电商平台日志分析系统（大数据） 上（不完整-版本不对应）
分析针对{历史数据，每天的增量数据}
站长工具 seo 优化， pageRank
http://seo.chinaz.com/www.taobao.com
PV (page view ） UV(user view) 页面访问量，用户访问量
一针对增量数据进行分析。 设定淘宝300G/每天； 唯品会访问量为17G
建立数据表时预留两个字段，同样程序功能也预留一个模块。
一般 有指标和维度 。
埋点 ： 向后端大数据平台报告请求。
时间参数格式举例：
js-sdk,java-sdk
startURL工具画时序图
node204 上安装nginx(tengine)
1002 cd software/
1004 tar -zxvf tengine-2.1.0.tar.gz ## 解压nginx
1005 cd tengine-2.1.0
1007 ./configure
1008 yum -y install gcc ## 安装依赖 否则confugure报错 CentOS nginx checking for C compiler ... not found
1009 yum -y install gcc-c++
1010 yum -y install openssl openssl-devel
1011 ./configure
1012 make && make install
1013 whereis nginx
1014 cd /usr/local/nginx/
1016 cd sbin/
1018 ./nginx ## 启动nginx
1020 cd conf/
1021 ls
1022 cp nginx.conf nginx.conf.bak
1023 vi nginx.conf # 配置nginx
[root@node204 data]# cat /usr/local/nginx/conf/nginx.conf
#user nobody;
worker_processes 1;
#error_log logs/error.log;
#error_log logs/error.log notice;
#error_log logs/error.log info;
#pid logs/nginx.pid;
events {
worker_connections 1024;
}
# load modules compiled as Dynamic Shared Object (DSO)
#
#dso {
# load ngx_http_fastcgi_module.so;
# load ngx_http_rewrite_module.so;
#}
http {
include mime.types;
default_type application/octet-stream;
#log_format main '$remote_addr - $remote_user [$time_local] "$request" '
# '$status $body_bytes_sent "$http_referer" '
# '"$http_user_agent" "$http_x_forwarded_for"';
log_format my_format '$remote_addr^A$msec^A$http_host^A$request_uri';
#access_log logs/access.log main;
sendfile on;
#tcp_nopush on;
#keepalive_timeout 0;
keepalive_timeout 65;
#gzip on;
server {
listen 80;
server_name localhost;
#charset koi8-r;
#access_log logs/host.access.log main;
location / {
root html;
index index.html index.htm;
}
location = /log.gif {
default_type image/gif;
access_log /opt/data/access.log my_format;
}
#error_page 404 /404.html;
# redirect server error pages to the static page /50x.html
#
error_page 500 502 503 504 /50x.html;
location = /50x.html {
root html;
}
# proxy the PHP scripts to Apache listening on 127.0.0.1:80
#
#location ~ \.php$ {
# proxy_pass http://127.0.0.1;
#}
# pass the PHP scripts to FastCGI server listening on 127.0.0.1:9000
#
#location ~ \.php$ {
# root html;
# fastcgi_pass 127.0.0.1:9000;
# fastcgi_index index.php;
# fastcgi_param SCRIPT_FILENAME /scripts$fastcgi_script_name;
# include fastcgi_params;
#}
# deny access to .htaccess files, if Apache's document root
# concurs with nginx's one
#
#location ~ /\.ht {
# deny all;
#}
}
# another virtual host using mix of IP-, name-, and port-based configuration
#
#server {
# listen 8000;
# listen somename:8080;
# server_name somename alias another.alias;
# location / {
# root html;
# index index.html index.htm;
# }
#}
# HTTPS server
#
#server {
# listen 443 ssl;
# server_name localhost;
# ssl_certificate cert.pem;
# ssl_certificate_key cert.key;
# ssl_session_cache shared:SSL:1m;
# ssl_session_timeout 5m;
# ssl_ciphers HIGH:!aNULL:!MD5;
# ssl_prefer_server_ciphers on;
# location / {
# root html;
# index index.html index.htm;
# }
#}
}
1024 mkdir -r /opt/data ## 创建日志存放的目录
1025 mkdir /opt/data
1026 cd vi /etc/init.d/nginx ## 配置service nginx 服务 ## 注意pid和安装目录需要与nginx.conf保持一致。 否则会报错
Centos7 配置systemctl的Nginx启动服务，start一直卡着，stop不生效https://www.cnblogs.com/JaminXie/p/11322697.html
[root@node204 data]# cat /etc/init.d/nginx
#!/bin/sh
#
# nginx - this script starts and stops the nginx daemon
#
# chkconfig: - 85 15
# description: Nginx is an HTTP(S) server, HTTP(S) reverse \
# proxy and IMAP/POP3 proxy server
# processname: nginx
# config: /etc/nginx/nginx.conf
# config: /etc/sysconfig/nginx
# pidfile: /usr/local/nginx/logs/nginx.pid
# Source function library.
. /etc/rc.d/init.d/functions
# Source networking configuration.
. /etc/sysconfig/network
# Check that networking is up.
[ "$NETWORKING" = "no" ] && exit 0
nginx="/usr/local/nginx/sbin/nginx"
prog=$(basename $nginx)
NGINX_CONF_FILE="/usr/local/nginx/conf/nginx.conf"
[ -f /etc/sysconfig/nginx ] && . /etc/sysconfig/nginx
lockfile=/var/lock/subsys/nginx
make_dirs() {
# make required directories
user=`nginx -V 2>&1 | grep "configure arguments:" | sed 's/[^*]*--user=\([^ ]*\).*/\1/g' -`
options=`$nginx -V 2>&1 | grep 'configure arguments:'`
for opt in $options; do
if [ `echo $opt | grep '.*-temp-path'` ]; then
value=`echo $opt | cut -d "=" -f 2`
if [ ! -d "$value" ]; then
# echo "creating" $value
mkdir -p $value && chown -R $user $value
fi
fi
done
}
start() {
[ -x $nginx ] || exit 5
[ -f $NGINX_CONF_FILE ] || exit 6
make_dirs
echo -n $"Starting $prog: "
daemon $nginx -c $NGINX_CONF_FILE
retval=$?
echo
[ $retval -eq 0 ] && touch $lockfile
return $retval
}
stop() {
echo -n $"Stopping $prog: "
killproc $prog -QUIT
retval=$?
echo
[ $retval -eq 0 ] && rm -f $lockfile
return $retval
}
restart() {
configtest || return $?
stop
sleep 1
start
}
reload() {
configtest || return $?
echo -n $"Reloading $prog: "
killproc $nginx -HUP
RETVAL=$?
