Example usage for org.apache.hadoop.mapreduce Job setOutputKeyClass

List of usage examples for org.apache.hadoop.mapreduce Job setOutputKeyClass

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapreduce.*
  5. Job
  6. setOutputKeyClass

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce Job setOutputKeyClass.

Prototype

public void setOutputKeyClass(Class<?> theClass) throws IllegalStateException

Source Link

Document

Set the key class for the job output data.

Usage

From source file:com.howbuy.hadoop.mr.online.SecondarySort.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: secondarysrot <in> <out>");
        System.exit(2);/* ww w .  j  a  v a  2  s  . com*/
    }
    Job job = new Job(conf, "secondary sort");
    job.setJarByClass(SecondarySort.class);
    job.setMapperClass(MapClass.class);
    job.setReducerClass(Reduce.class);

    // group and partition by the first int in the pair
    job.setPartitionerClass(FirstPartitioner.class);
    job.setGroupingComparatorClass(FirstGroupingComparator.class);

    // the map output is IntPair, IntWritable
    job.setMapOutputKeyClass(IntPair.class);
    job.setMapOutputValueClass(IntWritable.class);

    // the reduce output is Text, IntWritable
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    job.setInputFormatClass(TextInputFormat.class);
    // job.setOutputFormatClass(SequenceFileOutputFormat.class);

    job.setNumReduceTasks(3);

    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:com.huihui.mr.WordCount.java

License:Apache License

public static void main(String[] args) throws Exception {

    /*HadoopJava.util.Properties??Apache Jakarta Commons Configuration??
     * ????API?org.apache.hadoop.conf.Configuration???
     */// w  w  w  . j av a 2  s  .c o  m
    Configuration conf = new Configuration();
    /*
     * ?HadoopGenericOptionsParser
    ???
    -D mapreduce.job.queuename  ??getRemainingArgs()?
    ?"xrli/STJoin_in","xrli/STJoin_out"?otherArgs
            
    ? fs jt libjars files archives D tokenCacheFile
     */
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);
    }
    conf.set("fs.defaultFS", "hdfs://localhost:9000");
    //
    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);

    //??? 
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    //Path    ???URI?Path???Path
    String input = "hdfs://localhost:9000/input/";
    String output = "hdfs://localhost:9000/user/hdfs/log_kpi/browser1";
    FileInputFormat.addInputPath(job, new Path(input));
    FileOutputFormat.setOutputPath(job, new Path(output));
    //????
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:com.hzy.test.WordCount.java

License:Apache License

public static void main(String[] args) throws Exception {
    //        String input = "hdfs://192.168.1.118:9000/user/hdfs/log_kpi/";
    //        String output = "hdfs://192.168.1.118:9000/user/hdfs/log_kpi/wc/";
    String input = "/tmp/data.txt";
    // String input = args[0];
    String output = "/tmp/t1";

    // String output = args[1];

    Configuration conf = HdfsDAO.config();

    //        conf.set("mapreduce.framework.name", "yarn");
    ////        conf.set("hbase.zookeeper.quorum", "hadoop01:2181");
    //        conf.set("fs.default.name", "hdfs://hadoop01:9000");
    //        conf.set("yarn.resourcemanager.resource-tracker.address", "hadoop01:8031");
    //        conf.set("yarn.resourcemanager.address", "hadoop01:8032");
    //        conf.set("yarn.resourcemanager.scheduler.address", "hadoop01:8030");
    //        conf.set("yarn.resourcemanager.admin.address", "hadoop01:8033");
    //        conf.set("mapreduce.jobhistory.address", "hadoop01:10020");
    //        conf.set("mapreduce.jobhistory.webapp.address", "hadoop01:19888");

    //        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    //        if (otherArgs.length < 2) {
    //            System.err.println("Usage: wordcount <in> [<in>...] <out>");
    //            System.exit(2);
    //        }/* w  w  w.ja v  a  2s . c o m*/
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    //        for (int i = 0; i < otherArgs.length - 1; ++i) {
    FileInputFormat.addInputPath(job, new Path(input));
    //        }
    FileOutputFormat.setOutputPath(job, new Path(output));

    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:com.ifeng.hadoop.thinker.LogDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }//from w  ww .j  av a2 s.  c  o m

    Job job = Job.getInstance(super.getConf());
    job.setJarByClass(getClass());

    FileUtil.fullyDelete(new File(args[1]));

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(LogMapper.class);
    job.setReducerClass(LogReducer.class);
    job.setCombinerClass(LogReducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.ifeng.hadoop.thinker.LogLocalDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }//  w  w w.jav a2  s .  com

    Job job = Job.getInstance(super.getConf());
    job.setJarByClass(getClass());

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(LogMapper.class);
    job.setReducerClass(LogReducer.class);
    job.setCombinerClass(LogReducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.ifeng.ipserver.IPServerLogParseDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    Job job = Job.getInstance(super.getConf());
    job.setJarByClass(getClass());/*from w  ww  . j  a  v  a  2 s  . c om*/

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(IPServerLogParseMapper.class);
    job.setReducerClass(IPServerLogParseReducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.ifeng.logparser.NginxLogDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }// w ww  .j  a v a2 s  .  c  o m

    Job job = Job.getInstance(super.getConf());
    FileInputFormat.setInputDirRecursive(job, true);

    //FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    FileInputFormat.addInputPaths(job, args[0]);

    job.setMapperClass(NginxLogMapper.class);
    job.setReducerClass(NginxLogReducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.ifeng.logparser.NginxLogDriver2.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }//w ww  .j  a  v a 2s .com

    log.info("Input: {} , Outpu: {}", args[0], args[1]);

    Job job = Job.getInstance(super.getConf());
    //FileInputFormat.setInputDirRecursive(job, true);

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    //FileInputFormat.addInputPaths(job, args[0]);

    job.setMapperClass(NginxLogMapper.class);
    job.setReducerClass(NginxLogReducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.ifeng.sorter.LogSortDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }//from   w w w.  j a  va2 s .  c  o m

    log.info("Input: {} , Outpu: {}", args[0], args[1]);

    Job job = Job.getInstance(super.getConf());

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(LogSortMapper.class);
    job.setReducerClass(LogSortReducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    return job.waitForCompletion(true) ? 0 : 1;

}

From source file:com.ifeng.vdn.iparea.parser.IPAreaDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    Job job = Job.getInstance(getConf());

    job.setJarByClass(getClass());/*  ww w  . jav a  2s.c o  m*/

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(IPAreaMapper.class);
    job.setReducerClass(IPAreaReducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    return job.waitForCompletion(true) ? 0 : 1;
}