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"

Many years ago I made a demo for myself on how to drag and drop clones of a graph. I wanted to show a transparent picture of the new graph window as soon as the drag started, to give the user immediate feedback of what the drag does and the window to be placed exactly where it is wanted. I think I found inspiration for that on ni.com or here back then, but now I cannot find my old demo, nor the examples that inspired me back then. Now I have an application where I want to spawn trends of a tag if you drag the tag out of listbox and I had to remake the code...(see video below). At first I tried to use mouse events to position the window, but I was unable to get a smooth movement that way. I searched the web for similar solutions and found one that used the Input device API to read mouse positions to move a window without a title and that seemed to be much smoother. The first demo I made for myself is attached here (run the demo and drag from the list...). It lacks a way to cancel the drag though; Once you start the drag you have a clone no matter what. dragtrends.mp4 Has anyone else made a similar feature? Perhaps where cancelling is handled too, and/or with a more generic design / framework? Drag window out of listbox - Saved in LV2018.zip

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 once went for an interview where they gave me a coding test and asked me to modify it. It was a very long time ago so I don't remember the exact modification they wanted (nothing to do with memory leaks) but I do remember the obtain queue and read queue inside a while loop with the release queue outside. I asked if they wanted me to also fix the memory leak as well as the modifications and they were a little puzzled until I explained what you have just said. I must have seen (and fixed) this while-loop bug-pattern a thousand times since then in various code bases. I also created this VI which I generally use instead of the primitives as it intialises on first call, can be called from anywhere, and prevents most foot-shooting by rolling them all into a single VI and ensuring all references but 1 are closed after use. Queue.vi

Those aren't typo's and errors. They are tests to see if we are paying attention.

In the past I have used the IMAQ drivers for getting the image, which on its own does not require any additional runtime license. It is one of those lesser known secrets that acquiring and saving the image is free, but any of the useful tools have a development, and deployment license associated with it. I've also had mild success with leveraging VLC. Here is the library I used in the past, and here is another one I haven't used but looks promising. With these you can have a live stream of a camera as long as VLC can talk to it, and then pretty easily save snapshots. EDIT: The NI software for getting images through IMAQ for free is called "NI Vision Common Resources". This LAVA thread is where I first learned about it.

Just to share how I got around this: By deleting 1 front panel item at a time I found that one single control was causing PaneRelief to crash; an XY graph. Setting it temporarily to not scale and replacing it with a standard XY graph (the one I had had some colours set to transparent etc) was enough to avoid having PaneRelief crash LabVIEW, but it would now just present a timeout error: I found a way arund this too though: the VI in question was member of a DQMH lvlib that probably added a lot of complexity for PaneRelief. With a copy saved as a non-member it worked: I could replace the graph, edit the splitters with PaneRelief without the timeout error (even setting the size to 0), then copy back the original graph replacing the temporary one, and finally move the copy back into the lvlib and swap it with the original. Voila! What a Relief... 😉 I probably have to repeat this whole ordeal if I ever need to readjust the splitters in that VI with PaneRelief though 😮

I confirm that this license is nearly identical to the standard EULA we use for our commercial products. Some wording is not applicable to a distributed palette of VIs like this. Our intention was to share a few reusable tools, used internally, with the community. Ideally, we should have released them under a standard open-source license such as MIT or a similar option. These VIs have been released “as-is,” without support or any guarantee that they will function for your specific use case. You may need to troubleshoot or fix any issues on your own. Feel free to use them in any context. I’ll look into whether it's possible to update the packages on the tool network to replace the current license with a more standard open-source one.

I put a temporary ban on inserting external links in posts (except from a safe list). We'll see what affect it has.

This is the modern 2020's equivalent of "works for me".

Your reporting of spam is helpful. And just like you are doing one report per user is enough since I ban the user and all their posts are deleted. If spam gets too frequent I notify Michael and he tweaks dials behind the scene to try to help. This might be by looking at and temporarily banning new accounts from IP blocks, countries, or banning key words in posts. He also will upgrade the forum's platform tools occasionally and it gets better at detecting and rejecting spam.

Apparently they moved it under Visible Items Edit: This also affects other types of structures.

