JAVA 上传本地文件到HDFS

步入正题

本地安装的hadoop版本为3.1.3

pom.xml

<properties>
        <java.version>1.8</java.version>
        <spark.version>3.0.0</spark.version>

        <scala.version>2.12.10</scala.version>
        <scala.binary.version>2.12</scala.binary.version>
        <hive.version>2.3.7</hive.version>
        <hadoop.version>3.1.1</hadoop.version>
        <kafka.version>2.4.1</kafka.version>
        <zookeeper.version>3.4.14</zookeeper.version>
        <guava.version>14.0.1</guava.version>
    </properties>

<!--spark框架开始-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
            <exclusions>
                <exclusion>
                    <groupId>org.slf4j</groupId>
                    <artifactId>slf4j-log4j12</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <!--
        Add joda time to ensure that anything downstream which doesn't pull in spark-hive
        gets the correct joda time artifact, so doesn't have auth failures on later Java 8 JVMs
        -->
        <dependency>
            <groupId>joda-time</groupId>
            <artifactId>joda-time</artifactId>
            <scope>compile</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <!--spark框架结束-->
        <!--hadoop开始-->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
            <exclusions>
                <exclusion>
                    <groupId>org.slf4j</groupId>
                    <artifactId>slf4j-log4j12</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <!--hadoop结束-->

HDFSController

package com.example.controller.hdfs;

import com.example.utils.hdfs.HDFSUtils;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;
import org.springframework.web.multipart.MultipartFile;

/**
 * @ClassName HDFSController
 * @Date 2020/8/26 11:41
 */
@RestController
@RequestMapping("/spark/hdfs")
public class HDFSController {

    @GetMapping("/read")
    public String readFile(String fileName) throws Exception {
        return HDFSUtils.readFile(fileName);
    }

    @PostMapping("/upload")
    public void upload(MultipartFile file) throws Exception {
        HDFSUtils.createFile("ypp",file);
    }
}

工具类HDFSUtils

package com.example.utils.hdfs;

import com.alibaba.fastjson.JSONObject;
import com.example.utils.properties.HDFSPropertiesUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.io.IOUtils;
import org.springframework.web.multipart.MultipartFile;

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URI;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

/**
 * @ClassName HDFSUtils
 * @Date 2020/8/26 15:25
 */
public class HDFSUtils {

    private static String hdfsPath;
    private static String hdfsName;
    private static final int bufferSize = 1024 * 1024 * 64;

    static {
        //设置成自己的
        hdfsPath= HDFSPropertiesUtils.getPath();
        hdfsName=HDFSPropertiesUtils.getUserName();
    }

    /**
     * 获取HDFS配置信息
     * @return
     */
    private static Configuration getConfiguration() {
        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS", hdfsPath);
        configuration.set("HADOOP_USER_NAME",hdfsName);
        return configuration;
    }

    /**
     * 获取HDFS文件系统对象
     * @return
     * @throws Exception
     */
    public static FileSystem getFileSystem() throws Exception {
        /*
        //通过这种方式设置java客户端访问hdfs的身份：会以 ypp 的身份访问 hdfs文件系统目录下的路径：/user/ypp 的目录
        System.setProperty("HADOOP_USER_NAME","ypp");
        Configuration configuration = new Configuration();
        configuration.set("fs.defauleFS","hdfs://ypp:9090");
        FileSystem fileSystem = FileSystem.get(configuration);
         */

        /*
        客户端去操作hdfs时是有一个用户身份的，默认情况下hdfs客户端api会从jvm中获取一个参数作为自己的用户身份
        也可以在构造客户端fs对象时，通过参数传递进去
        FileSystem fileSystem = FileSystem.get(new URI(hdfsPath), getConfiguration(), hdfsName);
        */
        FileSystem fileSystem = FileSystem.get(new URI(hdfsPath), getConfiguration());
        return fileSystem;
    }

    /**
     * 在HDFS创建文件夹
     * @param path
     * @return
     * @throws Exception
     */
    public static boolean mkdir(String path) throws Exception {
        if (StringUtils.isEmpty(path)) {
            return false;
        }
        if (existFile(path)) {
            return true;
        }
        FileSystem fs = getFileSystem();
        // 目标路径
        Path srcPath = new Path(path);
        boolean isOk = fs.mkdirs(srcPath);
        fs.close();
        return isOk;
    }

