SlideShare a Scribd company logo
1 of 15
Web Archiving and Analytics by Qumram:
Lessons Learnt
Leonid Kyrpychenko
Qumram
@distributedLeo and @qumramAG
Barcelona
May 19th 2015
2
3
What are the lessons
learnt so far with Q5?
4
5
Lesson 1. Mocking is a MUST
stateManager = {
frameSent: function () {}
};
network = proxyquire('./network', {
'./stateManager': stateManager
});
With AngularJS we use standard ngMock.
We use jasmine in front and backend (but not only).
For the browser applications we use Proxyquireify (requires browserify)
6
Lesson 2. DOM changes not always
update innerHtml
// Risky Tag Names that should be handled manually
var tags = ['input', 'textarea', 'select', 'option'],
// Risky Attributes to backup
attributes = ['value', 'selected', 'checked', 'disabled'],
// Risky Attributes that has no value
noValueAttributes = ['selected', 'checked', 'disabled'];
7
Lesson 3. Compression and diffing
without web workers
/**
* Queue a work to the end of the javascript runtime excecution queue
*/
queueWork: function(context, fnNameOrReference, params, callback){
// add context to top of params, so that apply passes params correctly to bind
params.unshift(context);
// bind callback to context and add callback to end of parameter list
params.push(callback.bind(context));
// we use apply on bind because the params in array, bind needs each params as argument,
wheres
// apply can take a paramter array, so we do apply on bind.
if (typeof fnNameOrReference == 'string') {
setTimeout(Function.bind.apply(context[fnNameOrReference],params),0);
} else {
setTimeout(Function.bind.apply(fnNameOrReference,params),0);
}
},
8
Lesson 4. Track events with different
speed
To throttle the rate a function gets executed we use debouncing
var interval = config.get('recordMouseMovement').duration;
setInterval((function (buffer, activeMouseCordinates, lastRecordedMouseCordinates)
{
return recordMousePosition;
})(buffer, activeMouseCordinates, lastRecordedMouseCordinates), interval)
self.api.deBouncedFilter = debounce(self.api.filter, 400);
9
Lesson 5. Parse html in a new iFrame was
a huge bottleneck
var domParser = new DOMParser();
domParser.parseFromString(html, 'text/html');
10
Lesson 6. Browserify
return gulp.src(['./components/tracker/index.js'])
.pipe(transform(function(filename) {
return browserify({
entries: filename,
debug: true
}).bundle();
}))
.pipe(transform(function() {
return exorcist('./build/qumram.tracker.js.map');
}))
.pipe(rename('qumram.tracker.js'))
…
11
Lesson 7. Promises and bluebird
'use strict';
var bluebird = require('bluebird');
var mongodb = require('mongodb');
var config = require('./config.js');
bluebird.promisifyAll(mongodb);
bluebird.promisifyAll(mongodb.MongoClient);
bluebird.promisifyAll(mongodb.MongoClient.prototype);
bluebird.promisifyAll(mongodb.Collection);
bluebird.promisifyAll(mongodb.Collection.prototype);
bluebird.promisifyAll(mongodb.Cursor.prototype);
module.exports = {
/**
* initialise database connection
*/
init: function () {
return mongodb.MongoClient.connectAsync(config.dburl)
.then(function (db) {
module.exports.client = db;
});
}
};
12
Lesson 8. Koa
var koa = require('koa');
var cors = require('koa-cors');
var socket = require('koa-socket');
var qmrmRouter = require('qmrm-router');
var http = require('http');
var app = koa();
app.use(cors());
app.use(qmrmRouter.middleware());
socket.use(function *(next) {
this.method = this.event.split(' ')[0].toUpperCase();
this.path = this.event.split(' ')[1];
yield next;
this.socket.emit('resp ' + this.event, this.body);
});
socket.use(qmrmRouter.middleware());
socket.start(app);
app.server = [];
app.server[0] = http.createServer(app.callback());
app.init();
app.server[0].listen(3000);
13
Lesson 9. Sockets + REST router =
QRouter
npm install qrouter
var QmrmRouter = require('qrouter');
var router = new QmrmRouter();
router.options('/tokens', cors());
router.post('post_tokens', 'ack.post_tokens', '/tokens', cors(), function
(req, res) {
var token = req.body;
github.com/qumram/qrouter
14
Join US!
Jobs@Qumram.com
15

