WordCount程序结构

1. WordCount程序结构如下：

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

import java.io.IOException;
import java.util.StringTokenizer;

/**
 * Created by zhangyan on 2016/12/28.
 */
public class WordCount1 {
    public static void main(String args[])
            throws IOException, ClassNotFoundException, InterruptedException {
	//获取系统当前的配置项，默认加载core-default.xml和core-site.xml这两个xml中的内容
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Word Count 1.0");
        job.setJarByClass(WordCount1.class);
        //设置实现map函数的类
        job.setMapperClass(MyMap.class);
        //设置实现combiner的类
        job.setCombinerClass(MyReduce.class);
        //设置实现reduce函数的类
        job.setReducerClass(MyReduce.class);
        //设置map阶段产生的key和value的类型，
        //如果Map output的key和value的class与reduce output的key和value的class相同，以下两句可以不写
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置reduce阶段产生的key和value的类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //设置输入路径
        FileInputFormat.addInputPath(job, new Path(args[0]));
        // FileInputFormat.setInputPaths(job, new Path(args[0]));  // 可以设置多个Path
        //设置输出路径
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //job.waitForCompletion(true)  是提交job
        System.exit(job.waitForCompletion(true) ? 0 : 1 );
    }

    public static class MyMap extends Mapper<Object, Text, Text, LongWritable>{
        public static final LongWritable one = new LongWritable(1);   //不必是static的
        public static Text word = new Text();  //不必是static的

        public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
            String lines = value.toString();
            String[] arr = lines.split("\t");
            for (String wd: arr) {
                word.set(wd);
                context.write(word,one);
            }
        }
    }

    public static class MyReduce extends Reducer<Text, LongWritable, Text, LongWritable>{
        public static LongWritable result = new LongWritable();  //不必是static的
        public void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException,InterruptedException{
            long sum = 0;
            for (LongWritable value: values){
                sum+=value.get();
            }
            result.set(sum);
            context.write(key,result);
        }
    }

}

2. Configuration：
可以通过构造函数Configuration(boolean loadDefaults)以决定程序是否load系统的配置文件，参数为false则不load系统的配置文件
可以通过构造函数Configuration(Configuration other)加载其他的Configuration对象中的配置项
可以通过addResource()方法，加载其他的配置文件，例如：conf1.addResource(new Path("../hdfs-site.xml"));
Configuration的示例程序

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;

/**
 * Created by zhangyan on 2017/1/5.
 */
public class TestConfiguration {
    public static void main(String[] args) throws Exception{
        Configuration conf1=new Configuration();
        Configuration conf2=new Configuration(false);
        conf1.addResource(new Path("/Users/zhangyan/Documents/AuraBigData/ScalaCode/MyExercise/target/classes/hdfs-site.xml"));
        System.out.println(conf1.get("fs.defaultFS"));
        System.out.println(conf1.getInt("dfs.replication",-1));
        System.out.println(conf1.getResource("core-site.xml"));
        System.out.println(conf2.get("fs.defaultFS"));
        System.out.println(conf2.getInt("dfs.replication",-1));
        System.out.println(conf2.getResource("core-site.xml"));

        conf2.addResource("core-site.xml");
        conf2.addResource("hdfs-site.xml");
        System.out.println(conf2.get("fs.defaultFS"));
        System.out.println(conf2.getInt("dfs.replication",-1));
    }
}

3. Job对象

用来在程序中设置job、提交job、控制job执行、查询job状态，其set方法只能在提交job之前使用