Add Managed Kafka Connect Connectors Examples

managedkafka/snippets/connect/connectors/connectors_test.py

@@ -0,0 +1,195 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from unittest import mock
+from unittest.mock import MagicMock
+
+from google.api_core.operation import Operation
+from google.cloud import managedkafka_v1
+import pytest
+
+import create_bigquery_sink_connector
+import create_cloud_storage_sink_connector
+import create_mirrormaker_source_connector
+import create_pubsub_sink_connector
+import create_pubsub_source_connector
+
+PROJECT_ID = "test-project-id"
+REGION = "us-central1"
+CONNECT_CLUSTER_ID = "test-connect-cluster-id"
+
+
+@mock.patch(
+    "google.cloud.managedkafka_v1.services.managed_kafka_connect.ManagedKafkaConnectClient.create_connector"
+)
+def test_create_mirrormaker2_connector(
+    mock_method: MagicMock,
+    capsys: pytest.CaptureFixture[str],
+) -> None:
+    connector_id = "MM2_CONNECTOR_ID"
+    operation = mock.MagicMock(spec=Operation)
+    connector = managedkafka_v1.types.Connector()
+    connector.name = connector_id
+    operation.result = mock.MagicMock(return_value=connector)
+    mock_method.return_value = operation
+
+    create_mirrormaker_source_connector.create_mirrormaker_source_connector(
+        PROJECT_ID,
+        REGION,
+        CONNECT_CLUSTER_ID,
+        "3",
+        connector_id,
+        "GMK_TOPIC_NAME",
+        "source",
+        "target",
+        "GMK_SOURCE_CLUSTER_DNS",
+        "GMK_TARGET_CLUSTER_DNS",
+    )
+
+    out, _ = capsys.readouterr()
+    assert "Created Connector" in out
+    assert connector_id in out
+    mock_method.assert_called_once()
+
+
+@mock.patch(
+    "google.cloud.managedkafka_v1.services.managed_kafka_connect.ManagedKafkaConnectClient.create_connector"
+)
+def test_create_pubsub_source_connector(
+    mock_method: MagicMock,
+    capsys: pytest.CaptureFixture[str],
+) -> None:
+    connector_id = "CPS_SOURCE_CONNECTOR_ID"
+    operation = mock.MagicMock(spec=Operation)
+    connector = managedkafka_v1.types.Connector()
+    connector.name = connector_id
+    operation.result = mock.MagicMock(return_value=connector)
+    mock_method.return_value = operation
+
+    create_pubsub_source_connector.create_pubsub_source_connector(
+        PROJECT_ID,
+        REGION,
+        CONNECT_CLUSTER_ID,
+        connector_id,
+        "GMK_TOPIC_ID",
+        "CPS_SUBSCRIPTION_ID",
+        "GCP_PROJECT_ID",
+        "3",
+        "org.apache.kafka.connect.converters.ByteArrayConverter",
+        "org.apache.kafka.connect.storage.StringConverter",
+    )
+
+    out, _ = capsys.readouterr()
+    assert "Created Connector" in out
+    assert connector_id in out
+    mock_method.assert_called_once()
+
+
+@mock.patch(
+    "google.cloud.managedkafka_v1.services.managed_kafka_connect.ManagedKafkaConnectClient.create_connector"
+)
+def test_create_pubsub_sink_connector(
+    mock_method: MagicMock,
+    capsys: pytest.CaptureFixture[str],
+) -> None:
+    connector_id = "CPS_SINK_CONNECTOR_ID"
+    operation = mock.MagicMock(spec=Operation)
+    connector = managedkafka_v1.types.Connector()
+    connector.name = connector_id
+    operation.result = mock.MagicMock(return_value=connector)
+    mock_method.return_value = operation
+
+    create_pubsub_sink_connector.create_pubsub_sink_connector(
+        PROJECT_ID,
+        REGION,
+        CONNECT_CLUSTER_ID,
+        connector_id,
+        "GMK_TOPIC_ID",
+        "org.apache.kafka.connect.storage.StringConverter",
+        "org.apache.kafka.connect.storage.StringConverter",
+        "CPS_TOPIC_ID",
+        "GCP_PROJECT_ID",
+        "3",
+    )
+
+    out, _ = capsys.readouterr()
+    assert "Created Connector" in out
+    assert connector_id in out
+    mock_method.assert_called_once()
+
+
+@mock.patch(
+    "google.cloud.managedkafka_v1.services.managed_kafka_connect.ManagedKafkaConnectClient.create_connector"
+)
+def test_create_cloud_storage_sink_connector(
+    mock_method: MagicMock,
+    capsys: pytest.CaptureFixture[str],
+) -> None:
+    connector_id = "GCS_SINK_CONNECTOR_ID"
+    operation = mock.MagicMock(spec=Operation)
+    connector = managedkafka_v1.types.Connector()
+    connector.name = connector_id
+    operation.result = mock.MagicMock(return_value=connector)
+    mock_method.return_value = operation
+
+    create_cloud_storage_sink_connector.create_cloud_storage_sink_connector(
+        PROJECT_ID,
+        REGION,
+        CONNECT_CLUSTER_ID,
+        connector_id,
+        "GMK_TOPIC_ID",
+        "GCS_BUCKET_NAME",
+        "3",
+        "json",
+        "org.apache.kafka.connect.json.JsonConverter",
+        "false",
+        "org.apache.kafka.connect.storage.StringConverter",
+    )
+
+    out, _ = capsys.readouterr()
+    assert "Created Connector" in out
+    assert connector_id
+
+
+@mock.patch(
+    "google.cloud.managedkafka_v1.services.managed_kafka_connect.ManagedKafkaConnectClient.create_connector"
+)
+def test_create_bigquery_sink_connector(
+    mock_method: MagicMock,
+    capsys: pytest.CaptureFixture[str],
+) -> None:
+    connector_id = "BQ_SINK_CONNECTOR_ID"
+    operation = mock.MagicMock(spec=Operation)
+    connector = managedkafka_v1.types.Connector()
+    connector.name = connector_id
+    operation.result = mock.MagicMock(return_value=connector)
+    mock_method.return_value = operation
+
+    create_bigquery_sink_connector.create_bigquery_sink_connector(
+        PROJECT_ID,
+        REGION,
+        CONNECT_CLUSTER_ID,
+        connector_id,
+        "GMK_TOPIC_ID",
+        "3",
+        "org.apache.kafka.connect.storage.StringConverter",
+        "org.apache.kafka.connect.json.JsonConverter",
+        "false",
+        "BQ_DATASET_ID",
+    )
+
+    out, _ = capsys.readouterr()
+    assert "Created Connector" in out
+    assert connector_id in out
+    mock_method.assert_called_once()

