DEV Community

Cover image for Retro CRT terminal screen in CSS + JS
Edwin
Edwin

Posted on

Retro CRT terminal screen in CSS + JS

As a fun project, I decided to create a terminal interface that has the look and feel of an old CRT monitor.

The terminal is responsive, but it might be easier to work with on a larger screen (and it will provide a hint for the login).

Now, it's time to boot that terminal!

Goals

My goal is to build the whole thing using modern ECMAScript 6 features (without any transpiler such as Babel). Sorry Internet Explorer, it's time for you to retire.

During this project, I learned about a lot of topics:

  • ES6 features such as modules, dynamic import and async/await
  • CSS border-image, background gradients, animation and variables
  • JavaScript Audio and SpeechSynthesis APIs
  • Handling DOM elements using pure JS

There is too much going on to do a full tutorial, but in this article I'll explain the most important parts. Later on, I might do a follow up article about the details, such as individual components and how I organized the project. In the examples I often leave out some of the final code for clarity, but you can always view the source on Codesandbox.

Inspiration

I drew most of my inspiration for this project from the Fallout 3 game, where you can "hack" your way into computers by playing a mini game on one of these terminals:

Skeuomorphisms

Mimicing attributes of real life objects (such as the material or shape) in a design is called a skeuomorphism. The reasoning is that by making a design look like an object that the user is familiar with, it might become easier to understand. Apple used it a lot in their apps, such as the book store apps that showed your books on a 'real' shelf or a compass app that showed a spinning compass pointing to the direction you are facing.

This style has fallen in to disuse mostly due to the popularity of flat design, where extreme minimalism seems to be the norm. Most software still contains some skeuomorphisms though. For example, the simple unstyled HTML <button> on a webpage will resemble a hardware button, which should give the user a clue that this element can be pressed. Navigational tabs look like a physical tabbed folder.

Another great example that I recently encountered is this polaroid camera:

Coding a CRT

So how do we make our CRT resemble the real deal? We're gonna need a few parts:

  • Scanlines, the visual pattern of alternating horizontal lines that this type of monitor used to have.
  • A huge rounded bezel, to make it look like one of those tiny portable TV sets.
  • Some buttons, such as a power switch. I feel that manually switching on the device and actually seeing the device boot increases the immersion of the whole experience.
  • A text based interface where the user can type in commands.

Building the screen πŸ“Ί

The basic HTML is pretty simple, it's just a <div> for each part:

<!-- the actual device -->
<div id="monitor">
    <!-- the rounded edge near the glass -->
    <div id="bezel">
        <!-- the overlay and horizontal pattern -->
        <div id="crt" class="off" onClick="handleClick(event)"> 
            <!-- slowly moving scanline -->
            <div class="scanline"></div>
            <!-- the input and output -->
            <div class="terminal"></div>
        </div>
    </div>
</div>
Enter fullscreen mode Exit fullscreen mode

I might cover the button controls in a future article.

The scanlines

The horizontal black and semi-transparent lines from this Codepen seemed to do the trick:

#crt:before {
    content: " ";
    display: block;
    position: absolute;
    top: 0;
    left: 0;
    bottom: 0;
    right: 0;
    background: linear-gradient(
        to bottom,
        rgba(18, 16, 16, 0) 50%,
        rgba(0, 0, 0, 0.25) 50%
    );
    background-size: 100% 8px;
    z-index: 2;
    pointer-events: none;
}

Enter fullscreen mode Exit fullscreen mode

The :before pseudo class, combined with position: absolute, allows us to overlay the line pattern on top of the element. The linear-gradient fills the background for the top half with an opaque dark line and the bottom half with a semi-transparent black. The background-size property makes it full width and 8px high, so each individual line becomes 4px. This background is repeated vertically to create the alternating line pattern.

This article describes a way to create a really realistic scanline pattern, which even includes a screen door effect: a mesh-like appearance where you can see the gaps between pixels on the screen. This causes the screen to really flicker, which was very straining on my eyes, so I decided not to use that. I did use the color separation effect for the text, which adds an animated text-shadow to the terminal text which makes the text appear to move around a bit:

@keyframes textShadow {
  0% {
    text-shadow: 0.4389924193300864px 0 1px rgba(0,30,255,0.5), -0.4389924193300864px 0 1px rgba(255,0,80,0.3), 0 0 3px;
  }
  5% {
    text-shadow: 2.7928974010788217px 0 1px rgba(0,30,255,0.5), -2.7928974010788217px 0 1px rgba(255,0,80,0.3), 0 0 3px;
  }
  /** etc */
}
Enter fullscreen mode Exit fullscreen mode

Then there is also a scanline moving over the screen from top to bottom every ten seconds. It uses a similar, but larger linear-gradient and an animation to make it move from top to bottom.

