Skip to content

gh-138621: Increase test coverage for csv.DictReader and csv.Sniffer #138622

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

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

gh-138621: Increase test coverage for csv.DictReader and csv.Sniffer #138622

Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a796f9d
Increase test coverage for csv.DictReader and csv.Sniffer
JanEricNitschke Sep 7, 2025
22346fb
Revert whitespace change to comment
JanEricNitschke Sep 7, 2025
9d6d36f
Add a test that csv.Sniffer.has_header checks up to 20 rows
JanEricNitschke Sep 8, 2025
e44e9df
Replace name and age with letter and offset
JanEricNitschke Sep 8, 2025
ccf93cf
Address review comment
JanEricNitschke Sep 8, 2025
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
30 changes: 30 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 @@ -918,6 +918,13 @@ def test_dict_reader_fieldnames_accepts_list(self):
reader = csv.DictReader(f, fieldnames)
self.assertEqual(reader.fieldnames, fieldnames)

def test_dict_reader_set_fieldnames(self):
fieldnames = ["a", "b", "c"]
f = StringIO()
reader = csv.DictReader(f)
reader.fieldnames = fieldnames
self.assertEqual(reader.fieldnames, fieldnames)

def test_dict_writer_fieldnames_rejects_iter(self):
fieldnames = ["a", "b", "c"]
f = StringIO()
Expand All @@ -933,6 +940,7 @@ def test_dict_writer_fieldnames_accepts_list(self):
def test_dict_reader_fieldnames_is_optional(self):
f = StringIO()
reader = csv.DictReader(f, fieldnames=None)
self.assertEqual(reader.fieldnames, None)

def test_read_dict_fields(self):
with TemporaryFile("w+", encoding="utf-8") as fileobj:
Expand Down Expand Up @@ -1353,6 +1361,18 @@ class TestSniffer(unittest.TestCase):
ghi\0jkl
"""

sample15 = "\n\n\n"
sample16 = "abc\ndef\nghi"

sample17 = ["letter,offset"]
sample17.extend(f"{chr(ord('a') + i)},{i}" for i in range(20))
sample17.append("v,twenty_one")
sample17 = '\n'.join(sample17)
sample18 = ["letter,offset"]
sample18.extend(f"{chr(ord('a') + i)},{i}" for i in range(21))
sample18.append("v,twenty_one")
sample18 = '\n'.join(sample18)

def test_issue43625(self):
sniffer = csv.Sniffer()
self.assertTrue(sniffer.has_header(self.sample12))
Expand All @@ -1374,6 +1394,11 @@ def test_has_header_regex_special_delimiter(self):
self.assertIs(sniffer.has_header(self.sample8), False)
self.assertIs(sniffer.has_header(self.header2 + self.sample8), True)

def test_has_header_checks_20_rows(self):
sniffer = csv.Sniffer()
self.assertIs(sniffer.has_header(self.sample17), False)
self.assertIs(sniffer.has_header(self.sample18), True)

def test_guess_quote_and_delimiter(self):
sniffer = csv.Sniffer()
for header in (";'123;4';", "'123;4';", ";'123;4'", "'123;4'"):
Expand Down Expand Up @@ -1423,6 +1448,11 @@ def test_delimiters(self):
self.assertEqual(dialect.quotechar, "'")
dialect = sniffer.sniff(self.sample14)
self.assertEqual(dialect.delimiter, '\0')
self.assertRaisesRegex(csv.Error, "Could not determine delimiter",
sniffer.sniff, self.sample15)
self.assertRaisesRegex(csv.Error, "Could not determine delimiter",
sniffer.sniff, self.sample16)


def test_doublequote(self):
sniffer = csv.Sniffer()
Expand Down
Loading