# coding: utf-8 from __future__ import unicode_literals import pytest from spacy import displacy from spacy.tokens import Span from .util import get_doc 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["ORG"])] ents = displacy.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] pos = ["DET", "VERB", "DET", "NOUN"] tags = ["DT", "VBZ", "DT", "NN"] deps = ["nsubj", "ROOT", "det", "attr"] doc = get_doc(en_vocab, words=words, heads=heads, pos=pos, tags=tags, deps=deps) deps = displacy.parse_deps(doc) assert isinstance(deps, dict) assert deps["words"] == [ {"text": "This", "tag": "DET"}, {"text": "is", "tag": "VERB"}, {"text": "a", "tag": "DET"}, {"text": "sentence", "tag": "NOUN"}, ] 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"}, ] def test_displacy_spans(en_vocab): """Test that displaCy can render Spans.""" doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"]) doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings["ORG"])] html = displacy.render(doc[1:4], style="ent") assert html.startswith("TEST") def test_displacy_raises_for_wrong_type(en_vocab): with pytest.raises(ValueError): displacy.render("hello world")