echo
}
force_reload() {
restart
}
configtest() {
$nginx -t -c $NGINX_CONF_FILE
}
rh_status() {
status $prog
}
rh_status_q() {
rh_status >/dev/null 2>&1
}
case "$1" in
start)
rh_status_q && exit 0
$1
;;
stop)
rh_status_q || exit 0
$1
;;
restart|configtest)
$1
;;
reload)
rh_status_q || exit 7
$1
;;
force-reload)
force_reload
;;
status)
rh_status
;;
condrestart|try-restart)
rh_status_q || exit 0
;;
*)
echo $"Usage: $0 {start|stop|status|restart|condrestart|try-restart|reload|force-reload|configtest}"
exit 2
esac
1028 chmod +x /etc/init.d/nginx
1029 service nginx restart
1097 systemctl daemon-reload
1098 service nginx stop
1099 service nginx start
1100 cd /opt/data/ ##从window上传一张图片log.gif到 /usr/local/nginx/html/下。
1102 tail -f access.log
## http://node204/log.gif?name=zhangsan&age=19 可以收到日志
js-sdk,java-sdk访问方法：
analytics.js
(function() {
var CookieUtil = {
// get the cookie of the key is name
get : function(name) {
var cookieName = encodeURIComponent(name) + "=", cookieStart = document.cookie
.indexOf(cookieName), cookieValue = null;
if (cookieStart > -1) {
var cookieEnd = document.cookie.indexOf(";", cookieStart);
if (cookieEnd == -1) {
cookieEnd = document.cookie.length;
}
cookieValue = decodeURIComponent(document.cookie.substring(
cookieStart + cookieName.length, cookieEnd));
}
return cookieValue;
},
// set the name/value pair to browser cookie
set : function(name, value, expires, path, domain, secure) {
var cookieText = encodeURIComponent(name) + "="
+ encodeURIComponent(value);
if (expires) {
// set the expires time
var expiresTime = new Date();
expiresTime.setTime(expires);
cookieText += ";expires=" + expiresTime.toGMTString();
}
if (path) {
cookieText += ";path=" + path;
}
if (domain) {
cookieText += ";domain=" + domain;
}
if (secure) {
cookieText += ";secure";
}
document.cookie = cookieText;
},
setExt : function(name, value) {
this.set(name, value, new Date().getTime() + 315360000000, "/");
}
};
// 主体，其实就是tracker js
var tracker = {
// config
clientConfig : {
serverUrl : "http://node204/log.gif",
sessionTimeout : 360, // 360s -> 6min
maxWaitTime : 3600, // 3600s -> 60min -> 1h
ver : "1"
},
cookieExpiresTime : 315360000000, // cookie过期时间，10年
columns : {
// 发送到服务器的列名称
eventName : "en",
version : "ver",
platform : "pl",
sdk : "sdk",
uuid : "u_ud",
memberId : "u_mid",
sessionId : "u_sd",
clientTime : "c_time",
language : "l",
userAgent : "b_iev",
resolution : "b_rst",
currentUrl : "p_url",
referrerUrl : "p_ref",
title : "tt",
orderId : "oid",
orderName : "on",
currencyAmount : "cua",
currencyType : "cut",
paymentType : "pt",
category : "ca",
action : "ac",
kv : "kv_",
duration : "du"
},
keys : {
pageView : "e_pv",
chargeRequestEvent : "e_crt",
launch : "e_l",
eventDurationEvent : "e_e",
sid : "bftrack_sid",
uuid : "bftrack_uuid",
mid : "bftrack_mid",
preVisitTime : "bftrack_previsit",
},
/**
* 获取会话id
*/
getSid : function() {
return CookieUtil.get(this.keys.sid);
},
/**
* 保存会话id到cookie
*/
setSid : function(sid) {
if (sid) {
CookieUtil.setExt(this.keys.sid, sid);
}
},
/**
* 获取uuid，从cookie中
*/
getUuid : function() {
return CookieUtil.get(this.keys.uuid);
},
/**
* 保存uuid到cookie
*/
setUuid : function(uuid) {
if (uuid) {
CookieUtil.setExt(this.keys.uuid, uuid);
}
},
/**
* 获取memberID
*/
getMemberId : function() {
return CookieUtil.get(this.keys.mid);
},
/**
* 设置mid
*/
setMemberId : function(mid) {
if (mid) {
CookieUtil.setExt(this.keys.mid, mid);
}
},
startSession : function() {
// 加载js就触发的方法
if (this.getSid()) {
// 会话id存在，表示uuid也存在
if (this.isSessionTimeout()) {
// 会话过期,产生新的会话
this.createNewSession();
} else {
// 会话没有过期，更新最近访问时间
this.updatePreVisitTime(new Date().getTime());
}
} else {
// 会话id不存在，表示uuid也不存在
this.createNewSession();
}
this.onPageView();
},
onLaunch : function() {
// 触发launch事件
var launch = {};
launch[this.columns.eventName] = this.keys.launch; // 设置事件名称
this.setCommonColumns(launch); // 设置公用columns
this.sendDataToServer(this.parseParam(launch)); // 最终发送编码后的数据
},
onPageView : function() {
// 触发page view事件
if (this.preCallApi()) {
var time = new Date().getTime();
var pageviewEvent = {};
pageviewEvent[this.columns.eventName] = this.keys.pageView;
pageviewEvent[this.columns.currentUrl] = window.location.href; // 设置当前url
pageviewEvent[this.columns.referrerUrl] = document.referrer; // 设置前一个页面的url
pageviewEvent[this.columns.title] = document.title; // 设置title
this.setCommonColumns(pageviewEvent); // 设置公用columns
this.sendDataToServer(this.parseParam(pageviewEvent)); // 最终发送编码后的数据
this.updatePreVisitTime(time);
}
},
onChargeRequest : function(orderId, name, currencyAmount, currencyType, paymentType) {
// 触发订单产生事件
if (this.preCallApi()) {
if (!orderId || !currencyType || !paymentType) {
this.log("订单id、货币类型以及支付方式不能为空");
return;
}
if (typeof (currencyAmount) == "number") {
// 金额必须是数字
var time = new Date().getTime();
var chargeRequestEvent = {};
chargeRequestEvent[this.columns.eventName] = this.keys.chargeRequestEvent;
chargeRequestEvent[this.columns.orderId] = orderId;
chargeRequestEvent[this.columns.orderName] = name;
chargeRequestEvent[this.columns.currencyAmount] = currencyAmount;
chargeRequestEvent[this.columns.currencyType] = currencyType;
chargeRequestEvent[this.columns.paymentType] = paymentType;
this.setCommonColumns(chargeRequestEvent); // 设置公用columns
this.sendDataToServer(this.parseParam(chargeRequestEvent)); // 最终发送编码后的数据
this.updatePreVisitTime(time);
} else {
this.log("订单金额必须是数字");
return;
}
}
},
onEventDuration : function(category, action, map, duration) {
// 触发event事件
if (this.preCallApi()) {
if (category && action) {
var time = new Date().getTime();
var event = {};
event[this.columns.eventName] = this.keys.eventDurationEvent;
event[this.columns.category] = category;
event[this.columns.action] = action;
if (map) {
for ( var k in map) {
if (k && map[k]) {
event[this.columns.kv + k] = map[k];
}
}
}
if (duration) {
event[this.columns.duration] = duration;
}
this.setCommonColumns(event); // 设置公用columns
this.sendDataToServer(this.parseParam(event)); // 最终发送编码后的数据
this.updatePreVisitTime(time);
} else {
this.log("category和action不能为空");
}
}
},
/**
* 执行对外方法前必须执行的方法
*/
preCallApi : function() {
if (this.isSessionTimeout()) {
// 如果为true，表示需要新建
this.startSession();
} else {
this.updatePreVisitTime(new Date().getTime());
}
return true;
},
sendDataToServer : function(data) {
alert(data);
// 发送数据data到服务器，其中data是一个字符串
var that = this;
var i2 = new Image(1, 1);// <img src="url"></img>
i2.onerror = function() {
// 这里可以进行重试操作
};
i2.src = this.clientConfig.serverUrl + "?" + data;