managedkafka/snippets/connect/connectors/create_bigquery_sink_connector.py

@@ -0,0 +1,97 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+def create_bigquery_sink_connector(
+    project_id: str,
+    region: str,
+    connect_cluster_id: str,
+    connector_id: str,
+    topics: str,
+    tasks_max: str,
+    key_converter: str,
+    value_converter: str,
+    value_converter_schemas_enable: str,
+    default_dataset: str,
+) -> None:
+    """
+    Create a BigQuery Sink connector.
+
+    Args:
+        project_id: Google Cloud project ID.
+        region: Cloud region.
+        connect_cluster_id: ID of the Kafka Connect cluster.
+        connector_id: Name of the connector.
+        topics: Kafka topics to read from.
+        tasks_max: Maximum number of tasks.
+        key_converter: Key converter class.
+        value_converter: Value converter class.
+        value_converter_schemas_enable: Enable schemas for value converter.
+        default_dataset: BigQuery dataset ID.
+
+    Raises:
+        This method will raise the GoogleAPICallError exception if the operation errors or
+        the timeout before the operation completes is reached.
+    """
+    # TODO(developer): Update with your config values. Here is a sample configuration:
+    # project_id = "my-project-id"
+    # region = "us-central1"
+    # connect_cluster_id = "my-connect-cluster"
+    # connector_id = "BQ_SINK_CONNECTOR_ID"
+    # topics = "GMK_TOPIC_ID"
+    # tasks_max = "3"
+    # key_converter = "org.apache.kafka.connect.storage.StringConverter"
+    # value_converter = "org.apache.kafka.connect.json.JsonConverter"
+    # value_converter_schemas_enable = "false"
+    # default_dataset = "BQ_DATASET_ID"
+
+    # [START managedkafka_create_bigquery_sink_connector]
+    from google.api_core.exceptions import GoogleAPICallError
+    from google.cloud.managedkafka_v1.services.managed_kafka_connect import (
+        ManagedKafkaConnectClient,
+    )
+    from google.cloud.managedkafka_v1.types import Connector, CreateConnectorRequest
+
+    connect_client = ManagedKafkaConnectClient()
+    parent = connect_client.connect_cluster_path(project_id, region, connect_cluster_id)
+
+    configs = {
+        "name": connector_id,
+        "project": project_id,
+        "topics": topics,
+        "tasks.max": tasks_max,
+        "connector.class": "com.wepay.kafka.connect.bigquery.BigQuerySinkConnector",
+        "key.converter": key_converter,
+        "value.converter": value_converter,
+        "value.converter.schemas.enable": value_converter_schemas_enable,
+        "defaultDataset": default_dataset,
+    }
+
+    connector = Connector()
+    connector.name = connector_id
+    connector.configs = configs
+
+    request = CreateConnectorRequest(
+        parent=parent,
+        connector_id=connector_id,
+        connector=connector,
+    )
+
+    try:
+        operation = connect_client.create_connector(request=request)
+        print(f"Waiting for operation {operation.operation.name} to complete...")
+        response = operation.result()
+        print("Created Connector:", response)
+    except GoogleAPICallError as e:
+        print(f"The operation failed with error: {e}")
+    # [END managedkafka_create_bigquery_sink_connector]

