如题WordCount!
一、普通版本
1、TokenizerMapper.java
package hadooptest2; import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; //必须继承org.apache.hadoop.mapreduce.Mapper类,实现map函数 //Mapper类的四个泛型代表map函数输入键值对的键的类,值的类;map函数输出键值对的键的类,值的类 public class TokenizerMapper extends Mapper<LongWritable,Text,Text,IntWritable>{ private final static IntWritable one = new IntWritable(1); private Text word = new Text(); /** * 将键值作为参数传给map函数 * @param key 键,代表行号 * @param value 代表该行的内容 * @throws IOException */ public void map(LongWritable key,Text value,Context context)throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); while(itr.hasMoreTokens()) { //使用StringTokenizer类的nextToken()方法,将每行文本拆分的单个单词 word.set(itr.nextToken()); //Context类的Write(key,value) 将其作为中间结果输出 context.write(word, one); } } }
2、IntSumReducer.java
package hadooptest2; import java.io.IOException; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; /** * Reduce接受mapper输出的中间结果并执行reduce函数 * Reducer类的四个泛型代表reduce函数输入键值对的键的类,值的类;map函数输出键值对的键的类,值的类 */ public class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> { private IntWritable result = new IntWritable(); /** * * reduce中实现形同key值(同一单词)的计数,并将最后结果输出 * @param key 键,代表单词 * @param values reduce函数接收到的参数形如<key,List<value>> * 这是因为map函数将key值相同的所有value都发送给reduce函数 * 也就是特定单词的value都在这个List内 * @throws IOException */ public void reduce(Text key,Iterable<IntWritable>values,Context context) throws IOException,InterruptedException { int sum = 0; for(IntWritable val:values) { //只需要对List求和即可 sum += val.get(); } result.set(sum); context.write(key,result); } }
3、WordCount.java
package hadooptest2; import java.io.IOException; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class WordCount { public static void main(String[] args)throws IOException,ClassNotFoundException,InterruptedException { //Configuation包含了对Hadoop的配置 //也可以在代码中用该对象设置作业级别的配置 Configuration conf = new Configuration(); if(args.length !=2) { System.err.println("Usage:wordcount <in> <out>"); System.exit(2); } Job job = new Job(conf,"word count"); job.setJarByClass(WordCount.class); //指定Mapper类 job.setMapperClass(TokenizerMapper.class); //指定Reduce类 job.setReducerClass(IntSumReducer.class); //指定reduce函数输出key的类 job.setOutputKeyClass(Text.class); //指定reduce函数输出value的类 job.setOutputValueClass(IntWritable.class); //输入路径 FileInputFormat.addInputPath(job,new Path(args[0])); //输出路径 FileOutputFormat.setOutputPath(job,new Path(args[1])); //wartForCompletion函数向Hadoop函数提交任务 System.exit(job.waitForCompletion(true)?0:1); } }
二、提前聚合版
方法:设置Combiner函数,对map函数输出结构进行早期聚合以减少传输的数据量
Tip:
- Conbine过程发生在map和reduce函数之间,将中间结果进行了一次合并
- Hadoop不保证combiner是否被执行,可能会执行,可能不会执行,可能执行多次
- Combiner并不是所有场景都适应,随意使用可能导致结果错误。适合Combiner场景有最大值、最小值、求和等