在eclipse中编写word count的Java程序打包到虚拟机中运行

xiaoxiao2025-02-06 41

1.在eclipse中创建maven项目【file】-【new】-【Maven project】创建完成如图（新建class：WordCount_test java 程序） 2.在pom.xml中添加依赖

<dependencies> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-hdfs</artifactId> <version>2.7.3</version> </dependency> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-client</artifactId> <version>2.7.3</version> </dependency> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-common</artifactId> <version>2.7.3</version> </dependency> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-common</artifactId> <version>2.6.0</version> </dependency>  <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-mapreduce-client-core</artifactId> <version>2.6.0</version> </dependency>

3.在WordCount_test .java中编写Word Count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; public class WordCount_test { 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(); Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount_test.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); } }

4.可以在本地运行下可以看到没有错误 5.打包程序点击项目，右键选择export 选择JAR file-next，如图选择打包地址和命名包名 6.在虚拟机里用包进行程序运行在本地找到包然后将包放到虚拟机中输入命令hadoop jar Hadoop.jar WordCount_test /word.txt /output123运行，Hadoop.jar是包名，WordCount_test 是主类名，/word.txt 是要统计词数的hdfs文件（需事先传上去），/output123是存放运行结果的路径运行结果：结束

最新回复(0)