Leaderboard

So a couple of years ago I was reading about the ZLIB documentation on compression and how it works. It was an interesting blog post going into how it works, and what compression algorithms like zip really do. This is using the LZ77 and Huffman Tables. It was very education and I thought it might be fun to try to write some of it in G. The deflate function in ZLIB is very well understood from an external code call and so the only real ever so slight place that it made sense in my head was to use it on LabVIEW RT. The wonderful OpenG Zip package has support for Linux RT in version 4.2.0b1 as posted here. For now this is the version I will be sticking with because of the RT support. Still I went on my little journey trying to make my own in pure LabVIEW to see what I could do. My first attempt failed immensely and I did not have the knowledge, to understand what was wrong, or how to debug it. As a test of AI progression I decided to dig up this old code and start asking AI about what I could do to improve my code, and to finally have it working properly. Well over the holiday break Google Gemini delivered. It was very helpful for the first 90% or so. It was great having a dialog with back and forth asking about edge cases, and how things are handled. It gave examples and knew what the next steps were. Admittedly it is a somewhat academic problem, and so maybe that's why the AI did so well. And I did still reference some of the other content online. The last 10% were a bit of a pain. The AI hallucinated several times giving wrong information, or analyzed my byte streams incorrectly. But this did help me understand it even more since I had to debug it. So attached is my first go at it in 2022 Q3. It requires some packages from VIPM.IO. Image Manipulation, for making some debug tree drawings which is actually disabled at the moment. And the new version of my Array package 3.1.3.23. So how is performance? Well I only have the deflate function, and it only is on the dynamic table, which only gets called if there is some amount of data around 1K and larger. I tested it with random stuff with lots of repetition and my 700k string took about 100ms to process while the OpenG method took about 2ms. Compression was similar but OpenG was about 5% smaller too. It was a lot of fun, I learned a lot, and will probably apply things I learned, but realistically I will stick with the OpenG for real work. If there are improvements to make, the largest time sink is in detecting the patterns. It is a 32k sliding window and I'm unsure of what techniques can be used to make it faster. ZLIB G Compression.zip

Phew that is a pretty strong opinion! Although I personally am not a fan of the overall style of DQMH none of my problems are with the scripting/wizards or placeholder text. I think any framework that tries to do "a lot" will be complicated... your own personal framework (which you likely find trivial to use) is likely to be a bit weird to others. DQMH is extremely popular for a reason... To paraphrase the words of a wiser person than I, "please don't yuck someone elses yum"

This year I went to NI Connect (the new NI Week) for the first time in 7 years. I thought I would be the exception and see all those that have gone year after year. But it turns out that many of us this was our first year back, or some last year was their first year back since COVID. In general I think this is a good sign, that things are moving in the right direction. NI has some new leadership that has a LabVIEW focus, and at least at the moment appear to want to push adoption. Reversing the subscription only is a welcome change, but for many it hurt the inertia of business. Once a ship starts moving in the wrong direction it takes a while to come back. Or put another way, respect is lost in buckets and gained in drops. Plenty of businesses have likely moved away from LabVIEW and NI because of poor decisions, that in my opinion, were so NI would look more valuable for an Emerson sale. I'm in the Detroit area, and plan to retire doing LabVIEW. At the moment I think I can do that. Not long ago I didn't think that would be the case. We were just blindly paying the SSP each year. The subscription only model, made management here reevaluated things. We took a few years off. Then perpetual licenses came back again so we renewed. I think we will likely get a new perpetual license every 4 years or so. This will hurt NI since this means less users on the newest release finding issues. Building back trust will take time here, and this will likely play out in a similar way around the world for other companies.

It is not that LabVIEW MAY unregister the reference, but that it WILL unregister the reference as soon as the top level VI in whose hierarchy the reference was created goes idle. This is by design and the only way to prevent that is to either keep that hierarchy active until any other user of that refnum has finished or delegate creating of the refnum to the place where it is needed, for instance through a LV2 style global maintaining the reference in a shift register and when being called for the first time it will create the refnum if the shift register contains an invalid refnum. True Actor Framework design kind of mandates that all refnums are created in the context of where they are used not some other global instance that may or may not keep running for the time some Actor is using the refnum.

Hi everyone, Just want to share our open source project "Labview Python Bridge". Connect labview apps with python apps in realtime with multi-processing data queues. https://github.com/jmor2000/labview_python_bridge If anyone has any questions or suggestions for new developments / features, let me know. Cheers Jeff

Are you seriously expecting anyone to install a random executable on their system from an unknown publisher, provided by an anonymous person on the web, where one can't even get a proper link in Google to the actual company page? Sorry, but anyone doing that should not be allowed near 5m of a computer system!

Absolutely echo what Shaun says. Nobody banned them. But most who tried to use them have after some more or less short time run from them, with many hairs ripped out of their head, a few nervous tics from to much caffeine consume and swearing to never try them again. The idea is not really bad and if you are willing to suffer through it you can make pretty impressive things with them, but the execution of that idea is anything but ideal and feels in many places like a half thought out idea that was eventually abandoned when it was kind of working but before it was a really easily usable feature.

Seems like this one has "escaped everyone's grasp" too. ParallelLoop.ShowAllSchedules=True Because was only checked from the password-protected diagram of ParallelForLoopDialog.vi (LabVIEW 20xx\resource\dialog). Present since LabVIEW 2010. When activated, allows to apply more advanced iteration partitioning schedule. In other words, instead of this you will get this Сould this be useful? I can't say. Maybe in some very specific use-cases. In my quick tests I didn't manage to get increase in any productivity. It's easy to mess up with those options and make things worse, than by default. Also can be changed by this scripting counterpart.

