Contributions, ramblings, and rants from Rainabba

Understanding the implications of return await in ecmascript

2023-11-09T11:46:00.002-07:00

In ECMAScript, an async function always wraps the returned value in a Promise. If you return a value, it's equivalent to returning Promise.resolve(value). If you throw an error, it's akin to returning Promise.reject(error). When you await a Promise, the function's execution is paused until the Promise is settled.

Consider the following code inside an async function:

javascript
return await someAsyncFunction();

This will pause the execution of the current function until someAsyncFunction() resolves, and then immediately return the resolved value. However, since async functions automatically wrap returned values in Promises, you can simply write:

javascript
return someAsyncFunction();

In this case, someAsyncFunction() is returned directly. The Promise returned by someAsyncFunction() will be returned by your function as-is. The JavaScript engine doesn't need to create an additional microtask to resolve the await, which it would do in the return await case. Here's why you might see a performance difference:

Microtask Queue Management: Every time you await a Promise, the engine adds a microtask to the queue for when the Promise resolves. Using return await adds an unnecessary microtask because you could return the Promise directly, and the calling code will await it anyway.
Stack Trace Generation: When you use await, the engine keeps track of the function from which it was called for the purpose of generating stack traces if an error is thrown. This can add overhead compared to returning a Promise directly, which doesn't require the engine to manage the stack in the same way.
Optimization: JavaScript engines can optimize return someAsyncFunction(); more effectively than return await someAsyncFunction(); because the former has less complexity for the engine to analyze and optimize.

The performance penalty of return await is generally quite small and may not be noticeable in everyday code. However, it's a good practice to avoid unnecessary await for the reasons above, especially in performance-critical code or in loops.

Here’s an example where return await does make sense and has no performance penalty:

javascript
async function foo() {
  try {
    return await someAsyncFunction();
  } catch (error) {
    // Error handling
  }
}

In the example above, return await is necessary to catch any promise rejections from someAsyncFunction() within the foo function's try block. Without await, a rejected promise would not be caught by try/catch, and the error handling would not work as intended.

From CommonJS/Require to ES modules the easy way

2023-03-09T07:44:00.007-07:00

Introduction

When Node.js was first conceived, jQuery as a community; had embraced the AMD pattern and RequireJS in particular. Node.js was designed to run JavaScript code outside of a web browser, and as such, it needed a module system that was optimized for server-side development. CommonJS was the solution that was chosen because it fit the requirements of the Node.js ecosystem at the time.. CommonJS was the resulting solution and has been used in Node.js since v0.x.

Meanwhile, the browser has continued to evolve sought to address the need that RequireJS was filling. With ECMAScript 6 (ES6), ECMAScript modules (ESM) were introduced.

ESM is a newer module format that is part of the ECMAScript language specification, and it provides a standard way to define modules in JavaScript. ESM provides a number of benefits over CommonJS, including better performance, improved compatibility with tooling and bundlers, and better support for static analysis and tree-shaking.

Since the release of ECMAScript 6, many JavaScript environments have added support for ESM, including Node.js, web browsers, and many other runtimes.

FAQ First

1. What is CommonJS?

CommonJS module system is the default module system within the NodeJS ecosystem. CommonJS modules are the original way to package JavaScript code for Node.js. In terms of the loading paradigm for CommonJS, modules are loaded synchronously and are processed in the same order that the JavaScript runtime locates them. CommonJS provides require()

2. What are ESM?

The ES module usage format is the official standard to write JavaScript for maximum reusability and is what most web browsers natively support and Node.JS has fully supported since 12.x (experimental support as early as 9.x.)

3. What are major difference between CommonJS and ESM?

CommonJS is synchronous whereas ES is asynchronous
CommonJS supports only runtime resolution whereas ES supports both parse time and runtime
ESM support interoperability whereas CommonJS do not
CommonJS is the original standard in Node.js whereas ES recently achieved stable support and has been in in browsers for 5+ years
Common JS uses require() and ESM uses import export

4. What are the benefits of CommonJS?

CommonJS is the default standard and is supported in all Node.js versions. It is resolved at Runtime and has a wide amount of Dev support since it has been there since the beginning of Node.JS

5. Does Node.js use CommonJS?

Yes, CommonJS was the default Standard for module inclusion.

6. Does Node.js use ES Modules (ESM)?

Yes, ESM is fully supported since Node.js 12.x

7. Is CommonJS going away?

There is no sunset date on CommonJS, but it's not native to ecmascript as ESM is so it might be expected to be deprecated at some point in favor of ESM and, it is worth noting that many developers are now migrating to ESM, especially for new projects or where the benefits of ESM outweigh the costs of migration.

Commonjs/Requirejs/AMD pattern

function foo() {}

modules.exports = foo;

Use

foo = require('foo');

ECMAscript modules (ESM/modules)

export function foo() {}

Use

// An https url can also be provided import { foo } from "foo.mjs";

For some advanced tricks, check out Data URLs.

Package.json changes and file extensions

When using require('foo'); we are depending on CommonJS, which is well-established in Node.js since v0.1.0. As of node v9.x, it has been possible to enable an experimental flag to begin using ESM. As of Node.js v12.x, ESM are natively supported. The overall migration path from CommonJS to ESM can take multiple forms. To provide compatibility and keep longterm changes to a minimum, the following behaviors exist:

.js file extension is assumed to implement CommonJS
.mjs file extension is assumed to implement ESM
.cjs file extension is assumed to implement CommonJS
package.js can include { "type": "module" } to indicate .js file extension will contain ESM. With this, there is no longer a need to use the .mjs extension
Node can be run with --experimental-specifier-resolution=node to tell node to support CommonJS and ESM BOTH in .js files

ESLint

If you embrace ESlint, know that definitions must be based on es2021 (es12) or newer. Previous ecmascript versions require other approaches (like --experimental node.js flags.)

Bonus

Starting from Node.js 14.13.0 and higher, it's possible to import CommonJS modules using the ES module syntax (import/export). In other words, you can use the import statement to import objects from a CommonJS module that exports using module.exports.

For example, if you have a CommonJS module foo.js that exports an object like this:

module.exports = {
 a: 1,
 b: 2,
 c: 3
  };

You can import this object using the ES module syntax like this:

import foo from './foo.js';
      console.log(foo.a); // Output: 1

Note that you need to use a file extension of .mjs for the importing file (see above) if you're using ECMAScript modules. However, if you prefer to use the .js file extension for both CommonJS and ECMAScript modules, you can add "type": "module" to your package.json file OR run Node.js with --experimental-specifier-resolution=node

The FAQ and other bits where borrowed from:

https://www.knowledgehut.com/blog/web-development/commonjs-vs-es-modules

Reasons NOT to use ESlint (sarcasm)

2023-02-02T11:43:00.002-07:00

If you're looking to add chaos and confusion to your coding workflow, look no further than ESLint. This tool is designed to ensure that your code meets a certain set of standards and is free of any potential errors. But why would anyone want to use such a bothersome program? Here are just a few of the many reasons why you should avoid ESLint at all costs. Who needs organized and consistent code anyway? Who needs to save time by automatically catching syntax and formatting errors before they even reach the browser? And let's not forget about the joy of scrolling through hundreds of lines of messy, unreadable code. Who needs to be productive and efficient, right?

