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"

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

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

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

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

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

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

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

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

I 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.

My part of the world! Unfortunately, I don't have any connections to the realm you are talking about. But I would look at Northern Kentucky University (just across the Ohio river) as they have a good CS program (or at least used to). There is also Miami University (not to be confused with the one in Florida), Wright State University (where I got my MSE), and University of Dayton about an hour north of here in the Dayton area. University of Kentucky is about 2 hours south (Lexington, Kentucky), which is about the same distance from Ohio University (Athens) or THE Ohio State University (Columbus).

I tried hard to ignore your poisonous whisperings but eventually succumbed to it. 🤫

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.

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

There is an example shipped with LabVIEW called "Image Compression with DCT". If one added the colour-space conversion, quantization and changed the order of encoding (entropy encoding) and Huffman RLE you'd have a JPG [En/De]coder. That'd work on all platforms Not volunteering; just saying

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

This toolkit offer you an efficient, stable, and reliable front panel control value refresh function. User can design their UI dashboard without any code development. 1. Powerful parallel execution capability, Support clone reentrant execution running mode, you can create multi dashboard UIs at the same time and controls can synchronous refresh across different UI. 2. High-speed data refresh capability, even with thousands of controls on a single UI, can easily maintain a refresh rate of 50ms while consuming very little CPU resources. 3. Support all control data types that "Tag Engine" support, this mean the only thing you need to do is to change the control "Label" with "Tag name", then the control will refresh automatically. 4. Support "muParser Expression", you can type the control "Label" with "Expression" that muParser Expression support, For example "a + b" "a > 1 & b >= 2".

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

QUIC

Sir, TestStand is developed with C#, and my Sequence Toolkit was developed via LabVIEW from zero, and I posted it on this forum for the purpose of learning and communication. As a LabVIEW enthusiast who had ever worked at NI for several years, I don't understand why you said that.

This topic is repetitive. Please go here “Sequence Toolkit“ ”

When you send the message you encapsulate the message as a cluster of string and variant. You don't seem to unwrap the variant from the name/variant cluster in the receiver. What I expect to see is something like this in the receiver:

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

Yup. There is: MMAP (1.0.1).

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.

Discussion forums like LAVA and ni.com are challenged these days by LLMs that can answer in a well structured manner very quickly and handle follow-up questions on the spot. Forums have their stenghts, but when it comes to basic questions that LLMs can find a lot about, spread across multiple forums, the LLMs win. It is a bit of a catch 22 though, as the LLMs need the forums alive to stay up to date 😮 ------------------------------ Here is Grok answering you question of what a DVR is: DVRs as References: In LabVIEW, DVRs (Data Value References) are a mechanism to access data by reference rather than by value. This means that instead of creating copies of the data (as is typical in LabVIEW's dataflow paradigm), a DVR provides a pointer-like reference to a single memory location where the data resides. This avoids unnecessary data duplication, which can be critical for large datasets or performance-sensitive applications. Avoiding Copies: By using DVRs, you can manipulate the same data in memory without creating copies, which is especially useful for large arrays, clusters, or other complex data structures. This reduces memory usage and improves performance. Parallel Operations and Race Conditions: When multiple parallel operations (e.g., parallel loops or VIs) access the same DVR, there is a potential for race conditions if the access is not properly synchronized. LabVIEW provides the In-Place Element Structure to safely access and modify DVR data. This structure ensures that only one operation can read or write to the DVR at a time, preventing race conditions. Without this, simultaneous read/write operations could lead to unpredictable results or data corruption. Key Points to Add: Thread Safety: DVRs are not inherently thread-safe. You must use the In-Place Element Structure (or other synchronization mechanisms like semaphores) to avoid race conditions when multiple parallel tasks access the same DVR. Use Cases: DVRs are commonly used in scenarios where you need to share data between parallel loops, modules, or processes without copying, such as in real-time systems or when managing shared resources. Limitations: DVRs are only valid within the application instance where they are created, and the data they reference is freed when the reference is deleted or the application stops. --------------------- Before DVRs we typically had to resort to cloning of functional globals (VIs), but DVRs make this a little more dynamic and slick. You can have a single malleable VI operate on multiple types of DVRs too e.g., that opens up a lot of nice reuse. If you have an object that requires multiple circular buffers e.g. you can include circular buffer objects in the private data of that object, with the circular buffer objects containing a DVR to an array acting as that buffer... -------------------- Here is ChatGPT comparing functional globals with DVRs: Functional Globals (FGs) and Data Value References (DVRs) are both techniques used in programming (particularly in LabVIEW) to manage shared data, but they offer different approaches and have different strengths and weaknesses. FGs encapsulate data within a VI that provides access methods, while DVRs provide a reference to a shared memory location. Functional Globals (FGs): Encapsulation: FGs encapsulate data within a VI, often a subVI, that acts as an interface for accessing and modifying the data. This encapsulation can help prevent unintended modifications and promote better code organization. Control over Access: The FG's VI provides explicit methods (e.g., "Get" and "Set" operations) for interacting with the data, allowing for controlled access and potential validation or error handling. Potential for Race Conditions: While FGs can help avoid some race conditions associated with traditional global variables, they can still be susceptible if not implemented carefully, particularly if the access methods themselves are not synchronized. Performance: FGs can introduce some overhead due to the VI calls, but this can be mitigated by using techniques like inlining and careful design. Example: An FG could be used to manage a configuration setting, with a "Get Configuration" and "Set Configuration" VI providing access to the settings. Data Value References (DVRs): Shared Memory Reference: DVRs are references to a memory location, allowing multiple VIs to access and modify the same data. This is a more direct way of sharing data than FGs. Flexibility: DVRs can be used with various data types, including complex data structures, and can be passed as parameters to subVIs. Potential for Race Conditions: DVRs, like traditional globals, can be prone to race conditions if not handled carefully. Proper synchronization mechanisms (e.g., queues, semaphores, or action engines) are often needed to prevent data corruption. Performance: DVRs can be very efficient, especially when used with optimized data access patterns. Example: A DVR could be used to share a large array between different parts of an application, with one VI writing to the array and another reading from it. Key Differences and Considerations: Control vs. Flexibility: FGs offer more control over data access through their defined interface, while DVRs offer more flexibility in terms of the data types and structures that can be shared. Race Condition Mitigation: While both can be susceptible, FGs can be designed with built-in synchronization mechanisms (like action engines), while DVRs require explicit synchronization mechanisms to prevent race conditions. Performance Trade-offs: DVRs can offer better performance in many cases, especially when dealing with large data sets, but this can be offset by the complexity of managing synchronization. Code Readability and Maintainability: FGs can make code more readable and maintainable by encapsulating data access logic, but poorly designed FGs can also lead to confusion. In summary: Use Functional Globals when: You need controlled access to data, want to encapsulate data management logic, or need to ensure some level of synchronization. Use Data Value References when: You need to share data efficiently between multiple parts of your application, need flexibility in the data types you are sharing, or when performance is critical and synchronization can be handled externally. It's worth noting that in many cases, a combination of both techniques might be used to leverage the strengths of each approach. For example, a DVR might be used to share data, while a functional global (or an action engine) is used to manage access to that data in a controlled and synchronized manner.