Look at this new download on VIPM https://www.vipm.io/package/bjm_lib_request_power/

You want an ability to override the Equality or Comparison operators? I'm unsure, whether it really existed in OpenG packages, but now you have those neat malleable VIs, that let you do that: Search Unsorted 1D Array , Sort 1D Array , Search Sorted 1D Array. They have an additional input to specify your own equals or less function in a form of a custom comparison class or a VI refnum. There's an article to help: Creating a Custom Sorting Function in LabVIEW

This is exactly what was said in that ancient thread: Tree control in labview. So if you add 65536*N to the Item Symbols property of the Listbox and have the "Enable Indentation" option activated, you shift the symbol/glyph and the text N levels to the right. Could be useful for simple 'parent-child' relationships, if you don't want to use a Tree. And still it's used in Find Examples / NI Example Finder window:

I'll caveat this with this is only my opinion as a European. Market forces may be completely different to my perception in the US. When I first started, LabVIEW was basically a loss-leader to sell hardware. The sales people would give it away free (or heavily discounted) if you bought the hardware. It proliferated and people like myself learnt and expanded our capabilities. Over time it launched a small consultancy industry specialising in LabVIEW. There were a few major successes such as JKI and some partnerships along with single developer consultants. The test and measurement industry had few rivals to LabVIEW's capabilities. Fast forward to today and I think the emphasis is now firmly on large organisations with enormous hardware requirements-in particular governmental organisations. CERN is an obvious one in Europe (CERN being intergovernmental) but I believe there are many in the US. The Test and Measurement was, for the most part, lost to Python and although there are one or two consultants still operating in my neck of the woods, that part of the industry is basically gone here. So. In my view there is still an appreciable number of opportunities working for large companies' in the US and Europe but if you are looking to be a self employed contractor (in Europe) then you would be better off with something else.

I think there is a future and NI has significantly increased their activity and promotion for it (I guess one could be sarcastic and say that considering that NI's promotion of LabVIEW and active support of the community was pretty much zero just 3 years ago, anything more than zero is significant). It will however not reach the stage that Dr. T once optimistically proposed as "LabVIEW everywhere". But that is not necessary. LabVIEW has still some interesting features and advantages and there won't be any programming environment ever that suits everybody. The license change is welcome but not to significant, I think, as the new(old) perpetual license is basically quite beyond reasonable in my opinion. LabVIEW was expensive in the old days already but the new perpetual license cost is in my opinion simply to high (it's more than double of what it was before they tried to force feed the subscription). If I had to pay it myself, I would most likely stop with LabVIEW and simply use the Community Edition as a hobby. However, you should anyhow never build your future on just one leg. LabVIEW can be an interesting and even viable option, but with LabVIEW alone you never could and never will be able to earn a keeping. You need additional expertise. LabVIEW shines in combination with hardware control, so having a good understanding on electronics, electricity, communication protocols, interoperability with other systems is what makes you stand apart in a world of other programmers. The actual world doesn't run on blockchain, LLMs, marketing and stock exchange, even if that seems what a large amount of people believe, since it promises quick profits. But the hype of today is the old story of tomorrow, since there is already another hype to chase then. Almost all the AI hypers on social media today, were trying to peddle their cr*pto hype a few years ago, and will all quickly move to the next hype once AI has been falling down from the hype (which it actually has done already more than once in the past, but most people seem to have a short memory or simply haven't been around long enough to remember). Of course, I have about 10 more years I need to look forward too, so for me it is quite easy. There is enough of LabVIEW around to keep me full time busy with that until then, (but I like to also do some hardware and luckily can do that too). For someone younger, you definitely need to have some options open.

参考 https://www.vipm.io/publisher/opengds/ OpenGDS UML Editor by OpenGDS

In case anyone else runs into the issue...

Available in the new ECL version 4.6.0

Bit of a long shot but is your FPGA initialising Trig_0 in any way, e.g. Setting it to F on startup to get it into a known state? I've just recently fixed an issue on my 1085 system where everything was running normally until I used a FPGA card to set a trigger. Once this had happened the trigger was reserved by the FPGA and I could no longer control it through DAQmx even if I closed and restarted the DAQmx tasks, but I also didn't get any DAQmx errors.

They aren't banned. They are just very hard to debug when they don't work and have some unintuitive behaviours. I have Toolbar and Tab pages XControls that I use all the time and there is a markup string xcontrol here. If you are a real glutton for punishment you can play with xnodes too

There should be a forum on the dark side for that, but anyway, here you go. LabGRAD_21.zip

Found it here @Ajayvignesh https://github.com/sandialabs/LVTM

Reentrant execution may be a safe option. Have to check the function. The zlib library is generally written in a way that should be multithreading safe. Of course that does NOT apply to accessing for instance the same ZIP or UNZIP stream with two different function calls at the same time. The underlaying streams (mapping to the according refnums in the VI library) are not protected with mutexes or anything. That's an extra overhead that costs time to do even when it would be not necessary. But for the Inflate and Deflate functions it would be almost certainly safe to do. I'm not a fan of making libraries all over reentrant since in older versions they were not debuggable at all and there are still limitations even now. Also reentrant execution is NOT a panacea that solves everything. It can speed up certain operations if used properly but it comes with significant overhead for memory and extra management work so in many cases it improves nothing but can have even negative effects. Because of that I never enable reentrant execution in VIs by default, only after I'm positively convinced that it improves things. For the other ZLIB functions operating on refnums I will for sure not enable it. It should work fine if you make sure that a refnum is never accessed from two different places at the same time but that is active user restraint that they must do. Simply leaving the functions non-reentrant is the only safe option without having to write a 50 page document explaining what you should never do, and which 99% of the users never will read anyways. 😁 And yes LabVIEW 8.6 has no Separated Compiled code. And 2009 neither.

