org.apache.hadoop.mapred.lib.db.DBInputFormat Java Examples

The following examples show how to use org.apache.hadoop.mapred.lib.db.DBInputFormat. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: DBImportMapReduce.java    From hiped2 with Apache License 2.0 4 votes vote down vote up
/**
 * The MapReduce driver - setup and launch the job.
 *
 * @param args the command-line arguments
 * @return the process exit code
 * @throws Exception if something goes wrong
 */
public int run(final String[] args) throws Exception {

  Cli cli = Cli.builder().setArgs(args).addOptions(CliCommonOpts.OutputFileOption.values()).build();
  int result = cli.runCmd();

  if (result != 0) {
    return result;
  }

  Path output = new Path(cli.getArgValueAsString(CliCommonOpts.OutputFileOption.OUTPUT));

  Configuration conf = super.getConf();

  DBConfiguration.configureDB(conf, "com.mysql.jdbc.Driver",
      "jdbc:mysql://localhost/sqoop_test" +
          "?user=hip_sqoop_user&password=password");

  JobConf job = new JobConf(conf);
  job.setJarByClass(DBImportMapReduce.class);

  job.setInputFormat(DBInputFormat.class);
  job.setOutputFormat(AvroOutputFormat.class);
  AvroJob.setOutputSchema(job, Stock.SCHEMA$);
  job.set(AvroJob.OUTPUT_CODEC, SnappyCodec.class.getName());

  job.setMapperClass(Map.class);

  job.setNumMapTasks(4);
  job.setNumReduceTasks(0);

  job.setMapOutputKeyClass(AvroWrapper.class);
  job.setMapOutputValueClass(NullWritable.class);

  job.setOutputKeyClass(AvroWrapper.class);
  job.setOutputValueClass(NullWritable.class);

  FileOutputFormat.setOutputPath(job, output);

  DBInputFormat.setInput(
      job,
      StockDbWritable.class,
      "select * from stocks",
      "SELECT COUNT(id) FROM stocks");

  RunningJob runningJob = JobClient.runJob(job);

  return runningJob.isSuccessful() ? 0 : 1;
}
 
Example #2
Source File: DBCountPageView.java    From RDFS with Apache License 2.0 4 votes vote down vote up
@Override
//Usage DBCountPageView [driverClass dburl]
public int run(String[] args) throws Exception {
  
  String driverClassName = DRIVER_CLASS;
  String url = DB_URL;
  
  if(args.length > 1) {
    driverClassName = args[0];
    url = args[1];
  }
  
  initialize(driverClassName, url);

  JobConf job = new JobConf(getConf(), DBCountPageView.class);
      
  job.setJobName("Count Pageviews of URLs");

  job.setMapperClass(PageviewMapper.class);
  job.setCombinerClass(LongSumReducer.class);
  job.setReducerClass(PageviewReducer.class);

  DBConfiguration.configureDB(job, driverClassName, url);
  
  DBInputFormat.setInput(job, AccessRecord.class, "Access"
      , null, "url", AccessFieldNames);

  DBOutputFormat.setOutput(job, "Pageview", PageviewFieldNames);
  
  job.setMapOutputKeyClass(Text.class);
  job.setMapOutputValueClass(LongWritable.class);

  job.setOutputKeyClass(PageviewRecord.class);
  job.setOutputValueClass(NullWritable.class);

  try {
    JobClient.runJob(job);
    
    boolean correct = verify();
    if(!correct) {
      throw new RuntimeException("Evaluation was not correct!");
    }
  } finally {
    shutdown();    
  }
  return 0;
}
 
Example #3
Source File: DBCountPageView.java    From hadoop-book with Apache License 2.0 4 votes vote down vote up
@Override
//Usage DBCountPageView [driverClass dburl]
public int run(String[] args) throws Exception {

    String driverClassName = DRIVER_CLASS;
    String url = DB_URL;

    if (args.length > 1) {
        driverClassName = args[0];
        url = args[1];
    }

    initialize(driverClassName, url);

    JobConf job = new JobConf(getConf(), DBCountPageView.class);

    job.setJobName("Count Pageviews of URLs");

    job.setMapperClass(PageviewMapper.class);
    job.setCombinerClass(LongSumReducer.class);
    job.setReducerClass(PageviewReducer.class);

    DBConfiguration.configureDB(job, driverClassName, url);

    DBInputFormat.setInput(job, AccessRecord.class, "Access", null, "url", AccessFieldNames);

    DBOutputFormat.setOutput(job, "Pageview", PageviewFieldNames);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(LongWritable.class);

    job.setOutputKeyClass(PageviewRecord.class);
    job.setOutputValueClass(NullWritable.class);

    try {
        JobClient.runJob(job);

        boolean correct = verify();
        if (!correct) {
            throw new RuntimeException("Evaluation was not correct!");
        }
    } finally {
        shutdown();
    }
    return 0;
}
 
Example #4
Source File: DBCountPageView.java    From hadoop-gpu with Apache License 2.0 4 votes vote down vote up
@Override
//Usage DBCountPageView [driverClass dburl]
public int run(String[] args) throws Exception {
  
  String driverClassName = DRIVER_CLASS;
  String url = DB_URL;
  
  if(args.length > 1) {
    driverClassName = args[0];
    url = args[1];
  }
  
  initialize(driverClassName, url);

  JobConf job = new JobConf(getConf(), DBCountPageView.class);
      
  job.setJobName("Count Pageviews of URLs");

  job.setMapperClass(PageviewMapper.class);
  job.setCombinerClass(LongSumReducer.class);
  job.setReducerClass(PageviewReducer.class);

  DBConfiguration.configureDB(job, driverClassName, url);
  
  DBInputFormat.setInput(job, AccessRecord.class, "Access"
      , null, "url", AccessFieldNames);

  DBOutputFormat.setOutput(job, "Pageview", PageviewFieldNames);
  
  job.setMapOutputKeyClass(Text.class);
  job.setMapOutputValueClass(LongWritable.class);

  job.setOutputKeyClass(PageviewRecord.class);
  job.setOutputValueClass(NullWritable.class);

  try {
    JobClient.runJob(job);
    
    boolean correct = verify();
    if(!correct) {
      throw new RuntimeException("Evaluation was not correct!");
    }
  } finally {
    shutdown();    
  }
  return 0;
}