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

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

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

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.

yeah that is the payload 😉

I kind of liked this idea and wished VIM's could allow for such a backpropagation. Even had a thought of making an idea on the dark forums. But then I played a while with the Variant To Data node. It doesn't play well. It can't determine a sink, if a polymorphic VI is connected or even when a LV native (yellow) node is connected. Borders of structures are another issue, obviously. So, it'd require making two ideas at least: to implement VIM backpropagation and to enhance the Variant To Data node. (As a hack one could eliminate the Variant to Data in their code with coerceFromVariant=TRUE token, but then the diagram starts to look odd and no error handling is performed). If someone still wants the code, shown in the very first post, it's here: https://code.google.com/archive/p/party-licht-steuerung/source/default/source?page=3 (\trunk\PLS-Code\PLS Main.vi). And these are the papers to progress through the lessons: LabVIEW Intermediate I Successful Development Practices Course Manual. Nothing interesting there for an experienced LV'er though. XNodes demonstrated here work a way better, and could be a good alternative (if you're OK with unsupported features, of course). As I tried to adapt them for my own purposes, I decided to improve the sink search technique. It surprised me a bit, that there's still no complete code to walk through all the nested structures to determine a source/sink by its wire. Maybe I didn't search well but all I found was this popup plugin: Find Wire Source.llb. It stops on Case structures though. I have reversed its logic to search for a sink instead of a source and tried to apply recursion, when it encounters a Case structure. Well, it's still not ideal, but now it works in most my cases. There are some cases, when it cannot find a sink, e.g. wire branches with void terms: Too many scenarios to process them all. Nevertheless, this little VI might be useful for someone. You may use it as a popup plugin, of course, or may pull out that Execute Find Wire Destination (R).vi and use it in your XNodes. As an example: Find Wire Destination.llb Already tried such nodes in a work project. I must admit that not all the time back-propagation is suitable, so about 50/50. But when it's used, it works.

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 😮

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

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

Here is a VI that gets the title of the window that is active. You could then continually loop until the title you expect is active, then perform operations. https://forums.ni.com/t5/LabVIEW/Get-Current-Active-Window/m-p/3930389#M1116926

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

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

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

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.

I used scripting and low-level VI editing to generate a VI with every single decoration object in LabVIEW, at least those with ID's 0 to -4096. There may be some out of that range (and many in that range don't have a valid image associated with them) but this range contains a lot of them. 0 to -4096.vi

Looks like someone beat me to it! Oh well, I already exported it (also for 2009, incidentally) so I'll post it here in case it'd be more convenient to use a regular VI file. 0 to -4096.vi

I think I have this fixed. Tried a compiled version of the transport library; this worked without issue. I made the timeout changes, which did not seem to have an impact on performance. I then recompiled everything (the server-side code is used in multiple applications on the system); the delay I was seeing with the one message/response went to expected amounts in tests. I've been waiting to test this with the whole system up and going; unfortunately, we've been battling drive issues that are stopping everything else. Can't definitively say it's fixed. Can't point to a smoking gun. I'm appreciating this forum and the people on it right now.

Hi all, sorry i had to do some other work. @ O_o: We already took a look into the UML editor from GOOP: The code is horrible. @drjdpowell: Thank you for your Picture and your inspiration. Up to now we try an other way. We will report if we found a solution. Thanks again Oliver

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

The candles are starting to flicker to life... I read that and immediately wondered why the first case causes a broken run arrow and the second doesn't. (Hey, it was in CAPS... it was easy to skip the preceeding sentences.) Then the word "object" in the PRTC context help hit me over the head. From my end user perspective, previous versions of Labview don't make a distinction between classes and objects. (For example, the To More Specific Class prim has 'Target Class' as an input that in reality accepts an object.) Despite my attempts to differentiate between the two when posting, in my head I often use the terms interchangably. I'll have to work hard to change my way of thinking. I'd give you more kudos if I could...