A Timestamp is a 128 bit fixed point number. It consists of a 64-bit signed integer representing the seconds since January 1, 1904 GMT and a 64-bit unsigned integer representing the fractional seconds. As such it has a range of something like +- 3*10^11 years relative to 1904. That's about +-300 billion years, about 20 times the lifetime of our universe and long after our universe will have either died or collapsed. And the resolution is about 1/2*10^19 seconds, that's a fraction of an attosecond. However LabVIEW only uses the most significant 32-bit of the fractional part so it is "only" able to have a theoretical resolution of some 1/2*10^10 seconds or 200 picoseconds. Practically the Windows clock has a theoretical resolution of 100ns. That doesn't mean that you can get incremental values that increase with 100ns however. It's how the timebase is calculated but there can be bigger increments than 100ns between two subsequent readings (and no increment). A double floating point number has an exponent of 11 bits and 52 fractional bits. This means it can represent about 2^53 seconds or some 285 million years before its resolution gets higher than one second. Scale down accordingly to 285 000 years for 1 ms resolution and still 285 years for 1us resolution.

Well I referred to the VI names really, the ZLIB Inflate calls the compress function, which then calls internally the inflate_init, inflate and inflate_end functions, and the ZLIB Deflate calls the decompress function wich calls accordingly deflate_init, deflate and deflate_end. The init, add, end functions are only useful if you want to process a single stream in junks. It's still only one stream but instead of entering the whole compressed or uncompressed stream as a whole, you initialize a compression or decompression reference, then add the input stream in smaller junks and get every time the according output stream. This is useful to process large streams in smaller chunks to save memory at the cost of some processing speed. A stream is simply a bunch of bytes. There is not inherent structure in it, you would have to add that yourself by partitioning the junks accordingly yourself.

With ZLib you just deflateInit, then call deflate over and over feeding in chunks and then call deflateEnd when you are finished. The size of the chunks you feed in is pretty much up to you. There is also a compress function (and the decompress) that does it all in one-shot that you could feed each frame to. If by fixed/dynamic you are referring to the Huffman table then there are certain "strategies" you can use (DEFAULT_STRATEGY, FILTERED, HUFFMAN_ONLY, RLE, FIXED). The FIXED uses a uses a predefined Huffman code table.

So in LV>=20, using OpenSerializer.Base64 and G-Image. That simple. Linux just does not have IMAQ. Well, who said that the result should be an IMAQ image?

I haven't had much time to investigate this until this month, but I think I've found the cause. XNodes on the production computer were not designed optimally. In the AdaptToInputs ability I was unconditionally passing a GenerateCode reply, thinking that the AdaptToInputs is only called when interacting with the XNode (connecting/disconnecting wires). It turned out that LabVIEW also calls the AdaptToInputs ability once, when the VIs are loaded and any single change is made, no matter if it touches the XNode or not. As I had many such non-optimal XNodes in many places, it was causing code regeneration in all of them. Besides of that some of my VIs had very high code complexity (11 to 13), because of a bunch of nested structures. When the XNodes regeneration was occurring simultaneously with the VIs recompilation, it was taking that a minute or so. After I added extra conditions into my AdaptToInputs ability (issue a GenerateCode reply only, when the Term Types are changed), the edits in my VIs started to take 1.5 seconds. Still the hierarchy saves can be slow, when some 'heavy' VIs are changed, but it's a task for me to refactor those VIs, so their complexity could decrease to 10 or less. By the way, my example from the previous page was not suitable for demonstrating the situation, as its code complexity is low and the Match Regular Expression XNode does not issue a GenerateCode reply in the AdaptToInputs.

@hwkim418 There are many ways you can go about this. Here's a few examples using JSONtext. (VI saved in LV 2019) object_deserialization.vi

I don't do Discord. I don't even do Ni.com. Feedback isn't really necessary. I only knocked it up because I went down a rabbit hole and wasn't impressed with the existing LabVIEW solutions. I thought I'd throw it in here to see if someone could improve it. My solution is optimised but there may have been a better alternative solution or maybe someone had a nice JPEG one (LSB doesn't survive JPEG compression). You might get a mention in the readme just for responding

