大数据 | 实验一:大数据系统基本实验 | 熟悉常用的HDFS操作
文章目录
- 📚实验目的
- 📚实验平台
- 📚实验内容
-
- ⭐️HDFSApi
- ⭐️HDFSApi2
- ⭐️HDFSApi3
- ⭐️HDFSApi4
- ⭐️HDFSApi5
- ⭐️HDFSApi6
- ⭐️HDFSApi7
- ⭐️HDFSApi8
- ⭐️HDFSApi9
- ⭐️HDFSApi10
📚实验目的
1)理解 HDFS 在 Hadoop 体系结构中的角色。
2)熟练使用 HDFS 操作常用的 shell 命令。
3)熟悉 HDFS 操作常用的 Java API。
📚实验平台
1)操作系统:Linux;
2)Hadoop 版本:3.2.2;
3)JDK 版本:1.8;
4)Java IDE:Eclipse。
📚实验内容
编程实现以下功能,并利用 Hadoop 提供的 Shell 命令完成相同任务
⭐️HDFSApi
1)向 HDFS 中上传任意文本文件。如果指定的文件在 HDFS 中已经存在,则由用户来指定是追加到原有文件末尾还是覆盖原有的文件;
Shell命令
检查文件是否存在,可以使用如下命令:
cd /usr/local/hadoop
./bin/hdfs dfs -test -e text.txt
#执行完上述命令不会输出结果,需要继续输入以下命令查看结果
echo $?
重启了虚拟机开始做这个实验,一开始出现报错,搜索后发现原来是hadoop没开
echo $?
返回上一个命令的状态,0表示没有错误,其他任何值表明有错误(这里显然出错,因为还没有建text.txt文件夹),手动建一个text.txt然后拖到/usr/local/hadoop。
用户可以选择追加到原来文件末尾或者覆盖原来文件
cd /usr/local/hadoop
./bin/hdfs dfs -appendToFile local.txt text.txt #追加到原文件末尾
#touch local.txt
./bin/hdfs dfs -copyFromLocal -f local.txt text.txt #覆盖原来文件,第一种命令形式
./bin/hdfs dfs -cp -f file:///usr/local/hadoop/local.txt text.txt#覆盖原来文件,第二种命令形式
这样会自动建一个local.txt文件
实际上,也可以不用上述方法,而是采用如下命令来实现
if $(hdfs dfs -test -e text.txt);
then $(hdfs dfs -appendToFile local.txt text.txt);
else $(hdfs dfs -copyFromLocal -f local.txt text.txt);
fi
编程实现
package HDFSApi;
import java.util.Scanner;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
public class HDFSApi
{ /*判断路径是否存在*/public static boolean test(Configuration conf, String path) throws IOException { FileSystem fs = FileSystem.get(conf); return fs.exists(new Path(path)); } /*复制文件到指定路径若路径已存在,则进行覆盖*/public static void copyFromLocalFile(Configuration conf, String localFilePath, String remoteFilePath) throws IOException { FileSystem fs = FileSystem.get(conf); Path localPath = new Path(localFilePath); Path remotePath = new Path(remoteFilePath); /* fs.copyFromLocalFile 第一个参数表示是否删除源文件,第二个参数表示是否覆盖 */fs.copyFromLocalFile(false, true, localPath, remotePath); fs.close(); } /*追加文件内容*/public static void appendToFile(Configuration conf, String localFilePath, String remoteFilePath) throws IOException { FileSystem fs = FileSystem.get(conf); Path remotePath = new Path(remoteFilePath); /* 创建一个文件读入流 */FileInputStream in = new FileInputStream(localFilePath); /* 创建一个文件输出流,输出的内容将追加到文件末尾 */FSDataOutputStream out = fs.append(remotePath); /* 读写文件内容 */byte[] data = new byte[1024]; int read = -1; while ( (read = in.read(data)) > 0 ) { out.write(data, 0, read); } out.close(); in.close(); fs.close(); } /*主函数*/public static void main(String[] args) { Configuration conf = new Configuration();conf.set("fs.default.name","hdfs://localhost:9000"); String localFilePath = "/usr/local/hadoop/local.txt"; String remoteFilePath = "/usr/local/hadoop/text.txt"; String choice = "append";String choice2 = "overwrite"; Scanner in=new Scanner(System.in);String a=in.nextLine();boolean a1= a.contentEquals(choice2);boolean a2=a.contentEquals(choice);//System.out.println(a.contentEquals(choice));//try { /* 判断文件是否存在 */Boolean fileExists = false; if (HDFSApi.test(conf, remoteFilePath)) { fileExists = true; System.out.println(remoteFilePath + " 已存在."); } else { System.out.println(remoteFilePath + " 不存在."); } if ( !fileExists) {//文件不存在,则上传 HDFSApi.copyFromLocalFile(conf, localFilePath, remoteFilePath); System.out.println(localFilePath + " 已上传至 " + remoteFilePath); } else if (a2) {//选择覆盖 HDFSApi.copyFromLocalFile(conf, localFilePath, remoteFilePath); System.out.println(localFilePath + " 已覆盖 " + remoteFilePath); }else if(a1) {//选择追加 HDFSApi.appendToFile(conf, localFilePath, remoteFilePath); System.out.println(localFilePath + " 已追加至 " + remoteFilePath); } }catch (Exception e) { e.printStackTrace(); } }
}
⭐️HDFSApi2
2)从 HDFS 中下载指定文件。如果本地文件与要下载的文件名称相同,则自动对下载的文件重命名;
Shell命令
if $(./bin/hdfs dfs -test -e file:///usr/local/hadoop/text.txt);
then $(./bin/hdfs dfs -copyToLocal text.txt ./text2.txt);
else $(./bin/hdfs dfs -copyToLocal text.txt ./text.txt);
fi
编程实现
package HDFSApi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
public class HDFSApi2
{ /*下载文件到本地判断本地路径是否已存在,若已存在,则自动进行重命名*/public static void copyToLocal(Configuration conf, String remoteFilePath, String localFilePath) throws IOException { FileSystem fs = FileSystem.get(conf); Path remotePath = new Path(remoteFilePath); File f = new File(localFilePath); if(f.exists()) { //如果文件名存在,自动重命名(在文件名后面加上 _0, _1 ...) System.out.println(localFilePath + " 已存在."); Integer i = 0; while (true) { f = new File(localFilePath + "_" + i.toString()); if (!f.exists()) { localFilePath = localFilePath + "_" + i.toString(); break; }} System.out.println("将重新命名为: " + localFilePath); } // 下载文件到本地Path localPath = new Path(localFilePath); fs.copyToLocalFile(remotePath, localPath); fs.close(); } /*主函数*/public static void main(String[] args) { Configuration conf = new Configuration(); conf.set("fs.default.name","hdfs://localhost:9000");String localFilePath = "/usr/local/hadoop/local.txt"; String remoteFilePath = "/usr/local/hadoop/text.txt"; try { HDFSApi2.copyToLocal(conf, remoteFilePath, localFilePath); System.out.println("下载完成"); } catch (Exception e) { e.printStackTrace(); }}
}
⭐️HDFSApi3
3)将 HDFS 中指定文件的内容输出到终端中;
Shell命令
hdfs dfs -cat text.txt
刚开始先跑shell,运行不报错,但无内容输出(但txt里是有内容的)。编程实现跑了一遍,再回去跑shell就有输出了(?
