Enviar job hadoop fs

Envia um job do Hadoop FS para um cluster do Dataproc.

Exemplo de código

Java

Antes de testar este exemplo, siga as instruções de configuração do Java na Guia de início rápido do Dataproc usando bibliotecas de cliente. Para mais informações, consulte a documentação de referência da API Java do Dataproc.

Para autenticar no Dataproc, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.

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()));
    }
  }
}

A seguir

Para pesquisar e filtrar exemplos de código de outros produtos do Google Cloud, consulte a pesquisa de exemplos de código do Google Cloud.