Stowage/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-12-08 06:10:17 +00:00
Code Issues Projects Releases Packages Wiki Activity

gh-138621: Increase test coverage for csv.DictReader and csv.Sniffer (GH-138622)

Browse source 
* Increase test coverage for csv.DictReader and csv.Sniffer

Previously there were no tests for the DictReader fieldnames
setter, the case where a StopIteration was encountered when trying
to determine the fieldnames from the content or the case where
Sniffer could not find a delimiter.

* Revert whitespace change to comment

* Add a test that csv.Sniffer.has_header checks up to 20 rows

* Replace name and age with letter and offset

Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com>

* Address review comment

---------

Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com>
Co-authored-by: Gregory P. Smith <68491+gpshead@users.noreply.github.com>
This commit is contained in:
Jan-Eric Nitschke 2025-11-12 01:32:26 +01:00 • committed by GitHub
parent 0d7b48a8f5
commit 0e88be6f55
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 31 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

31
Lib/test/test_csv.py
View file

@ -918,6 +918,14 @@ def test_dict_reader_fieldnames_accepts_list(self):
reader = csv.DictReader(f, fieldnames) reader = csv.DictReader(f, fieldnames)
self.assertEqual(reader.fieldnames, fieldnames) self.assertEqual(reader.fieldnames, fieldnames)
def test_dict_reader_set_fieldnames(self):
fieldnames = ["a", "b", "c"]
f = StringIO()
reader = csv.DictReader(f)
self.assertIsNone(reader.fieldnames)
reader.fieldnames = fieldnames
self.assertEqual(reader.fieldnames, fieldnames)
def test_dict_writer_fieldnames_rejects_iter(self): def test_dict_writer_fieldnames_rejects_iter(self):
fieldnames = ["a", "b", "c"] fieldnames = ["a", "b", "c"]
f = StringIO() f = StringIO()
@ -933,6 +941,7 @@ def test_dict_writer_fieldnames_accepts_list(self):
def test_dict_reader_fieldnames_is_optional(self): def test_dict_reader_fieldnames_is_optional(self):
f = StringIO() f = StringIO()
reader = csv.DictReader(f, fieldnames=None) reader = csv.DictReader(f, fieldnames=None)
self.assertIsNone(reader.fieldnames)
def test_read_dict_fields(self): def test_read_dict_fields(self):
with TemporaryFile("w+", encoding="utf-8") as fileobj: with TemporaryFile("w+", encoding="utf-8") as fileobj:
@ -1353,6 +1362,19 @@ class TestSniffer(unittest.TestCase):
ghi\0jkl 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") # 'u' was skipped
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") # 'u' was not skipped
sample18 = '\n'.join(sample18)
def test_issue43625(self): def test_issue43625(self):
sniffer = csv.Sniffer() sniffer = csv.Sniffer()
self.assertTrue(sniffer.has_header(self.sample12)) self.assertTrue(sniffer.has_header(self.sample12))
@ -1374,6 +1396,11 @@ def test_has_header_regex_special_delimiter(self):
self.assertIs(sniffer.has_header(self.sample8), False) self.assertIs(sniffer.has_header(self.sample8), False)
self.assertIs(sniffer.has_header(self.header2 + self.sample8), True) self.assertIs(sniffer.has_header(self.header2 + self.sample8), True)
def test_has_header_checks_20_rows(self):
sniffer = csv.Sniffer()
self.assertFalse(sniffer.has_header(self.sample17))
self.assertTrue(sniffer.has_header(self.sample18))
def test_guess_quote_and_delimiter(self): def test_guess_quote_and_delimiter(self):
sniffer = csv.Sniffer() sniffer = csv.Sniffer()
for header in (";'123;4';", "'123;4';", ";'123;4'", "'123;4'"): for header in (";'123;4';", "'123;4';", ";'123;4'", "'123;4'"):
@ -1423,6 +1450,10 @@ def test_delimiters(self):
self.assertEqual(dialect.quotechar, "'") self.assertEqual(dialect.quotechar, "'")
dialect = sniffer.sniff(self.sample14) dialect = sniffer.sniff(self.sample14)
self.assertEqual(dialect.delimiter, '\0') 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): def test_doublequote(self):
sniffer = csv.Sniffer() sniffer = csv.Sniffer()