Leaderboard

I spent a long time online with YouTube support and finally got to the bottom of it. The Channel is back, and all the links work!

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

The examples you provide are invalid JSON, which makes it difficult to understand what you are actually trying to do. In your VI, the input data is a 2D array of string but the JSON output is completely different. Your first step should be to define the types you need to produce the expected JSON output. Afterwards you can map your input data to the output data and simply convert it to JSON. The structure of the inner-most object in your JSON appears to be the following: { "Type":"ABC", "IP":"192.168.0.0", "Port":111, "Still":1, "Register":"Register", "Address":12345, "SizeLength":1, "FET":2, "Size":"big", "Conversion":"small" } In LabVIEW, this can be represented by a cluster: When you convert this cluster to JSON, you'll get the output above. Now, the next level of your structure is a bit strange but can be solved in a similar manner. I assume that "1", "2", and "3" are instances of the object above: { "1": {}, "2": {}, "3": {} } So essentially, this is a cluster containing clusters: The approach for the next level is practically the same: { "TCP": {} } And finally, there can be multiple instances of that, which, again, works the same: { "EQ1": {}, "EQ2": {} } This is the final form as far as I can tell. Now you can use either JSONtext or LabVIEW's built-in Flatten To JSON function to convert it to JSON {"EQ1":{"TCP":{"1":{"Type":"ABC","IP":"192.168.0.0","Port":111,"Still":1,"Register":"Register","Address":12345,"SizeLength":1,"FET":2,"Size":"big","Conversion":"small"},"2":{"Type":"ABC","IP":"192.168.0.0","Port":111,"Still":1,"Register":"Register","Address":12345,"SizeLength":1,"FET":2,"Size":"big","Conversion":"small"},"3":{"Type":"ABC","IP":"192.168.0.0","Port":111,"Still":1,"Register":"Register","Address":12345,"SizeLength":1,"FET":2,"Size":"big","Conversion":"small"}}},"EQ2":{"TCP":{"1":{"Type":"ABC","IP":"192.168.0.0","Port":111,"Still":1,"Register":"Register","Address":12345,"SizeLength":1,"FET":2,"Size":"big","Conversion":"small"},"2":{"Type":"ABC","IP":"192.168.0.0","Port":111,"Still":1,"Register":"Register","Address":12345,"SizeLength":1,"FET":2,"Size":"big","Conversion":"small"},"3":{"Type":"ABC","IP":"192.168.0.0","Port":111,"Still":1,"Register":"Register","Address":12345,"SizeLength":1,"FET":2,"Size":"big","Conversion":"small"}}}} The mapping of your input data should be straight forward.

A customer asked me to create a powerpoint explaining the advantages of LabVIEW. While putting together the practical rationales, just for grins I asked Chatgpt to create a presentation explaining the philosophy of LabVIEW in a Zen sort of way. Here is what it came up with. Zen_of_LabVIEW.pdf

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?

Unfortunately, many of those are bots. I've disable user:pages long time ago, because of the spam. If there's anyone that deserves a lot of credit lately it's @LogMAN. He's doing amazing work cleaning up the pages and adding/editing content. There's a push recently from NI to support the Wiki and promote its use to the broader community and within NI internally as well. So, we should see more traffic and more activity than usual, which is great. This is one of the reasons for the recent stability updates. I encourage everyone here on LAVA to find whatever LabVIEW topic they are passionate about and start adding some pages or even fleshing out some existing content that needs improvement. One way to start would be to find some information that you always wish NI had easily available on their website but could never get easy access to. Then create that on the Wiki.

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

I am also rocking version 4.2.0b1-1 for the same reasons.

QUIC

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.

Aren't DVR's just LabVIEW's take on pointers?

