|
I got my Pike Virtual Machine for running regexs coded and it's a fun little widget;
L0000: split L0001, L0008, L0020, L0024
L0001: save 0
L0002: set "A".."Z", "_", "a".."z"
L0003: split L0004, L0006
L0004: set "0".."9", "A".."Z", "_", "a".."z"
L0005: jmp L0003
L0006: save 1
L0007: match 0
L0008: save 0
L0009: split L0010, L0012
L0010: char "0"
L0011: jmp L0018
L0012: split L0013, L0014
L0013: char "-"
L0014: set "1".."9"
L0015: split L0016, L0018
L0016: set "0".."9"
L0017: jmp L0015
L0018: save 1
L0019: match 1
L0020: save 0
L0021: set "\t", "\n", "\v", "\f", "\r", " "
L0022: save 1
L0023: match 2
L0024: save 0
L0025: any
L0026: save 1
L0027: match -1
That lexes a regex with an id (match 0), integer (match 1) or whitespace (match 2)
My little compiler generated that when I called this:
int[][] prog = Regex.CompileLexer(
@"[A-Z_a-z][A-Z_a-z0-9]*",
@"0|(\-?[1-9][0-9]*)",
@"[ \t\r\n\v\f]"
);
The instructions are encoded as an array of ints per, while the overarching instruction stream is int[][]. This way i can pass it around without requiring dependencies, and I can implement the VM/interpreter in an outside library without requiring a reference to an Instruction class or something.
The thing that's cool about this machine is it's cooperatively threaded. I'm tickled about that. Split jumps to multiple locations "at the same time." so it's concurrent. In reality this was a neat trick wherein i interleave the execution of each thread so i don't have to backtrack over the input.
It's the coolest project I've made this year, and the article is already getting underrated at codeproject. 
I think people ph33r regex.
Still, it's so much fun.
Thanks @BillWoodruff for finding my bug that inspired my misguided .NET unicode rant
Real programmers use butterflies
modified 18-Jan-20 11:27am.
|
|
|
|
|
honey the codewitch wrote: and the article is already getting underrated at codeproject.
Yeah, that really surprised me, as I thought what you're doing here is really the coolest thing since sliced bread. Oh well, go figure.
|
|
|
|
|
Thanks. I really think it's the regex. I think some people just hate it.
Real programmers use butterflies
|
|
|
|
|
honey the codewitch wrote: I think some people just hate it.
Not as much as perl.
I wanna be a eunuchs developer! Pass me a bread knife!
|
|
|
|
|
I used to hate regex, and then one day the Regex angels came to me in a vision and I understood!
|
|
|
|
|
I had a similar experience with COM
Real programmers use butterflies
|
|
|
|
|
honey the codewitch wrote: Thanks @BillWoodruff for finding my bug that inspired my misguided .NET unicode rant
Good ol' Bill! 
|
|
|
|
|
Jonathan Allen (InfoQ) writing on tiered compilation in .NET 3.0:Quote: the runtime initially produces quick to compile but non optimal JIT code as needed and then executes it. Then in the background the runtime analyzes the context and IL code to determine if a more optimal JIT solution can be achieved. If so, it recompiles the IL code and swaps out the slow JIT path with the optimal JIT path. I'm sure there's some additional complexity in how that's achieved, but that's the basic idea. For static class initializers and static readonly field initializers, the runtime will produce first pass code that takes the init lock. That protects against the initializers ever running twice. That locking also has a runtime performance penalty. So, once the initializer runs once, the optimizer will simply produce new optimized accessor code paths that don't do any locking anymore!
[^].
I find Allen's in-depth coverage of C# and .NET developments, future features, etc., the most useful of any current source ... okay, okay ... Kent Sharkey, Scott Hanselman, Mads Torgensen, and the Nabobs and Hierophants of CodeProject are equally stellar phenomena
«One day it will have to be officially admitted that what we have christened reality is an even greater illusion than the world of dreams.» Salvador Dali
|
|
|
|
|
Jonathan Allen wrote: So, once the initializer runs once, the optimizer will simply produce new optimized accessor code paths that don't do any locking anymore!
