def test_text_keywords(self):
text = get_text_from_test_data("mihalcea_tarau.txt")
# Calculate keywords
generated_keywords = keywords(text, split=True)
# To be compared to the reference.
reference_keywords = get_text_from_test_data("mihalcea_tarau.kw.txt").split("\n")
self.assertEqual({str(x) for x in generated_keywords}, {str(x) for x in reference_keywords})
def test_reference_text_summarization(self):
text = get_text_from_test_data("mihalcea_tarau.txt")
# Makes a summary of the text.
generated_summary = summarize(text)
# To be compared to the method reference.
summary = get_text_from_test_data("mihalcea_tarau.summ.txt")
self.assertEqual(generated_summary, summary)
def test_reference_text_summarization_with_split(self):
text = get_text_from_test_data("mihalcea_tarau.txt")
# Makes a summary of the text as a list.
generated_summary = summarize(text, split=True)
# To be compared to the method reference.
summary = get_text_from_test_data("mihalcea_tarau.summ.txt")
summary = summary.split("\n")
self.assertSequenceEqual(generated_summary, summary)
def test_text_summarization_on_short_input_text_is_not_empty_string(self):
text = get_text_from_test_data("unrelated.txt")
# Keeps the first 8 sentences to make the text shorter.
text = "\n".join(text.split('\n')[:8])
self.assertNotEquals(keywords(text, split=True), "")
def test_text_summarization_on_single_input_sentence_with_split_is_empty_list(self):
text = get_text_from_test_data("unrelated.txt")
# Keeps the first sentence only.
text = text.split('\n')[0]
self.assertEquals(summarize(text, split=True), [])
def test_text_summarization_on_single_input_sentence_is_empty_string(self):
text = get_text_from_test_data("unrelated.txt")
# Keeps the first sentence only.
text = text.split('\n')[0]
self.assertEquals(summarize(text), "")
def test_keywords_ratio(self):
text = get_text_from_test_data("mihalcea_tarau.txt")
# Check ratio parameter is well behaved.
# Because length is taken on tokenized clean text we just check that
# ratio 40% is twice as long as ratio 20%
selected_docs_20 = keywords(text, ratio=0.2, split=True)
selected_docs_40 = keywords(text, ratio=0.4, split=True)
self.assertAlmostEqual(float(len(selected_docs_40)) / len(selected_docs_20), 0.4 / 0.2, places=1)
def test_corpus_summarization_ratio(self):
text = get_text_from_test_data("mihalcea_tarau.txt")
sentences = text.split('\n')
# Makes summaries of the text using different ratio parameters.
for x in range(1, 10):
ratio = x / float(10)
selected_sentences = summarize(text, ratio=ratio, split=True)
expected_summary_length = int(len(sentences) * ratio)
self.assertEqual(len(selected_sentences), expected_summary_length)
def test_few_distinct_words_summarization_with_split_is_empty_list(self):
text = get_text_from_test_data("few_distinct_words.txt")
self.assertEquals(summarize(text, split=True), [])
def test_few_distinct_words_summarization_is_empty_string(self):
text = get_text_from_test_data("few_distinct_words.txt")
self.assertEquals(summarize(text), "")
def test_keywords_few_distinct_words_is_empty_string(self):
text = get_text_from_test_data("few_distinct_words.txt")
self.assertEquals(keywords(text), "")
def test_keywords_few_distinct_words_split_is_empty_list(self):
text = get_text_from_test_data("few_distinct_words.txt")
self.assertEquals(keywords(text, split=True), [])
def test_repeated_keywords(self):
text = get_text_from_test_data("repeated_keywords.txt")
kwds = keywords(text)
self.assertTrue(len(kwds.splitlines()))
def test_summary_from_unrelated_sentences_and_split_is_not_empty_list(self):
# Tests that the summarization of a text with unrelated sentences is not empty string.
text = get_text_from_test_data("unrelated.txt")
self.assertNotEquals(summarize(text, split=True), [])
def test_summary_from_unrelated_sentences_is_not_empty_string(self):
# Tests that the summarization of a text with unrelated sentences is not empty string.
text = get_text_from_test_data("unrelated.txt")
self.assertNotEquals(summarize(text), u"")