aeba99ab0d9cf3967ef54f3a1c509c9d496ce4b3,spacy/tests/doc/test_span_merge.py,,test_spans_merge_tokens,#Any#,11

Before Change

    assert len(doc) == 4
    assert doc[0].head.text == "Angeles"
    assert doc[1].head.text == "start"
    doc.merge(0, len("Los Angeles"), tag="NNP", lemma="Los Angeles", ent_type="GPE")
    assert len(doc) == 3
    assert doc[0].text == "Los Angeles"
    assert doc[0].head.text == "start"

After Change

    text = "Los Angeles start."
    heads = [1, 1, 0, -1]
    tokens = en_tokenizer(text)
    doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads)
    assert len(doc) == 4
    assert doc[0].head.text == "Angeles"
    assert doc[1].head.text == "start"
    with doc.retokenize() as retokenizer:
        retokenizer.merge(doc[0 : 2], attrs={"tag":"NNP", "lemma":"Los Angeles", "ent_type":"GPE"})
    assert len(doc) == 3
    assert doc[0].text == "Los Angeles"
    assert doc[0].head.text == "start"
    assert doc[0].ent_type_ == "GPE"

Instances