def test_header_only_input_one_output_file_with_header(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
m.split(rows, prefix='split.', chunk_size=1)
self.assertEqual(u'a,b', header(u'split.0'))
def test_header_only_input_one_output_file_with_header(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
m.split(rows, prefix='split.', chunk_size=1)
self.assertEqual(u'a,b', header(u'split.0'))
def test_multiple_output_files_have_same_header(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
rows.writerow([1, 2])
rows.writerow([3, 4])
m.split(rows, prefix='split.', chunk_size=1)
self.assertEqual(u'a,b', header(u'split.0'))
self.assertEqual(u'a,b', header(u'split.1'))
def test_less_data_rows_than_chunk_size_one_file_created(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
rows.writerow([1, 2])
rows.writerow([3, 4])
m.split(rows, prefix='split.', chunk_size=3)
self.assertTrue(os.path.exists(u'split.0'))
self.assertFalse(os.path.exists(u'split.1'))
def test_multiple_output_files_have_same_header(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
rows.writerow([1, 2])
rows.writerow([3, 4])
m.split(rows, prefix='split.', chunk_size=1)
self.assertEqual(u'a,b', header(u'split.0'))
self.assertEqual(u'a,b', header(u'split.1'))
def test_less_data_rows_than_chunk_size_one_file_created(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
rows.writerow([1, 2])
rows.writerow([3, 4])
m.split(rows, prefix='split.', chunk_size=3)
self.assertTrue(os.path.exists(u'split.0'))
self.assertFalse(os.path.exists(u'split.1'))
def test_output_file_contains_rows_from_input(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
rows.writerow([1, 2])
rows.writerow([3, 4])
m.split(rows, prefix='split.', chunk_size=2)
with codecs.open('split.0', encoding='utf8') as f:
self.assertEqual([[u'a', u'b'], [u'1', u'2'], [u'3', u'4']],
list(csv.reader(f)))
def test_11_data_rows_chunk_size_1_11_files_created(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
for i in range(11):
rows.writerow([i, i + 1])
m.split(rows, prefix='split.', chunk_size=1)
self.assertTrue(os.path.exists(u'split.0'))
self.assertTrue(os.path.exists(u'split.1'))
# ...
self.assertTrue(os.path.exists(u'split.10'))
self.assertFalse(os.path.exists(u'split.11'))
def test_11_data_rows_chunk_size_1_11_files_created(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
for i in range(11):
rows.writerow([i, i + 1])
m.split(rows, prefix='split.', chunk_size=1)
self.assertTrue(os.path.exists(u'split.0'))
self.assertTrue(os.path.exists(u'split.1'))
# ...
self.assertTrue(os.path.exists(u'split.10'))
self.assertFalse(os.path.exists(u'split.11'))
def test_output_file_contains_rows_from_input(self):
rows = ReaderWriter()
rows.writerow(u'a b'.split())
rows.writerow([1, 2])
rows.writerow([3, 4])
m.split(rows, prefix='split.', chunk_size=2)
with codecs.open('split.0', encoding='utf8') as f:
self.assertEqual(
[[u'a', u'b'],
[u'1', u'2'],
[u'3', u'4']],
list(csv.reader(f)))
def test_out_spec(self):
csv_in = ReaderWriter()
csv_in.writerow('a b c'.split())
csv_in.writerow('a1 b1 c1'.split())
csv_in.writerow('a2 b2 c2'.split())
csv_out_spec = ReaderWriter()
csv_out_unspec = ReaderWriter()
m.unzip(csv_in, ['a'], csv_out_spec, csv_out_unspec)
self.assertListEqual(
['id a'.split(),
'0 a1'.split(),
'1 a2'.split()],
csv_out_spec.rows)
def csv_header_a_b_c(self):
csv = ReaderWriter()
csv.writerow('a b c'.split())
return csv
