Python: Check if one dictionary is a subset of another larger dictionary

Question

I\'m trying to write a custom filter method that takes an arbitrary number of kwargs and returns a list containing the elements of a database-like list that contain

Answer 1

Here's a general recursive solution for the problem given:

import traceback
import unittest

def is_subset(superset, subset):
    for key, value in subset.items():
        if key not in superset:
            return False

        if isinstance(value, dict):
            if not is_subset(superset[key], value):
                return False

        elif isinstance(value, str):
            if value not in superset[key]:
                return False

        elif isinstance(value, list):
            if not set(value) <= set(superset[key]):
                return False
        elif isinstance(value, set):
            if not value <= superset[key]:
                return False

        else:
            if not value == superset[key]:
                return False

    return True


class Foo(unittest.TestCase):

    def setUp(self):
        self.dct = {
            'a': 'hello world',
            'b': 12345,
            'c': 1.2345,
            'd': [1, 2, 3, 4, 5],
            'e': {1, 2, 3, 4, 5},
            'f': {
                'a': 'hello world',
                'b': 12345,
                'c': 1.2345,
                'd': [1, 2, 3, 4, 5],
                'e': {1, 2, 3, 4, 5},
                'g': False,
                'h': None
            },
            'g': False,
            'h': None,
            'question': 'mcve',
            'metadata': {}
        }

    def tearDown(self):
        pass

    def check_true(self, superset, subset):
        return self.assertEqual(is_subset(superset, subset), True)

    def check_false(self, superset, subset):
        return self.assertEqual(is_subset(superset, subset), False)

    def test_simple_cases(self):
        self.check_true(self.dct, {'a': 'hello world'})
        self.check_true(self.dct, {'b': 12345})
        self.check_true(self.dct, {'c': 1.2345})
        self.check_true(self.dct, {'d': [1, 2, 3, 4, 5]})
        self.check_true(self.dct, {'e': {1, 2, 3, 4, 5}})
        self.check_true(self.dct, {'f': {
            'a': 'hello world',
            'b': 12345,
            'c': 1.2345,
            'd': [1, 2, 3, 4, 5],
            'e': {1, 2, 3, 4, 5},
        }})
        self.check_true(self.dct, {'g': False})
        self.check_true(self.dct, {'h': None})

    def test_tricky_cases(self):
        self.check_true(self.dct, {'a': 'hello'})
        self.check_true(self.dct, {'d': [1, 2, 3]})
        self.check_true(self.dct, {'e': {3, 4}})
        self.check_true(self.dct, {'f': {
            'a': 'hello world',
            'h': None
        }})
        self.check_false(
            self.dct, {'question': 'mcve', 'metadata': {'author': 'BPL'}})
        self.check_true(
            self.dct, {'question': 'mcve', 'metadata': {}})
        self.check_false(
            self.dct, {'question1': 'mcve', 'metadata': {}})

if __name__ == "__main__":
    unittest.main()

NOTE: The original code would fail in certain cases, credits for the fixing goes to @olivier-melançon

Answer 2

My function for the same purpose, doing this recursively:

def dictMatch(patn, real):
    """does real dict match pattern?"""
    try:
        for pkey, pvalue in patn.iteritems():
            if type(pvalue) is dict:
                result = dictMatch(pvalue, real[pkey])
                assert result
            else:
                assert real[pkey] == pvalue
                result = True
    except (AssertionError, KeyError):
        result = False
    return result

In your example, dictMatch(d1, d2) should return True even if d2 has other stuff in it, plus it applies also to lower levels:

d1 = {'a':'2', 'b':{3: 'iii'}}
d2 = {'a':'2', 'b':{3: 'iii', 4: 'iv'},'c':'4'}

dictMatch(d1, d2)   # True

Notes: There could be even better solution which avoids the if type(pvalue) is dict clause and applies to even wider range of cases (like lists of hashes etc). Also recursion is not limited here so use at your own risk. ;)

Answer 3

I know this question is old, but here is my solution for checking if one nested dictionary is a part of another nested dictionary. The solution is recursive.

def compare_dicts(a, b):
    for key, value in a.items():
        if key in b:
            if isinstance(a[key], dict):
                if not compare_dicts(a[key], b[key]):
                    return False
            elif value != b[key]:
                return False
        else:
            return False
    return True

Answer 4

Note for people that need this for unit testing: there's also an assertDictContainsSubset() method in Python's TestCase class.

http://docs.python.org/2/library/unittest.html?highlight=assertdictcontainssubset#unittest.TestCase.assertDictContainsSubset

It's however deprecated in 3.2, not sure why, maybe there's a replacement for it.