First of all, who has time to waste on pesky linting errors? It's much more fun to spend your valuable coding time debugging runtime issues. Not to mention, the rules that ESLint forces you to abide by are often arbitrary and outdated. Who wants to spend their days writing code that conforms to the stylistic preferences of others? Furthermore, the amount of time it takes to even set up ESLint can be a bit overwhelming. It might seem like a small task, but it can quickly become tedious and time-consuming.

Second, ESLint can be incredibly tedious to work with. It often requires you to spend hours hunting down small typos and other minor errors that could be easily overlooked. Not to mention, the linting rules can be difficult to decipher and often require you to make numerous adjustments to your code in order to comply. This can be incredibly time-consuming and ultimately leave you with code that doesn’t even meet the standards that ESLint was meant to enforce. Clearly, using ESLint is for the weak-hearted. It's for those who value productivity, consistency, and a well-organized codebase. But if you're like me, you'd much rather spend hours trying to decipher and fix code that could have been caught by a simple linter. So go ahead, do yourself a favor, and steer clear of the temptations of ESLint. Your code will thank you for it.

The final nail in the coffin is the fact that ESLint often introduces unexpected bugs into your code. Since the program is designed to catch coding errors, it can be difficult to figure out why an error is occurring, especially if you’re unfamiliar with the program. Furthermore, you can’t even trust ESLint to catch all of the errors in your code. This means that you may find yourself spending even more time troubleshooting and hunting down errors that the program missed. So, why bother using it in the first place? Furthermore, who needs the peace of mind that comes with knowing your code adheres to a standardized style guide, or the ability to easily catch potential bugs and security vulnerabilities before they become a problem? Who wants to work in a team where everyone follows the same code conventions, making collaboration smoother and conflicts less frequent?

In conclusion, ESLint is clearly not worth the headache. If you value your short-term sanity, you should avoid it. In the unlikely chance you like to sleep soundly, knowing your code is as solid as possible, you could look into it. What if sanity is overrated though?

Ecmascript es11 - es2020

2022-10-21T12:31:00.006-07:00

What's new with JavaScript in 2020 - Ecmascript 2020/ES11

Background

Before ecmaScript came Javascript. The creator Brendan Eich set out to create a language like, but simpler than Java. Javascript was originally created for Netscape and before it went down, a project was started to formalize the language and that became ecmascript. What we know today as Javascript, is really vendor-specific implementations of ecmascript.

Ecmascript didn't really gain traction until version 6 and it has continued to evolve since. Support for a given version is entirely dependent on the environment such as node vs browser, which browser, which version of that browser and such. Right now es version 13 also known as es2022 is stable, BUT support for it in Node isn't stable until version 17.9.1 (97% coverage). Since we are still on NodeJS 14, ecmaScript support is limited currently to es11 or es2020. When we make the move to Node 18.x, then we will have support for es version 13 aka es2022.

Hopefully you have some idea of the versions and timelines now, but why does it matter? Because each new ecmaScript version defines new features. As vendors improve support for that new version, they are exposed to developers in their products (like browsers and NodeJS). I show you all these now to give you an idea how many new features have released since es8/2017. I can't cover even a majority of them, but today I'm going to briefly highly some that may prove helpful in providing more stable code, code that's easier to read (and write tests for *nod*) or help you avoid anti-patterns or just write simpler code.

Nullish coalescing

A bit like using OR to return the first/left-most non-null, non-empty value; nullish coalescing returns the first/left-most non-null value, even if it's empty.

1. const response = {

2. settings: {

3. nullValue: null , height: 400, animationDuration: 0, headerText: '', showSplashScreen: false

4. },

5. };

6. const undefinedValue = response.settings.undefinedValue ?? 'some other default' ; // result: 'some other default'

7. const nullValue = response.settings.nullValue ?? 'some other default' ; // result: 'some other default'

8. const headerText = response.settings.headerText ?? 'Hello, world!' ; // result: ''

9. const animationDuration = response.settings.animationDuration ?? 300; // result: 0

10. const showSplashScreen = response.settings.showSplashScreen ?? true ; // result: false

11. const x = '' || 'x'; // result: 'x'

12. const x = '' ?? 'x'; // result: ''

Optional Chaining

When looking for a property value that's deep in a tree-like structure, one often has to check whether intermediate nodes exist before you can check for the deeper value. Optional chaining simplifies this by using a question-mark before the dot-notation.

1. const user = {};

3. Before:

4. var street = user.address.street; // Error: cannot read properties of undefined var street = user.address && user.address.street; // undefined

5. Now:

6. var street = user?.address?.street; // undefined

Logical assignment operator

This is a convenience operators, inspired by Ruby's . Javascript already has a dozen mathematical assignment operators , but we didn't have ones for the often used logical operators.

                
                    1.
                     
                    // Ok, but could trigger setter.
                  
                    2.
                     
                    opts.foo = opts.foo ??
                  
                    'bar'
                  
                    3.
                     
                    // No setter, but 'feels wrong' to write.
                  
                    4.
                     
                    opts.baz ?? (opts.baz =
                  
                    'qux'
                  
                    );
                  
                    5.
                     
                    // Setters are not needlessly called.
                  
                    6.
                     
                    opts.foo ??=
                  
                    'bar'
                  
                    7.
                     
                    // No repetition of `opts.baz`.
                  
                    8.
                     
                    opts.baz ??=
                  
                    'qux'
                  
                    ;

                
                    9.
                     
                    // This always logs "setter called"
                  
                    10.
                    
                    obj.x += 1;
                  
                    11.
                    
                    assert.equal(obj.x, 1);
                  
                    12.
                    
                    // Logical operators do not call setters unnecessarily
                  
                    13.
                    
                    // This will not log.
                  
                    14.
                    
                    obj.x ||= 2;
                  
                    15.
                    
                    assert.equal(obj.x, 1);
                  
                    16.
                    
                    // But setters are called if the operator does not short
                    circuit
                  
                    17.
                    
                    // "setter called"
                  
                    18.
                    
                    obj.x &&= 3;
                  
                    19.
                    
                    assert.equal(obj.x, 3);

Object rest/spread

ECMAScript 6 introduces rest elements for ARRAY destructuring assignment and spread elements for ARRAY literals. With es11, we get rest properties for OBJECT destructuring assignment and spread properties for OBJECT literals.

          
              1.
               
                let
              
              { x, y, ...z } = { x: 1, y: 2,  a: 3, b: 4  };
            
              2.
               
              x;
            
              // 1
            
              3.
               
              y;
            
              // 2
            
              4.
               
              z;
            
              // { a: 3, b: 4 }
            
              5.
               
                let
              
              n = { x, y, ...z };
            
              6.
               
              n;
            
              // { x: 1, y: 2,  a: 3, b: 4  }

Promise.allsettled

Previously we were given Promise.all, Promise.race, and Promise.any. Other Promise combinators can short-circuit, discarding the results of input values that lose the race to reach a certain state. Promise.allSettled is unique in always waiting for all of its input values. Promise.allSettled returns a promise that is fulfilled with an array of promise state snapshots, but only after all the original promises have settled, i.e. become either fulfilled or rejected.

