本次接上一篇,进行实际数据的获取和预处理,会有较多的代码内容
数据采集的需求广义上来说分为两大部分。
#!/bin/bash
#设置日志文件存放目录
logs_path="/usr/local/nginx/logs/"
#设置 pid 文件
pid_path="/usr/local/nginx/nginx-1.7.3/logs/nginx.pid"
#日志文件
filepath=${logs_path}"access.log"
# Source function library.
#重命名日志文件
mv ${logs_path}access.log
${logs_path}access_$(date -d '-1 day' '+%Y-%m-%d').log
#向 nginx 主进程发信号重新打开日志
kill -USR1 `cat ${pid_path}`
crontab 设置作业(每天零时零分执行):
0 0 * * * sh /usr/local/nginx/nginx_log.sh
a1.sources = r1
a1.sources.r1.type = TAILDIR
a1.sources.r1.channels = c1
a1.sources.r1.positionFile = /var/log/flume/taildir_position.json
a1.sources.r1.filegroups = f1 f2
a1.sources.r1.filegroups.f1 = /var/log/test1/example.log
a1.sources.r1.filegroups.f2 = /var/log/test2/.*log.*
说明:
8.215.204.118 - - [18/Sep/2013:06:51:35 +0000] "GET /wp-includes/js/jquery/jquery.js?ver=1.10.2 HTTP/1.1" 304 0 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
数据说明:
1、访客 ip 地址: 58.215.204.118
2、访客用户信息: - -
3、请求时间: [18/Sep/2013:06:51:35 +0000]
4、请求方式: GET
5、请求的 url: /wp-includes/js/jquery/jquery.js?ver=1.10.2
6、请求所用协议: HTTP/1.1
7、响应码: 304
8、返回的数据流量: 0
9、访客的来源 url: http://blog.fens.me/nodejs-socketio-chat/
过滤“不合规”数据,清洗无意义的数据格式转换和规整,根据后续的统计需求,过滤分离出各种不同主题(不同栏目 path)的基础数据。
数据的处理分为三个阶段进行:
阶段一:对无意义数据的清洗,无用的数据做标记
阶段二:对相同用户的信息整合,进行页面点击流模型的梳理,参考上一篇
阶段三:点击流模型 Visits 表(按 session 聚集的页面访问信息)
package com.weblog.mr.preprocess;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
public class WebLogBean implements Writable{
private boolean valid = true;// 判断数据是否合法
private String remote_addr;// 记录客户端的ip地址
private String remote_user;// 记录客户端用户名称,忽略属性"-"
private String time_local;// 记录访问时间与时区
private String request;// 记录请求的url与http协议
private String status;// 记录请求状态;成功是200
private String body_bytes_sent;// 记录发送给客户端文件主体内容大小
private String http_referer;// 用来记录从那个页面链接访问过来的
private String http_user_agent;// 记录客户浏览器的相关信息
public void set(boolean valid,String remote_addr, String remote_user, String time_local, String request, String status, String body_bytes_sent, String http_referer, String http_user_agent) {
this.valid = valid;
this.remote_addr = remote_addr;
this.remote_user = remote_user;
this.time_local = time_local;
this.request = request;
this.status = status;
this.body_bytes_sent = body_bytes_sent;
this.http_referer = http_referer;
this.http_user_agent = http_user_agent;
}
public void setValid(boolean valid) {
this.valid = valid;
}
public void setRemote_addr(String remote_addr) {
this.remote_addr = remote_addr;
}
public void setRemote_user(String remote_user) {
this.remote_user = remote_user;
}
public void setTime_local(String time_local) {
this.time_local = time_local;
}
public void setRequest(String request) {
this.request = request;
}
public void setStatus(String status) {
this.status = status;
}
public void setBody_bytes_sent(String body_bytes_sent) {
this.body_bytes_sent = body_bytes_sent;
}
public void setHttp_referer(String http_referer) {
this.http_referer = http_referer;
}
public void setHttp_user_agent(String http_user_agent) {
this.http_user_agent = http_user_agent;
}
public boolean isValid() {
return valid;
}
public String getRemote_addr() {
return remote_addr;
}
public String getRemote_user() {
return remote_user;
}
public String getTime_local() {
return time_local;
}
public String getRequest() {
return request;
}
public String getStatus() {
return status;
}
public String getBody_bytes_sent() {
return body_bytes_sent;
}
public String getHttp_referer() {
return http_referer;
}
public String getHttp_user_agent() {
return http_user_agent;
}
//重新整合数据
@Override
public String toString() {
StringBuilder sb = new StringBuilder();
sb.append(this.valid);
sb.append("\001").append(this.getRemote_addr());
sb.append("\001").append(this.getRemote_user());
sb.append("\001").append(this.getTime_local());
sb.append("\001").append(this.getRequest());
