def test_has_annotation(en_vocab):
doc = Doc(en_vocab, words=["Hello", "world"])
attrs = ("TAG", "POS", "MORPH", "LEMMA", "DEP", "HEAD", "ENT_IOB", "ENT_TYPE")
for attr in attrs:
assert not doc.has_annotation(attr)
assert not doc.has_annotation(attr, require_complete=True)
doc[0].tag_ = "A"
doc[0].pos_ = "X"
doc[0].set_morph("Feat=Val")
doc[0].lemma_ = "a"
doc[0].dep_ = "dep"
doc[0].head = doc[1]
doc.set_ents([Span(doc, 0, 1, label="HELLO")], default="missing")
for attr in attrs:
assert doc.has_annotation(attr)
assert not doc.has_annotation(attr, require_complete=True)
doc[1].tag_ = "A"
doc[1].pos_ = "X"
doc[1].set_morph("")
doc[1].lemma_ = "a"
doc[1].dep_ = "dep"
doc.ents = [Span(doc, 0, 2, label="HELLO")]
for attr in attrs:
assert doc.has_annotation(attr)
assert doc.has_annotation(attr, require_complete=True)
def __call__(self, doc: Doc) -> Doc:
ents = [
Span(doc, start=s, end=e, label="CUSTOM")
for _, s, e in self.matcher(doc)
]
ents = filter_spans(ents)
doc.set_ents(ents)
return doc