Hadoop统计中文字数

#Hadoop统计中文字数代码

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;


import java.io.IOException;

public class ChineseWordCountApp {
    public static class ChWordMapper extends Mapper<LongWritable,Text, Text, IntWritable> {
        Text outKey = new Text();
        IntWritable outValue = new IntWritable(1);
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString().replaceAll("[^\\u4e00-\\u9fa5]+","");
            //[^\u4e00-\u9fa5] 表示除所有汉字以外
            String[] words = line.split("");  //用空字符串分割汉字
            for(String word : words){
                outKey.set(word);
                context.write(outKey,outValue);
            }
        }
    }
    public static class ChWordReducer extends Reducer<Text,IntWritable,Text,IntWritable>{
        IntWritable outValue = new IntWritable();

        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            if(!"".equals(key.toString())){
                int count = 0;
                for(IntWritable value : values){
                    count += value.get();
                }
                outValue.set(count);
                context.write(key,outValue);
            }
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        if(args == null || args.length == 1){
            System.out.println("params is invalid");
            return;
        }
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        job.setJarByClass(ChineseWordCountApp.class);
        job.setMapperClass(ChWordMapper.class);
        job.setReducerClass(ChWordReducer.class);

        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);
    }
}