases(matcher, doc, i, matches):
"""Merge a phrase. We have to be careful here because we'll change the
token indices. To avoid problems, merge all the phrases once we're called
on the last match."""
if i != len(matches)-1:
return None
# Get Span objects
2017-05-22 14:54:20 +03:00
spans = [(ent_id, ent_id, doc[start : end]) for ent_id, start, end in matches]
for ent_id, label, span in spans:
span.merge('NNP' if label else span.root.tag_, span.text, doc.vocab.strings[label])
text = "The golf club is broken"
2017-05-22 14:54:20 +03:00
pattern = [{'ORTH': "golf"}, {'ORTH': "club"}]
label = "Sport_Equipment"
doc = en_tokenizer(text)
matcher = Matcher(doc.vocab)
2017-05-22 14:54:20 +03:00
matcher.add(label, merge_phrases, pattern)
2016-11-24 01:48:41 +03:00
match = matcher(doc)
entities = list(doc.ents)
assert entities != [] #assertion 1
assert entities[0].label != 0 #assertion 2