sb.append("\001").append(this.getStatus());
sb.append("\001").append(this.getBody_bytes_sent());
sb.append("\001").append(this.getHttp_referer());
sb.append("\001").append(this.getHttp_user_agent());
return sb.toString();
}
//重新定义WebLogBean的序列化方式,减轻无用信息的负载
@Override
public void write(DataOutput out) throws IOException {
out.writeBoolean(this.valid);
out.writeUTF(null==remote_addr?"":remote_addr);
out.writeUTF(null==remote_user?"":remote_user);
out.writeUTF(null==time_local?"":time_local);
out.writeUTF(null==request?"":request);
out.writeUTF(null==status?"":status);
out.writeUTF(null==body_bytes_sent?"":body_bytes_sent);
out.writeUTF(null==http_referer?"":http_referer);
out.writeUTF(null==http_user_agent?"":http_user_agent);
}
@Override
public void readFields(DataInput in) throws IOException {
this.valid = in.readBoolean();
this.remote_addr = in.readUTF();
this.remote_user = in.readUTF();
this.time_local = in.readUTF();
this.request = in.readUTF();
this.status = in.readUTF();
this.body_bytes_sent = in.readUTF();
this.http_referer = in.readUTF();
this.http_user_agent = in.readUTF();
}
}
处理数据清洗的方法类WebLogParser类
package com.weblog.mr.preprocess;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Locale;
import java.util.Set;
public class WebLogParser {
static SimpleDateFormat df1= new SimpleDateFormat("dd/MMM/yyyy:HH:mm:ss", Locale.US);
static SimpleDateFormat df2= new SimpleDateFormat("yyyy-MM-dd HH:mm:ss", Locale.US);
//对日志文件的实际处理方法
public static WebLogBean parser(String line){
WebLogBean webLogBean = new WebLogBean();
//切割
String[] arr = line.split(" ");
if(arr.length>11){
//设置IP地址
webLogBean.setRemote_addr(arr[0]);
//设置用户信息
webLogBean.setRemote_user(arr[1]);
//[18/Sep/2013:06:49:18 +0000] 设置时间信息
String time_local = formatDate(arr[3].substring(1));
webLogBean.setTime_local(time_local);
//HTTP/1.1
webLogBean.setRequest(arr[6]);
//304
webLogBean.setStatus(arr[8]);
//0
webLogBean.setBody_bytes_sent(arr[9]);
//Mozilla/4.0 (compatible;)
webLogBean.setHttp_referer(arr[10]);
//用户浏览器的信息较多,需要进行拼接
//"Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
if (arr.length > 12) {
StringBuilder sb = new StringBuilder();
for(int i=11;i= 400) {// 大于400,HTTP错误
webLogBean.setValid(false);
}
//非法时间格式的也设置为false;
if("-invalid_time-".equals(webLogBean.getTime_local())){
webLogBean.setValid(false);
}
}else{
return null;
}
return webLogBean;
}
//格式化时间的方法
private static String formatDate(String time_locale) {
try {
return df2.format(df1.parse(time_locale));
} catch (ParseException e) {
e.printStackTrace();
return null;
}
}
public static void filtStaticResource(WebLogBean bean,Set pages){
//如果不是规定的协议请求,标记为false
if (!pages.contains(bean.getRequest())) {
bean.setValid(false);
}
}
}
执行文件处理的类WeblogPreProcess
package com.weblog.mr.preprocess;
import org.apache.hadoop.conf.Configuration;
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;
import java.util.HashSet;
import java.util.Set;
public class WeblogPreProcess {
static class WeblogPreProcessMapper extends Mapper{
Set pages = new HashSet();
Text k = new Text();
NullWritable v = NullWritable.get();
//从外部配置文件中加载网站的有用url分类数据 存储到maptask的内存中,用来对日志数据进行过滤
//wp-content/themes/silesia/images/ico-twitter.png HTTP/1.1
@Override
protected void setup(Context context) throws IOException, InterruptedException {
pages.add("/about");
pages.add("/black-ip-list/");
pages.add("/cassandra-clustor/");
pages.add("/finance-rhive-repurchase/");
pages.add("/hadoop-family-roadmap/");
pages.add("/hadoop-hive-intro/");
pages.add("/hadoop-zookeeper-intro/");
pages.add("/hadoop-mahout-roadmap/");
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
WebLogBean webLogBean = WebLogParser.parser(line);
if (webLogBean !=null){
//过滤CSS/图片/js等静态资源
WebLogParser.filtStaticResource(webLogBean,pages);
k.set(webLogBean.toString());
context.write(k,v);
}
