大数据离线分析平台 JSSDK数据收集引擎编写

JsSDK设计规则
在js sdk中我们需要收集launch、pageview、chargeRequest和eventDuration四种数据，所以我们需要在js中写入四个方法来分别收集这些数据，另外我们还需要提供一些操作cookie和发送数据的的公用方法。

SDK测试
启动集群上的hdfs+nginx+flume进程，创建web项目加载js，然后发送数据到nginx服务器中，查看最终是否在hdfs中有数据的写入。
命令：

---

start-dfs.sh： 启动hdfs命令
su root：切换用户
service nginx restart: 启动nginx进程

---

启动flume进程：
进入flume安装根目录，执行命令：

---

flume-ng agent --conf ./conf/ --conf-file ./conf/test2.conf --name agent &

---

analytics.js集成
一、将analytics.js集成到你想收集收集的页面即可。集成方式主要分为以下两种：
1) 第一种方式
`将analytics.js集成到所有页面的的头部，然后通过提供的方法调用进行数据收集。
<script src='//www.beifeng.com/js/common/analytics.js'></script>
<script>__AE__.setMemberId("123456");</script>
2) 第二种方式
`使用javascript代码，异步引入analytics.js文件，在引入之前可以通过_aelog_设置会员id
<script type="text/javascript">
var _aelog_ = _aelog_ || window._aelog_ || [];
_aelog_.push(['member_id', '123456']); // 如果此时用户已经登录，那么通过才参数指定用户id
window._aelog_ = _aelog_;

(function() {
var amwae = document.createElement('script');
amwae.type = 'text/javascript';
amwae.async = true;
amwae.src = '//www.beifeng.com/js/common/analytics.js'; // 指定链接
var script = document.getElementsByTagName('script')[0];
script.parentNode.insertBefore(amwae, script);
})();
</script>
注意：当用户登录后，请调用__AE__.setMemberId('123456')方法进行会员id的设置，方便用户数据的收集。

web项目目录结构如下：

代码如下：

analytics.js如下：

(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://hadoop-001:8090/kkImg.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ss
                    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ss
                        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ss
                        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) {
                // 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);
                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

<%@ 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

<%@ 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

<%@ 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

<%@ 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","Transkai"]);
    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Transkai<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>