Issue #8383: pickle and pickletools use surrogatepass error handler when
encoding unicode as utf8 to support lone surrogates and stay compatible with
Python 2.x and 3.0
diff --git a/Modules/_pickle.c b/Modules/_pickle.c
index 29aed7a..0e1c2cd 100644
--- a/Modules/_pickle.c
+++ b/Modules/_pickle.c
@@ -1227,7 +1227,9 @@
if (self->bin) {
char pdata[5];
- encoded = PyUnicode_AsUTF8String(obj);
+ encoded = PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(obj),
+ PyUnicode_GET_SIZE(obj),
+ "surrogatepass");
if (encoded == NULL)
goto error;
@@ -3352,7 +3354,7 @@
if (unpickler_read(self, &s, size) < 0)
return -1;
- str = PyUnicode_DecodeUTF8(s, size, NULL);
+ str = PyUnicode_DecodeUTF8(s, size, "surrogatepass");
if (str == NULL)
return -1;