Python - comparing JSON data structures.

README.md

Python - comparing JSON data structures

A function compare_json_data(source_data_a,source_data_b), accepting structures populated with data loaded from json.load() and comparing for equality.

Example

$ ./compare.py 
Compare JSON result is: True

JSON files a.json and b.json are loaded via load_json() function and structures passed into compare_json_data() for comparison.

a.json

{
	"apple": "value",
	"orange": 12,
	"banana": [1,2,3,"One","Two","Three","Fourth"],
	"grape": false,
	"strawberry": null,
	"carrot": [
		{
			"fourth": "value-two",
			"first": {
				"apple": "value1",
				"orange": "value2"
			},
			"second": "value",
			"third": "another"
		},
		{},
		["One","Two","Three"]
	],
	"pear": {
		"first": "value",
		"second": "another",
		"third": [1,2,3,"One","Two","Three"],
		"fourth": [
			{
				"first": "value",
				"second": "another"
			},
			{}
		]
	}
}

b.json

{
	"apple": "value",
	"orange": 12,
	"banana": [1,2,3,"One","Two","Three","Fourth"],
	"pear": {
		"first": "value",
		"second": "another",
		"third": [1,2,3,"One","Two","Three"],
		"fourth": [
			{
				"second": "another",
				"first": "value"
			},
			{}
		]
	},
	"grape": false,
	"strawberry": null,
	"carrot": [
		{
			"second": "value",
			"third": "another",
			"fourth": "value-two",
			"first": {
				"apple": "value1",
				"orange": "value2"
			}
		},
		{},
		["One","Two","Three"]
	]
}

compare.py

#!/usr/bin/env python3

import json


def load_json(file_path):
    # open JSON file and parse contents
    fh = open(file_path, "r")
    data = json.load(fh)
    fh.close()

    return data


def compare_json_data(source_data_a, source_data_b):
    def compare(data_a, data_b):
        # type: list
        if type(data_a) is list:
            # is [data_b] a list and of same length as [data_a]?
            if (type(data_b) is not list) or (len(data_a) != len(data_b)):
                return False

            # iterate over list items
            for list_index, list_item in enumerate(data_a):
                # compare [data_a] list item against [data_b] at index
                if not compare(list_item, data_b[list_index]):
                    return False

            # list identical
            return True

        # type: dictionary
        if type(data_a) is dict:
            # is [data_b] a dictionary?
            if type(data_b) is not dict:
                return False

            # iterate over dictionary keys
            for dict_key, dict_value in data_a.items():
                # key exists in [data_b] dictionary, and same value?
                if (dict_key not in data_b) or (
                    not compare(dict_value, data_b[dict_key])
                ):
                    return False

            # dictionary identical
            return True

        # simple value - compare both value and type for equality
        return (data_a == data_b) and (type(data_a) is type(data_b))

    # compare a to b, then b to a
    return compare(source_data_a, source_data_b) and compare(
        source_data_b, source_data_a
    )


def main():
    # import testing JSON files to Python structures
    a_json = load_json("a.json")
    b_json = load_json("b.json")

    # compare first struct against second
    print(f"Compare JSON result is: {compare_json_data(a_json, b_json)}")


if __name__ == "__main__":
    main()

Hey @prixgoody - that's weird - this check should mean that's not possible:

(len(data_a) != len(data_b))

do you have an example of data structures that throw this error?

Hi, I have used your code but instead of returning true false, i am fetching more details like for which value it is diff. Still in progress.
Sorry for the miscommunication caused.

Hey @prixgoody - that's weird - this check should mean that's not possible:

(len(data_a) != len(data_b))

do you have an example of data structures that throw this error?

Hi, I have used your code but instead of returning true false, i am fetching more details like for which value it is diff. Still in progress.
Sorry for the miscommunication caused.

Any luck fetching which value is diff? I'm working on it too.