hadoop：IDEA本地编写mapreducer的wordcount并测试，并上传到hadoop的linux服务器进行测试

直接上代码：

package main.java;

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.output.FileOutputFormat;

public class WordCount {

    //        static {
//        try {
//            // 设置 HADOOP_HOME 目录
//            System.setProperty("hadoop.home.dir", "E:\\spark\\anzhuangsoft\\hadoop-2.7.5");
//            // 加载库文件
//            System.load("E:\\spark\\anzhuangsoft\\hadoop-2.7.5\\bin\\hadoop.dll");
//        } catch (UnsatisfiedLinkError e) {
//            System.err.println("Native code library failed to load.\n" + e);
//            System.exit(1);
//        }
//    }


    //静态内部类（静态内部类只能访问外部类的静态成员）
    public static class WordCountMapper extends Mapper<LongWritable, Text, Text,IntWritable>{
        // #2
        private Text mapOutPutKey=new Text();
        private final static IntWritable mapOutPutValue = new IntWritable(1);
        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            // #1 方式1
//            String [] words = value.toString().split(" ");//直接split性能较低，或参考
//            for (String word : words) {
//                context.write(new Text(word), new IntWritable(1));
//            }

            // #2 方式2 效率高
            StringTokenizer stringTokenizer = new StringTokenizer(value.toString());
            while(stringTokenizer.hasMoreTokens()){
                String wordValue = stringTokenizer.nextToken();
                mapOutPutKey.set(wordValue);
                context.write(mapOutPutKey,mapOutPutValue);
            }
        }
    }


    public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        // 注意 reduce的输入类型是个迭代器 Iterable<IntWritable> value，因为map将分组后的数据传过来，map会做group，将相同key的value合并在一起，放到一个集合中，如<hadoop,list(1,1,...)>
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable intWritable : values) {
                // total
                sum += intWritable.get();
            }
            context.write(key, new IntWritable(sum));//或 new IntWritable().set(sum)
        }
    }


    //dirver（将dirver提出来了）
    public int run(String[] args) throws Exception {
        //1.get configuration
        Configuration conf = new Configuration();
//        conf.set(