数据清洗ETL
代码实现
package com.it.lkw.etl;
public class LogBean {
private String remote_addr;
private String remote_user;
private String time_local;
private String request;
private String status;
private String body_bytes_sent;
private String http_referer;
private String http_user_agent;
private boolean valid = true;
public String getRemote_addr() {
return remote_addr;
}
public void setRemote_addr(String remote_addr) {
this.remote_addr = remote_addr;
}
public String getRemote_user() {
return remote_user;
}
public void setRemote_user(String remote_user) {
this.remote_user = remote_user;
}
public String getTime_local() {
return time_local;
}
public void setTime_local(String time_local) {
this.time_local = time_local;
}
public String getRequest() {
return request;
}
public void setRequest(String request) {
this.request = request;
}
public String getStatus() {
return status;
}
public void setStatus(String status) {
this.status = status;
}
public String getBody_bytes_sent() {
return body_bytes_sent;
}
public void setBody_bytes_sent(String body_bytes_sent) {
this.body_bytes_sent = body_bytes_sent;
}
public String getHttp_referer() {
return http_referer;
}
public void setHttp_referer(String http_referer) {
this.http_referer = http_referer;
}
public String getHttp_user_agent() {
return http_user_agent;
}
public void setHttp_user_agent(String http_user_agent) {
this.http_user_agent = http_user_agent;
}
public boolean isValid() {
return valid;
}
public void setValid(boolean valid) {
this.valid = valid;
}
@Override
public String toString() {
StringBuilder sb = new StringBuilder();
sb.append(this.valid);
sb.append("\t").append(this.remote_addr);
sb.append("\t").append(this.remote_user);
sb.append("\t").append(this.time_local);
sb.append("\t").append(this.request);
sb.append("\t").append(this.status);
sb.append("\t").append(this.body_bytes_sent);
sb.append("\t").append(this.http_referer);
sb.append("\t").append(this.http_user_agent);
return sb.toString();
}
}
package com.it.lkw.etl;
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.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class LogDemo {
public static class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
private Text k = new Text();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
LogBean bean = parseLog(line);
if (!bean.isValid()) {
return;
}
k.set(bean.toString());
context.write(k, NullWritable.get());
}
private LogBean parseLog(String line) {
LogBean logBean = new LogBean();
String[] fields = line.split(" ");
if (fields.length > 11) {
logBean.setRemote_addr(fields[0]);
logBean.setRemote_user(fields[1]);
logBean.setTime_local(fields[3].substring(1));
logBean.setRequest(fields[6]);
logBean.setStatus(fields[8]);
logBean.setBody_bytes_sent(fields[9]);
logBean.setHttp_referer(fields[10]);
if (fields.length > 12) {
logBean.setHttp_user_agent(fields[11] + " " + fields[12]);
} else {
logBean.setHttp_user_agent(fields[11]);
}
if (Integer.parseInt(logBean.getStatus()) >= 400) {
logBean.setValid(false);
}
} else {
logBean.setValid(false);
}
return logBean;
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(LogDemo.class);
job.setMapperClass(LogMapper.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
Path output = new Path(args[1]);
if (FileSystem.get(conf).exists(output)) {
FileSystem.get(conf).delete(output, true);
}
FileInputFormat.setInputPaths(job, args[0]);
FileOutputFormat.setOutputPath(job, output);
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : -1);
}
}