DEV Community

We had a date bug that happened two times a year, and we didn't know, you might have it too 😱

Zac_A_Clifton on September 11, 2023

TL;DR Novu's team encountered a significant bug affecting date calculations in their CI/CD pipelines, hindering all deployments. The i...

Read full post

𒎏Wii 🏳️‍⚧️ • Sep 11 '23

I'm sorry for the off-topic, but the joke just has to be made:

Two dates a year is a problem? I'm lucky if I even get that many... 🤭

Nevo David • Sep 12 '23

🤣

Emil Pearce • Sep 11 '23

Two key takeaways:

Never Assume: Even popular libraries can have hidden pitfalls. Always question, regardless of its reputation.

Testing is Crucial: Your robust tests highlighted a significant issue, emphasizing the need for thorough testing in software development.

Thanks for sharing this valuable lesson! Here's to more bug-free coding! 🥂

Zac_A_Clifton • Sep 11 '23

These are great takeaways, thank you for sharing!

John Barrow • Sep 14 '23

I think that the issue is one of definition rather than coding around the end of the month. We write software that calculates rental periods. When the rent is monthly, the start date could fall on (say) the 31st or 30th of the month. Advancing these through the year gives an ambiguity. When you get to (e.g.) February, both charges are adjusted to the 28th / 29th. What day should they be in March? They should be back to 31st or 30th. You can't know this without storing an additional peice of information, in this case the regular billing day. However, without needing to support both methods, most people expect the last day of the month to be dominant so, once the day is the last date of the month it stays there when next move a month. To easily spoort this dominant definition, you add one day to the date (for all calculations), then add / subtract the required number of months, then subtract one day. This makes the end of the month dominant. Remember that, if advancing a date monthly through the year using the dominant method, then any date with a day greater than or equal to 28 will eventually end up being the 31st or last day of the month (without also knowing the regular billing day to make the distinction).

Cezary Tomczyk • Sep 12 '23

From my experience, I'd advise using always fixed version of the npm package. The most common usage I've seen is to use a tilde. Using tilde (~) gives you bug-fix releases. However, on CI/CD, npm may fetch a really tiny next version, and that may fail your build. You'll spend a whole day investigating the root cause. Even more confusion comes from the fact that package.json contains the same version, e.g., 3.4.0 in the repository and on your computer, but in fact on the server there might be 3.4.1 installed. Hence, fixed versions ensure that npm dependencies will always be on the same version.

Niklas • Sep 14 '23

It's fine using dependency constraints like ^ and ~ as long as you are locking your dependencies with a lock file and only use npm ci inside your pipeline instead of npm i as this will always take the resolves versions from the lockfile. If any commit breaks the pipeline you can just check if the lock file was updated 👍

Cezary Tomczyk • Sep 14 '23

@niklaspor I don't recall exactly, but I think I had a past problem with package-lock.json. There were unresolvable conflicts. You can use the keywords "package lock json problem" to find out what others are struggling with.

One of the points npm documentation says is "install exactly the same dependencies". That's what you can exactly achieve without ^ and ~.

From my personal side, I have never found any real practical usage of package-lock.json.

Niklas • Sep 14 '23

npm i / npm install will bump any package to the latest matching package version. npm ci or pnpm --frozen-lockfile will keep exactly the versions which were resolves in the last npm i which was executes.

Always use npm ci inside your pipelines, otherwise you risk getting different packages from your local installation, even if you don't use any ranged but just plain veesions. Also any package deeper in your dependency tree might specify a version range, which might lead to a newer resolves dependency, if you execute npm i instead of npm ci. Same for pnpm and yarn.

I would even suggest you use npm ci on your local machine, when your working with any teams of bigger size and you don't want to update dependencies. Otherwise the code on your machine might differ from the one one your colleagues.

stackoverflow.com/questions/524996...

support.deploybot.com/article/131-....

Cezary Tomczyk • Sep 15 '23

@niklaspor Let me put this into a different perspective. The most important thing here is to ask, what kind of problem is being solved here? So the problem is: how to keep npm package dependencies consistent? If using a fixed version works, any other solution will simply be unnecessary. And so far, the solution is working excellently.

