首先首先要安装Java
首先,到官网下载Hadoop安装包:
http://hadoop.apache.org/->左边点Releases->点mirror site->点http://mirrors.tuna.tsinghua.edu.cn/apache/hadoop/common->下载hadoop-2.9.1.tar.gz
然后,解压到自己喜欢的文件夹即可,我的是路径是E:\hadoop-2.9.1,到http://download.csdn.net/detail/wuxun1997/9841472下载相关工具类(别人的,很好用),直接解压后把文件丢到E:\hadoop-2.9.1\bin,将其中的hadoop.dll在c:\windows/System32下也丢一份;接着设置环境Hadoop的环境变量
接下来做配置(最简单配置)
core-site.xml
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://localhost:9000</value>
</property>
</configuration>
hdfs-site.xml
<configuration>
<property>
<name>dfs.replication</name>
<value>1</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/hadoop/data/dfs/namenode</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/hadoop/data/dfs/datanode</value>
</property>
</configuration>
mapred-site.xml(复制mapred-site-template文件修改文件名即可)
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>
yarn-site.xml
<configuration>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
</configuration>
接下来,进入到etc\hadoop中,修改hadoop-env.cmd中的java路径为你安装Java的路径
配置完成
准备启动Hadoop
进入bin,运行hdfs namenode -format(以后再启动Hadoop就不要执行这个命令,否则可能报错)。进入sbin目录,运行start-all.cmd,出现四个界面,最后输入jps可以看到启动的节点:
至此,Hadoop就启动完成了,这个时候Hadoop里面什么文件都没有,自己可以通过hadoop fs -ls .来查看
接下来在myeclipse中编写mapreduce程序
新建maven项目
在WordCount.java中放入下面代码:
package hadoop;
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
public class WordCount {
public static class Map extends MapReduceBase implements
Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(LongWritable key, Text value,
OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
}
public static class Reduce extends MapReduceBase implements
Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> values,
OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
}
在pom.xml中放入下面代码段:
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>HadoopJar</groupId>
<artifactId>Hadoop</artifactId>
<version>0.0.1-SNAPSHOT</version>
<name>Hadoop</name>
<dependencies>
<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.9.1</version>
</dependency>
<dependency>
<groupId>net.minidev</groupId>
<artifactId>json-smart</artifactId>
<version>2.3</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-core -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<version>2.9.1</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-hdfs -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.9.1</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-common -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-common</artifactId>
<version>2.9.1</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-jobclient -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-jobclient</artifactId>
<version>2.9.1</version>
</dependency>
<dependency>
<groupId>jdk.tools</groupId>
<artifactId>jdk.tools</artifactId>
<version>1.8</version>
<scope>system</scope>
<systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
</dependency>
</dependencies>
<build>
<finalName>Hadoop</finalName>
<plugins>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.8</source>
<target>1.8</target>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-resources-plugin</artifactId>
<configuration>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
</plugins>
</build>
</project>
将项目打包成jar,打包maven项目成Jar有两种方式,第一种右击项目->export->jar file后面设置jar名和存储路径即可,第二种右击项目->run as ->maven install后面东西自己设置即可。
接下来在本地创建目录input在该目录下创建两个文本文件,在hadoop上创建目录input,在input中上传本地的两个文本文件如下:
红框处根据自己的本地input目录所在路径而定
两个文本文件的内容分别为hello world和hello hadoop
上传jar包到Hadoop上,与上传文本文件相同,在Hadoop上执行jar包
红框处 是主函数所在的类,执行完毕看结果(ouput文件夹之前不存在,执行之后才生成)
统计出了单词的数量,至于命令行的编写还是很不懂
还有一种执行mapreduce项目的方法,是在eclipse中装Hadoop插件,待续