Mercurial > cpython-lru_cache-weakref
diff Objects/unicodeobject.c @ 81519:6ac4f1609847 3.3
Issue #14850: Now a chamap decoder treates U+FFFE as "undefined mapping"
in any mapping, not only in an unicode string.
| author | Serhiy Storchaka <storchaka@gmail.com> |
|---|---|
| date | Tue, 15 Jan 2013 15:01:20 +0200 |
| parents | 3e18ccaa537e 13cd78a2a17b |
| children | 8f10c9eae183 03e22cc9407a |
line wrap: on
line diff
--- a/Objects/unicodeobject.c Tue Jan 15 13:27:28 2013 +0200 +++ b/Objects/unicodeobject.c Tue Jan 15 15:01:20 2013 +0200 @@ -7511,15 +7511,18 @@ 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 > MAX_UNICODE) { PyErr_Format(PyExc_TypeError, "character mapping must be in range(0x%lx)", @@ -7530,21 +7533,6 @@ if (unicode_putchar(&v, &outpos, value) < 0) goto onError; } - else if (x == Py_None) { - /* undefined mapping */ - 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)) { - Py_DECREF(x); - goto onError; - } - Py_DECREF(x); - continue; - } else if (PyUnicode_Check(x)) { Py_ssize_t targetsize; @@ -7554,8 +7542,10 @@ if (targetsize == 1) { /* 1-1 mapping */ - if (unicode_putchar(&v, &outpos, - PyUnicode_READ_CHAR(x, 0)) < 0) + Py_UCS4 value = PyUnicode_READ_CHAR(x, 0); + if (value == 0xFFFE) + goto Undefined; + if (unicode_putchar(&v, &outpos, value) < 0) goto onError; } else if (targetsize > 1) { @@ -7590,6 +7580,19 @@ } Py_DECREF(x); ++s; + continue; +Undefined: + /* undefined mapping */ + Py_XDECREF(x); + 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)) { + goto onError; + } } } if (unicode_resize(&v, outpos) < 0)
