Hadoop自带例子WordCount.java
/** * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ package org.apache.hadoop.examples; import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; public class WordCount { public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{ private final static IntWritable one = new IntWritable(1); private Text word = new Text(); public void map(Object key, Text value, Context context ) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } } } public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> { private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable<IntWritable> values, Context context ) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in> <out>"); System.exit(2); } Job job = new Job(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
Job job = new Job(conf, "word count");语句实例化一个Job对象,然后就为Job对像指定运行时所需的类
job.setJarByClass(WordCount.class);表示告诉Hadoop集群,作业从哪个类开始运行,
job.setMapperClass(TokenizerMapper.class);表示执行哪个类的map方法,我们这里指定的是方法
public void map(Object key, Text value, Context context ) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } }这个方法对要进行map的每行数据,使用StringTokenizer类进行分割,分割出来的值在保存到context中进行,从而在reduce中进行单词数量统计。
job.setReducerClass(IntSumReducer.class);这行语句设置用于进行Reduce的类,告诉Hadoop集群执行哪个reduce函数:
public void reduce(Text key, Iterable<IntWritable> values, Context context ) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); }在这个函数执行之前,Hadoop已经为我们将各个单词的个数大概的归并在一起了,函数的前两个参数是Text 类型和Iterable类型,参数名分别为key和alues,其中在这里key表示在map方法中分割得到的单词,values表示在map阶段统计的单词的数量(由于reduce阶段接收到多个数据结点发送过来的统计结果,所以对应于一个key,可能有多个value,所以将这些value都保存在一迭代器中,然后对迭代器进行遍历,这个过程以后再讨论。),遍历values迭代器,对每个key的数量进行汇总,然后再记录在context中。
job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class);表示MapReduce执行结束之后,将结果保存在HDFS中时,保存的数据类型。这里将结果的key以Text类型保存,value以IntWritable类型保存。
FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));分别表示输入和输出的路径。
job.setCombinerClass(IntSumReducer.class);这行语句,在Hadoop中,Combiner主要用于提升Hadoop的处理效率,为了集中于理解MapReduce,我去掉了这行代码,待以后讨论提升Hadoop性能时,再学习Combiner。