Skip to content

bpo-36346: Prepare for removing the legacy Unicode C API (AC only). #21223

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
merged 1 commit into from
Jun 30, 2020
Merged

bpo-36346: Prepare for removing the legacy Unicode C API (AC only). #21223

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 5 additions & 0 deletions Include/cpython/unicodeobject.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@

/* --- Internal Unicode Operations ---------------------------------------- */

#define USE_UNICODE_WCHAR_CACHE 1

/* Since splitting on whitespace is an important use case, and
whitespace in most situations is solely ASCII whitespace, we
optimize for the common case by using a quick look-up table
Expand Down Expand Up @@ -1177,4 +1179,7 @@ PyAPI_FUNC(PyObject*) _PyUnicode_FromId(_Py_Identifier*);
and where the hash values are equal (i.e. a very probable match) */
PyAPI_FUNC(int) _PyUnicode_EQ(PyObject *, PyObject *);

PyAPI_FUNC(int) _PyUnicode_WideCharString_Converter(PyObject *, void *);
PyAPI_FUNC(int) _PyUnicode_WideCharString_Opt_Converter(PyObject *, void *);

PyAPI_FUNC(Py_ssize_t) _PyUnicode_ScanIdentifier(PyObject *);
19 changes: 16 additions & 3 deletions Lib/test/clinic.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1813,13 +1813,26 @@ test_Py_UNICODE_converter(PyObject *module, PyObject *const *args, Py_ssize_t na
const Py_UNICODE *e;
Py_ssize_clean_t e_length;

if (!_PyArg_ParseStack(args, nargs, "uuZu#Z#:test_Py_UNICODE_converter",
&a, &b, &c, &d, &d_length, &e, &e_length)) {
if (!_PyArg_ParseStack(args, nargs, "O&O&O&u#Z#:test_Py_UNICODE_converter",
_PyUnicode_WideCharString_Converter, &a, _PyUnicode_WideCharString_Converter, &b, _PyUnicode_WideCharString_Opt_Converter, &c, &d, &d_length, &e, &e_length)) {
goto exit;
}
return_value = test_Py_UNICODE_converter_impl(module, a, b, c, d, d_length, e, e_length);

exit:
/* Cleanup for a */
#if !USE_UNICODE_WCHAR_CACHE
PyMem_Free((void *)a);
#endif /* USE_UNICODE_WCHAR_CACHE */
/* Cleanup for b */
#if !USE_UNICODE_WCHAR_CACHE
PyMem_Free((void *)b);
#endif /* USE_UNICODE_WCHAR_CACHE */
/* Cleanup for c */
#if !USE_UNICODE_WCHAR_CACHE
PyMem_Free((void *)c);
#endif /* USE_UNICODE_WCHAR_CACHE */

return return_value;
}

Expand All @@ -1830,7 +1843,7 @@ test_Py_UNICODE_converter_impl(PyObject *module, const Py_UNICODE *a,
Py_ssize_clean_t d_length,
const Py_UNICODE *e,
Py_ssize_clean_t e_length)
/*[clinic end generated code: output=dd0a09a1b772e57b input=064a3b68ad7f04b0]*/
/*[clinic end generated code: output=ef45e982fedf0b3d input=064a3b68ad7f04b0]*/


/*[clinic input]
Expand Down
15 changes: 12 additions & 3 deletions Modules/clinic/_winapi.c.h
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

63 changes: 56 additions & 7 deletions Modules/clinic/posixmodule.c.h
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

74 changes: 74 additions & 0 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3273,6 +3273,80 @@ PyUnicode_AsWideCharString(PyObject *unicode,

#endif /* HAVE_WCHAR_H */

int
_PyUnicode_WideCharString_Converter(PyObject *obj, void *ptr)
{
wchar_t **p = (wchar_t **)ptr;
if (obj == NULL) {
#if !USE_UNICODE_WCHAR_CACHE
PyMem_Free(*p);
#endif /* USE_UNICODE_WCHAR_CACHE */
*p = NULL;
return 1;
}
if (PyUnicode_Check(obj)) {
#if USE_UNICODE_WCHAR_CACHE
_Py_COMP_DIAG_PUSH
_Py_COMP_DIAG_IGNORE_DEPR_DECLS
*p = (wchar_t *)_PyUnicode_AsUnicode(obj);
if (*p == NULL) {
return 0;
}
return 1;
_Py_COMP_DIAG_POP
#else /* USE_UNICODE_WCHAR_CACHE */
*p = PyUnicode_AsWideCharString(obj, NULL);
if (*p == NULL) {
return 0;
}
return Py_CLEANUP_SUPPORTED;
#endif /* USE_UNICODE_WCHAR_CACHE */
}
PyErr_Format(PyExc_TypeError,
"argument must be str, not %.50s",
obj->ob_type->tp_name);
return 0;
}

int
_PyUnicode_WideCharString_Opt_Converter(PyObject *obj, void *ptr)
{
wchar_t **p = (wchar_t **)ptr;
if (obj == NULL) {
#if !USE_UNICODE_WCHAR_CACHE
PyMem_Free(*p);
#endif /* USE_UNICODE_WCHAR_CACHE */
*p = NULL;
return 1;
}
if (obj == Py_None) {
*p = NULL;
return 1;
}
if (PyUnicode_Check(obj)) {
#if USE_UNICODE_WCHAR_CACHE
_Py_COMP_DIAG_PUSH
_Py_COMP_DIAG_IGNORE_DEPR_DECLS
*p = (wchar_t *)_PyUnicode_AsUnicode(obj);
if (*p == NULL) {
return 0;
}
return 1;
_Py_COMP_DIAG_POP
#else /* USE_UNICODE_WCHAR_CACHE */
*p = PyUnicode_AsWideCharString(obj, NULL);
if (*p == NULL) {
return 0;
}
return Py_CLEANUP_SUPPORTED;
#endif /* USE_UNICODE_WCHAR_CACHE */
}
PyErr_Format(PyExc_TypeError,
"argument must be str or None, not %.50s",
obj->ob_type->tp_name);
return 0;
}

PyObject *
PyUnicode_FromOrdinal(int ordinal)
{
Expand Down
Loading