How to check something isn't an email address?


The HTML5 Logo.

In web-development circles, it is a well-known fact that trying to validate an email using a regular expression is… complex. The full set of modern email standards allows for such wonderful addresses as: chief.o'brien+ds9@spásárthach.भारत So determining whether or not your user has entered a valid email address becomes an ever-increasing challenge. But what if you have the opposite issue? Suppose you have a form which takes something which mustn't be an email address? For example - imagine y…

Continue reading →

I think I kind of hate lazy loading


An icon representing a broken image.

Yesterday I was on a train. I clicked on a link and my browser loaded a long article for me to read. Halfway through reading it, the train went into a tunnel and I lost signal. That meant I couldn't see the images on the other half of the page for the rest of the journey. I had a sea of broken images. Even though the page had fully loaded, the images were set to "lazy" loading. When my browser sees it defers downloading the picture until it is about …

Continue reading →

This link is only available by keyboard navigation


The HTML5 Logo.

There's a link, right here ➡️⬅️ but, if you're on a touchscreen, you can't tap on it. Using a mouse? Nope, that won't work either. The only way to navigate to it is via keyboard navigation. Hit your Tab ⭾ button! There's a little bit of me wants to build an entire website which can only be navigated by keyboard. What would the world look like if Engelbart never invented the mouse? Or if Johnson never published his work on touchscreens? Anyway, there are two ways to do this. The first is to …

Continue reading →

Can this device make a phone call?


The Doctor holding Ryan's phone.

I want to detect if a web browser is running on a device which is capable of placing a telephone call. Is that possible? I'm going to go with a cautious "no - not quite". Although there are several proxies which get you part of the way there. Here's a link to a telephone number "call me!" - the HTML is: <a href="tel:+441234815259">call me!</a> You can use tel: in just the same way you'd use http: or mailto:. It tells the User Agent to open the correct program to deal …

Continue reading →

Does AI mean we don't need the Semantic Web?


User: Read the following sentence: "Our opening hours are: Weekdays 10 until 7. Weekend 10 until 10 (Early closing 9 o'clock Sunday)." ChatGPT: The given sentence states the opening hours of a certain establishment. Here is the breakdown of the opening hours mentioned: Weekdays: The establishment is open from 10 in the morning until 7 in the evening. Weekend: On weekends, the establishment is open from 10 in the morning until 10 at night. Early closing on Sunday: On Sundays, the establishment closes earlier than usual, at 9 o'clock in the evening. Please note that this information is based solely on the provided sentence, and the specific establishment or its type is not mentioned. User: Is the establishment open at 2130 on Sunday? ChatGPT: Based on the information provided in the sentence, the establishment has early closing on Sunday, with the closing time set at 9 o'clock in the evening. Therefore, the establishment would not be open at 21:30 (or 9:30 PM) on Sunday.

If you hang around with computerists long enough, they start talking about the Semantic Web. If you can represent human knowledge in a way that's easy for computers to understand it will be transformative for information processing. But computers, traditionally, haven't been very good at parsing ambiguous human text. Suppose you saw this text written for a human: Our opening hours are: Weekdays 10 until 7. Weekend 10 until 10 (Early closing 9 o'clock Sunday). Not the most straightforward…

Continue reading →

The limits of CSS styling select options


Checkboxes in a line.

Sometimes you learn the most from failures! I wanted a