def test_init(self):
result = file_indexer.Histogram()
self.assertIsInstance(result._words, collections.defaultdict)
self.assertEqual(result._words, {})
self.assertEqual(result._words['spam'], 0) # test the lambda
self.assertEqual(result._total, 0)
def test_dunder_add_base(self):
obj1 = file_indexer.Histogram()
obj1._words.update({
'word1': 50,
'word2': 40,
'word3': 30,
'word4': 20,
'word5': 10,
})
obj1._total = 150
obj2 = file_indexer.Histogram()
obj2._words.update({
'word2': 20,
'word4': 50,
'word6': 80,
})
obj2._total = 150
result = obj1 + obj2
self.assertEqual(
result._words, {
'word1': 50,
'word2': 60,
'word3': 30,
'word4': 70,
'word5': 10,
'word6': 80,
})
self.assertEqual(result._total, 300)
self.assertEqual(obj1._words, {
'word1': 50,
'word2': 40,
'word3': 30,
'word4': 20,
'word5': 10,
})
self.assertEqual(obj1._total, 150)
self.assertEqual(obj2._words, {
'word2': 20,
'word4': 50,
'word6': 80,
})
self.assertEqual(obj2._total, 150)
def test_distinct_words(self):
obj = file_indexer.Histogram()
obj._words.update({
'word1': 50,
'word2': 40,
'word3': 30,
'word4': 20,
'word5': 10,
})
obj._total = 150
self.assertEqual(obj.distinct_words, 5)
def make_results(self, file_cnt=5):
result = [file_indexer.Histogram() for i in range(file_cnt)]
for hist in result:
hist._words.update({
'word1': 50,
'word2': 40,
'word3': 30,
'word4': 20,
'word5': 10,
})
hist._total = 150
return result
def test_add(self):
obj = file_indexer.Histogram()
obj.add('SpAm')
obj.add('sPaM')
obj.add('spam')
obj.add('spammER')
self.assertEqual(obj._words, {
'spam': 3,
'spammer': 1,
})
self.assertEqual(obj._total, 4)
def test_negative_workers(self, mock_from_file, mock_Pool, mock_cpu_count):
files = ['file%d' % i for i in range(5)]
out = six.StringIO()
mock_Pool.return_value.map.return_value = self.make_results()
mock_from_file.side_effect = lambda x: file_indexer.Histogram()
self.assertRaises(ValueError,
file_indexer.main,
files,
out,
workers=-1)
self.assertFalse(mock_cpu_count.called)
self.assertFalse(mock_Pool.called)
self.assertFalse(mock_from_file.called)
def test_top_words_small_count(self):
obj = file_indexer.Histogram()
obj._words.update({
'word1': 50,
'word2': 40,
'word3': 30,
'word4': 20,
'word5': 10,
})
obj._total = 150
result = obj.top_words(4)
self.assertEqual(result, [
('word1', 50),
('word2', 40),
('word3', 30),
('word4', 20),
])
def test_top_words_too_few(self):
obj = file_indexer.Histogram()
obj._words.update({
'word1': 50,
'word2': 40,
'word3': 30,
'word4': 20,
'word5': 10,
})
obj._total = 150
result = obj.top_words() # default word count is 10
self.assertEqual(result, [
('word1', 50),
('word2', 40),
('word3', 30),
('word4', 20),
('word5', 10),
])
def test_top_words_small_count_with_tie(self):
obj = file_indexer.Histogram()
obj._words.update({
'word1': 50,
'word2': 40,
'word3': 40,
'word4': 40,
'word5': 10,
})
obj._total = 150
result = obj.top_words(3)
self.assertEqual(
result,
[
('word1', 50),
('word4', 40), # words will be lexicographically sorted
('word3', 40),
('word2', 40),
])
def test_workers_specified(self, mock_from_file, mock_Pool,
mock_cpu_count):
files = ['file%d' % i for i in range(5)]
out = six.StringIO()
mock_Pool.return_value.map.return_value = self.make_results()
mock_from_file.side_effect = lambda x: file_indexer.Histogram()
file_indexer.main(files, out, workers=7)
self.assertEqual(
out.getvalue(), 'Total number of words: 750\n'
'Total distinct words: 5\n'
'\n'
'Top 5 word(s):\n'
' word1: 250\n'
' word2: 200\n'
' word3: 150\n'
' word4: 100\n'
' word5: 50\n')
self.assertFalse(mock_cpu_count.called)
mock_Pool.assert_called_once_with(7)
mock_Pool.return_value.map.assert_called_once_with(
file_indexer.histogram_from_file, files)
self.assertFalse(mock_from_file.called)
def test_iadd_bad_other(self):
obj = file_indexer.Histogram()
result = obj.__iadd__('other')
self.assertEqual(result, NotImplemented)