3252f2117a4b693ca001613b13c28cc2d8cd9eb7,tests/candidates/test_candidates.py,,test_mention_longest_match,#,508

Before Change

    PARALLEL = 1

    max_docs = 1
    session = Meta.init(CONN_STRING).Session()

    docs_path = "tests/data/pure_html/lincoln_short.html"

    // Parsing
    logger.info("Parsing...")
    doc_preprocessor = HTMLDocPreprocessor(docs_path, max_docs=max_docs)
    corpus_parser = Parser(session, structural=True, lingual=True)
    corpus_parser.apply(doc_preprocessor, parallelism=PARALLEL)
    docs = session.query(Document).order_by(Document.name).all()
    // Mention Extraction
    name_ngrams = MentionNgramsPart(n_max=3)
    place_ngrams = MentionNgramsTemp(n_max=4)

After Change

    assert len(mention_spans) == 23

    // Clear manually
    for mention in doc.places[:]:
        doc.places.remove(mention)

    birthplace_matcher = LambdaFunctionMatcher(

Instances