},
/**
* 往data中添加发送到日志收集服务器的公用部分
*/
setCommonColumns : function(data) {
data[this.columns.version] = this.clientConfig.ver;
data[this.columns.platform] = "website";
data[this.columns.sdk] = "js";
data[this.columns.uuid] = this.getUuid(); // 设置用户id
data[this.columns.memberId] = this.getMemberId(); // 设置会员id
data[this.columns.sessionId] = this.getSid(); // 设置sid
data[this.columns.clientTime] = new Date().getTime(); // 设置客户端时间
data[this.columns.language] = window.navigator.language; // 设置浏览器语言
data[this.columns.userAgent] = window.navigator.userAgent; // 设置浏览器类型
data[this.columns.resolution] = screen.width + "*" + screen.height; // 设置浏览器分辨率
},
/**
* 创建新的会员，并判断是否是第一次访问页面，如果是，进行launch事件的发送。
*/
createNewSession : function() {
var time = new Date().getTime(); // 获取当前操作时间
// 1. 进行会话更新操作
var sid = this.generateId(); // 产生一个session id
this.setSid(sid);
this.updatePreVisitTime(time); // 更新最近访问时间
// 2. 进行uuid查看操作
if (!this.getUuid()) {
// uuid不存在，先创建uuid，然后保存到cookie，最后触发launch事件
var uuid = this.generateId(); // 产品uuid
this.setUuid(uuid);
this.onLaunch();
}
},
/**
* 参数编码返回字符串
*/
parseParam : function(data) {
var params = "";
for ( var e in data) {
if (e && data[e]) {
params += encodeURIComponent(e) + "="
+ encodeURIComponent(data[e]) + "&";
}
}
if (params) {
return params.substring(0, params.length - 1);
} else {
return params;
}
},
/**
* 产生uuid
*/
generateId : function() {
var chars = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz';
var tmpid = [];
var r;
tmpid[8] = tmpid[13] = tmpid[18] = tmpid[23] = '-';
tmpid[14] = '4';
for (i = 0; i < 36; i++) {
if (!tmpid[i]) {
r = 0 | Math.random() * 16;
tmpid[i] = chars[(i == 19) ? (r & 0x3) | 0x8 : r];
}
}
return tmpid.join('');
},
/**
* 判断这个会话是否过期，查看当前时间和最近访问时间间隔时间是否小于this.clientConfig.sessionTimeout<br/>
* 如果是小于，返回false;否则返回true。
*/
isSessionTimeout : function() {
var time = new Date().getTime();
var preTime = CookieUtil.get(this.keys.preVisitTime);
if (preTime) {
// 最近访问时间存在,那么进行区间判断
return time - preTime > this.clientConfig.sessionTimeout * 1000;
}
return true;
},
/**
* 更新最近访问时间
*/
updatePreVisitTime : function(time) {
CookieUtil.setExt(this.keys.preVisitTime, time);
},
/**
* 打印日志
*/
log : function(msg) {
console.log(msg);
},
};
// 对外暴露的方法名称
window.__AE__ = {
startSession : function() {
tracker.startSession();
},
onPageView : function() {
tracker.onPageView();
},
onChargeRequest : function(orderId, name, currencyAmount, currencyType, paymentType) {
tracker.onChargeRequest(orderId, name, currencyAmount, currencyType, paymentType);
},
onEventDuration : function(category, action, map, duration) {
tracker.onEventDuration(category, action, map, duration);
},
setMemberId : function(mid) {
tracker.setMemberId(mid);
}
};
// 自动加载方法
var autoLoad = function() {
// 进行参数设置
var _aelog_ = _aelog_ || window._aelog_ || [];
var memberId = null;
for (i = 0; i < _aelog_.length; i++) {
_aelog_[i][0] === "memberId" && (memberId = _aelog_[i][1]);
}
// 根据是给定memberid，设置memberid的值
memberId && __AE__.setMemberId(memberId);
// 启动session
__AE__.startSession();
};
autoLoad();
})();
demo.jsp
<%@ page contentType="text/html; charset=utf-8" pageEncoding="utf-8"%>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>测试页面1</title>
<script type="text/javascript" src="./js/analytics.js"></script>
</head>
<body>
测试页面1<br/>
跳转到:
<a href="demo.jsp">demo</a>
<a href="demo2.jsp">demo2</a>
<a href="demo3.jsp">demo3</a>
<a href="demo4.jsp">demo4</a>
</body>
</html>
demo2.jsp
<%@ page contentType="text/html; charset=utf-8" pageEncoding="utf-8"%>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>测试页面2</title>
<script type="text/javascript" src="./js/analytics.js"></script>
</head>
<body>
测试页面2
<br/>
<label>orderid: 123456</label><br>
<label>orderName: 测试订单123456</label><br/>
<label>currencyAmount: 524.01</label><br/>
<label>currencyType: RMB</label><br/>
<label>paymentType: alipay</label><br/>
<button onclick="__AE__.onChargeRequest('123456','测试订单123456',524.01,'RMB','alipay')">触发chargeRequest事件</button><br/>
跳转到:
<a href="demo.jsp">demo</a>
<a href="demo2.jsp">demo2</a>
<a href="demo3.jsp">demo3</a>
<a href="demo4.jsp">demo4</a>
</body>
</html>
demo3.jsp
<%@ page contentType="text/html; charset=utf-8" pageEncoding="utf-8"%>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>测试页面3</title>
<script type="text/javascript" src="./js/analytics.js"></script>
</head>
<body>
测试页面3<br/>
<label>category: event的category名称</label><br/>
<label>action: event的action名称</label><br/>
<label>map: {"key1":"value1", "key2":"value2"}</label><br/>
<label>duration: 1245</label><br/>
<button onclick="__AE__.onEventDuration('event的category名称','event的action名称', {'key1':'value1','key2':'value2'}, 1245)">触发带map和duration的事件</button><br/>
<button onclick="__AE__.onEventDuration('event的category名称','event的action名称')">触发不带map和duration的事件</button><br/>
跳转到:
<a href="demo.jsp">demo</a>
<a href="demo2.jsp">demo2</a>
<a href="demo3.jsp">demo3</a>
<a href="demo4.jsp">demo4</a>
</body>
</html>
demo4.jsp
<%@ page contentType="text/html; charset=utf-8" pageEncoding="utf-8"%>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>测试页面4</title>
<script type="text/javascript">
(function(){
var _aelog_ = _aelog_ || window._aelog_ || [];
// 设置_aelog_相关属性
_aelog_.push(["memberId","zhangsan"]);
window._aelog_ = _aelog_;
(function(){
var aejs = document.createElement('script');
aejs.type = 'text/javascript';
aejs.async = true;
aejs.src = './js/analytics.js';
var script = document.getElementsByTagName('script')[0];
script.parentNode.insertBefore(aejs, script);
})();
})();
</script>
</head>
<body>
测试页面4<br/>
在本页面设置memberid为zhangsan<br/>
跳转到:
<a href="demo.jsp">demo</a>
<a href="demo2.jsp">demo2</a>
<a href="demo3.jsp">demo3</a>
<a href="demo4.jsp">demo4</a>
</body>
</html>
package com.sxt.client;
import java.io.UnsupportedEncodingException;
import java.net.URLEncoder;
import java.util.HashMap;
import java.util.Map;
import java.util.logging.Level;
import java.util.logging.Logger;
/**
* 分析引擎sdk java服务器端数据收集
*
* @author root
* @version 1.0
*
*/
public class AnalyticsEngineSDK {
// 日志打印对象
private static final Logger log = Logger.getGlobal();
// 请求url的主体部分
public static final String accessUrl = "http://node204/log.gif";
private static final String platformName = "java_server";
private static final String sdkName = "jdk";
private static final String version = "1";
/**
* 触发订单支付成功事件，发送事件数据到服务器
*
* @param orderId
* 订单支付id
* @param memberId
* 订单支付会员id
* @return 如果发送数据成功(加入到发送队列中)，那么返回true；否则返回false(参数异常&添加到发送队列失败).
