From a9b1c0cc1f599500ca8026f8232bf65f4ee7aced Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Thu, 3 Oct 2024 14:35:35 +0200
Subject: [PATCH 01/11] fix OOB in `UnicodeError.__str__`

---
 Objects/exceptions.c | 119 ++++++++++++++++++++++---------------------
 1 file changed, 60 insertions(+), 59 deletions(-)

diff --git a/Objects/exceptions.c b/Objects/exceptions.c
index b3910855165494..0d1fd205068642 100644
--- a/Objects/exceptions.c
+++ b/Objects/exceptions.c
@@ -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;
+    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;
+    ssize_t len = PyUnicode_GET_LENGTH(exc->object);
+    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 = {
@@ -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) {
         /* 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;
+    ssize_t len = PyBytes_GET_SIZE(exc->object);
+    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 = {

From 356742648151df9dc6d88c36c581a965566364b4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Thu, 3 Oct 2024 14:39:46 +0200
Subject: [PATCH 02/11] blurb

---
 .../2024-10-03-14-39-41.gh-issue-123378.dCxANf.rst             | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 Misc/NEWS.d/next/Core_and_Builtins/2024-10-03-14-39-41.gh-issue-123378.dCxANf.rst

diff --git a/Misc/NEWS.d/next/Core_and_Builtins/2024-10-03-14-39-41.gh-issue-123378.dCxANf.rst b/Misc/NEWS.d/next/Core_and_Builtins/2024-10-03-14-39-41.gh-issue-123378.dCxANf.rst
new file mode 100644
index 00000000000000..5cd34535d674d3
--- /dev/null
+++ b/Misc/NEWS.d/next/Core_and_Builtins/2024-10-03-14-39-41.gh-issue-123378.dCxANf.rst
@@ -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.

From 43141c0bfd3f4ef4d96dd935e258def44e8fe975 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Thu, 3 Oct 2024 14:43:29 +0200
Subject: [PATCH 03/11] add tests

---
 Lib/test/test_exceptions.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/Lib/test/test_exceptions.py b/Lib/test/test_exceptions.py
index ba858c49400911..cf81acd29a8e9e 100644
--- a/Lib/test/test_exceptions.py
+++ b/Lib/test/test_exceptions.py
@@ -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,
@@ -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):
+        for meth, start, end in product(
+            (str, repr),
+            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,

From 0c613750ac03f6016d99bb015d347378dffff8b1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Thu, 3 Oct 2024 14:52:31 +0200
Subject: [PATCH 04/11] small fixup

---
 Objects/exceptions.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Objects/exceptions.c b/Objects/exceptions.c
index 0d1fd205068642..fa5dd4be3af0a0 100644
--- a/Objects/exceptions.c
+++ b/Objects/exceptions.c
@@ -3110,7 +3110,7 @@ UnicodeDecodeError_str(PyObject *self)
 {
     PyUnicodeErrorObject *exc = (PyUnicodeErrorObject *)self;
 
-    if (!exc->object) {
+    if (exc->object == NULL) {
         /* Not properly initialized. */
         return PyUnicode_FromString("");
     }

From 80287f624058cd3ba13d10208e5a2d9de0883ac0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Thu, 3 Oct 2024 14:59:21 +0200
Subject: [PATCH 05/11] Fix Windows compilation

---
 Objects/exceptions.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Objects/exceptions.c b/Objects/exceptions.c
index fa5dd4be3af0a0..64a6d7f5fc4c8a 100644
--- a/Objects/exceptions.c
+++ b/Objects/exceptions.c
@@ -3014,8 +3014,8 @@ UnicodeEncodeError_str(PyObject *self)
     }
 
     PyObject *res;
-    ssize_t len = PyUnicode_GET_LENGTH(exc->object);
-    ssize_t start = exc->start, end = exc->end;
+    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);
@@ -3128,8 +3128,8 @@ UnicodeDecodeError_str(PyObject *self)
     }
 
     PyObject *res;
-    ssize_t len = PyBytes_GET_SIZE(exc->object);
-    ssize_t start = exc->start, end = exc->end;
+    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);

From 7bbc0f59b05d28ba855e1bf2bd16a66b7bbdb0d5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Fri, 4 Oct 2024 13:54:16 +0200
Subject: [PATCH 06/11] improve test coverage

