def test_split(self):
self.assertEqual(
csv_utils.split_quoted_str(' aaa, " aaa, bbb " , ccc , ddd ', ',',
True)[0],
[' aaa', ' " aaa, bbb " ', ' ccc ', ' ddd '])
self.assertEqual(
csv_utils.split_quoted_str(' aaa, " aaa, bbb " , ccc , ddd ', ',',
False)[0],
[' aaa', ' aaa, bbb ', ' ccc ', ' ddd '])
test_cases = list()
test_cases.append(('hello,world', (['hello', 'world'], False)))
test_cases.append(('hello,"world"', (['hello', 'world'], False)))
test_cases.append(('"abc"', (['abc'], False)))
test_cases.append(('abc', (['abc'], False)))
test_cases.append(('', ([''], False)))
test_cases.append((',', (['', ''], False)))
test_cases.append((',,,', (['', '', '', ''], False)))
test_cases.append((',"",,,', (['', '', '', '', ''], False)))
test_cases.append(('"","",,,""', (['', '', '', '', ''], False)))
test_cases.append(('"aaa,bbb",', (['aaa,bbb', ''], False)))
test_cases.append(('"aaa,bbb",ccc', (['aaa,bbb', 'ccc'], False)))
test_cases.append(('"aaa,bbb","ccc"', (['aaa,bbb', 'ccc'], False)))
test_cases.append(('"aaa,bbb","ccc,ddd"', (['aaa,bbb',
'ccc,ddd'], False)))
test_cases.append((' "aaa,bbb" , "ccc,ddd" ', (['aaa,bbb',
'ccc,ddd'], False)))
test_cases.append(('"aaa,bbb",ccc,ddd', (['aaa,bbb', 'ccc',
'ddd'], False)))
test_cases.append(
('"a"aa" a,bbb",ccc,ddd', (['"a"aa" a', 'bbb"', 'ccc',
'ddd'], True)))
test_cases.append(
('"aa, bb, cc",ccc",ddd', (['aa, bb, cc', 'ccc"', 'ddd'], True)))
test_cases.append(('hello,world,"', (['hello', 'world', '"'], True)))
test_cases.append((' aaa, " aaa, bbb " , ccc , ddd ',
([' aaa', ' aaa, bbb ', ' ccc ', ' ddd '], False)))
test_cases.append(
(' aaa ,bbb ,ccc , ddd ', ([' aaa ', 'bbb ', 'ccc ',
' ddd '], False)))
for tc in test_cases:
src = tc[0]
expected_dst = tc[1]
warning_expected = expected_dst[1]
test_dst = csv_utils.split_quoted_str(tc[0], ',')
self.assertEqual(
expected_dst,
test_dst,
msg='\nsrc: {}\ntest_dst: {}\nexpected_dst: {}\n'.format(
src, test_dst, expected_dst))
test_dst_preserved = csv_utils.split_quoted_str(tc[0], ',', True)
self.assertEqual(test_dst[1], test_dst_preserved[1])
self.assertEqual(','.join(test_dst_preserved[0]), tc[0],
'preserved split failure')
if not warning_expected:
self.assertEqual(
test_dst[0],
csv_utils.unquote_fields(test_dst_preserved[0]))
def test_random(self):
random_records = make_random_csv_records_naive()
for ir, rec in enumerate(random_records):
expected_fields = rec[0]
escaped_entry = rec[1]
expected_warning = rec[2]
test_fields, test_warning = csv_utils.split_quoted_str(escaped_entry, ',')
test_fields_preserved, test_warning_preserved = csv_utils.split_quoted_str(escaped_entry, ',', True)
self.assertEqual(','.join(test_fields_preserved), escaped_entry)
self.assertEqual(expected_warning, test_warning)
self.assertEqual(test_warning_preserved, test_warning)
self.assertEqual(test_fields, csv_utils.unquote_fields(test_fields_preserved))
if not expected_warning:
self.assertEqual(expected_fields, test_fields)
def randomly_join_quoted(fields, delim):
efields = list()
for field in fields:
efields.append(randomly_quote_field(field, delim))
assert csv_utils.unquote_fields(efields) == fields
return delim.join(efields)
