Transfiere objetos o archivos específicos con un manifiesto

import (
	"context"
	"fmt"
	"io"

	storagetransfer "cloud.google.com/go/storagetransfer/apiv1"
	"cloud.google.com/go/storagetransfer/apiv1/storagetransferpb"
)

func transferUsingManifest(w io.Writer, projectID string, sourceAgentPoolName string, rootDirectory string, gcsSinkBucket string, manifestBucket string, manifestObjectName string) (*storagetransferpb.TransferJob, error) {
	// Your project id
	// projectId := "myproject-id"

	// The agent pool associated with the POSIX data source. If not provided, defaults to the default agent
	// sourceAgentPoolName := "projects/my-project/agentPools/transfer_service_default"

	// The root directory path on the source filesystem
	// rootDirectory := "/directory/to/transfer/source"

	// The ID of the GCS bucket to transfer data to
	// gcsSinkBucket := "my-sink-bucket"

	// The ID of the GCS bucket that contains the manifest file
	// manifestBucket := "my-manifest-bucket"

	// The name of the manifest file in manifestBucket that specifies which objects to transfer
	// manifestObjectName := "path/to/manifest.csv"

	ctx := context.Background()
	client, err := storagetransfer.NewClient(ctx)
	if err != nil {
		return nil, fmt.Errorf("storagetransfer.NewClient: %w", err)
	}
	defer client.Close()

	manifestLocation := "gs://" + manifestBucket + "/" + manifestObjectName
	req := &storagetransferpb.CreateTransferJobRequest{
		TransferJob: &storagetransferpb.TransferJob{
			ProjectId: projectID,
			TransferSpec: &storagetransferpb.TransferSpec{
				SourceAgentPoolName: sourceAgentPoolName,
				DataSource: &storagetransferpb.TransferSpec_PosixDataSource{
					PosixDataSource: &storagetransferpb.PosixFilesystem{RootDirectory: rootDirectory},
				},
				DataSink: &storagetransferpb.TransferSpec_GcsDataSink{
					GcsDataSink: &storagetransferpb.GcsData{BucketName: gcsSinkBucket},
				},
				TransferManifest: &storagetransferpb.TransferManifest{Location: manifestLocation},
			},
			Status: storagetransferpb.TransferJob_ENABLED,
		},
	}

	resp, err := client.CreateTransferJob(ctx, req)
	if err != nil {
		return nil, fmt.Errorf("failed to create transfer job: %w", err)
	}
	if _, err = client.RunTransferJob(ctx, &storagetransferpb.RunTransferJobRequest{
		ProjectId: projectID,
		JobName:   resp.Name,
	}); err != nil {
		return nil, fmt.Errorf("failed to run transfer job: %w", err)
	}
	fmt.Fprintf(w, "Created and ran transfer job from %v to %v using manifest file %v with name %v", rootDirectory, gcsSinkBucket, manifestLocation, resp.Name)
	return resp, nil
}

import com.google.storagetransfer.v1.proto.StorageTransferServiceClient;
import com.google.storagetransfer.v1.proto.TransferProto;
import com.google.storagetransfer.v1.proto.TransferTypes.GcsData;
import com.google.storagetransfer.v1.proto.TransferTypes.PosixFilesystem;
import com.google.storagetransfer.v1.proto.TransferTypes.TransferJob;
import com.google.storagetransfer.v1.proto.TransferTypes.TransferManifest;
import com.google.storagetransfer.v1.proto.TransferTypes.TransferSpec;
import java.io.IOException;

public class TransferUsingManifest {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.

    // Your project id
    String projectId = "my-project-id";

    // The agent pool associated with the POSIX data source. If not provided, defaults to the
    // default agent
    String sourceAgentPoolName = "projects/my-project-id/agentPools/transfer_service_default";

    // The root directory path on the source filesystem
    String rootDirectory = "/directory/to/transfer/source";

    // The ID of the GCS bucket to transfer data to
    String gcsSinkBucket = "my-sink-bucket";

    // The ID of the GCS bucket which has your manifest file
    String manifestBucket = "my-bucket";

