Commit 3fd4ab35 authored by Serhiy Storchaka's avatar Serhiy Storchaka

Issue #17043: The unicode-internal decoder no longer read past the end of

input buffer.
parent df4bb464
......@@ -10,6 +10,9 @@ What's New in Python 3.2.4
Core and Builtins
-----------------
- Issue #17043: The unicode-internal decoder no longer read past the end of
input buffer.
- Issue #16979: Fix error handling bugs in the unicode-escape-decode decoder.
- Issue #10156: In the interpreter's initialization phase, unicode globals
......
......@@ -4392,37 +4392,34 @@ PyObject *_PyUnicode_DecodeUnicodeInternal(const char *s,
end = s + size;
while (s < end) {
if (end-s < Py_UNICODE_SIZE) {
endinpos = end-starts;
reason = "truncated input";
goto error;
}
memcpy(p, s, sizeof(Py_UNICODE));
#ifdef Py_UNICODE_WIDE
/* We have to sanity check the raw data, otherwise doom looms for
some malformed UCS-4 data. */
if (
#ifdef Py_UNICODE_WIDE
*p > unimax || *p < 0 ||
#endif
end-s < Py_UNICODE_SIZE
)
{
startinpos = s - starts;
if (end-s < Py_UNICODE_SIZE) {
endinpos = end-starts;
reason = "truncated input";
}
else {
endinpos = s - starts + Py_UNICODE_SIZE;
reason = "illegal code point (> 0x10FFFF)";
}
outpos = p - PyUnicode_AS_UNICODE(v);
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"unicode_internal", reason,
&starts, &end, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p)) {
goto onError;
}
if (*p > unimax || *p < 0) {
endinpos = s - starts + Py_UNICODE_SIZE;
reason = "illegal code point (> 0x10FFFF)";
goto error;
}
else {
p++;
s += Py_UNICODE_SIZE;
#endif
p++;
s += Py_UNICODE_SIZE;
continue;
error:
startinpos = s - starts;
outpos = p - PyUnicode_AS_UNICODE(v);
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"unicode_internal", reason,
&starts, &end, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p)) {
goto onError;
}
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment