java mapreduce 例子_MapReduce案例

package first;

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 org.wltea.analyzer.core.IKSegmenter;

import org.wltea.analyzer.core.Lexeme;

import java.io.IOException;

import java.io.StringReader;

public class FirstMap extends Mapper {

private Text t = new Text();

private IntWritable intWritable = new IntWritable(1);

//3823890210294392今天我约了豆浆，油条

//word_id count

@Override

protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

String[] split = value.toString().trim().split("\t");

if (split.length > 2) {

String id = split[0].trim();

String word = split[1].trim();

//对word 进行分词

StringReader sr = new StringReader(word);

IKSegmenter ikSegmenter = new IKSegmenter(sr, true);

Lexeme text = null;

while ((text = ikSegmenter.next()) != null) {

String w = text.getLexemeText();

//word_id count

t.set(w + "_" + id);

context.write(t,new IntWritable(1));

}

}

//输出总行数

context.write(new Text("count"), new IntWritable(1));

}

}

单词统计 cord count