Merged revisions 78418 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r78418 | eric.smith | 2010-02-24 09:15:36 -0500 (Wed, 24 Feb 2010) | 1 line

  Issue #7309: Unchecked pointer access when converting UnicodeEncodeError, UnicodeDecodeError, and UnicodeTranslateError to strings.
........
This commit is contained in:
Eric Smith 2010-02-24 15:42:29 +00:00
parent 33091a8321
commit 0facd77015
3 changed files with 117 additions and 32 deletions

View File

@ -568,6 +568,42 @@ class ExceptionTests(unittest.TestCase):
pass pass
self.assertEquals(e, (None, None, None)) self.assertEquals(e, (None, None, None))
def testUnicodeChangeAttributes(self):
# See issue 7309. This was a crasher.
u = UnicodeEncodeError('baz', 'xxxxx', 1, 5, 'foo')
self.assertEqual(str(u), "'baz' codec can't encode characters in position 1-4: foo")
u.end = 2
self.assertEqual(str(u), "'baz' codec can't encode character '\\x78' in position 1: foo")
u.end = 5
u.reason = 0x345345345345345345
self.assertEqual(str(u), "'baz' codec can't encode characters in position 1-4: 965230951443685724997")
u.encoding = 4000
self.assertEqual(str(u), "'4000' codec can't encode characters in position 1-4: 965230951443685724997")
u.start = 1000
self.assertEqual(str(u), "'4000' codec can't encode characters in position 1000-4: 965230951443685724997")
u = UnicodeDecodeError('baz', b'xxxxx', 1, 5, 'foo')
self.assertEqual(str(u), "'baz' codec can't decode bytes in position 1-4: foo")
u.end = 2
self.assertEqual(str(u), "'baz' codec can't decode byte 0x78 in position 1: foo")
u.end = 5
u.reason = 0x345345345345345345
self.assertEqual(str(u), "'baz' codec can't decode bytes in position 1-4: 965230951443685724997")
u.encoding = 4000
self.assertEqual(str(u), "'4000' codec can't decode bytes in position 1-4: 965230951443685724997")
u.start = 1000
self.assertEqual(str(u), "'4000' codec can't decode bytes in position 1000-4: 965230951443685724997")
u = UnicodeTranslateError('xxxx', 1, 5, 'foo')
self.assertEqual(str(u), "can't translate characters in position 1-4: foo")
u.end = 2
self.assertEqual(str(u), "can't translate character '\\x78' in position 1: foo")
u.end = 5
u.reason = 0x345345345345345345
self.assertEqual(str(u), "can't translate characters in position 1-4: 965230951443685724997")
u.start = 1000
self.assertEqual(str(u), "can't translate characters in position 1000-4: 965230951443685724997")
def test_badisinstance(self): def test_badisinstance(self):
# Bug #2542: if issubclass(e, MyException) raises an exception, # Bug #2542: if issubclass(e, MyException) raises an exception,

View File

@ -12,6 +12,10 @@ What's New in Python 3.2 Alpha 1?
Core and Builtins Core and Builtins
----------------- -----------------
- Issue #7309: Fix unchecked attribute access when converting
UnicodeEncodeError, UnicodeDecodeError, and UnicodeTranslateError to
strings.
- Issue #6902: Fix problem with built-in types format incorrectly with - Issue #6902: Fix problem with built-in types format incorrectly with
0 padding. 0 padding.

