Issue #19881: Fix bad pickling of large bytes in cpickle.

diff --git a/Lib/test/pickletester.py b/Lib/test/pickletester.py
index 1b08dbd8b5f31014459e7fefb50ed35f52f6a442..040c26f2577985130d5a0ac54e4cbdee111b34fd 100644 (file)
--- a/Lib/test/pickletester.py
+++ b/Lib/test/pickletester.py
@@ -3,6 +3,7 @@ import io
 import pickle
 import pickletools
 import random
+import struct
 import sys
 import unittest
 import weakref
@@ -1611,9 +1612,9 @@ class BigmemPickleTests(unittest.TestCase):
         data = 1 << (8 * size)
         try:
             for proto in protocols:
+                if proto < 2:
+                    continue
                 with self.subTest(proto=proto):
-                    if proto < 2:
-                        continue
                     with self.assertRaises((ValueError, OverflowError)):
                         self.dumps(data, protocol=proto)
         finally:
@@ -1628,13 +1629,17 @@ class BigmemPickleTests(unittest.TestCase):
         data = b"abcd" * (size // 4)
         try:
             for proto in protocols:
+                if proto < 3:
+                    continue
                 with self.subTest(proto=proto):
-                    if proto < 3:
-                        continue
                     try:
                         pickled = self.dumps(data, protocol=proto)
-                        self.assertTrue(b"abcd" in pickled[:19])
-                        self.assertTrue(b"abcd" in pickled[-18:])
+                        header = (pickle.BINBYTES +
+                                  struct.pack("<I", len(data)))
+                        data_start = pickled.index(data)
+                        self.assertEqual(
+                            header,
+                            pickled[data_start-len(header):data_start])
                     finally:
                         pickled = None
         finally:
@@ -1642,14 +1647,28 @@ class BigmemPickleTests(unittest.TestCase):
 
     @bigmemtest(size=_4G, memuse=1 + 1, dry_run=False)
     def test_huge_bytes_64b(self, size):
-        data = b"a" * size
+        data = b"acbd" * (size // 4)
         try:
             for proto in protocols:
+                if proto < 3:
+                    continue
                 with self.subTest(proto=proto):
-                    if proto < 3:
+                    if proto == 3:
+                        # Protocol 3 does not support large bytes objects.
+                        # Verify that we do not crash when processing one.
+                        with self.assertRaises((ValueError, OverflowError)):
+                            self.dumps(data, protocol=proto)
                         continue
-                    with self.assertRaises((ValueError, OverflowError)):
-                        self.dumps(data, protocol=proto)
+                    try:
+                        pickled = self.dumps(data, protocol=proto)
+                        header = (pickle.BINBYTES8 +
+                                  struct.pack("<Q", len(data)))
+                        data_start = pickled.index(data)
+                        self.assertEqual(
+                            header,
+                            pickled[data_start-len(header):data_start])
+                    finally:
+                        pickled = None
         finally:
             data = None
 
@@ -1661,11 +1680,19 @@ class BigmemPickleTests(unittest.TestCase):
         data = "abcd" * (size // 4)
         try:
             for proto in protocols:
+                if proto == 0:
+                    continue
                 with self.subTest(proto=proto):
                     try:
                         pickled = self.dumps(data, protocol=proto)
-                        self.assertTrue(b"abcd" in pickled[:19])
-                        self.assertTrue(b"abcd" in pickled[-18:])
+                        header = (pickle.BINUNICODE +
+                                  struct.pack("<I", len(data)))
+                        data_start = pickled.index(b'abcd')
+                        self.assertEqual(
+                            header,
+                            pickled[data_start-len(header):data_start])
+                        self.assertEqual((pickled.rindex(b"abcd") + len(b"abcd") -
+                                          pickled.index(b"abcd")), len(data))
                     finally:
                         pickled = None
         finally:
@@ -1680,19 +1707,25 @@ class BigmemPickleTests(unittest.TestCase):
         data = "abcd" * (size // 4)
         try:
             for proto in protocols:
+                if proto == 0:
+                    continue
                 with self.subTest(proto=proto):
-                    if proto == 0:
-                        continue
                     if proto < 4:
                         with self.assertRaises((ValueError, OverflowError)):
                             self.dumps(data, protocol=proto)
-                    else:
-                        try:
-                            pickled = self.dumps(data, protocol=proto)
-                            self.assertTrue(b"abcd" in pickled[:19])
-                            self.assertTrue(b"abcd" in pickled[-18:])
-                        finally:
-                            pickled = None
+                        continue
+                    try:
+                        pickled = self.dumps(data, protocol=proto)
+                        header = (pickle.BINUNICODE8 +
+                                  struct.pack("<Q", len(data)))
+                        data_start = pickled.index(b'abcd')
+                        self.assertEqual(
+                            header,
+                            pickled[data_start-len(header):data_start])
+                        self.assertEqual((pickled.rindex(b"abcd") + len(b"abcd") -
+                                          pickled.index(b"abcd")), len(data))
+                    finally:
+                        pickled = None
         finally:
             data = None
 

diff --git a/Misc/NEWS b/Misc/NEWS
index 90e0dce393aa12eaf11d56d4418fc556aba31b24..2d7acddbb1fc84fbec41a0f2eae4fcc6a4bb497f 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -18,11 +18,15 @@ Core and Builtins
 Library
 -------
 
+
 - Issue #19296: Silence compiler warning in dbm_open
 
 - Issue #19839: Fix regression in bz2 module's handling of non-bzip2 data at
   EOF, and analogous bug in lzma module.
 
+- Issue #19881: Fix pickling bug where cpickle would emit bad pickle data for
+  large bytes string (i.e., with size greater than 2**32-1).
+
 - Issue #19138: doctest's IGNORE_EXCEPTION_DETAIL now allows a match when
   no exception detail exists (no colon following the exception's name, or
   a colon does follow but no text follows the colon).

diff --git a/Modules/_pickle.c b/Modules/_pickle.c
index c8afa8e47c3cf22efd7c7d439daf2934aba10355..330b17ddca54b24b33c4843c129521149445f0ab 100644 (file)
--- a/Modules/_pickle.c
+++ b/Modules/_pickle.c
@@ -2027,7 +2027,7 @@ save_bytes(PicklerObject *self, PyObject *obj)
         else if (self->proto >= 4) {
             header[0] = BINBYTES8;
             _write_size64(header + 1, size);
-            len = 8;
+            len = 9;
         }
         else {
             PyErr_SetString(PyExc_OverflowError,