As for CI/CD, it is organised in very different ways, and there is no single approach. So if npm ci solves specific problems for someone, then using this approach is the right solution.

Zac_A_Clifton • Sep 11 '23

Have you had a bug with dates before?

Tomer Barnea • Sep 11 '23

The question should be if you ever wrote something with dates with no bugs at all????

Rocky Kev • Sep 13 '23

Two hardest things in programming: Cache invalidation and naming things.

I think we should add time, timezones and dates.

Zac_A_Clifton • Sep 11 '23

That is so true, even the best of us get tripped up by this.

𒎏Wii 🏳️‍⚧️ • Sep 11 '23

Not quite dates, but arguably even more strange: Lua is a very small language, with a relatively simple model for handling dates, and sometimes you need to get a bit hackey to deal with time zones.

Well, luckily it just uses the C time/date functions, which are clearly defined, so you can at least rely on your hacks to work everywhe— hold up a second, you didn't consider windows.

Turns out microsoft's fuck-up of a C compiler knows better than the spec, so on any Lua version compiled using it, you cannot get the current time zone as a numeric offset, because the library function just returns some other short string instead.

This took way too long to debug, and when I figured out the cause was that microsoft simply does what microsoft wants, I felt like throwing my PC out the window.

Zac_A_Clifton • Sep 11 '23

I think most people feel the same way about microsoft.

and, by the way, I enjoyed reading this story!

Prosper Otemuyiwa • Sep 14 '23 • Edited

The good old date time problem.

We have two popular problems in programming:

Naming things
Cache Invalidation

Now with this exposé, we have a third - date/time problems!

Thanks for writing this u @cliftonz . Good lessons learned

Thorsten Hirsch • Sep 16 '23

I wouldn't consider this a bug.

const startDate = new Date("2023-08-31");
const oneMonthAhead = addMonths(startDate, 1);
const result = subMonths(oneMonthAhead, 1);
console.log(result);  // 30th of August

This works as I expect it to work.

Zac_A_Clifton • Sep 16 '23

I think your thought is very true, while in our perspective it was a bug I agree the actually logic is not a bug.
However, I do think that there should be a warning about this edge case as not everyone would be able to see it.

Jean-Philippe Green • Sep 11 '23

Doesn't this happen for Mars, May and October too? So 5 times a year rather than 2

Hussein Kizz • Sep 13 '23

The fact that the bug was happening 2 times a year brough me all the way here, like have you ever encountered a bug that only manifests say after 5 years under very specific scenarios? Damn it was working all long you say!!!

Tai Kedzierski • Sep 11 '23

Date-math is non-trivial, month-math especially so.

What does "add one month" (or subtract) actually mean? In the case of this library, it's "jump to the same day number ahead/back". Adding/subtracting 30 would also be error-prone.

So your takeaways are spot on, though I'd also add this caveat:

When something isn't of a given fixed quantity, beware abstractions that treat them as if they were...!

Zac_A_Clifton • Sep 11 '23

Great Insight!

1Link.Fun • Sep 12 '23

The picture has no link to your repo

Nevo David • Sep 12 '23

Fixed :)

Robina • Sep 11 '23

Awesome

Zac_A_Clifton • Sep 11 '23

How worried are you about date bugs coming up in your product?

Yeom suyun • Sep 11 '23

The bug does not occur in the Date object of v8.
I like to leverage the basic features of the JS engine.

Zac_A_Clifton • Sep 11 '23

That is very true, I do not know why we choose this library but it does provide a lot of good utilities to leverage.

Samuel Rouse • Sep 14 '23

The native Date object has plenty of complexity to be aware of, too. Entering "equivalent" date strings do not always produce the same result:

// ISO Assumes UTC Timezone, so we get Midnight UTC
const dateFromISO = new Date('2023-09-14');
// 'Wed Sep 13 2023 20:00:00 GMT-0400 (Eastern Daylight Time)'

// Other formats assume local time zone so I get Midnight Eastern
const dateFromMDY = new Date('9/14/2023');
const dateFromElements = new Date(2023, 8, 14);
// 'Thu Sep 14 2023 00:00:00 GMT-0400 (Eastern Daylight Time)'

This can be a real problem when parsing user-entered dates... some regions/people use the YYYY-MM-DD format for dates, which means you can be many hours off from the expected time.

