package com.bwzy.hadoop;
import java.io.File;
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
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 org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class WordCount extends Configured implements Tool {public static class Mapextendsorg.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, IntWritable> {private final static IntWritable one = new IntWritable(1);private Text word = new Text();public void map(LongWritable key,Text value,Context context){String line = value.toString();StringTokenizer tokenizer = new StringTokenizer(line);//读取每一行数据，并将该行数据以空格分割（StringTokenizer默认是以空格分割字符串）while (tokenizer.hasMoreTokens()) {word.set(tokenizer.nextToken());try {context.write(word, one);//输出给Reduce} catch (IOException e) {e.printStackTrace();} catch (InterruptedException e) {e.printStackTrace();}}}}public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {public void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException{int sum = 0;
//合并每个单词出现的次数for (IntWritable val : values) {sum+=val.get();}context.write(key, new IntWritable(sum));}}public static void main(String[] args) throws Exception {int ret = ToolRunner.run(new WordCount(), args);System.exit(ret);}@Overridepublic int run(String[] arg0) throws Exception {Job job = new Job(getConf());job.setJobName("wordcount");job.setOutputKeyClass(Text.class);//key--设置输出格式job.setOutputValueClass(IntWritable.class);//value--设置输出格式job.setMapperClass(Map.class);job.setReducerClass(Reduce.class);job.setInputFormatClass(TextInputFormat.class);job.setOutputFormatClass(TextOutputFormat.class);FileInputFormat.setInputPaths(job, new Path(arg0[0]));FileOutputFormat.setOutputPath(job, new Path(arg0[1]));boolean success = job.waitForCompletion(true);return success?0:1;}
}