This makes me wonder what sort of jit magic happens with synchronizing awaitable methods.
Real programmers use butterflies
|
|
|
|
|
but this comment was in response to something some other c# dev team/section were adding,
... JA basically pointing out what they had proposed was superfluous.
shows the c# dev teams don't always communicate / are often disjointed. Too many cooks....
I'm not against introduction of new features as long as older code is not affected (still compiles/tests as before) - good thing is so far c# dev have managed at least that.
Where it does become an issue though are kiddies: that as soon as new features are released feel the need to use those new features everywhere including public github sources they can modify.
- not fun at a customer site maintaining something that uses those (and the local vs/c# can/may not be updated - licence, time...)
An example: within days of the nameof() operator being introduced [even then only in beta] some kiddie decided to use/add it in every single method in a github library I was using. Nothing else was modified "updated", silly kiddie just decided to "contribute" by using/adding nameof() everywhere he could - even where it made no sense (or way less sense than the original exception messages that he removed). - WTF??
... luckily I did have an older backed up version. (and very soon after the original owner rolled it back specifically to undo that stupidity.)
yeah OK, typically if/when I use entire github repos I'll download full source and purposely disconnect it - sometimes though get caught when maintaining / rebuilding [others'] older apps.
after many otherwise intelligent sounding suggestions that achieved nothing the nice folks at Technet said the only solution was to low level format my hard disk then reinstall my signature. Sadly, this still didn't fix the issue!
|
|
|
|
|
Sorry to hear about your "code kid" experience ... haven't met one of those myself
One of the things I most like about Allen's writing is the sharp-minded criticisms he renders of both released, and proposed, new C# features.
Null checks are a kind of dismal swamp we're stuck in: imho, no clean way out. My preference would be use of Attributes. Too bad Code Contracts never became useful.
cheers, Bill
«One day it will have to be officially admitted that what we have christened reality is an even greater illusion than the world of dreams.» Salvador Dali
|
|
|
|
|
"Nameof" replaces a lot of "magic words" like property names (in UI bindings), that break when class property names are changed.
Mea Culpa on the "let's see if I can find a use for every function in PL/I for this (first) program".
It was only in wine that he laid down no limit for himself, but he did not allow himself to be confused by it.
― Confucian Analects: Rules of Confucius about his food
|
|
|
|
|
I go to my dollar account and click "Log in".
Up pops the login screen, covered with a "shield" and a "optional cookies" accept / decline. There is a "More info on the cookies", so I click that.
And I get the info. COVERED. WITH. THE. SHIELD. AND. ACCEPT. DECLINE. BUTTONS. 
"I have no idea what I did, but I'm taking full credit for it." - ThisOldTony
AntiTwitter: @DalekDave is now a follower!
|
|
|
|
|
That's even worse than what happens when I logout from my insurance company's website! I get a confirmation screen that reads:
Are you sure you want to logout?
[Quit] [Cancel]
/ravi
|
|
|
|
|
Change the zoom on the page to move the info into view - the shield should remain centered.
- I would love to change the world, but they won’t give me the source code.
|
|
|
|
|
Right click, "Inspect", "Delete element" works better! :laugh.
There is also "Block element" on uBlock ... don't tempt me ...
"I have no idea what I did, but I'm taking full credit for it." - ThisOldTony
AntiTwitter: @DalekDave is now a follower!
|
|
|
|
|
you should absolutely get a euro account; they have cookies there.
I'd rather be phishing!
|
|
|
|
|
I've thought about it, but I've never needed one - I do occasionally get payments in US$ so I have a Transferwise dollar account - if I need one, it can be open and ready in around 60 seconds anyway. And that includes logging in.
"I have no idea what I did, but I'm taking full credit for it." - ThisOldTony
AntiTwitter: @DalekDave is now a follower!
|
|
|
|
|
Is there an overlay remover plug-in for your browser?