.scanline {
    width: 100%;
    height: 100px;
    z-index: 8;
    background: linear-gradient(
        0deg,
        rgba(0, 0, 0, 0) 0%,
        rgba(255, 255, 255, 0.2) 10%,
        rgba(0, 0, 0, 0.1) 100%
    );
    opacity: 0.1;
    position: absolute;
    bottom: 100%;
    animation: scanline 10s linear infinite;
}
Enter fullscreen mode Exit fullscreen mode

The animation is out of view for 80% of the time and moves from top to bottom in the remaining 20%:

@keyframes scanline {
    0% {
        bottom: 100%;
    }
    80% {
        bottom: 100%;
    }
    100% {
        bottom: 0%;
    }
}
Enter fullscreen mode Exit fullscreen mode

The bezel πŸ–΅

To create the rounded edge, I use a border-image, a CSS property that I have never even heard of before! The idea is that you create a background image that is sliced up automatically into several regions, one for each edge and corner.

Bezel

You can indicate how much of the image is actually used by the unitless border-image-slice property. It uses the value as pixels for raster images and as percentage for SVG. In our case, we want 30px from the edge. Defining the border: 30px solid transparent property seemed necessary to make it look OK in Android Chrome.

#screen {
    position: relative;
    width: 100%;
    height: 67.5vmin;
    border: 30px solid transparent;
    border-image-source: url(./bezel.png);
    border-image-slice: 30 fill;
    border-image-outset: 0;
    overflow: hidden;
}
Enter fullscreen mode Exit fullscreen mode

Your browser will then automagically use the border image and scale the middle sections for varying width and height of the element. ✨

Screens

To create an experience where the user can interact with the terminal and have some screens where all the output is automatic and others where there is alternating input/output, I created one function for each of the screens:

  • boot - the start-up sequence
  • login - a very secure authentication mechanism
  • main - where the user can type commands

Boot

The boot screen just outputs a lot of text on the screen. To achieve this, I created a type() function, which returns a promise that resolves when the typing animation is finished. It is crucial to make it an asynchronous function, because we want to wait for the typing animation to complete before we let the user type his input. How the function works is explained further below.

In all of my functions, I use a simple async/await pattern that is shown here, so I can build my screens in a synchronous flow, which keeps the code very readable.

In the boot() function, I can then just await the typer() function to finish and move to the next screen:

async function boot() {
    clear();
    await typer("Hello world");

    login();
}
Enter fullscreen mode Exit fullscreen mode

The clear() function just empties the terminal div by resetting the innerHTML. I will skip the login screen for now and explain the main loop.

Main

The main() function shows the input and waits for the user to type a command. The command is then parsed and based on a lot of if/else statements, we can call a function and/or show some output to the user. When the command has finished, we start over by recursively calling the main() function!

async function main() {
    let command = await input();
    await parse(command);

    main();
}
Enter fullscreen mode Exit fullscreen mode

I just love how concise and readable this code is, despite the fact that we are using an imperative style of programming. Creating and updating DOM elements manually is a bit of a chore, but quite manageable in our case.

Input/output ⌨️

The CSS for the input and output text is pretty simple, the only interesting thing to mention is the pixely VT323 font and all text is transformed to uppercase:

@import url("https://fonts.googleapis.com/css?family=VT323&display=swap");

.terminal {
    font-family: "VT323", monospace;
    text-transform: uppercase;
}
Enter fullscreen mode Exit fullscreen mode

Animated typing for the output

This is the part where most of the JavaScript stuff comes in. I started out using a library called TypeIt to create an animated typing effect for the command line output. It's quite versatile - you can just pass it a container element and an array of strings and off it goes!

new TypeIt('#container', {
    strings: ["Hello", "world"],
    speed: 50,
    lifeLike: true,
    startDelay: 0,
    cursorChar: "β– "
}).go();
Enter fullscreen mode Exit fullscreen mode

After a while I decided to roll my own typing function, because I wanted to add a fancy animation when characters appeared on the screen (try clicking the red button). The core of this functionality is a while loop that adds one character to the screen and then pauses for a short while:

async function type(text, container) {

    await pause(1);

    let queue = text.split("");

    while (queue.length) {
        let char = queue.shift();
        container.appendChild(char);
        await pause(0.05);
    }

    await pause(0.5);
    container.classList.remove("active");
    return;
}
Enter fullscreen mode Exit fullscreen mode

The while loop keeps running as long as the queue string has length > 0 and the String.shift() function removes the first character and returns it.

