电商项目实战页面浏览量统计功能升级（十二）

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 {
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 info = logParser.parserv2(log);
context.write(new Text(info.get("pageId")), ONE);
}
}
static class MyReducer extends Reducer {
@Override
protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
long count = 0;
for(LongWritable value: values){
count++;
}
context.write(key, new LongWritable(count));
}
}
}