编程实现
package HDFSApi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
public class HDFSApi3
{public static void cat(Configuration conf, String remoteFilePath) throws IOException {/*读取文件内容*/FileSystem fs = FileSystem.get(conf);Path remotePath = new Path(remoteFilePath);FSDataInputStream in = fs.open(remotePath);BufferedReader d = new BufferedReader(new InputStreamReader(in));String line = null;while ( (line = d.readLine()) != null ) {System.out.println(line);}d.close();in.close();fs.close();}/*主函数*/public static void main(String[] args) {Configuration conf = new Configuration();conf.set("fs.default.name","hdfs://localhost:9000");String remoteFilePath = "/usr/local/hadoop/text.txt"; // HDFS 路径try {System.out.println("读取文件: " + remoteFilePath);HDFSApi3.cat(conf, remoteFilePath);System.out.println("\\n 读取完成");} catch (Exception e) {e.printStackTrace();}}
}
⭐️HDFSApi4
4)显示 HDFS 中指定的文件的读写权限、大小、创建时间、路径等信息;
Shell命令
hdfs dfs -ls -h text.txt
编程实现
package HDFSApi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
import java.text.SimpleDateFormat;
public class HDFSApi4
{/*显示指定文件的信息*/public static void ls(Configuration conf, String remoteFilePath) throws IOException {FileSystem fs = FileSystem.get(conf);Path remotePath = new Path(remoteFilePath);FileStatus[] fileStatuses = fs.listStatus(remotePath);for (FileStatus s : fileStatuses) {System.out.println("路径: " + s.getPath().toString());System.out.println("权限: " + s.getPermission().toString());System.out.println("大小: " + s.getLen());/* 返回的是时间戳,转化为时间日期格式 */Long timeStamp = s.getModificationTime();SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");String date = format.format(timeStamp); System.out.println("时间: " + date);}fs.close();}/*** 主函数*/public static void main(String[] args) {Configuration conf = new Configuration();conf.set("fs.default.name","hdfs://localhost:9000");String remoteFilePath = "/usr/local/hadoop/text.txt"; // HDFS 路径try {System.out.println("读取文件信息: " + remoteFilePath);HDFSApi4.ls(conf, remoteFilePath);System.out.println("\\n 读取完成");} catch (Exception e) {e.printStackTrace();}}
}
⭐️HDFSApi5
5)给定 HDFS 中某一个目录,递归输出该目录下的所有文件的读写权限、大小、创建时间、路径等信息;
Shell命令
cd /usr/local/hadoop
./bin/hdfs dfs -ls -R -h /usr/hadoop
编程实现
package HDFSApi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
import java.text.SimpleDateFormat;
public class HDFSApi5
{/*显示指定文件夹下所有文件的信息(递归)*/public static void lsDir(Configuration conf, String remoteDir) throws IOException {FileSystem fs = FileSystem.get(conf);Path dirPath = new Path(remoteDir);/* 递归获取目录下的所有文件 */RemoteIterator<LocatedFileStatus> remoteIterator = fs.listFiles(dirPath, true);/* 输出每个文件的信息 */while (remoteIterator.hasNext()) {FileStatus s = remoteIterator.next();System.out.println("路径: " + s.getPath().toString());System.out.println("权限: " + s.getPermission().toString());System.out.println("大小: " + s.getLen());/* 返回的是时间戳,转化为时间日期格式 */Long timeStamp = s.getModificationTime();SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");String date = format.format(timeStamp); System.out.println("时间: " + date);System.out.println();}fs.close();} /*主函数*/public static void main(String[] args) {Configuration conf = new Configuration();conf.set("fs.default.name","hdfs://localhost:9000");String remoteDir = "/usr/hadoop"; // HDFS 路径try {System.out.println("(递归)读取目录下所有文件的信息: " + remoteDir);HDFSApi5.lsDir(conf, remoteDir);System.out.println("读取完成");} catch (Exception e) {e.printStackTrace();}}
