用MR统计页面浏览量页面编号功能

package project.mr;

import com.imooc.bigdata.hadoop.hdfs.mr.project.utils.ContentUtils;
import com.imooc.bigdata.hadoop.hdfs.mr.project.utils.LogParser;
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 javax.naming.Context;
import java.io.IOException;
import java.util.Map;

public class PageStatApp {

    // Driver端的代码：八股文
    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();

        // 如果输出目录已经存在，则先删除
        FileSystem fileSystem = FileSystem.get(configuration);
        Path outputPath = new Path("output/v1/pagestat");
        if (fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath, true);
        }

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

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

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

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


        FileInputFormat.setInputPaths(job, new Path("input/trackinfo_20130721.data"));

        FileOutputFormat.setOutputPath(job, new Path("output/v1/pagestat"));

        job.waitForCompletion(true);
    }

    static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

        private LogParser parser;
        private LongWritable ONE = new LongWritable(1);

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

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String log = value.toString();
            Map<String, String> logInfo = parser.parse(log);
            String url = logInfo.get("url");
            String pageId = ContentUtils.getPageId(url);
            context.write(new Text(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 access : values) {
                count++;
            }
            context.write(key, new LongWritable(count));

        }
    }

}