'The Promise.allSettled() method returns a promise that fulfills after all of the given promises have either fulfilled or rejected, with an array of objects that each describes the outcome of each promise.'

          
              1.
               
              const promise1 = Promise.resolve(3);
            
              2.
               
              const promise2 =
            
                new
              
              Promise((resolve, reject) => setTimeout(reject, 100,
            
              'foo'
            
              ));
            
              3.
               
              const promises = [promise1, promise2];
            
              4.
               
              Promise.allSettled(promises).
            
              5.
               
                  then((results) => results.forEach((result) =>
              console.log(result.status)));
            
              6.
               
              // expected output:
            
              7.
               
              // "fulfilled"
            
              8.
               
              // "rejected"

Conclusion

ECMAScript is constantly evolving and the more current your environment (latest Node.js, browser, or other client), the more features you'll have access to. Be sure to keep an eye on which version of eslint you want to target by watching resources like https://node.green/ and https://caniuse.com/?search=es11.

JS Promises - Execution Order and Timing

2021-10-11T18:38:00.005-07:00

As long as I've been working with JS (just look at how old this blog is to begin getting an idea), I've continued to struggle with execution order and wanted to get it clear in my head. The following helped me do that so I wanted to share.

GitHub Gist

console.time('full execution');
console.time('code block');
function showExecutionOrder(parm) {
    console.time('outside promise');
    new Promise((resolve, reject) => {
        console.time('inside promise');
        resolve(parm);
        console.timeEnd('inside promise');
    }).then((data) => {
        // Lookup mdn and invoke the account sync as required
        console.log({ data });
    });
    console.timeEnd('outside promise');
}
console.time('function call');
showExecutionOrder({ foo: true });
console.timeEnd('function call');
console.timeEnd('code block');
console.timeEnd('full execution');

Update: Another demonstration, in another context: https://gist.github.com/rainabba/6847b06bff1f5a37bb19663c7a4e3c0e

Executing Gitlab-runner locally with Docker (local runner and local code)

2020-09-21T12:38:00.002-07:00

It's hard to prioritize writing when I have so many responsibilities AND interests, but when my battles stand to save others days or weeks of pain (or abandoning a project) and it can hilite my work (rare), I must write, right!? ;P

So far, I cannot get a runner to use my local files mounted, but I can commit locally, execute the runner locally and have it use that latest commit (not yet pushed). This is arguably better than my present approach other than having to commit (even locally) for every change.

If anyone knows how to skip Git locally all-together, I'd love to hear how!

What you wanted!

mkdir -p ./.gitlab-runner/builds \  
 docker run --name=runner-${PWD##*/} --privileged -t --rm \  
 -v /var/run/docker.sock:/var/run/docker.sock \  
 -v $PWD/.gitlab-runner/:/etc/gitlab-runner \  
 -v ${PWD}:${PWD} \  
 --workdir $PWD \  
 gitlab/gitlab-runner \  
 exec docker --builds-dir $PWD/.gitlab-runner/builds/ yourStage;

If "yourStage" were debug and your .gitlab-ci.yml looked like the following, you should expect to see the output of the `ls` command reflecting your WORKDIR.

image: docker:git  
 stages:  
  - debug  
 variables:  
  DOCKER_DRIVER: overlay2  
  DOCKER_TLS_CERTDIR: "/certs"  
  CI_REGISTRY: registry.gitlab.com  
 before_script:  
  - printf "::STARTING_BEFORE_SCRIPT\n\n";  
  - export REVISION=$(git rev-parse --short HEAD)  
  - printf "::REVISION=${REVISION}\n"  
 debug:  
  image: docker:19.03-dind  
  stage: debug  
  script:  
   - pwd; ls -lah;

I hope to spend time in the near future covering the experiences I've had implementing GitLab, challenges I've faced, solutions to those challenges and my hot-takes on the overall approach. For now, I hope that helped someone else because it was a long-time coming for me :)

Chrome DevTools has implemented code-folding (as of v73 apparently)!

2020-09-02T08:32:00.000-07:00

Open Chrome devtools settings, then under preferences, sources, enable "code folding", then code suddenly becomes more manageable in DevTools :)

https://developers.google.com/web/updates/2019/01/devtools#folding

https://bugs.chromium.org/p/chromium/issues/detail?id=328431#c33

Before:

After enabling code-folding:

Installing WSL+Ubunutu+Docker on Windows 10/2019 1803

2018-06-01T14:08:00.002-07:00

How's that for a needfully-long title? This article comes years after my first taste of Docker and some weeks after diving deep to migrate a legacy app, to node.js, to docker containers so it can be managed and run more effectively.

There is a LOT to share, but for the moment I'm going to focus on the biggest pain-point in getting to really appreciate what Docker can do for a Windows developer; getting Docker running in an environment friendly to all you'll find about Docker on Linux or OSX!

In a nut-shell, you need WSL (which effectively connects a "distro" to Windows low-level APIs). Then you need an environment/distro to actually work in. I'm using Ubuntu here and some of the script is sensitive to that, but there are many other distros available now so you have freedom. Once you have Ubuntu and WSL, you can install Docker-CE. You need CE specifically to work nicely with WSL, otherwise you can use the regular Docker, but then why are you reading this?!

To help ensure my environments were consistent (and because I had to try this dozens of times before it all worked for me), I've created a bash script and in the comments are 4 PowerShell commands you can use to get started with nothing more than a working install of Windows 10 1803 or Server 2019 Preview 1803. I'll let the script explain the details and I make no guarantees about this script so test in a safe place, but I rely on it :)

**Bash script**
https://gist.github.com/rainabba/6f345c439261882e0c1e648fcfc43df4

Uninstall OneDrive from Windows 10 - half-baked

2017-04-28T14:29:00.001-07:00

OneDrive is a "cloud-file" service by Microsoft which is not unlike Google Drive, DropBox, Box, SugarSync and like Drive also provides some nifty web-based tools.

OneDrive is NOT critical to any aspect of Windows. OneDrive is treated by MS as an app (nota service) in all respects except the implementation in Windows which is atrocious.

You can disable the "Start with Windows" option then exit it (like any other systray service), but it will pop back up later and harass you if you've not set it up. That sort of behavior is more what you'd expect from a "Windows Feature" which you'd turn off using the Windows "Programs and Features" dialog.

That's NOT how OneDrive is to be managed though so if you don't use and don't want to see it, be prepared for the most absurd "configuration" I've ever seen from MS. Even a registry change would be easier than this mess....

https://support.office.com/en-US/article/Turn-off-or-uninstall-OneDrive-f32a17ce-3336-40fe-9c38-6efb09f944b0

WHY? Microsoft, WHY are you pushing OneDrive at me SO HARD that you're doing stupid crap like this? Either make it part of the OS (and a service we can just simply disable) or make it a Feature that can be managed reasonably.

Who am I? Who are you?

2017-01-04T14:32:00.000-07:00

What part(s) of our body are permanent? That is, what parts grow, then never get replaced/recycled/regrown?

If all if it, then we are NEVER the same person from moment to moment in the most literaly sense.

Since we appear to have consistency from day to day, the process must be somewhat slow. What about year to year or decade to decade? Is the process that slow though? If not, how are we consistent across so much time in appearance, personality, habits and such?