*/
public static boolean onChargeSuccess(String orderId, String memberId) {
try {
if (isEmpty(orderId) || isEmpty(memberId)) {
// 订单id或者memberid为空
log.log(Level.WARNING, "订单id和会员id不能为空");
return false;
}
// 代码执行到这儿，表示订单id和会员id都不为空。
Map<String, String> data = new HashMap<String, String>();
data.put("u_mid", memberId);
data.put("oid", orderId);
data.put("c_time", String.valueOf(System.currentTimeMillis()));
data.put("ver", version);
data.put("en", "e_cs");
data.put("pl", platformName);
data.put("sdk", sdkName);
// 创建url
String url = buildUrl(data);
// 发送url&将url加入到队列
SendDataMonitor.addSendUrl(url);
return true;
} catch (Throwable e) {
log.log(Level.WARNING, "发送数据异常", e);
}
return false;
}
/**
* 触发订单退款事件，发送退款数据到服务器
*
* @param orderId
* 退款订单id
* @param memberId
* 退款会员id
* @return 如果发送数据成功，返回true。否则返回false。
*/
public static boolean onChargeRefund(String orderId, String memberId) {
try {
if (isEmpty(orderId) || isEmpty(memberId)) {
// 订单id或者memberid为空
log.log(Level.WARNING, "订单id和会员id不能为空");
return false;
}
// 代码执行到这儿，表示订单id和会员id都不为空。
Map<String, String> data = new HashMap<String, String>();
data.put("u_mid", memberId);
data.put("oid", orderId);
data.put("c_time", String.valueOf(System.currentTimeMillis()));
data.put("ver", version);
data.put("en", "e_cr");
data.put("pl", platformName);
data.put("sdk", sdkName);
// 构建url
String url = buildUrl(data);
// 发送url&将url添加到队列中
SendDataMonitor.addSendUrl(url);
return true;
} catch (Throwable e) {
log.log(Level.WARNING, "发送数据异常", e);
}
return false;
}
/**
* 根据传入的参数构建url
*
* @param data
* @return
* @throws UnsupportedEncodingException
*/
private static String buildUrl(Map<String, String> data)
throws UnsupportedEncodingException {
StringBuilder sb = new StringBuilder();
sb.append(accessUrl).append("?");
for (Map.Entry<String, String> entry : data.entrySet()) {
if (isNotEmpty(entry.getKey()) && isNotEmpty(entry.getValue())) {
sb.append(entry.getKey().trim())
.append("=")
.append(URLEncoder.encode(entry.getValue().trim(), "utf-8"))
.append("&");
}
}
return sb.substring(0, sb.length() - 1);// 去掉最后&
}
/**
* 判断字符串是否为空，如果为空，返回true。否则返回false。
*
* @param value
* @return
*/
private static boolean isEmpty(String value) {
return value == null || value.trim().isEmpty();
}
/**
* 判断字符串是否非空，如果不是空，返回true。如果是空，返回false。
*
* @param value
* @return
*/
private static boolean isNotEmpty(String value) {
return !isEmpty(value);
}
}
package com.sxt.client;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.concurrent.BlockingQueue;
import java.util.concurrent.LinkedBlockingQueue;
import java.util.logging.Level;
import java.util.logging.Logger;
/**
* 发送url数据的监控者，用于启动一个单独的线程来发送数据
*
* @author root
*
*/
public class SendDataMonitor {
// 日志记录对象
private static final Logger log = Logger.getGlobal();
// 队列，用户存储发送url
private BlockingQueue<String> queue = new LinkedBlockingQueue<String>();
// 用于单列的一个类对象
private static SendDataMonitor monitor = null;
private SendDataMonitor() {
// 私有构造方法，进行单列模式的创建
}
/**
* 获取单列的monitor对象实例
*
* @return
*/
public static SendDataMonitor getSendDataMonitor() {
if (monitor == null) {
synchronized (SendDataMonitor.class) {
if (monitor == null) {
monitor = new SendDataMonitor();
Thread thread = new Thread(new Runnable() {
@Override
public void run() {
// 线程中调用具体的处理方法
SendDataMonitor.monitor.run();
}
});
// 测试的时候，不设置为守护模式
// thread.setDaemon(true);
thread.start();
}
}
}
return monitor;
}
/**
* 添加一个url到队列中去
*
* @param url
* @throws InterruptedException
*/
public static void addSendUrl(String url) throws InterruptedException {
getSendDataMonitor().queue.put(url);
}
/**
* 具体执行发送url的方法
*
*/
private void run() {
while (true) {
try {
String url = this.queue.take();
// 正式的发送url
HttpRequestUtil.sendData(url);
} catch (Throwable e) {
log.log(Level.WARNING, "发送url异常", e);
}
}
}
/**
* 内部类，用户发送数据的http工具类
*
* @author root
*
*/
public static class HttpRequestUtil {
/**
* 具体发送url的方法
*
* @param url
* @throws IOException
*/
public static void sendData(String url) throws IOException {
HttpURLConnection con = null;
BufferedReader in = null;
try {
URL obj = new URL(url); // 创建url对象
con = (HttpURLConnection) obj.openConnection(); // 打开url连接
// 设置连接参数
con.setConnectTimeout(5000); // 连接过期时间
con.setReadTimeout(5000); // 读取数据过期时间
con.setRequestMethod("GET"); // 设置请求类型为get
System.out.println("发送url:" + url);
// 发送连接请求
in = new BufferedReader(new InputStreamReader(
con.getInputStream()));
// TODO: 这里考虑是否可以
} finally {
try {
if (in != null) {
in.close();
}
} catch (Throwable e) {
// nothing
}
try {
con.disconnect();
} catch (Throwable e) {
// nothing
}
}
}
}
}
package com.sxt.log.test;
import java.util.Random;
import com.sxt.client.AnalyticsEngineSDK;
public class Test {
public static String day = "20160607";
static Random r = new Random();
public static void main(String[] args) {
AnalyticsEngineSDK.onChargeSuccess("orderid123", "zhangsan");
AnalyticsEngineSDK.onChargeRefund("orderid456", "lisi");
// try {
// String d = day
// + String.format(
// "%02d%02d%02d",
// new Object[] { r.nextInt(24), r.nextInt(60),
// r.nextInt(60) });
// System.out.println(d);
// Date date = new SimpleDateFormat("yyyyMMddhhmmss").parse(d);
// System.out.println(date);
// String datetime = date.getTime() + "";
// System.out.println(datetime);
// String prefix = datetime.substring(0, datetime.length() - 3);
// System.out.println(prefix + "." + r.nextInt(1000));
// System.out.println(new Date(1423634643000l));
// } catch (ParseException e) {
// e.printStackTrace();
// }
}
}
使用tomcat 8运行。访问jsp; 能够看到日志。
flume http://flume.apache.org/index.html
亦可以在命令行运行时的参数。
单节点配置
安装flume 204上。 可以参考官网文档，非常详细
1007 tar -zxvf apache-flume-1.6.0-bin.tar.gz -C /opt/sxt/
1008 cd /opt/sxt/apache-flume-1.6.0-bin/conf/
1015 cp flume-env.sh.template flume-env.sh
1016 vi flume-env.sh
export JAVA_HOME=/usr/java/jdk1.8.0_221
1020 vi /etc/profile
export FLUME_HOME=/opt/sxt/apache-flume-1.6.0-bin
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HIVE_HOME/bin:$HBASE_HOME/bin:$FLUME_HOME/bin
1021 source /etc/profile
1022 flume-ng
1023 flume-ng version ## 查看版本
1024 cd /opt/
1032 mkdir flumedir ## 配置flume
1033 cd flumedir/
1035 vi option
[root@node204 conf]# cat /opt/flumedir/option
# example.conf: A single-node Flume configuration
# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1
# Describe/configure the source
a1.sources.r1.type = netcat ## netcat方式获取
a1.sources.r1.bind = node204
a1.sources.r1.port = 44444
# Describe the sink
a1.sinks.k1.type = logger
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
1036 flume-ng agent --conf-file option --name a1 -Dflume.root.logger=INFO,console ## 启动flume
2019-08-27 04:41:00,537 INFO node.Application: Starting Source r1 2019-08-27 04:41:00,542 INFO source.NetcatSource: Source starting 2019-08-27 04:41:00,650 INFO source.NetcatSource: Created serverSocket:sun.nio.ch.ServerSocketChannelImpl[/192.168.112.204:44444]
node205上操作 telnet发送socket数据，查看flume204 是否接收到。 795 yum install -y telnet [root@node205 ~]# telnet node204 44444 Trying 192.168.112.204... Connected to node204. Escape character is '^]'. ## 分隔符] hello OK hi OK sxt OK nihao OK ##在node204 flume程序下可以看到telnet发送的信息。
多节点配置
AVRO 格式（通过RPC发送数据）
node204(左) node205 （右）
node204
scp -r apache-flume-1.6.0-bin root@node205:`pwd` ## 分发文件
cd /opt/flumedir/
1048 vi option
# example.conf: A single-node Flume configuration
# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1
# Describe/configure the source
a1.sources.r1.type = netcat
a1.sources.r1.bind = node204
a1.sources.r1.port = 44444
# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = node205
a1.sinks.k1.port = 10086
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
node205 配置 flume环境变量
cd /opt/flumedir/
1048 vi option2