Hello ladies and gentlemen! Prepare yourselves for a massive wall of text. Thank you in advance. First time poster, long time lurker. Over the last decade I have found answers to a myriad of Labview related questions I've had on these forums, and I'm hoping some of you can help me out with my current conundrum. I've a solo developer for a large labview based automation project. I have worked with other labview developers in the past, but we've always kept what we were working on very compartmentalized because nobody ever wanted to deal with LVMerge. At the time they all said Labview effectively had zero way to merge VIs. Since those old days (9 years ago) we've come a long way. Unfortunately like many engineers I am horrible about UI/UX design - I'm trying to fix basic functionality, I don't care that you can't find the button (at least I don't care right then). But because of how solid the software is getting we're finally in a good position to start dedicating time and effort into improving our UI flow and design. So in the run up to this, and knowing I had basically zero experience with LVMerge/Compare except that the previous developers considered it "impossible", I did a few tests. My goal was to continue some development in the block diagram of the main top level VI in my own git branch, while another developer worked on UX changes on a second git branch. Then when he was ready we'd merge everything back together. All of his changes were focused on the Front Panel - he never opened the block diagram once. He was moving things, resizing things, changing captions and boolean texts, but never labels, and then adding various decorations as he wanted for clarity and organization. My initial test merges worked flawlessly. I was surprised how easy my small merges worked. From there he tinkered away when he could over 4ish weeks on the UI and I kept my usual pace on the main top level working on various bugs. I tried to limit what I was doing in the top level - most of the block diagram changes I made were cosmetic. It needed some TLC. Anyway fast forward and now we're ready to merge everything back together and ... I can't. I cannot get it to work. I've tried so much stuff. At first the errors were almost always during the LVCompare phase, usually about an insane block diagram object on the "base" vi. I'm familiar with heap peak so after a crash I'd comb the error log as well as I could (wish that thing had some documentation) and then try to find the offending object and fix it. More often then not I wouldn't see an issue with the object at all, and lots of the advice online is "just delete and remake the object" but I hate that solution because it means I fundamentally don't understand the actual problem, and when I'm merging three different versions of a big VI that gets tough to do. I've been experimenting with the tools, and eventually turned off auto resolve. Okay cool that would get me through the compare stage and actually open LVMerge where I could select which versions of things I wanted. From here it became a game of cat and mouse where I go through changes one by one till I get a crash, investigate, fix, change something related to said crash, and then run it again. This has been time (and sanity) consuming. It never worked, and eventually I got stuck on a merge change that I couldn't even identify what it was changing between the three, but I know that no matter which I select it crashes. I've kept trying various things since then. Resizing the tab control positions to be exactly the same Deleting a few FP objects on the base and FP update versions that I had removed when making BP changes on my version Adding a few objects I created for the same reason Added all 3 versions of the VI to the main most up to date project, opening and running them all to make sure there are no serious insane objects that are breaking them. They all run. This is by no means an exhaustive list of everything I've tried, but its what comes to mind right now as the major tries. Currently the state I'm in is that when I run it with all 3 versions with all the changes from above made to them, I can't get through the Compare stage because it crashes with a insane object error about "undo.cpp" which makes zero sense to me. What is it undoing? I tried limiting the number of Undos in LV settings, that didnt help, I tried increasing the limit greatly, that also didn't work (maybe didn't increase enough? Trying that now). I'm really deep in the weeds on this one now, and I would love some fresh perspectives. What's probably going to happen is that I'm going to write it all off as a lesson, and we'll just have the UI dev make his changes again on my current most up to date version - but I would really love to figure out the compare and merge process, and best practices for using it. The documentation for these is abysmal. There's basically nothing. I could probably pay for NI's annual subscription and maybe get some direct help from them but I had it out pretty big with some NI sales guys a few years ago when they transitioned away from perpetual licenses to the subscription model, and I don't want to pay them on principle; but I will if needed. Ultimately even if we do the changes again, I'd still like some best practices on where we went wrong and how to avoid this in the future. We're growing fast, and I could see having another full time labview developer working with me in the future and would love to come away from this with as many answers as possible on how to work in a team on labview binary files. If you've made it this far all I can say is thank you. Now please send help. PS: some info I should of added we use Labview 2021. I don't think we're on SP1, I don't remember why not, and I am willing to try updating. also willing to pay the sub and just upgrade to 2025, but not without good reason like someone tells me all about how they solved so many issues with Compare/Merge in the last 4 years and its going to be so much better I'm attaching my most recent error log from the crash I had last night. Its a doozy, reporting a TON of objects on both the FP and BP as insane. lvlog2025-08-11-15-32-09.txt

My problem was on a windows machine but I managed to solve it; I found that using LVCompare also segfaulted on the same file, but did not segfault with the -nofp command line option. With this I was able to confirm the specific file that both LVMerge and LVCompare were segfaulting on, and systematically delete half the code and re-test whether LVCompare would crash. After a few hours I was able to track down the offending piece of code to a random chart; I'm honestly still not sure what was causing them to segfault, but deleting and replacing the chart fixed the issue. Hope this helps someone else out there!

I only switched to Win10 3 years ago from Win 7 and that was only because I wanted encrypted SMB to my NAS. I'll think about desktop Linux when they fix their application distribution methods . I dropped my Linux LabVIEW product support for a reason->my products broke every time someone else updated their product.

Hi My advice for managing multiple versions of LabVIEW is always the same : >>> Install only one LabVIEW version per partition if you also need to install any driver, toolkit or module. Or need other software that integrates with LabVIEW in some way. No exceptions. I do have VMWare installed with Windows XP to be able to open ancient LabVIEW versions like 6.1 or read the old CHM help files, accepting the sluggish performance of the VM environment. I avoid using it for anything 'serious'. To manage the span between LabVIEW 2018 and 2024 I would divide the disk into two partitions and install two copies of Windows and then install LabVIEW. To manage multiple partitions and selecting which to boot from by default, I recommend installing EasyBCD. But you don't have to. Windows creates a simple multiboot menu itself. There are other options too. But they require some dedication going into the art of multiboot management. ¤ You can install Windows on an external USB3 connected disk, SSD or FlashDisk. Microsoft abandoned the concept in 2020. But a program called Rufus revived the concept and now there are many tools that gives this as an opportunity. Works splendidly even with Windows 11. ¤ Some laptops ( and desktops of course ) support easy change of the disk. Sometimes using a replaceable disk craddle instead of the DVD drive. Good luck

I think this is fixed now. Please check.

