Skip to content

[3.11] gh-67044: Always quote or escape \r and \n in csv.writer() (GH-115741) #115867

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
serhiy-storchaka merged 1 commit into from
Feb 23, 2024
Merged

[3.11] gh-67044: Always quote or escape \r and \n in csv.writer() (GH-115741) #115867

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
54 changes: 39 additions & 15 deletions Lib/test/test_csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,9 +237,11 @@ def test_write_lineterminator(self):
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"')
Expand Down Expand Up @@ -455,22 +457,44 @@ def test_read_linenum(self):
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):
Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Library/2024-02-20-22-02-34.gh-issue-67044.QF9_Ru.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
:func:`csv.writer` now always quotes or escapes ``'\r'`` and ``'\n'``,
regardless of *lineterminator* value.
2 changes: 2 additions & 0 deletions Modules/_csv.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1109,6 +1109,8 @@ join_append_data(WriterObj *self, unsigned int field_kind, const void *field_dat
if (c == dialect->delimiter ||
c == dialect->escapechar ||
c == dialect->quotechar ||
c == '\n' ||
c == '\r' ||
PyUnicode_FindChar(
dialect->lineterminator, c, 0,
PyUnicode_GET_LENGTH(dialect->lineterminator), 1) >= 0) {
Expand Down