From 3dd910f4da86bcaa98b5e4e49232940a6716c4ab Mon Sep 17 00:00:00 2001 From: Toshio Kuratomi Date: Aug 20 2010 21:31:03 +0000 Subject: Rebase patch --- diff --git a/python3-r80382-lone-surrogate-and-utf8-error-handler.patch b/python3-r80382-lone-surrogate-and-utf8-error-handler.patch index b4b59f2..6287d7f 100644 --- a/python3-r80382-lone-surrogate-and-utf8-error-handler.patch +++ b/python3-r80382-lone-surrogate-and-utf8-error-handler.patch @@ -1,8 +1,8 @@ -Index: Objects/unicodeobject.c +Index: Python-3.1.2/Objects/unicodeobject.c =================================================================== ---- Objects/unicodeobject.c (revision 80382) -+++ Objects/unicodeobject.c (revision 80383) -@@ -159,6 +159,12 @@ +--- Python-3.1.2.orig/Objects/unicodeobject.c ++++ Python-3.1.2/Objects/unicodeobject.c +@@ -159,6 +159,12 @@ static PyObject *unicode_encode_call_err const Py_UNICODE *unicode, Py_ssize_t size, PyObject **exceptionObject, Py_ssize_t startpos, Py_ssize_t endpos, Py_ssize_t *newpos); @@ -15,7 +15,7 @@ Index: Objects/unicodeobject.c /* Same for linebreaks */ static unsigned char ascii_linebreak[] = { 0, 0, 0, 0, 0, 0, 0, 0, -@@ -2461,61 +2467,88 @@ +@@ -2461,59 +2467,88 @@ PyUnicode_EncodeUTF8(const Py_UNICODE *s /* Encode Latin-1 */ *p++ = (char)(0xc0 | (ch >> 6)); *p++ = (char)(0x80 | (ch & 0x3f)); @@ -60,6 +60,12 @@ Index: Objects/unicodeobject.c - (errors, &errorHandler, "utf-8", "surrogates not allowed", - s, size, &exc, i-1, i, &newpos); - if (!rep) +- goto error; +- /* Implementation limitations: only support error handler that return +- bytes, and only support up to four replacement bytes. */ +- if (!PyBytes_Check(rep)) { +- PyErr_SetString(PyExc_TypeError, "error handler should have returned bytes"); +- Py_DECREF(rep); + } else { + Py_ssize_t newpos; + PyObject *rep; @@ -87,12 +93,6 @@ Index: Objects/unicodeobject.c + /* integer overflow */ + PyErr_NoMemory(); goto error; -- /* Implementation limitations: only support error handler that return -- bytes, and only support up to four replacement bytes. */ -- if (!PyBytes_Check(rep)) { -- PyErr_SetString(PyExc_TypeError, "error handler should have returned bytes"); -- Py_DECREF(rep); -- goto error; } - if (PyBytes_Size(rep) > 4) { - PyErr_SetString(PyExc_TypeError, "error handler returned too many bytes"); @@ -140,9 +140,7 @@ Index: Objects/unicodeobject.c - continue; + Py_DECREF(rep); } --#ifndef Py_UNICODE_WIDE - encodeUCS4: --#endif + } else if (ch < 0x10000) { + *p++ = (char)(0xe0 | (ch >> 12)); + *p++ = (char)(0x80 | ((ch >> 6) & 0x3f)); @@ -151,11 +149,11 @@ Index: Objects/unicodeobject.c /* Encode UCS4 Unicode ordinals */ *p++ = (char)(0xf0 | (ch >> 18)); *p++ = (char)(0x80 | ((ch >> 12) & 0x3f)); -Index: Lib/test/test_codecs.py +Index: Python-3.1.2/Lib/test/test_codecs.py =================================================================== ---- Lib/test/test_codecs.py (revision 80382) -+++ Lib/test/test_codecs.py (revision 80383) -@@ -571,6 +571,16 @@ +--- Python-3.1.2.orig/Lib/test/test_codecs.py ++++ Python-3.1.2/Lib/test/test_codecs.py +@@ -571,6 +571,16 @@ class UTF8Test(ReadTest): def test_lone_surrogates(self): self.assertRaises(UnicodeEncodeError, "\ud800".encode, "utf-8") self.assertRaises(UnicodeDecodeError, b"\xed\xa0\x80".decode, "utf-8") @@ -172,4 +170,3 @@ Index: Lib/test/test_codecs.py def test_surrogatepass_handler(self): self.assertEquals("abc\ud800def".encode("utf-8", "surrogatepass"), -