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//加载类信息
job.setJarByClass(WeblogPreProcess.class);
job.setMapperClass(WeblogPreProcessMapper.class);
//加载输出的数据类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
//加载文件的位置
FileInputFormat.setInputPaths(job, new Path("d:/weblog/input"));
FileOutputFormat.setOutputPath(job, new Path("d:/weblog/output"));
//设置reduce不执行
job.setNumReduceTasks(0);
//输出结果
boolean res = job.waitForCompletion(true);
System.exit(res?0:1);
}
}
package cn.itcast.mr.weblog.pageview;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
public class PageViewsBean implements Writable {
private String session;
private String remote_addr;
private String timestr;
private String request;
private int step;
private String staylong;
private String referal;
private String useragent;
private String bytes_send;
private String status;
public void set(String session, String remote_addr, String useragent, String timestr, String request, int step, String staylong, String referal, String bytes_send, String status) {
this.session = session;
this.remote_addr = remote_addr;
this.useragent = useragent;
this.timestr = timestr;
this.request = request;
this.step = step;
this.staylong = staylong;
this.referal = referal;
this.bytes_send = bytes_send;
this.status = status;
}
public String getSession() {
return session;
}
public void setSession(String session) {
this.session = session;
}
public String getRemote_addr() {
return remote_addr;
}
public void setRemote_addr(String remote_addr) {
this.remote_addr = remote_addr;
}
public String getTimestr() {
return timestr;
}
public void setTimestr(String timestr) {
this.timestr = timestr;
}
public String getRequest() {
return request;
}
public void setRequest(String request) {
this.request = request;
}
public int getStep() {
return step;
}
public void setStep(int step) {
this.step = step;
}
public String getStaylong() {
return staylong;
}
public void setStaylong(String staylong) {
this.staylong = staylong;
}
public String getReferal() {
return referal;
}
public void setReferal(String referal) {
this.referal = referal;
}
public String getUseragent() {
return useragent;
}
public void setUseragent(String useragent) {
this.useragent = useragent;
}
public String getBytes_send() {
return bytes_send;
}
public void setBytes_send(String bytes_send) {
this.bytes_send = bytes_send;
}
public String getStatus() {
return status;
}
public void setStatus(String status) {
this.status = status;
}
@Override
public void readFields(DataInput in) throws IOException {
this.session = in.readUTF();
this.remote_addr = in.readUTF();
this.timestr = in.readUTF();
this.request = in.readUTF();
this.step = in.readInt();
this.staylong = in.readUTF();
this.referal = in.readUTF();
this.useragent = in.readUTF();
this.bytes_send = in.readUTF();
this.status = in.readUTF();
}
@Override
public void write(DataOutput out) throws IOException {
out.writeUTF(session);
out.writeUTF(remote_addr);
out.writeUTF(timestr);
out.writeUTF(request);
out.writeInt(step);
out.writeUTF(staylong);
out.writeUTF(referal);
out.writeUTF(useragent);
out.writeUTF(bytes_send);
out.writeUTF(status);
}
}
数据处理类
package cn.itcast.mr.weblog.pageview;
import java.io.IOException;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.Date;
import java.util.Locale;
import java.util.UUID;
import cn.itcast.mr.weblog.preprocess.WebLogBean;
import org.apache.commons.beanutils.BeanUtils;
import org.apache.hadoop.conf.Configuration;
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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
*
* 将清洗之后的日志梳理出点击流pageviews模型数据
*
* 输入数据是清洗过后的结果数据
*
* 区分出每一次会话,给每一次visit(session)增加了session-id(随机uuid)
* 梳理出每一次会话中所访问的每个页面(请求时间,url,停留时长,以及该页面在这次session中的序号)
* 保留referral_url,body_bytes_send,useragent
*
*
* @author
*
*/
public class ClickStreamPageView {