View File

@ -1434,8 +1434,20 @@ static PyObject *
UnicodeEncodeError_str(PyObject *self) UnicodeEncodeError_str(PyObject *self)
{ {
PyUnicodeErrorObject *uself = (PyUnicodeErrorObject *)self; PyUnicodeErrorObject *uself = (PyUnicodeErrorObject *)self;
PyObject *result = NULL;
PyObject *reason_str = NULL;
PyObject *encoding_str = NULL;
if (uself->end==uself->start+1) { /* Get reason and encoding as strings, which they might not be if
they've been modified after we were contructed. */
reason_str = PyObject_Str(uself->reason);
if (reason_str == NULL)
goto done;
encoding_str = PyObject_Str(uself->encoding);
if (encoding_str == NULL)
goto done;
if (uself->start < PyUnicode_GET_SIZE(uself->object) && uself->end == uself->start+1) {
int badchar = (int)PyUnicode_AS_UNICODE(uself->object)[uself->start]; int badchar = (int)PyUnicode_AS_UNICODE(uself->object)[uself->start];
const char *fmt; const char *fmt;
if (badchar <= 0xff) if (badchar <= 0xff)
@ -1444,21 +1456,25 @@ UnicodeEncodeError_str(PyObject *self)
fmt = "'%U' codec can't encode character '\\u%04x' in position %zd: %U"; 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"; fmt = "'%U' codec can't encode character '\\U%08x' in position %zd: %U";
return PyUnicode_FromFormat( result = PyUnicode_FromFormat(
fmt, fmt,
((PyUnicodeErrorObject *)self)->encoding, encoding_str,
badchar, badchar,
uself->start, uself->start,
((PyUnicodeErrorObject *)self)->reason reason_str);
);
} }
return PyUnicode_FromFormat( else {
"'%U' codec can't encode characters in position %zd-%zd: %U", result = PyUnicode_FromFormat(
((PyUnicodeErrorObject *)self)->encoding, "'%U' codec can't encode characters in position %zd-%zd: %U",
uself->start, encoding_str,
uself->end-1, uself->start,
((PyUnicodeErrorObject *)self)->reason uself->end-1,
); reason_str);
}
done:
Py_XDECREF(reason_str);
Py_XDECREF(encoding_str);
return result;
} }
static PyTypeObject _PyExc_UnicodeEncodeError = { static PyTypeObject _PyExc_UnicodeEncodeError = {
@ -1536,24 +1552,41 @@ static PyObject *
UnicodeDecodeError_str(PyObject *self) UnicodeDecodeError_str(PyObject *self)
{ {
PyUnicodeErrorObject *uself = (PyUnicodeErrorObject *)self; PyUnicodeErrorObject *uself = (PyUnicodeErrorObject *)self;
PyObject *result = NULL;
PyObject *reason_str = NULL;
PyObject *encoding_str = NULL;
if (uself->end==uself->start+1) { /* Get reason and encoding as strings, which they might not be if
they've been modified after we were contructed. */
reason_str = PyObject_Str(uself->reason);
if (reason_str == NULL)
goto done;
encoding_str = PyObject_Str(uself->encoding);
if (encoding_str == NULL)
goto done;
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); int byte = (int)(PyBytes_AS_STRING(((PyUnicodeErrorObject *)self)->object)[uself->start]&0xff);
return PyUnicode_FromFormat( result = PyUnicode_FromFormat(
"'%U' codec can't decode byte 0x%02x in position %zd: %U", "'%U' codec can't decode byte 0x%02x in position %zd: %U",
((PyUnicodeErrorObject *)self)->encoding, encoding_str,
byte, byte,
uself->start, uself->start,
((PyUnicodeErrorObject *)self)->reason reason_str);
);
} }
return PyUnicode_FromFormat( else {
"'%U' codec can't decode bytes in position %zd-%zd: %U", result = PyUnicode_FromFormat(
((PyUnicodeErrorObject *)self)->encoding, "'%U' codec can't decode bytes in position %zd-%zd: %U",
uself->start, encoding_str,
uself->end-1, uself->start,
((PyUnicodeErrorObject *)self)->reason uself->end-1,
); reason_str
);
}
done:
Py_XDECREF(reason_str);
Py_XDECREF(encoding_str);
return result;
} }
static PyTypeObject _PyExc_UnicodeDecodeError = { static PyTypeObject _PyExc_UnicodeDecodeError = {
@ -1617,8 +1650,16 @@ static PyObject *
UnicodeTranslateError_str(PyObject *self) UnicodeTranslateError_str(PyObject *self)
{ {
PyUnicodeErrorObject *uself = (PyUnicodeErrorObject *)self; PyUnicodeErrorObject *uself = (PyUnicodeErrorObject *)self;
PyObject *result = NULL;
PyObject *reason_str = NULL;
if (uself->end==uself->start+1) { /* Get reason as a string, which it might not be if it's been
modified after we were contructed. */
reason_str = PyObject_Str(uself->reason);
if (reason_str == NULL)
goto done;
if (uself->start < PyUnicode_GET_SIZE(uself->object) && uself->end == uself->start+1) {
int badchar = (int)PyUnicode_AS_UNICODE(uself->object)[uself->start]; int badchar = (int)PyUnicode_AS_UNICODE(uself->object)[uself->start];
const char *fmt; const char *fmt;
if (badchar <= 0xff) if (badchar <= 0xff)
@ -1631,15 +1672,19 @@ UnicodeTranslateError_str(PyObject *self)
fmt, fmt,
badchar, badchar,
uself->start, uself->start,
uself->reason reason_str
); );
} else {
result = PyUnicode_FromFormat(
"can't translate characters in position %zd-%zd: %U",
uself->start,
uself->end-1,
reason_str
);
} }
return PyUnicode_FromFormat( done:
"can't translate characters in position %zd-%zd: %U", Py_XDECREF(reason_str);
uself->start, return result;
uself->end-1,
uself->reason
);
} }
static PyTypeObject _PyExc_UnicodeTranslateError = { static PyTypeObject _PyExc_UnicodeTranslateError = {