# example.conf: A single-node Flume configuration
# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1
# Describe/configure the source
a1.sources.r1.type = avro
a1.sources.r1.bind = node205
a1.sources.r1.port = 10086
# Describe the sink
a1.sinks.k1.type = logger
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
## a1.sources.r1.bind = node205 表示我监听本机端口获取数据。
node205 服务端先启动
flume-ng agent --conf-file option2 --name a1 -Dflume.root.logger=INFO,console
node204客户端在启动
flume-ng agent --conf-file option --name a1 -Dflume.root.logger=INFO,console
在node205上试用telnet发送消息，node205 flume conlose下能够查看到消息。
2019-08-27 05:16:11,893 INFO sink.LoggerSink: Event: { headers:{} body: 68 65 6C 6C 6F 0D hello. }
2019-08-27 05:16:11,893 INFO sink.LoggerSink: Event: { headers:{} body: 6E 69 6E 68 61 6F 08 08 08 0D ninhao.... }
2019-08-27 05:16:16,169 INFO sink.LoggerSink: Event: { headers:{} body: 77 6F 6D 65 6E 0D women. }
## 配置读取文件末尾Exec source ## tail 监控文件增量 [root@node204 ~]# cat /opt/flumedir/option3 # example.conf: A single-node Flume configuration # Name the components on this agent a1.sources = r1 a1.sinks = k1 a1.channels = c1 # Describe/configure the source a1.sources.r1.type = exec a1.sources.r1.command = tail -F /root/sxt.log # Describe the sink a1.sinks.k1.type = avro a1.sinks.k1.hostname = node205 a1.sinks.k1.port = 10086 # Use a channel which buffers events in memory a1.channels.c1.type = memory a1.channels.c1.capacity = 1000 a1.channels.c1.transactionCapacity = 100 # Bind the source and sink to the channel a1.sources.r1.channels = c1 a1.sinks.k1.channel = c1 [root@node204 ~]# vi sxt.log ## 在node205上也启动option2 # flume-ng agent --conf-file option3 --name a1 -Dflume.root.logger=INFO,console [root@node204 ~]# echo 'sxt' >> sxt.log ## 此时，王文建最佳呢绒。node205的console会输出sxt字样。 [root@node204 ~]# echo 'sxt' >> sxt.log [root@node204 ~]# echo 'sxt' >> sxt.log [root@node204 ~]# echo 'sxt' >> sxt.log ## vi 操作 vi sxt.log sxt sxt sxt :.,$y ## 复制当前行到末尾行内容
配置文件夹作为source [root@node204 ~]# cat /opt/flumedir/option4 # Name the components on this agent a1.sources = r1 a1.sinks = k1 a1.channels = c1 # Describe/configure the source a1.sources.r1.type = spooldir a1.sources.r1.spoolDir = /root/abc/ a1.sources.r1.fileHeader = true ### 表示是否显示文件名 # Describe the sink a1.sinks.k1.type = logger # Use a channel which buffers events in memory a1.channels.c1.type = memory a1.channels.c1.capacity = 1000 a1.channels.c1.transactionCapacity = 100 # Bind the source and sink to the channel a1.sources.r1.channels = c1 a1.sinks.k1.channel = c1 [root@node204 flumedir]# flume-ng agent --conf-file option4 --name a1 -Dflume.root.logger=INFO,console [root@node204 ~]# mkdir abc [root@node204 ~]# echo 1111 >> aaa [root@node204 ~]# echo 2222 >> aaa [root@node204 ~]# echo 3333 >> bbb [root@node204 ~]# echo 4444 >> bbb [root@node204 ~]# cp aaa abc/ [root@node204 ~]# cp bbb abc/ ##此时能够在option4下看到文件内容 [root@node204 ~]# cd abc/ [root@node204 abc]# ls aaa.COMPLETED bbb.COMPLETED
sink 为hdfs [root@node204 ~]# cat /opt/flumedir/option5 # Name the components on this agent a1.sources = r1 a1.sinks = k1 a1.channels = c1 # Describe/configure the source a1.sources.r1.type = exec a1.sources.r1.command = tail -F /root/sxt.log # Describe the sink a1.sinks.k1.type = hdfs a1.sinks.k1.hdfs.path = /flume/events/%y-%m-%d/%H%M/%S a1.sinks.k1.hdfs.filePrefix = events- a1.sinks.k1.hdfs.round = true a1.sinks.k1.hdfs.roundValue = 10 a1.sinks.k1.hdfs.roundUnit = minute a1.sinks.k1.hdfs.useLocalTimeStamp =true # Use a channel which buffers events in memory a1.channels.c1.type = memory a1.channels.c1.capacity = 1000 a1.channels.c1.transactionCapacity = 100 # Bind the source and sink to the channel a1.sources.r1.channels = c1 a1.sinks.k1.channel = c1
[root@node204 flumedir]# flume-ng agent --conf-file option5 --name a1 -Dflume.root.logger=INFO,console ## 会在hdfs上创建目录和文件。 （必须启动hdfs）
[root@node204 ~]# echo 'hello sxt ni hao' >> sxt.log ## 继续最佳文件内容，hdfs数据增加。 [root@node204 ~]# echo 'hello sxt ni hao' >> sxt.log [root@node204 ~]# echo 'hello sxt ni hao' >> sxt.log [root@node204 ~]# echo 'hello sxt ni hao' >> sxt.log
[root@node204 ~]# cat aaa | tee a.log ## 一个source 多个sink；可以再用linux实现。 1111 2222 [root@node204 ~]# cat a.log 1111 2222
kafka 与flume一般组对使用
ETL 程序和操作
node204配置：
[root@node204 ~]# service nginx start [root@node204 ~]# cat /opt/flumedir/option6 a1.sources = r1 a1.sinks = k1 a1.channels = c1 a1.sources.r1.type = exec a1.sources.r1.command = tail -F /opt/data/access.log a1.sinks.k1.type=hdfs a1.sinks.k1.hdfs.path=hdfs://mycluster/log/%Y%m%d a1.sinks.k1.hdfs.rollCount=0 a1.sinks.k1.hdfs.rollInterval=0 a1.sinks.k1.hdfs.rollSize=10240 a1.sinks.k1.hdfs.idleTimeout=5 a1.sinks.k1.hdfs.fileType=DataStream a1.sinks.k1.hdfs.useLocalTimeStamp=true a1.sinks.k1.hdfs.callTimeout=40000 a1.channels.c1.type = memory a1.channels.c1.capacity = 1000 a1.channels.c1.transactionCapacity = 100 a1.sources.r1.channels = c1 a1.sinks.k1.channel = c1 ## 使用eclipse 运行BIG_DATA_LOG2 项目，访问jsp页面触发埋点上报信息到nginx ,可以看到数据被上传到hdfs 。 tail -f /opt/data/access.log 查看访问的数据。
关于ETL在此处的作用 过滤脏数据（没有?或en参数的请求过滤掉） 解析ip 为地域 解析浏览器。 存储到hbase rowid 使用CRC32编码（将时间戳，事件，用户信息带入）
使用工具类： 解析浏览器
package com.sxt.etl.util;
import java.io.IOException;
import cz.mallat.uasparser.OnlineUpdater;
import cz.mallat.uasparser.UASparser;
/**
* 解析浏览器的user agent的工具类，内部就是调用这个uasparser jar文件
*
* @author root
*
*/
public class UserAgentUtil {
static UASparser uasParser = null;
// static 代码块, 初始化uasParser对象
static {
try {
uasParser = new UASparser(OnlineUpdater.getVendoredInputStream());
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 解析浏览器的user agent字符串，返回UserAgentInfo对象。<br/>
* 如果user agent为空，返回null。如果解析失败，也直接返回null。
*
* @param userAgent
* 要解析的user agent字符串
* @return 返回具体的值
*/
public static UserAgentInfo analyticUserAgent(String userAgent) {
UserAgentInfo result = null;
if (!(userAgent == null || userAgent.trim().isEmpty())) {
// 此时userAgent不为null，而且不是由全部空格组成的
try {
cz.mallat.uasparser.UserAgentInfo info = null;
info = uasParser.parse(userAgent);
result = new UserAgentInfo();
result.setBrowserName(info.getUaFamily());
result.setBrowserVersion(info.getBrowserVersionInfo());
result.setOsName(info.getOsFamily());
result.setOsVersion(info.getOsName());
} catch (IOException e) {
// 出现异常，将返回值设置为null
result = null;
}
}
return result;
}
/**
* 内部解析后的浏览器信息model对象
*
* @author root
*
*/
public static class UserAgentInfo {
private String browserName; // 浏览器名称
private String browserVersion; // 浏览器版本号
private String osName; // 操作系统名称
private String osVersion; // 操作系统版本号
public String getBrowserName() {
return browserName;
}
public void setBrowserName(String browserName) {
this.browserName = browserName;
}
public String getBrowserVersion() {
return browserVersion;
}
public void setBrowserVersion(String browserVersion) {
this.browserVersion = browserVersion;
}
public String getOsName() {
return osName;
}
public void setOsName(String osName) {
this.osName = osName;
}
public String getOsVersion() {
return osVersion;
}
public void setOsVersion(String osVersion) {
this.osVersion = osVersion;
}
@Override
public String toString() {
return "UserAgentInfo [browserName=" + browserName + ", browserVersion=" + browserVersion + ", osName="
+ osName + ", osVersion=" + osVersion + "]";
}
}
}
ip地址. qqwry.dat
package com.sxt.etl.util.ip;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.RandomAccessFile;
import java.io.UnsupportedEncodingException;
import java.nio.ByteOrder;
import java.nio.MappedByteBuffer;
import java.nio.channels.FileChannel;
import java.util.ArrayList;
import java.util.Hashtable;
import java.util.List;
/**
* * 用来读取QQwry.dat文件，以根据ip获得好友位置，QQwry.dat的格式是 一. 文件头，共8字节 1. 第一个起始IP的绝对偏移， 4字节
* 2. 最后一个起始IP的绝对偏移， 4字节 二. "结束地址/国家/区域"记录区 四字节ip地址后跟的每一条记录分成两个部分 1. 国家记录 2.
