Skip to content

gh-99612: Fix PyUnicode_DecodeUTF8Stateful() for ASCII-only data #99613

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 5 commits into from
Dec 1, 2022
Merged

gh-99612: Fix PyUnicode_DecodeUTF8Stateful() for ASCII-only data #99613

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8ff13de
gh-99612: Fix PyUnicode_DecodeUTF8Stateful() for ASCII-only data
serhiy-storchaka Nov 20, 2022
b99be83
Move tests to test_capi.test_codecs.
serhiy-storchaka Nov 21, 2022
3d23080
Merge branch 'main' into capi-PyUnicode_DecodeUTF8Stateful
serhiy-storchaka Nov 29, 2022
1c07d9f
Merge branch 'main' into capi-PyUnicode_DecodeUTF8Stateful
serhiy-storchaka Nov 30, 2022
fd8c21d
Address review comments.
serhiy-storchaka Nov 30, 2022
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
Move tests to test_capi.test_codecs.
  • Loading branch information
@serhiy-storchaka
serhiy-storchaka committed Nov 21, 2022
commit b99be83be8265de6a5aef221d57879dc8c98c61d
61 changes: 61 additions & 0 deletions Lib/test/test_capi/test_codecs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,61 @@
import unittest
from test import support

try:
import _testcapi
except ImportError:
_testcapi = None
Copy link
Copy Markdown
Member

@vstinner vstinner Nov 29, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why not skipping this test if the module is missing?



class CAPITest(unittest.TestCase):

@support.cpython_only
Copy link
Copy Markdown
Member

@vstinner vstinner Nov 29, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For me it's redundant with testing _testcapi. For example, PyPy doesn't have _testcapi. But you can keep it if you prefer to be explicit.

@unittest.skipIf(_testcapi is None, 'need _testcapi module')
Copy link
Copy Markdown
Member

@vstinner vstinner Nov 29, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

IMO you can move it on the whole class.

def test_decodeutf8(self):
"""Test PyUnicode_DecodeUTF8()"""
from _testcapi import unicode_decodeutf8 as decodeutf8
Copy link
Copy Markdown
Member

@vstinner vstinner Nov 29, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You may use decodeutf8 = _testcapi.unicode_decodeutf8.


for s in ['abc', '\xa1\xa2', '\u4f60\u597d', 'a\U0001f600']:
b = s.encode('utf-8')
self.assertEqual(decodeutf8(b), s)
self.assertEqual(decodeutf8(b, 'strict'), s)

self.assertRaises(UnicodeDecodeError, decodeutf8, b'\x80')
self.assertRaises(UnicodeDecodeError, decodeutf8, b'\xc0')
self.assertRaises(UnicodeDecodeError, decodeutf8, b'\xff')
self.assertRaises(UnicodeDecodeError, decodeutf8, b'a\xf0\x9f')
self.assertEqual(decodeutf8(b'a\xf0\x9f', 'replace'), 'a\ufffd')
self.assertEqual(decodeutf8(b'a\xf0\x9fb', 'replace'), 'a\ufffdb')

self.assertRaises(LookupError, decodeutf8, b'a\x80', 'foo')
# TODO: Test PyUnicode_DecodeUTF8() with NULL as data and
# negative size.

@support.cpython_only
@unittest.skipIf(_testcapi is None, 'need _testcapi module')
def test_decodeutf8stateful(self):
"""Test PyUnicode_DecodeUTF8Stateful()"""
from _testcapi import unicode_decodeutf8stateful as decodeutf8stateful

for s in ['abc', '\xa1\xa2', '\u4f60\u597d', 'a\U0001f600']:
b = s.encode('utf-8')
self.assertEqual(decodeutf8stateful(b), (s, len(b)))
self.assertEqual(decodeutf8stateful(b, 'strict'), (s, len(b)))

self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\x80')
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\xc0')
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\xff')
self.assertEqual(decodeutf8stateful(b'a\xf0\x9f'), ('a', 1))
self.assertEqual(decodeutf8stateful(b'a\xf0\x9f', 'replace'), ('a', 1))
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'a\xf0\x9fb')
self.assertEqual(decodeutf8stateful(b'a\xf0\x9fb', 'replace'), ('a\ufffdb', 4))

self.assertRaises(LookupError, decodeutf8stateful, b'a\x80', 'foo')
# TODO: Test PyUnicode_DecodeUTF8Stateful() with NULL as data and
# negative size.
# TODO: Test PyUnicode_DecodeUTF8Stateful() with NULL as the address of
# "consumed".


if __name__ == "__main__":
unittest.main()
47 changes: 0 additions & 47 deletions Lib/test/test_capi/test_unicode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,53 +11,6 @@

class CAPITest(unittest.TestCase):

@support.cpython_only
@unittest.skipIf(_testcapi is None, 'need _testcapi module')
def test_decodeutf8(self):
"""Test PyUnicode_DecodeUTF8()"""
from _testcapi import unicode_decodeutf8 as decodeutf8

for s in ['abc', '\xa1\xa2', '\u4f60\u597d', 'a\U0001f600']:
b = s.encode('utf-8')
self.assertEqual(decodeutf8(b), s)
self.assertEqual(decodeutf8(b, 'strict'), s)

self.assertRaises(UnicodeDecodeError, decodeutf8, b'\x80')
self.assertRaises(UnicodeDecodeError, decodeutf8, b'\xc0')
self.assertRaises(UnicodeDecodeError, decodeutf8, b'\xff')
self.assertRaises(UnicodeDecodeError, decodeutf8, b'a\xf0\x9f')
self.assertEqual(decodeutf8(b'a\xf0\x9f', 'replace'), 'a\ufffd')
self.assertEqual(decodeutf8(b'a\xf0\x9fb', 'replace'), 'a\ufffdb')

self.assertRaises(LookupError, decodeutf8, b'a\x80', 'foo')
# TODO: Test PyUnicode_DecodeUTF8() with NULL as data and
# negative size.

@support.cpython_only
@unittest.skipIf(_testcapi is None, 'need _testcapi module')
def test_decodeutf8stateful(self):
"""Test PyUnicode_DecodeUTF8Stateful()"""
from _testcapi import unicode_decodeutf8stateful as decodeutf8stateful

for s in ['abc', '\xa1\xa2', '\u4f60\u597d', 'a\U0001f600']:
b = s.encode('utf-8')
self.assertEqual(decodeutf8stateful(b), (s, len(b)))
self.assertEqual(decodeutf8stateful(b, 'strict'), (s, len(b)))

self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\x80')
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\xc0')
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\xff')
self.assertEqual(decodeutf8stateful(b'a\xf0\x9f'), ('a', 1))
self.assertEqual(decodeutf8stateful(b'a\xf0\x9f', 'replace'), ('a', 1))
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'a\xf0\x9fb')
self.assertEqual(decodeutf8stateful(b'a\xf0\x9fb', 'replace'), ('a\ufffdb', 4))

self.assertRaises(LookupError, decodeutf8stateful, b'a\x80', 'foo')
# TODO: Test PyUnicode_DecodeUTF8Stateful() with NULL as data and
# negative size.
# TODO: Test PyUnicode_DecodeUTF8Stateful() with NULL as the address of
# "consumed".

# Test PyUnicode_FromFormat()
def test_from_format(self):
import_helper.import_module('ctypes')
Expand Down