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/Lib/pickle.py b/Lib/pickle.py
index 8a2abcc..c4fc2c4 100644
--- a/Lib/pickle.py
+++ b/Lib/pickle.py
@@ -499,7 +499,7 @@
def save_str(self, obj, pack=struct.pack):
if self.bin:
- encoded = obj.encode('utf-8')
+ encoded = obj.encode('utf-8', 'surrogatepass')
n = len(encoded)
self.write(BINUNICODE + pack("<i", n) + encoded)
else:
@@ -966,7 +966,7 @@
def load_binunicode(self):
len = mloads(b'i' + self.read(4))
- self.append(str(self.read(len), 'utf-8'))
+ self.append(str(self.read(len), 'utf-8', 'surrogatepass'))
dispatch[BINUNICODE[0]] = load_binunicode
def load_short_binstring(self):
diff --git a/Lib/pickletools.py b/Lib/pickletools.py
index ca11aa3..6ab75c7 100644
--- a/Lib/pickletools.py
+++ b/Lib/pickletools.py
@@ -469,7 +469,7 @@
raise ValueError("unicodestring4 byte count < 0: %d" % n)
data = f.read(n)
if len(data) == n:
- return str(data, 'utf-8')
+ return str(data, 'utf-8', 'surrogatepass')
raise ValueError("expected %d bytes in a unicodestring4, but only %d "
"remain" % (n, len(data)))
diff --git a/Lib/test/pickletester.py b/Lib/test/pickletester.py
index 79407a6..dd0ed15 100644
--- a/Lib/test/pickletester.py
+++ b/Lib/test/pickletester.py
@@ -515,7 +515,9 @@
def test_unicode(self):
endcases = ['', '<\\u>', '<\\\u1234>', '<\n>',
- '<\\>', '<\\\U00012345>']
+ '<\\>', '<\\\U00012345>',
+ # surrogates
+ '<\udc80>']
for proto in protocols:
for u in endcases:
p = self.dumps(u, proto)
diff --git a/Misc/NEWS b/Misc/NEWS
index 8f80a96..35a405f 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -312,6 +312,10 @@
Library
-------
+- 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
+
- Issue #7585: difflib context and unified diffs now place a tab between
filename and date, conforming to the 'standards' they were originally
designed to follow. This improves compatibility with patch tools.
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;