hadoop mapreduce 简单例子
本例子统计 用空格分开的单词出现数量( 这个Main.mian 启动方式是hadoop 2.0 的写法。1.0 不一样 )
目录结构:
使用的 maven : 下面是maven 依赖。
<dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-client</artifactId> <version>2.8.5</version> </dependency>
Main.java:
package com.zyk.test; import java.io.IOException; import java.util.ArrayList; import java.util.List; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; public class Main { public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { Configuration conf = new Configuration(); GenericOptionsParser optionParser = new GenericOptionsParser(conf, args); String[] remainingArgs = optionParser.getRemainingArgs(); if ((remainingArgs.length != 2) && (remainingArgs.length != 4)) { System.err.println("Usage: wordcount <in> <out> [-skip skipPatternFile]"); System.exit(2); } Job job = Job.getInstance(conf, "word count"); job.setJarByClass(Main.class); job.setMapperClass(WordMap.class); // job.setCombinerClass(IntSumReducer.class); job.setReducerClass(WordReduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); //FileInputFormat.addInputPath(job, new Path("/wd/in")); //FileOutputFormat.setOutputPath(job, new Path("/wd/out")); List<String> otherArgs = new ArrayList<String>(); for (int i = 0; i < remainingArgs.length; ++i) { if ("-skip".equals(remainingArgs[i])) { job.addCacheFile(new Path(remainingArgs[++i]).toUri()); job.getConfiguration().setBoolean("wordcount.skip.patterns", true); } else { otherArgs.add(remainingArgs[i]); } } FileInputFormat.addInputPath(job, new Path(otherArgs.get(0))); FileOutputFormat.setOutputPath(job, new Path(otherArgs.get(1))); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
WordMap.java
package com.zyk.test; import java.io.IOException; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; public class WordMap extends Mapper<LongWritable, Text, Text, LongWritable> { @Override protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, LongWritable>.Context context)throws IOException, InterruptedException { String[] words = value.toString().split(" "); for(String word : words) { context.write (new Text( word ), new LongWritable( 1 ) ); } } }
WordReduce.java
package com.zyk.test; import java.io.IOException; import java.util.Iterator; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; public class WordReduce extends Reducer<Text, LongWritable, Text, LongWritable > { @Override protected void reduce(Text key, Iterable<LongWritable> arg1,Reducer<Text, LongWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException { Iterator<LongWritable> its = arg1.iterator(); long sum = 0L; while( its.hasNext() ) { LongWritable it = its.next(); sum += it.get(); } context.write( key , new LongWritable( sum ) ); } }
content.txt 是 要上传到hdfs 上作为输入参数目录的 ,内容我就不提提供了。随便找个页面复制一些文本就可以。
然后打成 jar 包。 发布到hadoop 上运行。( 后面 两个参数是 指定的 输入 和输出路径 )运行前应该吧 要统计的文件复制到 hdfs 的 /wd/in 目录里面。
./hadoop jar /tools/wd.jar com.zyk.test.Main /wd/in /wd/out4
运行结果:
能耍的时候就一定要耍,不能耍的时候一定要学。
天道酬勤,贵在坚持
posted on 2018-10-08 14:35 zhangyukun 阅读(205) 评论(0) 编辑 收藏 举报