DNA likely accounts for much of this, but how much? If none, then where does it come from? If all then the moment we're concieved, we ARE who we are. We may make choices along the way, but those choices are a result of who we are so those choices are determined in the most fundamental sense, the moment we're conceived.

If it's not entirely DNA that dictates who we are, then how much of it is DNA (nature) and how much is otherwise (nurture) and where is that nurture recorded/maintained in ourselves? Our brain? How fast does it regenerate itself? If not at all, then our brain IS who WE ARE. If it regenerates over time, then either that period of time is how often we change OR there's some other part of us that dictates who we are.

Perhaps DNA kickstarts us, our brain is US from day to day, and as it regenerates, it's influenced by who we are (what we do, think, etc..) and so we end up with consistency. In that case, we could halt that consistency up to the point of who we are from our DNA, by interurrupting our decisions and environment completely.

What part of ME is seeking these answers? Why do so many humans seem to have the same quest? Is that explained by DNA or circumstance? If the former, we all are likely to find us here eventually. If the later, some cultures will never ask these questions because they will never come into contact with those who do. How could we know though because if you're asking these questions, you can't go ask others or lead them to the question without putting it in their "minds". It's a bit like (to quote Alan Watts) saying, "Don't think of a pink elephant while taking your medicine." Once heard, one cannot avoid the thought because it's already been comprehended.

Relaxing in a houseboat on the Amstel, overlooking the Magere Brug - Perspective

2016-11-05T08:21:00.002-07:00

The tour boats full of people taking in the sights keep sliding by. The sun occasionally teases me with it's warmth, but mostly stays hidden behind clouds that promise more rain, but that doesn't really bother me; I have an umbrella for that.

I'm sitting on a cute little couch, in the parlor for a beautiful houseboat and it feels like one of the 100's of cafe's nearby. Across the river are homes that have existed more than 5 times longer than I have. At any given moment, I can see more people on bicycles than cars and boats combined and that's saying something because there are a LOT of boats here on the river and the nearby canals I can see.

The Michelangelo, one of the boats belonging to "LOVERS canal cruises" just did a graceful pirouette to turn around and head back up river. A lot of the tour boats do that right here, in front of my little home for the week and I wonder why. Not all of them though and the ones that continue down river have a very tight squeeze to get through if they want to go under the Magere Brug, the "Skinny Bridge" that is an extremely old, manually operated, wooden draw-bridge meant only for pedestrians and cyclists and even they have to be careful as they pass each other over the top.

How did I end up here? Just last week my 2 year-old daughter was to undergo a dangerous surgery to remove a chunk from her left lung where a pocket has formed that held group a streptococcus; an infection that nearly took her life. It looks like her body is finally dealing with the pocket that was leftover so the surgery was canceled, much like my life had been when we found out the doctors wanted to do the surgery. My wife Jessica and I both stopped making plans. I resigned from my latest venture; something I'd been close to doing anyway after 2.5 years of the most unreal stress and accomplishments I could never have imagined. I say that as a US Marine that's had more than a few challenges in life too. That journey took me to New Zealand, introduced me to famous musicians and made me an "Executive Producer" working for the likes of Samsung and Red Bull at the largest music festivals in North American. Hell, I got to be the first one (literally "ME") to do a major 360, live-streaming production for and to YouTube to help them show off their newest feature.

I'm just a geek that likes to learn, explore, play with technology and quietly build relationships with others of a like mind though. Few people really know my name. Fewer have any idea what skills I posess, I'm nothing close to important by the social and cultural standards that surround me, yet I find myself in a position that is about as likely as winning the lottery back home I think. I grew up poor with very few privileges save for being a white, male which lately feels as much like a curse as anything given all the resentment aired in the media from those who aren't "white" or "male" which I think is more people than not.

All I do know is that right now I've got peace and I hope that my perspective on this moment is clear and my appreciation for it is deep and complete.

Thanks to my friend Tim for inviting me to his home town to help "consult" for him and making this all possible. Thanks to Kelly for making me feel so welcome every time I see her. Thanks to Ben, Wim and everyone at VRDays for throwing a great event and showing me so much hospitality. Most of all though, thank you to my wife Jessica for giving me her blessing to go on this trip and find this moment of peace while she stays home taking care of my 3 treasured children even though I've been traveling so much and have to leave again only a day after I get back home. Without her, Andrew, Jolie and Ayla back home, I think I'd only be lonely in this moment, but instead I feel loved everywhere I go.

Building ffmpeg with opencl support on Linux (AWS Linux AMI)

2016-06-06T11:52:00.000-07:00

The last year I've learned more about video, live production, DIT, editing, encoding, players, codecs and ffmpeg than I could have imagined there was to know (and that only of course proved that there's 1,000x more to learn), but one particular part of this journey has proven VERY difficult so I wanted to share some of that.

ffmpeg is an open-source project and there are NO definitive binaries for any platform. There ARE some great builds out there which are well-maintained and very useful, but they aren't "official" and they weren't meeting all my needs so I had to setup a basic build environment which proved difficult itself for me even though I've been compiling on Linux (building Android Kernels even) for some 15 years.

I've put together a GIST to share the key points (an updated ffmpeg build with x264, x265, aac and opencl acceleration in particular) and I'm still evolving it. Find that gist HERE.

If you already know how to build, this should be a great reference. If you don't and want to use this with no real experience, please know that this was done an an AWS G2 instance (nvidia grid GPUs) running an AWS Linux AMI so it won't copy/paste/work just anywhere, but if you're running a distro with YUM and have an nvidia card, it should be pretty close at the least.

Who IS a "professional"?

2016-01-26T08:38:00.001-07:00

I subscribe to very few blogs and today an article was posted on what may be my favorite, and it got me thinking. The following started as a reply, but I decided it might be appropriate here too.

In the last couple years, I've been forced to reevaluate myself in light of my career. I've spent nearly 2 decades in software in one form or another and despite being able to make some pretty hefty claims; they always sounded exaggerated to my own ears, when coming out of my mouth so I felt awkward calling myself a professional even though I can't imagine many people refuting the claim. Still, I was reluctant to claim the title until my personal interest in virtual reality, backed by my years of photography and a years of "playing around" with a variety of video technologies saw me into the role of CTO in an up-and-coming VR company which in turn found me working side-by-side with (not employed by or for to be clear) the production team for RedBull, with the streaming engineers they use to broadcast to the Internet, and helping Samsung give 1,000's their first experience with VR at the largest music festivals in North America.

This article [https://houldsworth.wordpress.com/2016/01/26/what-makes-a-professional] resonates with me because by most objective definitions, I'm a professional software developer and DBA, but I didn't feel like it and few labeled me as such who had the knowledge and experience to do so (worth mentioning that I work from home and am not even surrounded by co-workers or peers often in that field). On the other hand, I'm quite new to the "professional" field of photography, videography and VR, yet I don't mind saying that I'm one of very few people in the world who has done a real-time video production broadcasting to VR and I've been complimented by some rather significant people in the industry both explicitly and implicitly and a large part of that comes down to the fact that we show up to do what we do amongst 10k's of people, have to deal with incredible challenges on the fly and have yet to fail.

