adding mypy.ini but there are still way too many mypy errors

Author: seperman

deepdiff/__init__.py

@@ -7,8 +7,8 @@
     logging.basicConfig(format='%(asctime)s %(levelname)8s %(message)s')
 
 
-from .diff import DeepDiff
-from .search import DeepSearch, grep
-from .deephash import DeepHash
-from .delta import Delta
-from .path import extract, parse_path
+from .diff import DeepDiff as DeepDiff
+from .search import DeepSearch as DeepSearch, grep as grep
+from .deephash import DeepHash as DeepHash
+from .delta import Delta as Delta
+from .path import extract as extract, parse_path as parse_path

deepdiff/deephash.py

@@ -107,8 +107,8 @@ def prepare_string_for_hashing(
                 break
             except UnicodeDecodeError as er:
                 err = er
-        if not encoded:
-            obj_decoded = obj.decode('utf-8', errors='ignore')
+        if not encoded and err is not None:
+            obj_decoded = obj.decode('utf-8', errors='ignore')  # type: ignore
             start = max(err.start - 20, 0)
             start_prefix = ''
             if start > 0:
@@ -379,7 +379,7 @@ def _skip_this(self, obj, parent):
                         skip = False
                         break
         elif self.exclude_regex_paths and any(
-                [exclude_regex_path.search(parent) for exclude_regex_path in self.exclude_regex_paths]):
+                [exclude_regex_path.search(parent) for exclude_regex_path in self.exclude_regex_paths]):  # type: ignore
             skip = True
         elif self.exclude_types_tuple and isinstance(obj, self.exclude_types_tuple):
             skip = True
@@ -540,7 +540,7 @@ def _hash(self, obj, parent, parents_ids=EMPTY_FROZENSET):
         elif isinstance(obj, datetime.date):
             result = self._prep_date(obj)
 
-        elif isinstance(obj, numbers):
+        elif isinstance(obj, numbers):  # type: ignore
             result = self._prep_number(obj)
 
         elif isinstance(obj, MutableMapping):
@@ -549,17 +549,17 @@ def _hash(self, obj, parent, parents_ids=EMPTY_FROZENSET):
         elif isinstance(obj, tuple):
             result, counts = self._prep_tuple(obj=obj, parent=parent, parents_ids=parents_ids)
 
-        elif (pandas and isinstance(obj, pandas.DataFrame)):
-            def gen():
-                yield ('dtype', obj.dtypes)
-                yield ('index', obj.index)
-                yield from obj.items()  # which contains (column name, series tuples)
+        elif (pandas and isinstance(obj, pandas.DataFrame)):  # type: ignore
+            def gen():  # type: ignore
+                yield ('dtype', obj.dtypes)  # type: ignore
+                yield ('index', obj.index)  # type: ignore
+                yield from obj.items()  # type: ignore  # which contains (column name, series tuples)
             result, counts = self._prep_iterable(obj=gen(), parent=parent, parents_ids=parents_ids)
-        elif (polars and isinstance(obj, polars.DataFrame)):
+        elif (polars and isinstance(obj, polars.DataFrame)):  # type: ignore
             def gen():
-                yield from obj.columns
-                yield from list(obj.schema.items())
-                yield from obj.rows()
+                yield from obj.columns  # type: ignore
+                yield from list(obj.schema.items())  # type: ignore
+                yield from obj.rows()  # type: ignore
             result, counts = self._prep_iterable(obj=gen(), parent=parent, parents_ids=parents_ids)
 
         elif isinstance(obj, Iterable):

deepdiff/delta.py

@@ -171,7 +171,7 @@ def reset(self):
         self.post_process_paths_to_convert = dict_()
 
     def __add__(self, other):
-        if isinstance(other, numbers) and self._numpy_paths:
+        if isinstance(other, numbers) and self._numpy_paths:  # type: ignore
             raise DeltaNumpyOperatorOverrideError(DELTA_NUMPY_OPERATOR_OVERRIDE_MSG)
         if self.mutate:
             self.root = other
@@ -240,7 +240,7 @@ def _get_elem_and_compare_to_old_value(
             if action == GET:
                 current_old_value = obj[elem]
             elif action == GETATTR:
-                current_old_value = getattr(obj, elem)
+                current_old_value = getattr(obj, elem)  # type: ignore
             else:
                 raise DeltaError(INVALID_ACTION_WHEN_CALLING_GET_ELEM.format(action))
         except (KeyError, IndexError, AttributeError, TypeError) as e:
@@ -261,7 +261,7 @@ def _get_elem_and_compare_to_old_value(
                     else:
                         obj[elem] = _forced_old_value
                 elif action == GETATTR:
-                    setattr(obj, elem, _forced_old_value)
+                    setattr(obj, elem, _forced_old_value)  # type: ignore
                 return _forced_old_value
             current_old_value = not_found
             if isinstance(path_for_err_reporting, (list, tuple)):
@@ -289,7 +289,7 @@ def _simple_set_elem_value(self, obj, path_for_err_reporting, elem=None, value=N
                     else:
                         self._raise_or_log(ELEM_NOT_FOUND_TO_ADD_MSG.format(elem, path_for_err_reporting))
             elif action == GETATTR:
-                setattr(obj, elem, value)
+                setattr(obj, elem, value)  # type: ignore
             else:
                 raise DeltaError(INVALID_ACTION_WHEN_CALLING_SIMPLE_SET_ELEM.format(action))
         except (KeyError, IndexError, AttributeError, TypeError) as e:
@@ -457,8 +457,8 @@ def _do_item_added(self, items, sort=True, insert=False):
                 continue  # pragma: no cover. Due to cPython peephole optimizer, this line doesn't get covered. https://github.com/nedbat/coveragepy/issues/198
 
