Merge pull request #176 from seperman/dev

adding exclude_obj_callback

README.md

@@ -1,4 +1,4 @@
-# DeepDiff v 4.2.0
+# DeepDiff v 4.3.0
 
 <!-- ![Downloads](https://img.shields.io/pypi/dm/deepdiff.svg?style=flat) -->
 ![Python Versions](https://img.shields.io/pypi/pyversions/deepdiff.svg?style=flat)
@@ -417,6 +417,7 @@ And then running
 
 # ChangeLog
 
+- v4-3-0: adding exclude_obj_callback
 - v4-2-0: .json property is finally removed. Fix for Py3.10. Dropping support for EOL Python 3.4. Ignoring private keys when calculating hashes. For example __init__ is not a part of hash calculation anymore. Fix for #166 Problem with comparing lists, with an boolean as element.
 - v4-0-9: Fixing the bug for hashing custom unhashable objects
 - v4-0-8: Adding ignore_nan_inequality for float('nan')
@@ -507,3 +508,4 @@ Thank you!
 - Juan Soler (Soleronline) for adding ignore_type_number
 - mthaddon for adding timedelta diffing support
 - Necrophagos for Hashing of the number 1 vs. True
+- gaal-dev for adding exclude_obj_callback

deepdiff/__init__.py

@@ -1,6 +1,6 @@
 """This module offers the DeepDiff, DeepSearch, grep and DeepHash classes."""
 # flake8: noqa
-__version__ = '4.2.0'
+__version__ = '4.3.0'
 import logging
 
 if __name__ == '__main__':

deepdiff/deephash_doc.rst

@@ -34,6 +34,11 @@ exclude_paths: list, default = None
 exclude_regex_paths: list, default = None
     List of string regex paths or compiled regex paths objects to exclude from the report. If only one item, you can path it as a string instead of a list containing only one regex path.
 
+exclude_obj_callback
+    function, default = None
+    A function that takes the object and its path and returns a Boolean. If True is returned, the object is excluded from the results, otherwise it is included.
+    This is to give the user a higher level of control than one can achieve via exclude_paths, exclude_regex_paths or other means.
+
 hasher: function. default = DeepHash.murmur3_128bit
     hasher is the hashing function. The default is DeepHash.murmur3_128bit.
     But you can pass another hash function to it if you want.
@@ -286,6 +291,22 @@ ignore_string_case
     >>> DeepHash('hello', ignore_string_case=True)['hello'] == DeepHash('heLLO', ignore_string_case=True)['heLLO']
     True
 
+exclude_obj_callback
+    function, default = None
+    A function that takes the object and its path and returns a Boolean. If True is returned, the object is excluded from the results, otherwise it is included.
+    This is to give the user a higher level of control than one can achieve via exclude_paths, exclude_regex_paths or other means.
+
+    >>> dic1 = {"x": 1, "y": 2, "z": 3}
+    >>> t1 = [dic1]
+    >>> t1_hash = DeepHash(t1, exclude_obj_callback=exclude_obj_callback)
+    >>>
+    >>> dic2 = {"z": 3}
+    >>> t2 = [dic2]
+    >>> t2_hash = DeepHash(t2, exclude_obj_callback=exclude_obj_callback)
+    >>>
+    >>> t1_hash[t1] == t2_hash[t2]
+    True
+
 number_format_notation : string, default="f"
     When numbers are converted to the string, you have the choices between "f" as fixed point and "e" as scientific notation:
 

deepdiff/diff.py

@@ -484,6 +484,7 @@ def __create_hashtable(self, t, level):
                                       ignore_type_subclasses=self.ignore_type_subclasses,
                                       ignore_string_case=self.ignore_string_case,
                                       number_to_string_func=self.number_to_string,
+                                      exclude_obj_callback=self.exclude_obj_callback,
                                       )
                 # import pytest; pytest.set_trace()
                 key = item

deepdiff/diff_doc.rst

@@ -71,6 +71,10 @@ view: string, default = text
 exclude_types: list, default = None
     List of object types to exclude from the report.
 
+exclude_obj_callback: function, default = None
+    A function that takes the object and its path and returns a Boolean. If True is returned, the object is excluded from the results, otherwise it is included.
+    This is to give the user a higher level of control than one can achieve via exclude_paths, exclude_regex_paths or other means.
+
 ignore_string_type_changes: Boolean, default = False
     Whether to ignore string type changes or not. For example b"Hello" vs. "Hello" are considered the same if ignore_string_type_changes is set to True.
 
