chore: datazone example documentation

.projenrc.ts

@@ -527,6 +527,7 @@ const datazoneMskGovernance = new awscdk.AwsCdkPythonApp({
 
 datazoneMskGovernance.addGitIgnore('cdk.context.json');
 datazoneMskGovernance.addGitIgnore('resources/flink/?');
+datazoneMskGovernance.addGitIgnore('resources/flink/dependency-reduced-pom.xml');
 datazoneMskGovernance.removeTask('deploy');
 datazoneMskGovernance.removeTask('destroy');
 datazoneMskGovernance.removeTask('diff');

examples/datazone-msk-governance/resources/flink/src/main/java/com/amazonaws/services/msf/KafkaStreamingJob.java

@@ -1,3 +1,6 @@
+// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+
 package com.amazonaws.services.msf;
 
 import com.amazonaws.services.kinesisanalytics.runtime.KinesisAnalyticsRuntime;

examples/datazone-msk-governance/resources/flink/src/main/java/com/amazonaws/services/msf/openlineage/AmazonDataZoneConfig.java

@@ -1,3 +1,6 @@
+// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+
 package com.amazonaws.services.msf.openlineage;
 
 

examples/datazone-msk-governance/resources/flink/src/main/java/com/amazonaws/services/msf/openlineage/AmazonDataZoneTransport.java

@@ -1,3 +1,6 @@
+// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+
 package com.amazonaws.services.msf.openlineage;
 
 import io.openlineage.client.OpenLineage;

examples/datazone-msk-governance/resources/flink/src/main/java/com/amazonaws/services/msf/openlineage/AmazonDataZoneTransportBuilder.java

@@ -1,3 +1,6 @@
+// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+// SPDX-License-Identifier: Apache-2.0
+
 package com.amazonaws.services.msf.openlineage;
 
 import io.openlineage.client.transports.Transport;

examples/datazone-msk-governance/resources/lambda/consumer/consumer_factory.py

@@ -1,3 +1,6 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
 import logging
 from kafka import KafkaConsumer
 from aws_schema_registry import SchemaRegistryClient

examples/datazone-msk-governance/resources/lambda/consumer/index.py

@@ -1,3 +1,6 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
 from consumer_factory import ConsumerFactory
 import logging
 from common import load_config

examples/datazone-msk-governance/resources/lambda/producer/index.py

@@ -1,3 +1,6 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
 from producer.producer_factory import ProducerFactory
 import os
 

examples/datazone-msk-governance/resources/lambda/producer/producer_factory.py

@@ -1,3 +1,6 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
 import yaml
 from kafka import KafkaProducer
 from aws_msk_iam_sasl_signer import MSKAuthTokenProvider

examples/datazone-msk-governance/resources/lambda/utils/common.py

@@ -1,3 +1,6 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
 from openlineage.client import OpenLineageClient
 from openlineage.client.run import RunEvent, RunState, Run, Job, Dataset
 from openlineage.client.facet import SchemaDatasetFacet

examples/datazone-msk-governance/resources/lambda/utils/custom_transport.py

@@ -1,3 +1,6 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
 import logging
 from typing import Dict, Any
 from dataclasses import dataclass

examples/datazone-msk-governance/resources/lambda/utils/schema_registry.py

@@ -1,3 +1,6 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
 from aws_schema_registry import SchemaRegistryClient, Schema
 from aws_schema_registry.adapter.kafka import KafkaSerializer
 from aws_schema_registry.avro import AvroSchema

examples/datazone-msk-governance/stacks/main.py

@@ -1,3 +1,6 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
 from aws_cdk import (
     BundlingOptions,
     CfnParameterProps,

website/docs/examples/streaming-governance.md

@@ -5,9 +5,9 @@ sidebar_label: Streaming governance with DataZone example
 
 # Streaming governance with Amazon DataZone
 
-Govern Kafka topics from Amazon MSK in DataZone. Store metadata like lineage, schema and data format in DataZone business catalog. Subscribe to MSK topics via the DataZone subcription grant process.
+Govern Kafka topics from Amazon MSK in DataZone. Store metadata including data lineage, schema and data format in DataZone's business catalog. Subscribe to MSK topics using the DataZone subscription and fulfillment workflows.
 
-In this example, we will be using DSF on AWS to quickly build an end-to-end data governance for Kafka topic. The example provision resources to illustrate a scenario where a Lambda based Kafka producer publish a Kafka topic into DataZone to allow for discovery via its business catalog. The producer is using DSF on AWS to create the custom asset type in DataZone for MSK topics. DSF also provides a custom DataZone data source that automatically creates the asset in DataZone based on the producer Glue schema Registry. After the asset is created, a consumer can browse the DataZone catalog and request access to the MSK topic. When approved by the producer team, DSF custom authorizer automatically grants the consumer access to the MSK topic from a Flink application running on Amazon Managed Streaming for Apache Flink. Both producer and consumer are registering lineage information into DataZone.
+In this example, we will be using DSF on AWS to quickly build an end-to-end data governance solution for Kafka topics. The example provisions resources to illustrate a scenario where a Lambda based Kafka producer publishes a Kafka topic into Amazon DataZone to allow for discovery via its business catalog. The producer is using DSF on AWS to create the custom asset type in DataZone for MSK topics. DSF also provides a custom DataZone data source that automatically creates the asset in DataZone based on the producer's Glue schema Registry. After the asset is created, a consumer can browse the DataZone catalog and request access to the MSK topic. When approved by the producer team, DSF custom authorizer automatically grants the consumer access to the MSK topic from a Flink application running on Amazon Managed Streaming for Apache Flink. Both producer and consumer are registering lineage information into DataZone.
 
 The AWS CDK application using the DSF on AWS contains a single stack which provisions the following DSF constructs:
    * [`DataZoneMskAssetType`](../constructs/library/04-Governance/03-datazone-msk-asset-type.mdx)