Skip to content

gh-119182: Add PyUnicodeWriter_DecodeUTF8Stateful() #120639

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
vstinner merged 9 commits into from
Jun 21, 2024
Merged

gh-119182: Add PyUnicodeWriter_DecodeUTF8Stateful() #120639

Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
8aa73b7
gh-119182: Add PyUnicodeWriter_DecodeUTF8Stateful()
vstinner Jun 17, 2024
788a85f
doc: fix typo
vstinner Jun 17, 2024
e67a8b4
Optimize PyUnicodeWriter_WriteWideChar()
vstinner Jun 19, 2024
de56475
Update Objects/unicodeobject.c
serhiy-storchaka Jun 19, 2024
e48eec7
Fix compiler warning
vstinner Jun 19, 2024
75fa8ba
Add unicode_write_widechar()
vstinner Jun 20, 2024
3f284f8
Update Doc/c-api/unicode.rst
vstinner Jun 20, 2024
1e018d2
Address Serhiy's review
vstinner Jun 20, 2024
6f29c53
Add more tests
vstinner Jun 20, 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
Add more tests
  • Loading branch information
@vstinner
vstinner committed Jun 20, 2024
commit 6f29c53223b57e7fa1eca35dcf7d9446d278a180
35 changes: 33 additions & 2 deletions Modules/_testcapi/unicode.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -391,12 +391,22 @@ test_unicodewriter_decode_utf8(PyObject *self, PyObject *Py_UNUSED(args))
if (PyUnicodeWriter_DecodeUTF8Stateful(writer, "replace\xFF", -1, "replace", NULL) < 0) {
Comment thread
vstinner marked this conversation as resolved.
goto error;
}
if (PyUnicodeWriter_WriteChar(writer, '-') < 0) {
goto error;
}

// incomplete trailing UTF-8 sequence
if (PyUnicodeWriter_DecodeUTF8Stateful(writer, "incomplete\xC3", -1, "replace", NULL) < 0) {
goto error;
}

PyObject *result = PyUnicodeWriter_Finish(writer);
if (result == NULL) {
return NULL;
}
assert(PyUnicode_EqualToUTF8(result, "ignore-replace\xef\xbf\xbd"));
assert(PyUnicode_EqualToUTF8(result,
"ignore-replace\xef\xbf\xbd"
"-incomplete\xef\xbf\xbd"));
Py_DECREF(result);

Py_RETURN_NONE;
Expand All @@ -423,7 +433,16 @@ test_unicodewriter_decode_utf8_consumed(PyObject *self, PyObject *Py_UNUSED(args
goto error;
}
assert(consumed == 4);
if (PyUnicodeWriter_WriteChar(writer, '-') < 0) {
goto error;
}

// non-ASCII
consumed = 12345;
if (PyUnicodeWriter_DecodeUTF8Stateful(writer, "\xC3\xA9-\xE2\x82\xAC", 6, NULL, &consumed) < 0) {
goto error;
}
assert(consumed == 6);
if (PyUnicodeWriter_WriteChar(writer, '-') < 0) {
goto error;
}
Expand All @@ -440,12 +459,24 @@ test_unicodewriter_decode_utf8_consumed(PyObject *self, PyObject *Py_UNUSED(args
goto error;
}
assert(consumed == 5);
if (PyUnicodeWriter_WriteChar(writer, '-') < 0) {
goto error;
}

// incomplete trailing UTF-8 sequence
consumed = 12345;
if (PyUnicodeWriter_DecodeUTF8Stateful(writer, "incomplete\xC3", -1, "ignore", &consumed) < 0) {
goto error;
}
assert(consumed == 10);

PyObject *result = PyUnicodeWriter_Finish(writer);
if (result == NULL) {
return NULL;
}
assert(PyUnicode_EqualToUTF8(result, "text-more"));
assert(PyUnicode_EqualToUTF8(result,
"text-\xC3\xA9-\xE2\x82\xAC-"
"more-incomplete"));
Py_DECREF(result);

Py_RETURN_NONE;
Expand Down