@@ -497,6 +501,20 @@ ignore_nan_inequality
     >>> DeepDiff(float('nan'), float('nan'), ignore_nan_inequality=True)
     {}
 
+
+exclude_obj_callback
+    function, default = None
+    A function that takes the object and its path and returns a Boolean. If True is returned, the object is excluded from the results, otherwise it is included.
+    This is to give the user a higher level of control than one can achieve via exclude_paths, exclude_regex_paths or other means.
+
+    >>> def exclude_obj_callback(obj, path):
+    ...     return True if "skip" in path or isinstance(obj, int) else False
+    ...
+    >>> t1 = {"x": 10, "y": "b", "z": "c", "skip_1": 0}
+    >>> t2 = {"x": 12, "y": "b", "z": "c", "skip_2": 0}
+    >>> DeepDiff(t1, t2, exclude_obj_callback=exclude_obj_callback)
+    {}
+
 **Tree View**
 
 Starting the version 3 You can chooe the view into the deepdiff results.
@@ -806,7 +824,7 @@ Example:
 .. seealso::
     Take a look at to_json() documentation in this page for more details.
 
-If you want the original DeepDiff object to be serialized with all the bells and whistles, you can use the to_json_pickle() and to_json_pickle() in order to serialize and deserialize its results into json. Note that json_pickle is unsafe and json pickle dumps from untrusted sources should never be loaded.
+If you want the original DeepDiff object to be serialized with all the bells and whistles, you can use the to_json_pickle() and from_json_pickle() in order to serialize and deserialize its results into json. Note that json_pickle is unsafe and json pickle dumps from untrusted sources should never be loaded.
 
 Serialize and then deserialize back to deepdiff
     >>> t1 = {1: 1, 2: 2, 3: 3}

docs/conf.py

@@ -59,9 +59,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = '4.2.0'
+version = '4.3.0'
 # The full version, including alpha/beta/rc tags.
-release = '4.2.0'
+release = '4.3.0'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

docs/index.rst

@@ -4,7 +4,7 @@
    contain the root `toctree` directive.
 
 
-DeepDiff 4.2.0 documentation!
+DeepDiff 4.3.0 documentation!
 =============================
 
 **DeepDiff: Deep Difference of dictionaries, iterables, strings and other objects. It will recursively look for all the changes.**
@@ -281,6 +281,7 @@ Indices and tables
 Changelog
 =========
 
+- v4-3-0: adding exclude_obj_callback
 - v4-2-0: .json property is finally removed. Fix for Py3.10. Dropping support for EOL Python 3.4. Ignoring private keys when calculating hashes. For example __init__ is not a part of hash calculation anymore. Fix for #166 Problem with comparing lists, with an boolean as element.
 - v4-1-0: .json property is finally removed.
 - v4-0-9: Fixing the bug for hashing custom unhashable objects
@@ -364,4 +365,4 @@ And thanks to the following people for their great contributions!
 - Necrophagos for Hashing of the number 1 vs. True
 - Hugo (hugovk) for fixes for Python 3.10 and dropping support for EOL Python 3.4
 - Andrey Gavrilin (gaal-dev) for hashing classes.
-
+- gaal-dev for adding exclude_obj_callback

setup.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 4.2.0
+current_version = 4.3.0
 commit = True
 tag = True
 tag_name = {new_version}

setup.py

@@ -10,7 +10,7 @@
 if os.environ.get('USER', '') == 'vagrant':
     del os.link
 
-version = '4.2.0'
+version = '4.3.0'
 
 
 def get_reqs(filename):

tests/test_diff_text.py

@@ -1651,8 +1651,8 @@ def test_skip_exclude_obj_callback(self):
         def exclude_obj_callback(obj, path):
             return True if "skip" in path or isinstance(obj, int) else False
 
-        t1 = {"x": "a", "y": "b", "z": "c", "skip_1": 0}
-        t2 = {"x": "a", "y": "b", "z": "c", "skip_2": 1}
+        t1 = {"x": 10, "y": "b", "z": "c", "skip_1": 0}
+        t2 = {"x": 12, "y": "b", "z": "c", "skip_2": 0}
         ddiff = DeepDiff(t1, t2, exclude_obj_callback=exclude_obj_callback)
         result = {}
         assert result == ddiff

tests/test_hash.py

@@ -529,6 +529,10 @@ def exclude_obj_callback(obj, parent):
         t1_hash = DeepHashPrep(t1, exclude_obj_callback=exclude_obj_callback)
         assert t1_hash == {'y': 'str:y', 'z': 'str:z', 3: 'int:3',
                            get_id(dic1): 'dict:{str:z:int:3}', get_id(t1): 'list:dict:{str:z:int:3}'}
+        dic2 = {"z": 3}
+        t2 = [dic2]
+        t2_hash = DeepHashPrep(t2, exclude_obj_callback=exclude_obj_callback)
+        assert t1_hash[t1] == t2_hash[t2]
 
     def test_string_case(self):
         t1 = "Hello"