hanoop的helloworld——WordCount解读
来源:互联网 发布:李小璐遇网络诈骗 编辑:程序博客网 时间:2024/06/05 14:17
关于MapReduce的大概过程,请看:http://www.cnblogs.com/xia520pi/archive/2012/05/16/2504205.html图文并茂,讲解详细。
package hadoop_test;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 WordCountTest {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 st = new StringTokenizer(value.toString());while(st.hasMoreTokens()){word.set(st.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;//int[] a = {1,2,3,4};//for (int i : a){}for(IntWritable val : values)sum+=val.get();//get()返回intresult.set(sum);//set()设置intcontext.write(key, result);}}public static void main(String[] args) throws Exception {args = new String[2];args[0]="hdfs://hadoop1:9000/input";args[1]="hdfs://hadoop1:9000/output";//获得Configuration配置 Configuration: core-default.xml, core-site.xmlConfiguration conf = new Configuration();//获得输入参数 [hdfs://localhost:9000/input, hdfs://localhost:9000/output]String[] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs();if (otherArgs.length != 2) {//判断输入参数,不是2个,就是异常退出System.err.println("usage:wordcount <in> <out>");System.exit(2);}//设置job属性//有横线,说明函数是旧版本,不建议使用//Job job = new Job(conf, "WordCountTest");Job job = Job.getInstance(conf, "WordCountTest");job.setJarByClass(WordCountTest.class);job.setMapperClass(TokenizerMapper.class);job.setCombinerClass(IntSumReducer.class);//将map后到中间结果,在本机进行局部合并job.setReducerClass(IntSumReducer.class);job.setOutputKeyClass(Text.class);//设置Job输出结果<key,word>--<Text,IntWritable>job.setOutputValueClass(IntWritable.class);FileInputFormat.addInputPath(job, new Path(otherArgs[0]));//设置输入和输出路径FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));System.exit(job.waitForCompletion(true)?0:1);}}
package hadoop_test;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 WordCountTest{ 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 values,Context context) throws IOException,InterruptedException{ StringTokenizer st = new StringTokenizer(values.toString()); while(st.hasMoreTokens()){ word.set(st.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 i: values) sum+=i.get(); result.set(sum); context.write(key,result); } } public static void main(String args[]) throws Exception { args = new String[2]; args[0]="hdfs://hadoop1:9000/input"; args[1]="hdfs://hadoop1:9000/output"; Configuration conf = new Configuration(); Job job = Job.getInstance(conf,"WordCountTest"); job.setJarByClass(WordCountTest.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(args[0])); FileOutputFormat.setOutputPath(job,new Path(args[1])); System.exit(job.waitForCompletion(true)?0:1); }}
0 0
- hanoop的helloworld——WordCount解读
- hadoop2.5的第一个HelloWorld程序—单词计数(WordCount.)
- 解读Helloworld的代码
- Hadoop(二)——WordCount运行和解读
- WordCount:Hadoop中MapReduce的HelloWorld程序
- Hadoop-HelloWorld(WordCount)
- hadoop helloworld(wordcount)
- Symbian 的HelloWorld的详细解读
- Hadoop WordCount解读
- Hadoop WordCount解读
- Hadoop WordCount源码解读
- Trident wordCount例子解读
- SparkStreaming---wordCount源码解读
- Rachel_Zhang的“压缩感知”之“HelloWorld"解读
- 对Hadoop自带程序WordCount的解读(转载,自用)
- MapReduce——wordcount
- pig—WordCount analysis
- MapReduce 新旧WordCount 代码解读
- 如何修改远程桌面的端口号
- 数据结构和算法系列 - FP-Tree算法的实现
- 移动终端基带芯片的基本架构介绍之二(移动终端中的基带芯片)
- c++中构造函数初始化的方法以及主要区别
- 内存拷贝和字符串拷贝
- hanoop的helloworld——WordCount解读
- 重新认识C语言
- nginx-lua-fastdfs-GraphicsMagick整合
- Google Java编程风格指南中文版
- Fusion 360 API 入门在线课程
- Java 泛型
- DAX Tabular Calculate,Filter,Value和All
- 排序 - 归并排序
- N-Queens DFS