Well, there are two aspects. The first is the technical one from hackers diving into the software and unhiding things that NI felt were not ready for prime time, to complicated for simple users, or possibly also to powerful. The main reason definitely always is however: if we release that, we have to spend a lot more effort to make it a finished feature (a feature for internal use where you can tell your users: "sorry that was not meant to be used in the way you just tried") is maybe 10 - 20% of development time than the finished feature for public use. There is also support required. That costs money in terms of substantial extra development, end user quality documentation (a simple notepad file doesn't cut it), maintenance and fixing things if something does not match the documented behaviour. And yes I'm aware they don't always fix bugs immediately (or ever) but the premise is, that releasing a feature causes a lot of additional costs and obligations, if you want to or not. The other aspect is, if someone who is an active partner and has active contacts with various people at NI, he is infinitely more likely to be able to influence decisions at NI than the greatest hacker doing his thing in his attic and never talking with anyone from NI. In that sense it is very likely that Jim having talked with a few people at NI has done a lot more to make NI release this feature eventually, than 20 hackers throwing every single "secret" about this feature on the street. In that sense the term "forcing NI's hands" is maybe a bit inaccurate. He didn't force them, but led them to see the light! Not out of pure selfless love, but to be able to officially use that feature for himself. The according Right-Click framework was a proof of concept to see how this feature can be used and mainly an example to other users how it can be used, and indeed once it worked it had fulfilled its purpose. That it was not maintained afterwards is not specifically JKI's fault. It is open source, so anyone could have picked up the baton, if they felt it was so valuable for them. The problem with many libraries is actually, if they are not open source and free, many complain about that, if it is open source and/or free, they still expect full support for it! In that sense I have seen a nice little remark recently:

Well, you are missing some important details in "The story of how this came about". So maybe indeed "it is worth a post of its own". It was LabVIEW 7.0 where they forgot to put a password on one of the VIs shipped with LabVIEW. And that VI had some node(s) on its block diagram including, I think, the BD reference property for the VI class. The community indeed got excited. But what did NI do? They tried to hide everything again in LabVIEW 7.1! I made a joke then that "our mother" NI must had had a PMS so she put the most interesting toys on a top shelf. So I made a"ladder" for us, kids, to get to them again and called it hviewlabs was me then, because that was a name of my company I used to sell my LabHSM Toolkit, an actor framework with actors controlled by hierarchical state machines (statecharts), long before the Statechart toolkit by NI, "THE Actor Framework", DQMH, and even before LVOOP. After PJM_Labview has published his private class generator http://forums.lavag.org/index.php?showtopic=307&hl=# and class hierarchies http://forums.lavag.org/index.php?showtopic=2161# and http://forums.lavag.org/index.php?showtopic=314&hl=hierarchy# (neither topic is available anymore) it became clear how to get access to private classes, properties and methods. However, it wasn't convenient enough. My PMS Assistant made it really easy. It gave back the access to those features to a much wider community of LabVIEW enthusiasts As you can see from the PMS topic discussion, by that time brian175 already had made his DataAct Class Browser. And he got really excited about the possibility not only browse but also to actually create objects, property and method nodes with the properties and method NI didn't want the users to see. By April of the same 2006 he figured out object creation too and incorporated the capabilities of PMS Assistant into DataAct Class Browser. At that point, I guess, NI decided that "the cat is out of the bag" and there is no point to resist. Nevertheless even after VI Scripting was made released by NI some classes, and even some properties and methods of public classes remain hidden even in LabVIEW 2024. I wonder why DataAct Class Browser is no longer available (as of January 2025) as well as original findings by PJM_Labview even here, on LavaG. Did NI "politely asked" admins to remove all that and just forgot about my PMS Assistant?

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.

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.

You could also check https://github.com/ISISSynchGroup/mjpeg-reader which provides a .Net solution (not tried). So, who volunteers for something working on linux?

