better support for Pydantic models. Ignore model_fields_set when

comparing pydantic objects

Author: seperman

deepdiff/deephash.py

@@ -12,7 +12,7 @@
                              convert_item_or_items_into_compiled_regexes_else_none,
                              get_id, type_is_subclass_of_type_group, type_in_type_group,
                              number_to_string, datetime_normalize, KEY_TO_VAL_STR, short_repr,
-                             get_truncate_datetime, dict_, add_root_to_paths)
+                             get_truncate_datetime, dict_, add_root_to_paths, PydanticBaseModel)
 from deepdiff.base import Base
 
 try:
@@ -331,13 +331,15 @@ def values(self):
     def items(self):
         return ((i, v[0]) for i, v in self.hashes.items())
 
-    def _prep_obj(self, obj, parent, parents_ids=EMPTY_FROZENSET, is_namedtuple=False):
+    def _prep_obj(self, obj, parent, parents_ids=EMPTY_FROZENSET, is_namedtuple=False, is_pydantic_object=False):
         """prepping objects"""
         original_type = type(obj) if not isinstance(obj, type) else obj
 
         obj_to_dict_strategies = []
         if is_namedtuple:
             obj_to_dict_strategies.append(lambda o: o._asdict())
+        elif is_pydantic_object:
+            obj_to_dict_strategies.append(lambda o: {k: v for (k, v) in o.__dict__.items() if v !="model_fields_set"})
         else:
             obj_to_dict_strategies.append(lambda o: o.__dict__)
 
@@ -562,6 +564,8 @@ def gen():
 
         elif obj == BoolObj.TRUE or obj == BoolObj.FALSE:
             result = 'bool:true' if obj is BoolObj.TRUE else 'bool:false'
+        elif isinstance(obj, PydanticBaseModel):
+            result, counts = self._prep_obj(obj=obj, parent=parent, parents_ids=parents_ids, is_pydantic_object=True)
         else:
             result, counts = self._prep_obj(obj=obj, parent=parent, parents_ids=parents_ids)
 

deepdiff/diff.py

@@ -80,6 +80,9 @@ def _report_progress(_stats, progress_logger, duration):
 PURGE_LEVEL_RANGE_MSG = 'cache_purge_level should be 0, 1, or 2.'
 _ENABLE_CACHE_EVERY_X_DIFF = '_ENABLE_CACHE_EVERY_X_DIFF'
 
+model_fields_set = frozenset(["model_fields_set"])
+
+
 # What is the threshold to consider 2 items to be pairs. Only used when ignore_order = True.
 CUTOFF_DISTANCE_FOR_PAIRS_DEFAULT = 0.3
 
@@ -437,13 +440,16 @@ def _diff_enum(self, level, parents_ids=frozenset(), local_tree=None):
             local_tree=local_tree,
         )
 
-    def _diff_obj(self, level, parents_ids=frozenset(), is_namedtuple=False, local_tree=None):
+    def _diff_obj(self, level, parents_ids=frozenset(), is_namedtuple=False, local_tree=None, is_pydantic_object=False):
         """Difference of 2 objects"""
         processing_error = False
         try:
             if is_namedtuple:
                 t1 = level.t1._asdict()
                 t2 = level.t2._asdict()
+            elif is_pydantic_object:
+                t1 = detailed__dict__(level.t1, ignore_private_variables=self.ignore_private_variables, ignore_keys=model_fields_set)
+                t2 = detailed__dict__(level.t2, ignore_private_variables=self.ignore_private_variables, ignore_keys=model_fields_set)
             elif all('__dict__' in dir(t) for t in level):
                 t1 = detailed__dict__(level.t1, ignore_private_variables=self.ignore_private_variables)
                 t2 = detailed__dict__(level.t2, ignore_private_variables=self.ignore_private_variables)
@@ -1678,7 +1684,7 @@ def _diff(self, level, parents_ids=frozenset(), _original_type=None, local_tree=
             self._diff_numpy_array(level, parents_ids, local_tree=local_tree)
 
         elif isinstance(level.t1, PydanticBaseModel):
-            self._diff_obj(level, parents_ids, local_tree=local_tree)
+            self._diff_obj(level, parents_ids, local_tree=local_tree, is_pydantic_object=True)
 
         elif isinstance(level.t1, Iterable):
             self._diff_iterable(level, parents_ids, _original_type=_original_type, local_tree=local_tree)