* 地区记录 但是地区记录是不一定有的。而且国家记录和地区记录都有两种形式 1. 以0结束的字符串 2. 4个字节，一个字节可能为0x1或0x2 a.
* 为0x1时，表示在绝对偏移后还跟着一个区域的记录，注意是绝对偏移之后，而不是这四个字节之后 b. 为0x2时，表示在绝对偏移后没有区域记录
* 不管为0x1还是0x2，后三个字节都是实际国家名的文件内绝对偏移
* 如果是地区记录，0x1和0x2的含义不明，但是如果出现这两个字节，也肯定是跟着3个字节偏移，如果不是 则为0结尾字符串 三.
* "起始地址/结束地址偏移"记录区 1. 每条记录7字节，按照起始地址从小到大排列 a. 起始IP地址，4字节 b. 结束ip地址的绝对偏移，3字节
*
* 注意，这个文件里的ip地址和所有的偏移量均采用little-endian格式，而java是采用 big-endian格式的，要注意转换
*
* @author root
*/
public class IPSeeker {
// 一些固定常量，比如记录长度等等
private static final int IP_RECORD_LENGTH = 7;
private static final byte AREA_FOLLOWED = 0x01;
private static final byte NO_AREA = 0x2;
// 用来做为cache，查询一个ip时首先查看cache，以减少不必要的重复查找
private Hashtable ipCache;
// 随机文件访问类
private RandomAccessFile ipFile;
// 内存映射文件
private MappedByteBuffer mbb;
// 单一模式实例
private static IPSeeker instance = null;
// 起始地区的开始和结束的绝对偏移
private long ipBegin, ipEnd;
// 为提高效率而采用的临时变量
private IPLocation loc;
private byte[] buf;
private byte[] b4;
private byte[] b3;
/** */
/**
* 私有构造函数
*/
protected IPSeeker() {
ipCache = new Hashtable();
loc = new IPLocation();
buf = new byte[100];
b4 = new byte[4];
b3 = new byte[3];
try {
String ipFilePath = IPSeeker.class.getResource("/qqwry.dat")
.getFile();
ipFile = new RandomAccessFile(ipFilePath, "r");
} catch (FileNotFoundException e) {
System.out.println("IP地址信息文件没有找到，IP显示功能将无法使用");
ipFile = null;
}
// 如果打开文件成功，读取文件头信息
if (ipFile != null) {
try {
ipBegin = readLong4(0);
ipEnd = readLong4(4);
if (ipBegin == -1 || ipEnd == -1) {
ipFile.close();
ipFile = null;
}
} catch (IOException e) {
System.out.println("IP地址信息文件格式有错误，IP显示功能将无法使用");
ipFile = null;
}
}
}
/** */
/**
* @return 单一实例
*/
public static IPSeeker getInstance() {
if (instance == null) {
instance = new IPSeeker();
}
return instance;
}
/** */
/**
* 给定一个地点的不完全名字，得到一系列包含s子串的IP范围记录
*
* @param s
* 地点子串
* @return 包含IPEntry类型的List
*/
public List getIPEntriesDebug(String s) {
List ret = new ArrayList();
long endOffset = ipEnd + 4;
for (long offset = ipBegin + 4; offset <= endOffset; offset += IP_RECORD_LENGTH) {
// 读取结束IP偏移
long temp = readLong3(offset);
// 如果temp不等于-1，读取IP的地点信息
if (temp != -1) {
IPLocation loc = getIPLocation(temp);
// 判断是否这个地点里面包含了s子串，如果包含了，添加这个记录到List中，如果没有，继续
if (loc.country.indexOf(s) != -1 || loc.area.indexOf(s) != -1) {
IPEntry entry = new IPEntry();
entry.country = loc.country;
entry.area = loc.area;
// 得到起始IP
readIP(offset - 4, b4);
entry.beginIp = IPSeekerUtils.getIpStringFromBytes(b4);
// 得到结束IP
readIP(temp, b4);
entry.endIp = IPSeekerUtils.getIpStringFromBytes(b4);
// 添加该记录
ret.add(entry);
}
}
}
return ret;
}
/** */
/**
* 给定一个地点的不完全名字，得到一系列包含s子串的IP范围记录
*
* @param s
* 地点子串
* @return 包含IPEntry类型的List
*/
public List getIPEntries(String s) {
List ret = new ArrayList();
try {
// 映射IP信息文件到内存中
if (mbb == null) {
FileChannel fc = ipFile.getChannel();
mbb = fc.map(FileChannel.MapMode.READ_ONLY, 0, ipFile.length());
mbb.order(ByteOrder.LITTLE_ENDIAN);
}
int endOffset = (int) ipEnd;
for (int offset = (int) ipBegin + 4; offset <= endOffset; offset += IP_RECORD_LENGTH) {
int temp = readInt3(offset);
if (temp != -1) {
IPLocation loc = getIPLocation(temp);
// 判断是否这个地点里面包含了s子串，如果包含了，添加这个记录到List中，如果没有，继续
if (loc.country.indexOf(s) != -1
|| loc.area.indexOf(s) != -1) {
IPEntry entry = new IPEntry();
entry.country = loc.country;
entry.area = loc.area;
// 得到起始IP
readIP(offset - 4, b4);
entry.beginIp = IPSeekerUtils.getIpStringFromBytes(b4);
// 得到结束IP
readIP(temp, b4);
entry.endIp = IPSeekerUtils.getIpStringFromBytes(b4);
// 添加该记录
ret.add(entry);
}
}
}
} catch (IOException e) {
System.out.println(e.getMessage());
}
return ret;
}
/** */
/**
* 从内存映射文件的offset位置开始的3个字节读取一个int
*
* @param offset
* @return
*/
private int readInt3(int offset) {
mbb.position(offset);
return mbb.getInt() & 0x00FFFFFF;
}
/** */
/**
* 从内存映射文件的当前位置开始的3个字节读取一个int
*
* @return
*/
private int readInt3() {
return mbb.getInt() & 0x00FFFFFF;
}
/** */
/**
* 根据IP得到国家名
*
* @param ip
* ip的字节数组形式
* @return 国家名字符串
*/
public String getCountry(byte[] ip) {
// 检查ip地址文件是否正常
if (ipFile == null)
return "错误的IP数据库文件";
// 保存ip，转换ip字节数组为字符串形式
String ipStr = IPSeekerUtils.getIpStringFromBytes(ip);
// 先检查cache中是否已经包含有这个ip的结果，没有再搜索文件
if (ipCache.containsKey(ipStr)) {
IPLocation loc = (IPLocation) ipCache.get(ipStr);
return loc.country;
} else {
IPLocation loc = getIPLocation(ip);
ipCache.put(ipStr, loc.getCopy());
return loc.country;
}
}
/** */
/**
* 根据IP得到国家名
*
* @param ip
* IP的字符串形式
* @return 国家名字符串
*/
public String getCountry(String ip) {
return getCountry(IPSeekerUtils.getIpByteArrayFromString(ip));
}
/** */
/**
* 根据IP得到地区名
*
* @param ip
* ip的字节数组形式
* @return 地区名字符串
*/
public String getArea(byte[] ip) {
// 检查ip地址文件是否正常
if (ipFile == null)
return "错误的IP数据库文件";
// 保存ip，转换ip字节数组为字符串形式
String ipStr = IPSeekerUtils.getIpStringFromBytes(ip);
// 先检查cache中是否已经包含有这个ip的结果，没有再搜索文件
if (ipCache.containsKey(ipStr)) {
IPLocation loc = (IPLocation) ipCache.get(ipStr);
return loc.area;
} else {
IPLocation loc = getIPLocation(ip);
ipCache.put(ipStr, loc.getCopy());
return loc.area;
}
}
/**
* 根据IP得到地区名
*
* @param ip
* IP的字符串形式
* @return 地区名字符串
*/
public String getArea(String ip) {
return getArea(IPSeekerUtils.getIpByteArrayFromString(ip));
}
/** */
