[Python-checkins] cpython (3.4): Issue #25262. Added support for BINBYTES8 opcode in Python implementation of

[serhiy.storchaka]

https://hg.python.org/cpython/rev/d4f8316d0860
changeset:   98402:d4f8316d0860
branch:      3.4
parent:      98399:1ab732cb4643
user:        Serhiy Storchaka <storchaka at gmail.com>
date:        Tue Sep 29 22:10:07 2015 +0300
summary:
  Issue #25262. Added support for BINBYTES8 opcode in Python implementation of
unpickler.  Highest 32 bits of 64-bit size for BINUNICODE8 and BINBYTES8
opcodes no longer silently ignored on 32-bit platforms in C implementation.

files:
  Lib/pickle.py            |   8 ++++++++
  Lib/test/pickletester.py |  20 ++++++++++++++++++++
  Misc/NEWS                |   4 ++++
  Modules/_pickle.c        |  12 +++++++++++-
  4 files changed, 43 insertions(+), 1 deletions(-)


diff --git a/Lib/pickle.py b/Lib/pickle.py
--- a/Lib/pickle.py
+++ b/Lib/pickle.py
@@ -1204,6 +1204,14 @@
         self.append(str(self.read(len), 'utf-8', 'surrogatepass'))
     dispatch[BINUNICODE8[0]] = load_binunicode8
 
+    def load_binbytes8(self):
+        len, = unpack('<Q', self.read(8))
+        if len > maxsize:
+            raise UnpicklingError("BINBYTES8 exceeds system's maximum size "
+                                  "of %d bytes" % maxsize)
+        self.append(self.read(len))
+    dispatch[BINBYTES8[0]] = load_binbytes8
+
     def load_short_binstring(self):
         len = self.read(1)[0]
         data = self.read(len)
diff --git a/Lib/test/pickletester.py b/Lib/test/pickletester.py
--- a/Lib/test/pickletester.py
+++ b/Lib/test/pickletester.py
@@ -857,6 +857,26 @@
         self.assert_is_copy([(100,), (100,)],
                             self.loads(b'((Kdtp0\nh\x00l.))'))
 
+    def test_binbytes8(self):
+        dumped = b'\x80\x04\x8e\4\0\0\0\0\0\0\0\xe2\x82\xac\x00.'
+        self.assertEqual(self.loads(dumped), b'\xe2\x82\xac\x00')
+
+    def test_binunicode8(self):
+        dumped = b'\x80\x04\x8d\4\0\0\0\0\0\0\0\xe2\x82\xac\x00.'
+        self.assertEqual(self.loads(dumped), '\u20ac\x00')
+
+    @requires_32b
+    def test_large_32b_binbytes8(self):
+        dumped = b'\x80\x04\x8e\4\0\0\0\1\0\0\0\xe2\x82\xac\x00.'
+        with self.assertRaises((pickle.UnpicklingError, OverflowError)):
+            self.loads(dumped)
+
+    @requires_32b
+    def test_large_32b_binunicode8(self):
+        dumped = b'\x80\x04\x8d\4\0\0\0\1\0\0\0\xe2\x82\xac\x00.'
+        with self.assertRaises((pickle.UnpicklingError, OverflowError)):
+            self.loads(dumped)
+
     def test_get(self):
         pickled = b'((lp100000\ng100000\nt.'
         unpickled = self.loads(pickled)
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -78,6 +78,10 @@
 Library
 -------
 
+- Issue #25262. Added support for BINBYTES8 opcode in Python implementation of
+  unpickler.  Highest 32 bits of 64-bit size for BINUNICODE8 and BINBYTES8
+  opcodes no longer silently ignored on 32-bit platforms in C implementation.
+
 - Issue #25034: Fix string.Formatter problem with auto-numbering and
   nested format_specs. Patch by Anthon van der Neut.
 
diff --git a/Modules/_pickle.c b/Modules/_pickle.c
--- a/Modules/_pickle.c
+++ b/Modules/_pickle.c
@@ -4540,7 +4540,17 @@
     int i;
     size_t x = 0;
 
-    for (i = 0; i < nbytes && i < sizeof(size_t); i++) {
+    if (nbytes > (int)sizeof(size_t)) {
+        /* Check for integer overflow.  BINBYTES8 and BINUNICODE8 opcodes
+         * have 64-bit size that can't be represented on 32-bit platform.
+         */
+        for (i = (int)sizeof(size_t); i < nbytes; i++) {
+            if (s[i])
+                return -1;
+        }
+        nbytes = (int)sizeof(size_t);
+    }
+    for (i = 0; i < nbytes; i++) {
         x |= (size_t) s[i] << (8 * i);
     }
 

-- 
Repository URL: https://hg.python.org/cpython