The pause function is a glorified wrapper for setTimeout(), returning a Promise so we can wait for it using async/await - nifty! Usually you want to postpone executing a callback function using setTimeout, but here we just want to pause the code execution, to simulate the terminal processing your command. Thanks Stackoverflow.

function pause(s = 1) {
    return new Promise(resolve => setTimeout(resolve, 1000 * Number(s)));
}
Enter fullscreen mode Exit fullscreen mode

One second is the default argument, because that is how I wanted to use it most of the time.

Handling input commands

In a very similar fashion, I let the user type a command by creating an input element that returns a resolved promise when the user presses the enter key.

async function input(pw) {
    return new Promise(resolve => {
        const onKeyDown = event => {
            if (event.keyCode === 13) {
                event.preventDefault();
                let result = event.target.textContent;
                resolve(result);
            }
        };

        let terminal = document.querySelector(".terminal");
        let input = document.createElement("div");
        input.setAttribute("id", "input");
        input.setAttribute("contenteditable", true);
        input.addEventListener("keydown", onKeyDown);
        terminal.appendChild(input);
        input.focus();
    });
}
Enter fullscreen mode Exit fullscreen mode

The input is actually a <div> with the contenteditable attribute property, which allows the user to type inside the element. This may come in handy if we want to do fancy HTML stuff inside the div, which is mostly not allowed inside a regular <input> element.

The blinking caret 🟩

The blinking square at the end of a line really adds to the whole typing animation (credits to TypeIt for the inspiration). It is nothing more than a character placed in the :after pseudo class!

#input {
    position: relative;
    caret-color: transparent;
}
/* Puts a blinking square after the content as replacement for caret */
#input[contenteditable="true"]:after {
    content: "β– ";
    animation: cursor 1s infinite;
    animation-timing-function: step-end;
    margin-left: 1px;
}
/* Inserts the > before terminal input */
#input:before {
    content: ">";
    position: absolute;
    padding-left: 1.5rem;
    left: 0;
}
Enter fullscreen mode Exit fullscreen mode

The animation-timing-function: step-end makes the cursor change its transparency discretely to make it blink, rather than as a linear fade.

Then I also place a > character before the input to indicate that he user can type there. A neat little trick is settings caret-color: transparent; on the actual element itself, to hide the default caret. This will break moving the cursor if the user clicks in the middle of the text, but it does not bother me all too much.

Executing commands

I started off with a large if/else block to handle all the different commands, but that got out of hand quickly, so I needed something more modular.

This is where I decided to use dynamic imports. Another ES6 feature that has great browser support, now that Chromium version of Edge is released!

You probably know static imports, where you import your dependencies at the top of your own module:

import moment from 'moment'
Enter fullscreen mode Exit fullscreen mode

A dynamic import can be used anywhere, even conditionally, with variable paths and will require the specified resource on demand! Just what we need! The import will return a Promise with your module. If you use async/await, you can access any of its exports directly:

const { format } = await import('date-fns');
Enter fullscreen mode Exit fullscreen mode

So here is how I used imports in for parsing commands:

async function parse(command) {

    let module;

    // Try to import the command function
    try {
        module = await import(`../commands/${command}.js`);
    } catch (e) {
        console.error(e);
        return await type("Unknown command");
    }

    // Type the output if the command exports any
    if (module && module.output) {
        await type(module.output);
    }

    await pause();

    // Execute and wait for the command (default export) to finish
    if (module.default) {
        await module.default();
    }
    return;
}
Enter fullscreen mode Exit fullscreen mode

Doing this kind of stuff directly in the browser without any transpiler such as Babel and a code bundler like Webpack is very cutting-edge. It gives the developer a lot of freedom to only load resources whenever they are needed, preventing your main app from getting bloated. This is one of the main features that will make it easy to write modular, lightweight apps in native JavaScript.

Commands πŸ‘¨β€πŸ’»

Every command is simply a JavaScript module with a default export function that is executed when it is loaded. It can also directly output some text when the user presses enter by adding an output named export, as explained above. If we return a Promise here, the main() function will wait for the command to be finished.

const output = "Hello world.";

const helloWorld = () => {
   // do whatever...
};

export { output };

export default helloWorld;
Enter fullscreen mode Exit fullscreen mode

Now that we can add commands in a modular way, we can go completely crazy and write any cool stuff we can think of.

I'm trying to free your mind, Neo. But I can only show you the door. You're the one that has to walk through it.

-- Morpheus

Matrix

Next time...