FF has one, so I just switch to FF, when I hit sites with annoying nag overlays (particularly newspaper sites that I only visit through links, but which use half the screen to "request" that I subscribe). One click, and they're out of your way.
I wanna be a eunuchs developer! Pass me a bread knife!
|
|
|
|
|
I am a Microsoft developer but have to use PostgreSql for some things. I had to restore a database and in Microsoft Sql Server you just right-click, Restore, pick your file and done. Simple.
In PostgreSql you have to first create a database and then right-click the database and restore a backup into the new database. Seems backwards and non-intuitive. Then in the restore options they have a section of negative boolean fields. I hate negative booleans.
I also had underscores in the name of my database and was getting a weird error restoring the backup. I finally removed the underscores and the backup restored into the new database fine.
Social Media - A platform that makes it easier for the crazies to find each other.
Everyone is born right handed. Only the strongest overcome it.
Fight for left-handed rights and hand equality.
|
|
|
|
|
ZurdoDev wrote: In PostgreSql you have to first create a database and then right-click the database and restore a backup into the new database. Seems backwards and non-intuitive.
Both ways are logical enough ("get a container/object/variable, then put stuff in it" happens all over the place, in programming), so it just depends on the logic preferences of the app's developers.ZurdoDev wrote: in the restore options they have a section of negative boolean fields
This, on the other hand, is completely unforgivable.
The number of heads I've had to pound "Say what IS, not what is not!" into goes beyond counting.
Misusing negatives happens all over, though. If you use VLC (one of the best apps around), and have the audio or a subtitle running out of sync, there are hotkeys for "delay up" and "delay down", so if it's early, you have to press a key to increase the delay, etc.
Making the delay number bigger moves the audio/subtitle backward, and a negative number moves it forward: -0.4 seconds is 0.4 seconds in advance! It does your bloody head in, when you're trying to read lips and make the voices sync with them!
I'd love to meet the dev who thought that was logical, and introduce him to the logic of cricket-bat diplomacy.
I wanna be a eunuchs developer! Pass me a bread knife!
|
|
|
|
|
Mark_Wallace wrote: Making the delay number bigger moves the audio/subtitle backward, and a negative number moves it forward: -0.4 seconds is 0.4 seconds in advance!
Seems perfectly logical to me.
If your train is delayed by four minutes (+4), it turns up four minutes after the scheduled time. Make the number bigger, and the train turns up later. Make it smaller (or negative), and the train turns up earlier.
"These people looked deep within my soul and assigned me a number based on the order in which I joined."
- Homer
|
|
|
|
|
Back when I was on the clock I'd tell people if I'm say 10 minutes late for work (+10 min) then I made up for it by leaving 10 minutes early (-10 min).
They just didn't get it. Why??? Zero time difference = leveled out fair and square, right or no?
It's really effective when you're say an hour late; I certainly felt much more ...at peace.
after many otherwise intelligent sounding suggestions that achieved nothing the nice folks at Technet said the only solution was to low level format my hard disk then reinstall my signature. Sadly, this still didn't fix the issue!
|
|
|
|
|
My motto is if you can't be punctual arriving then at least be punctual leaving.
"They have a consciousness, they have a life, they have a soul! Damn you! Let the rabbits wear glasses! Save our brothers! Can I get an amen?"
|
|
|
|
|
Yes, it's perfectly logical that making a delay smaller moves something forward in time.
The problem is in figuring out which key you're supposed to hit when you're twisted awkwardly to look at the image on the wall while you're doing it, and you're trying to align lip movements (which are either early or late) with sounds.
"Pressing this moves the number backward so it moves the sound synchronisation point forward" is really not helpful -- particularly since, if you're into plus seconds, there is no delay to adjust!
Of course, the root cause and underlying problem is that developers think they're logical[^]
I wanna be a eunuchs developer! Pass me a bread knife!
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