    /**
     * 判断HDFS文件是否存在
     * @param path
     * @return
     * @throws Exception
     */
    public static boolean existFile(String path) throws Exception {
        if (StringUtils.isEmpty(path)) {
            return false;
        }
        FileSystem fs = getFileSystem();
        Path srcPath = new Path(path);
        boolean isExists = fs.exists(srcPath);
        return isExists;
    }

    /**
     * 读取HDFS目录信息
     * @param path
     * @return
     * @throws Exception
     */
    public static List<Map<String, Object>> readPathInfo(String path) throws Exception {
        if (StringUtils.isEmpty(path)) {
            return null;
        }
        if (!existFile(path)) {
            return null;
        }
        FileSystem fs = getFileSystem();
        // 目标路径
        Path newPath = new Path(path);
        FileStatus[] statusList = fs.listStatus(newPath);
        List<Map<String, Object>> list = new ArrayList<>();
        if (null != statusList && statusList.length > 0) {
            for (FileStatus fileStatus : statusList) {
                Map<String, Object> map = new HashMap<>();
                map.put("filePath", fileStatus.getPath());
                map.put("fileStatus", fileStatus.toString());
                list.add(map);
            }
            return list;
        } else {
            return null;
        }
    }

    /**
     * HDFS创建文件
     * @param path
     * @param file
     * @throws Exception
     */
    public static void createFile(String path, MultipartFile file) throws Exception {
        if (StringUtils.isEmpty(path) || null == file.getBytes()) {
            return;
        }
        String fileName = file.getOriginalFilename();
        FileSystem fs = getFileSystem();
        // 上传时默认当前目录，后面自动拼接文件的目录
        Path newPath = new Path(path + "/" + fileName);
        // 打开一个输出流
        FSDataOutputStream outputStream = fs.create(newPath);
        outputStream.write(file.getBytes());
        outputStream.close();
        fs.close();
    }

    /**
     * 读取HDFS文件内容
     * @param path
     * @return
     * @throws Exception
     */
    public static String readFile(String path) throws Exception {
        if (StringUtils.isEmpty(path)) {
            return null;
        }
        if (!existFile(path)) {
            return null;
        }
        FileSystem fs = getFileSystem();
        // 目标路径
        Path srcPath = new Path(path);
        FSDataInputStream inputStream = null;
        try {
            inputStream = fs.open(srcPath);
            // 防止中文乱码
            BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));
            String lineTxt = "";
            StringBuffer sb = new StringBuffer();
            while ((lineTxt = reader.readLine()) != null) {
                sb.append(lineTxt);
            }
            return sb.toString();
        } finally {
            inputStream.close();
            fs.close();
        }
    }

    /**
     * 读取HDFS文件列表
     * @param path
     * @return
     * @throws Exception
     */
    public static List<Map<String, String>> listFile(String path) throws Exception {
        if (StringUtils.isEmpty(path)) {
            return null;
        }
        if (!existFile(path)) {
            return null;
        }

        FileSystem fs = getFileSystem();
        // 目标路径
        Path srcPath = new Path(path);
        // 递归找到所有文件
        RemoteIterator<LocatedFileStatus> filesList = fs.listFiles(srcPath, true);
        List<Map<String, String>> returnList = new ArrayList<>();
        while (filesList.hasNext()) {
            LocatedFileStatus next = filesList.next();
            String fileName = next.getPath().getName();
            Path filePath = next.getPath();
            Map<String, String> map = new HashMap<>();
            map.put("fileName", fileName);
            map.put("filePath", filePath.toString());
            returnList.add(map);
        }
        fs.close();
        return returnList;
    }

    /**
     * HDFS重命名文件
     * @param oldName
     * @param newName
     * @return
     * @throws Exception
     */
    public static boolean renameFile(String oldName, String newName) throws Exception {
        if (StringUtils.isEmpty(oldName) || StringUtils.isEmpty(newName)) {
            return false;
        }
        FileSystem fs = getFileSystem();
        // 原文件目标路径
        Path oldPath = new Path(oldName);
        // 重命名目标路径
        Path newPath = new Path(newName);
        boolean isOk = fs.rename(oldPath, newPath);
        fs.close();
        return isOk;
    }

    /**
     * 删除HDFS文件
     * @param path
     * @return
     * @throws Exception
     */
    public static boolean deleteFile(String path) throws Exception {
        if (StringUtils.isEmpty(path)) {
            return false;
        }
        if (!existFile(path)) {
            return false;
        }
        FileSystem fs = getFileSystem();
        Path srcPath = new Path(path);
        boolean isOk = fs.deleteOnExit(srcPath);
        fs.close();
        return isOk;
    }