In the next part of this article, I will explain more about how I added sound, control buttons and theming! For now, have fun hacking!

hackerman

Oldest comments (34)

Collapse
 
fossheim profile image
Sarah

Really love this! 😍

Collapse
 
fritzvd profile image
Fritz van Deventer • Edited

This is awesome. Thanks for sharing. I totally stole everything from here to create my birthday β€œinvite”: fritzvd.com/33/

Collapse
 
ekeijl profile image
Edwin

Nice!

Collapse
 
maveric profile image
maveric

Edwin,

I love this. By far the most in-depth, well written fallout game (as well as the terminal, but I found it looking for the fallout game) I've seen yet. The fact that it's in such an amazing package of the terminal with scanlines, typing, other command framework. It's great.

I'd like to use this for our airsoft events that we host (you read that right) and would like to know how to properly attribute you. I also have a question about why / how to fix - in the fallout game, when the typer is updating the lives (updateLives()) and you move the cursor it cancels the typer and can sometimes mess up the ending of the game (assuming waiting for a promise that gets wonkey?)

If you're willing, let me know your thoughts on the typer, but please let me know how to best give you credit to our players.

Collapse
 
ekeijl profile image
Edwin

Hey, thanks man! I'm really happy to hear that other people use my code for all kinds of stuff! I have not really thought about how to give credit, maybe just link to my dev.to profile for now. I was working on a portfolio site, this might be the motivation to actually finish it. :)

About the updateLives function, I assume you want to wait for the updateLives function to finish before doing the next thing. I see that this function does not return anything, that may cause the issue?

async function updateLives() {
    let span = document.querySelector(".lives");

    let blocks = Array(lives)
        .fill(0)
        .map(() => "β–  ")
        .join("");

        // Added return here
    return await type("Text", { clearContainer: true }, span);
  }
Enter fullscreen mode Exit fullscreen mode

Then you can wait for the function to finish by using async/await:

async function doStuff() {

  //...
  await updateLIves();
  // should wait for updateLives to finish
Enter fullscreen mode Exit fullscreen mode
Collapse
 
maveric profile image
maveric • Edited

I've made that change, and the execution does not seem to change. I have a "console.log" immediately following the call to updateLives that in fact will not show until it completes. But if I move the mouse, the

wordSpan.addEventListener("mouseenter", handleWordHover);

gets called (as it's on all elements) and seems to interrupt the promise. If I move the mouse, I never get that console.log statement for that call. If that game ends with that interrupted, it won't show the game end typer properly.

I have not been able to find any resources on this type of interaction - an event listener popping off during an await that messes it up - and this whole async/await was not a paradigm when I was coding last. Trying to catch up.

Your help/suggestions would be greatly appreciated but I know this was just a side/learning project, not something you intended to support and won't be offended if you chose not to.

Thread Thread
 
ekeijl profile image
Edwin

If I could look at the code somehow I can help debugging. Can you put it online somewhere like a codesandbox?

Thread Thread
 
maveric profile image
maveric • Edited

The sandbox is at:
codesandbox.io/s/hungry-booth-wyl1...
It really is just your code that I've made some minor bug fixes and personal debug/figure out code to. The same thing happens on the sandbox from this write up as well if it's easier to look at code I haven't put any hack-it-to-figure-it-out code into.

Thread Thread
 
ekeijl profile image
Edwin • Edited

Oh, it was easier than I thought.

I defined the interval variable at the top of the io.js module. Everytime you call type() it will overwrite the interval. I use setInterval to process the queue of characters one by one. So if type() is called while another is still running, only the last one will finish.

Moving the interval variable inside the type() function ensures every promise will execute asynchronously like you expect. Not sure why I wrote it like this in the first place, probably because I thought I would only need 1 typer at the same time, lol.

Thread Thread
 
maveric profile image
maveric

That's fantastic. I'm very glad it was an easy find for you and greatly appreciate you looking into it for me. Works like a charm. That would have taken me ages to find, as I was going down the "how's the promise getting messed up" path.

I've got a lot to learn, but you've got great code for me to follow, so thanks again.

Collapse
 
maveric profile image
maveric

I'm not sure if you are still reading comments on this article but we had our airsoft event last month and these were a HIT. I loaded it up on some rPi's and battery packs with wifi that redirected all traffic to the pi.

I built a local backend API that took in the "command" and tested it against our list and sent back either brogue or fallout to run based on our new command names. Then hooked into the win/losses and sent that back to the api so we could have dynamic win/loss messages based on the game that was played. It added something completely new to the airsoft world and we will absolutely be bringing it back in future games.

