Skip to content

[3.13] gh-103925: Fix csv.Sniffer for a quoted field ending a CRLF line (GH-103926) #154330

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
Jul 21, 2026
+13 −4
Merged

[3.13] gh-103925: Fix csv.Sniffer for a quoted field ending a CRLF line (GH-103926) #154330

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
8 changes: 4 additions & 4 deletions Lib/csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -283,10 +283,10 @@ def _guess_quote_and_delimiter(self, data, delimiters):
"""

matches = []
for restr in (r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?",
r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)', # ".*?",
r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?"
r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)'): # ".*?" (no delim, no space)
for restr in (r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?",
r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)', # ".*?",
r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\r|\n)', # ,".*?"
r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\r|\n)'): # ".*?" (no delim, no space)
regexp = re.compile(restr, re.DOTALL | re.MULTILINE)
matches = regexp.findall(data)
if matches:
Expand Down
6 changes: 6 additions & 0 deletions Lib/test/test_csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1357,6 +1357,9 @@ class TestSniffer(unittest.TestCase):
ghi\0jkl
"""

sample19 = ('time,title\r\n'
'2020-10-01,"Pocket - Save news, videos, stories and more"\r\n')

def test_issue43625(self):
sniffer = csv.Sniffer()
self.assertTrue(sniffer.has_header(self.sample12))
Expand Down Expand Up @@ -1427,6 +1430,9 @@ def test_delimiters(self):
self.assertEqual(dialect.quotechar, "'")
dialect = sniffer.sniff(self.sample14)
self.assertEqual(dialect.delimiter, '\0')
dialect = sniffer.sniff(self.sample19)
self.assertEqual(dialect.delimiter, ',')
self.assertEqual(dialect.quotechar, '"')

def test_doublequote(self):
sniffer = csv.Sniffer()
Expand Down
3 changes: 3 additions & 0 deletions Misc/NEWS.d/next/Library/2023-04-27-14-50-03.gh-issue-103925.khC-El.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
Fix :meth:`csv.Sniffer.sniff` for a sample with ``\r\n`` line endings in
which a quoted field ends a line: a letter could be detected as the
delimiter.
Loading