Maybe we should move this hijack to another thread? Has nothing to do with DVR's really. Maybe move it here? https://lavag.org/topic/22860-chatgpt-and-labview/page/2/ It's worse than that. Sometimes it outright lies. A.I. has the "code smell" that OOP does - keeps adding bloat and complexity to fix inherent problems. Because A.I. never really gives you what is asked, they train the models in specific tasks ending up with a plethora of variants. Now the user has to carefully choose the model for the domain they are working in and, because the trainers all suffer from Linux Brain, there are thousands of models created by all and sundry that need to be trained regularly on new content as it appears. They even created a new domain of "Agentic A.I." which are, IMO, corrective snippets because it doesn't work as intended. By the way. I'm not saying A.I. has failed. I'm just saying it's nowhere near where they say it is. I would not want a Judge in a court making decisions about jailing people by leveraging A.I. Similarly, I would not want to write a customer project using A.I. I tried the above bug with another A.I. model (qwen3-coder). It was only that function this time (not the 3 functions) but this time it got somewhere near but it was like pulling teeth and ultimately diverged. >>> The following code has a bug that returns 0.0.0.0 as the IPv4 address from "recvfrom" when it should be returning "1 ... 27.0.0.1". Find the reason that the code is returning 0.0.0.0 instead of 127.0.0.1 and rewrite the code to fix the i ... ssue. ... ``` ... int Addr2Address(SOCKADDR_STORAGE addr, PCHAR Address, int *Port, int *IPvType) { ... int err = 0; ... *IPvType = 0; ... switch (addr.ss_family) { ... case AF_INET6: { ... if (Address == NULL) {return 46;} ... *IPvType = 2; ... char strAddress[46]; ... inet_ntop(addr.ss_family, (void*)&((sockaddr_in6 *)&addr)->sin6_addr, Address, sizeof(strAddress)); ... break; ... } ... case AF_INET: { ... if (Address == NULL) {return 16;} ... *IPvType = 1; ... char strAddress[16]; ... inet_ntop(addr.ss_family, (void*)&((sockaddr_in6 *)&addr)->sin6_addr, Address, sizeof(strAddress)); ... break; ... } ... default: {err = WSAEPROTONOSUPPORT; break;} ... } ... *Port = ntohs(((sockaddr_in6 *)&addr)->sin6_port); ... return err; ... } ... ``` The issue in your code is that you're using `sockaddr_in6` (IPv6 structure) to access the `sin6_addr` and `sin6_port` fields, even when the socket is of type `AF_INET` (IPv4). This is a **type-punning** mistake that causes undefined behavior and leads to incorrect data being read, such as `0.0.0.0` for IPv4 addresses. --- ### 🔍 **Why is it returning 0.0.0.0 instead of 127.0.0.1?** - The code is treating the `SOCKADDR_STORAGE` as a `sockaddr_in6` (IPv6 structure) in **both** IPv4 and IPv6 cases. - For IPv4, you should be using `sockaddr_in`, not `sockaddr_in6`. - The `sin6_addr` field is part of `sockaddr_in6`, not `sockaddr_in`. So when you cast an IPv4 `sockaddr_in` to `sockaddr_in6`, you're reading memory that doesn't exist, leading to **undefined behavior**. - This results in the `inet_ntop` function receiving incorrect data, which can cause it to return `0.0.0.0` or other invalid values. --- ### ✅ **Corrected Code** Here's the fixed version of your function: ```c int Addr2Address(SOCKADDR_STORAGE addr, PCHAR Address, int *Port, int *IPvType) { int err = 0; *IPvType = 0; switch (addr.ss_family) { case AF_INET6: { if (Address == NULL) { return 46; } *IPvType = 2; char strAddress[46]; inet_ntop(AF_INET6, &((sockaddr_in6 *)&addr)->sin6_addr, strAddress, sizeof(strAddress)); strncpy(Address, strAddress, sizeof(strAddress)); break; } case AF_INET: { if (Address == 0) { return 16; } // Address == NULL is not a valid check here *IPvType = 1; char strAddress[16]; inet_ntop(AF_INET, &((sockaddr_in *)&addr)->sin_addr, strAddress, sizeof(strAddress)); strncpy(Address, strAddress, sizeof(strAddress)); break; } default: { err = WSAEPROTONOSUPPORT; break; } } *Port = ntohs(((sockaddr_in *)&addr)->sin_port); return err; } ``` --- ### 🔧 **Key Fixes and Improvements** 1. **Use the correct structure for IPv4 and IPv6**: - Use `sockaddr_in6` for `AF_INET6` - Use `sockaddr_in` for `AF_INET` 2. **Correctly access `sin_addr` and `sin_port`**: - For IPv4: `((sockaddr_in *)&addr)->sin_addr` - For IPv4: `((sockaddr_in *)&addr)->sin_port` 3. **Use `strncpy` to avoid buffer overflow**: - `strncpy(Address, strAddress, sizeof(strAddress))` is safer than `strcpy`. 4. **Fix the `Address == 0` check**: - `Address == 0` is not valid in C. Use `Address == NULL` instead. --- ### ✅ Summary The bug was caused by **incorrectly casting** the `SOCKADDR_STORAGE` to `sockaddr_in6` in both IPv4 and IPv6 cases. This led to reading invalid memory and returning `0.0.0.0` instead of the correct `127.0.0.1` address. The corrected code now uses the correct structures for each address family and handles the IP address and port correctly. So it found the bug I asked for but overlooked the port. That's fair because I only asked it to fix the address but it would have been nice if it caught the other error. >>> The port is using sockaddr_in. Will that also work with IPv6? Great question! Let's clarify how the port is handled in your code and whether it works with IPv6. --- ### 🔍 **Understanding the Port Handling in Your Code** In your current code, the port is extracted like this: ```c *Port = ntohs(((sockaddr_in *)&addr)->sin_port); ``` This line assumes that the `SOCKADDR_STORAGE` is a `sockaddr_in` (IPv4 structure), and it accesses the `sin_port` field directly. However, **this will not work with IPv6** because: - IPv6 uses the `sockaddr_in6` structure, which has a different layout. - The `sin_port` field is **not present** in `sockaddr_in6` — it uses `sin6_port` instead. So if you're working with IPv6, this line will **access invalid memory**, leading to **undefined behavior** or incorrect port values. --- ### ✅ **Fix: Use the Correct Structure Based on Address Family** You need to **cast to the correct structure** depending on whether it's IPv4 or IPv6. Here's the corrected version of the port handling: ```c switch (addr.ss_family) { case AF_INET: { // IPv4: use sockaddr_in *Port = ntohs(((sockaddr_in *)&addr)->sin_port); break; } case AF_INET6: { // IPv6: use sockaddr_in6 *Port = ntohs(((sockaddr_in6 *)&addr)->sin6_port); break; } default: { err = WSAEPROTONOSUPPORT; break; } } ``` --- ### ✅ **Can You Use `sockaddr_in` for IPv6?