static class ClickStreamMapper extends Mapper {
Text k = new Text();
WebLogBean v = new WebLogBean();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] fields = line.split("\001");
if (fields.length < 9) return;
//将切分出来的各字段set到weblogbean中
v.set("true".equals(fields[0]) ? true : false, fields[1], fields[2], fields[3], fields[4], fields[5], fields[6], fields[7], fields[8]);
//只有有效记录才进入后续处理
if (v.isValid()) {
//此处用ip地址来标识用户
k.set(v.getRemote_addr());
context.write(k, v);
}
}
}
static class ClickStreamReducer extends Reducer {
Text v = new Text();
@Override
protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
ArrayList beans = new ArrayList();
// 先将一个用户的所有访问记录中的时间拿出来排序
try {
for (WebLogBean bean : values) {
WebLogBean webLogBean = new WebLogBean();
try {
BeanUtils.copyProperties(webLogBean, bean);
} catch(Exception e) {
e.printStackTrace();
}
beans.add(webLogBean);
}
//将bean按时间先后顺序排序
Collections.sort(beans, new Comparator() {
@Override
public int compare(WebLogBean o1, WebLogBean o2) {
try {
Date d1 = toDate(o1.getTime_local());
Date d2 = toDate(o2.getTime_local());
if (d1 == null || d2 == null)
return 0;
return d1.compareTo(d2);
} catch (Exception e) {
e.printStackTrace();
return 0;
}
}
});
/**
* 以下逻辑为:从有序bean中分辨出各次visit,并对一次visit中所访问的page按顺序标号step
* 核心思想:
* 就是比较相邻两条记录中的时间差,如果时间差<30分钟,则该两条记录属于同一个session
* 否则,就属于不同的session
*
*/
int step = 1;
String session = UUID.randomUUID().toString();
for (int i = 0; i < beans.size(); i++) {
WebLogBean bean = beans.get(i);
// 如果仅有1条数据,则直接输出
if (1 == beans.size()) {
// 设置默认停留时长为60s
v.set(session+"\001"+key.toString()+"\001"+bean.getRemote_user() + "\001" + bean.getTime_local() + "\001" + bean.getRequest() + "\001" + step + "\001" + (60) + "\001" + bean.getHttp_referer() + "\001" + bean.getHttp_user_agent() + "\001" + bean.getBody_bytes_sent() + "\001"
+ bean.getStatus());
context.write(NullWritable.get(), v);
session = UUID.randomUUID().toString();
break;
}
// 如果不止1条数据,则将第一条跳过不输出,遍历第二条时再输出
if (i == 0) {
continue;
}
// 求近两次时间差
long timeDiff = timeDiff(toDate(bean.getTime_local()), toDate(beans.get(i - 1).getTime_local()));
// 如果本次-上次时间差<30分钟,则输出前一次的页面访问信息
if (timeDiff < 30 * 60 * 1000) {
v.set(session+"\001"+key.toString()+"\001"+beans.get(i - 1).getRemote_user() + "\001" + beans.get(i - 1).getTime_local() + "\001" + beans.get(i - 1).getRequest() + "\001" + step + "\001" + (timeDiff / 1000) + "\001" + beans.get(i - 1).getHttp_referer() + "\001"
+ beans.get(i - 1).getHttp_user_agent() + "\001" + beans.get(i - 1).getBody_bytes_sent() + "\001" + beans.get(i - 1).getStatus());
context.write(NullWritable.get(), v);
step++;
} else {
// 如果本次-上次时间差>30分钟,则输出前一次的页面访问信息且将step重置,以分隔为新的visit
v.set(session+"\001"+key.toString()+"\001"+beans.get(i - 1).getRemote_user() + "\001" + beans.get(i - 1).getTime_local() + "\001" + beans.get(i - 1).getRequest() + "\001" + (step) + "\001" + (60) + "\001" + beans.get(i - 1).getHttp_referer() + "\001"
+ beans.get(i - 1).getHttp_user_agent() + "\001" + beans.get(i - 1).getBody_bytes_sent() + "\001" + beans.get(i - 1).getStatus());
context.write(NullWritable.get(), v);
// 输出完上一条之后,重置step编号
step = 1;
session = UUID.randomUUID().toString();
}
// 如果此次遍历的是最后一条,则将本条直接输出
if (i == beans.size() - 1) {
// 设置默认停留市场为60s
v.set(session+"\001"+key.toString()+"\001"+bean.getRemote_user() + "\001" + bean.getTime_local() + "\001" + bean.getRequest() + "\001" + step + "\001" + (60) + "\001" + bean.getHttp_referer() + "\001" + bean.getHttp_user_agent() + "\001" + bean.getBody_bytes_sent() + "\001" + bean.getStatus());
context.write(NullWritable.get(), v);
}
}
} catch (ParseException e) {
e.printStackTrace();
}
}
private String toStr(Date date) {
SimpleDateFormat df = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss", Locale.US);
return df.format(date);
}
private Date toDate(String timeStr) throws ParseException {
