mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 18:07:26 +03:00
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.tokens import Doc
|
|
from spacy.attrs import ORTH, SHAPE, POS, DEP
|
|
|
|
from ..util import get_doc
|
|
|
|
|
|
def test_doc_array_attr_of_token(en_vocab):
|
|
doc = Doc(en_vocab, words=["An", "example", "sentence"])
|
|
example = doc.vocab["example"]
|
|
assert example.orth != example.shape
|
|
feats_array = doc.to_array((ORTH, SHAPE))
|
|
assert feats_array[0][0] != feats_array[0][1]
|
|
assert feats_array[0][0] != feats_array[0][1]
|
|
|
|
|
|
def test_doc_stringy_array_attr_of_token(en_vocab):
|
|
doc = Doc(en_vocab, words=["An", "example", "sentence"])
|
|
example = doc.vocab["example"]
|
|
assert example.orth != example.shape
|
|
feats_array = doc.to_array((ORTH, SHAPE))
|
|
feats_array_stringy = doc.to_array(("ORTH", "SHAPE"))
|
|
assert feats_array_stringy[0][0] == feats_array[0][0]
|
|
assert feats_array_stringy[0][1] == feats_array[0][1]
|
|
|
|
|
|
def test_doc_scalar_attr_of_token(en_vocab):
|
|
doc = Doc(en_vocab, words=["An", "example", "sentence"])
|
|
example = doc.vocab["example"]
|
|
assert example.orth != example.shape
|
|
feats_array = doc.to_array(ORTH)
|
|
assert feats_array.shape == (3,)
|
|
|
|
|
|
def test_doc_array_tag(en_vocab):
|
|
words = ["A", "nice", "sentence", "."]
|
|
pos = ["DET", "ADJ", "NOUN", "PUNCT"]
|
|
doc = get_doc(en_vocab, words=words, pos=pos)
|
|
assert doc[0].pos != doc[1].pos != doc[2].pos != doc[3].pos
|
|
feats_array = doc.to_array((ORTH, POS))
|
|
assert feats_array[0][1] == doc[0].pos
|
|
assert feats_array[1][1] == doc[1].pos
|
|
assert feats_array[2][1] == doc[2].pos
|
|
assert feats_array[3][1] == doc[3].pos
|
|
|
|
|
|
def test_doc_array_dep(en_vocab):
|
|
words = ["A", "nice", "sentence", "."]
|
|
deps = ["det", "amod", "ROOT", "punct"]
|
|
doc = get_doc(en_vocab, words=words, deps=deps)
|
|
feats_array = doc.to_array((ORTH, DEP))
|
|
assert feats_array[0][1] == doc[0].dep
|
|
assert feats_array[1][1] == doc[1].dep
|
|
assert feats_array[2][1] == doc[2].dep
|
|
assert feats_array[3][1] == doc[3].dep
|
|
|
|
|
|
@pytest.mark.parametrize("attrs", [["ORTH", "SHAPE"], "IS_ALPHA"])
|
|
def test_doc_array_to_from_string_attrs(en_vocab, attrs):
|
|
"""Test that both Doc.to_array and Doc.from_array accept string attrs,
|
|
as well as single attrs and sequences of attrs.
|
|
"""
|
|
words = ["An", "example", "sentence"]
|
|
doc = Doc(en_vocab, words=words)
|
|
Doc(en_vocab, words=words).from_array(attrs, doc.to_array(attrs))
|