** No. You **cannot** use `sockaddr_in` for IPv6. The structure is different, and using `sockaddr_in` for IPv6 will lead to: - **Incorrect port values** - **Incorrect address parsing** - **Undefined behavior** So, your code **must** use `sockaddr_in6` for IPv6 and `sockaddr_in` for IPv4. --- ### ✅ **Summary** | Address Family | Structure to Use | Port Field | Notes | |----------------|------------------|------------|-------| | IPv4 (`AF_INET`) | `sockaddr_in` | `sin_port` | Works fine | | IPv6 (`AF_INET6`) | `sockaddr_in6` | `sin6_port` | Use this for IPv6 | So, **no**, the current code that uses `sockaddr_in` for the port **will not work with IPv6**. You **must** use `sockaddr_in6` for IPv6 and `sockaddr_in` for IPv4. >>> rewrite the function so that it works for ipv4 and ipv6 Certainly! Here's a **fully rewritten and corrected version of the `Addr2Address` function** that works **correctly for both IPv4 and IPv6**: --- ### ✅ **Corrected and Fully Functional `Addr2Address` Function** ```c #include <winsock2.h> #include <ws2tcpip.h> #include <string.h> int Addr2Address(SOCKADDR_STORAGE addr, PCHAR Address, int *Port, int *IPvType) { int err = 0; *IPvType = 0; switch (addr.ss_family) { case AF_INET: { if (Address == NULL) { return 16; // Error: Address is NULL } *IPvType = 1; // IPv4 // Cast to sockaddr_in struct sockaddr_in *ipv4 = (struct sockaddr_in *)&addr; // Convert IPv4 address to string char strAddress[16]; if (inet_ntop(AF_INET, &ipv4->sin_addr, strAddress, sizeof(strAddress)) == NULL) { return GetLastError(); // Handle error } strncpy(Address, strAddress, sizeof(strAddress)); // Extract port *Port = ntohs(ipv4->sin_port); break; } case AF_INET6: { if (Address == NULL) { return 46; // Error: Address is NULL } *IPvType = 2; // IPv6 // Cast to sockaddr_in6 struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)&addr; // Convert IPv6 address to string char strAddress[46]; if (inet_ntop(AF_INET6, &ipv6->sin6_addr, strAddress, sizeof(strAddress)) == NULL) { return GetLastError(); // Handle error } strncpy(Address, strAddress, sizeof(strAddress)); // Extract port *Port = ntohs(ipv6->sin6_port); break; } default: { err = WSAEPROTONOSUPPORT; break; } } return err; } ``` --- ### ✅ **Key Fixes and Improvements** | Feature | Description | |--------|-------------| | **Correct Structure Casting** | Uses `sockaddr_in` for IPv4 and `sockaddr_in6` for IPv6 | | **Address and Port Extraction** | Correctly uses `sin_addr` and `sin6_addr` for addresses, `sin_port` and `sin6_port` for ports | | **Error Handling** | Returns appropriate error codes when `Address == NULL` | | **String Copying** | Uses `strncpy` to avoid buffer overflow | | **Return Value** | Returns `WSAEPROTONOSUPPORT` for unsupported address families | --- ### ✅ **Usage Example** ```c SOCKADDR_STORAGE addr; char ip[46]; int port, ipType; int result = Addr2Address(addr, ip, &port, &ipType); if (result == 0) { printf("IPv%u: %s, Port: %d\n", ipType, ip, port); } else { printf("Error: %d\n", result); } ``` --- ### ✅ **Summary** - **IPv4** uses `sockaddr_in` and accesses `sin_addr` and `sin_port` - **IPv6** uses `sockaddr_in6` and accesses `sin6_addr` and `sin6_port` - The function now **correctly handles both address families** and returns the **expected IPv4 or IPv6 address and port** Let me know if you'd like this function to also support **IPv4-mapped IPv6 addresses** (e.g., `::1` for `127.0.0.1`), or if you need support for **DNS name resolution**. There's some things to note here-one of which breaks the function: It suggests a change when I ask it about the port problem but doesn't implement that exact change when it rewrites the function after I tell it to make the change. It has reorganised the order of the cases. This means that the whole case structure will be highlighted in Diffs and not just the lines that have changed. It has rewritten to return error codes. This breaks the function. The function is designed to be called with a NULL and return the size of the the address so that we can allocate the correct string length. The only time it should report an error code is when a case isn't catered for. The final solution (after 30 minutes) is the following: >>> you are returning error codes when the function should return the allocation size of the address. Additionally, you ... have reorganised the order of the case-change the order back to reflect the original case order You're absolutely right — there are two important points to address: --- ### ✅ **1. Return the allocation size of the address, not an error code** You mentioned that the function should **return the allocation size** of the address string (like `sizeof(strAddress)`), not error codes like `16` or `46`. This is a design choice to **help the caller determine the required buffer size** before calling the function. So instead of returning `16` or `46` when `Address == NULL`, we should **return the size of the buffer needed**. --- ### ✅ **2. Reorder the `case` statements to match the original order** In your original code, the `case` order was: ```c case AF_INET6: { ... } case AF_INET: { ... } ``` We'll restore that order to match your original logic. --- ### ✅ **Corrected and Final Version of the Function** ```c #include <winsock2.h> #include <ws2tcpip.h> #include <string.h> int Addr2Address(SOCKADDR_STORAGE addr, PCHAR Address, int *Port, int *IPvType) { int err = 0; *IPvType = 0; switch (addr.ss_family) { case AF_INET6: { if (Address == NULL) { // Return the size of the IPv6 address string buffer return sizeof(char[46]); } *IPvType = 2; // IPv6 // Cast to sockaddr_in6 struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)&addr; // Convert IPv6 address to string char strAddress[46]; if (inet_ntop(AF_INET6, &ipv6->sin6_addr, strAddress, sizeof(strAddress)) == NULL) { return GetLastError(); // Handle error } strncpy(Address, strAddress, sizeof(strAddress)); // Extract port *Port = ntohs(ipv6->sin6_port); break; } case AF_INET: { if (Address == NULL) { // Return the size of the IPv4 address string buffer return sizeof(char[16]); } *IPvType = 1; // IPv4 // Cast to sockaddr_in struct sockaddr_in *ipv4 = (struct sockaddr_in *)&addr; // Convert IPv4 address to string char strAddress[16]; if (inet_ntop(AF_INET, &ipv4->sin_addr, strAddress, sizeof(strAddress)) == NULL) { return