/**
* 根据ip搜索ip信息文件，得到IPLocation结构，所搜索的ip参数从类成员ip中得到
*
* @param ip
* 要查询的IP
* @return IPLocation结构
*/
public IPLocation getIPLocation(byte[] ip) {
IPLocation info = null;
long offset = locateIP(ip);
if (offset != -1)
info = getIPLocation(offset);
if (info == null) {
info = new IPLocation();
info.country = "未知国家";
info.area = "未知地区";
}
return info;
}
/**
* 从offset位置读取4个字节为一个long，因为java为big-endian格式，所以没办法 用了这么一个函数来做转换
*
* @param offset
* @return 读取的long值，返回-1表示读取文件失败
*/
private long readLong4(long offset) {
long ret = 0;
try {
ipFile.seek(offset);
ret |= (ipFile.readByte() & 0xFF);
ret |= ((ipFile.readByte() << 8) & 0xFF00);
ret |= ((ipFile.readByte() << 16) & 0xFF0000);
ret |= ((ipFile.readByte() << 24) & 0xFF000000);
return ret;
} catch (IOException e) {
return -1;
}
}
/**
* 从offset位置读取3个字节为一个long，因为java为big-endian格式，所以没办法 用了这么一个函数来做转换
*
* @param offset
* @return 读取的long值，返回-1表示读取文件失败
*/
private long readLong3(long offset) {
long ret = 0;
try {
ipFile.seek(offset);
ipFile.readFully(b3);
ret |= (b3[0] & 0xFF);
ret |= ((b3[1] << 8) & 0xFF00);
ret |= ((b3[2] << 16) & 0xFF0000);
return ret;
} catch (IOException e) {
return -1;
}
}
/**
* 从当前位置读取3个字节转换成long
*
* @return
*/
private long readLong3() {
long ret = 0;
try {
ipFile.readFully(b3);
ret |= (b3[0] & 0xFF);
ret |= ((b3[1] << 8) & 0xFF00);
ret |= ((b3[2] << 16) & 0xFF0000);
return ret;
} catch (IOException e) {
return -1;
}
}
/**
* 从offset位置读取四个字节的ip地址放入ip数组中，读取后的ip为big-endian格式，但是
* 文件中是little-endian形式，将会进行转换
*
* @param offset
* @param ip
*/
private void readIP(long offset, byte[] ip) {
try {
ipFile.seek(offset);
ipFile.readFully(ip);
byte temp = ip[0];
ip[0] = ip[3];
ip[3] = temp;
temp = ip[1];
ip[1] = ip[2];
ip[2] = temp;
} catch (IOException e) {
System.out.println(e.getMessage());
}
}
/**
* 从offset位置读取四个字节的ip地址放入ip数组中，读取后的ip为big-endian格式，但是
* 文件中是little-endian形式，将会进行转换
*
* @param offset
* @param ip
*/
private void readIP(int offset, byte[] ip) {
mbb.position(offset);
mbb.get(ip);
byte temp = ip[0];
ip[0] = ip[3];
ip[3] = temp;
temp = ip[1];
ip[1] = ip[2];
ip[2] = temp;
}
/**
* 把类成员ip和beginIp比较，注意这个beginIp是big-endian的
*
* @param ip
* 要查询的IP
* @param beginIp
* 和被查询IP相比较的IP
* @return 相等返回0，ip大于beginIp则返回1，小于返回-1。
*/
private int compareIP(byte[] ip, byte[] beginIp) {
for (int i = 0; i < 4; i++) {
int r = compareByte(ip[i], beginIp[i]);
if (r != 0)
return r;
}
return 0;
}
/**
* 把两个byte当作无符号数进行比较
*
* @param b1
* @param b2
* @return 若b1大于b2则返回1，相等返回0，小于返回-1
*/
private int compareByte(byte b1, byte b2) {
if ((b1 & 0xFF) > (b2 & 0xFF)) // 比较是否大于
return 1;
else if ((b1 ^ b2) == 0)// 判断是否相等
return 0;
else
return -1;
}
/**
* 这个方法将根据ip的内容，定位到包含这个ip国家地区的记录处，返回一个绝对偏移 方法使用二分法查找。
*
* @param ip
* 要查询的IP
* @return 如果找到了，返回结束IP的偏移，如果没有找到，返回-1
*/
private long locateIP(byte[] ip) {
long m = 0;
int r;
// 比较第一个ip项
readIP(ipBegin, b4);
r = compareIP(ip, b4);
if (r == 0)
return ipBegin;
else if (r < 0)
return -1;
// 开始二分搜索
for (long i = ipBegin, j = ipEnd; i < j;) {
m = getMiddleOffset(i, j);
readIP(m, b4);
r = compareIP(ip, b4);
// log.debug(Utils.getIpStringFromBytes(b));
if (r > 0)
i = m;
else if (r < 0) {
if (m == j) {
j -= IP_RECORD_LENGTH;
m = j;
} else
j = m;
} else
return readLong3(m + 4);
}
// 如果循环结束了，那么i和j必定是相等的，这个记录为最可能的记录，但是并非
// 肯定就是，还要检查一下，如果是，就返回结束地址区的绝对偏移
m = readLong3(m + 4);
readIP(m, b4);
r = compareIP(ip, b4);
if (r <= 0)
return m;
else
return -1;
}
/**
* 得到begin偏移和end偏移中间位置记录的偏移
*
* @param begin
* @param end
* @return
*/
private long getMiddleOffset(long begin, long end) {
long records = (end - begin) / IP_RECORD_LENGTH;
records >>= 1;
if (records == 0)
records = 1;
return begin + records * IP_RECORD_LENGTH;
}
/**
* 给定一个ip国家地区记录的偏移，返回一个IPLocation结构
*
* @param offset
* @return
*/
private IPLocation getIPLocation(long offset) {
try {
// 跳过4字节ip
ipFile.seek(offset + 4);
// 读取第一个字节判断是否标志字节
byte b = ipFile.readByte();
if (b == AREA_FOLLOWED) {
// 读取国家偏移
long countryOffset = readLong3();
// 跳转至偏移处
ipFile.seek(countryOffset);
// 再检查一次标志字节，因为这个时候这个地方仍然可能是个重定向
b = ipFile.readByte();
if (b == NO_AREA) {
loc.country = readString(readLong3());
ipFile.seek(countryOffset + 4);
} else
loc.country = readString(countryOffset);
// 读取地区标志
loc.area = readArea(ipFile.getFilePointer());
} else if (b == NO_AREA) {
loc.country = readString(readLong3());
loc.area = readArea(offset + 8);
} else {
loc.country = readString(ipFile.getFilePointer() - 1);
loc.area = readArea(ipFile.getFilePointer());
}
return loc;
} catch (IOException e) {
return null;
}
}
/**
* @param offset
* @return
*/
private IPLocation getIPLocation(int offset) {
// 跳过4字节ip
mbb.position(offset + 4);
// 读取第一个字节判断是否标志字节
byte b = mbb.get();
if (b == AREA_FOLLOWED) {
// 读取国家偏移
int countryOffset = readInt3();
// 跳转至偏移处
mbb.position(countryOffset);
// 再检查一次标志字节，因为这个时候这个地方仍然可能是个重定向
b = mbb.get();
if (b == NO_AREA) {
loc.country = readString(readInt3());
mbb.position(countryOffset + 4);
} else
loc.country = readString(countryOffset);
// 读取地区标志
loc.area = readArea(mbb.position());
} else if (b == NO_AREA) {
loc.country = readString(readInt3());
loc.area = readArea(offset + 8);
} else {
loc.country = readString(mbb.position() - 1);
loc.area = readArea(mbb.position());