From what I can remember, for LV 5.0.x and older RTE (i.e., a loader plus small subset of resources) was included into the EXE automatically during the build process. For LV 5.1.x there was a choice: to include RTE into the build or to use an external RTE. And since LV 6.0 only an external RTE was supposed. I could say more, such a trick is still possible for all modern versions on all three platforms (Win, Mac, Linux). The latest version I tested it on, was LV 2018, but I'm pretty sure, the technique hasn't changed much. I can't remember, from which version NI started to use Visual Studio 2015, but since then each EXE requires The Universal CRT, that is contained in Microsoft Visual C++ 2015 Redistributable. One could install such a distro on a clean machine or copy all these files from the machine, where such a CRT is already installed. Now besides of those the application will also require this minimal subset of folders/files (true for LV 2018 64-bit): On Linux it goes much easier (true for LV 2014 64-bit): For LV 2018 64-bit with a "dark" RTE it also wants And for Mac OS you can embed RTE into the application with this script: Standalone LabVIEW-built Mac Application with Post-Build Action. Of course (and I'm sure everyone understands that), the technique described above, is applicable to very simple 'a la calculator' apps and not very to not at all for more or less complex projects. The more functions are called, the more dependencies you get. If something from MKL is used, you need lvanlys.dll and LV##0000_BLASLAPACK.dll, if VISA is used, you need visa32.dll, NiViAsrl.dll and maybe others, and so on and so forth.

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.

I have always used this library to prevent the screensaver and windows lock from occurring. Our IT locks down the computer so the screensaver, lock screen, cannot be changed. This library bascially tells Windows it's in Presentation mode, e.g., slideshow, watching a movie, etc, such that the screen will not got to screensaver or lock screen.

@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 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.

You may also want tell people where you can actually download or at least buy this. Although if you want to sell it, do not expect to many reactions. It is already hard to get people to use such toolkits when you offer them for free download.

I posted a demo set of VIs here which can pop up a window, centered on whatever monitor the mouse is on. There's also settings to have the window center on the mouse wherever it is, but saying on the same monitor. And yes this uses the All Screens, Working Area properties.

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.

Some people might be tempted to use Obtain Queue and Obtain Notifier with a name and assume that since the queue is named each Obtain function returns the same refnum. That is however not true. Each Obtain returns a unique refnum that references a memory structure of a few 10s of bytes that references the actual Queue or Notifier. So the underlaying Queue or Notifier is indeed only existing once per name, BUT each refnum still consumes some memory. And to make matters more tricky, there is only a limited amount of refnum IDs of any sort that can be created. This number lies somewhere between 2^20 and 2^24. Basically for EVERY Obtain you also have to call a Release. Otherwise you leak memory and unique refnum IDs.

Drat, and now my typos and errors are put in stone for eternity (well at least until LavaG is eventually shutdown when the last person on earth turns off the light) 😁

@Rolf Kalbermatter the admins removed that setting for you as everything you say should be written down and never deleted 🙂

yeah that is the payload 😉

In addition to the LV native method, there are options with .NET and command prompt: Get Recently Modified Files.

I'm prone to use JKI state machines for this sort of simple test sequencing. It is easy to learn, and surprisingly powerful once you become proficient with it. You can also use JKI State Machine Objects (traditional JKI SM wrapped in a class) which makes it simple to support multiple parallel state machines, and which also supports using events. Regards, Rick

I can create it without problems in LabVIEW 2018 and 2020! So it is either that Scripting is not enabled in that LabVIEW installation or a bug in backsaving some of the scripting nodes to earlier LabVIEW versions. And I'm pretty sure that the Diagram property (called Block Diagram in the menu) is available since at least 2009 or thereabout. I can check this evening. My computer at work only has LabVIEW versions back to 2018 installed.

Since you asked, here are my findings: LV23 - can create the attached snippet (don't know if it works), and save it for LV14 (also attached). All the pulldown menues show relevant properties LV21 and LV 19 - open the saved for LV14, show a correct image, but the first property node lacks the "Block Diagram" entry in the pulldown; further properties have no menu ETA - and show the relevant pulldown menues when "Show VI scripting" is checked. LV14 - the first property node menu *has* a "Block Diagram" entry, but the further properties don't match LV23 W14.vi W23.vi

I actually had a similar experience when first moving everything to the new OpenG structure. It broke heaps of stuff (even inside its own OpenG stuff), so I rolled back the change. Some time later I tried again, and think I did have to deal with a bit of pain initially with relinking or maybe some missing stuff, but since then things have been stable.

