gh-94526: getpath_dirname() no longer encodes the path (GH-97645)

Fix the Python path configuration used to initialized sys.path at
Python startup. Paths are no longer encoded to UTF-8/strict to avoid
encoding errors if it contains surrogate characters (bytes paths are
decoded with the surrogateescape error handler).

getpath_basename() and getpath_dirname() functions no longer encode
the path to UTF-8/strict, but work directly on Unicode strings. These
functions now use PyUnicode_FindChar() and PyUnicode_Substring() on
the Unicode path, rather than strrchr() on the encoded bytes string.
(cherry picked from commit 9f2f1dd131)

Co-authored-by: Victor Stinner <vstinner@python.org>
This commit is contained in:
Miss Islington (bot) 2022-09-30 06:38:41 -07:00 committed by GitHub
parent 0fbee30f71
commit 6537bc9a49
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 18 additions and 9 deletions

View file

@ -0,0 +1,4 @@
Fix the Python path configuration used to initialized :data:`sys.path` at
Python startup. Paths are no longer encoded to UTF-8/strict to avoid encoding
errors if it contains surrogate characters (bytes paths are decoded with the
surrogateescape error handler). Patch by Victor Stinner.

View file

@ -82,27 +82,32 @@ getpath_abspath(PyObject *Py_UNUSED(self), PyObject *args)
static PyObject *
getpath_basename(PyObject *Py_UNUSED(self), PyObject *args)
{
const char *path;
if (!PyArg_ParseTuple(args, "s", &path)) {
PyObject *path;
if (!PyArg_ParseTuple(args, "U", &path)) {
return NULL;
}
const char *name = strrchr(path, SEP);
return PyUnicode_FromString(name ? name + 1 : path);
Py_ssize_t end = PyUnicode_GET_LENGTH(path);
Py_ssize_t pos = PyUnicode_FindChar(path, SEP, 0, end, -1);
if (pos < 0) {
return Py_NewRef(path);
}
return PyUnicode_Substring(path, pos + 1, end);
}
static PyObject *
getpath_dirname(PyObject *Py_UNUSED(self), PyObject *args)
{
const char *path;
if (!PyArg_ParseTuple(args, "s", &path)) {
PyObject *path;
if (!PyArg_ParseTuple(args, "U", &path)) {
return NULL;
}
const char *name = strrchr(path, SEP);
if (!name) {
Py_ssize_t end = PyUnicode_GET_LENGTH(path);
Py_ssize_t pos = PyUnicode_FindChar(path, SEP, 0, end, -1);
if (pos < 0) {
return PyUnicode_FromStringAndSize(NULL, 0);
}
return PyUnicode_FromStringAndSize(path, (name - path));
return PyUnicode_Substring(path, 0, pos);
}