SimpleDateFormat df = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss", Locale.US);
return df.parse(timeStr);
}
private long timeDiff(String time1, String time2) throws ParseException {
Date d1 = toDate(time1);
Date d2 = toDate(time2);
return d1.getTime() - d2.getTime();
}
private long timeDiff(Date time1, Date time2) throws ParseException {
return time1.getTime() - time2.getTime();
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(ClickStreamPageView.class);
job.setMapperClass(ClickStreamMapper.class);
job.setReducerClass(ClickStreamReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(WebLogBean.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// FileInputFormat.setInputPaths(job, new Path(args[0]));
// FileOutputFormat.setOutputPath(job, new Path(args[1]));
FileInputFormat.setInputPaths(job, new Path("d:/weblog/output"));
FileOutputFormat.setOutputPath(job, new Path("d:/weblog/pageviews"));
job.waitForCompletion(true);
}
}
package cn.itcast.mr.weblog.vists;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
public class VisitBean implements Writable {
private String session;
private String remote_addr;
private String inTime;
private String outTime;
private String inPage;
private String outPage;
private String referal;
private int pageVisits;
public void set(String session, String remote_addr, String inTime, String outTime, String inPage, String outPage, String referal, int pageVisits) {
this.session = session;
this.remote_addr = remote_addr;
this.inTime = inTime;
this.outTime = outTime;
this.inPage = inPage;
this.outPage = outPage;
this.referal = referal;
this.pageVisits = pageVisits;
}
public String getSession() {
return session;
}
public void setSession(String session) {
this.session = session;
}
public String getRemote_addr() {
return remote_addr;
}
public void setRemote_addr(String remote_addr) {
this.remote_addr = remote_addr;
}
public String getInTime() {
return inTime;
}
public void setInTime(String inTime) {
this.inTime = inTime;
}
public String getOutTime() {
return outTime;
}
public void setOutTime(String outTime) {
this.outTime = outTime;
}
public String getInPage() {
return inPage;
}
public void setInPage(String inPage) {
this.inPage = inPage;
}
public String getOutPage() {
return outPage;
}
public void setOutPage(String outPage) {
this.outPage = outPage;
}
public String getReferal() {
return referal;
}
public void setReferal(String referal) {
this.referal = referal;
}
public int getPageVisits() {
return pageVisits;
}
public void setPageVisits(int pageVisits) {
this.pageVisits = pageVisits;
}
@Override
public void readFields(DataInput in) throws IOException {
this.session = in.readUTF();
this.remote_addr = in.readUTF();
this.inTime = in.readUTF();
this.outTime = in.readUTF();
this.inPage = in.readUTF();
this.outPage = in.readUTF();
this.referal = in.readUTF();
this.pageVisits = in.readInt();
}
@Override
public void write(DataOutput out) throws IOException {
out.writeUTF(session);
out.writeUTF(remote_addr);
out.writeUTF(inTime);
out.writeUTF(outTime);
out.writeUTF(inPage);
out.writeUTF(outPage);
out.writeUTF(referal);
out.writeInt(pageVisits);
}
@Override
public String toString() {
return session + "\001" + remote_addr + "\001" + inTime + "\001" + outTime + "\001" + inPage + "\001" + outPage + "\001" + referal + "\001" + pageVisits;
}
}
数据处理类ClickStreamVisit
package cn.itcast.mr.weblog.vists;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import cn.itcast.mr.weblog.pageview.PageViewsBean;
import org.apache.commons.beanutils.BeanUtils;
import org.apache.hadoop.conf.Configuration;
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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
* 输入数据:pageviews模型结果数据
* 从pageviews模型结果数据中进一步梳理出visit模型
* sessionid start-time out-time start-page out-page pagecounts ......
