fix(parser): fix data types for sourceIPAddress and sequencer fields in S3RecordModel Model (#6154)

make it possible for S3 object to have s3.amazonaws.com in sourceIPAddress and not to have sequencer

Author: DKurilo

aws_lambda_powertools/utilities/parser/models/s3.py

@@ -1,5 +1,5 @@
 from datetime import datetime
-from typing import List, Literal, Optional
+from typing import List, Literal, Optional, Union
 
 from pydantic import BaseModel, model_validator
 from pydantic.fields import Field
@@ -23,7 +23,7 @@ class S3Identity(BaseModel):
 
 
 class S3RequestParameters(BaseModel):
-    sourceIPAddress: IPvAnyNetwork
+    sourceIPAddress: Union[IPvAnyNetwork, Literal["s3.amazonaws.com"]]
 
 
 class S3ResponseElements(BaseModel):
@@ -45,7 +45,7 @@ class S3Object(BaseModel):
     key: str
     size: Optional[NonNegativeFloat] = None
     eTag: Optional[str] = None
-    sequencer: str
+    sequencer: Optional[str] = None
     versionId: Optional[str] = None
 
 

tests/events/s3EventLifecycleTransition.json

@@ -0,0 +1,43 @@
+{
+  "Records": [
+    {
+      "eventVersion": "2.3",
+      "eventSource": "aws:s3",
+      "awsRegion": "us-east-1",
+      "eventTime": "2019-09-03T19:37:27.192Z",
+      "eventName": "LifecycleTransition",
+      "userIdentity": {
+        "principalId": "s3.amazonaws.com"
+      },
+      "requestParameters": {
+        "sourceIPAddress": "s3.amazonaws.com"
+      },
+      "responseElements": {
+        "x-amz-request-id": "D82B88E5F771F645",
+        "x-amz-id-2": "vlR7PnpV2Ce81l0PRw6jlUpck7Jo5ZsQjryTjKlc5aLWGVHPZLj5NeC6qMa0emYBDXOo6QBU0Wo="
+      },
+      "s3": {
+        "s3SchemaVersion": "1.0",
+        "configurationId": "828aa6fc-f7b5-4305-8584-487c791949c1",
+        "bucket": {
+          "name": "lambda-artifacts-deafc19498e3f2df",
+          "ownerIdentity": {
+            "principalId": "A3I5XTEXAMAI3E"
+          },
+          "arn": "arn:aws:s3:::lambda-artifacts-deafc19498e3f2df"
+        },
+        "object": {
+          "key": "/path/to/file.parquet",
+          "size": 12345,
+          "eTag": "abcdef1232423423",
+          "versionId": "SomeThingThere"
+        }
+      },
+      "lifecycleEventData": {
+        "transitionEventData": {
+          "destinationStorageClass": "INTELLIGENT_TIERING"
+        }
+      }
+    }
+  ]
+}

tests/unit/parser/_pydantic/test_s3.py

@@ -157,3 +157,44 @@ def test_s3_none_etag_value_failed_validation():
     raw_event["Records"][0]["s3"]["object"]["eTag"] = None
     with pytest.raises(ValidationError):
         S3Model(**raw_event)
+
+
+def test_s3_trigger_event_lifecycle_transition():
+    raw_event = load_event("s3EventLifecycleTransition.json")
+    parsed_event: S3Model = S3Model(**raw_event)
+
+    records = list(parsed_event.Records)
+    assert len(records) == 1
+
+    record: S3RecordModel = records[0]
+    raw_record = raw_event["Records"][0]
+    assert record.eventVersion == raw_record["eventVersion"]
+    assert record.eventSource == raw_record["eventSource"]
+    assert record.awsRegion == raw_record["awsRegion"]
+    convert_time = int(round(record.eventTime.timestamp() * 1000))
+    assert convert_time == 1567539447192
+    assert record.eventName == raw_record["eventName"]
+    assert record.glacierEventData is None
+
+    user_identity = record.userIdentity
+    assert user_identity.principalId == raw_record["userIdentity"]["principalId"]
+
+    request_parameters = record.requestParameters
+    assert str(request_parameters.sourceIPAddress) == "s3.amazonaws.com"
+    assert record.responseElements.x_amz_request_id == raw_record["responseElements"]["x-amz-request-id"]
+    assert record.responseElements.x_amz_id_2 == raw_record["responseElements"]["x-amz-id-2"]
+
+    s3 = record.s3
+    raw_s3 = raw_event["Records"][0]["s3"]
+    assert s3.s3SchemaVersion == raw_record["s3"]["s3SchemaVersion"]
+    assert s3.configurationId == raw_record["s3"]["configurationId"]
+    assert s3.object.key == raw_s3["object"]["key"]
+    assert s3.object.size == 12345
+    assert s3.object.eTag == "abcdef1232423423"
+    assert s3.object.versionId == "SomeThingThere"
+
+    bucket = s3.bucket
+    raw_bucket = raw_record["s3"]["bucket"]
+    assert bucket.name == raw_bucket["name"]
+    assert bucket.ownerIdentity.principalId == raw_bucket["ownerIdentity"]["principalId"]
+    assert bucket.arn == raw_bucket["arn"]