//这个是在原来的基础上修改以后得到的,将其中的分词的依据给换掉了,并且进行词频统计的时候会自动的忽略大小写
packageorg.apache.hadoop.mapred;
importjava.io.IOException;
importjava.util.ArrayList;
importjava.util.Iterator;
importjava.util.List;
importjava.util.StringTokenizer;
importorg.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
importorg.apache.hadoop.fs.Path;
importorg.apache.hadoop.io.IntWritable;
importorg.apache.hadoop.io.LongWritable;
importorg.apache.hadoop.io.Text;
importorg.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
importorg.apache.hadoop.mapred.JobClient;
importorg.apache.hadoop.mapred.JobConf;
importorg.apache.hadoop.mapred.MapReduceBase;
importorg.apache.hadoop.mapred.Mapper;
importorg.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
importorg.apache.hadoop.mapred.Reporter;
importorg.apache.hadoop.util.Tool;
importorg.apache.hadoop.util.ToolRunner;
public classWordCount extends Configured implements Tool {
/*
这个类实现mapper接口的map方法,输入的是文本总的每一行。利用StringTokenizer将字符串拆分成单词。然后将输出结果(word, 1)写入到Outp