Hadoop之二次排序

一、基本概念

二次排序就是首先按照第一字段排序，然后再对第一字段相同的行按照第二字段排序，注意不能破坏第一次排序的结果。

二、测试数据（部分）

1   5
1   3
1   4
1   99
2   400
2   240
2   237
2   238
2   239
2   245 

三、输出数据（部分）

------------------------------------------------
1   1
1   2
1   3
1   4
1   5
1   6
1   7
1   8
1   9
------------------------------------------------
2   235
2   236
2   237
2   238
2   239
2   240
2   241
2   242
2   243
2   244

四、源代码

package secondarySort;  
import java.io.DataInput;  
import java.io.DataOutput;  
import java.io.IOException;  
import java.net.URI;
import java.util.StringTokenizer;  

import org.apache.hadoop.conf.Configuration;  
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;  
import org.apache.hadoop.io.IntWritable;  
import org.apache.hadoop.io.LongWritable;  
import org.apache.hadoop.io.Text;  
import org.apache.hadoop.io.WritableComparable;  
import org.apache.hadoop.io.WritableComparator;  
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.mapreduce.lib.input.FileInputFormat;  
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;  
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;  
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;  

public class SecondarySort {  
    //自己定义的key类应该实现WritableComparable接口  
    public static class IntPair implements WritableComparable<IntPair> {  
        int first;  
        int second;  
        /** 
         * 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;  
        }  
        @Override  
        //反序列化，从流中的二进制转换成IntPair  
        public void readFields(DataInput in) throws IOException {  
            // TODO Auto-generated method stub  
            first = in.readInt();  
            second = in.readInt();  
        }  
        @Override  
        //序列化，将IntPair转化成使用流传送的二进制  
        public void write(DataOutput out) throws IOException {  
            // TODO Auto-generated method stub  
            out.writeInt(first);  
            out.writeInt(second);  
        }  
        @Override  
        //key的比较  
        public int compareTo(IntPair o) {  
            // TODO Auto-generated method stub  
            if (first != o.first) {  
                return first < o.first ? -1 : 1;  
            } else if (second != o.second) {  
                return second < o.second ? -1 : 1;  
            } else {  
                return 0;  
            }  
        }  

        //新定义类应该重写的两个方法  
        @Override  
        //The hashCode() method is used by the HashPartitioner (the default partitioner in MapReduce)  
        public int hashCode() {  
            return first * 157 + second;  
        }  
        @Override  
        public boolean equals(Object right) {  
            if (right == null)  
                return false;  
            if (this == right)  
                return true;  
            if (right instanceof IntPair) {  
                IntPair r = (IntPair) right;  
                return r.first == first && r.second == second;  
            } else {  
                return false;  
            }  
        }  
    }  
     /** 
       * 分区函数类。根据first确定Partition。 
       */  
      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;  
        }  
      }  

      /** 
       * 分组函数类。只要first相同就属于同一个组。 
       */  
    /*//第一种方法，实现接口RawComparator 
    public static class GroupingComparator implements RawComparator<IntPair> { 
        @Override 
        public int compare(IntPair o1, IntPair o2) { 
            int l = o1.getFirst(); 
            int r = o2.getFirst(); 
            return l == r ? 0 : (l < r ? -1 : 1); 
        } 
        @Override 
        //一个字节一个字节的比，直到找到一个不相同的字节，然后比这个字节的大小作为两个字节流的大小比较结果。 
        public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2){ 
            // TODO Auto-generated method stub 
             return WritableComparator.compareBytes(b1, s1, Integer.SIZE/8,  
                     b2, s2, Integer.SIZE/8); 
        } 
    }*/  
    //第二种方法，继承WritableComparator  
    public static class GroupingComparator extends WritableComparator {  
          protected GroupingComparator() {  
            super(IntPair.class, true);  
          }  
          @Override  
          //Compare two WritableComparables.  
          public int compare(WritableComparable w1, WritableComparable w2) {  
            IntPair ip1 = (IntPair) w1;  
            IntPair ip2 = (IntPair) w2;  
            int l = ip1.getFirst();  
            int r = ip2.getFirst();  
            return l == r ? 0 : (l < r ? -1 : 1);  
          }  
        }  


