mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-09 19:38:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

[3.12] gh-67044: Always quote or escape \r and \n in csv.writer() (GH-115741) (GH-115866)

Browse source 
(cherry picked from commit c688c0f130)

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
This commit is contained in:
Miss Islington (bot) 2024-02-23 21:45:04 +01:00 • committed by GitHub
parent 10907bdad3
commit 4ac657a62f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 43 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

54
Lib/test/test_csv.py
View file

@ -240,9 +240,11 @@ class Test_Csv(unittest.TestCase):
writer = csv.writer(sio, lineterminator=lineterminator)
writer.writerow(['a', 'b'])
writer.writerow([1, 2])
writer.writerow(['\r', '\n'])
self.assertEqual(sio.getvalue(),
f'a,b{lineterminator}'
f'1,2{lineterminator}')
f'1,2{lineterminator}'
f'"\r","\n"{lineterminator}')
def test_write_iterable(self):
self._write_test(iter(['a', 1, 'p,q']), 'a,1,"p,q"')
@ -469,22 +471,44 @@ class Test_Csv(unittest.TestCase):
self.assertEqual(r.line_num, 3)
def test_roundtrip_quoteed_newlines(self):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj)
rows = [['a\nb','b'],['c','x\r\nd']]
writer.writerows(rows)
fileobj.seek(0)
for i, row in enumerate(csv.reader(fileobj)):
self.assertEqual(row, rows[i])
rows = [
['\na', 'b\nc', 'd\n'],
['\re', 'f\rg', 'h\r'],
['\r\ni', 'j\r\nk', 'l\r\n'],
['\n\rm', 'n\n\ro', 'p\n\r'],
['\r\rq', 'r\r\rs', 't\r\r'],
['\n\nu', 'v\n\nw', 'x\n\n'],
]
for lineterminator in '\r\n', '\n', '\r':
with self.subTest(lineterminator=lineterminator):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj, lineterminator=lineterminator)
writer.writerows(rows)
fileobj.seek(0)
for i, row in enumerate(csv.reader(fileobj)):
self.assertEqual(row, rows[i])
def test_roundtrip_escaped_unquoted_newlines(self):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj,quoting=csv.QUOTE_NONE,escapechar="\\")
rows = [['a\nb','b'],['c','x\r\nd']]
writer.writerows(rows)
fileobj.seek(0)
for i, row in enumerate(csv.reader(fileobj,quoting=csv.QUOTE_NONE,escapechar="\\")):
self.assertEqual(row,rows[i])
rows = [
['\na', 'b\nc', 'd\n'],
['\re', 'f\rg', 'h\r'],
['\r\ni', 'j\r\nk', 'l\r\n'],
['\n\rm', 'n\n\ro', 'p\n\r'],
['\r\rq', 'r\r\rs', 't\r\r'],
['\n\nu', 'v\n\nw', 'x\n\n'],
]
for lineterminator in '\r\n', '\n', '\r':
with self.subTest(lineterminator=lineterminator):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj, lineterminator=lineterminator,
quoting=csv.QUOTE_NONE, escapechar="\\")
writer.writerows(rows)
fileobj.seek(0)
for i, row in enumerate(csv.reader(fileobj,
quoting=csv.QUOTE_NONE,
escapechar="\\")):
self.assertEqual(row, rows[i])
class TestDialectRegistry(unittest.TestCase):
def test_registry_badargs(self):