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"

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 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.

yes

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

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.

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?

The thing I loved about the original LabVIEW was that it was not namespaced or partitioned. You could run an executable and share variables without having to use things like memory maps. I used to to have a toolbox of executables (DVM, Power Supplies, oscilloscopes, logging etc. ) and each test system was just launching the appropriate executable[s] at the appropriate times. It was like OOP composition for an entire test system but with executable modules. Additionally, crashes were unheard of. In the 1990's I think I had 1 insane object in 18 months and didn't know what a GPF fault was until I started looking at other languages. We could run out of memory if we weren't careful though (remember the Bulldozer?). Progress!

@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

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

I would suggest rabbitmq, i want(ed) to present it at a LabVIEW user group (LUGE) but haven't done it yet. It's very powerful. I use redis and did a quick presentation (in french) at LUGE recently, i haven't used the stream feature though, I only used it as cache.

Redis is certainly high performance and suited to multiple, loose writers, readers and subscribers, with bindings for so many ecosystems. One of its several features, which I haven't perused, are Streams. I'd be curious too to know whether continuous cross-app data streaming could be efficiently implemented using them.

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.

I cannot look at your file, but I suggest save the data to TDMS or any binary format of your choice. Once the file is saved, then you can convert it to text.

There is no typos and errors in your posts. Only pearls of wisdom and oracles of truth that we mortals can't understand yet...

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

If the child classes are statically linked in the code (via class constants, or whatever other mechanism you use), then this approach should always work, because the child classes will always be in memory.

Hello everyone, I developed an Addons-Toolkit of LabVIEW, which achieves most of the OpenCV's APIs. It includes more than 2700 VIs, covering 13/15 modules of OpenCV (except flann and gapi) . You can use it to control cameras, process images, run DNN models and so on. Welcome to my CSDN blog to download and give it a try! (Chargeable, 30 days trial) Requirements: Windows 10 or 11, LabVIEW>=2018, 32 or 64 bits.

yeah that is the payload 😉

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

That's how I'd do it. Then combine that with the Foreign Key Sort from my Array package, putting the Time Stamps into the Keys, then paths into the Arrays, and it will sort the paths from oldest to newest. Reverse the array and index at 0, or use Delete From Array to get the last element, which would be the newest file.

The popular serializer/deserializer problem. The serializer is never really the hard part (it can be laborious if you have to handle many data types but it's doable) but the deserializer gets almost always tricky. Every serious programmer gets into this problem at some point, and many spend countless hours to write the perfect serializer/deserializer library, only to abandon their own creation after a few attempts to shoehorn it into other applications. 🙂

I have experienced the same thing when my VI was the member of a large class. I removed the VI from the class, set the splitter positions, and then added it back to the class. :shrug:

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

Open the search function (Ctrl+F) and browse for the "NaN" constant. A dialog pops up telling you this palette item is not supported by the Find Dialog... You can search for the "NaN" string and it will find all the NaN constants (plus all the occurrences of the "NaN" string). You can search for all other constants (pi, machine epsilon, +/-Inf, etc.), but not for the NaN constant, which is just a numeric constant with NaN typed in it. You can search for ALL numeric constants, but not for a specific one, say "1". Of course, you can search for all "1" strings in your code, and the constant 1 will show up among the search results, but it will be hidden in a long list of irrelevant results. And try to search for a constant with units... You can't. What would be nice is to look for a constant irrespective of its unit, as for instance 60 s = 1 min. Did I encode that time constant as 60 s or 1 min? I need to search for 60 AND 1 to find out.

Example of camera grab using the Pylon .net API. (Credits: GrokAI)

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.

Put the acquire image and save to file in the event structure timeout case, but only write to file conditionally (i.e. if the user has clicked the button)

@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.

What doesn't work with the function: AJ_NETSDK_IPC_PTZControl() on page 21/22? Or are you not using the SDK functions to retrieve the RTSP stream but some other ready made interface for LabVIEW? Meaning you have no idea how to interface to a DLL? A few points to consider: 1) The camera may not like a secondary connection, either through the SDK or through generic TCP/IP while it is busy streaming image data to the VLC or whatever interface. 2) Trying to reverse engineer the TCP/IP binary stream protocol is likely going to be cumbersome and difficult to realize as it is usually proprietary. The SDK interface is simple enough to use, except if you lack any and all understanding about C programming. It's not a CIN node either that you will need to configure but a CLN (Call Library Node). CINs are not only legacy technology but on most modern LabVIEW versions simply not supported anymore. An interesting problem, but none I can help you as I do not have that hardware, and I would expect it to be a bit cumbersome considering above 2 points.

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:

Update To get it to work I had to downgrade to version 6.0.0.25 - OpenG File Library (from 6.0.2.28) 6.0.0.18 - OpenG Array Library (from 6.0.1.20) May be this helps someone else 🤷‍♂️ Thanks

I used LabVIEW to develop a toolkit for ATE software. The toolkit is called "Test bench Framework", which includes a test sequence editor and a test engine.This toolkit features the ability to execute several different sequences in parallel.If you are interested in this kit please contact me, thank you! This toolkit is over 10MB in file size and cannot be published on VIPM, so I uploaded it to Github.Test-Bench-Framework . I used the TestStand icon inside my own sequence editor and wondered if there would be any copyright issues involved.But it's not commercially available yet.

@Ravi Beniwal, I have the same problem, VIPM reports that missing dependency for me too. If it isn't required could it be removed ? If it is required could it be included ? I suspect it is included in version 1.7.028 which does not report the error. I spent(wasted !) time looking for the dependency and downloading it, only to realise it might not be needed as it launches OK from the LV IDE menu Tools\LabVIEW Task Maanger.... Peter

Regarding Levenshtein: Wladimir Levenshtein developed 1995 an algorithm for this. It is called the Levenshtein Distance. Some years ago I developed a VI to calculate the Levenshtein Distance. Here it is (LabVIEW 2016). Can you post your VIs in LV2020 or 2019, please. Levenshtein Distance.vi

Which is funny because when I took them, I thought the CLD was much harder than the CLA.

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.

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