rclayton-the-terrible

<workflow-app name='example' xmlns="uri:oozie:workflow:0.1">
    <start to='firstjob' />
    <action name="firstjob">
        <map-reduce>
            <job-tracker>${jobtracker}</job-tracker>
            <name-node>${namenode}</name-node>
            <configuration>
                <property><name>mapred.mapper.class</name><value>org.apache.hadoop.example.IdMapper</value></property>
                <property><name>mapred.reducer.class</name><value>org.apache.hadoop.example.IdReducer</value></property>

rclayton-the-terrible

<workflow-app name='example' xmlns="uri:oozie:workflow:0.1">
    <start to='firstjob' />
    <action name="firstjob">
        <map-reduce>
            <job-tracker>${jobtracker}</job-tracker>
            <name-node>${namenode}</name-node>
            <configuration>
                <property><name>mapred.mapper.class</name><value>org.apache.hadoop.example.IdMapper</value></property>
                <property><name>mapred.reducer.class</name><value>org.apache.hadoop.example.IdReducer</value></property>

rclayton-the-terrible

Scheme sourceScheme = new TextLine( new Fields( "line" ) );
Tap source = new Hfs( sourceScheme, inputPath );

Scheme sinkScheme = new TextLine( new Fields( "word", "count" ) );
Tap sink = new Hfs( sinkScheme, outputPath, SinkMode.REPLACE );

Pipe assembly = new Pipe( "wordcount" );

String regex = "(?<!\\pL)(?=\\pL)[^ ]*(?<=\\pL)(?!\\pL)";
Function function = new RegexGenerator( new Fields( "word" ), regex );

rclayton-the-terrible

public interface Mapper<InKey, InValue, OutKey, OutValue> {
    void map(InKey key, InValue value, OutputCollector<OutKey, OutValue> output, Reporter reporter) throws IOException;
}

rclayton-the-terrible

public interface EventFilter<TEvent> {

  public enum Decision {
      Handle,
      Reject,
      Retry
  }

  Decision filter(TEvent event);

rclayton-the-terrible

public interface EnvelopeFilter {

  public enum Decision {
    Handle,
    Reject,
    Retry
  }

rclayton-the-terrible

    public class MyWritable implements Writable {
       // Some data     
       private int counter;
       private long timestamp;
       
       public void write(DataOutput out) throws IOException {
         out.writeInt(counter);
         out.writeLong(timestamp);
       }
       

rclayton-the-terrible

     public class MyWritableComparable implements WritableComparable {
       // Some data
       private int counter;
       private long timestamp;
       
       public void write(DataOutput out) throws IOException {
         out.writeInt(counter);
         out.writeLong(timestamp);
       }
       

rclayton-the-terrible

package org.apache.hadoop.io;

import java.io.DataOutput;
import java.io.DataInput;
import java.io.IOException;

public interface Writable {
  
  void write(DataOutput out) throws IOException;

rclayton-the-terrible

package org.apache.hadoop.io;

public interface WritableComparable<T> extends Writable, Comparable<T> {}