import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
//LongWritable 偏移量 long 表示改行在文件中的位置,而不是行号
//Text map阶段的输入数据 一行文本信息 字符串类型 string
// Text map阶段的数据字符串类型 string
//IntWritable map阶段输出的value类型,对应java中的int类型,表示行号
public class WordCountMap extends Mapper
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//读取每行文本
String line = value.toString();
//splite拆分每行
String[] words = line.split(" ");//分词
//去除每个单词
for (String word : words){
//将行数据转换为Text类型
Text wordText = new Text(word);
//将1 转变为IntWritable
IntWritable outValue = new IntWritable(1);
//写出单词跟对应1
context.write(wordText,outValue);
}
}
}
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class WordCountReduce extends Reducer
@Override
protected void reduce(Text key, Iterable
int sum=0;
for (IntWritable number:values) {
sum += number.get();
}
context.write(key,new IntWritable());
}
}



