源代码程序
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.setCombinerClass(IntSumReducer.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); } }
本节将对WordCount进行更详细的讲解。详细执行步骤如下
1)将文件拆分成splits,由于测试用的文件较小,所以每个文件为一个split,并将文件按行分割形成<key,value>对,如图所示。这一步由MapReduce框架自动完成,其中偏移量(即key值)包括了回车所占的字符数
2)将分割好的<key,value>对交给用户定义的map方法进行处理,生成新的<key,value>对,如图所示
3)得到map方法输出的<key,value>对后,Mapper会将它们按照key值进行排序,并执行Combine过程,将key至相同value值累加,得到Mapper的最终输出结果。如图所示
4)Reducer先对从Mapper接收的数据进行排序,再交由用户自定义的reduce方法进行处理,得到新的<key,value>对,并作为WordCount的输出结果,如图所示