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.

diff --git a/Lib/pickle.py b/Lib/pickle.py
index cb768b28586a1de6acd146de288e9a9785c13a02..a67ac7dd8b686ace0bf4e9510b7683eb40e87c4b 100644 (file)
--- a/Lib/pickle.py
+++ b/Lib/pickle.py
@@ -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)

diff --git a/Lib/test/pickletester.py b/Lib/test/pickletester.py
index f6fda9ee6d8363cc2f043eea036d4ff6afa22c87..f8f3bc92e7fe6b632b505c3ef6e0de6505c8207b 100644 (file)
--- a/Lib/test/pickletester.py
+++ b/Lib/test/pickletester.py
@@ -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.

diff --git a/Misc/NEWS.d/next/Library/2017-10-21-12-07-56.bpo-31829.6IhP-O.rst b/Misc/NEWS.d/next/Library/2017-10-21-12-07-56.bpo-31829.6IhP-O.rst
new file mode 100644 (file)
index 0000000..aefb8ae
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2017-10-21-12-07-56.bpo-31829.6IhP-O.rst
@@ -0,0 +1,3 @@
+``\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.

diff --git a/Modules/_pickle.c b/Modules/_pickle.c
index 57145beb8fff887b9d6f7287ccfe97804d6a183f..34e11bd5f820cdb9e9b08c031e934f2f0efc5dfd 100644 (file)
--- a/Modules/_pickle.c
+++ b/Modules/_pickle.c
@@ -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)