             # Insert is only true for iterables, make sure it is a valid index.
-            if(insert and elem < len(obj)):
-                obj.insert(elem, None)
+            if(insert and elem < len(obj)):  # type: ignore
+                obj.insert(elem, None)  # type: ignore
 
             self._set_new_value(parent, parent_to_obj_elem, parent_to_obj_action,
                                 obj, elements, path, elem, action, new_value)
@@ -482,7 +482,7 @@ def _do_post_process(self):
     def _do_pre_process(self):
         if self._numpy_paths and ('iterable_item_added' in self.diff or 'iterable_item_removed' in self.diff):
             preprocess_paths = dict_()
-            for path, type_ in self._numpy_paths.items():
+            for path, type_ in self._numpy_paths.items():  # type: ignore
                 preprocess_paths[path] = {'old_type': np_ndarray, 'new_type': list}
                 try:
                     type_ = numpy_dtype_string_to_type(type_)
@@ -507,7 +507,7 @@ def _get_elements_and_details(self, path):
                 parent_to_obj_elem, parent_to_obj_action = elements[-2]
                 obj = self._get_elem_and_compare_to_old_value(
                     obj=parent, path_for_err_reporting=path, expected_old_value=None,
-                    elem=parent_to_obj_elem, action=parent_to_obj_action, next_element=next2_element)
+                    elem=parent_to_obj_elem, action=parent_to_obj_action, next_element=next2_element)  # type: ignore
             else:
                 # parent = self
                 # obj = self.root
@@ -516,7 +516,7 @@ def _get_elements_and_details(self, path):
                 parent = parent_to_obj_elem = parent_to_obj_action = None
                 obj = self
                 # obj = self.get_nested_obj(obj=self, elements=elements[:-1])
-            elem, action = elements[-1]
+            elem, action = elements[-1]  # type: ignore
         except Exception as e:
             self._raise_or_log(UNABLE_TO_GET_ITEM_MSG.format(path, e))
             return None
@@ -550,7 +550,7 @@ def _do_values_or_type_changed(self, changes, is_type_change=False, verify_chang
                     else:
                         new_value = new_type(current_old_value)
                 except Exception as e:
-                    self._raise_or_log(TYPE_CHANGE_FAIL_MSG.format(obj[elem], value.get('new_type', 'unknown'), e))
+                    self._raise_or_log(TYPE_CHANGE_FAIL_MSG.format(obj[elem], value.get('new_type', 'unknown'), e))  # type: ignore
                     continue
             else:
                 new_value = value['new_value']
@@ -582,7 +582,7 @@ def _do_item_removed(self, items):
             current_old_value = not_found
             try:
                 if action == GET:
-                    current_old_value = obj[elem]
+                    current_old_value = obj[elem]  # type: ignore
                 elif action == GETATTR:
                     current_old_value = getattr(obj, elem)
                 look_for_expected_old_value = current_old_value != expected_old_value
@@ -644,15 +644,15 @@ def _do_iterable_opcodes(self):
                         transformed.extend(opcode.new_values)
                     elif opcode.tag == 'equal':
                         # Items are the same in both lists, so we add them to the result
-                        transformed.extend(obj[opcode.t1_from_index:opcode.t1_to_index])
+                        transformed.extend(obj[opcode.t1_from_index:opcode.t1_to_index])  # type: ignore
                 if is_obj_tuple:
-                    obj = tuple(obj)
+                    obj = tuple(obj)  # type: ignore
                     # Making sure that the object is re-instated inside the parent especially if it was immutable
                     # and we had to turn it into a mutable one. In such cases the object has a new id.
                     self._simple_set_elem_value(obj=parent, path_for_err_reporting=path, elem=parent_to_obj_elem,
                                                 value=obj, action=parent_to_obj_action)
                 else:
-                    obj[:] = transformed
+                    obj[:] = transformed  # type: ignore
 
