fix(ingestion/mongodb): MongoDB source unable to parse datetimes with…

… years > 9999

metadata-ingestion/src/datahub/ingestion/source/mongodb.py

@@ -4,8 +4,8 @@
 from typing import Dict, Iterable, List, Optional, Tuple, Type, Union, ValuesView
 
 import bson.timestamp
-import pymongo
 import pymongo.collection
+from bson import CodecOptions, DatetimeConversion
 from packaging import version
 from pydantic import PositiveInt, validator
 from pydantic.fields import Field
@@ -281,8 +281,11 @@ def __init__(self, ctx: PipelineContext, config: MongoDBConfig):
             **options,
             **self.config.options,
         }
+        codec_options: CodecOptions = CodecOptions(
+            datetime_conversion=DatetimeConversion.DATETIME_AUTO
+        )
 
-        self.mongo_client = pymongo.MongoClient(self.config.connect_uri, **options)  # type: ignore
+        self.mongo_client = MongoClient(self.config.connect_uri, codec_options=codec_options, **options)  # type: ignore
 
         # This cheaply tests the connection. For details, see
         # https://pymongo.readthedocs.io/en/stable/api/pymongo/mongo_client.html#pymongo.mongo_client.MongoClient