More Related Content

Similar to 20150519 qumram barcelona_js

Java script performance tips
Java script performance tipsJava script performance tips
Java script performance tips
Shakti Shrestha
 
Android programming -_pushing_the_limits
Android programming -_pushing_the_limitsAndroid programming -_pushing_the_limits
Android programming -_pushing_the_limits
Droidcon Berlin
 

Similar to 20150519 qumram barcelona_js (20)

Ten useful JavaScript tips & best practices
Ten useful JavaScript tips & best practicesTen useful JavaScript tips & best practices
Ten useful JavaScript tips & best practices
 
OSCON - ES6 metaprogramming unleashed
OSCON -  ES6 metaprogramming unleashedOSCON -  ES6 metaprogramming unleashed
OSCON - ES6 metaprogramming unleashed
 
Building resilient applications
Building resilient applicationsBuilding resilient applications
Building resilient applications
 
MeasureCamp IX (London) - 10 JavaScript Concepts for web analysts
MeasureCamp IX (London) - 10 JavaScript Concepts for web analystsMeasureCamp IX (London) - 10 JavaScript Concepts for web analysts
MeasureCamp IX (London) - 10 JavaScript Concepts for web analysts
 
Java Concurrency and Asynchronous
Java Concurrency and AsynchronousJava Concurrency and Asynchronous
Java Concurrency and Asynchronous
 
ES6 metaprogramming unleashed
ES6 metaprogramming unleashedES6 metaprogramming unleashed
ES6 metaprogramming unleashed
 
Junit_.pptx
Junit_.pptxJunit_.pptx
Junit_.pptx
 
Use me strict
Use me strictUse me strict
Use me strict
 
6976.ppt
6976.ppt6976.ppt
6976.ppt
 
OSMC 2021 | inspectIT Ocelot: Dynamic OpenTelemetry Instrumentation at Runtime
OSMC 2021 | inspectIT Ocelot: Dynamic OpenTelemetry Instrumentation at RuntimeOSMC 2021 | inspectIT Ocelot: Dynamic OpenTelemetry Instrumentation at Runtime
OSMC 2021 | inspectIT Ocelot: Dynamic OpenTelemetry Instrumentation at Runtime
 
Practical JavaScript Programming - Session 7/8
Practical JavaScript Programming - Session 7/8Practical JavaScript Programming - Session 7/8
Practical JavaScript Programming - Session 7/8
 
Efficient Memory and Thread Management in Highly Parallel Java Applications
Efficient Memory and Thread Management in Highly Parallel Java ApplicationsEfficient Memory and Thread Management in Highly Parallel Java Applications
Efficient Memory and Thread Management in Highly Parallel Java Applications
 
DBI-Assisted Android Application Reverse Engineering
DBI-Assisted Android Application Reverse EngineeringDBI-Assisted Android Application Reverse Engineering
DBI-Assisted Android Application Reverse Engineering
 
NodeJs
NodeJsNodeJs
NodeJs
 
What`s new in Java 7
What`s new in Java 7What`s new in Java 7
What`s new in Java 7
 
Java script performance tips
Java script performance tipsJava script performance tips
Java script performance tips
 
Grâce aux tags Varnish, j'ai switché ma prod sur Raspberry Pi
Grâce aux tags Varnish, j'ai switché ma prod sur Raspberry PiGrâce aux tags Varnish, j'ai switché ma prod sur Raspberry Pi
Grâce aux tags Varnish, j'ai switché ma prod sur Raspberry Pi
 
JavaScript Basics
JavaScript BasicsJavaScript Basics
JavaScript Basics
 
Android programming -_pushing_the_limits
Android programming -_pushing_the_limitsAndroid programming -_pushing_the_limits
Android programming -_pushing_the_limits
 
Angular Intermediate
Angular IntermediateAngular Intermediate
Angular Intermediate
 

Recently uploaded

Recently uploaded (20)

TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 

20150519 qumram barcelona_js

  • 1. Web Archiving and Analytics by Qumram: Lessons Learnt Leonid Kyrpychenko Qumram @distributedLeo and @qumramAG Barcelona May 19th 2015
  • 2. 2
  • 3. 3
  • 4. What are the lessons learnt so far with Q5? 4
  • 5. 5 Lesson 1. Mocking is a MUST stateManager = { frameSent: function () {} }; network = proxyquire('./network', { './stateManager': stateManager }); With AngularJS we use standard ngMock. We use jasmine in front and backend (but not only). For the browser applications we use Proxyquireify (requires browserify)
  • 6. 6 Lesson 2. DOM changes not always update innerHtml // Risky Tag Names that should be handled manually var tags = ['input', 'textarea', 'select', 'option'], // Risky Attributes to backup attributes = ['value', 'selected', 'checked', 'disabled'], // Risky Attributes that has no value noValueAttributes = ['selected', 'checked', 'disabled'];
  • 7. 7 Lesson 3. Compression and diffing without web workers /** * Queue a work to the end of the javascript runtime excecution queue */ queueWork: function(context, fnNameOrReference, params, callback){ // add context to top of params, so that apply passes params correctly to bind params.unshift(context); // bind callback to context and add callback to end of parameter list params.push(callback.bind(context)); // we use apply on bind because the params in array, bind needs each params as argument, wheres // apply can take a paramter array, so we do apply on bind. if (typeof fnNameOrReference == 'string') { setTimeout(Function.bind.apply(context[fnNameOrReference],params),0); } else { setTimeout(Function.bind.apply(fnNameOrReference,params),0); } },
  • 8. 8 Lesson 4. Track events with different speed To throttle the rate a function gets executed we use debouncing var interval = config.get('recordMouseMovement').duration; setInterval((function (buffer, activeMouseCordinates, lastRecordedMouseCordinates) { return recordMousePosition; })(buffer, activeMouseCordinates, lastRecordedMouseCordinates), interval) self.api.deBouncedFilter = debounce(self.api.filter, 400);
  • 9. 9 Lesson 5. Parse html in a new iFrame was a huge bottleneck var domParser = new DOMParser(); domParser.parseFromString(html, 'text/html');
  • 10. 10 Lesson 6. Browserify return gulp.src(['./components/tracker/index.js']) .pipe(transform(function(filename) { return browserify({ entries: filename, debug: true }).bundle(); })) .pipe(transform(function() { return exorcist('./build/qumram.tracker.js.map'); })) .pipe(rename('qumram.tracker.js')) …
  • 11. 11 Lesson 7. Promises and bluebird 'use strict'; var bluebird = require('bluebird'); var mongodb = require('mongodb'); var config = require('./config.js'); bluebird.promisifyAll(mongodb); bluebird.promisifyAll(mongodb.MongoClient); bluebird.promisifyAll(mongodb.MongoClient.prototype); bluebird.promisifyAll(mongodb.Collection); bluebird.promisifyAll(mongodb.Collection.prototype); bluebird.promisifyAll(mongodb.Cursor.prototype); module.exports = { /** * initialise database connection */ init: function () { return mongodb.MongoClient.connectAsync(config.dburl) .then(function (db) { module.exports.client = db; }); } };
  • 12. 12 Lesson 8. Koa var koa = require('koa'); var cors = require('koa-cors'); var socket = require('koa-socket'); var qmrmRouter = require('qmrm-router'); var http = require('http'); var app = koa(); app.use(cors()); app.use(qmrmRouter.middleware()); socket.use(function *(next) { this.method = this.event.split(' ')[0].toUpperCase(); this.path = this.event.split(' ')[1]; yield next; this.socket.emit('resp ' + this.event, this.body); }); socket.use(qmrmRouter.middleware()); socket.start(app); app.server = []; app.server[0] = http.createServer(app.callback()); app.init(); app.server[0].listen(3000);
  • 13. 13 Lesson 9. Sockets + REST router = QRouter npm install qrouter var QmrmRouter = require('qrouter'); var router = new QmrmRouter(); router.options('/tokens', cors()); router.post('post_tokens', 'ack.post_tokens', '/tokens', cors(), function (req, res) { var token = req.body; github.com/qumram/qrouter
  • 15. 15

Editor's Notes

  1. Part of our architecture
  2. Can be shown in qumramapi/app/mongodb.js, (node-service-template branch) we are using bluebird to promisify mongodb native library. Qumramui/gulp_tasks can be shown to show how we leverage promises for better structured readable code.