Use to_python to make sure keys are correct type (#22)

* pass values to prep functions

* test that values are prepped

* formatting

* always return identity func if no 'to_python' method

Author: VKFisher

bulk_sync/__init__.py

@@ -1,5 +1,6 @@
-from collections import OrderedDict
+from collections import OrderedDict, defaultdict
 import logging
+import functools
 
 from django.db import transaction, router
 from django.core.exceptions import FieldDoesNotExist
@@ -50,7 +51,8 @@ def bulk_sync(
 
     if db_class is None:
         raise RuntimeError(
-            "Unable to identify model to sync. Need to provide at least one object in `new_models`, provide `db_class`, or set `new_models` with a queryset like `db_class.objects.none()`."
+            "Unable to identify model to sync. Need to provide at least one object in `new_models`, provide "
+            "`db_class`, or set `new_models` with a queryset like `db_class.objects.none()`."
         )
 
     if fields is None:
@@ -79,15 +81,25 @@ def bulk_sync(
             objs = objs.filter(filters)
         objs = objs.only("pk", *key_fields).select_for_update()
 
-        def get_key(obj):
-            return tuple(getattr(obj, k) for k in key_fields)
+        prep_functions = defaultdict(lambda: lambda x: x)
+        prep_functions.update({
+            field.name: functools.partial(field.to_python)
+            for field in (db_class._meta.get_field(k) for k in key_fields)
+            if hasattr(field, 'to_python')
+        })
+
+        def get_key(obj, prep_values=False):
+            return tuple(
+                prep_functions[k](getattr(obj, k)) if prep_values else getattr(obj, k)
+                for k in key_fields
+            )
 
         obj_dict = {get_key(obj): obj for obj in objs}
 
         new_objs = []
         existing_objs = []
         for new_obj in new_models:
-            old_obj = obj_dict.pop(get_key(new_obj), None)
+            old_obj = obj_dict.pop(get_key(new_obj, prep_values=True), None)
             if old_obj is None:
                 # This is a new object, so create it.
                 new_objs.append(new_obj)

tests/tests.py

@@ -219,6 +219,28 @@ def test_empty_new_models_class_detection_works(self):
         ret = bulk_sync(new_models=[], filters=None, key_fields=("name",), db_class=Employee)
         ret = bulk_sync(new_models=Employee.objects.none(), filters=None, key_fields=("name",))
 
+    def test_new_objs_with_unprepped_field_values_are_processed_correctly(self):
+        c1 = Company.objects.create(name="Foo Products, Ltd.")
+        c2 = Company.objects.create(name="Bar Microcontrollers, Inc.")
+        e1 = Employee.objects.create(name="Scott", age=40, company=c1)
+
+        new_objs = [Employee(name="Scott", age="40", company=c2)]
+
+        ret = bulk_sync(
+            new_models=new_objs,
+            filters=None,
+            key_fields=("name", "age"),
+        )
+
+        # we should should update e1's company to c2
+        self.assertEqual(1, ret["stats"]["updated"])
+        self.assertEqual(c2, Employee.objects.get(pk=e1.pk).company)
+
+        # we should not create or delete anything
+        self.assertEqual(0, ret["stats"]["created"])
+        self.assertEqual(0, ret["stats"]["deleted"])
+        self.assertEqual(1, Employee.objects.count())
+
 
 class BulkCompareTests(TestCase):
     """ Test `bulk_compare` method """