package mapred; import java.io.*; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.*; import org.apache.hadoop.io.*; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.*; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; public class USA_ZCoord { public static class USA_ZCoordMapper extends Mapper { private final static Text txt1 = new Text(); private final static Text txt2 = new Text(); public void map(Text key, Text value, Context context) throws IOException, InterruptedException { txt1.set(key.toString()+" 0"); txt2.set(value.toString()); context.write(txt1, txt2); } } public static class USA_ZCoordReducer extends Reducer { private final static Text txt2 = new Text(); public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException { for(Text val:values) {//only 1 value txt2.set(key.toString()+"\t"+val.toString()); context.write(NullWritable.get(), txt2); } } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = new Job(conf, "USA_ZCoord"); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Args: "); System.exit(2); } job.setJarByClass(USA_ZCoord.class); job.setMapperClass(USA_ZCoordMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setReducerClass(USA_ZCoordReducer.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Text.class); job.setNumReduceTasks(120); job.setInputFormatClass(KeyValueTextInputFormat.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true)?0:1); } }