mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 00:48:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

bpo-27580: Add support of null characters in the csv module. (GH-28808)

Browse source
This commit is contained in:
Serhiy Storchaka 2021-10-09 19:17:43 +03:00 • committed by GitHub
parent b4903afd4d
commit b454e8e4df
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 70 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

44
Lib/test/test_csv.py
View file

@ -217,6 +217,17 @@ class Test_Csv(unittest.TestCase):
self._write_test(['C\\', '6', '7', 'X"'], 'C\\\\,6,7,"X"""',
escapechar='\\', quoting=csv.QUOTE_MINIMAL)
def test_write_lineterminator(self):
for lineterminator in '\r\n', '\n', '\r', '!@#', '\0':
with self.subTest(lineterminator=lineterminator):
with StringIO() as sio:
writer = csv.writer(sio, lineterminator=lineterminator)
writer.writerow(['a', 'b'])
writer.writerow([1, 2])
self.assertEqual(sio.getvalue(),
f'a,b{lineterminator}'
f'1,2{lineterminator}')
def test_write_iterable(self):
self._write_test(iter(['a', 1, 'p,q']), 'a,1,"p,q"')
self._write_test(iter(['a', 1, None]), 'a,1,')
@ -286,14 +297,10 @@ class Test_Csv(unittest.TestCase):
self._read_test([''], [[]])
self.assertRaises(csv.Error, self._read_test,
['"ab"c'], None, strict = 1)
# cannot handle null bytes for the moment
self.assertRaises(csv.Error, self._read_test,
['ab\0c'], None, strict = 1)
self._read_test(['"ab"c'], [['abc']], doublequote = 0)
self.assertRaises(csv.Error, self._read_test,
[b'ab\0c'], None)
[b'abc'], None)
def test_read_eol(self):
self._read_test(['a,b'], [['a','b']])
@ -313,6 +320,18 @@ class Test_Csv(unittest.TestCase):
self.assertRaises(csv.Error, self._read_test,
['^'], [], escapechar='^', strict=True)
def test_read_nul(self):
self._read_test(['\0'], [['\0']])
self._read_test(['a,\0b,c'], [['a', '\0b', 'c']])
self._read_test(['a,b\0,c'], [['a', 'b\0', 'c']])
self._read_test(['a,b\\\0,c'], [['a', 'b\0', 'c']], escapechar='\\')
self._read_test(['a,"\0b",c'], [['a', '\0b', 'c']])
def test_read_delimiter(self):
self._read_test(['a,b,c'], [['a', 'b', 'c']])
self._read_test(['a;b;c'], [['a', 'b', 'c']], delimiter=';')
self._read_test(['a\0b\0c'], [['a', 'b', 'c']], delimiter='\0')
def test_read_escape(self):
self._read_test(['a,\\b,c'], [['a', 'b', 'c']], escapechar='\\')
self._read_test(['a,b\\,c'], [['a', 'b,c']], escapechar='\\')
@ -320,6 +339,11 @@ class Test_Csv(unittest.TestCase):
self._read_test(['a,"b,\\c"'], [['a', 'b,c']], escapechar='\\')
self._read_test(['a,"b,c\\""'], [['a', 'b,c"']], escapechar='\\')
self._read_test(['a,"b,c"\\'], [['a', 'b,c\\']], escapechar='\\')
self._read_test(['a,^b,c'], [['a', 'b', 'c']], escapechar='^')
self._read_test(['a,\0b,c'], [['a', 'b', 'c']], escapechar='\0')
self._read_test(['a,\\b,c'], [['a', '\\b', 'c']], escapechar=None)
self._read_test(['a,\\b,c'], [['a', '\\b', 'c']], escapechar='')
self._read_test(['a,\\b,c'], [['a', '\\b', 'c']])
def test_read_quoting(self):
self._read_test(['1,",3,",5'], [['1', ',3,', '5']])
@ -334,6 +358,8 @@ class Test_Csv(unittest.TestCase):
self.assertRaises(ValueError, self._read_test,
['abc,3'], [[]],
quoting=csv.QUOTE_NONNUMERIC)
self._read_test(['1,@,3,@,5'], [['1', ',3,', '5']], quotechar='@')
self._read_test(['1,\0,3,\0,5'], [['1', ',3,', '5']], quotechar='\0')
def test_read_bigfield(self):
# This exercises the buffer realloc functionality and field size
@ -1074,6 +1100,12 @@ Stonecutters Seafood and Chop House+ Lemont+ IL+ 12/19/02+ Week Back
a,b
""")
sample14 = """\
abc\0def
ghijkl\0mno
ghi\0jkl
"""
def test_issue43625(self):
sniffer = csv.Sniffer()
self.assertTrue(sniffer.has_header(self.sample12))
@ -1142,6 +1174,8 @@ Stonecutters Seafood and Chop House+ Lemont+ IL+ 12/19/02+ Week Back
dialect = sniffer.sniff(self.sample9)
self.assertEqual(dialect.delimiter, '+')
self.assertEqual(dialect.quotechar, "'")
dialect = sniffer.sniff(self.sample14)
self.assertEqual(dialect.delimiter, '\0')
def test_doublequote(self):
sniffer = csv.Sniffer()