MongoDB: Add support for UUID types

CHANGES.md

@@ -3,6 +3,7 @@
 
 ## Unreleased
 - MongoDB: Rename columns with leading underscores to use double leading underscores
+- MongoDB: Add support for UUID types
 
 ## 2024/09/02 v0.0.21
 - DynamoDB: Add special decoding for varied lists.

cratedb_toolkit/io/mongodb/export.py

@@ -24,8 +24,10 @@
 Export the documents from a MongoDB collection as JSON, to be ingested into CrateDB.
 """
 
+import base64
 import calendar
 import typing as t
+from uuid import UUID
 
 import bsonjs
 import dateutil.parser as dateparser
@@ -65,6 +67,9 @@ def extract_value(value, parent_type=None):
     """
     if isinstance(value, dict):
         if len(value) == 1:
+            if "$binary" in value and value["$binary"]["subType"] in ["03", "04"]:
+                decoded = UUID(bytes=base64.b64decode(value["$binary"]["base64"]))
+                return extract_value(decoded, parent_type)
             for k, v in value.items():
                 if k.startswith("$"):
                     return extract_value(v, k.lstrip("$"))

cratedb_toolkit/io/mongodb/extract.py

@@ -67,6 +67,7 @@
 import typing as t
 
 import bson
+from bson import OLD_UUID_SUBTYPE, UUID_SUBTYPE
 from pymongo.collection import Collection
 from rich import progress
 from rich.console import Console
@@ -197,4 +198,7 @@ def get_type(value):
             return "INTEGER"
         else:
             return "INT64"
+    if type_ is bson.binary.Binary:
+        if value.subtype in [OLD_UUID_SUBTYPE, UUID_SUBTYPE]:
+            return "UUID"
     return TYPES_MAP.get(type_, "UNKNOWN")

cratedb_toolkit/io/mongodb/translate.py

@@ -37,6 +37,7 @@
 
 TYPES = {
     "OID": "TEXT",
+    "UUID": "TEXT",
     "DATETIME": "TIMESTAMP WITH TIME ZONE",
     "TIMESTAMP": "TIMESTAMP WITHOUT TIME ZONE",
     "INT64": "BIGINT",