コード例 #1
0
 def test_main(self, mock_remove_entity_overlapping, mock_analyze_sentence):
     article_data_sources = [MockDataSource(), MockDataSource()]
     bacteria_catalog = MockCatalog("a")
     nutrients_catalog = MockCatalog("b")
     diseases_catalog = MockCatalog("c")
     food_catalog = MockCatalog("d")
     sentence_parser = StanfordSentenceParser(stanford_dependency_parser=None, stanford_tokenizer=False)
     sentence_parser.parse_sentence = MagicMock()
     sentence_parser.parse_sentence.return_value = ["yeah"]
     constants.logger.info("asdasd")
     main(article_data_sources, sentence_parser,
          tokenizer=None, pattern_finder=None, writers=[])
コード例 #2
0
    do_nothing_analyzer = DoNothingSentenceAnalyzer()
    analyzer = SentenceAnalyzer()
    sentence_finder = SentenceFinder([], do_nothing_parser, do_nothing_analyzer, all_bacteria_catalog, [BACTERIA_TAG])

    nxml_article_data_source = NxmlFreeArticleDataSource(articles_folder=nxml_articles_dir)
    medline_article_data_source = MedlineAbstractsArticleDataSource(medline_file=abstracts_dir)
    libgen_article_data_source = LibgenTxtArticleDataSource(libgen_folder=libgen_texts_dir)

    with open(verb_ontollogy_path) as f:
        verb_ontology = eval("".join(f.readlines()))

    lancaster_stemmer = LancasterStemmer()
    pattern_finder = PatternFinder(verb_ontology, lancaster_stemmer)

    article_data_sources = [nxml_article_data_source, libgen_article_data_source, medline_article_data_source]

    output_dir = get_output_dir_path()
    csv_path = get_csv_path()
    csv_writer = CsvWriter(csv_path)
    pkl_writer = PklWriter(output_dir)
    log_writer = LogWriter()

    main(
        article_data_sources,
        writers=[csv_writer, log_writer],
        sentence_finder=sentence_finder,
        data_sources_to_skip=data_sources_to_skip_number,
        sentences_to_skip=sentences_to_skip_number,
    )