}
⭐️HDFSApi6
6)提供一个 HDFS 内的文件的路径,对该文件进行创建和删除操作。如果文件所在目录不存在,则自动创建目录;
Shell命令
if $(hdfs dfs -test -d dir1/dir2);
then $(hdfs dfs -touchz dir1/dir2/filename);
else $(hdfs dfs -mkdir -p dir1/dir2 && hdfs dfs -touchz dir1/dir2/filename);
fi
hdfs dfs -rm dir1/dir2/filename #删除文件
编程实现
路径存在的情况(以下代码是路径存在的情况)
路径不存在的情况
目录不存在的情况
package HDFSApi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
public class HDFSApi6
{/*判断路径是否存在*/public static boolean test(Configuration conf, String path) throws IOException {FileSystem fs = FileSystem.get(conf);return fs.exists(new Path(path));}/*创建目录*/public static boolean mkdir(Configuration conf, String remoteDir) throws IOException {FileSystem fs = FileSystem.get(conf);Path dirPath = new Path(remoteDir);boolean result = fs.mkdirs(dirPath);fs.close();return result;}/*创建文件*/public static void touchz(Configuration conf, String remoteFilePath) throws IOException {FileSystem fs = FileSystem.get(conf);Path remotePath = new Path(remoteFilePath);FSDataOutputStream outputStream = fs.create(remotePath);outputStream.close();fs.close();} /*删除文件*/public static boolean rm(Configuration conf, String remoteFilePath) throws IOException {FileSystem fs = FileSystem.get(conf);Path remotePath = new Path(remoteFilePath);boolean result = fs.delete(remotePath, false);fs.close();return result;}/*主函数*/public static void main(String[] args) {Configuration conf = new Configuration();conf.set("fs.default.name","hdfs://localhost:9000");String remoteFilePath = "/usr/local/hadoop/text.txt"; // HDFS 路径String remoteDir = "/usr/hadoop/input"; // HDFS 路径对应的目录try {/* 判断路径是否存在,存在则删除,否则进行创建 */if ( HDFSApi6.test(conf, remoteFilePath) ) {HDFSApi6.rm(conf, remoteFilePath); // 删除System.out.println("删除路径: " + remoteFilePath);} else {if ( !HDFSApi6.test(conf, remoteDir) ) { // 若目录不存在,则进行创建HDFSApi6.mkdir(conf, remoteDir);System.out.println("创建文件夹: " + remoteDir);}HDFSApi6.touchz(conf, remoteFilePath);System.out.println("创建路径: " + remoteFilePath);}} catch (Exception e) {e.printStackTrace();}}
}
⭐️HDFSApi7
7)提供一个 HDFS 的目录的路径,对该目录进行创建和删除操作。创建目录时,如果目录文件所在目录不存在,则自动创建相应目录;删除目录时,当该目录为空时删除,当该目录不为空时不删除该目录;
Shell命令
cd /usr/local/hadoop
./bin/hdfs dfs -mkdir -p dir1/dir2
./bin/hdfs dfs -rmdir dir1/dir2
#若为非空目录,强制删除语句如下
./bin/hdfs dfs -rm -R dir1/dir2
编程实现
目录不存在于是创建
目录存在且为空,删除
package HDFSApi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
public class HDFSApi7
