bpo-26707: Enable plistlib to read UID keys. (GH-12153)

Plistlib currently throws an exception when asked to decode a valid
.plist file that was generated by Apple's NSKeyedArchiver. Specifically,
this is caused by a byte 0x80 (signifying a UID) not being understood.

This fixes the problem by enabling the binary plist reader and writer
to read and write plistlib.UID objects.

1 files changed, 46 insertions, 3 deletions

diff --git a/Lib/plistlib.py b/Lib/plistlib.py
index 248f514..0133c89 100644
--- a/Lib/plistlib.py
+++ b/Lib/plistlib.py
@@ -48,7 +48,7 @@ Parse Plist example:
 __all__ = [
     "readPlist", "writePlist", "readPlistFromBytes", "writePlistToBytes",
     "Data", "InvalidFileException", "FMT_XML", "FMT_BINARY",
-    "load", "dump", "loads", "dumps"
+    "load", "dump", "loads", "dumps", "UID"
 ]
 
 import binascii
@@ -175,6 +175,34 @@ class Data:
 #
 
 
+class UID:
+    def __init__(self, data):
+        if not isinstance(data, int):
+            raise TypeError("data must be an int")
+        if data >= 1 << 64:
+            raise ValueError("UIDs cannot be >= 2**64")
+        if data < 0:
+            raise ValueError("UIDs must be positive")
+        self.data = data
+
+    def __index__(self):
+        return self.data
+
+    def __repr__(self):
+        return "%s(%s)" % (self.__class__.__name__, repr(self.data))
+
+    def __reduce__(self):
+        return self.__class__, (self.data,)
+
+    def __eq__(self, other):
+        if not isinstance(other, UID):
+            return NotImplemented
+        return self.data == other.data
+
+    def __hash__(self):
+        return hash(self.data)
+
+
 #
 # XML support
 #
@@ -649,8 +677,9 @@ class _BinaryPlistParser:
             s = self._get_size(tokenL)
             result = self._fp.read(s * 2).decode('utf-16be')
 
-        # tokenH == 0x80 is documented as 'UID' and appears to be used for
-        # keyed-archiving, not in plists.
+        elif tokenH == 0x80:  # UID
+            # used by Key-Archiver plist files
+            result = UID(int.from_bytes(self._fp.read(1 + tokenL), 'big'))
 
         elif tokenH == 0xA0:  # array
             s = self._get_size(tokenL)
@@ -874,6 +903,20 @@ class _BinaryPlistWriter (object):
 
             self._fp.write(t)
 
+        elif isinstance(value, UID):
+            if value.data < 0:
+                raise ValueError("UIDs must be positive")
+            elif value.data < 1 << 8:
+                self._fp.write(struct.pack('>BB', 0x80, value))
+            elif value.data < 1 << 16:
+                self._fp.write(struct.pack('>BH', 0x81, value))
+            elif value.data < 1 << 32:
+                self._fp.write(struct.pack('>BL', 0x83, value))
+            elif value.data < 1 << 64:
+                self._fp.write(struct.pack('>BQ', 0x87, value))
+            else:
+                raise OverflowError(value)
+
         elif isinstance(value, (list, tuple)):
             refs = [self._getrefnum(o) for o in value]
             s = len(refs)