Q52672598: Read bson representation into JSON

#!/usr/bin/env python3

import re
import json
import tempfile
from bson import json_util
from pprint import pprint

example = \
"""{
   "_id" : ObjectId("5baca841d25ce14b7d3d017c"),
    "country" : "in",
    "state" : "",
    "date" : ISODate("1902-01-31T00:00:00.000Z")
}"""


def read_mongoextjson_file(filename):
    with open(filename, "r") as f:
        # read the entire input; in a real application,
        # you would want to read a chunk at a time
        bsondata = f.read()

        # convert the TenGen JSON to Strict JSON
        # here, I just convert the ObjectId and Date structures,
        # but it's easy to extend to cover all structures listed at
        # http://www.mongodb.org/display/DOCS/Mongo+Extended+JSON
        jsondata = re.sub(r'ObjectId\s*\(\s*\"(\S+)\"\s*\)',
                          r'{"$oid": "\1"}',
                          bsondata)
        jsondata = re.sub(r'ISODate\s*\(\s*(\S+)\s*\)',
                          r'{"$date": \1}',
                          jsondata)
        jsondata = re.sub(r'NumberInt\s*\(\s*(\S+)\s*\)',
                          r'{"$numberInt": "\1"}',
                          jsondata)

        # now we can parse this as JSON, and use MongoDB's object_hook
        # function to get rich Python data structures inside a dictionary
        data = json.loads(jsondata, object_hook=json_util.object_hook)

        return data


if __name__ == '__main__':

    with tempfile.NamedTemporaryFile(mode='w+') as temp:
        temp.write(example)
        temp.flush()

        data = read_mongoextjson_file(temp.name)

    print('data is of type: {}'.format(type(data)))

    pprint(data)

    exit(0)