Am I more of a "professional" for having spent decades in a field, or for successfully doing something new and difficult? I think you raise a great point and I'm presently of the mind that I am on both accounts, but for very different reasons in each field. In the end, not even others with experience in these fields; paid or not, could do what I do readily (and for pay) and that seems like a good basis to label me a professional in general and in those fields. It does not mean that others are not are not either though, so where do we stop applying the label OR is the label possibly less meaningful in this world where knowledge and experience are such different beasts?

Was Einstein a professional in physics when he was a "only" a patent clerk, but generating his Theory of Relativity, or did he not earn that title until he quit and started receiving funding and/or recognition for that theory?

Is a soldier a professional right after boot-camp, or not until he's fought in a war [and killed an enemy?]

FINALLY working on my pilots license for real

2015-08-14T10:13:00.000-07:00

I've had a few false-starts towards my powered license, but each time I lost the motivation just enough and didn't really undestand why until a few weeks ago when I was in Chicago (doing a production at Lollapalooza to bring vantage.tv to the public for the first time) when a friend hooked me up with an instructor and we took a Cessna 172 out, did a touch-n-go at Midway, flew out over lake Michagan than did some slow-flight work before returning, all after dark.

That same friend got me interested in gliding simulators such as Condor and Silent Wings, some months ago. I've been building and playing with toy/model/rc gliders my entire life and I've always been fascinated. Somehow though, I never made the connection and suddenly I realized that it's not so much "flight" that I'm interested in as "unpowered flight" (soaring, gliding, para-gliding, para-sailing, etc..). This realization motivated me to locate an instruction school nearby and I was luck to find AZSoaring.com (owned by a family that's been gliding for decades and largely managed by a champion aerobatic glider pilot). I think I've found that hobby I've been looking for my entire life. No sound but the wind, almost nothing obstructing my view of the world, and the perfect balance between me, nature and machine.

This was the first of 3 flights this day and despite decades of simulator time, I was surprised at how much higher my cognitive load was compared to when I'm in a sim and what I expected (I knew it would be at least somewhat higher).

By flight #3 (with plenty of coaching an an instructor ready to take the controls at any moment of course), I was largely handling takeoff, tow, release, flight, pattern, descent and landing.

I was also pleasantly surprised at how nice the 2-33 was to fly despite my preconceptions about how "poor" a glider it is. In reality, it's magnitudes nicer to fly that a 162/172 (by my tastes) which makes me even more excited at the idea of making my way to the Grob 103a and such.

Adventures in Git OR How to fork folders in one Repo to their own repo with history

2014-10-07T00:40:00.003-07:00

In short, I had one repo, with multiple folders where each really represented its own project and I needed to fork each folder to a separate repo WITH history. This is the solution I came up with. This does require git 1.8.4 (git subtree split).

git subtree split --prefix=sourceFolderInAnyExistingProject -b anyNewBranchNameForFork

mkdir ../someNewRepoFolder

cd ../someNewRepoFolder

git init --bare

cd backToOriginalWorkingFolder

git push ../someNewRepoFolder anyNewBranchNameForFork:master

cd ../someNewRepoFolder

git remote add origin YourNewRepoRemote

git push -u origin --all

cd ..

rm -rf somenewRepoFolder

git clone YournewRepoRemote someNewRepoFolder

Sorry if that's not clear enough, but basically, you use git subtree split to take ANY folder presently in a repo and create a branch that's filtered to have just that folder and all the history for it. Then you create a bare repo, push the branch into it, then push that repo (without working folder) to your new repo, then either trash the folder or clone the repo into another one and BAM, you've forked not only an existing repo, but just one folder in it if you prefer (I had many "projects" in one repo that needed to be forked individually so this was useful for me) and history stays intact.

SuperAdmin (GodMode) folder for Windows 8.1

2014-04-04T11:59:00.000-07:00

I didn't think there were any cool tricks left for Windows that I wasn't aware of but I just learned otherwise.

Create a folder using one of the following names based on your version of Windows and have access to a SuperAdmin folder that makes finding all sorts of admin shortcuts as easy to find as they always SHOULD have been. I've only tested the 8.1 but am under the impression that it should work for 7 and 8 also.

Windows 8.1 - SuperAdmin.{ED7BA470-8E54-465E-825C-99712043E01C}

SSL Certs for IIS with PFX once and for all - SSL and IIS Explained

2014-03-07T17:19:00.001-07:00

The problem is more common than dirt but the solutions provided are so often entirely incorrect and obscure and that's likely because the "Linux and Apache" folks are trying to use their standard approach with MS platforms that like to do their own thing.

Here's what you need to understand:

CSR - Certificate Signing Request: A CSR is how you ask for a certificate and provides things like your identify, the use, etc..

KEY - Private Key: When someone uses the public key that you share with the world (like that which your web server will give the client and they will use to encrypt traffic), your possession of the private key is how you prove (as a web site) that you are master. You encrypt using your private key and the client decrypts with your public key. ANYONE can have your public key and thus anyone can decrypt but since you are the only one with a private key, it is guaranteed (when you control that key correctly) that if the public key works, traffic must have come from you. Similarly, anything encrypted with your public key can ONLY be decrypted using your private key.

CER/CRT/CERT/CERTIFICATE - Public Key: See KEY explanation

PFX: Along comes microsoft and their proprietary way of doing things and the confusion that follows. IIS expects a PFX but the format has nothing to do with the standards world of PKI, keys and certs really. So how do you give them a PFX that includes the private key (needed to encrypted/decrypt your web traffic)? The intended way is for you to generate the CSR using IIS then give that CSR to your CA (internal or public) then get a key back based on the private key known by the creator of the CSR (IIS). This is where things are "all wrong" in the public CA business (from the perspective of us using IIS but really, they have it right). Most likely you created the CSR using your CA or the company reselling for them (cheapssl, gogetssl, etc..). When you do this, they give you a private key to keep safe and a public key to use but IIS/Windows has no concept of the private key so you're dead in the water from the start.

The solution:

Use IIS "Server Certificates" UI to "Generate Certificate Request" (the details of this request are out of the scope of this article but those details are critical). This will give you a CSR prepped for IIS. You then give that CSR to your CA and ask for a certificate. Then you take the CER/CRT file they give you, go back to IIS, "Complete Certificate Request" in the same place you generated the request. It may ask for a .CER and you might have a .CRT. They are the same thing. Just change the extension or use the *.* extension drop-down to select your .CRT. Now provide a proper "friendly name" (*.yourdomain.com, yourdomain.com, foo.yourdomain.com, etc..) THIS IS IMPORTANT! This MUST match what you setup the CSR for and what your CA provided you. If you asked for a wildcard, your CA must have approved and generated a wildcard and you must use the same. If your CSR was generated for foo.yourdomain.com, you MUST provide the same at this step.

Now select the PERSONAL store (No, not webhost). This will import your CRT in the personal store where it can be associated with the private key generated by IIS when it created the CSR. THIS IS WHERE ALL THE PROBLEMS COME FROM. This is what causes SO many headaches. The CRT you got from your CA and the KEY they gave you are useless here unless you do as others might suggest and go play around with other tools like openssl (which can work but why bother when you can do it the way IIS intended?)

Now you should see your cert in the server certificates list and if you open it, you should see something like, "You have a private key that corresponds to this certificate".