}
return loc;
}
/**
* 从offset偏移开始解析后面的字节，读出一个地区名
*
* @param offset
* @return 地区名字符串
* @throws IOException
*/
private String readArea(long offset) throws IOException {
ipFile.seek(offset);
byte b = ipFile.readByte();
if (b == 0x01 || b == 0x02) {
long areaOffset = readLong3(offset + 1);
if (areaOffset == 0)
return "未知地区";
else
return readString(areaOffset);
} else
return readString(offset);
}
/**
* @param offset
* @return
*/
private String readArea(int offset) {
mbb.position(offset);
byte b = mbb.get();
if (b == 0x01 || b == 0x02) {
int areaOffset = readInt3();
if (areaOffset == 0)
return "未知地区";
else
return readString(areaOffset);
} else
return readString(offset);
}
/**
* 从offset偏移处读取一个以0结束的字符串
*
* @param offset
* @return 读取的字符串，出错返回空字符串
*/
private String readString(long offset) {
try {
ipFile.seek(offset);
int i;
for (i = 0, buf[i] = ipFile.readByte(); buf[i] != 0; buf[++i] = ipFile
.readByte())
;
if (i != 0)
return IPSeekerUtils.getString(buf, 0, i, "GBK");
} catch (IOException e) {
System.out.println(e.getMessage());
}
return "";
}
/**
* 从内存映射文件的offset位置得到一个0结尾字符串
*
* @param offset
* @return
*/
private String readString(int offset) {
try {
mbb.position(offset);
int i;
for (i = 0, buf[i] = mbb.get(); buf[i] != 0; buf[++i] = mbb.get())
;
if (i != 0)
return IPSeekerUtils.getString(buf, 0, i, "GBK");
} catch (IllegalArgumentException e) {
System.out.println(e.getMessage());
}
return "";
}
public String getAddress(String ip) {
String country = getCountry(ip).equals(" CZ88.NET") ? ""
: getCountry(ip);
String area = getArea(ip).equals(" CZ88.NET") ? "" : getArea(ip);
String address = country + " " + area;
return address.trim();
}
/**
* * 用来封装ip相关信息，目前只有两个字段，ip所在的国家和地区
*
*
* @author swallow
*/
public class IPLocation {
public String country;
public String area;
public IPLocation() {
country = area = "";
}
public IPLocation getCopy() {
IPLocation ret = new IPLocation();
ret.country = country;
ret.area = area;
return ret;
}
}
/**
* 一条IP范围记录，不仅包括国家和区域，也包括起始IP和结束IP *
*
*
* @author root
*/
public class IPEntry {
public String beginIp;
public String endIp;
public String country;
public String area;
public IPEntry() {
beginIp = endIp = country = area = "";
}
public String toString() {
return this.area + " " + this.country + "IP Χ:" + this.beginIp
+ "-" + this.endIp;
}
}
/**
* 操作工具类
*
* @author root
*
*/
public static class IPSeekerUtils {
/**
* 从ip的字符串形式得到字节数组形式
*
* @param ip
* 字符串形式的ip
* @return 字节数组形式的ip
*/
public static byte[] getIpByteArrayFromString(String ip) {
byte[] ret = new byte[4];
java.util.StringTokenizer st = new java.util.StringTokenizer(ip,
".");
try {
ret[0] = (byte) (Integer.parseInt(st.nextToken()) & 0xFF);
ret[1] = (byte) (Integer.parseInt(st.nextToken()) & 0xFF);
ret[2] = (byte) (Integer.parseInt(st.nextToken()) & 0xFF);
ret[3] = (byte) (Integer.parseInt(st.nextToken()) & 0xFF);
} catch (Exception e) {
System.out.println(e.getMessage());
}
return ret;
}
/**
* 对原始字符串进行编码转换，如果失败，返回原始的字符串
*
* @param s
* 原始字符串
* @param srcEncoding
* 源编码方式
* @param destEncoding
* 目标编码方式
* @return 转换编码后的字符串，失败返回原始字符串
*/
public static String getString(String s, String srcEncoding,
String destEncoding) {
try {
return new String(s.getBytes(srcEncoding), destEncoding);
} catch (UnsupportedEncodingException e) {
return s;
}
}
/**
* 根据某种编码方式将字节数组转换成字符串
*
* @param b
* 字节数组
* @param encoding
* 编码方式
* @return 如果encoding不支持，返回一个缺省编码的字符串
*/
public static String getString(byte[] b, String encoding) {
try {
return new String(b, encoding);
} catch (UnsupportedEncodingException e) {
return new String(b);
}
}
/**
* 根据某种编码方式将字节数组转换成字符串
*
* @param b
* 字节数组
* @param offset
* 要转换的起始位置
* @param len
* 要转换的长度
* @param encoding
* 编码方式
* @return 如果encoding不支持，返回一个缺省编码的字符串
*/
public static String getString(byte[] b, int offset, int len,
String encoding) {
try {
return new String(b, offset, len, encoding);
} catch (UnsupportedEncodingException e) {
return new String(b, offset, len);
}
}
/**
* @param ip
* ip的字节数组形式
* @return 字符串形式的ip
*/
public static String getIpStringFromBytes(byte[] ip) {
StringBuffer sb = new StringBuffer();
sb.append(ip[0] & 0xFF);
sb.append('.');
sb.append(ip[1] & 0xFF);
sb.append('.');
sb.append(ip[2] & 0xFF);
sb.append('.');
sb.append(ip[3] & 0xFF);
return sb.toString();
}
}
/**
* 获取全部ip地址集合列表
*
* @return
*/
public List<String> getAllIp() {
List<String> list = new ArrayList<String>();
byte[] buf = new byte[4];
for (long i = ipBegin; i < ipEnd; i += IP_RECORD_LENGTH) {
try {
this.readIP(this.readLong3(i + 4), buf); // 读取ip，最终ip放到buf中
String ip = IPSeekerUtils.getIpStringFromBytes(buf);
list.add(ip);
} catch (Exception e) {
// nothing
}
}
return list;
}
}
测试时，jdk版本选择为1.7可以运行老师提供的源码
由于ETL 只需要过滤和解析，不涉及到聚合，直接写入到hbase.一次不需要reduce.
[root@node204 ~]# hadoop-daemon.sh stop namenode ## 切换active standby
配置程序的 hdfs 和zookeeper
@Override
public void setConf(Configuration conf) {
conf.set("fs.defaultFS", "hdfs://node203:8020");
// conf.set("yarn.resourcemanager.hostname", "node3");
conf.set("hbase.zookeeper.quorum", "node204,node205,node206");
this.conf = HBaseConfiguration.create(conf);
}
run main方法，并且通过runconfuguration配置参数 -d hdfs 上flume创建的文件目录。如 -d 2019-08-28 用-风格的日期