---
 Lib/test/test_exceptions.py | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/Lib/test/test_exceptions.py b/Lib/test/test_exceptions.py
index cf81acd29a8e9e..c441e93ba77ad7 100644
--- a/Lib/test/test_exceptions.py
+++ b/Lib/test/test_exceptions.py
@@ -1338,20 +1338,20 @@ def test_unicode_errors_no_object(self):
             self.assertEqual(str(klass.__new__(klass)), "")
 
     def test_unicode_error_str_gh_123378(self):
-        for meth, start, end in product(
+        for fn, start, end, obj in product(
             (str, repr),
             range(-5, 5),
             range(-5, 5),
+            ('', 'a', '123', '1234', '12345', 'abc123'),
         ):
-            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)
+            with self.subTest(fn, obj=obj, start=start, end=end):
+                exc = UnicodeEncodeError('utf-8', obj, start, end, '')
+                self.assertIsInstance(fn(exc), str)
+
+            encoded = obj.encode()
+            with self.subTest(fn, obj=encoded, start=start, end=end):
+                exc = UnicodeDecodeError('utf-8', encoded, start, end, '')
+                self.assertIsInstance(fn(exc), str)
 
     @no_tracing
     def test_badisinstance(self):

From 2313cd1def7843e9d5f42690805c7ca1373d8b8f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Fri, 4 Oct 2024 14:21:33 +0200
Subject: [PATCH 07/11] fix `UnicodeTranslateError`

---
 Objects/exceptions.c | 55 ++++++++++++++++++++++----------------------
 1 file changed, 28 insertions(+), 27 deletions(-)

diff --git a/Objects/exceptions.c b/Objects/exceptions.c
index 64a6d7f5fc4c8a..587256f393f271 100644
--- a/Objects/exceptions.c
+++ b/Objects/exceptions.c
@@ -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 = {

From a27a88bff15a3245e33fce0c305aa3db8a1f437b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Fri, 4 Oct 2024 14:19:00 +0200
Subject: [PATCH 08/11] improve test coverage

---
 Lib/test/test_exceptions.py | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/Lib/test/test_exceptions.py b/Lib/test/test_exceptions.py
index c441e93ba77ad7..0cc2913d940664 100644
--- a/Lib/test/test_exceptions.py
+++ b/Lib/test/test_exceptions.py
@@ -1338,20 +1338,24 @@ def test_unicode_errors_no_object(self):
             self.assertEqual(str(klass.__new__(klass)), "")
 
     def test_unicode_error_str_gh_123378(self):
-        for fn, start, end, obj in product(
+        for formatter, start, end, obj in product(
             (str, repr),
             range(-5, 5),
             range(-5, 5),
             ('', 'a', '123', '1234', '12345', 'abc123'),
         ):
-            with self.subTest(fn, obj=obj, start=start, end=end):
+            with self.subTest(formatter, obj=obj, start=start, end=end):
                 exc = UnicodeEncodeError('utf-8', obj, start, end, '')
-                self.assertIsInstance(fn(exc), str)
+                self.assertIsInstance(formatter(exc), str)
+
+            with self.subTest(formatter, obj=obj, start=start, end=end):
+                exc = UnicodeTranslateError(obj, start, end, '')
+                self.assertIsInstance(formatter(exc), str)
 
             encoded = obj.encode()
-            with self.subTest(fn, obj=encoded, start=start, end=end):
+            with self.subTest(formatter, obj=encoded, start=start, end=end):
                 exc = UnicodeDecodeError('utf-8', encoded, start, end, '')
-                self.assertIsInstance(fn(exc), str)
+                self.assertIsInstance(formatter(exc), str)
 
     @no_tracing
     def test_badisinstance(self):

From 360c1a583ecaf8d1a978c0f4d8450f7c39e5e583 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Sat, 5 Oct 2024 12:22:37 +0200
Subject: [PATCH 09/11] revert cosmetic changes

---
 Objects/exceptions.c | 144 ++++++++++++++++++++++---------------------
 1 file changed, 74 insertions(+), 70 deletions(-)

diff --git a/Objects/exceptions.c b/Objects/exceptions.c
index 587256f393f271..ed3ea1f1272c64 100644
--- a/Objects/exceptions.c
+++ b/Objects/exceptions.c
@@ -2995,52 +2995,54 @@ static PyObject *
 UnicodeEncodeError_str(PyObject *self)
 {
     PyUnicodeErrorObject *exc = (PyUnicodeErrorObject *)self;
+    PyObject *result = NULL;
+    PyObject *reason_str = NULL;
+    PyObject *encoding_str = NULL;
 
