def test_clustering(self):
s = summarizer.Summarizer()
testdir = os.path.dirname(os.path.realpath(__file__))
doc = document.Document(os.path.join(testdir, 'testdata/smalldoc.txt'))
s.addDocument(doc)
s.addDocument(doc)
s.clusterSentences()
self.assertEqual(len(s.clusters), 2)
def test_selectSentences(self):
s = summarizer.Summarizer()
testdir = os.path.dirname(os.path.realpath(__file__))
doc1 = document.Document(os.path.join(testdir, 'testdata/smalldoc.txt'))
doc2 = document.Document(os.path.join(testdir, 'testdata/smalldocb.txt'))
s.addDocument(doc1)
s.addDocument(doc2)
maxwords = 50
s.summarize(maxwords)
print(s.summary)
def test_doclogic(self):
s = summarizer.Summarizer()
testdir = os.path.dirname(os.path.realpath(__file__))
doc = document.Document(os.path.join(testdir, 'testdata/smalldoc.txt'))
s.addDocument(doc)
s.addDocument(doc)
self.assertEqual(len(s.documents), 2)
s.clearDocuments()
self.assertEqual(s.documents, None)
s.setDocuments([doc])
self.assertEqual(len(s.documents), 1)
def test_init(self):
s = summarizer.Summarizer()
testdir = os.path.dirname(os.path.realpath(__file__))
doc = document.Document(os.path.join(testdir, 'testdata/smalldoc.txt'))
s.addDocument(doc)
self.assertEqual(len(s.documents), 1)