【学习】Hadoop大数据平台架构与实践--基础篇下

文章来源：
http://blog.csdn.net/huanglong8/article/details/64124063

视频教学来源：
http://www.imooc.com/learn/391

5. 统计示例WordCount

基本过程是
编写WordCount.java，包含Mapper类，Reducer类
编译WordCount.java，javac -classpath
打包jar -cvf WordCount.jar classes/*
作业提交 hadoop jar WordCount.jar WordCount input output

代码就不讲了，这里直接贴

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.Text;
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.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 WordCount {
    public static class WordCountMap extends
            Mapper<LongWritable, Text, Text, IntWritable> {
        private final IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            String line = value.toString();
            StringTokenizer token = new StringTokenizer(line);
            while (token.hasMoreTokens()) {
                word.set(token.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class WordCountReduce extends
            Reducer<Text, IntWritable, Text, IntWritable> {
        public void reduce(Text key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            context.write(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = new Job(conf);
        job.setJarByClass(WordCount.class);
        job.setJobName("wordcount");
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setMapperClass(WordCountMap.class);
        job.setReducerClass(WordCountReduce.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
}

楼主重新开了一下机，所有要重新启动hadoop，完了可以用jps查看。

./opt/hadoop-1.2.1/bin/start-all.sh

通过Samba进行上传，如果不会配Samba自己补一下。。。

上传上去后，cp到目录下，然后开始编译

mkdir word_count_class
javac -classpath  /opt/hadoop-1.2.1/hadoop-core-1.2.1.jar:/opt/hadoop-1.2.1/lib/commons-cli-1.2.jar -d word_count_class/ WordCount.java

编译完成后，在目录下就会有三个文件了。

下来是打包的过程

jar -cvf wordcount.jar *.class

好，下来创建示例的参数文件，然后并提交到hdfs中。
目录word_count/input/file1
hello world
hello hadoop
hadoop file system
hadoop java api
hello java
hello api
hello ubuntu

目录word_count/input/file2
new file
new system
hadoop file
hadoop new world
hadoop free home
hadoop free school

创建hdfs目录
提交两个文件到hdfs目录中

hadoop fs -mkdir input_wordcount
hadoop fs -put input/* input_wordcount/

然后调用hd来执行

hadoop jar word_count_class/wordcount.jar WordCount input_wordcount output_wordcount

查看文件结果

hadoop fs -ls output_wordcount
hadoop fs -cat output_wordcount/part-r-00000

6. 利用MapReduce进行排序

其思想原理是 将所有数据先分区域分块 对独立的区块进行排序，最后进入到Reduce中进行合并输出。

上代码吧。。。

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.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.Partitioner;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.util.GenericOptionsParser;

public class Sort {

    public static class Map extends
            Mapper<Object, Text, IntWritable, IntWritable> {

        private static IntWritable data = new IntWritable();

        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            String line = value.toString();

            data.set(Integer.parseInt(line));

            context.write(data, new IntWritable(1));

        }

    }

    public static class Reduce extends
            Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {

        private static IntWritable linenum = new IntWritable(1);

        public void reduce(IntWritable key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {

            for (IntWritable val : values) {

                context.write(linenum, key);

                linenum = new IntWritable(linenum.get() + 1);
            }

        }
    }

    public static class Partition extends Partitioner<IntWritable, IntWritable> {

        @Override
        public int getPartition(IntWritable key, IntWritable value,
                int numPartitions) {
            int MaxNumber = 65223;
            int bound = MaxNumber / numPartitions + 1;
            int keynumber = key.get();
            for (int i = 0; i < numPartitions; i++) {
                if (keynumber < bound * i && keynumber >= bound * (i - 1))
                    return i - 1;
            }
            return 0;
        }
    }

    /**
     * @param args
     */

    public static void main(String[] args) throws Exception {
        // TODO Auto-generated method stub
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args)
                .getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage WordCount <int> <out>");
            System.exit(2);
        }
        Job job = new Job(conf, "Sort");
        job.setJarByClass(Sort.class);
        job.setMapperClass(Map.class);
        job.setPartitionerClass(Partition.class);
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(IntWritable.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);
    }

}

其实贴代码不好，只是便于学习，目的还是先把hd熟悉流程起来，至于hd中的一些类库的使用，现学现用呗。。。

map类是用来排序的，Partition类是进行分区合并的。

然后用同样的方式运行就行了。自己练习吧。