def test_wc_extractor_file_end_to_end_integration(self):
openMock = MagicMock()
openMock.return_value.__enter__.return_value = [
TEST_SENTENCE, TEST_SENTENCE_2
]
extractor = WCExtractor(file_opener=openMock, filter_words=[])
result_dw = {}
expected_dw = {
TEST_WORD: {
"word_count": TEST_WORD_COUNT,
"files": {
TEST_FILE: [TEST_SENTENCE, TEST_SENTENCE_2]
}
},
TEST_WORD_2: {
"word_count": TEST_WORD_COUNT_2,
"files": {
TEST_FILE: [TEST_SENTENCE, TEST_SENTENCE_2]
}
},
TEST_WORD_3: {
"word_count": TEST_WORD_COUNT_3,
"files": {
TEST_FILE: [TEST_SENTENCE_2]
}
}
}
extractor.extract_wc_from_file(TEST_FILE, result_dw)
self.assertEqual(result_dw, expected_dw)
def test_extract(self):
openMock = MagicMock()
openMock.return_value.__enter__.return_value = [
TEST_SENTENCE, TEST_SENTENCE_2
]
extractor = WCExtractor(file_opener=openMock, filter_words=[])
add_word_mock = MagicMock()
extractor._add_word = add_word_mock
split_line_mock = MagicMock(return_value=TEST_SENTENCE)
extractor._split_line = split_line_mock
result_dw = {}
extractor.extract_wc_from_file(TEST_FILE, result_dw)
expected_line_calls = [call(TEST_SENTENCE), call(TEST_SENTENCE_2)]
openMock.assert_called_once_with(TEST_FILE)
split_line_mock.assert_has_calls(expected_line_calls)
def test_wc_extractor_file_end_to_end_with_files(self):
extractor = WCExtractor()
result_wc = {}
extractor.extract_wc_from_file(ACTUAL_FILE, result_wc)
# Make sure result is not empty
self.assertTrue(result_wc)
for o_words in result_wc:
word_count = result_wc[o_words]["word_count"]
total_sentences = 0
o_words_f = result_wc[o_words]["files"]
for file in o_words_f:
total_sentences += len(o_words_f[file])
# Make sure that all the word counts are equal or greater
# than the number of sentences
self.assertGreaterEqual(word_count, total_sentences)
def test_wc_extractor_file_integration_filters(self):
filter_words = [TEST_WORD]
openMock = MagicMock()
openMock.return_value.__enter__.return_value = [
TEST_SENTENCE, TEST_SENTENCE_2
]
extractor = WCExtractor(file_opener=openMock,
filter_words=filter_words)
result_d_words = {}
expected_d_words = {
TEST_WORD: {
"word_count": 2,
"files": {
TEST_FILE: [TEST_SENTENCE, TEST_SENTENCE_2]
}
}
}
extractor.extract_wc_from_file(TEST_FILE, result_d_words)
self.assertEqual(result_d_words, expected_d_words)