環境爲Hadoop2.5.2(如何搭建環境教程),在pom.xml中加入如下配置文件。java
<dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-common</artifactId> <version>2.5.2</version> </dependency> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-hdfs</artifactId> <version>2.5.2</version> </dependency> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-client</artifactId> <version>2.5.2</version> </dependency> <dependency> <groupId>junit</groupId> <artifactId>junit</artifactId> <version>3.8.1</version> <scope>test</scope> </dependency>
測試HDFSshell
public class HdfsTest { public static void main( String[] args ) throws IOException { String uri = "hdfs://192.168.1.112:9000/"; Configuration config = new Configuration(); FileSystem fs = FileSystem.get(URI.create(uri), config); //列出目錄全部文件 FileStatus[] statuses = fs.listStatus(new Path("/data")); for (FileStatus status : statuses) { System.out.println(status); } //建立新文件 FSDataOutputStream os = fs.create(new Path("/data/hdfs_test.txt")); os.write("測試HDFS第一條\r\n".getBytes()); os.write("測試HDFS第二條\r\n".getBytes()); os.flush(); os.close(); //讀取文件 InputStream is = fs.open(new Path("/data/hdfs_test.txt")); IOUtils.copyBytes(is, System.out, 1024, true); } }
測試Map/Reduce
apache
實例:將多個文件裏面的內容去掉重複行。
服務器
思路:把數據行當作map/reduce的key來處理便可。value能夠爲空。app
代碼實現以下:maven
package com.zhm; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; 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; import java.io.IOException; /** * Created by zhm on 2015/7/8. */ public class MapReduceTest { public static class MyMapper extends Mapper<Object, Text, Text, Text> { public void map(Object key, Text value, Context context) throws IOException, InterruptedException { //將文本行放入key context.write(value,new Text("")); } } public static class MyReducer extends Reducer<Text,Text,Text,Text> { public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException { //輸出key context.write(key, new Text("")); } } 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: MapReduceTest <in> <out>"); System.exit(2); } Job job = Job.getInstance(conf, "MapReduceTest"); job.setJarByClass(MapReduceTest.class); job.setMapperClass(MyMapper.class); job.setCombinerClass(MyReducer.class); job.setReducerClass(MyReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
運行:mvn clean package 打好jar包。並上傳至服務器的hadoop安裝目錄中。oop
在服務器上建立須要統計去重的文件。測試
mkdir /tmp/mapred cd /tmp/mapred vi file1.txt #輸入如下內容 192.168.1.1 192.168.1.2 192.168.1.4 vi file2.txt #輸入如下內容 192.168.1.3 192.168.1.2 192.168.1.5 vi file3.txt #輸入如下內容 192.168.1.1 192.168.1.3 192.168.1.4 #清空hdfs目錄,tmp目錄不要刪除。主要是測試方便,也能夠不刪除目錄,只要將文件指定一個新的測試目錄就行。 hdfs dfs -rm -r -f -skipTrash /目錄名 #將建立好的文件上傳至HDFS hdfs dfs -put /tmp/mapred /input #進入hadoop安裝主目錄 hadoop jar maven_hadoop-1.0-SNAPSHOT.jar com.zhm.MapReduceTest /input /output #查看結果 hdfs dfs -cat /output/part-r-00000 #結果以下: 192.168.1.1 192.168.1.2 192.168.1.3 192.168.1.4 192.168.1.5