465e3da40350f30c2ef965b72531fb33666fa388,tests/test_extract.py,,test_pos_regex_matches,#Any#,282

Before Change

def test_pos_regex_matches(spacy_doc):
    expected = [
        "Two weeks",
        "Kuwait",
        "an I.M.F. seminar",
        "Arab educators",
        "30 minutes",
        "the impact",
        "technology trends",
        "education",
        "the Middle East",
        "an Egyptian education official",
        "his hand",
        "a personal question",
        "Donald Trump",
        "mosques",
        "the United States",
        "great sorrow",
        "that what",
        "our kids",
    ]
    observed = [
        span.text
        for span in extract.pos_regex_matches(
            spacy_doc, constants.POS_REGEX_PATTERNS["en"]["NP"]

After Change

def test_pos_regex_matches(spacy_doc):
    pattern = constants.POS_REGEX_PATTERNS["en"]["NP"]
    valid_pos = set(re.findall(r"(\w+)", pattern))
    required_pos = {"NOUN", "PROPN"}
    result = list(extract.pos_regex_matches(spacy_doc, pattern))
    assert all(isinstance(span, SpacySpan) for span in result)
    assert all(tok.pos_ in valid_pos for span in result for tok in span)

Instances