-    if (exc->object == NULL) {
+    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. */
-    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;
-    }
+    reason_str = PyObject_Str(exc->reason);
+    if (reason_str == NULL)
+        goto done;
+    encoding_str = PyObject_Str(exc->encoding);
+    if (encoding_str == NULL)
+        goto done;
 
-    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";
-        }
-        res = PyUnicode_FromFormat(fmt, encoding, (int)badchar, start, reason);
+        result = PyUnicode_FromFormat(
+            fmt,
+            encoding_str,
+            (int)badchar,
+            start,
+            reason_str);
     }
     else {
-        res = PyUnicode_FromFormat(
+        result = PyUnicode_FromFormat(
             "'%U' codec can't encode characters in position %zd-%zd: %U",
-            encoding, start, end - 1, reason
-        );
+            encoding_str,
+            start,
+            end - 1,
+            reason_str);
     }
-
-    Py_DECREF(reason);
-    Py_DECREF(encoding);
-    return res;
+done:
+    Py_XDECREF(reason_str);
+    Py_XDECREF(encoding_str);
+    return result;
 }
 
 static PyTypeObject _PyExc_UnicodeEncodeError = {
@@ -3109,45 +3111,47 @@ static PyObject *
 UnicodeDecodeError_str(PyObject *self)
 {
     PyUnicodeErrorObject *exc = (PyUnicodeErrorObject *)self;
+    PyObject *result = NULL;
+    PyObject *reason_str = NULL;
+    PyObject *encoding_str = NULL;
 
-    if (exc->object == NULL) {
+    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. */
-    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;
-    }
+    reason_str = PyObject_Str(exc->reason);
+    if (reason_str == NULL)
+        goto done;
+    encoding_str = PyObject_Str(exc->encoding);
+    if (encoding_str == NULL)
+        goto done;
 
-    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(
+        result = PyUnicode_FromFormat(
             "'%U' codec can't decode byte 0x%02x in position %zd: %U",
-            encoding, badbyte, start, reason
-        );
+            encoding_str,
+            badbyte,
+            start,
+            reason_str);
     }
     else {
-        res = PyUnicode_FromFormat(
+        result = PyUnicode_FromFormat(
             "'%U' codec can't decode bytes in position %zd-%zd: %U",
-            encoding, start, end - 1, reason
-        );
+            encoding_str,
+            start,
+            end - 1,
+            reason_str);
     }
-
-    Py_DECREF(reason);
-    Py_DECREF(encoding);
-    return res;
+done:
+    Py_XDECREF(reason_str);
+    Py_XDECREF(encoding_str);
+    return result;
 }
 
 static PyTypeObject _PyExc_UnicodeDecodeError = {
@@ -3206,46 +3210,46 @@ static PyObject *
 UnicodeTranslateError_str(PyObject *self)
 {
     PyUnicodeErrorObject *exc = (PyUnicodeErrorObject *)self;
+    PyObject *result = NULL;
+    PyObject *reason_str = NULL;
 
-    if (exc->object == NULL) {
+    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. */
-    PyObject *reason = PyObject_Str(exc->reason);
-    if (reason == NULL) {
-        return NULL;
-    }
+    reason_str = PyObject_Str(exc->reason);
+    if (reason_str == NULL)
+        goto done;
 
-    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 = "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";
-        }
-        res = PyUnicode_FromFormat(fmt, (int)badchar, start, reason);
-    }
-    else {
-        res = PyUnicode_FromFormat(
+        result = PyUnicode_FromFormat(
+            fmt,
+            (int)badchar,
+            start,
+            reason_str);
+    } else {
+        result = PyUnicode_FromFormat(
             "can't translate characters in position %zd-%zd: %U",
-            start, end - 1, reason
-        );
+            start,
+            end - 1,
+            reason_str);
     }
-
-    Py_DECREF(reason);
-    return res;
+done:
+    Py_XDECREF(reason_str);
+    return result;
 }
 
 static PyTypeObject _PyExc_UnicodeTranslateError = {

From 85199f81d34a6a45788ec8d89ee8ea039265dbce Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Mon, 7 Oct 2024 16:21:15 +0200
Subject: [PATCH 10/11] add back PEP-7 braces

---
 Objects/exceptions.c | 45 +++++++++++++++++++++++++++++---------------
 1 file changed, 30 insertions(+), 15 deletions(-)

diff --git a/Objects/exceptions.c b/Objects/exceptions.c
index ed3ea1f1272c64..c685481b13a93a 100644
--- a/Objects/exceptions.c
+++ b/Objects/exceptions.c
@@ -2999,18 +2999,21 @@ UnicodeEncodeError_str(PyObject *self)
     PyObject *reason_str = NULL;
     PyObject *encoding_str = NULL;
 