@Natiq this (non-functional example) should be enough to get you started. The weird arrow thing on the boundaries of the while loop is a shift register. The event structure can also be configured to have a timeout case where you can then perform other stuff, like reading your image and writing it to the reference on the the shift register. There is heaps of information out there (YouTube for example), a bit of searching will lead to some more details.

Makes sense. It just goes to show how ingrained workflows are and little things can trip you up. I was right-clicking over the N, over the I. Right clicking 2 pixels down/up from the edge. Top edge, bottom edge, left right.

Probably not the feedback you are expecting but we really should do something about the nasty root loop API calls in the input API. I have somewhat progressed with this over the years and have the windows stuff all working for mouse and keyboard (and a little of the Linux) but I don't have a Mac so can't do anything on that. If there is some interest then let me know and I will see if I can allocate time to getting an API together.

To analyze large time series remotely I have a client application that splits the data transfer using two methods; It will break down the periods into subperiods that is then assembled into the full period by the receiver *and* if the subperiods are too large as well they are retrieved gradually (interlaced) by transferring decimated sets with a decimation offset. So, as a result of this I need to merge multiple overlapping fragments of time series (X and Y array sets). My base solution for this just concatinates two sets, sorts the result based on the time (X values) and finally removes duplicate samples (XY pairs) from it. This is simple to do with OpenG array VIs (sort 1D and remove duplicates VIs) or the improved VIM-versions from @hooovahh, but this is not optimal. My first optimized version runs through the two XY sets in a for-loop instead, a for loop that picks consecutive unique values from either of the two sets until there are no such entries left. This solution is typically 12-15 times faster than the base case (<10 ms to merge two sets into one set with 250 000 samples on my computer e.g.). Has anyone else made or seen a solution for this before? It is not as generic as the array operations covered by the OpenG array library e.g., but it still seems like something many people might need to do here and there...(I had VIs in my collection to stitch consecutive time series together with some overlap, but not any that handles interlacing as well). It would be interesting to see how optimized and/or generalized it could be solved. I have attached the two mentioned examples here , they are not thorougly tested yet, but just as a reference (VIMs included just in case...). Below is a picture of the front panel showing an example of the result they produce with two given XY sets (in this case overlapping samples do not share the same value, but this is done just to illustrate what Y value it has picked when boths sets have entries for the same X (time) value): Merging XY series LV2022.zip

This is by no means a full EtherCAT tutorial but, rather, introductory notes. Please, feel free to add to this post, expend and/or correct any mistakes and information.

I can confirm that LabVIEW 2018 SP1 f4 (32-bit) automatically selects LabVIEW Runtime 2018 SP1 f5 when "automatically select recommended installers" is checked and LabVIEW Runtime 2018 SP1 f5 is installed. Though, it does not ask for the installer source. There used to be SFX installers that were extracted to "C:\National Instruments Downloads". When such an installer was used, the destination folder must not be deleted as it is used as a source location when creating installers in LabVIEW. Perhaps you installed the runtime engine through an old SFX installer and deleted those files at some point?

MAT files are now just H5 files(HDF). Look at the library https://h5labview.sourceforge.io/ and find the example for writing a MAT file. You just need to add a special header in the beginning. I assume the dlls needed will work on Windows server, but am not sure.

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.

Maybe you'll get Xmas before you know it... I found a way to retrieve all tags from a VI. I basically scan the VI file and get an index to the position of tags in the file. I then extract the tag names. Since I don't know to which objects it is related, I have to scan all objects on FP and BD to associate them properly. Once done, you get a list of refnums and variants for the Object's references and a list of tags to which it is associated. I also included an example of code to write a tag to the Block Diagram. Use the same template to write to FP or any objects. Open the project and launch "Get All Tags from VI". Browse the path to the example file "Tagged Test VI" and that's it. Saved in 8.6 but will work in 9.0 (2009) as well. Note that the versioning is important as tags are seen only through scripting and NI can change the way it is saved from one version to the other. Retrieve Tags 8.6.zip