    // 自定义map  
    public static class Map extends  
            Mapper<LongWritable, Text, IntPair, IntWritable> {  
        private final IntPair intkey = new IntPair();  
        private final IntWritable intvalue = new IntWritable();  
        public void map(LongWritable key, Text value, Context context)  
                throws IOException, InterruptedException {  
            String line = value.toString();  
            StringTokenizer tokenizer = new StringTokenizer(line);  
            int left = 0;  
            int right = 0;  
            if (tokenizer.hasMoreTokens()) {  
                left = Integer.parseInt(tokenizer.nextToken());  
                if (tokenizer.hasMoreTokens())  
                    right = Integer.parseInt(tokenizer.nextToken());  
                intkey.set(left, right);  
                intvalue.set(right);  
                context.write(intkey, intvalue);  
            }  
        }  
    }  
    // 自定义reduce  
    //  
    public static class Reduce extends  
            Reducer<IntPair, IntWritable, Text, IntWritable> {  
        private final Text left = new Text();  
        private static final Text SEPARATOR =   
              new Text("------------------------------------------------");  
        public void reduce(IntPair key, Iterable<IntWritable> values,  
                Context context) throws IOException, InterruptedException {  
            context.write(SEPARATOR, null);  
            left.set(Integer.toString(key.getFirst()));  
            for (IntWritable val : values) {  
                context.write(left, val);  
            }  
        }  
    }  
    /** 
     * @param args 
     */  
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {  
        // TODO Auto-generated method stub  
        // 读取hadoop配置  
        Configuration conf = new Configuration();  
        // 实例化一道作业  
        Job job = new Job(conf, "secondarysort");  
        job.setJarByClass(SecondarySort.class);  
        // Mapper类型  
        job.setMapperClass(Map.class);  
        // 不再需要Combiner类型，因为Combiner的输出类型<Text, IntWritable>对Reduce的输入类型<IntPair, IntWritable>不适用  
        //job.setCombinerClass(Reduce.class);  
        // Reducer类型  
        job.setReducerClass(Reduce.class);  
        // 分区函数  
        job.setPartitionerClass(FirstPartitioner.class);  
        // 分组函数  
        job.setGroupingComparatorClass(GroupingComparator.class);  

        // map 输出Key的类型  
        job.setMapOutputKeyClass(IntPair.class);  
        // map输出Value的类型  
        job.setMapOutputValueClass(IntWritable.class);  
        // rduce输出Key的类型，是Text，因为使用的OutputFormatClass是TextOutputFormat  
        job.setOutputKeyClass(Text.class);  
        // rduce输出Value的类型  
        job.setOutputValueClass(IntWritable.class);  

        // 将输入的数据集分割成小数据块splites，同时提供一个RecordReder的实现。  
        job.setInputFormatClass(TextInputFormat.class);  
        // 提供一个RecordWriter的实现，负责数据输出。  
        job.setOutputFormatClass(TextOutputFormat.class);  
        //判断输入路径是否存在，存在即删除
        FileSystem fs= FileSystem.get(URI.create(args[1]), conf);
        Path path  = new Path(args[1]);
        if(fs.exists(path))
        {   try 
            {
                fs.delete(path, true);
                System.out.println(path.getName() + "删除成功 ");
            }catch(Exception e){
                System.err.println(e.getMessage());
            }
        }  
        // 输入hdfs路径  
        FileInputFormat.setInputPaths(job, new Path(args[0]));  
        // 输出hdfs路径  
        FileOutputFormat.setOutputPath(job, new Path(args[1]));  
        // 提交job  
        System.exit(job.waitForCompletion(true) ? 0 : 1);  
    }  
}  

五、提升

将代码优化，实现字符串排序。

import java.io.DataInput;
import java.io.DataOutput;
import java.io.File;
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.mapred.JobConf;
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.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

import service.plugin.EJob;

public class SecondarySortString {
    // 自己定义的key类应该实现WritableComparable接口
    public static class IntPair implements WritableComparable<IntPair> {
        String first;
        String second;

        /**
         * Set the left and right values.
         */
        public void set(String left, String right) {
            first = left;
            second = right;
        }

        public String getFirst() {
            return first;
        }

        public String getSecond() {
            return second;
        }

        // 反序列化，从流中的二进制转换成IntPair
        public void readFields(DataInput in) throws IOException {
            first = in.readUTF();
            second = in.readUTF();
        }

        // 序列化，将IntPair转化成使用流传送的二进制
        public void write(DataOutput out) throws IOException {
            out.writeUTF(first);
            out.writeUTF(second);
        }

        // 重载 compareTo 方法，进行组合键 key 的比较，该过程是默认行为。
        // 分组后的二次排序会隐式调用该方法。
        public int compareTo(IntPair o) {
            if (!first.equals(o.first)) {
                return first.compareTo(o.first);
            } else if (!second.equals(o.second)) {
                return second.compareTo(o.second);
            } else {
                return 0;
            }
        }

        // 新定义类应该重写的两个方法
        // The hashCode() method is used by the HashPartitioner (the default
        // partitioner in MapReduce)
        public int hashCode() {
            return first.hashCode() * 157 + second.hashCode();
        }

        public boolean equals(Object right) {
            if (right == null)
                return false;
            if (this == right)
                return true;
            if (right instanceof IntPair) {
                IntPair r = (IntPair) right;
                return r.first.equals(first) && r.second.equals(second);
            } else {
                return false;
            }
        }
    }

