02ba343e85f299130d2a1fc38e702040ef620c87,gensim/test/test_summarization.py,TestSummarizationTest,test_corpus_summarization,#TestSummarizationTest#,41

Before Change

        self.assertEqual(generated_summary, summary)

    def test_corpus_summarization(self):
        pre_path = os.path.join(os.path.dirname(__file__), "test_data")

        with utils.smart_open(os.path.join(pre_path, "mihalcea_tarau.txt"), mode="r") as f:
            text = f.read()

        // Generate the corpus.
        sentences = text.split("\n")
        tokens = [sentence.split() for sentence in sentences]
        dictionary = Dictionary(tokens)
        corpus = [dictionary.doc2bow(sentence_tokens) for sentence_tokens in tokens]

        // Extract the most important documents.
        selected_documents = summarize_corpus(corpus)

        // They are compared to the method reference.
        with utils.smart_open(os.path.join(pre_path, "mihalcea_tarau.summ.txt"), mode="r") as f:
            summary = f.read()
            summary = summary.split("\n")

        // Each sentence in the document selection has to be in the model summary.
        for doc_number, document in enumerate(selected_documents):
            // Retrieves all words from the document.
            words = [dictionary[token_id] for (token_id, count) in document]

After Change

        self.assertEqual(generated_summary, summary)

    def test_corpus_summarization(self):
        text = self._get_text_from_test_data("mihalcea_tarau.txt")

        // Generate the corpus.
        sentences = text.split("\n")
        tokens = [sentence.split() for sentence in sentences]

Instances