class TestJourneyFederalSenateDataset(TestCase):
def setUp(self):
self.path = gettempdir()
self.subject = Dataset(self.path)
def test_journey_federal_senate_dataset(self):
# fetch_saves_raw_files
self.subject.fetch()
federal_senate_csv_files = [
'federal-senate-{}.csv'.format(year)
for year in self.subject.year_range
]
for federal_senate_csv_file in federal_senate_csv_files:
file_path = os.path.join(self.path, federal_senate_csv_file)
self.assertTrue(os.path.exists(file_path), 'fetch_saves_raw_files')
# translate_creates_english_versions_for_every_csv
self.subject.translate()
federal_senate_xz_files = [
'federal-senate-{}.xz'.format(year)
for year in self.subject.year_range
]
for federal_senate_xz_file in federal_senate_xz_files:
file_path = os.path.join(self.path, federal_senate_xz_file)
self.assertTrue(
os.path.exists(file_path),
'translate_creates_english_versions_for_every_csv')
# clean_creates_a_reimbursements_file
self.subject.clean()
file_path = os.path.join(self.path, 'federal-senate-reimbursements.xz')
self.assertTrue(os.path.exists(file_path),
'clean_creates_a_reimbursements_file')
def update_datasets(self):
os.makedirs(self.path, exist_ok=True)
federal_senate = Dataset(self.path)
federal_senate.fetch()
federal_senate.translate()
federal_senate_reimbursements_path = federal_senate.clean()
return federal_senate_reimbursements_path
class TestJourneyFederalSenateDataset(TestCase):
def setUp(self):
self.path = gettempdir()
self.subject = Dataset(self.path)
def test_journey_federal_senate_dataset(self):
# fetch_saves_raw_files
self.subject.fetch()
federal_senate_csv_files = ['federal-senate-{}.csv'.format(year) for year in self.subject.years]
for federal_senate_csv_file in federal_senate_csv_files:
file_path = os.path.join(self.path, federal_senate_csv_file)
self.assertTrue(os.path.exists(file_path), 'fetch_saves_raw_files')
# translate_creates_english_versions_for_every_csv
self.subject.translate()
federal_senate_xz_files = ['federal-senate-{}.xz'.format(year) for year in self.subject.years]
for federal_senate_xz_file in federal_senate_xz_files:
file_path = os.path.join(self.path, federal_senate_xz_file)
self.assertTrue(os.path.exists(file_path), 'translate_creates_english_versions_for_every_csv')
# clean_creates_a_reimbursements_file
self.subject.clean()
file_path = os.path.join(self.path, 'federal-senate-reimbursements.xz')
self.assertTrue(os.path.exists(file_path), 'clean_creates_a_reimbursements_file')
class TestFederalSenateDataset(TestCase):
@classmethod
def setUpClass(cls):
cls.expected_files = [
'federal-senate-2008.csv', 'federal-senate-2009.csv'
]
@patch('serenata_toolbox.federal_senate.dataset.urlretrieve')
def test_fetch_files_from_S3(self, mocked_url_etrieve):
self.path = gettempdir()
self.subject = Dataset(self.path)
retrieved_files, not_found_files = self.subject.fetch()
self.assertTrue(mocked_url_etrieve.called)
self.assertEqual(mocked_url_etrieve.call_count,
len(self.subject.year_range))
for retrieved_file, expected_file in zip(retrieved_files,
self.expected_files):
self.assertIn(expected_file, retrieved_file)
def test_fetch_not_found_files_from_S3(self):
self.path = gettempdir()
self.subject = Dataset(self.path, 2007, 2008)
retrieved_files, not_found_files = self.subject.fetch()
for not_found_file, expected_file in zip(not_found_files,
self.expected_files):
self.assertIn('federal-senate-2007.csv', not_found_file)
def test_dataset_translation(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'csv'), 2008,
2009)
expected_files = ['federal-senate-2008.csv']
translated_files, not_found_files = self.subject.translate()
for translated_file, expected_file in zip(translated_files,
expected_files):
self.assertIn(expected_file, translated_file)
