Fix Issue #805: Added check in summarize_corpus

gensim/summarization/summarizer.py

@@ -158,6 +158,11 @@ def summarize_corpus(corpus, ratio=0.2):
     _set_graph_edge_weights(graph)
     _remove_unreachable_nodes(graph)
 
+    # Cannot calculate eigenvectors if number of unique words in text < 3. Warns user to add more text. The function ends.
+    if len(graph.nodes()) < 3:
+        logger.warning("Please add more sentences to the text. The number of reachable nodes is below 3")
+        return
+
     pagerank_scores = _pagerank(graph)
 
     hashable_corpus.sort(key=lambda doc: pagerank_scores.get(doc, 0), reverse=True)

gensim/test/test_data/testlowdistinctwords.txt

@@ -0,0 +1,10 @@
+here here.
+there there. 
+here here.
+there there.
+here here.
+there there.
+here here.
+there there.
+here here.
+there there.

gensim/test/test_summarization.py

@@ -160,6 +160,20 @@ def test_keywords_runs(self):
         kwds_lst = keywords(text, split=True)
         self.assertTrue(len(kwds_lst))
 
+    def test_low_distinct_words_corpus_summarization_is_none(self):
+        pre_path = os.path.join(os.path.dirname(__file__), 'test_data')
+
+        with utils.smart_open(os.path.join(pre_path, "testlowdistinctwords.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]
+
+        self.assertTrue(summarize_corpus(corpus) is None)
+
 if __name__ == '__main__':
     logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.DEBUG)
     unittest.main()

gensim/test/test_wikicorpus.py

@@ -27,10 +27,11 @@ class TestWikiCorpus(unittest.TestCase):
     def setUp(self):
         wc = WikiCorpus(datapath(FILENAME))
 
-
     def test_get_texts_returns_generator_of_lists(self):
+
         if sys.version_info < (2, 7, 0):
             return
+
         wc = WikiCorpus(datapath(FILENAME))
         l = wc.get_texts()
         self.assertEqual(type(l), types.GeneratorType)