Thread Thread
 
ekeijl profile image
Edwin

That's so cool! I picture this as a "retro arcade" that you use during the downtime of the airsoft event? Thanks for the update!

Thread Thread
 
maveric profile image
maveric

Nope. :P We've got the pi's people connect with with their phone and a few toughbooks they've got to be in front of. You've got to have people pull security (to keep enemies away) or play the game under fire in order to get the information out of it to complete your mission and keep things progressing. The "hacking terminal" is very much a part of the live fire scenario game.

Thread Thread
 
ekeijl profile image
Edwin

That is freakin' genius! Sort of "hacking" mini-games during the event, that's so creative! Reminds me of this "scavenger hunt" game that we used to play on my university campus.

I'm currently playing a game called "Control" which also has some terminal based mini-games, might add it to this project. (no promises tho)

Collapse
 
hbaguette profile image
H-Baguette

Hey! I'm trying to use this code to make a small terminal for a game, but... for whatever reason, it's saying the :after elements are invalid names, and thus none of it shows up. I'm also having an issue of my scanlines appearing over my border image.

Collapse
 
ekeijl profile image
Edwin

Can you show me the code somehow? Codesandbox or github? I'm not sure what you mean.

Collapse
 
hbaguette profile image
H-Baguette

I managed to fix most of those issues, plus a few more I was having after adapting it for my own purposes, but I'm still having the issue with the scanlines appearing over the corners of the border image. The code's probably gonna look confusing and spaghettified to all hell, but I can add you to the Github repo, if you want to take a look.

Collapse
 
fradar profile image
FRADAR

I just love this.

Collapse
 
zcysxy profile image
Chenyu ZHANG

Great article! I can easily follow all the steps. There's only one thing that is I couldn't find the bezel.png, am I missing something?

Collapse
 
zcysxy profile image
Chenyu ZHANG

Oh I found it in the codesandbox! How can I miss that. Thanks!

Collapse
 
wordpressure profile image
TricaExMachina

This is gorgeous, what great work.

Collapse
 
chafalleiro profile image
Chafalleiro

Hello I borrowed your code, also added some SVG effect to do a barrel distortion of the screen that you can find interesting. Credited in the credits menu, I hope the crediting is correct.

chafalleiro.github.io/retromator/v...

Collapse
 
ekeijl profile image
Edwin

This looks perfect! 🀩

Collapse
 
chafalleiro profile image
Chafalleiro

Thank you very much :) Certainly you post helped me a lot.

Collapse
 
fhgaha profile image
fhgaha • Edited

im trying to repeat. almost done but cant find what "sphere_wide_1.png" look like

Collapse
 
junipersaroj profile image
juniperSaroj

how can i log in it is asking for the password and username
i need to use this for some video editing process guess ... please help bro.

Collapse
 
ekeijl profile image
Edwin

Just use "admin" for both username and password, it's in the source code πŸ˜†

Collapse
 
sungbinlee profile image
Sungbin Lee

Hey Edwin, Just wanted to say a big thank you for your amazing article. Thanks for sharing your knowledge. It's been a huge inspiration for my project! github.com/sungbinlee/TicTacToeWit...

Collapse
 
ekeijl profile image
Edwin

Hello Sungbin Lee, that's a cool project, glad I could be of help! :D

Collapse
 
doug_davison_2f87696dcf3d profile image
Doug Davison

It would be cool to use this to build various screens for use during an RPG session. I could see a need for building a custom intro screen for each terminal's welcome screen and login, and then menu items that do various things or open log journal records.

  1. Shut off exterior turrets (admin only)
  2. Open valve in backup tank
  3. Read Journal Entries
  4. Hack system to gain admin rights
Collapse
 
rizpng profile image
RIZ

Hey Edwin,

I'd like to say i love the way you designed your terminal and I'm glad it's being used to help other people. I was just wondering if it's possible to convert the terminal into a text editor tool instead given that I cannot freely text as i receive "unknown command" error whenever i type.

I'm not tech saavy at all so I'm unsure how to utilise Sandbox or any of the other tools used to code. Any feedback would be greatly appreciated

Image description

Collapse
 
ekeijl profile image
Edwin

Hey RIZ, I made a new command text-editor command, it saves what you typed in your browser.

tlijm.csb.app/?command=text-editor

Collapse
 
rizpng profile image
RIZ

yeah, i've been playing around with it and it works perfectly. i appreciate the support edwin and will continue to follow and support your work.
have a nice one mate :)

Collapse
 
bartydash profile image
BartyDash

Great job! It's awesome 😍🀯