大数据第二课-HDFS Java API开发

1、配置windows当中的环境变量

解压资料当中的 hadoop-2.6.0-cdh5.14.2_windows环境配置安装包.rar 这个压缩文件文件到一个没有中文没有空格的目录下

 

 

然后在windows当中配置hadoop的环境变量

然后将hadoop.dll文件拷贝到C:\Windows\System32

注意 如果没有 配置好windows的hadoop的环境变量，那么就会报以下错误

 

 

 二、创建Maven工程并导入jar包

1、首先，需要配置Maven的本地仓库，远程仓库，安装路径等（具体参考别人的博客）

 

 

 2、创建Maven工程，导入jar包

创建工程参考别人博客，我这只给下面的 pom.xml 文件内容（最好在没网的时候创建，不要Enable import Automatic，我这之前老是自动加载包出错）

    <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0-mr1-cdh5.14.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.6.0-cdh5.14.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.6.0-cdh5.14.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.6.0-cdh5.14.2</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/junit/junit -->
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>7.0.0</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                    <!--   <verbal>true</verbal>-->
                </configuration>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <minimizeJar>true</minimizeJar>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

 然后在下面这个文件下创建  .java  文件

 

 HdfsOpreate.java的内容如下：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.junit.Test;

import java.io.IOException;

public class HdfsOpreate {

    @Test
    public void mkdirToHdfs() throws IOException {
        Configuration configuration = new Configuration();
        //如果是操作hdfs上面的文件，一定要配置fs.defaultFS
        configuration.set("fs.defaultFS","hdfs://node01:8020");
        FileSystem fileSystem = FileSystem.get(configuration);
        fileSystem.mkdirs(new Path("/kaikeba/dir2"));
        fileSystem.close();
    }

    @Test
    public void uploadFile() throws IOException {
        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://node01:8020");
        FileSystem fileSystem = FileSystem.get(configuration);
        fileSystem.copyFromLocalFile(new Path("E:\\BigDataCode\\Java\\data\\wc\\input\\text1.txt"),new Path("hdfs://node01:8020/kaikeba/dir2"));
        fileSystem.close();
    }

    @Test
    public void downloadFile() throws IOException {
        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://node01:8020");
        FileSystem fileSystem = FileSystem.get(configuration);
        fileSystem.copyToLocalFile(new Path("hdfs://node01:8020/kaikeba/dir1/word.txt"),new Path("E:\\BigDataCode\\Java\\data\\word2.txt"));
        fileSystem.close();
    }

    

}

然后执行代码。