    /**
     * 分区函数类。根据first确定Partition。
     */
    public static class FirstPartitioner extends Partitioner<IntPair, Text> {
        public int getPartition(IntPair key, Text value, int numPartitions) {
            return Math.abs(key.getFirst().hashCode() * 127) % numPartitions;
        }
    }

    /**
     * 分组函数类。只要first相同就属于同一个组。
     */
    /*
     * //第一种方法，实现接口RawComparator public static class GroupingComparator
     * implements RawComparator<IntPair> { public int compare(IntPair o1,
     * IntPair o2) { int l = o1.getFirst(); int r = o2.getFirst(); return l == r
     * ? 0 : (l < r ? -1 : 1); }
     * //一个字节一个字节的比，直到找到一个不相同的字节，然后比这个字节的大小作为两个字节流的大小比较结果。 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); } }
     */
    // 第二种方法，继承WritableComparator
    public static class GroupingComparator extends WritableComparator {
        protected GroupingComparator() {
            super(IntPair.class, true);
        }
        // Compare two WritableComparables.
        // 重载 compare：对组合键按第一个自然键排序分组
        public int compare(WritableComparable w1, WritableComparable w2) {
            IntPair ip1 = (IntPair) w1;
            IntPair ip2 = (IntPair) w2;
            String l = ip1.getFirst();
            String r = ip2.getFirst();
            return l.compareTo(r);
        }
    }

    // 自定义map
    public static class Map extends Mapper<LongWritable, Text, IntPair, Text> {
        private final IntPair keyPair = new IntPair();
        String[] lineArr = null;
        public void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            String line = value.toString();
            if(line.isEmpty()){
                return;
            }
            lineArr = line.split(" ", -1);
            keyPair.set(lineArr[0], lineArr[1]);
            context.write(keyPair, value);
        }
    }

    // 自定义reduce
    public static class Reduce extends Reducer<IntPair, Text, Text, Text> {
        private static final Text SEPARATOR = new Text("------------------------------------------------");
        public void reduce(IntPair key, Iterable<Text> values, Context context)
                throws IOException, InterruptedException {
            context.write(SEPARATOR, null);
            for (Text val : values) {
                context.write(null, val);
            }
        }
    }

    public static void main(String[] args) throws IOException,
            InterruptedException, ClassNotFoundException {
        File jarFile = EJob.createTempJar("bin");
        ClassLoader classLoader = EJob.getClassLoader();
        Thread.currentThread().setContextClassLoader(classLoader);

        Configuration conf = new Configuration(true);
        String[] otherArgs = new String[2];
        otherArgs[0] = "hdfs://192.168.1.100:9000/data/test_in/secondary_sort_data_string.txt";
        String time = new SimpleDateFormat("yyyyMMddHHmmss").format(new Date());
        otherArgs[1] = "hdfs://192.168.1.100:9000/data/test_out/mr-" + time;

        // 实例化一道作业
        Job job = new Job(conf, "secondarysort");
        job.setJarByClass(SecondarySort.class);

        ((JobConf) job.getConfiguration()).setJar(jarFile.toString());

        // Mapper类型
        job.setMapperClass(Map.class);
        // 不再需要Combiner类型，因为Combiner的输出类型<Text,
        // IntWritable>对Reduce的输入类型<IntPair, IntWritable>不适用
        // job.setCombinerClass(Reduce.class);
        // Reducer类型
        job.setReducerClass(Reduce.class);
        // 分区函数
        job.setPartitionerClass(FirstPartitioner.class);
        // 分组函数
        job.setGroupingComparatorClass(GroupingComparator.class);

        // map 输出Key的类型
        job.setMapOutputKeyClass(IntPair.class);
        // map输出Value的类型
        job.setMapOutputValueClass(Text.class);
        // rduce输出Key的类型，是Text，因为使用的OutputFormatClass是TextOutputFormat
        job.setOutputKeyClass(Text.class);
        // rduce输出Value的类型
        job.setOutputValueClass(Text.class);

        // 将输入的数据集分割成小数据块splites，同时提供一个RecordReder的实现。
        job.setInputFormatClass(TextInputFormat.class);
        // 提供一个RecordWriter的实现，负责数据输出。
        job.setOutputFormatClass(TextOutputFormat.class);

        // 输入hdfs路径
        FileInputFormat.setInputPaths(job, new Path(otherArgs[0]));
        // 输出hdfs路径
//        FileSystem.get(conf).delete(new Path(args[1]), true);
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        // 提交job
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}