 
 
@@ -745,7 +745,7 @@ def _do_ignore_order(self):
         fixed_indexes = self.diff.get('iterable_items_added_at_indexes', dict_())
         remove_indexes = self.diff.get('iterable_items_removed_at_indexes', dict_())
         paths = SetOrdered(fixed_indexes.keys()) | SetOrdered(remove_indexes.keys())
-        for path in paths:
+        for path in paths:  # type: ignore
             # In the case of ignore_order reports, we are pointing to the container object.
             # Thus we add a [0] to the elements so we can get the required objects and discard what we don't need.
             elem_and_details = self._get_elements_and_details("{}[0]".format(path))
@@ -1021,7 +1021,7 @@ def _from_flat_dicts(flat_dict_list):
                     result['_iterable_opcodes'][path_str] = []
                 result['_iterable_opcodes'][path_str].append(
                     Opcode(
-                        tag=FLAT_DATA_ACTION_TO_OPCODE_TAG[action],
+                        tag=FLAT_DATA_ACTION_TO_OPCODE_TAG[action],  # type: ignore
                         t1_from_index=flat_dict.get('t1_from_index'),
                         t1_to_index=flat_dict.get('t1_to_index'),
                         t2_from_index=flat_dict.get('t2_from_index'),
@@ -1091,7 +1091,7 @@ def to_flat_dicts(self, include_action_in_path=False, report_type_changes=True)
         """
         return [
             i._asdict() for i in self.to_flat_rows(include_action_in_path=False, report_type_changes=True)
-        ]
+        ]  # type: ignore
 
     def to_flat_rows(self, include_action_in_path=False, report_type_changes=True) -> List[FlatDeltaRow]:
         """
@@ -1141,13 +1141,13 @@ def to_flat_rows(self, include_action_in_path=False, report_type_changes=True) -
                     for index, value in index_to_value.items():
                         path2 = path.copy()
                         if include_action_in_path:
-                            path2.append((index, 'GET'))
+                            path2.append((index, 'GET'))  # type: ignore
                         else:
                             path2.append(index)
                         if report_type_changes:
-                            row = FlatDeltaRow(path=path2, value=value, action=new_action, type=type(value))
+                            row = FlatDeltaRow(path=path2, value=value, action=new_action, type=type(value))  # type: ignore
                         else:
-                            row = FlatDeltaRow(path=path2, value=value, action=new_action)
+                            row = FlatDeltaRow(path=path2, value=value, action=new_action)  # type: ignore
                         result.append(row)
             elif action in {'set_item_added', 'set_item_removed'}:
                 for path, values in info.items():
@@ -1167,15 +1167,15 @@ def to_flat_rows(self, include_action_in_path=False, report_type_changes=True) -
                         value = value[new_key]
                     elif isinstance(value, (list, tuple)) and len(value) == 1:
                         value = value[0]
-                        path.append(0)
+                        path.append(0)  # type: ignore
                         action = 'iterable_item_added'
                     elif isinstance(value, set) and len(value) == 1:
                         value = value.pop()
                         action = 'set_item_added'
                     if report_type_changes:
-                        row = FlatDeltaRow(path=path, value=value, action=action, type=type(value))
+                        row = FlatDeltaRow(path=path, value=value, action=action, type=type(value))  # type: ignore
                     else:
-                        row = FlatDeltaRow(path=path, value=value, action=action)
+                        row = FlatDeltaRow(path=path, value=value, action=action)  # type: ignore
                     result.append(row)
             elif action in {
                 'dictionary_item_removed', 'iterable_item_added',

deepdiff/lfucache.py

@@ -23,17 +23,17 @@ def __init__(self, key, report_type, value, freq_node, pre, nxt):
         self.nxt = nxt  # next CacheNode
 
     def free_myself(self):
-        if self.freq_node.cache_head == self.freq_node.cache_tail:
-            self.freq_node.cache_head = self.freq_node.cache_tail = None
-        elif self.freq_node.cache_head == self:
-            self.nxt.pre = None
-            self.freq_node.cache_head = self.nxt
-        elif self.freq_node.cache_tail == self:
-            self.pre.nxt = None
-            self.freq_node.cache_tail = self.pre
+        if self.freq_node.cache_head == self.freq_node.cache_tail:  # type: ignore
+            self.freq_node.cache_head = self.freq_node.cache_tail = None  # type: ignore
+        elif self.freq_node.cache_head == self:  # type: ignore
+            self.nxt.pre = None  # type: ignore
+            self.freq_node.cache_head = self.nxt  # type: ignore
+        elif self.freq_node.cache_tail == self:  # type: ignore
+            self.pre.nxt = None  # type: ignore
+            self.freq_node.cache_tail = self.pre  # type: ignore
         else:
-            self.pre.nxt = self.nxt
-            self.nxt.pre = self.pre
+            self.pre.nxt = self.nxt  # type: ignore
+            self.nxt.pre = self.pre  # type: ignore
 
