Current class fields when unpickling. Fixes #888

Optimize dereferencing map by using sets.

AUTHORS

@@ -218,3 +218,4 @@ that much better:
  * Matthew Ellison (https://github.com/seglberg)
  * Jimmy Shen (https://github.com/jimmyshen)
  * J. Fernando Sánchez (https://github.com/balkian)
+ * Michael Chase (https://github.com/rxsegrxup)

docs/changelog.rst

@@ -7,6 +7,8 @@ Changes in 0.9.X - DEV
 ======================
 - ListField of embedded docs doesn't set the _instance attribute when iterating over it #914
 - Support += and *= for ListField #595
+- Use sets for populating dbrefs to dereference
+- Fixed unpickled documents replacing the global field's list. #888
 
 Changes in 0.9.0
 ================

mongoengine/base/document.py

@@ -206,7 +206,12 @@ class BaseDocument(object):
             if k in data:
                 setattr(self, k, data[k])
         if '_fields_ordered' in data:
-            setattr(type(self), '_fields_ordered', data['_fields_ordered'])
+            if self._dynamic:
+                setattr(self, '_fields_ordered', data['_fields_ordered'])
+            else:
+                _super_fields_ordered = type(self)._fields_ordered
+                setattr(self, '_fields_ordered', _super_fields_ordered)
+
         dynamic_fields = data.get('_dynamic_fields') or SON()
         for k in dynamic_fields.keys():
             setattr(self, k, data["_data"].get(k))

mongoengine/dereference.py

@@ -102,24 +102,24 @@ class DeReference(object):
                 for field_name, field in item._fields.iteritems():
                     v = item._data.get(field_name, None)
                     if isinstance(v, (DBRef)):
-                        reference_map.setdefault(field.document_type, []).append(v.id)
+                        reference_map.setdefault(field.document_type, set()).add(v.id)
                     elif isinstance(v, (dict, SON)) and '_ref' in v:
-                        reference_map.setdefault(get_document(v['_cls']), []).append(v['_ref'].id)
+                        reference_map.setdefault(get_document(v['_cls']), set()).add(v['_ref'].id)
                     elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:
                         field_cls = getattr(getattr(field, 'field', None), 'document_type', None)
                         references = self._find_references(v, depth)
                         for key, refs in references.iteritems():
                             if isinstance(field_cls, (Document, TopLevelDocumentMetaclass)):
                                 key = field_cls
-                            reference_map.setdefault(key, []).extend(refs)
+                            reference_map.setdefault(key, set()).update(refs)
             elif isinstance(item, (DBRef)):
-                reference_map.setdefault(item.collection, []).append(item.id)
+                reference_map.setdefault(item.collection, set()).add(item.id)
             elif isinstance(item, (dict, SON)) and '_ref' in item:
-                reference_map.setdefault(get_document(item['_cls']), []).append(item['_ref'].id)
+                reference_map.setdefault(get_document(item['_cls']), set()).add(item['_ref'].id)
             elif isinstance(item, (dict, list, tuple)) and depth - 1 <= self.max_depth:
                 references = self._find_references(item, depth - 1)
                 for key, refs in references.iteritems():
-                    reference_map.setdefault(key, []).extend(refs)
+                    reference_map.setdefault(key, set()).update(refs)
 
         return reference_map
 
@@ -128,8 +128,8 @@ class DeReference(object):
         """
         object_map = {}
         for collection, dbrefs in self.reference_map.iteritems():
-            keys = object_map.keys()
+            refs = [dbref for dbref in dbrefs
-            refs = list(set([dbref for dbref in dbrefs if unicode(dbref).encode('utf-8') not in keys]))
+                    if unicode(dbref).encode('utf-8') not in object_map]
             if hasattr(collection, 'objects'):  # We have a document class for the refs
                 references = collection.objects.in_bulk(refs)
                 for key, doc in references.iteritems():

tests/document/instance.py

@@ -10,6 +10,7 @@ import uuid
 
 from datetime import datetime
 from bson import DBRef, ObjectId
+from tests import fixtures
 from tests.fixtures import (PickleEmbedded, PickleTest, PickleSignalsTest,
                             PickleDyanmicEmbedded, PickleDynamicTest)
 
@@ -2085,6 +2086,29 @@ class InstanceTest(unittest.TestCase):
         self.assertEqual(pickle_doc.string, "Two")
         self.assertEqual(pickle_doc.lists, ["1", "2", "3"])
 
+    def test_regular_document_pickle(self):
+
+        pickle_doc = PickleTest(number=1, string="One", lists=['1', '2'])
+        pickled_doc = pickle.dumps(pickle_doc)  # make sure pickling works even before the doc is saved
+        pickle_doc.save()
+
+        pickled_doc = pickle.dumps(pickle_doc)
+
+        # Test that when a document's definition changes the new
+        # definition is used
+        fixtures.PickleTest = fixtures.NewDocumentPickleTest
+
+        resurrected = pickle.loads(pickled_doc)
+        self.assertEqual(resurrected.__class__,
+                         fixtures.NewDocumentPickleTest)
+        self.assertEqual(resurrected._fields_ordered,
+                         fixtures.NewDocumentPickleTest._fields_ordered)
+        self.assertNotEqual(resurrected._fields_ordered,
+                            pickle_doc._fields_ordered)
+
+        # The local PickleTest is still a ref to the original
+        fixtures.PickleTest = PickleTest
+
     def test_dynamic_document_pickle(self):
 
         pickle_doc = PickleDynamicTest(

tests/fixtures.py

@@ -17,6 +17,15 @@ class PickleTest(Document):
     photo = FileField()
 
 
+class NewDocumentPickleTest(Document):
+    number = IntField()
+    string = StringField(choices=(('One', '1'), ('Two', '2')))
+    embedded = EmbeddedDocumentField(PickleEmbedded)
+    lists = ListField(StringField())
+    photo = FileField()
+    new_field = StringField()
+
+
 class PickleDyanmicEmbedded(DynamicEmbeddedDocument):
     date = DateTimeField(default=datetime.now)