Skip to content

gh-119609: Add PyUnicode_Export() and PyUnicode_Import() functions #119610

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

Closed
vstinner wants to merge 13 commits into from
Closed

gh-119609: Add PyUnicode_Export() and PyUnicode_Import() functions #119610

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
32a373a
gh-119609: Add PyUnicode_Export() function
vstinner May 27, 2024
c42cebc
stable_abi.toml: Add constants
vstinner Jun 21, 2024
1310b6d
Export UCS1 as UCS2
vstinner Jun 21, 2024
1c78103
Add test_unicode_export_import_roundtrip()
vstinner Jun 21, 2024
62f4598
Rename size parameter to nbytes
vstinner Jun 21, 2024
53cd937
Update doc
vstinner Jun 21, 2024
3a08491
Make sure that exported string ends with NUL character
vstinner Jun 21, 2024
a9a9083
tests: rename size to nbytes
vstinner Jun 21, 2024
1297c52
Update Doc/c-api/unicode.rst
vstinner Jun 22, 2024
d8e3d5d
Update Doc/c-api/unicode.rst
vstinner Jun 22, 2024
da67c89
Address Petr's review
vstinner Jun 22, 2024
894921a
Merge branch 'main' into unicode_native
vstinner Jun 22, 2024
f3857d8
Fix doc: add uint32_t type
vstinner Jun 26, 2024
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
Add test_unicode_export_import_roundtrip()
  • Loading branch information
@vstinner
vstinner committed Jun 21, 2024
commit 1c781036927abd5be60212a45814f06b12fa69d7
34 changes: 34 additions & 0 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 @@ -1808,5 +1808,39 @@ def test_unicode_import(self):
unicode_import(ucs4[:-3], PyUnicode_FORMAT_UCS4)



def test_unicode_export_import_roundtrip(self):
unicode_export = _testlimitedcapi.unicode_export
unicode_import = _testlimitedcapi.unicode_import

ASCII = PyUnicode_FORMAT_ASCII
UCS1 = PyUnicode_FORMAT_UCS1
UCS2 = PyUnicode_FORMAT_UCS2
UCS4 = PyUnicode_FORMAT_UCS4
UTF8 = PyUnicode_FORMAT_UTF8
ALL = (ASCII | UCS1 | UCS2 | UCS4 | UTF8)

for string, allowed_formats in (
('', {ASCII, UCS1, UCS2, UCS4, UTF8}),
('ascii', {ASCII, UCS1, UCS2, UCS4, UTF8}),
('latin1:\xe9', {UCS1, UCS2, UCS4, UTF8}),
('ucs2:\u20ac', {UCS2, UCS4, UTF8}),
('ucs4:\U0001f638', {UCS4, UTF8}),
):
for format in ASCII, UCS1, UCS2, UCS4, UTF8:
with self.subTest(string=string, format=format):
if format not in allowed_formats:
with self.assertRaises(ValueError):
unicode_export(string, format)
else:
buf, buf_fmt = unicode_export(string, format)
restored = unicode_import(buf, buf_fmt)
self.assertEqual(restored, string)

buf, buf_fmt = unicode_export(string, ALL)
restored = unicode_import(buf, buf_fmt)
self.assertEqual(restored, string)


if __name__ == '__main__':
unittest.main()
6 changes: 3 additions & 3 deletions Modules/_testlimitedcapi/unicode.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1843,14 +1843,14 @@ static PyObject*
unicode_export(PyObject *self, PyObject *args)
{
PyObject *obj;
unsigned int supported_formats;
if (!PyArg_ParseTuple(args, "OI", &obj, &supported_formats)) {
unsigned int requested_formats;
if (!PyArg_ParseTuple(args, "OI", &obj, &requested_formats)) {
return NULL;
}

Py_ssize_t size;
uint32_t format;
const void *data = PyUnicode_Export(obj, supported_formats, &size, &format);
const void *data = PyUnicode_Export(obj, requested_formats, &size, &format);
if (data == NULL) {
return NULL;
}
Expand Down