    // The ID of the object in manifestBucket that specifies which files to transfer
    String manifestObjectName = "path/to/manifest.csv";

    transferUsingManifest(
        projectId,
        sourceAgentPoolName,
        rootDirectory,
        gcsSinkBucket,
        manifestBucket,
        manifestObjectName);
  }

  public static void transferUsingManifest(
      String projectId,
      String sourceAgentPoolName,
      String rootDirectory,
      String gcsSinkBucket,
      String manifestBucket,
      String manifestObjectName)
      throws IOException {
    String manifestLocation = "gs://" + manifestBucket + "/" + manifestObjectName;
    TransferJob transferJob =
        TransferJob.newBuilder()
            .setProjectId(projectId)
            .setTransferSpec(
                TransferSpec.newBuilder()
                    .setSourceAgentPoolName(sourceAgentPoolName)
                    .setPosixDataSource(
                        PosixFilesystem.newBuilder().setRootDirectory(rootDirectory).build())
                    .setGcsDataSink((GcsData.newBuilder().setBucketName(gcsSinkBucket)).build())
                    .setTransferManifest(
                        TransferManifest.newBuilder().setLocation(manifestLocation).build()))
            .setStatus(TransferJob.Status.ENABLED)
            .build();

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources,
    // or use "try-with-close" statement to do this automatically.
    try (StorageTransferServiceClient storageTransfer = StorageTransferServiceClient.create()) {

      // Create the transfer job
      TransferJob response =
          storageTransfer.createTransferJob(
              TransferProto.CreateTransferJobRequest.newBuilder()
                  .setTransferJob(transferJob)
                  .build());

      System.out.println(
          "Created and ran a transfer job from "
              + rootDirectory
              + " to "
              + gcsSinkBucket
              + " using "
              + "manifest file "
              + manifestLocation
              + " with name "
              + response.getName());
    }
  }
}

// Imports the Google Cloud client library
const {
  StorageTransferServiceClient,
} = require('@google-cloud/storage-transfer');

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// Your project id
// const projectId = 'my-project'

// The agent pool associated with the POSIX data source. Defaults to the default agent
// const sourceAgentPoolName = 'projects/my-project/agentPools/transfer_service_default'

// The root directory path on the source filesystem
// const rootDirectory = '/directory/to/transfer/source'

// The ID of the GCS bucket to transfer data to
// const gcsSinkBucket = 'my-sink-bucket'

// Transfer manifest location. Must be a `gs:` URL
// const manifestLocation = 'gs://my-bucket/sample_manifest.csv'

// Creates a client
const client = new StorageTransferServiceClient();

/**
 * Creates a request to transfer from the local file system to the sink bucket
 */
async function transferViaManifest() {
  const createRequest = {
    transferJob: {
      projectId,
      transferSpec: {
        sourceAgentPoolName,
        posixDataSource: {
          rootDirectory,
        },
        gcsDataSink: {bucketName: gcsSinkBucket},
        transferManifest: {
          location: manifestLocation,
        },
      },
      status: 'ENABLED',
    },
  };

  // Runs the request and creates the job
  const [transferJob] = await client.createTransferJob(createRequest);

  const runRequest = {
    jobName: transferJob.name,
    projectId: projectId,
  };

  await client.runTransferJob(runRequest);

  console.log(
    `Created and ran a transfer job from '${rootDirectory}' to '${gcsSinkBucket}' using manifest \`${manifestLocation}\` with name ${transferJob.name}`
  );
}

transferViaManifest();

from google.cloud import storage_transfer


def create_transfer_with_manifest(
    project_id: str,
    description: str,
    source_agent_pool_name: str,
    root_directory: str,
    sink_bucket: str,
    manifest_location: str,
):
    """Create a transfer from a POSIX file system to a GCS bucket using
    a manifest file."""

    client = storage_transfer.StorageTransferServiceClient()

    # The ID of the Google Cloud Platform Project that owns the job
    # project_id = 'my-project-id'

    # A useful description for your transfer job
    # description = 'My transfer job'

    # The agent pool associated with the POSIX data source.
    # Defaults to 'projects/{project_id}/agentPools/transfer_service_default'
    # source_agent_pool_name = 'projects/my-project/agentPools/my-agent'

    # The root directory path on the source filesystem
    # root_directory = '/directory/to/transfer/source'

    # Google Cloud Storage destination bucket name
    # sink_bucket = 'my-gcs-destination-bucket'

    # Transfer manifest location. Must be a `gs:` URL
    # manifest_location = 'gs://my-bucket/sample_manifest.csv'

    transfer_job_request = storage_transfer.CreateTransferJobRequest(
        {
            "transfer_job": {
                "project_id": project_id,
                "description": description,
                "status": storage_transfer.TransferJob.Status.ENABLED,
                "transfer_spec": {
                    "source_agent_pool_name": source_agent_pool_name,
                    "posix_data_source": {
                        "root_directory": root_directory,
                    },
                    "gcs_data_sink": {
                        "bucket_name": sink_bucket,
                    },
                    "transfer_manifest": {"location": manifest_location},
                },
            }
        }
    )

    result = client.create_transfer_job(transfer_job_request)
    print(f"Created transferJob: {result.name}")