电商实战——Hadoop实现Day3

继续问题二

编写LogAnalysisDriver.java类

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class LogAnalysisDriver {

    public static void main(String[] args) throws Exception {
        if (args.length != 2) {
            System.err.println("Usage: LogAnalysisDriver <input path> <output path>");
            System.exit(-1);
        }

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Page View Count");

        job.setJarByClass(LogAnalysisDriver.class);
        job.setMapperClass(PageViewMapper.class);
        job.setCombinerClass(PageViewReducer.class);
        job.setReducerClass(PageViewReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

编写Mapper类

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class PageViewMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

    private static final IntWritable one = new IntWritable(1);
    private Text city = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // Split the input line into fields based on the delimiter
        String[] fields = value.toString().split("\u0001");

        if (fields.length > 13) {
            // Assuming the IP address is in the 14th field (index 13)
            String ip = fields[13];
            IPParser ipParser = IPParser.getInstance();
            IPParser.RegionInfo regionInfo = ipParser.analyseIp(ip);

            String province = regionInfo.getProvince(); // Get province from RegionInfo
            if (province != null) { // Check if province is not null
                context.write(new Text(province), new IntWritable(1));
            }
        }
    }

}

 编写reducer类

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class PageViewReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    private final IntWritable result = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable val : values) {
            sum += val.get();
        }
        result.set(sum);
        context.write(key, result);
    }
}

 以上是对项目二第二问的实现过程

三、将编写的MapReduce程序打包并上传，启动集群的Linux系统，运行结果

 （1）Idea中打包 java程序可参考往期内容

 （2）运行程序

在运行程序之前，需要启动Hadoop，命令如下：

cd /usr/local/hadoop  //hadoop目录
./sbin/start-dfs.sh

 在启动Hadoop之后，需要首先删除HDFS中与当前Linux用户hadoop对应的input和output目录

cd /usr/local/hadoop
./bin/hdfs dfs -rm -r etcinput
./bin/hdfs dfs -rm -r etcoutput

然后，再在HDFS中新建与当前Linux用户hadoop对应的input目录，即“/user/hadoop/input”目录，具体命令如下：

cd /usr/local/hadoop
./bin/hdfs dfs -mkdir etcinput

然后，把之前的文件trackinfo_20130721.txt上传到HDFS中的“/user/hadoop/input”目录下，命令如下：

cd /usr/local/hadoop
./bin/hdfs dfs -put ./trackinfo_20130721.txt etcinput

现在，就可以在Linux系统中，使用hadoop jar命令运行程序，命令如下：

cd /usr/local/hadoop
./bin/hadoop jar ./Log2.jar etcinput etcoutput

上面命令执行以后，当运行顺利结束时，HDFS中output目录下出现以下文件证明成功：

文件详情内容：