{/*判断路径是否存在*/public static boolean test(Configuration conf, String path) throws IOException {//访问获取hdfs文件系统数据FileSystem fs = FileSystem.get(conf);return fs.exists(new Path(path));}/*判断目录是否为空true: 空,false: 非空*/public static boolean isDirEmpty(Configuration conf, String remoteDir) throws IOException {FileSystem fs = FileSystem.get(conf);Path dirPath = new Path(remoteDir);//获取hdfs文件路径RemoteIterator<LocatedFileStatus> remoteIterator = fs.listFiles(dirPath, true);//获取当前路径下的文件,得到file类型的数组return !remoteIterator.hasNext();//hasNext表示文件有内容,用这个判断目录是否为空}/*创建目录*/public static boolean mkdir(Configuration conf, String remoteDir) throws IOException {FileSystem fs = FileSystem.get(conf);Path dirPath = new Path(remoteDir);boolean result = fs.mkdirs(dirPath);//mkdirs,创建fs.close();return result;}/*删除目录*/public static boolean rmDir(Configuration conf, String remoteDir) throws IOException {FileSystem fs = FileSystem.get(conf);//访问获取hdfs文件系统数据Path dirPath = new Path(remoteDir);//获取hdfs文件路径/* 第二个参数表示是否递归删除所有文件 */boolean result = fs.delete(dirPath, true);//delete,删除fs.close();return result;}/*主函数*/public static void main(String[] args) {Configuration conf = new Configuration();conf.set("fs.default.name","hdfs://localhost:9000"); String remoteDir = "/usr/hadoop/test/dir"; Boolean forceDelete = false; try {/* 判断目录是否存在,不存在则创建,存在则删除 */if ( !HDFSApi7.test(conf, remoteDir) ) {HDFSApi7.mkdir(conf, remoteDir); //创建System.out.println("创建目录: " + remoteDir);} else {if ( HDFSApi7.isDirEmpty(conf, remoteDir) || forceDelete ) { // 目录为空或强制删除HDFSApi7.rmDir(conf, remoteDir);System.out.println("删除目录: " + remoteDir);} else { // 目录不为空System.out.println("目录不为空,不删除: " + remoteDir);}}} catch (Exception e) {e.printStackTrace();}}
}
⭐️HDFSApi8
8)向 HDFS 中指定的文件追加内容,由用户指定内容追加到原有文件的开头或结尾;
Shell命令
#追加到原文件末尾
cd /usr/local/hadoop
hdfs dfs -appendToFile local.txt text.txt
#追加到原文件开头
hdfs dfs -get text.txt
cat text.txt >> local.txt
hdfs dfs -copyFromLocal -f local.txt text.txt
编程实现
package HDFSApi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
import java.util.Scanner;
public class HDFSApi8
{/*判断路径是否存在*/public static boolean test(Configuration conf, String path) throws IOException {FileSystem fs = FileSystem.get(conf);return fs.exists(new Path(path));}/*追加文本内容*/public static void appendContentToFile(Configuration conf, String content, String remoteFilePath) throws IOException {FileSystem fs = FileSystem.get(conf);//获取数据Path remotePath = new Path(remoteFilePath);//获取路径/* 创建一个文件输出流,输出的内容将追加到文件末尾 */FSDataOutputStream out = fs.append(remotePath);//追加文件内容out.write(content.getBytes());//把字符串转化为字节数组out.close();fs.close();}/*追加文件内容*/public static void appendToFile(Configuration conf, String localFilePath, String remoteFilePath) throws IOException {FileSystem fs = FileSystem.get(conf);//获取数据Path remotePath = new Path(remoteFilePath);//获取路径/* 创建一个文件读入流 */FileInputStream in = new FileInputStream(localFilePath);/* 创建一个文件输出流,输出的内容将追加到文件末尾 */FSDataOutputStream out = fs.append(remotePath);/* 读写文件内容 */byte[] data = new byte[1024];int read = -1;if(in!=null){while ( (read = in.read(data)) > 0 ) {out.write(data, 0, read);}}out.close();in.close();fs.close();}/*移动文件到本地移动后,删除源文件*/public static void moveToLocalFile(Configuration conf, String remoteFilePath, String localFilePath) throws IOException {FileSystem fs = FileSystem.get(conf);//获取数据Path remotePath = new Path(remoteFilePath);//获取路径Path localPath = new Path(localFilePath);//获取路径fs.moveToLocalFile(remotePath, localPath);//移动文件到本地}/*创建文件*/public static void touchz(Configuration conf, String remoteFilePath) throws IOException { FileSystem fs = FileSystem.get(conf);//获取数据Path remotePath = new Path(remoteFilePath);//获取路径FSDataOutputStream outputStream = fs.create(remotePath);//创建输出文件outputStream.close();fs.close();}/*主函数*/public static void main(String[] args) {Configuration conf = new Configuration();conf.set("fs.default.name","hdfs://localhost:9000"); conf.set("dfs.client.block.write.replace-datanode-on-failure.policy","NEVER");String remoteFilePath = "/usr/local/hadoop/text.txt"; // HDFS 文件,output fileString content = "新追加的内容\\n";String choice = "after"; //追加到文件末尾String choice2 = "before"; //追加到文件开头Scanner in=new Scanner(System.in);//输入流String a=in.nextLine();boolean a1= a.contentEquals(choice2);//判断内容是否相等boolean a2=a.contentEquals(choice);//判断内容是否相等try {/* 判断文件是否存在 */if ( !HDFSApi8.test(conf, remoteFilePath) ) {//路径不存在System.out.println("文件不存在: " + remoteFilePath);} else {//有这个文件if ( a2 ) { // 追加在文件末尾HDFSApi8.appendContentToFile(conf, content, remoteFilePath);System.out.println("已追加内容到文件末尾" + remoteFilePath);} else if ( a1 ) { //追加到文件开头/* 没有相应的 api 可以直接操作,因此先把文件移动到本地*//*创建一个新的 HDFS,再按顺序追加内容 */String localTmpPath = "/usr/local/hadoop/tmp.txt";// 移动到本地HDFSApi8.moveToLocalFile(conf, remoteFilePath, localTmpPath);// 创建一个新文件HDFSApi8.touchz(conf, remoteFilePath); // 先写入新内容HDFSApi8.appendContentToFile(conf, content, remoteFilePath);// 再写入原来内容HDFSApi8.appendToFile(conf, localTmpPath, remoteFilePath); System.out.println("已追加内容到文件开头: " + remoteFilePath);}}} catch (Exception e) {e.printStackTrace();}}
}
⭐️HDFSApi9
9)删除 HDFS 中指定的文件;
Shell命令
hdfs dfs -rm text.txt
编程实现
package HDFSApi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
public class HDFSApi9
{/*删除文件*/public static boolean rm(Configuration conf, String remoteFilePath) throws IOException {FileSystem fs = FileSystem.get(conf);Path remotePath = new Path(remoteFilePath);boolean result = fs.delete(remotePath, false);fs.close();return result;}/*主函数*/public static void main(String[] args) {Configuration conf = new Configuration();conf.set("fs.default.name","hdfs://localhost:9000"); String remoteFilePath = "/usr/local/hadoop/text.txt"; // HDFS 文件try {if ( HDFSApi9.rm(conf, remoteFilePath) ) {System.out.println("文件删除: " + remoteFilePath);} else {System.out.println("操作失败(文件不存在或删除失败)");}} catch (Exception e) {e.printStackTrace();}}
}
⭐️HDFSApi10
10)在 HDFS 中,将文件从源路径移动到目的路径。
Shell命令
第九题刚好把text.txt删了,这里用的是上头建的dir(shell和编程实现移来移去了属于是
hdfs dfs -mv /usr/dir /usr/hadoop/test
编程实现
(两种情况)
package HDFSApi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import java.util.Scanner;public class HDFSApi10
{public static void main(String[] args) {try {Scanner in = new Scanner(System.in);System.out.println("请输入你要移动的文件地址");Path srcPath = new Path(in.next());System.out.println("请输入你的文件移动目的地址");Path dstPath = new Path(in.next());Configuration conf = new Configuration(); conf.set("fs.default.name","hdfs://localhost:9000"); FileSystem fs = FileSystem.get(conf);if (!fs.exists(srcPath)) {System.out.println("操作失败(源文件不存在或移动失败)");} else {fs.rename(srcPath, dstPath);System.out.println(" 将文件 " + srcPath + " 移动到 " +dstPath);}in.close();}catch (Exception e) {e.printStackTrace();}}
}
把HDFSApi(就第一题)编程部分重新跑一边后边的就能重新调试。