练习内容

任务一：HDFS API连接测试；

1、Test类测试连接；

关键代码：

package org.gy.myhadoop.mr;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IOUtils;import org.junit.Before;import java.io.FileOutputStream;import java.io.IOException;import java.io.InputStream;import java.io.OutputStream;import java.net.URI;import java.net.URISyntaxException;/**** @author yanxukun* @date 2019年3月7日 上午11:46:23*/public class Test {@Beforepublic static void main(String[] args )throws Exception{System.out.println("Hello World!");Configuration conf = new Configuration();conf.set("fs.defaultFS","hdfs://192.168.10.111:9000");FileSystem fs = null;fs = FileSystem.get(conf);fs.mkdirs(new Path("hdfs://192.168.10.111:9000/user/input/test2"));}}

运行结果：

任务二：单元测试的setUp和tearDown方法

关键代码：

package org.gy.myhadoop.mr;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IOUtils;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.*;import org.junit.Before;import org.junit.After;import org.junit.Test;public class HDFSApp {public static final String HDFS_PATH = "hdfs://192.168.10.111:9000";public static Configuration configuration = null;public static FileSystem fileSystem = null;@Beforepublic void setUp() throws Exception {System.out.println("HDFSApp.setUp()");configuration = new Configuration();configuration.set("fs.defaultFS", "hdfs://192.168.10.111:9000");fileSystem = FileSystem.get(configuration);}@Afterpublic void tearDown() throws Exception{fileSystem = null;configuration = null;System.out.println("HDFSApp.tearDown()");}@Testpublic void rename() throws Exception{Path oldPath = new Path("hdfs://192.168.10.111:9000/user/test/a.txt");Path newPath = new Path("hdfs://192.168.10.111:9000/user/test/b.txt");System.out.println(fileSystem.rename(oldPath, newPath));}@Testpublic void copyFromLocalFile() throws Exception{Path src = new Path("C:/luke/hello.txt");Path dist = new Path("hdfs://192.168.10.111:9000/user/test/");fileSystem.copyFromLocalFile(src, dist);}@Testpublic void listFiles() throws Exception{FileStatus[] listStatus = fileSystem.listStatus(new Path("hdfs://192.168.2.100:9000/user/test"));for (FileStatus fileStatus : listStatus) {String isDir = fileStatus.isDirectory() ? "文件夹" : "文件";String permission = fileStatus.getPermission().toString();short replication = fileStatus.getReplication();long len = fileStatus.getLen();String path = fileStatus.getPath().toString();System.out.println(isDir+"\t"+permission+"\t"+replication+"\t"+len+"\t"+path);}}}

运行结果：

任务三：SequenceFile的基本操作

1、SequenceFile文件的写操作；

关键代码：

package org.gy.myhadoop.mr;import java.io.IOException;import java.text.SimpleDateFormat;import java.util.Date;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IOUtils;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.SequenceFile;import org.apache.hadoop.io.Text;public class SequenceFileWriter {private static Configuration configuration = new Configuration();private static String url = "hdfs://192.168.10.111:9000";private static String[] data = {"a,b,c,d,e,f,g","e,f,g,h,i,j,k","l,m,n,o,p,q,r,s","t,u,v,w,x,y,z"};public static void main(String[] args) throws Exception {FileSystem fs = FileSystem.get(configuration);Path outputPath = new Path("MySequenceFile.seq");IntWritable key = new IntWritable();Text value = new Text();SequenceFile.Writer writer = SequenceFile.createWriter(fs, configuration, outputPath, IntWritable.class, Text.class);for (int i=0;i<10;i++) {key.set(10-i);value.set(data[i%data.length]);writer.append(key, value);}IOUtils.closeStream(writer);Date day = new Date();SimpleDateFormat df = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");System.out.println("计算机161燕旭坤在"+df.format(day)+"完成");}}

运行结果：

2、SequenceFile读操作；

关键代码：

package org.gy.myhadoop.mr;import java.io.IOException;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IOUtils;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.SequenceFile;import org.apache.hadoop.io.Text;import org.apache.hadoop.io.Writable;import org.apache.hadoop.util.ReflectionUtils;public class SequenceFileReader{private static Configuration configuration = new Configuration();private static String url = "hdfs://192.168.10.111:9000";public static void main(String[] args) throws Exception{FileSystem fs = FileSystem.get(configuration);Path inputPath = new Path("MySequenceFile.seq");SequenceFile.Reader reader = new SequenceFile.Reader(fs,inputPath, configuration);Writable keyClass = (Writable) ReflectionUtils.newInstance(reader.getKeyClass(), configuration);Writable valueClass = (Writable) ReflectionUtils.newInstance(reader.getValueClass(), configuration);while(reader.next(keyClass,valueClass)){System.out.println("key:"+keyClass);System.out.println("value:"+valueClass);System.out.println("position:"+reader.getPosition());}IOUtils.closeStream(reader);}}

