d8051e89ca9daeb047d40a113fa45ccecfd0f493,spacy/tests/doc/test_doc_spilt.py,,test_doc_split,#,11

Before Change

    text = "LosAngeles start."
    heads = [1, 1, 0]
    tokens = en_tokenizer(text)
    doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads)

    assert len(doc) == 3
    assert len(str(doc)) == 19

After Change

def test_doc_split(en_vocab):
    words = ["LosAngeles", "start", "."]
    heads = [1, 1, 0]
    doc = get_doc(en_vocab, words=words, heads=heads)
    assert len(doc) == 3
    assert len(str(doc)) == 19
    assert doc[0].head.text == "start"
    assert doc[1].head.text == "."

Instances