Now if you can use the Export function (IIS 8 provides this in the same place as the "request" and "complete request" links) or use the Certificate MMC then navigate to the personal store and export from there to the PFX format. You need to provide a strong password to protect this file because it will have the entire certificate chain AND your private key. In other words, this PFX has the keys to the entire "domain" (speaking figuratively).

Chances are that you don't even need the PFX now because you already have the certificate inside IIS but if you're using the centralized certificate store like I am, you do AND the file name is critical. For wildcard certs, the name MUST be _.yourdomain.com.pfx (assuming your request was for *.yourdomain.com). If you asked for www.somedomain.org, then the filename must be www.somedomain.org.pfx because this is how SNI and centralized SSL store will look for the right one.

In summary, the easy way to install an SSL cert into IIS:

Generate your CSR using IIS
Provide that CSR to your CA
"Complete Request" using the CER/CRT you get back from the CA
[optional] Export to PFX and protect with a strong password
Live long and encrypt

Update (20191201): Even today, I am using this post as I have to renew SSL for a stack that lives both on IIS and Node.js. Because of this, I also need the private key file so if you've done step #4 above and need a .key also, the following might save you some googling. Be sure to protect your .key file when you do this though!

`openssl pkcs12 -in exported.pfx -nocerts -out key.pem -nodes`

then

`openssl rsa -in key.pem -out server.key`

Now you you can use server.key and the cer/crt you were provided.

My first experience with VMware vCHS - Part 2 - vCloud Connector

2014-03-04T11:33:00.001-07:00

This is the 2nd in a vCHS series. You can find the previous entry HERE.

OnPrem - vCloud Connector (general label for a collection of systems and configuration)

If you don't know what vCloud is or about the vConnector, right now all you need to know is that you can't do actual migrations (it creates vApp templates from powered down VMs) and the only other thing is really useful for are stretch migrations (a vShield networking trick that are only useful in some very rare situations.

VCC does NOT allow you to use the vSphere client to manage vCHS any more than you can do on the web (for the most part, it just gives you a window to the web interface and does some back-end management that you can also initiate from the web).

vCloud Connector Server - Provided as a zip containing an OVF that can be easily added to any host onPrem. Once you've installed, visit https://assignedip:5480/ (port 5480 is a theme so learn it). Once you've configured networking, set the time-zone and changed the password, contine to the Node which is the same process.
vCloud Connector Node- Provided as a zip containing an OVF that can be easily added to any host onPrem. Once you've installed, visit https://assignedip:5480/

Once you've installed the node and done the same basic config (IP/Time-zone/Password), you need to go to the Node/Cloud menu and register your vCenter to the node (the node manages vCenter and the VCCS manages the node).
Next you can go back to the VCCS and "register the node".
Now we want to register the vCHS node to your VCCS.

This is what allows you to use your vCenter to manage onPrem and vCHS together (and any other nodes you register). This is where I hit some frustrating resistance.
To register vCHS node you need the Node URL (given to me in my onboarding email), VCD Org Name (not given to me and I had to deduce that it was provided in vCHS vCloud Director. It is the unique ID at the very top of the page, next to the navigation arrows. For me it was MXXXXXXX-XXX. You also need a username and password which you might think should be the same you log into the vCHS portal with but it apparently is not.
After a few failed attempts, I was able to navigate to the vCloud Director, My Cloud, Logs, Events and see the failed attempts. Despite multiple emails and a phone call to vCHS support, I presently do not have the credentials I need so I'm stuck with the connector for now. More to come.....
UPDATE: After speaking with vCHS support, it sounds like my credentials are out of sync in one of their DBs and I was doing everything right. Now I wait for them to tell me it's fixed.
The solution came fairly quickly (less than 2 hours) and I had my vCHS node registered with VCCS.

If you have questions, please feel free to ask in comments. This was someone brief but it's because once it's working, it's really very straight-forward until/unless you try a stretch deploy (which I haven't).

Next will be an entry on vCHS networking.

My first experience with VMware vCHS - Part 1 - Setup and IPSEC

2014-03-04T11:09:00.000-07:00

Prologue to vCHS Migration

I've decided to do a few articles regarding my migration to VMware vCHS (cloud hosting) solution and this is the 1st in the series.

I've had a few significant technical issues but the support has been as good as I can imagine. Last night I even met up with the specialty sales-rep assigned to my account and we spent nearly 3 hours talking over dinner about things in general and my project. VMware is not only doing more than I could hope to get me up and running but they're also looking at how they can help me through their "success stories" to help promote our business in a mutually beneficial manner which is wonderful because after 10 years of seeing 20%+ growth per year, we're likely going to explode this year leaving those gains in the dust and any help they provide will only strengthen our growth.

By the way, the "Customer Success Team" isn't a hollow catch-phrase. It reminds me of my experience as a consumer with American Express. They JUMP every time I need help. We have scheduled 2 hours calls (that we 3 hours) where they literally sat on the phone with me to walk through issues and wait for me to learn and question them AND did it with a wonderful attitude (sincerely eager to help).

In summary, the migration has been rough, but when do they go smooth? That said, I can't imagine a better infrastructure than they're giving me and their support is the best I've seen for any product/service anywhere save perhaps for high-end auto purchase experiences I've had.

I would HIGHLY recommend vCHS to anyone that needs a rock-solid, highly flexible hosting solution that covers everything from end-end.

At the moment we have 3 units of the VPS solution (they have dedicated and shared, VPS is the shared solution) which includes 15GHz dedicated CPU (you really can't talk cores or speed with the way they work), 30Ghz Burst, 60GB Ram (dedicated) and 2TB of SAN storage that is SSD cached and I'm constantly seeing 150MB-250MB/s with <2ms latency and my SQL Server is running as fast as it was locally with dual-quad xeons on a 8-disk RAID 10 over 15kSAS drives.

My first experience with VMware vCHS - Part1 - Setup and IPSEC

My present hosting provider hasn't been a pleasant experience. I seem to have some bad luck this way. My last experience was with RackSpace who has very good service in so many ways, but I found out the hard way that their security is severely lacking and when they make a mistake that cost me $10,000's, they had NO interest in taking responsibility and I'm not big on law suits so I dealt with the months (almost years) of heartache, moved on and tried Central Host (the hosting division of 8x8 which has since been bought up by Black Lotus.

My experience with 8x8 was a nightmare and I'm still feeling the pain as Black Lotus does their best to clean up the data center I'm in. They've also made amazing efforts to make things right with me but I'll leave that for my other blog. In the end, they offered me an incredible deal (~$2,000/mo for dedicated virtual hosts, 6-core HT, 3.5Ghz Xeon CPUs, 32GB ram, 2TB SATA RAID with 200GB SSD caching, 24 IPS and each of 2 hosts were at different data-centers) but they use App-Assure (Xen and/or Kvm) and I'm a Vmware guy interested in uptime and performance more than raw performance and didn't want to learn new systems either. VCenter is amazing and I know how to keep my business running with it so I went with vCHS. I also appreciate the way vCHS scales compared to typical virtual hosting solutions. I don't have to worry about "hosts".