def test_if_translation_happened_as_expected(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'csv'), 2008,
2009)
file_path = os.path.join(self.subject.path, 'federal-senate-2008.csv')
federal_senate_2008 = pd.read_csv(file_path,
sep=';',
encoding='ISO-8859-1',
skiprows=1)
self.assertIsNotNone(federal_senate_2008['ANO'],
'expects \'ANO\' as column in this dataset')
self.subject.translate()
translated_file_path = os.path.join(self.subject.path,
'federal-senate-2008.xz')
translated_federal_senate_2008 = pd.read_csv(translated_file_path,
encoding='utf-8')
self.assertIsNotNone(translated_federal_senate_2008['year'],
'expects \'year\' as column in this dataset')
os.remove(os.path.join(self.subject.path, 'federal-senate-2008.xz'))
def test_dataset_translation_failing_to_find_file(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'csv'), 2007,
2008)
expected_files = ['federal-senate-2007.csv']
translated_files, not_found_files = self.subject.translate()
for not_found_files, expected_file in zip(not_found_files,
expected_files):
self.assertIn(expected_file, not_found_files)
def test_dataset_cleanup(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'xz'), 2009,
2010)
reimbursement_path = self.subject.clean()
expected_path = os.path.join('tests', 'fixtures', 'xz',
'federal-senate-reimbursements.xz')
self.assertEqual(reimbursement_path, expected_path)
os.remove(expected_path)
class TestFederalSenateDataset(TestCase):
@classmethod
def setUpClass(cls):
cls.expected_files = ['federal-senate-2008.csv',
'federal-senate-2009.csv']
@patch('serenata_toolbox.federal_senate.dataset.urlretrieve')
def test_fetch_files_from_S3(self, mocked_url_retrieve):
path = gettempdir()
self.subject = Dataset(path)
retrieved_files, _ = self.subject.fetch()
self.assertTrue(mocked_url_retrieve.called)
self.assertEqual(mocked_url_retrieve.call_count, len(self.subject.years))
for retrieved_file, expected_file in zip(
retrieved_files, self.expected_files):
self.assertIn(expected_file, retrieved_file)
@patch('serenata_toolbox.federal_senate.dataset.urlretrieve')
def test_fetch_raises_HTTPError(self, mocked_url_retrieve):
mocked_url_retrieve.side_effect = urllib.error.HTTPError(None, None, None, None, None)
self.path = gettempdir()
self.subject = Dataset(self.path, [2007])
with self.assertRaises(urllib.error.HTTPError) as context:
self.subject.fetch()
self.assertTrue(isinstance(context.exception, urllib.error.HTTPError))
@patch('serenata_toolbox.federal_senate.dataset.urlretrieve')
def test_fetch_raises_URLError(self, mocked_url_retrieve):
mocked_url_retrieve.side_effect = urllib.error.URLError('tests reason')
path = gettempdir()
subject = Dataset(path, [2007])
with self.assertRaises(urllib.error.URLError) as context:
subject.fetch()
self.assertTrue(isinstance(context.exception, urllib.error.URLError))
def test_dataset_translation(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'csv'),
[2008])
expected_files = ['federal-senate-2008.csv']
translated_files, _ = self.subject.translate()
for translated_file, expected_file in zip(
translated_files, expected_files):
self.assertIn(expected_file, translated_file)
def test_if_translation_happened_as_expected(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'csv'),
[2008])
file_path = os.path.join(self.subject.path, 'federal-senate-2008.csv')
federal_senate_2008 = pd.read_csv(file_path,
sep=';',
encoding='ISO-8859-1',
skiprows=1)
self.assertIsNotNone(federal_senate_2008['ANO'],
"expects 'ANO' as column in this dataset")
self.subject.translate()
translated_file_path = os.path.join(self.subject.path, 'federal-senate-2008.xz')
translated_federal_senate_2008 = pd.read_csv(translated_file_path,
encoding='utf-8')
self.assertIsNotNone(translated_federal_senate_2008['year'],
