hadoop配置Windows环境与JAVA开发API

环境配置

Windows依赖包，拷贝hadoop-3.1.0到非中文路径（比如d:\）

https://gitee.com/eeasy/hadoop_windows_dependency/repository/archive/master.zip

配置HADOOP_HOME环境变量

配置Path环境变量 %HADOOP_HOME%\bin

检测微软运行库

用管理方式打开PowerShell，进入D:\hadoop-3.1.0\bin，执行.\winutils.exe

操作Hdfs代码

pom.xml

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.30</version>
        </dependency>
    </dependencies>

配置日志 log4j.properties

log4j.rootLogger=INFO, stdout  
log4j.appender.stdout=org.apache.log4j.ConsoleAppender  
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout  
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n  
log4j.appender.logfile=org.apache.log4j.FileAppender  
log4j.appender.logfile.File=target/spring.log  
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout  
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

编写类HdfsClient

package com.chen;

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

import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;

public class HdfsClient {
    private FileSystem fileSystem;

    //初始化
    @Before
    public void init() throws URISyntaxException, IOException, InterruptedException {
        //配置连接地址
        URI uri = new URI("hdfs://hadoop100:8020");
        //创建配置文件
        Configuration configuration = new Configuration();
        String user = "root";
        //获取客户端
        fileSystem = FileSystem.get(uri, configuration, user);
    }

    //关闭连接
    @After
    public void close() throws IOException {
        fileSystem.close();
    }

    //创建目录
    @Test
    public void mkdirs() throws IOException {
        //创建文件夹
        fileSystem.mkdirs(new Path("/chen"));
    }

    //上传文件
    @Test
    public void put() throws IOException {
        fileSystem.copyFromLocalFile(false, true, new Path("D://chen.txt"), new Path("/chen"));
    }
}

修改参数

参数优先级排序：客户端代码中的值 > Classpath（src/main/resources）下的用户自定义配置文件 >服务器自定义配置（安装目录/etc/hadoop/xxx-site.xml）> 服务器默认配置（安装目录/share/doc/hadoop/xxx/xxx/xxx-default.xml）

将hdfs-site.xml拷贝到项目的resources资源目录下，修改副本数

<configuration>
    <property>
        <name>dfs.replication</name>
        <value>1</value>
    </property>
</configuration>

修改完变为1