The way the actual provisioning went was very straight forward. I got an email once the contract was signed and they told me provisioning had started. Once provisioning was done, I got an email with vCloud login and password setup links. I set my password, logged in, and headed over to the edge network configuration interface in the vCloud Director portal (the things they haven't made more simple and put into the vCHS portal and accessed through a full-blow vCloud Director instance which I prefer anyway not having really taken to the vSphere Web interface as it is).

Since I use pfSense (presently 2.1 and everything below assumes that) at all my other data-centers, I did a quick search and ended up using THIS guide as a reference to catch the nuances of their IPSec implementation (main/aggressive, which encryption he got working, etc..)

From there I went to my only gateway, edge gateway services, enabled VPN, setup the public IP, then added my tunnel (they combine phase 1 and phase 2 into a single UI). I quickly found that they use main and not aggressive which I should have caught from the tutorial I found. This is where I had my first issue. vCloud directory gateway status shows "System Alerts" with a red icon that was clickable and I wanted to see what it had to say so I clicked it and watched the entire UI refresh. I tried this a few times before giving up. I'm guessing it's a popup blocker issue at this point but since the directory comes up in a new window with no address bar and uses Flash (grr, WHY would they do that with such a new system???!!!) so there was no way to tell quickly and so I gave up there and went back to pfSense logs to see how things are going.

As so often is the case when doing IPSEC between pfSense and anything other than pfSense, I had to figure out what IPSEC standards they use. Here's what I found and I hope it saves someone some time. It's taken me years to get to a point where this doesn't become an all-night project:

If you know what you're doing and want to skim the settings, just know that even though vCHS asks for "Peer ID", it only supports Main mode which only supports IPs are IDs so Peer ID MUST be the remote gateway IP. This stinks for those of us trying to use more advanced methods to get around dynamic IPs. Really, "Peer ID" should read "Peer IP" and the only reason you have to provide both it AND "Peer IP" (which should read "Peer Gateway IP") is because they do support NAT-T.

Once I realized my mistake with the Peer ID, I had to delete the entry and create a new one then got an error about "Configuring Edge Gateway Services". I refreshed and it disappeared so I figured it was a fluke until I was seeing the same errors about IDs and when I check vCHS, the settings were back to the first entry so I deleted and tried again tripple-checking using the settings below and THEN I got a connection (I already had phase 2 setup. See below Phase 1 for settings). Once everything was working, my IPSec log had only 3 entries before a full connection (since there were so few options or advanced features being used).

Phase 1

Main Mode
Name: Anything descriptive you like
Description: More descriptive stuff you like
Enable this VPN: checked (default)
Establish VPN to: "a remote network"
Local Endpoint: (predefined external IP endpoint at the vCHS end)
Local ID: The vCHS public IP assigned to the local endpoint (pfsense: Remote Gateway and Peer identifier)
Peer ID: The IP of the remote gateway (pfsense: My identifier, My IP Address)
Peer IP: The IP of the remote gateway
Encryption protocol: AES-256 (pfsense: same for Phase 1 Encryption algorithm)
pfsense-Hash: SHA1
pfsense-DH Key Group: 2 (1024 bit)
pfsense-Lifetime: 28800
pfsense-Nat-T: Disable (if you need it, enable and update the Local ID on vCHS accordingly)

Phase 2 (pfsense)

Mode: Tunner IPv4
Local Network: Lan subnet
Remote Network: CIDR format for remote subnet (ex. 192.168.110.0/24)
Protocol: ESP
Encryption: AES 256 (they only appear to support AES at this time)
Hash: SHA1
PDF key group: 2 (1024bit) (they support off also)

Adventures in Node.js - Using NPM on Windows

2014-02-28T10:12:00.001-07:00

The following still needs to be more carefully verified but I'm making this public now to help someone and hopefully do just that....

We'll call this installment #2 of "Adventures in Node.js" even though my previous Node entry didn't have this in mind.

I'm short on time today so I can't elaborate so much but in short:

One time on your machine:

Install Python 2.7 and add the python.exe folder location to your PATH environment variable.
Either 1 or 2 depending on your setup:

If you don't have Visual Studio 2008 installed (which provides vcbuild.exe):

install the Windows SDK (to provide vcbuild.exe). Good reference at https://github.com/TooTallNate/node-gyp/wiki/Visual-Studio-2010-Setup then ensure that the path to vcbuild.exe is in your PATH environment variable
npm install -g socket.io --msvs_version=2012

If you DO have VS installed, run the following to setup your environment properly:

Add the path to vcbuild.exe to your PATH environment variable then run the following
npm install -g node-gyp
node-gyp configure --msvs_version=2012
node-gyp build
npm install -g socket.io --msvs_version=2012

Once for your project:

npm install

Now your project should be ready for you to use npm in general. My purpose today was to check out grunt, grunt-cli and grunt-devtools thanks to recommendations from Paul Irish both at Google I/O 2013 and a couple weeks ago at the Chrome Dev Summit.

Now that I have npm working it was as simple as (from http://gruntjs.com/getting-started#preparing-a-new-grunt-project):

npm install -g grunt-cli
npm install grunt --save-dev
npm install grunt-devtools

Next I try to setup and use Yeoman (another framework he suggested that relies on Grunt).

How We Can Begin to Fix the Government and Your Responsibility and Right as a Juror

2014-02-25T16:18:00.002-07:00

One way we have to begin to get our government back in check 100% legally, without any violence

WARNING: If you continue reading, you will likely ruin your ability to serve on any jury that is well managed OR you will forfeit your ability to use this knowledge without being guilty of perjury. This is no joke and you better research this yourself because I'm not responsible for your actions, your interpretation of this information, or any consequences. On the other hand, it is YOUR RESPONSIBILITY as an American to know this.

YOU WERE WARNED

Scroll down to read....

Pushed down so you must scroll to read and won't be exposed without that effort......

*Jury Nullification*: Ultimately, it's the jurors RIGHT and RESPONSIBILITY to make a guilty judgement not ONLY based on the facts and law, but ALSO on what you think is right; thereby judging the law itself as well as the "crime". It is a mechanism very intentionally built into the core of our legal system.

This is not my interpretation either, this is our founding forefathers design:

John Adams wrote, “_It is not only the juror’s right, but his duty to find the verdict according to his own best understanding, judgment and conscience, though in direct opposition to the instruction of the court._”

Thomas Jefferson wrote, “_I consider trial by jury as the only anchor yet imagined by man by which a government can be held to the principles of its constitution._”

This video and the following link help explain but beware because jury selection includes questions worded very carefully to eliminate people who understand their full responsibility and power as a juror and those questions are typically worded in a way that if you use jury nullification, you will likely find yourself guilty of perjury. This is because the people who run the legal system as as susceptible to this power as criminals and your ignorance of it gives them tyrannical power. As long as they can keep you off a jury, they can manipulate the legal system rather than have it manipulated by the people who should be doing so, "THE PEOPLE".

The only real way to address this abuse is spread the knowledge so far that they cannot reasonably assemble an otherwise fair jury without allowing jurors who know their full responsibilities and rights as a juror.

How to KILL Performance in Chrome 34 dev channel with one CSS rule

2014-02-11T21:52:00.001-07:00

I just accidentally discovered a sure-fire way to KILL performance in Chrome 34 dev. I mean, going from a decent 30-60 fps to 0.25-1 fps.

See link below for sample code.