I've just spent an hour arguing with an LLM (Deepcoder). TL;DR A.I. is useless at programming. I had a bug. I'd spent about an hour trying to figure it out and not succeeding but it shouldn't be that hard-I'm just missing something obvious. So. Ideal scenario for a clever AI to show dominance and help out a poor old flesh-bag programmer, right? Just point out the mistake or mistakes and laugh at my stupidity like a real coder. The bug was that the address from recvfrom would be 0.0.0.0 instead of 127.0.0.1. The problem was either bind wasn't binding to a specific address (which it was supposed to) or the address translation was not working quite right. I gave it 3 functions where I thought the bug was and explained that IPv6 seemed to be reporting correctly but IPv4 was in error: one function (Listen) had the bind function one function had IPv6 and IPv4 address translation from a SOCKADDR_STORAGE structure to strings and the other function was the read function with the recvfrom. This is an abbreviation of the conversion: - Round one. The following code has a bug that returns 0.0.0.0 as the IPv4 address from "recvfrom" when it should be returning "127.0.0.1". 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 issue. It told me how to bind to a specific address and how to use the recvfrom function. It then basically wrote the example on the MS page for recvfrom but within the Listen function. - Round 2. I'm not using the "sockaddr_in" structures; I'm using SOCKADDR_STORAGE structures. Please modify your example to use SOCKADDR_STORAGE structures. It apologised made an excuse about misunderstanding and then proceeded to create an example, still using sockaddr_in structures, but this time hardcoding "127.0.0.1" in the bind address. - Round 3. No, no, no. It needs to support user entered IPv6 and IPv4 but there is a bug with the IPv4 address. It also needs to use SOCKADDR_STORAGE as in the code I supplied to you. Reevaluate the code and write a version of the code that fixes the bug. It apologised, said that it understands why it got it wrong, and then proceeded to create an example, still using sockaddr_in structures, but now hardcoding "::1" in the bind address. -Round 4. Look. It needs to support both IPv6 and IPv4 and that's the reason I'm using SOCKADDR_STORAGE. If you don't have enough information then ask for clarification but you have the code that the bug is in so find the damned bug FFS! Another apology, said it can understand my frustration and then proceeded to spit out the example from MS again. This went on for an hour. No code I could actually use in my functions, never pointed out the bug in my code and the prompts just got longer and longer as I tried to head-off it's stupidity. This was one of the functions. 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 bug is in the AF_INET case. inet_ntop(addr.ss_family, (void*)&((sockaddr_in6 *)&addr)->sin6_addr, Address, sizeof(strAddress)); It should not be an IPv6 address conversion, it should be an IPv4 conversion. That code results in a null for the address to inetop which is converted to 0.0.0.0. I found it after a good nights sleep and a fresh start.

Done some simple testing. On a directory containing 838 files it took 60 ms.

It feels strange to me too. As I understand it, the "no merge" clause makes libraries legally unusable by others. A quick search reveals that the "no merge" clause is found in numerous different software licenses: https://www.google.com/search?q="merge+the+Software+into+any+other+software" My best guess is that the clause was originally written for standalone applications (meaning that you're meant to run the software as-is, without copying its source code into your own, or linking your own software to its binaries). However, somewhere along the way the clause got copied directly into a library license, without the involvement of a lawyer who understands software licensing. Perhaps @mabe can clarify? He helped at:

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.

Top Level here almost certainly doesn't mean the diagram of the template VI. Instead LabVIEW distinguishes between a Top Level diagram which is basically the entire diagram window of a VI and sub diagrams such as each individual frame inside a case structure but also the diagram space inside a loop structure for instance. The tricky part may be that the diagram itself may indeed only exist once and remains the same even for clone VIs. The actual relevant part is the data space which is separate for each active clone (when you have shared clones) and unique for each clone (when you have pre-allocated clones).

Started playing with XNodes a bit and noticed the same behaviour as well. Really upsetting. But there is the solution. Just send FailTransaction reply in a Cancel case in the OnDoubleClick ability of your XNode and that 'dirty dot' never appears! That's exactly what the Timed Loop XNode does internally. Looking at this description I get the impression that this reply was invented precisely to overcome that bug (was even given its own CAR #571353). Similar thread for cross-reference: LabVIEW Bug Report: Error Ring Edit + Cancel modifies the owning VI

I don't have anything to contribute to the development here. Only to say that I really like this type of function, and looking at your source it sure looks efficient. Thanks for sharing.

In the LabVIEW community a phrase that has been used to describe undocumented, or incomplete features of LabVIEW has at times been called Rusty Nails. In searching LAVA it appear this is never explained and so this post is intended to give a brief history with as many details as I know having not been active when this all took place. The earliest reference to "Rusty Nails" found online (thanks to AQ) is by Greg McKaskle of NI in 1999. Someone was asking about all the undocumented INI settings that could be found, and how some weren't exposed to the Tools >> Options dialog. Greg's reply was this: Back in the LabVIEW 5.x and 6.x era there was a new emerging technology that was LabVIEW Scripting. NI had created scripting for their own purposes but the community saw it and wanted to be able to automate editing, or creating LabVIEW code. With the help from Jim Kring and others, the basic tools for enabling scripting in LabVIEW were available. The story of how this came about is worth a post of its own, but the summary is that NI shipped a VI that didn't have a password on the block diagram, which allowed for the creation of any object, given an ID. Using a for loop, you could easily create every object in LabVIEW, including objects which facilitate in creating and manipulating code. Discussing scripting often leads into discussing other INI keys which enable private functions like the well known SuperSecretPrivateSpecialStuff. It is possible this is one of the keys Greg was referring to. Other INI keys from 5.x can be found here. After these discoveries the NI forums started getting users asking about scripting, and private functions. Users were looking for help, and documentation but NI wasn't ready for this knowledge to be public and so they started deleting all posts related to private, and scripting functionality. Some of the motivation for the creation of LAVAG came about by a desire to have an independent place to discuss the LabVIEW topics that NI didn't want to have on the public forums, potentially adding to the number of support calls, and confusing new users with advanced topics that were undocumented or incomplete. After LAVA's creation a subforum section was labeled Rusty Nails, and intended to be a place to discuss Scripting, ExternalNodes, XNodes, Private methods, and general LabVIEW hackery. Over the years several private functions have been made public, and scripting has become an official feature shipping with LabVIEW. Because of this the Rusty Nails and XNodes subforums were combined into what is now the VI Scripting section. Even over on the official NI forums, discussions about private functionality and XNodes has been relaxed since those early days. Asking for private methods and getting unofficial help is something users, and sometimes NI employees will participate in, without the heavy censorship seen earlier. And topics of scripting are encouraged now that the feature has been official since LabVIEW 8.6. If you have anything you'd like me to add regarding scripting's history feel free to reply and I can add it. And if I got any of the details wrong let me know. Again I wasn't around when this all took place and I've just tried putting down the details I've heard from other developers.

