MapReduce编程:词频统计
首先在项目的src文件中需要加入以下文件,log4j的内容为:
log4j.rootLogger=INFO, stdout log4j.appender.stdout=org.apache.log4j.ConsoleAppender log4j.appender.stdout.layout=org.apache.log4j.PatternLayout log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n log4j.appender.logfile=org.apache.log4j.FileAppender log4j.appender.logfile.File=target/spring.log log4j.appender.logfile.layout=org.apache.log4j.PatternLayout log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n
代码如下:
package org.apache.hadoop.examples; import java.io.IOException; import java.util.Iterator; 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 WordCount() { } //main函数,MapReduce程序运行的入口 public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); //指定HDFS相关的参数 //String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs(); String[] otherArgs = new String[]{"input","output"}; if(otherArgs.length < 2) { System.err.println("Usage: wordcount <in> [<in>...] <out>"); System.exit(2); } //通过Job类设置Hadoop程序运行时的环境变量 Job job = Job.getInstance(conf, "word count"); //设置环境参数 job.setJarByClass(WordCount.class); //设置整个程序的类名 job.setMapperClass(WordCount.TokenizerMapper.class); //添加Mapper类 job.setCombinerClass(WordCount.IntSumReducer.class); job.setReducerClass(WordCount.IntSumReducer.class); //添加Reducer类 job.setOutputKeyClass(Text.class); //设置输出类型,因为输出的形式是<单词,个数>,所以这里用Text,类似于Java的String,但还是有些区别 job.setOutputValueClass(IntWritable.class); //设置输出类型,类似于Java的Int for(int i = 0; i < otherArgs.length - 1; ++i) { FileInputFormat.addInputPath(job, new Path(otherArgs[i])); //设置输入文件 } FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1])); //设置输出文件 System.exit(job.waitForCompletion(true)?0:1); //提交作业 } //Reduce处理逻辑 public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> { private IntWritable result = new IntWritable(); public IntSumReducer() { } public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException { int sum = 0; IntWritable val; for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get()) { val = (IntWritable)i$.next(); } this.result.set(sum); context.write(key, this.result); } } //Map处理逻辑 public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> { private static final IntWritable one = new IntWritable(1); private Text word = new Text(); public TokenizerMapper() { } public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); //分词器 while(itr.hasMoreTokens()) { this.word.set(itr.nextToken()); context.write(this.word, one); //输出键值对 //这里也可以直接写成context.write(new Text(word), new IntWritable(1)); } } } }