managedkafka/snippets/connect/connectors/create_cloud_storage_sink_connector.py

@@ -0,0 +1,101 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+def create_cloud_storage_sink_connector(
+    project_id: str,
+    region: str,
+    connect_cluster_id: str,
+    connector_id: str,
+    topics: str,
+    gcs_bucket_name: str,
+    tasks_max: str,
+    format_output_type: str,
+    value_converter: str,
+    value_converter_schemas_enable: str,
+    key_converter: str,
+) -> None:
+    """
+    Create a Cloud Storage Sink connector.
+
+    Args:
+        project_id: Google Cloud project ID.
+        region: Cloud region.
+        connect_cluster_id: ID of the Kafka Connect cluster.
+        connector_id: Name of the connector.
+        topics: Kafka topics to read from.
+        gcs_bucket_name: Google Cloud Storage bucket name.
+        tasks_max: Maximum number of tasks.
+        format_output_type: Output format type.
+        value_converter: Value converter class.
+        value_converter_schemas_enable: Enable schemas for value converter.
+        key_converter: Key converter class.
+
+    Raises:
+        This method will raise the GoogleAPICallError exception if the operation errors or
+        the timeout before the operation completes is reached.
+    """
+    # TODO(developer): Update with your config values. Here is a sample configuration:
+    # project_id = "my-project-id"
+    # region = "us-central1"
+    # connect_cluster_id = "my-connect-cluster"
+    # connector_id = "GCS_SINK_CONNECTOR_ID"
+    # topics = "GMK_TOPIC_ID"
+    # gcs_bucket_name = "GCS_BUCKET_NAME"
+    # tasks_max = "3"
+    # format_output_type = "json"
+    # value_converter = "org.apache.kafka.connect.json.JsonConverter"
+    # value_converter_schemas_enable = "false"
+    # key_converter = "org.apache.kafka.connect.storage.StringConverter"
+
+    # [START managedkafka_create_cloud_storage_sink_connector]
+    from google.api_core.exceptions import GoogleAPICallError
+    from google.cloud.managedkafka_v1.services.managed_kafka_connect import (
+        ManagedKafkaConnectClient,
+    )
+    from google.cloud.managedkafka_v1.types import Connector, CreateConnectorRequest
+
+    connect_client = ManagedKafkaConnectClient()
+    parent = connect_client.connect_cluster_path(project_id, region, connect_cluster_id)
+
+    configs = {
+        "connector.class": "io.aiven.kafka.connect.gcs.GcsSinkConnector",
+        "tasks.max": tasks_max,
+        "topics": topics,
+        "gcs.bucket.name": gcs_bucket_name,
+        "gcs.credentials.default": "true",
+        "format.output.type": format_output_type,
+        "name": connector_id,
+        "value.converter": value_converter,
+        "value.converter.schemas.enable": value_converter_schemas_enable,
+        "key.converter": key_converter,
+    }
+
+    connector = Connector()
+    connector.name = connector_id
+    connector.configs = configs
+
+    request = CreateConnectorRequest(
+        parent=parent,
+        connector_id=connector_id,
+        connector=connector,
+    )
+
+    try:
+        operation = connect_client.create_connector(request=request)
+        print(f"Waiting for operation {operation.operation.name} to complete...")
+        response = operation.result()
+        print("Created Connector:", response)
+    except GoogleAPICallError as e:
+        print(f"The operation failed with error: {e}")
+    # [END managedkafka_create_cloud_storage_sink_connector]