DynamoDB: Fix serializing ARRAYs of OBJECTs using a cast to OBJECT[]

crate · Aug 23, 2024 · f382455 · f382455
1 parent 5ab7848
commit f382455
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 15 deletions.
diff --git a/src/commons_codec/transform/dynamodb.py b/src/commons_codec/transform/dynamodb.py
@@ -177,20 +177,8 @@ def values_to_update(self, keys: t.Dict[str, t.Dict[str, str]]) -> str:
                 # TODO: Does it also need escaping of inner TEXT values, like the above?
                 key_value = "'" + json.dumps(key_value) + "'::OBJECT"
 
-            # TODO: ARRAY types do not support JSON syntax yet.
-            #       Let's relay them 1:1, which works for primitive inner types,
-            #       but complex ones need special treatment, like representing
-            #       OBJECTs in CrateDB-native syntax.
-            # FIXME: Find a way to use a custom JSONEncoder for that, in order to
-            #        fully support also nested elements of those.
-            # https://github.com/crate/commons-codec/issues/33
-            elif isinstance(key_value, list):
-                if key_value:
-                    if isinstance(key_value[0], dict):
-                        items = []
-                        for item in key_value:
-                            items.append("{" + ", ".join(f"{key}='{value}'" for key, value in item.items()) + "}")
-                        key_value = "[" + ",".join(items) + "]"
+            elif isinstance(key_value, list) and key_value and isinstance(key_value[0], dict):
+                key_value = "'" + json.dumps(key_value) + "'::OBJECT[]"
 
             constraint = f"{self.DATA_COLUMN}['{key_name}'] = {key_value}"
             constraints.append(constraint)

diff --git a/tests/transform/test_dynamodb.py b/tests/transform/test_dynamodb.py
@@ -228,7 +228,7 @@ def test_decode_cdc_modify_nested():
         "SET data['tags'] = ['foo', 'bar'], data['empty_map'] = '{}'::OBJECT, data['empty_list'] = [],"
         " data['string_set'] = ['location_1'], data['number_set'] = [0.34, 1.0, 2.0, 3.0],"
         " data['binary_set'] = ['U3Vubnk='], data['somemap'] = '{\"test\": 1.0, \"test2\": 2.0}'::OBJECT,"
-        " data['list_of_objects'] = [{foo='bar'},{baz='qux'}]"
+        ' data[\'list_of_objects\'] = \'[{"foo": "bar"}, {"baz": "qux"}]\'::OBJECT[]'
         " WHERE data['device'] = 'foo' AND data['timestamp'] = '2024-07-12T01:17:42';"
     )