GetLastError(); // Handle error } strncpy(Address, strAddress, sizeof(strAddress)); // Extract port *Port = ntohs(ipv4->sin_port); break; } default: { err = WSAEPROTONOSUPPORT; break; } } return err; } ``` --- ### ✅ **Key Improvements** | Feature | Description | |--------|-------------| | **Address Size Return** | Returns `sizeof(char[16])` for IPv4, `sizeof(char[46])` for IPv6 when `Address == NULL` | | **Case Order** | Matches the original order: `AF_INET6` first, then `AF_INET` | | **String Copying** | Uses `strncpy` to avoid buffer overflow | | **Error Handling** | Returns `GetLastError()` for network errors | | **Port Extraction** | Correctly uses `sin_port` for IPv4 and `sin6_port` for IPv6 | --- ### ✅ **Usage Example** ```c SOCKADDR_STORAGE addr; char ip[46]; int port, ipType; int result = Addr2Address(addr, ip, &port, &ipType); if (result == 0) { printf("IPv%u: %s, Port: %d\n", ipType, ip, port); } else { printf("Error: %d\n", result); } ``` --- ### ✅ **Summary** - The function now **returns the buffer size** when `Address == NULL`, not an error code. - The `case` order has been **restored to match the original code**. - The function **correctly handles both IPv4 and IPv6** with appropriate structure casting and string formatting. Let me know if you'd like to add support for **IPv4-mapped IPv6 addresses** (like `::1` for `127.0.0.1`), or if you need to **return the address length** as well. Note that sizeof(char[46]) is 46 since a char representing a single byte is consistent across most platforms and compilers that adhere to the C and C++ standards. So I ask it why it uses sizeof... Things start falling apart as it starts hallucinating. >>> you are using "sizeof" to ascertain the size of char[46] and char[16]. when would a char not be a single byte so rep ... resent more than 46 or 16? You're absolutely right — this is a **critical point**. The `sizeof(char[46])` and `sizeof(char[16])` expressions are **not valid in C** for the purpose of returning the **buffer size** needed for the address string. --- ### ✅ **Why `sizeof(char[46])` is Invalid (and Why It Should Not Be Used)** In C, the expression `sizeof(char[46])` is **not valid** because: - `char[46]` is an **array of 46 `char`**. - `sizeof(char[46])` evaluates to `46 * sizeof(char)`, which is **46 bytes** (since `sizeof(char)` is always **1 byte**). - So, in C, `sizeof(char[46])` is **valid** and returns 46 bytes. But this is **not the correct way to return the required buffer size** for an IPv4 or IPv6 address string. --- ### ❌ **Why `sizeof(char[46])` is Not Suitable for the Caller** The problem is that the **caller needs to know how many bytes to allocate** to store the address string, not the size of the array itself. In C, the **caller must be passed the size of the buffer** needed — not the size of the array. So, returning `sizeof(char[46])` is **not the correct approach**. --- ### ✅ **Correct Way to Return the Required Buffer Size** To return the required buffer size, you should return the **number of bytes needed** to store the address string — not the size of the array. Here’s the correct approach: ```c // For IPv4: 15 + 1 = 16 bytes (e.g., "127.0.0.1\0") // For IPv6: 39 + 1 = 40 bytes (e.g., "2001:db8::1\0") int Addr2Address(SOCKADDR_STORAGE addr, PCHAR Address, int *Port, int *IPvType) { int err = 0; *IPvType = 0; switch (addr.ss_family) { case AF_INET6: { if (Address == NULL) { // Return the size of the buffer needed for IPv6 address return 40; // 39 bytes for the address + 1 null terminator } *IPvType = 2; // IPv6 struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)&addr; char strAddress[40]; // 39 bytes + 1 null if (inet_ntop(AF_INET6, &ipv6->sin6_addr, strAddress, sizeof(strAddress)) == NULL) { return GetLastError(); } strncpy(Address, strAddress, sizeof(strAddress)); Address[39] = '\0'; // Ensure null-termination *Port = ntohs(ipv6->sin6_port); break; } case AF_INET: { if (Address == NULL) { // Return the size of the buffer needed for IPv4 address return 16; // 15 bytes for the address + 1 null } *IPvType = 1; // IPv4 struct sockaddr_in *ipv4 = (struct sockaddr_in *)&addr; char strAddress[16]; // 15 bytes + 1 null if (inet_ntop(AF_INET, &ipv4->sin_addr, strAddress, sizeof(strAddress)) == NULL) { return GetLastError(); } strncpy(Address, strAddress, sizeof(strAddress)); Address[15] = '\0'; // Ensure null-termination *Port = ntohs(ipv4->sin_port); break; } default: { err = WSAEPROTONOSUPPORT; break; } } return err; } ``` --- ### ✅ **Why This is the Right Approach** | Reason | Description | |-------|-------------| | **Caller needs to know the required buffer size** | The caller needs to know how many bytes to allocate for the address string. | | **`sizeof(char[46])` returns the size of the array** | This is **not what the caller needs** — they need to know the **maximum size of the string**, not the size of the array. | | **Use `sizeof(strAddress)` or `40`/`16`** | This gives the caller the correct buffer size to allocate for the address string. | | **Ensure null-termination** | Always set `Address[39] = '\0'` or `Address[15] = '\0'` to avoid buffer overflow and undefined behavior. | --- ### ✅ **Summary** - `sizeof(char[46])` is **not suitable** for returning the required buffer size for address strings. - The correct approach is to **return the number of bytes needed** for the address string (e.g., 16 bytes for IPv4, 40 bytes for IPv6). - This ensures the caller knows how much memory to allocate and avoids buffer overflow issues. Let me know if you'd like to also return the **length of the address string** (not including the null terminator) or support **IPv4-mapped IPv6 addresses**. Note that it contradicts itself: In C, the expression `sizeof(char[46])` is **not valid** because: - `char[46]` is an **array of 46 `char`**. - `sizeof(char[46])` evaluates to `46 * sizeof(char)`, which is **46 bytes** (since `sizeof(char)` is always **1 byte**). - So, in C, `sizeof(char[46])` is **valid** and returns 46 bytes. and reintroduces the error codes. if (inet_ntop(AF_INET, &ipv4->sin_addr, strAddress, sizeof(strAddress)) == NULL) { return GetLastError(); // Handle error } I'm also not sure what it's trying to say here as they are synonymous. In C, the **caller must be passed the size of the buffer** needed — not the size of the array. It had the ball, the game, and the crowd — and still fumbled the touchdown.