运行结果：

任务四：MapFile的基本操作

1、MapFile的写操作；

关键代码：

package org.gy.myhadoop.mr;import java.io.IOException;import java.net.URI;import java.text.SimpleDateFormat;import java.util.Date;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IOUtils;import org.apache.hadoop.io.MapFile;import org.apache.hadoop.io.Text;public class MapFileWriter {static Configuration configuration = new Configuration();private static String url = "hdfs://192.168.10.111:9000";public static void main(String[] args) throws Exception {FileSystem fs = FileSystem.get(URI.create(url),configuration);Path outPath = new Path("MyMapFile.map");Text key = new Text();key.set("mymapkey");Text value = new Text();value.set("mymapvalue");MapFile.Writer writer = new MapFile.Writer(configuration, fs,outPath.toString(),Text.class,Text.class);writer.append(key, value);IOUtils.closeStream(writer);Date day = new Date();SimpleDateFormat df = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");System.out.println("计算机161燕旭坤在"+df.format(day)+"完成");}}

运行结果：

2、MapFile的读操作；

关键代码：

package org.gy.myhadoop.mr;import java.io.IOException;import java.net.URI;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IOUtils;import org.apache.hadoop.io.MapFile;import org.apache.hadoop.io.Text;import org.apache.hadoop.io.Writable;import org.apache.hadoop.io.WritableComparable;import org.apache.hadoop.util.ReflectionUtils;public class MapFileReader {static Configuration configuration = new Configuration();private static String url = "hdfs://192.168.10.111:9000";public static void main(String[] args) throws Exception {FileSystem fs = FileSystem.get(URI.create(url),configuration);Path inPath = new Path("MyMapFile.map");MapFile.Reader reader  = new MapFile.Reader(fs,inPath.toString(),configuration);Writable keyclass = (Writable) ReflectionUtils.newInstance(reader.getKeyClass(), configuration);Writable valueclass = (Writable) ReflectionUtils.newInstance(reader.getValueClass(), configuration);while(reader.next((WritableComparable) keyclass,valueclass)) {System.out.println(keyclass);System.out.println(valueclass);}IOUtils.closeStream(reader);}}

运行结果：

出现的问题与解决方案

排错一：JavaAPI操作HDFS文件系统报错，Connection refused

错误：在WIN10系统下使用IDEA操作部HDFS系统时报错java.net.ConnectException:Connection refused:no，我们要首先检查以下设置是否正确；

排错思路：

1.虚拟机的防火墙需要关闭

2.虚拟机和物理机需要互相ping通。

3.虚拟机HDFS的Hadoop目录下的etc/hadoop/core-site.xml配置正确

4.物理机C:\Windows\System32\drivers\etc\hosts需要配置虚拟机ip和主机名的映射

在以上几步均正确的情况下，依然报错，那么检查下虚拟机的主机名是不是localhost（我当时把localhost改成hadoop之后问题解决），如果是的话，建议换成别的

排错二：

错误：ava.lang.IllegalArgumentException: Wrong FS: hdfs://master:9000/test.txt, expected: file:///   at org.apache.hadoop.fs.FileSystem.checkPath(FileSystem.java:648)

原因： 默认读取file:///..., 其中的core-site.xml文件，我们没有配置，所以得

解决：在工程下创建core-site.xml，将虚拟机master的core-site.xml复制到工程 下 的 core- site.xml.

排错三：

错误：org.apache.hadoop.hdfs.protocol.DSQuotaExceededException:

 The DiskSpace quota of /spaceQuota is exceeded: quota = 402653184 B = 384 MB but diskspace consumed = 402653220 B = 384.00 MB

原因：文件的空间配额做出了限制，导致不能进行写操作

解决：2个

$> hdfs dfsadmin -setSpaceQuota  384p /spaceQuota  //增大空间配额

$>hadoop dfsadmin -clrSpaceQuota /user/hadoop        //清除空间配额的限制