-    if (exc->object == NULL)
+    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(exc->reason);
-    if (reason_str == NULL)
+    if (reason_str == NULL) {
         goto done;
+    }
     encoding_str = PyObject_Str(exc->encoding);
-    if (encoding_str == NULL)
+    if (encoding_str == NULL) {
         goto done;
+    }
 
     Py_ssize_t len = PyUnicode_GET_LENGTH(exc->object);
     Py_ssize_t start = exc->start, end = exc->end;
@@ -3018,12 +3021,15 @@ UnicodeEncodeError_str(PyObject *self)
     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,
@@ -3115,18 +3121,21 @@ UnicodeDecodeError_str(PyObject *self)
     PyObject *reason_str = NULL;
     PyObject *encoding_str = NULL;
 
-    if (exc->object == NULL)
+    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(exc->reason);
-    if (reason_str == NULL)
+    if (reason_str == NULL) {
         goto done;
+    }
     encoding_str = PyObject_Str(exc->encoding);
-    if (encoding_str == NULL)
+    if (encoding_str == NULL) {
         goto done;
+    }
 
     Py_ssize_t len = PyBytes_GET_SIZE(exc->object);
     Py_ssize_t start = exc->start, end = exc->end;
@@ -3213,15 +3222,17 @@ UnicodeTranslateError_str(PyObject *self)
     PyObject *result = NULL;
     PyObject *reason_str = NULL;
 
-    if (exc->object == NULL)
+    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(exc->reason);
-    if (reason_str == NULL)
+    if (reason_str == NULL) {
         goto done;
+    }
 
     Py_ssize_t len = PyUnicode_GET_LENGTH(exc->object);
     Py_ssize_t start = exc->start, end = exc->end;
@@ -3229,18 +3240,22 @@ UnicodeTranslateError_str(PyObject *self)
     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,
             start,
             reason_str);
-    } else {
+    }
+    else {
         result = PyUnicode_FromFormat(
             "can't translate characters in position %zd-%zd: %U",
             start,

From 44dfaeb960454266cc2e96c01d05f2bc6325a673 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?B=C3=A9n=C3=A9dikt=20Tran?=
 <10796600+picnixz@users.noreply.github.com>
Date: Tue, 8 Oct 2024 11:06:24 +0200
Subject: [PATCH 11/11] address Victor's review

---
 Lib/test/test_exceptions.py | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/Lib/test/test_exceptions.py b/Lib/test/test_exceptions.py
index 0cc2913d940664..b3c21cd4f3d585 100644
--- a/Lib/test/test_exceptions.py
+++ b/Lib/test/test_exceptions.py
@@ -1337,25 +1337,28 @@ 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):
-        for formatter, start, end, obj in product(
-            (str, repr),
+    def test_unicode_error_str_does_not_crash(self):
+        # Test that str(UnicodeError(...)) does not crash.
+        # See https://github.com/python/cpython/issues/123378.
+
+        for start, end, objlen in product(
             range(-5, 5),
             range(-5, 5),
-            ('', 'a', '123', '1234', '12345', 'abc123'),
+            range(7),
         ):
-            with self.subTest(formatter, obj=obj, start=start, end=end):
+            obj = 'a' * objlen
+            with self.subTest('encode', objlen=objlen, start=start, end=end):
                 exc = UnicodeEncodeError('utf-8', obj, start, end, '')
-                self.assertIsInstance(formatter(exc), str)
+                self.assertIsInstance(str(exc), str)
 
-            with self.subTest(formatter, obj=obj, start=start, end=end):
+            with self.subTest('translate', objlen=objlen, start=start, end=end):
                 exc = UnicodeTranslateError(obj, start, end, '')
-                self.assertIsInstance(formatter(exc), str)
+                self.assertIsInstance(str(exc), str)
 
             encoded = obj.encode()
-            with self.subTest(formatter, obj=encoded, start=start, end=end):
+            with self.subTest('decode', objlen=objlen, start=start, end=end):
                 exc = UnicodeDecodeError('utf-8', encoded, start, end, '')
-                self.assertIsInstance(formatter(exc), str)
+                self.assertIsInstance(str(exc), str)
 
     @no_tracing
     def test_badisinstance(self):