首页 > 代码库 > 二次排序
二次排序
工作原理：
使用如下map和reduce：（特别注意输入输出类型， 其中IntPair为自定义类型）
public static class Map extends Mapper<LongWritable, Text, IntPair, IntWritable>
public static class Reduce extends Reducer<IntPair, IntWritable, IntWritable, IntWritable>
在map阶段，使用job.setInputFormatClass(TextInputFormat)做为输入格式。注意输出应该符合自定义Map中定义的输出<IntPair, IntWritable>。最终是生成一个List<IntPair, IntWritable>。在map阶段的最后，会先调用job.setPartitionerClass对这个List进行分区，每个分区映射到一个reducer。每个分区内可以调用job.setSortComparatorClass设置的key比较函数类排序。如果没有通过job.setSortComparatorClass设置key比较函数类，则使用key的实现的compareTo方法。在随后的例子中，第一个例子中，使用了IntPair实现的compareTo方法，而在下一个例子中，专门定义了key比较函数类。
在reduce阶段，reducer接收到所有映射到这个reducer的map输出后，也是会调用job.setSortComparatorClass设置的key比较函数类对所有数据对排序。然后开始构造一个key对应的value迭代器。这时就要用到分组，使用jobjob.setGroupingComparatorClass设置的分组函数类。只要这个比较器比较的两个key相同，他们就属于同一个组，它们的value放在一个value迭代器，而这个迭代器的key使用属于同一个组的所有key的第一个key。最后就是进入Reducer的reduce方法，reduce方法的输入是所有的（key和它的value迭代器）。同样注意输入与输出的类型必须与自定义的Reducer中声明的一致。
代码：
package org.apache.hadoop.examples;import java.io.DataInput;import java.io.DataOutput;import java.io.IOException;import java.util.StringTokenizer;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.RawComparator;import org.apache.hadoop.io.Text;import org.apache.hadoop.io.WritableComparable;import org.apache.hadoop.io.WritableComparator;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.mapreduce.Job;import org.apache.hadoop.mapreduce.Mapper;import org.apache.hadoop.mapreduce.Partitioner;import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.util.GenericOptionsParser;/** * This is an example Hadoop Map/Reduce application. * It reads the text input files that must contain two integers per a line. * The output is sorted by the first and second number and grouped on the * first number. * * To run: bin/hadoop jar build/hadoop-examples.jar secondarysort * <i>in-dir</i> <i>out-dir</i> */public class SecondarySort { /** * Define a pair of integers that are writable. * They are serialized in a byte comparable format. */ public static class IntPair implements WritableComparable<IntPair> { private int first = 0; private int second = 0; /** * Set the left and right values. */ public void set(int left, int right) { first = left; second = right; } public int getFirst() { return first; } public int getSecond() { return second; } /** * Read the two integers. * Encoded as: MIN_VALUE -> 0, 0 -> -MIN_VALUE, MAX_VALUE-> -1 */ @Override public void readFields(DataInput in) throws IOException { first = in.readInt() + Integer.MIN_VALUE; second = in.readInt() + Integer.MIN_VALUE; } @Override public void write(DataOutput out) throws IOException { out.writeInt(first - Integer.MIN_VALUE); out.writeInt(second - Integer.MIN_VALUE); } @Override public int hashCode() { return first * 157 + second; } @Override public boolean equals(Object right) { if (right instanceof IntPair) { IntPair r = (IntPair) right; return r.first == first && r.second == second; } else { return false; } } /** A Comparator that compares serialized IntPair. */ public static class Comparator extends WritableComparator { public Comparator() { super(IntPair.class); } public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) { return compareBytes(b1, s1, l1, b2, s2, l2); } } static { // register this comparator WritableComparator.define(IntPair.class, new Comparator()); } @Override public int compareTo(IntPair o) { if (first != o.first) { return first < o.first ? -1 : 1; } else if (second != o.second) { return second < o.second ? -1 : 1; } else { return 0; } } } /** * Partition based on the first part of the pair. */ public static class FirstPartitioner extends Partitioner<IntPair,IntWritable>{ @Override public int getPartition(IntPair key, IntWritable value, int numPartitions) { return Math.abs(key.getFirst() * 127) % numPartitions; } } /** * Compare only the first part of the pair, so that reduce is called once * for each value of the first part. */ public static class FirstGroupingComparator implements RawComparator<IntPair> { @Override public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) { return WritableComparator.compareBytes(b1, s1, Integer.SIZE/8, b2, s2, Integer.SIZE/8); } @Override public int compare(IntPair o1, IntPair o2) { int l = o1.getFirst(); int r = o2.getFirst(); return l == r ? 0 : (l < r ? -1 : 1); } } /** * Read two integers from each line and generate a key, value pair * as ((left, right), right). */ public static class MapClass extends Mapper<LongWritable, Text, IntPair, IntWritable> { private final IntPair key = new IntPair(); private final IntWritable value = http://www.mamicode.com/new IntWritable(); @Override public void map(LongWritable inKey, Text inValue, Context context) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(inValue.toString()); int left = 0; int right = 0; if (itr.hasMoreTokens()) { left = Integer.parseInt(itr.nextToken()); if (itr.hasMoreTokens()) { right = Integer.parseInt(itr.nextToken()); } key.set(left, right); value.set(right); context.write(key, value); } } } /** * A reducer class that just emits the sum of the input values. */ public static class Reduce extends Reducer<IntPair, IntWritable, Text, IntWritable> { private static final Text SEPARATOR = new Text("------------------------------------------------"); private final Text first = new Text(); @Override public void reduce(IntPair key, Iterable<IntWritable> values, Context context ) throws IOException, InterruptedException { context.write(SEPARATOR, null); first.set(Integer.toString(key.getFirst())); for(IntWritable value: values) { context.write(first, value); } } } 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); } 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); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }}
----引用文章 http://blog.csdn.net/heyutao007/article/details/5890103
----引用hadoop1.2.1源码
声明：以上内容来自用户投稿及互联网公开渠道收集整理发布，本网站不拥有所有权，未作人工编辑处理，也不承担相关法律责任，若内容有误或涉及侵权可进行投诉： 投诉/举报 工作人员会在5个工作日内联系你，一经查实，本站将立刻删除涉嫌侵权内容。