"expects 'year' as column in this dataset")
os.remove(os.path.join(self.subject.path, 'federal-senate-2008.xz'))
def test_dataset_translation_failing_to_find_file(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'csv'),
[2007])
with self.assertRaises(FileNotFoundError) as context:
self.subject.translate()
self.assertTrue(isinstance(context.exception, FileNotFoundError))
def test_dataset_cleanup(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'xz'),
[2009])
reimbursement_path = self.subject.clean()
expected_path = os.path.join('tests',
'fixtures',
'xz',
'federal-senate-reimbursements.xz')
self.assertEqual(
reimbursement_path,
expected_path
)
os.remove(expected_path)
class TestFederalSenateDataset(TestCase):
@classmethod
def setUpClass(cls):
cls.expected_files = [
'federal-senate-2008.csv', 'federal-senate-2009.csv'
]
@patch('serenata_toolbox.federal_senate.dataset.urlretrieve')
def test_fetch_files_from_S3(self, mocked_url_retrieve):
path = gettempdir()
self.subject = Dataset(path)
retrieved_files, _ = self.subject.fetch()
self.assertTrue(mocked_url_retrieve.called)
self.assertEqual(mocked_url_retrieve.call_count,
len(self.subject.years))
for retrieved_file, expected_file in zip(retrieved_files,
self.expected_files):
self.assertIn(expected_file, retrieved_file)
@patch('serenata_toolbox.federal_senate.dataset.urlretrieve')
def test_fetch_raises_HTTPError(self, mocked_url_retrieve):
mocked_url_retrieve.side_effect = urllib.error.HTTPError(
None, None, None, None, None)
self.path = gettempdir()
self.subject = Dataset(self.path, [2007])
with self.assertRaises(urllib.error.HTTPError) as context:
self.subject.fetch()
self.assertTrue(isinstance(context.exception, urllib.error.HTTPError))
@patch('serenata_toolbox.federal_senate.dataset.urlretrieve')
def test_fetch_raises_URLError(self, mocked_url_retrieve):
mocked_url_retrieve.side_effect = urllib.error.URLError('tests reason')
path = gettempdir()
subject = Dataset(path, [2007])
with self.assertRaises(urllib.error.URLError) as context:
subject.fetch()
self.assertTrue(isinstance(context.exception, urllib.error.URLError))
def test_dataset_translation(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'csv'),
[2008])
expected_files = ['federal-senate-2008.csv']
translated_files, _ = self.subject.translate()
for translated_file, expected_file in zip(translated_files,
expected_files):
self.assertIn(expected_file, translated_file)
def test_if_translation_happened_as_expected(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'csv'),
[2008])
file_path = os.path.join(self.subject.path, 'federal-senate-2008.csv')
federal_senate_2008 = pd.read_csv(file_path,
sep=';',
encoding='ISO-8859-1',
skiprows=1)
self.assertIsNotNone(federal_senate_2008['ANO'],
"expects 'ANO' as column in this dataset")
self.subject.translate()
translated_file_path = os.path.join(self.subject.path,
'federal-senate-2008.xz')
translated_federal_senate_2008 = pd.read_csv(translated_file_path,
encoding='utf-8')
self.assertIsNotNone(translated_federal_senate_2008['year'],
"expects 'year' as column in this dataset")
os.remove(os.path.join(self.subject.path, 'federal-senate-2008.xz'))
def test_dataset_translation_failing_to_find_file(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'csv'),
[2007])
with self.assertRaises(FileNotFoundError) as context:
self.subject.translate()
self.assertTrue(isinstance(context.exception, FileNotFoundError))
def test_dataset_cleanup(self):
self.subject = Dataset(os.path.join('tests', 'fixtures', 'xz'), [2009])
reimbursement_path = self.subject.clean()
expected_path = os.path.join('tests', 'fixtures', 'xz',
'federal-senate-reimbursements.xz')
self.assertEqual(reimbursement_path, expected_path)
os.remove(expected_path)