         self.pre = None
         self.nxt = None
@@ -77,8 +77,8 @@ def pop_head_cache(self):
             return cache_head
         else:
             cache_head = self.cache_head
-            self.cache_head.nxt.pre = None
-            self.cache_head = self.cache_head.nxt
+            self.cache_head.nxt.pre = None  # type: ignore
+            self.cache_head = self.cache_head.nxt  # type: ignore
             return cache_head
 
     def append_cache_to_tail(self, cache_node):
@@ -89,7 +89,7 @@ def append_cache_to_tail(self, cache_node):
         else:
             cache_node.pre = self.cache_tail
             cache_node.nxt = None
-            self.cache_tail.nxt = cache_node
+            self.cache_tail.nxt = cache_node  # type: ignore
             self.cache_tail = cache_node
 
     def insert_after_me(self, freq_node):
@@ -172,12 +172,12 @@ def move_forward(self, cache_node, freq_node):
 
     def dump_cache(self):
         head_freq_node = self.freq_link_head
-        self.cache.pop(head_freq_node.cache_head.key)
-        head_freq_node.pop_head_cache()
+        self.cache.pop(head_freq_node.cache_head.key)  # type: ignore
+        head_freq_node.pop_head_cache()  # type: ignore
 
-        if head_freq_node.count_caches() == 0:
-            self.freq_link_head = head_freq_node.nxt
-            head_freq_node.remove()
+        if head_freq_node.count_caches() == 0:  # type: ignore
+            self.freq_link_head = head_freq_node.nxt  # type: ignore
+            head_freq_node.remove()  # type: ignore
 
     def create_cache_node(self, key, report_type, value):
         cache_node = CacheNode(

docs/faq.rst

@@ -149,6 +149,7 @@ Or use the tree view so you can use path(output_format='list'):
 
 
 Q: Why my datetimes are reported in UTC?
+----------------------------------------
 
 **Answer**
 

mypy.ini

@@ -0,0 +1,2 @@
+[mypy]
+warn_unused_ignores = False

requirements-dev.txt

@@ -19,3 +19,4 @@ pytest-benchmark==5.1.0
 pandas==2.2.3
 polars==1.21.0
 setuptools==75.8.0
+types-setuptools==75.8.0

tests/test_operators.py

@@ -31,7 +31,7 @@ def _l2_distance(self, c1, c2):
                     (c1["x"] - c2["x"]) ** 2 + (c1["y"] - c2["y"]) ** 2
                 )
 
-            def give_up_diffing(self, level, diff_instance):
+            def give_up_diffing(self, level, diff_instance) -> bool:
                 l2_distance = self._l2_distance(level.t1, level.t2)
                 if l2_distance > self.distance_threshold:
                     diff_instance.custom_report_result('distance_too_far', level, {
@@ -77,7 +77,7 @@ def _l2_distance(self, c1, c2):
                     (c1["x"] - c2["x"]) ** 2 + (c1["y"] - c2["y"]) ** 2
                 )
 
-            def give_up_diffing(self, level, diff_instance):
+            def give_up_diffing(self, level, diff_instance) -> bool:
                 l2_distance = self._l2_distance(level.t1, level.t2)
                 if l2_distance > self.distance_threshold:
                     diff_instance.custom_report_result('distance_too_far', level, {
@@ -122,7 +122,7 @@ class ExpectChangeOperator(BaseOperator):
             def __init__(self, regex_paths):
                 super().__init__(regex_paths)
 
-            def give_up_diffing(self, level, diff_instance):
+            def give_up_diffing(self, level, diff_instance) -> bool:
                 if level.t1 == level.t2:
                     diff_instance.custom_report_result('unexpected:still', level, {
                         "old": level.t1,
@@ -154,9 +154,10 @@ def __repr__(self):
 
         class ListMatchOperator(BaseOperator):
 
-            def give_up_diffing(self, level, diff_instance):
+            def give_up_diffing(self, level, diff_instance) -> bool:
                 if set(level.t1.dict['list']) == set(level.t2.dict['list']):
                     return True
+                return False
 
         ddiff = DeepDiff(custom1, custom2, custom_operators=[
             ListMatchOperator(types=[CustomClass])
@@ -260,6 +261,7 @@ def __init__(self, tolerance, types):
             def match(self, level) -> bool:
                 if type(level.t1) in self.types:
                     return True
+                return False
 
             def give_up_diffing(self, level, diff_instance) -> bool:
                 relative = abs(abs(level.t1 - level.t2) / level.t1)