标签：浏览量 hadoop job org apache import 电商 class 页面

1、PageStartV2App.java

src/main/java/project/mrv2/PageStartV2App.java

与ProvinceStartV2App.java相同

重要的是使用logParser.parserv2(log)，然后使用pageId作为key值

package project.mrv2;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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.output.FileOutputFormat;
import project.mrv1.ProvinceStartApp;
import project.utils.ContentUtils;
import project.utils.LogParser;

import java.io.IOException;
import java.util.Map;

public class PageStartV2App {

    public static void main(String[] args) throws Exception{

        Configuration configuration = new Configuration();

        FileSystem fileSystem = FileSystem.get(configuration);
        Path outputPath = new Path("output/v2/pagestart");
        if (fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath, true);
        }

        Job job = Job.getInstance(configuration);
        job.setJarByClass(ProvinceStartApp.class);

        job.setMapperClass(PageStartV2App.MyMapper.class);
        job.setReducerClass(PageStartV2App.MyReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

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

        FileInputFormat.setInputPaths(job, new Path("input/etl"));
        FileOutputFormat.setOutputPath(job, new Path("output/v2/pagestart"));

        job.waitForCompletion(true);

    }

    static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
        private LongWritable ONE = new LongWritable(1);
        private LogParser logParser;

        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            logParser = new LogParser();
        }

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            //value：是日志
            //拿到日志
            String log = value.toString();
            //将日志传进来
            Map<String, String> info = logParser.parserv2(log);
            context.write(new Text(info.get("pageId")), ONE);
        }
    }

    static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
            long count = 0;
            for(LongWritable value: values){
                count++;
            }
            context.write(key, new LongWritable(count));
        }
    }

}

标签：浏览量,hadoop,job,org,apache,import,电商,class,页面
来源： https://www.cnblogs.com/jieqiong1755/p/15066108.html

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。