Commit 38ab7d47 authored by Serhiy Storchaka's avatar Serhiy Storchaka Committed by GitHub

bpo-31829: Make protocol 0 pickles be loadable in text mode in Python 2. (GH-11859)

Escape ``\r``, ``\0`` and ``\x1a`` (end-of-file on Windows) in Unicode strings.
parent ba043021
......@@ -852,7 +852,10 @@ class _Pickler:
self.write(BINUNICODE + pack("<I", n) + encoded)
else:
obj = obj.replace("\\", "\\u005c")
obj = obj.replace("\0", "\\u0000")
obj = obj.replace("\n", "\\u000a")
obj = obj.replace("\r", "\\u000d")
obj = obj.replace("\x1a", "\\u001a") # EOF on DOS
self.write(UNICODE + obj.encode('raw-unicode-escape') +
b'\n')
self.memoize(obj)
......
......@@ -3067,22 +3067,20 @@ class BadGetattr:
class AbstractPickleModuleTests(unittest.TestCase):
def test_dump_closed_file(self):
import os
f = open(TESTFN, "wb")
try:
f.close()
self.assertRaises(ValueError, self.dump, 123, f)
finally:
os.remove(TESTFN)
support.unlink(TESTFN)
def test_load_closed_file(self):
import os
f = open(TESTFN, "wb")
try:
f.close()
self.assertRaises(ValueError, self.dump, 123, f)
finally:
os.remove(TESTFN)
support.unlink(TESTFN)
def test_load_from_and_dump_to_file(self):
stream = io.BytesIO()
......@@ -3106,6 +3104,19 @@ class AbstractPickleModuleTests(unittest.TestCase):
self.Pickler(f, -1)
self.Pickler(f, protocol=-1)
def test_dump_text_file(self):
f = open(TESTFN, "w")
try:
for proto in protocols:
self.assertRaises(TypeError, self.dump, 123, f, proto)
finally:
f.close()
support.unlink(TESTFN)
def test_incomplete_input(self):
s = io.BytesIO(b"X''.")
self.assertRaises((EOFError, struct.error, pickle.UnpicklingError), self.load, s)
def test_bad_init(self):
# Test issue3664 (pickle can segfault from a badly initialized Pickler).
# Override initialization without calling __init__() of the superclass.
......
``\r``, ``\0`` and ``\x1a`` (end-of-file on Windows) are now escaped in
protocol 0 pickles of Unicode strings. This allows to load them without loss
from files open in text mode in Python 2.
......@@ -2588,7 +2588,10 @@ raw_unicode_escape(PyObject *obj)
*p++ = Py_hexdigits[ch & 15];
}
/* Map 16-bit characters, '\\' and '\n' to '\uxxxx' */
else if (ch >= 256 || ch == '\\' || ch == '\n') {
else if (ch >= 256 ||
ch == '\\' || ch == 0 || ch == '\n' || ch == '\r' ||
ch == 0x1a)
{
/* -1: subtract 1 preallocated byte */
p = _PyBytesWriter_Prepare(&writer, p, 6-1);
if (p == NULL)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment