Skip to content

gh-126004: fix positions handling in codecs.xmlcharrefreplace_errors #127672

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

Closed
picnixz wants to merge 2 commits into from
Closed

gh-126004: fix positions handling in codecs.xmlcharrefreplace_errors #127672

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2a51f60
Fix `codecs.backslashreplace_errors` handler
picnixz Dec 6, 2024
c958a0b
blurb
picnixz Dec 6, 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
Next Next commit
Fix codecs.backslashreplace_errors handler
  • Loading branch information
@picnixz
picnixz committed Dec 6, 2024
commit 2a51f60ae36e91be73e0bac61e309eedf7f4510e
7 changes: 4 additions & 3 deletions Lib/test/test_capi/test_codecs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -843,7 +843,8 @@ def test_codec_replace_errors_handler(self):

def test_codec_xmlcharrefreplace_errors_handler(self):
handler = _testcapi.codec_xmlcharrefreplace_errors
self.do_test_codec_errors_handler(handler, self.unicode_encode_errors)
self.do_test_codec_errors_handler(handler, self.unicode_encode_errors,
safe=True)

def test_codec_backslashreplace_errors_handler(self):
handler = _testcapi.codec_backslashreplace_errors
Expand All @@ -853,12 +854,12 @@ def test_codec_namereplace_errors_handler(self):
handler = _testlimitedcapi.codec_namereplace_errors
self.do_test_codec_errors_handler(handler, self.unicode_encode_errors)

def do_test_codec_errors_handler(self, handler, exceptions):
def do_test_codec_errors_handler(self, handler, exceptions, *, safe=False):
at_least_one = False
for exc in exceptions:
# See https://github.com/python/cpython/issues/123378 and related
# discussion and issues for details.
if self._exception_may_crash(exc):
if not safe and self._exception_may_crash(exc):
continue

at_least_one = True
Expand Down
193 changes: 105 additions & 88 deletions Python/codecs.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -755,100 +755,117 @@ PyObject *PyCodec_ReplaceErrors(PyObject *exc)

PyObject *PyCodec_XMLCharRefReplaceErrors(PyObject *exc)
{
if (PyObject_TypeCheck(exc, (PyTypeObject *)PyExc_UnicodeEncodeError)) {
PyObject *restuple;
PyObject *object;
Py_ssize_t i;
Py_ssize_t start;
Py_ssize_t end;
PyObject *res;
Py_UCS1 *outp;
Py_ssize_t ressize;
Py_UCS4 ch;
if (PyUnicodeEncodeError_GetStart(exc, &start))
return NULL;
if (PyUnicodeEncodeError_GetEnd(exc, &end))
return NULL;
if (!(object = PyUnicodeEncodeError_GetObject(exc)))
return NULL;
if (end - start > PY_SSIZE_T_MAX / (2+7+1))
end = start + PY_SSIZE_T_MAX / (2+7+1);
for (i = start, ressize = 0; i < end; ++i) {
/* object is guaranteed to be "ready" */
ch = PyUnicode_READ_CHAR(object, i);
if (ch<10)
ressize += 2+1+1;
else if (ch<100)
ressize += 2+2+1;
else if (ch<1000)
ressize += 2+3+1;
else if (ch<10000)
ressize += 2+4+1;
else if (ch<100000)
ressize += 2+5+1;
else if (ch<1000000)
ressize += 2+6+1;
else
ressize += 2+7+1;
if (!PyObject_TypeCheck(exc, (PyTypeObject *)PyExc_UnicodeEncodeError)) {
wrong_exception_type(exc);
return NULL;
}

Py_ssize_t start, end;
if (PyUnicodeEncodeError_GetStart(exc, &start)) {
return NULL;
}
if (PyUnicodeEncodeError_GetEnd(exc, &end)) {
return NULL;
}
if (end <= start) {
// gh-12337 will handle negative end or start (for now we crash)
return Py_BuildValue("(Nn)", Py_GetConstant(Py_CONSTANT_EMPTY_STR), end);
}

PyObject *obj = PyUnicodeEncodeError_GetObject(exc);
if (obj == NULL) {
return NULL;
}

if (end - start > PY_SSIZE_T_MAX / 10) {
end = start + PY_SSIZE_T_MAX / 10;
}

end = Py_MIN(end, PyUnicode_GET_LENGTH(obj));

Py_ssize_t ressize = 0;
for (Py_ssize_t i = start; i < end; ++i) {
/* object is guaranteed to be "ready" */
Py_UCS4 ch = PyUnicode_READ_CHAR(obj, i);
// The number of characters that each character 'ch' contributes
// in the result is 2 + k + 1, where k = min{t >= 1 | 10^t > ch}.
if (ch < 10) {
ressize += 4;
}
/* allocate replacement */
res = PyUnicode_New(ressize, 127);
if (res == NULL) {
Py_DECREF(object);
return NULL;
else if (ch < 100) {
ressize += 5;
}
outp = PyUnicode_1BYTE_DATA(res);
/* generate replacement */
for (i = start; i < end; ++i) {
int digits;
int base;
ch = PyUnicode_READ_CHAR(object, i);
*outp++ = '&';
*outp++ = '#';
if (ch<10) {
digits = 1;
base = 1;
}
else if (ch<100) {
digits = 2;
base = 10;
}
else if (ch<1000) {
digits = 3;
base = 100;
}
else if (ch<10000) {
digits = 4;
base = 1000;
}
else if (ch<100000) {
digits = 5;
base = 10000;
}
else if (ch<1000000) {
digits = 6;
base = 100000;
}
else {
digits = 7;
base = 1000000;
}
while (digits-->0) {
*outp++ = '0' + ch/base;
ch %= base;
base /= 10;
}
*outp++ = ';';
else if (ch < 1000) {
ressize += 6;
}
else if (ch < 10000) {
ressize += 7;
}
else if (ch < 100000) {
ressize += 8;
}
else if (ch < 1000000) {
ressize += 9;
}
else {
assert(ch < 10000000);
ressize += 10;
}
assert(_PyUnicode_CheckConsistency(res, 1));
restuple = Py_BuildValue("(Nn)", res, end);
Py_DECREF(object);
return restuple;
}
else {
wrong_exception_type(exc);

/* allocate replacement */
PyObject *res = PyUnicode_New(ressize, 127);
if (res == NULL) {
Py_DECREF(obj);
return NULL;
}
Py_UCS1 *outp = PyUnicode_1BYTE_DATA(res);
/* generate replacement */
for (Py_ssize_t i = start; i < end; ++i) {
int digits, base;
Py_UCS4 ch = PyUnicode_READ_CHAR(obj, i);
if (ch < 10) {
digits = 1;
base = 1;
}
else if (ch < 100) {
digits = 2;
base = 10;
}
else if (ch < 1000) {
digits = 3;
base = 100;
}
else if (ch < 10000) {
digits = 4;
base = 1000;
}
else if (ch < 100000) {
digits = 5;
base = 10000;
}
else if (ch < 1000000) {
digits = 6;
base = 100000;
}
else {
assert(ch < 10000000);
digits = 7;
base = 1000000;
}
*outp++ = '&';
*outp++ = '#';
while (digits-- > 0) {
*outp++ = '0' + ch / base;
ch %= base;
base /= 10;
}
*outp++ = ';';
}
assert(_PyUnicode_CheckConsistency(res, 1));
PyObject *restuple = Py_BuildValue("(Nn)", res, end);
Py_DECREF(obj);
return restuple;
}

PyObject *PyCodec_BackslashReplaceErrors(PyObject *exc)
Expand Down