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

Show file tree
Hide file tree
Changes from 5 commits
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
17 changes: 17 additions & 0 deletions Lib/test/test_exceptions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
import weakref
import errno
from codecs import BOM_UTF8
from itertools import product
from textwrap import dedent

from test.support import (captured_stderr, check_impl_detail,
Expand Down Expand Up @@ -1336,6 +1337,22 @@ def test_unicode_errors_no_object(self):
for klass in klasses:
self.assertEqual(str(klass.__new__(klass)), "")

def test_unicode_error_str_gh_123378(self):

@vstinner vstinner Oct 7, 2024

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The purpose of the test is unclear to me, it just calls str(). Please add a comment to explain that you check that str() doesn't crash with a reference to the issue.

for meth, start, end in product(
(str, repr),

@vstinner vstinner Oct 7, 2024

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Testing repr() if we already test str() sounds redundant to me. Is it really worth it?

@picnixz picnixz Oct 8, 2024

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No you're right. I'll remove it.

range(-5, 5),
range(-5, 5),
):
for obj in ('', 'a'):
with self.subTest(meth, obj=obj, start=start, end=end):
res = meth(UnicodeEncodeError('utf-8', obj, start, end, ''))
self.assertIsInstance(res, str)

for obj in (b'', b'a'):
with self.subTest(meth, obj=obj, start=start, end=end):
res = meth(UnicodeDecodeError('utf-8', obj, start, end, ''))
self.assertIsInstance(res, str)

@no_tracing
def test_badisinstance(self):
# Bug #2542: if issubclass(e, MyException) raises an exception,
Expand Down
3 changes: 3 additions & 0 deletions Misc/NEWS.d/next/Core_and_Builtins/2024-10-03-14-39-41.gh-issue-123378.dCxANf.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
Fix a crash in the :meth:`~object.__str__` method of :exc:`UnicodeError`
objects when the :attr:`UnicodeError.start` and :attr:`UnicodeError.end`
values are invalid or out-of-range. Patch by Bénédikt Tran.
119 changes: 60 additions & 59 deletions Objects/exceptions.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2994,52 +2994,53 @@ UnicodeEncodeError_init(PyObject *self, PyObject *args, PyObject *kwds)
static PyObject *
UnicodeEncodeError_str(PyObject *self)
{
PyUnicodeErrorObject *uself = (PyUnicodeErrorObject *)self;
PyObject *result = NULL;
PyObject *reason_str = NULL;
PyObject *encoding_str = NULL;
Comment thread
picnixz marked this conversation as resolved.
PyUnicodeErrorObject *exc = (PyUnicodeErrorObject *)self;

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

/* Get reason and encoding as strings, which they might not be if
they've been modified after we were constructed. */
reason_str = PyObject_Str(uself->reason);
if (reason_str == NULL)
goto done;
encoding_str = PyObject_Str(uself->encoding);
if (encoding_str == NULL)
goto done;
PyObject *reason = PyObject_Str(exc->reason);
if (reason == NULL) {
return NULL;
}
PyObject *encoding = PyObject_Str(exc->encoding);
if (encoding == NULL) {
Py_DECREF(reason);
return NULL;
}

if (uself->start < PyUnicode_GET_LENGTH(uself->object) && uself->end == uself->start+1) {
Py_UCS4 badchar = PyUnicode_ReadChar(uself->object, uself->start);
PyObject *res;
Py_ssize_t len = PyUnicode_GET_LENGTH(exc->object);
Py_ssize_t start = exc->start, end = exc->end;

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 = "'%U' codec can't encode character '\\x%02x' in position %zd: %U";
else if (badchar <= 0xffff)
}
else if (badchar <= 0xffff) {
fmt = "'%U' codec can't encode character '\\u%04x' in position %zd: %U";
else
}
else {
fmt = "'%U' codec can't encode character '\\U%08x' in position %zd: %U";
result = PyUnicode_FromFormat(
fmt,
encoding_str,
(int)badchar,
uself->start,
reason_str);
}
res = PyUnicode_FromFormat(fmt, encoding, (int)badchar, start, reason);
}
else {
result = PyUnicode_FromFormat(
res = PyUnicode_FromFormat(
"'%U' codec can't encode characters in position %zd-%zd: %U",
encoding_str,
uself->start,
uself->end-1,
reason_str);
encoding, start, end - 1, reason
);
}
done:
Py_XDECREF(reason_str);
Py_XDECREF(encoding_str);
return result;

Py_DECREF(reason);
Py_DECREF(encoding);
return res;
}

static PyTypeObject _PyExc_UnicodeEncodeError = {
Expand Down Expand Up @@ -3107,46 +3108,46 @@ UnicodeDecodeError_init(PyObject *self, PyObject *args, PyObject *kwds)
static PyObject *
UnicodeDecodeError_str(PyObject *self)
{
PyUnicodeErrorObject *uself = (PyUnicodeErrorObject *)self;
PyObject *result = NULL;
PyObject *reason_str = NULL;
PyObject *encoding_str = NULL;
PyUnicodeErrorObject *exc = (PyUnicodeErrorObject *)self;

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

/* Get reason and encoding as strings, which they might not be if
they've been modified after we were constructed. */
reason_str = PyObject_Str(uself->reason);
if (reason_str == NULL)
goto done;
encoding_str = PyObject_Str(uself->encoding);
if (encoding_str == NULL)
goto done;
PyObject *reason = PyObject_Str(exc->reason);
if (reason == NULL) {
return NULL;
}
PyObject *encoding = PyObject_Str(exc->encoding);
if (encoding == NULL) {
Py_DECREF(reason);
return NULL;
}

if (uself->start < PyBytes_GET_SIZE(uself->object) && uself->end == uself->start+1) {
int byte = (int)(PyBytes_AS_STRING(((PyUnicodeErrorObject *)self)->object)[uself->start]&0xff);
result = PyUnicode_FromFormat(
PyObject *res;
Py_ssize_t len = PyBytes_GET_SIZE(exc->object);
Py_ssize_t start = exc->start, end = exc->end;

if ((start >= 0 && start < len) && (end >= 0 && end <= len) && end == start + 1) {
int badbyte = (int)(PyBytes_AS_STRING(exc->object)[start] & 0xff);
res = PyUnicode_FromFormat(
"'%U' codec can't decode byte 0x%02x in position %zd: %U",
encoding_str,
byte,
uself->start,
reason_str);
encoding, badbyte, start, reason
);
}
else {
result = PyUnicode_FromFormat(
res = PyUnicode_FromFormat(
"'%U' codec can't decode bytes in position %zd-%zd: %U",
encoding_str,
uself->start,
uself->end-1,
reason_str
);
encoding, start, end - 1, reason
);
}
done:
Py_XDECREF(reason_str);
Py_XDECREF(encoding_str);
return result;

Py_DECREF(reason);
Py_DECREF(encoding);
return res;
}

static PyTypeObject _PyExc_UnicodeDecodeError = {
Expand Down