提交 hadoop fs 作业

将 Hadoop FS 作业提交到 Dataproc 集群。

代码示例

Java

试用此示例之前，请按照 Java Managed Service for Apache Spark 快速入门中的设置说明进行操作。如需了解详情，请参阅 Managed Service for Apache Spark Java API 参考文档。

如需向 Managed Service for Apache Spark 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅 为本地开发环境设置身份验证。

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.dataproc.v1.HadoopJob;
import com.google.cloud.dataproc.v1.Job;
import com.google.cloud.dataproc.v1.JobControllerClient;
import com.google.cloud.dataproc.v1.JobControllerSettings;
import com.google.cloud.dataproc.v1.JobMetadata;
import com.google.cloud.dataproc.v1.JobPlacement;
import com.google.cloud.storage.Blob;
import com.google.cloud.storage.Storage;
import com.google.cloud.storage.StorageOptions;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.concurrent.ExecutionException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class SubmitHadoopFsJob {

  public static ArrayList<String> stringToList(String s) {
    return new ArrayList<>(Arrays.asList(s.split(" ")));
  }

  public static void submitHadoopFsJob() throws IOException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String region = "your-project-region";
    String clusterName = "your-cluster-name";
    String hadoopFsQuery = "your-hadoop-fs-query";
    submitHadoopFsJob(projectId, region, clusterName, hadoopFsQuery);
  }

  public static void submitHadoopFsJob(
      String projectId, String region, String clusterName, String hadoopFsQuery)
      throws IOException, InterruptedException {
    String myEndpoint = String.format("%s-dataproc.googleapis.com:443", region);

    // Configure the settings for the job controller client.
    JobControllerSettings jobControllerSettings =
        JobControllerSettings.newBuilder().setEndpoint(myEndpoint).build();

    // Create a job controller client with the configured settings. Using a try-with-resources
    // closes the client,
    // but this can also be done manually with the .close() method.
    try (JobControllerClient jobControllerClient =
        JobControllerClient.create(jobControllerSettings)) {

      // Configure cluster placement for the job.
      JobPlacement jobPlacement = JobPlacement.newBuilder().setClusterName(clusterName).build();

      // Configure Hadoop job settings. The HadoopFS query is set here.
      HadoopJob hadoopJob =
          HadoopJob.newBuilder()
              .setMainClass("org.apache.hadoop.fs.FsShell")
              .addAllArgs(stringToList(hadoopFsQuery))
              .build();

      Job job = Job.newBuilder().setPlacement(jobPlacement).setHadoopJob(hadoopJob).build();

      // Submit an asynchronous request to execute the job.
      OperationFuture<Job, JobMetadata> submitJobAsOperationAsyncRequest =
          jobControllerClient.submitJobAsOperationAsync(projectId, region, job);

      Job response = submitJobAsOperationAsyncRequest.get();

      // Print output from Google Cloud Storage.
      Matcher matches =
          Pattern.compile("gs://(.*?)/(.*)").matcher(response.getDriverOutputResourceUri());
      matches.matches();

      Storage storage = StorageOptions.getDefaultInstance().getService();
      Blob blob = storage.get(matches.group(1), String.format("%s.000000000", matches.group(2)));

      System.out.println(
          String.format("Job finished successfully: %s", new String(blob.getContent())));

    } catch (ExecutionException e) {
      // If the job does not complete successfully, print the error message.
      System.err.println(String.format("submitHadoopFSJob: %s ", e.getMessage()));
    }
  }
}

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例，请参阅Google Cloud 示例浏览器。