On a page with a good number of input elements (like a management dashboard I'm working with), apply "border: dotted 1px rgba(200, 200, 200, 0.9);" to input elements. It's the combination of the INPUT, element, border-style:dotted and border-color:rgba(). Remove the dotted (use solid) or remove the alpha channel and use rgb() instead and performance returns.

Even after the page is fully rendered and I scroll a few times, which causes things to smooth out a bit, dev-tools is rendered useless.

A sample page can be found here: https://github.com/rainabba/miscCode/blob/master/Chrome34KillPerfUsingInputs

Glass is NOT Augmented Reality and you Should Stop Comparing it to AR

2014-01-30T18:09:00.000-07:00

First, let me say that I AM a Glass explorer and I'm also KickStarter backer #1 for Meta. I've also been working with just about every stereoscopic tech you can think of over the last 15 years (I'm a backer for Oculus Rift, was using LCD Shutter Glasses back in '97, used to DRAW stereoscopic images by hand as a child, wrote my own "Magic Eye" app in DOS 6 using qbasic at the age of 15, etc...)

I feel like I've been talking to walls the last year but here it is said better than I have been able to word it so far. The CEO of Meta (SpaceGlases, Meta-View) Meron Gribetz, the man that hired Steve Mann (a top authority on wearable computing) and Steven Feiner (credited with coining the term augmented reality), says in very simple terms that Glass is not AR so don't take my word for it. To understand how much of an authority Meta is on AR, make sure you know who Steve Mann and Steven Feiner are and then understand that the CTO for Meta has been working with Mann for more than 10 years.

"The 3D output allows you of course allows you to paint graphics on regions of interest in the real world; *TRUE* augmented reality"

"The modern definition of augmented reality; the ability to take digital information and register it to parts of the real world."

"Glass is a Notification Machine"

Glass is a HUD which can be manipulated to provide some VERY BASIC AR-LIKE behavior. That doesn't make it AR any more than a the Nintendo Virtual Boy was VR. That's not to call Glass inferior in any way. Glass just wasn't intended for AR applications. Eventually technology will get to a point where a real AR display like Meta will be useful for something like Glass (lightweight, unobtrusive, wireless, decent battery life; everything Meta is trying to improve right now but falls far short in compared to Glass). With its present design, Glass will never be real AR; no stereoscopy, no direct fov, no 3D tracking, almost nothing that would allow it to convincingly "augment reality" any more than your smartphone currently can. If you're going to call Glass an AR device, then so is ANY smartphone with a camera on the back of a screen. If anything, your phone is MORE appropriate for AR than Glass.

Here is the video where I pulled those quotes from.

This is the man who will bring AR mainstream and who presently employs the two TOP authorities on AR. He validates what I've been saying since Glass was released. I hate to even mention Glass and AR in the same topic because I don't want to perpetuate the confusion but to clarify, I must do so.

Clarification: Based on a question just posed to me elsewhere, I came up with the following clarification.

The reason I'd more readily call a smartphone AR hardware is because of the fact that you can move the display in your line of sight and it will then (in general) have a camera pointed where your eyes do. Glass intentionally places the display above and to the side of your primary visions so immediately it cannot be in your direct field of view. It does have a camera facing forward with a huge FOV though so the display can be aligned with the camera. It might be a fine distinction, but that's why I say that it's isn't AR but has AR-like ability. You could call a car a bus because it can carry many passengers, but it's still not a bus, it's a car and the difference might seem insignificant, but only until you need a bus (something that does what the name implies). Furthermore, to "augment reality", you must have some reasonably level of belief that your reality has been augmented. As the Oculus Rift has proven, just putting a display in front of you does not accomplish this. Certain things like stereoscopic vision and latency are FAR more important than just having a display. A phone has a larger, higher resolution display that can easily take up a large portion of your primary FOV which is critical to AR. Add an auto-stereoscopic display (EVO 3D or Nintendo 3ds), and you'd also gain stereoscopic vision and with that, be much close to what AR needs to "augment reality" as opposed to just superimposing images into space. Glass has an interesting phenomenon where the display size is entirely dependant on what you see behind it. Because no stereoscopic cues are provided, the only way to make it even remotely believable is perfect scaling of the virtual image of the real one, something next to impossible with only the one camera. The Evo 3D has 2 cameras and so would be that much closer STILL to being a useful AR device but it falls far short in one way that Glass doesn't (not entirely anyway) and that is keeping your hands free so you can interact with reality. A major difference between superimposing graphics and AR is the fact that you not only could believe at some level that your reality has been augmented (not just projected over), but that you can still interact with your reality. That rules out the "phone as AR hardware" idea. So to sum it up, AR must make your reality appear to have changed (not just a projection) and you must be able to interact with that augmented reality. The primary difference between VR and AR is the fact that VR disconnects you from reality. Even with various hand-sensors, VR wouldn't be AR. Similarly, a HMD (head mounted display, like Glass and similar devices) will never be AR. The only real common thread is a see-through, head mounted display (HMD).

Chrome Dev Tools - Code Collapsing / Folding in Source Editor On Its Way!

2013-12-14T09:31:00.001-07:00

I should be able to highlight some code or act on an entire file by hitting a keyboard shortcut (I'm accustomed to Ctrl-M, Ctrl-M to collapse/expand a selected chunk) and have that code visually collapse to just the definition/signature line and a + show up on the left side of the IDE which I could click to re-expand that collapsed piece of code. Ideally, collapsing would also work anywhere there are mandatory closing symbols on a separate like (such as each/while/do/if/else/etc...)

What went wrong? The behavior just doesn't exist as of right now that I can find.

Did this work before? No

How to solve the issue? Ask the Chrome Dev Team to implement it via the bug submitted below :)

The value of this behavior is evident when you consider how often it appears elsewhere even in Chrome (any collapsable treeview demonstrates this). Elements tab does it, all the tabs in the right-pane of Elements (Styles, Computed, Event Listeners, etc..) also do it. Nearly every major IDE does it (Netbeans, VIM, Eclipse, Visual Studio, etc..)

This is extremely valuable to me when working with larger code files to the extent that I'm still using other IDEs instead of DevTools when working with larger or more complex files.

If you're not familiar with this behavior somehow, http://vimeo.com/4020903 does a great job at showing the behavior, some potentially configurable options and perhaps a pattern to emulate since it's VIM and oss.

If you like the idea, go vote (not sure if it matters now, but it can't hurt) by clicking the star at the top left of the bug report below.

https://code.google.com/p/chromium/issues/detail?id=328431

Another from Tony - How Babies Are [NOT] Made

2013-12-13T19:31:00.001-07:00

Wish I'd have thought of this with both my children. Priceless!

How Babies are Made - Who Knew

Canadian photographer Patrice Laroche surely will have no trouble explaining to his kids about the birds and the bees.

During his wife Sandra’s pregnancy, the artist created this hilarious explanatory photo series titled “How to Make a Baby”...

The creative couple planned and carried out their project throughout the whole period of 9 months, taking pictures in the exact same settings as Sandra’s belly expanded.

The pregnancy saga of Sandra and Patrice basically denounces all the traditional cabbage and the stork stories.

Now how could I not have shared this with you -?

Go ahead, smile, and enjoy your day!!

Courtesy of TonyD (He'll be blogging directly soon)