mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-19 09:15:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

Issue #14850: Now a chamap decoder treates U+FFFE as "undefined mapping"

Browse source 
in any mapping, not only in an unicode string.
This commit is contained in:
Serhiy Storchaka 2013-01-15 14:43:21 +02:00
parent ad1d5f908a
commit 4fb8caee87
3 changed files with 74 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

46
Objects/unicodeobject.c
View file

@ -5245,15 +5245,18 @@ PyObject *PyUnicode_DecodeCharmap(const char *s,
if (PyErr_ExceptionMatches(PyExc_LookupError)) {
/* No mapping found means: mapping is undefined. */
PyErr_Clear();
x = Py_None;
Py_INCREF(x);
goto Undefined;
} else
goto onError;
}
/* Apply mapping */
if (x == Py_None)
goto Undefined;
if (PyLong_Check(x)) {
long value = PyLong_AS_LONG(x);
if (value == 0xFFFE)
goto Undefined;
if (value < 0 || value > 0x10FFFF) {
PyErr_SetString(PyExc_TypeError,
"character mapping must be in range(0x110000)");
@ -5286,29 +5289,16 @@ PyObject *PyUnicode_DecodeCharmap(const char *s,
#endif
*p++ = (Py_UNICODE)value;
}
else if (x == Py_None) {
/* undefined mapping */
outpos = p-PyUnicode_AS_UNICODE(v);
startinpos = s-starts;
endinpos = startinpos+1;
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"charmap", "character maps to <undefined>",
&starts, &e, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p)) {
Py_DECREF(x);
goto onError;
}
Py_DECREF(x);
continue;
}
else if (PyUnicode_Check(x)) {
Py_ssize_t targetsize = PyUnicode_GET_SIZE(x);
if (targetsize == 1)
if (targetsize == 1) {
/* 1-1 mapping */
*p++ = *PyUnicode_AS_UNICODE(x);
Py_UNICODE value = *PyUnicode_AS_UNICODE(x);
if (value == 0xFFFE)
goto Undefined;
*p++ = value;
}
else if (targetsize > 1) {
/* 1-n mapping */
if (targetsize > extrachars) {
@ -5342,6 +5332,20 @@ PyObject *PyUnicode_DecodeCharmap(const char *s,
}
Py_DECREF(x);
++s;
continue;
Undefined:
/* undefined mapping */
Py_XDECREF(x);
outpos = p-PyUnicode_AS_UNICODE(v);
startinpos = s-starts;
endinpos = startinpos+1;
if (unicode_decode_call_errorhandler(
errors, &errorHandler,
"charmap", "character maps to <undefined>",
&starts, &e, &startinpos, &endinpos, &exc, &s,
&v, &outpos, &p)) {
goto onError;
}
}
}
if (p - PyUnicode_AS_UNICODE(v) < PyUnicode_GET_SIZE(v))