Fix piskvorky#851, Error is raised instead of returning text [WiP] (p…

…iskvorky#902)

* Update summarizer.py

Return statement removed and error raised.

* Update test_summarization.py

Removed test for single sentence input.

* Update CHANGELOG.md

* Update summarizer.py

* Update test_wikicorpus.py

* Update test_summarization.py

CHANGELOG.md

@@ -10,7 +10,7 @@ Changes
     - bigram construction can now support multiple bigrams within one sentence
 * Fixed issue #838, RuntimeWarning: overflow encountered in exp  (@markroxor, [#895](https://github.com/RaRe-Technologies/gensim/pull/895))
 *  Changed some log messages to warnings as suggested in issue #828. (@rhnvrm, [#884](https://github.com/RaRe-Technologies/gensim/pull/884))
-*  Fixed issue #851, In summarizer.py, check for single sentence as an input added to avoid ZeroDivionError, added test cases in test/test_summarization.py(@metalaman, #887)
+*  Fixed issue #851, In summarizer.py, RunTimeError is raised if single sentence input is provided to avoid ZeroDivionError. (@metalaman, #887)
 
 
 0.13.2, 2016-08-19

gensim/summarization/summarizer.py

@@ -198,10 +198,9 @@ def summarize(text, ratio=0.2, word_count=None, split=False):
         logger.warning("Input text is empty.")
         return
 
-    # If only one sentence is present, the function return the input text (Avoids ZeroDivisionError). 
+    # If only one sentence is present, the function raises an error (Avoids ZeroDivisionError). 
     if len(sentences) == 1:
-        logger.warning("Summarization not performed since the document has only one sentence.")
-        return text
+        raise ValueError("input must have more than one sentence")
 
     # Warns if the text is too short.
     if len(sentences) < INPUT_MIN_LENGTH:

gensim/test/test_summarization.py

@@ -87,7 +87,7 @@ def test_text_summarization_raises_exception_on_short_input_text(self):
         text = "\n".join(text.split('\n')[:8])
 
         self.assertTrue(summarize(text) is not None)
-
+        
     def test_text_summarization_returns_input_on_single_input_sentence(self):
         pre_path = os.path.join(os.path.dirname(__file__), 'test_data')
 
@@ -97,7 +97,7 @@ def test_text_summarization_returns_input_on_single_input_sentence(self):
         # Keeps the first sentence only.
         text = text.split('\n')[0]
 
-        self.assertEqual(summarize(text),text)
+        self.assertRaises(ValueError,summarize,text)
 
     def test_corpus_summarization_raises_exception_on_short_input_text(self):
         pre_path = os.path.join(os.path.dirname(__file__), 'test_data')

gensim/test/test_wikicorpus.py

@@ -12,25 +12,25 @@
 import os
 import sys
 import types
-
+import logging
 import unittest
 
 from gensim.corpora.wikicorpus import WikiCorpus
 
 
-
 module_path = os.path.dirname(__file__) # needed because sample data files are located in the same folder
 datapath = lambda fname: os.path.join(module_path, 'test_data', fname)
 FILENAME = 'enwiki-latest-pages-articles1.xml-p000000010p000030302-shortened.bz2'
 
+logger = logging.getLogger(__name__)
 
 class TestWikiCorpus(unittest.TestCase):
 
     def setUp(self):
         wc = WikiCorpus(datapath(FILENAME))
 
     def test_get_texts_returns_generator_of_lists(self):
-
+        logger.debug("Current Python Version is "+str(sys.version_info))
         if sys.version_info < (2, 7, 0):
             return