mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-29 05:05:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Issue #16979: Fix error handling bugs in the unicode-escape-decode decoder.

Browse source
This commit is contained in:
Serhiy Storchaka 2013-01-29 10:20:44 +02:00
parent 8e0ae2a4f0
commit d679377be7
4 changed files with 117 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

79
Objects/unicodeobject.c
View file

@ -3760,7 +3760,6 @@ PyObject *PyUnicode_DecodeUnicodeEscape(const char *s,
Py_ssize_t startinpos;
Py_ssize_t endinpos;
Py_ssize_t outpos;
int i;
PyUnicodeObject *v;
Py_UNICODE *p;
const char *end;
@ -3846,29 +3845,19 @@ PyObject *PyUnicode_DecodeUnicodeEscape(const char *s,
message = "truncated \\UXXXXXXXX escape";
hexescape:
chr = 0;
outpos = p-PyUnicode_AS_UNICODE(v);
if (s+digits>end) {
endinpos = size;
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"unicodeescape", "end of string in escape sequence",
&starts, &end, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p))
goto onError;
goto nextByte;
}
for (i = 0; i < digits; ++i) {
c = (unsigned char) s[i];
if (!Py_ISXDIGIT(c)) {
endinpos = (s+i+1)-starts;
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"unicodeescape", message,
&starts, &end, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p))
goto onError;
goto nextByte;
if (end - s < digits) {
/* count only hex digits */
for (; s < end; ++s) {
c = (unsigned char)*s;
if (!Py_ISXDIGIT(c))
goto error;
}
goto error;
}
for (; digits--; ++s) {
c = (unsigned char)*s;
if (!Py_ISXDIGIT(c))
goto error;
chr = (chr<<4) & ~0xF;
if (c >= '0' && c <= '9')
chr += c - '0';
@ -3877,7 +3866,6 @@ PyObject *PyUnicode_DecodeUnicodeEscape(const char *s,
else
chr += 10 + c - 'A';
}
s += i;
if (chr == 0xffffffff && PyErr_Occurred())
/* _decoding_error will have already written into the
target buffer. */
@ -3898,14 +3886,8 @@ PyObject *PyUnicode_DecodeUnicodeEscape(const char *s,
*p++ = 0xDC00 + (Py_UNICODE) (chr & 0x03FF);
#endif
} else {
endinpos = s-starts;
outpos = p-PyUnicode_AS_UNICODE(v);
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"unicodeescape", "illegal Unicode character",
&starts, &end, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p))
goto onError;
message = "illegal Unicode character";
goto error;
}
break;
@ -3932,28 +3914,13 @@ PyObject *PyUnicode_DecodeUnicodeEscape(const char *s,
goto store;
}
}
endinpos = s-starts;
outpos = p-PyUnicode_AS_UNICODE(v);
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"unicodeescape", message,
&starts, &end, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p))
goto onError;
break;
goto error;
default:
if (s > end) {
message = "\\ at end of string";
s--;
endinpos = s-starts;
outpos = p-PyUnicode_AS_UNICODE(v);
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"unicodeescape", message,
&starts, &end, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p))
goto onError;
goto error;
}
else {
*p++ = '\\';
@ -3961,8 +3928,18 @@ PyObject *PyUnicode_DecodeUnicodeEscape(const char *s,
}
break;
}
nextByte:
;
continue;
error:
endinpos = s-starts;
outpos = p-PyUnicode_AS_UNICODE(v);
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"unicodeescape", message,
&starts, &end, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p))
goto onError;
continue;
}
if (_PyUnicode_Resize(&v, p - PyUnicode_AS_UNICODE(v)) < 0)
goto onError;