Skip to content

gh-123378: fix a crash in UnicodeError.__str__ #124935

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 11 commits into from
Oct 8, 2024
Merged

gh-123378: fix a crash in UnicodeError.__str__ #124935

Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
a9b1c0c
fix OOB in `UnicodeError.__str__`
picnixz Oct 3, 2024
3567426
blurb
picnixz Oct 3, 2024
43141c0
add tests
picnixz Oct 3, 2024
0c61375
small fixup
picnixz Oct 3, 2024
80287f6
Fix Windows compilation
picnixz Oct 3, 2024
7bbc0f5
improve test coverage
picnixz Oct 4, 2024
2313cd1
fix `UnicodeTranslateError`
picnixz Oct 4, 2024
a27a88b
improve test coverage
picnixz Oct 4, 2024
360c1a5
revert cosmetic changes
picnixz Oct 5, 2024
85199f8
add back PEP-7 braces
picnixz Oct 7, 2024
44dfaeb
address Victor's review
picnixz Oct 8, 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
fix UnicodeTranslateError
  • Loading branch information
@picnixz
picnixz committed Oct 4, 2024
commit 2313cd1def7843e9d5f42690805c7ca1373d8b8f
55 changes: 28 additions & 27 deletions Objects/exceptions.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3205,46 +3205,47 @@ UnicodeTranslateError_init(PyUnicodeErrorObject *self, PyObject *args,
static PyObject *
UnicodeTranslateError_str(PyObject *self)
{
PyUnicodeErrorObject *uself = (PyUnicodeErrorObject *)self;
PyObject *result = NULL;
PyObject *reason_str = NULL;
PyUnicodeErrorObject *exc = (PyUnicodeErrorObject *)self;

if (!uself->object)
if (exc->object == NULL) {
/* Not properly initialized. */
return PyUnicode_FromString("");
}

/* Get reason as a string, which it might not be if it's been
modified after we were constructed. */
reason_str = PyObject_Str(uself->reason);
if (reason_str == NULL)
goto done;
PyObject *reason = PyObject_Str(exc->reason);
if (reason == NULL) {
return NULL;
}

PyObject *res;
Py_ssize_t len = PyUnicode_GET_LENGTH(exc->object);
Py_ssize_t start = exc->start, end = exc->end;

if (uself->start < PyUnicode_GET_LENGTH(uself->object) && uself->end == uself->start+1) {
Py_UCS4 badchar = PyUnicode_ReadChar(uself->object, uself->start);
if ((start >= 0 && start < len) && (end >= 0 && end <= len) && end == start + 1) {
Py_UCS4 badchar = PyUnicode_ReadChar(exc->object, start);
const char *fmt;
if (badchar <= 0xff)
if (badchar <= 0xff) {
fmt = "can't translate character '\\x%02x' in position %zd: %U";
else if (badchar <= 0xffff)
}
else if (badchar <= 0xffff) {
fmt = "can't translate character '\\u%04x' in position %zd: %U";
else
}
else {
fmt = "can't translate character '\\U%08x' in position %zd: %U";
result = PyUnicode_FromFormat(
fmt,
(int)badchar,
uself->start,
reason_str
);
} else {
result = PyUnicode_FromFormat(
}
res = PyUnicode_FromFormat(fmt, (int)badchar, start, reason);
}
else {
res = PyUnicode_FromFormat(
"can't translate characters in position %zd-%zd: %U",
uself->start,
uself->end-1,
reason_str
);
start, end - 1, reason
);
}
done:
Py_XDECREF(reason_str);
return result;

Py_DECREF(reason);
return res;
}

static PyTypeObject _PyExc_UnicodeTranslateError = {
Expand Down