    /**
     * 上传HDFS文件
     * @param path
     * @param uploadPath
     * @throws Exception
     */
    public static void uploadFile(String path, String uploadPath) throws Exception {
        if (StringUtils.isEmpty(path) || StringUtils.isEmpty(uploadPath)) {
            return;
        }
        FileSystem fs = getFileSystem();
        // 上传路径
        Path clientPath = new Path(path);
        // 目标路径
        Path serverPath = new Path(uploadPath);

        // 调用文件系统的文件复制方法，第一个参数是否删除原文件true为删除，默认为false
        fs.copyFromLocalFile(false, clientPath, serverPath);
        fs.close();
    }

    /**
     * 下载HDFS文件
     * @param path
     * @param downloadPath
     * @throws Exception
     */
    public static void downloadFile(String path, String downloadPath) throws Exception {
        if (StringUtils.isEmpty(path) || StringUtils.isEmpty(downloadPath)) {
            return;
        }
        FileSystem fs = getFileSystem();
        // 上传路径
        Path clientPath = new Path(path);
        // 目标路径
        Path serverPath = new Path(downloadPath);

        // 调用文件系统的文件复制方法，第一个参数是否删除原文件true为删除，默认为false
        fs.copyToLocalFile(false, clientPath, serverPath);
        fs.close();
    }

    /**
     * HDFS文件复制
     * @param sourcePath
     * @param targetPath
     * @throws Exception
     */
    public static void copyFile(String sourcePath, String targetPath) throws Exception {
        if (StringUtils.isEmpty(sourcePath) || StringUtils.isEmpty(targetPath)) {
            return;
        }
        FileSystem fs = getFileSystem();
        // 原始文件路径
        Path oldPath = new Path(sourcePath);
        // 目标路径
        Path newPath = new Path(targetPath);

        FSDataInputStream inputStream = null;
        FSDataOutputStream outputStream = null;
        try {
            inputStream = fs.open(oldPath);
            outputStream = fs.create(newPath);

            IOUtils.copyBytes(inputStream, outputStream, bufferSize, false);
        } finally {
            inputStream.close();
            outputStream.close();
            fs.close();
        }
    }

    /**
     * 打开HDFS上的文件并返回byte数组
     * @param path
     * @return
     * @throws Exception
     */
    public static byte[] openFileToBytes(String path) throws Exception {
        if (StringUtils.isEmpty(path)) {
            return null;
        }
        if (!existFile(path)) {
            return null;
        }
        FileSystem fs = getFileSystem();
        // 目标路径
        Path srcPath = new Path(path);
        try {
            FSDataInputStream inputStream = fs.open(srcPath);
            return IOUtils.readFullyToByteArray(inputStream);
        } finally {
            fs.close();
        }
    }

    /**
     * 打开HDFS上的文件并返回java对象
     * @param path
     * @return
     * @throws Exception
     */
    public static <T extends Object> T openFileToObject(String path, Class<T> clazz) throws Exception {
        if (StringUtils.isEmpty(path)) {
            return null;
        }
        if (!existFile(path)) {
            return null;
        }
        String jsonStr = readFile(path);
        return JSONObject.parseObject(jsonStr, clazz);
    }

    /**
     * 获取某个文件在HDFS的集群位置
     * @param path
     * @return
     * @throws Exception
     */
    public static BlockLocation[] getFileBlockLocations(String path) throws Exception {
        if (StringUtils.isEmpty(path)) {
            return null;
        }
        if (!existFile(path)) {
            return null;
        }
        FileSystem fs = getFileSystem();
        // 目标路径
        Path srcPath = new Path(path);
        FileStatus fileStatus = fs.getFileStatus(srcPath);
        return fs.getFileBlockLocations(fileStatus, 0, fileStatus.getLen());
    }

}

注意容易出现权限问题，由于开发阶段我都是用的自己windows安装的，HADOOP_USER_NAME直接用的administrator

 

文件内容

上传文件

上传文件 hadoop namenode日志

查看HDFS文件

hadoop fs -ls /user/ypp/ypp #查看指定目录下的文件和文件夹。/user/ypp/ypp 是HDFS上的目录，不是本地目录，命令不分操作系统

查看文件内容

hadoop fs -cat /user/ypp/ypp/111.txt #查看文件内容,这里涉及到中文乱码了(后面补充解决)，同样是HDFS上的目录，不是本地目录，命令不分操作系统

读取文件内容