*
* @author
*
*/
public class ClickStreamVisit {
// 以session作为key,发送数据到reducer
static class ClickStreamVisitMapper extends Mapper {
PageViewsBean pvBean = new PageViewsBean();
Text k = new Text();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] fields = line.split("\001");
int step = Integer.parseInt(fields[5]);
//(String session, String remote_addr, String timestr, String request, int step, String staylong, String referal, String useragent, String bytes_send, String status)
//299d6b78-9571-4fa9-bcc2-f2567c46df3472.46.128.140-2013-09-18 07:58:50/hadoop-zookeeper-intro/160"https://www.google.com/""Mozilla/5.0"14722200
pvBean.set(fields[0], fields[1], fields[2], fields[3],fields[4], step, fields[6], fields[7], fields[8], fields[9]);
k.set(pvBean.getSession());
context.write(k, pvBean);
}
}
static class ClickStreamVisitReducer extends Reducer {
@Override
protected void reduce(Text session, Iterable pvBeans, Context context) throws IOException, InterruptedException {
// 将pvBeans按照step排序
ArrayList pvBeansList = new ArrayList();
for (PageViewsBean pvBean : pvBeans) {
PageViewsBean bean = new PageViewsBean();
try {
BeanUtils.copyProperties(bean, pvBean);
pvBeansList.add(bean);
} catch (Exception e) {
e.printStackTrace();
}
}
Collections.sort(pvBeansList, new Comparator() {
@Override
public int compare(PageViewsBean o1, PageViewsBean o2) {
return o1.getStep() > o2.getStep() ? 1 : -1;
}
});
// 取这次visit的首尾pageview记录,将数据放入VisitBean中
VisitBean visitBean = new VisitBean();
// 取visit的首记录
visitBean.setInPage(pvBeansList.get(0).getRequest());
visitBean.setInTime(pvBeansList.get(0).getTimestr());
// 取visit的尾记录
visitBean.setOutPage(pvBeansList.get(pvBeansList.size() - 1).getRequest());
visitBean.setOutTime(pvBeansList.get(pvBeansList.size() - 1).getTimestr());
// visit访问的页面数
visitBean.setPageVisits(pvBeansList.size());
// 来访者的ip
visitBean.setRemote_addr(pvBeansList.get(0).getRemote_addr());
// 本次visit的referal
visitBean.setReferal(pvBeansList.get(0).getReferal());
visitBean.setSession(session.toString());
context.write(NullWritable.get(), visitBean);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(ClickStreamVisit.class);
job.setMapperClass(ClickStreamVisitMapper.class);
job.setReducerClass(ClickStreamVisitReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(PageViewsBean.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(VisitBean.class);
// FileInputFormat.setInputPaths(job, new Path(args[0]));
// FileOutputFormat.setOutputPath(job, new Path(args[1]));
FileInputFormat.setInputPaths(job, new Path("d:/weblog/pageviews"));
FileOutputFormat.setOutputPath(job, new Path("d:/weblog/visitout"));
boolean res = job.waitForCompletion(true);
System.exit(res?0:1);
}
}
上述各项操作, 在实际的生产环境中, 明显是需要周期性运行的。所以任务的工作流调度就显得特别的重要。 除了使用我们 linux 自带的定时调度外,市面上还有许多成熟的调度产品。
下一篇介绍工作流调度器。