mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-10 19:57:17 +03:00
Add tests for displaCy and util functions and fix util typo
This commit is contained in:
parent
c5714d4fb2
commit
df920ba0e7
|
@ -1,7 +1,10 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from ..util import ensure_path
|
||||
from .. import util
|
||||
from ..displacy import parse_deps, parse_ents
|
||||
from ..tokens import Span
|
||||
from .util import get_doc
|
||||
|
||||
from pathlib import Path
|
||||
import pytest
|
||||
|
@ -9,5 +12,46 @@ import pytest
|
|||
|
||||
@pytest.mark.parametrize('text', ['hello/world', 'hello world'])
|
||||
def test_util_ensure_path_succeeds(text):
|
||||
path = ensure_path(text)
|
||||
path = util.ensure_path(text)
|
||||
assert isinstance(path, Path)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('package', ['thinc'])
|
||||
def test_util_is_package(package):
|
||||
"""Test that an installed package via pip is recognised by util.is_package."""
|
||||
assert util.is_package(package)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('package', ['thinc'])
|
||||
def test_util_get_package_path(package):
|
||||
"""Test that a Path object is returned for a package name."""
|
||||
path = util.get_package_path(package)
|
||||
assert isinstance(path, Path)
|
||||
|
||||
|
||||
def test_displacy_parse_ents(en_vocab):
|
||||
"""Test that named entities on a Doc are converted into displaCy's format."""
|
||||
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
|
||||
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings[u'ORG'])]
|
||||
ents = parse_ents(doc)
|
||||
assert isinstance(ents, dict)
|
||||
assert ents['text'] == 'But Google is starting from behind '
|
||||
assert ents['ents'] == [{'start': 4, 'end': 10, 'label': 'ORG'}]
|
||||
|
||||
|
||||
def test_displacy_parse_deps(en_vocab):
|
||||
"""Test that deps and tags on a Doc are converted into displaCy's format."""
|
||||
words = ["This", "is", "a", "sentence"]
|
||||
heads = [1, 0, 1, -2]
|
||||
tags = ['DT', 'VBZ', 'DT', 'NN']
|
||||
deps = ['nsubj', 'ROOT', 'det', 'attr']
|
||||
doc = get_doc(en_vocab, words=words, heads=heads, tags=tags, deps=deps)
|
||||
deps = parse_deps(doc)
|
||||
assert isinstance(deps, dict)
|
||||
assert deps['words'] == [{'text': 'This', 'tag': 'DT'},
|
||||
{'text': 'is', 'tag': 'VBZ'},
|
||||
{'text': 'a', 'tag': 'DT'},
|
||||
{'text': 'sentence', 'tag': 'NN'}]
|
||||
assert deps['arcs'] == [{'start': 0, 'end': 1, 'label': 'nsubj', 'dir': 'left'},
|
||||
{'start': 2, 'end': 3, 'label': 'det', 'dir': 'left'},
|
||||
{'start': 1, 'end': 3, 'label': 'attr', 'dir': 'right'}]
|
||||
|
|
|
@ -179,7 +179,7 @@ def get_package_path(name):
|
|||
"""
|
||||
# Here we're importing the module just to find it. This is worryingly
|
||||
# indirect, but it's otherwise very difficult to find the package.
|
||||
pkg = importlib.import_module(package_name)
|
||||
pkg = importlib.import_module(name)
|
||||
return Path(pkg.__file__).parent
|
||||
|
||||
|
||||
|
|
Loading…
Reference in New Issue
Block a user