i can't really answer your question but I suggest you watch this presentation :

I fixed the issue. It was actually kind of funny. So there's a security rule on the server to protect against SQL injection. It found a match with "User_group". I guess it thought someone was trying to get the user data from the database? 😁 I added an exception. All good now.

The idea about NXG in terms of how "bad" the old code base was, always struck me a bit like "throwing out the baby with the bathwater". And while I wasn't involved in any of the user sessions about NXG myself, from the things I heard, I got the impression that they were mainly trying to look for an echo chamber instead of real constructive critique. (Probably one reason I did not get contacted as I never held back about not being a cheerleader). 😁

You are probably getting a permissions error on the Open (windows doesn't ordinarily allow writing "c:") which will yield a null refnum and an err 8 on the open. Your err 5000 becomes a noop as does the write. You're then clearing that error so when you come to close the null refnum it complains it's an invalid parameter - equivalent to the following. Is it expected behaviour? Yes. Should it report a different error code? Maybe.

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?

There are several alternatives for the NI GPU Toolkit that are considerably more up to date and actually still maintained. https://www.ngene.co/gpu-toolkit-for-labview https://www.g2cpu.com/

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

@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

When do we get vector graphics in LV?

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

Here is a quick and dirty edit. It allows for column separators to be moved, but I noticed that on resize it will set the column widths. So this means if you manually move the columns, and then resize the control it may change the columns in an unexpected way. But at that point you can manually move the separators again. I only have 2017 and 2018 so this is for 2017 and newer now. Variant_Probe-2.4.3-0.ogp

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.

Updated VIs to obtain hwnd by FP.NativeWindow as suggested above. Saved in LV 2013 SP1. Only tested with Windows 7 64-bit and LV2013 SP1 32-bit. Set Calling VI Wnd Top & Active.vi Set Calling VI Wnd Topmost & Active.vi Cancel Calling VI Wnd Topmost.vi

I am attaching a simplified example and but I'm going to describe an example of where I'm running into this problem. Lets say I have a class "Dialog" and from that I have a child class "Channel Config Dialog" The Dialog class accepts Dialog Pages and puts them in its private data, and the Channel Config Dialog accepts Channel Config Dialog Pages (a subclass of dialog page), but wants to reuse the fact that its parent already caries around pages. So there is a protected set method defined in the dialog class that allows the Channel Config Dialog to put Channel Config pages into the Parent Dialog Class's private data. So, I do this by having a static method in the child class, call it "set pages," and this method only accepts Channel Config Dialog Pages on its connector pane. This method then calls the protected method of the parent class to set the pages in the parent data. However, now the pages are being carried around on a parent Dialog Pages wire. If I want to call a Channel Config Dialog Pages method I'm out of luck. So, I was using to more specific class, assuming it's fairly safe because I have specified the connector pane on the child class's "Set Pages" method to not accept any Dialog Page type other than the type it expects. What I can't determine is if this is Ok or if it's pointing to a bad design decision and there is a better way. If you are confused hopefully the attached code helps config.zip

I think that's what the function does behind the scene. A rectangle is simply one case of any number of geometries you can make with this function's inputs. NI Vision rotation algorithm is more complete because it will interpolate colours when the rotated pixel positions are not integers, but otherwise it's the same. The rotation matrix in 2D is exactly what you state above. Rotation of points.vi

It adds properties and methods to the LabVIEW VI server hierarchy, mostly application related and presumably project and other such stuff, that NI considers to dangerous, untested, or giving to deep insight into LabVIEW. It is related to scripting but not the same thing. Rolf Kalbermatter

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