玩转linux主机--hadoop伪分布式配置及单词计数程序的运行

设置sudo权限

su
vi /etc/sudoers

在root ALL=(ALL) ALL
增加一行

用户名 ALL=(ALL)   ALL

ssh免密码登录

ssh localhost

cd ~/.ssh/                    
ssh-keygen -t rsa
一直回车即可


cat id_rsa.pub >> authorized_keys  
chmod 600 ./authorized_keys   权限问题

jdk安装

tar -zxvf jdk-8u77-linux-x64.tar.gz 
sudo vi /etc/profile

export JAVA_HOME=/home/yushengyun/jdk1.8.0_77
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
export PATH=$JAVA_HOME/bin:$PATH

source /etc/profile

java -version

hadoop安装

tar -zxvf hadoop-2.6.2.tar.gz 
sudo vi /etc/profile

Hadoop Environment Variables

    export HADOOP_HOME=/usr/local/hadoop
    export HADOOP_INSTALL=$HADOOP_HOME
    export HADOOP_MAPRED_HOME=$HADOOP_HOME
    export HADOOP_COMMON_HOME=$HADOOP_HOME
    export HADOOP_HDFS_HOME=$HADOOP_HOME
    export YARN_HOME=$HADOOP_HOME
    export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
    export PATH=$PATH:$HADOOP_HOME/sbin:$HADOOP_HOME/bin

source /etc/profile

core-site.xml

    <configuration>
        <property>
            <name>hadoop.tmp.dir</name>
            <value>file:/home/yushengyun/hadoop-2.6.2/tmp</value>
            <description>Abase for other temporary directories.</description>
        </property>
        <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:/home/yushengyun/hadoop-2.6.2/tmp/dfs/name</value>
        </property>
        <property>
            <name>dfs.datanode.data.dir</name>
            <value>file:/home/yushengyun/hadoop-2.6.2/tmp/dfs/data</value>
        </property>
    </configuration>

hadoop namenode -format

然后我们启动hadoop

进入hadoop文件夹
执行./sbin/start-dfs.sh

jps

在用户文件夹下创建
mkdir word_count
mkdir word_input

我们创建等会使用单词计数的文件

cd word_input/
vi word.txt

javac -classpath /home/yushengyun/hadoop-2.6.2/share/hadoop/common/hadoop-common-2.6.2.jar:/home/yushengyun/hadoop-2.6.2/share/hadoop/common/lib/commons-cli-1.2.jar:/home/yushengyun/hadoop-2.6.2/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.6.2.jar -d /home/yushengyun/word_count// WordCount.java 

jar -cvf wordcount.jar *.class
hadoop fs -mkdir word_input
hadoop fs -put word_input/word.txt word_input/
hadoop jar word_count/wordcount.jar WordCount word_input word_output
hadoop fs -ls word_output
hadoop fs -cat word_output/part-r-00000

java程序

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
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.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class WordCount {
    public static class WordCountMap extends
            Mapper<LongWritable, Text, Text, IntWritable> {
        private final IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            String line = value.toString();
            StringTokenizer token = new StringTokenizer(line);
            while (token.hasMoreTokens()) {
                word.set(token.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class WordCountReduce extends
            Reducer<Text, IntWritable, Text, IntWritable> {
        public void reduce(Text key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            context.write(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = new Job(conf);
        job.setJarByClass(WordCount.class);
        job.setJobName("wordcount");
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setMapperClass(WordCountMap.class);
        job.setReducerClass(WordCountReduce.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
}