mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-23 20:39:20 +03:00
45 lines
1.3 KiB
Python
45 lines
1.3 KiB
Python
|
# coding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
import pytest
|
||
|
|
|
||
|
|
from ..util import get_doc
|
||
|
|
from ...language import Language
|
||
|
|
from ...tokens import Span
|
||
|
|
from ... import util
|
||
|
|
|
||
|
|
@pytest.fixture
|
||
|
|
def doc(en_tokenizer):
|
||
|
|
text = 'I like New York in Autumn.'
|
||
|
|
heads = [1, 0, 1, -2, -3, -1, -5]
|
||
|
|
tags = ['PRP', 'IN', 'NNP', 'NNP', 'IN', 'NNP', '.']
|
||
|
|
pos = ['PRON', 'VERB', 'PROPN', 'PROPN', 'ADP', 'PROPN', 'PUNCT']
|
||
|
|
deps = ['ROOT', 'prep', 'compound', 'pobj', 'prep', 'pobj', 'punct']
|
||
|
|
tokens = en_tokenizer(text)
|
||
|
|
doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads,
|
||
|
|
tags=tags, pos=pos, deps=deps)
|
||
|
|
doc.ents = [Span(doc, 2, 4, doc.vocab.strings['GPE'])]
|
||
|
|
doc.is_parsed = True
|
||
|
|
doc.is_tagged = True
|
||
|
|
return doc
|
||
|
|
|
||
|
|
|
||
|
|
def test_factories_merge_noun_chunks(doc):
|
||
|
|
assert len(doc) == 7
|
||
|
|
nlp = Language()
|
||
|
|
merge_noun_chunks = nlp.create_pipe('merge_noun_chunks')
|
||
|
|
merge_noun_chunks(doc)
|
||
|
|
assert len(doc) == 6
|
||
|
|
assert doc[2].text == 'New York'
|
||
|
|
|
||
|
|
|
||
|
|
def test_factories_merge_ents(doc):
|
||
|
|
assert len(doc) == 7
|
||
|
|
assert len(list(doc.ents)) == 1
|
||
|
|
nlp = Language()
|
||
|
|
merge_entities = nlp.create_pipe('merge_entities')
|
||
|
|
merge_entities(doc)
|
||
|
|
assert len(doc) == 6
|
||
|
|
assert len(list(doc.ents)) == 1
|
||
|
|
assert doc[2].text == 'New York'
|