Skip to content

Update codecs from 3.13.7 #6130

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
youknowone merged 3 commits into from
Sep 7, 2025
Merged

Update codecs from 3.13.7 #6130

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8cd0410
Update `codecs` from 3.13.7
ShaharNaveh Sep 5, 2025
dd30099
Mark failing tests
ShaharNaveh Sep 5, 2025
9efb9dd
Resotre some missing comments
ShaharNaveh Sep 5, 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
Prev Previous commit
Next Next commit
Mark failing tests
  • Loading branch information
@ShaharNaveh
ShaharNaveh committed Sep 5, 2025
commit dd300991ee17e844558b75cf19d4e501067802ce
14 changes: 12 additions & 2 deletions Lib/test/test_codecs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -762,6 +762,7 @@ def test_only_one_bom(self):
f = reader(s)
self.assertEqual(f.read(), "spamspam")

@unittest.expectedFailure # TODO: RUSTPYTHON;; UTF-16 stream does not start with BOM
def test_badbom(self):
s = io.BytesIO(b"\xff\xff")
f = codecs.getreader(self.encoding)(s)
Expand Down Expand Up @@ -810,7 +811,6 @@ def test_decoder_state(self):
self.check_state_handling_decode(self.encoding,
"spamspam", self.spambe)

@unittest.expectedFailure # TODO: RUSTPYTHON; - ValueError: invalid mode 'Ub'
def test_bug691291(self):
# If encoding is not None, then
# files are always opened in binary mode, even if no binary mode was
Expand Down Expand Up @@ -1335,6 +1335,7 @@ def test_escape(self):
check(br"[\x41]", b"[A]")
check(br"[\x410]", b"[A0]")

@unittest.expectedFailure # TODO: RUSTPYTHON; DeprecationWarning not triggered
def test_warnings(self):
decode = codecs.escape_decode
check = coding_checker(self, decode)
Expand Down Expand Up @@ -1508,6 +1509,7 @@ def test_decode(self):
puny = puny.decode("ascii").encode("ascii")
self.assertEqual(uni, puny.decode("punycode"))

@unittest.expectedFailure # TODO: RUSTPYTHON; b'Pro\xffprostnemluvesky' != b'Pro\xffprostnemluvesky-uyb24dma41a'
def test_decode_invalid(self):
testcases = [
(b"xn--w&", "strict", UnicodeDecodeError("punycode", b"", 5, 6, "")),
Expand Down Expand Up @@ -1692,6 +1694,7 @@ def test_decode_invalid(self):


class NameprepTest(unittest.TestCase):
@unittest.expectedFailure # TODO: RUSTPYTHON; UnicodeError: Invalid character '\u1680'
def test_nameprep(self):
from encodings.idna import nameprep
for pos, (orig, prepped) in enumerate(nameprep_tests):
Expand Down Expand Up @@ -1729,6 +1732,7 @@ class IDNACodecTest(unittest.TestCase):
("あさ.\u034f", UnicodeEncodeError("idna", "あさ.\u034f", 3, 4, "")),
]

@unittest.expectedFailure # TODO: RUSTPYTHON; 'XN--pythn-mua.org.' != 'pythön.org.'
def test_builtin_decode(self):
self.assertEqual(str(b"python.org", "idna"), "python.org")
self.assertEqual(str(b"python.org.", "idna"), "python.org.")
Expand All @@ -1742,6 +1746,7 @@ def test_builtin_decode(self):
self.assertEqual(str(b"bugs.XN--pythn-mua.org.", "idna"),
"bugs.pyth\xf6n.org.")

@unittest.expectedFailure # TODO: RUSTPYTHON; 'ascii' != 'idna'
def test_builtin_decode_invalid(self):
for case, expected in self.invalid_decode_testcases:
with self.subTest(case=case, expected=expected):
Expand All @@ -1759,6 +1764,7 @@ def test_builtin_encode(self):
self.assertEqual("pyth\xf6n.org".encode("idna"), b"xn--pythn-mua.org")
self.assertEqual("pyth\xf6n.org.".encode("idna"), b"xn--pythn-mua.org.")

@unittest.expectedFailure # TODO: RUSTPYTHON; UnicodeError: label empty or too long
def test_builtin_encode_invalid(self):
for case, expected in self.invalid_encode_testcases:
with self.subTest(case=case, expected=expected):
Expand All @@ -1770,6 +1776,7 @@ def test_builtin_encode_invalid(self):
self.assertEqual(exc.start, expected.start)
self.assertEqual(exc.end, expected.end)

@unittest.expectedFailure # TODO: RUSTPYTHON; UnicodeError: label empty or too long
def test_builtin_decode_length_limit(self):
with self.assertRaisesRegex(UnicodeDecodeError, "way too long"):
(b"xn--016c"+b"a"*1100).decode("idna")
Expand Down Expand Up @@ -1811,6 +1818,7 @@ def test_incremental_decode(self):
self.assertEqual(decoder.decode(b"rg."), "org.")
self.assertEqual(decoder.decode(b"", True), "")

@unittest.expectedFailure # TODO: RUSTPYTHON; 'ascii' != 'idna'
def test_incremental_decode_invalid(self):
iterdecode_testcases = [
(b"\xFFpython.org", UnicodeDecodeError("idna", b"\xFF", 0, 1, "")),
Expand Down Expand Up @@ -1872,6 +1880,7 @@ def test_incremental_encode(self):
self.assertEqual(encoder.encode("ample.org."), b"xn--xample-9ta.org.")
self.assertEqual(encoder.encode("", True), b"")

@unittest.expectedFailure # TODO: RUSTPYTHON; UnicodeError: label empty or too long
def test_incremental_encode_invalid(self):
iterencode_testcases = [
(f"foo.{'\xff'*60}", UnicodeEncodeError("idna", f"{'\xff'*60}", 0, 60, "")),
Expand Down Expand Up @@ -2801,7 +2810,6 @@ def test_escape_encode(self):
check('\u20ac', br'\u20ac')
check('\U0001d120', br'\U0001d120')

@unittest.expectedFailure # TODO: RUSTPYTHON
def test_escape_decode(self):
decode = codecs.unicode_escape_decode
check = coding_checker(self, decode)
Expand All @@ -2827,6 +2835,7 @@ def test_escape_decode(self):
check(br"\u20ac", "\u20ac")
check(br"\U0001d120", "\U0001d120")

@unittest.expectedFailure # TODO: RUSTPYTHON; DeprecationWarning not triggered
def test_decode_warnings(self):
decode = codecs.unicode_escape_decode
check = coding_checker(self, decode)
Expand Down Expand Up @@ -3420,6 +3429,7 @@ def test_codec_lookup_failure(self):
with self.assertRaisesRegex(LookupError, msg):
codecs.decode(b"bytes input", self.codec_name)

@unittest.expectedFailure # TODO: RUSTPYTHON;
def test_unflagged_non_text_codec_handling(self):
# The stdlib non-text codecs are now marked so they're
# pre-emptively skipped by the text model related methods
Expand Down