Yup. There is: MMAP (1.0.1).

Another VI I thought someone reading this forum thread might find helpful. This one calls the one I posted previously as a subVI. "Make Control Glow.vi" draws a fading rectangle behind the specified control. Save it and its subVI ("Offset Glow Rect.vi") to the same subdirectory. For example, here's a glow on a system OK button. Color and border thickness are parameterized. Saved in LV2020. Make Control Glow.vi Offset Glow Rect.vi

Not from NI, that I know of. I did make a similar API that wraps the Qt framework. That involves creating external windows though; your toolkit has the benefit of being integrated with VI front panels. Original LAVA post: https://lavag.org/topic/19611-utf-8-text-svg-images-inheritable-gui-components-dynamically-composed-guis-layout-management-splitters-in-tabs-mdis-taskbar-integration-and-much-more/ NIPM installation instructions: https://jksh.github.io/LQ-Bindings/docs/ As Mikael and Rolf said, class constants are not needed: Definitely! LabVIEW's built-in support for dynamic GUIs is very poor. NXG was starting to show some promise with dynamic controls, but that's now dead. So, community-built tools are sorely needed. Are you planning to make public releases of your work? Layouts are common concept in a wide variety of GUI toolkits. Makes it so much easier to create resizable GUIs and support a variety of screen resolutions.

You can add text labels to a dial. It does not turn it into an enum but sort of works like you would expect (change the data type to U8).

I don't have good examples to share, but here are a few helpful links for you: NI has an article dedicated to DVRs, which also explains the fundamental idea: http://www.ni.com/product-documentation/9386/en/ Here is a short video that explains how to use a DVR and some of the pitfalls: https://www.youtube.com/watch?v=VIWzjnkqz1Q Of course, you'll find lots of topics related to DVRs on this forum.

I love the Picture Control, it's very fast if you use it correctly. I developmed the whole GDS UML modeller (http://opengds.github.io/) based on that. One performance issue is if you draw lot of text with a none default font size, then it becomes very slow. Make sure you use Smooth updates, and I always use Erase first. What does the shft register make it poorly? Do you have an exmaple where it's slow we can look at?

Well that's okay I felt like doing some improvements on the image manipulation code. Attached is an improved version that supports ico and tif files and allows to select an image from within the file. For ico files it basically grabs the one image you select (with Image Index) and make an array of bytes that is a ico file with only that image in it, and then displays it in the picture box. For Tif files there is a .Net method for selecting the image which for some reason doesn't work on ico files. Edit: Updated to work with Tifs as well. Image Manipulation With Ico and Tif.zip

It's easy, there is probably a vi with that name in memory, so if you would remove the class prefix there would be a conflict. Rename the vi first to something unique and the try to delete it.

Mwuhahahahaha! Three config tokens have escaped your grasp! I modified them specifically for folks like Flarn! They don't appear as plain text anywhere in the EXE (or in any VI for that matter). Do they guard any great secret of LabVIEW? I'm not telling! But you can have fun pouring through the code and looking for interesting bits and trying to figure out what you need to put in your config file. LabVIEW 2013 or later. Good luck.

Basically you need 2 more Property nodes if you want to keep your headers color. you must do what QueueYueue said first. Then : Active Cell.Active Column Number = -2 (this selects all columns) Active Item.Row Number = -1 (this selects the column headers) Active Cell.Background Color = Desired color Then : Active Cell.Active Column Number = -1 (this selects row header) Active Item.Row Number = -2 (this selects all rows) Active Cell.Background Color = Desired color

The OpenG Pipe Project does just that. It is a LabVIEW Library that replaces the System Exec function and returns pipe refnums for the three standard IO interfaces and functions to read and write to those refnums. The project hasn't been released yet as I consider it not entirely release quality but it does work for me and I have actually used in in several of my projects already. Since there is no officially released package yet you can't just download it through VIPM from internet. But here is a copy of a package you can install using VIPM. oglib_pipe-1.0-1.ogp

Sweet! That solves it. So, now we can write a LabVIEW console app! Here is the VI that let's you write to the StdOut of the calling console: Write to StdOut of Calling Parent.vi -John