Yeom suyun • Sep 15 '23

The default Date object is indeed complex, and this is also a problem of ambiguity that exists throughout JavaScript.
However, I think the confusion that JavaScript's Date object gives to developers mostly comes from time zones and the conversion between strings and Dates.
If only these three problems could be solved, wouldn't we be able to get a lot of benefits from the basic features of JS?
For example, you can use a simple string_to_date function to solve the problems you mentioned, as follows.

function string_to_date(date, format = "YYYY-MM-DDTHH:mm:ss.sss") => {
    let x = format.indexOf("YYYY")
    const year = x < 0 ? "0000" : date.slice(x, x + 4)
    x = format.indexOf("MM")
    const month = x < 0 ? "00" : date.slice(x, x + 2)
    x = format.indexOf("DD")
    const day = x < 0 ? "00" : date.slice(x, x + 2)
    x = format.indexOf("HH")
    const hours = x < 0 ? "00" : date.slice(x, x + 2)
    x = format.indexOf("mm")
    const minutes = x < 0 ? "00" : date.slice(x, x + 2)
    x = format.indexOf("ss")
    const seconds = x < 0 ? "00" : date.slice(x, x + 2)
    x = format.indexOf("sss")
    const milliseconds = x < 0 ? "000" : date.slice(x, x + 3)
    return new Date(`${year}-${month}-${day}T${hours}:${minutes}:${seconds}.${milliseconds}`)
}

Red Ochsenbein (he/him) • Sep 11 '23

Now, also try to deal with timezones and daylight saving, and leap seconds as well. There is a huge rabbit hole to go down and no right or wrong, but expectations and solutions on a case by case basis.

Zac_A_Clifton • Sep 12 '23

Absolutely, we are looking at implementing timezone aware notifications for our users and it adds a plethora of complexity.

Sang • Sep 12 '23

If you have ever had a problem with timezone, espescially DST and timezone stuff. You can try this: dev.to/sang/javascript-zoned-date-...

Sang • Sep 12 '23

A bit off-topic. Recently I published zoned-date library.

dev.to/sang/javascript-zoned-date-...

The library has a sophisticated DST support (better than date-fns) and very elegant API interfaces. If you have ever had a problem with DST or timezone-related, I would highly recommend it. Of course, feedbacks are always recommended.

Zac_A_Clifton • Sep 12 '23

Thanks for letting us know!

Mateusz Koteja • Sep 12 '23

Funny and insightful video on related topic - timezones:
youtube.com/watch?v=-5wpm-gesOY

I didn't have such problems like in the video, but I was working with transforming dates for aggregation into timezones (for example: night means something different in Japan and France, and it was important whether data point happened at night or not. I had date from one part in the world mapped to date in another part of the world).

It looks I finally made this working, but the worst part: whenever client was not sure about the results I had to go back to that bullshit code and data in database, and figure out whether there is a bug or not, and then explain to the client why his data produces such results. I discovered that human mind is absolutely terrible in such calculations or making assumptions about this topic. It's one of the most unintuitive things I worked with.

Jason Mishike • Sep 14 '23

Month math and math with leap years is weird, I'm sure there is some sort of reason things are the way they are in calendars, but it is annoying that the stuff isn't very math, and consequentially computer, friendly...

Voltra • Sep 12 '23

Was a pull-request to date-fns created as a result?

Zac_A_Clifton • Sep 12 '23

Absolutely, its linked in the bottom of the article, but you can go directly to issue with this link.
github.com/date-fns/date-fns/issue...

Red Ochsenbein (he/him) • Sep 11 '23

Well, Dates are hard...

Zac_A_Clifton • Sep 11 '23

Exactly

Freddy Hidalgo-Monchez • Sep 12 '23

Great catch! This is part of the 10% of bugs that make you question the fabric of nature 😁

What was the test about that helped you find the bug? If you feel comfortable sharing :)

Zac_A_Clifton • Sep 12 '23

The was ensuring that the date to send a notification was correct.
Such a simple thing turned into something much bigger.