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.

In case anyone else runs into the issue...

Available in the new ECL version 4.6.0

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

@Rolf Kalbermatter my team and I still use in some systems here! In fact this very last week we have needed to add some lua stuff to an old project.

yes

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

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

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

The Weather Station example that ships with LabVIEW shows a bit of this. but the data is not Base64, its just a pure characters,

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

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

You might have more success posting this on the Discord. Most of the conversations happen there these days.

QUIC

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

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.

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

There is an Application property called Display->All Monitors. It will give you the pixel ranges of the monitors in your system. What I've done is to use the calling VI's position to figure out which monitor it was on and then place the new VI window as needed. You could use a win32 dll call to get the mouse position as well if that better meets your requirements.

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

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

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

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

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/

I'm excited to release ViPER ViPER is an Object Oriented design Framework that supports dependency injection and recursive object creation. Systems are assembled at runtime from a collection of pre-built components defined by an Object Definition Document. Please visit the project on GitHub https://github.com/kurtafriday/ViPER I've presented this framework at several GLA Conferences, for an overview and guidance please view. GLA 2021 https://labviewwiki.org/wiki/GLA_Summit_2021/Open_Source_ViPER GLA 2020 https://labviewwiki.org/wiki/GLA_Summit_2020/ViPER_-_A_LabVIEW_Dependency_Injection_Framework This branch of ViPER has been used by us to develop systems in regulated industries for several years, it's solid and reliable, however its windows only. I'm working on ViPER_WinRT which is compatible with Windows and RT and we have already used it for several systems. I'll be releasing ViPER_WinRT in the coming months. I'll work to get ViPER onto the VIPM Tools Network soon. I'm looking forward to the feedback and I hope you enjoy and get value from this framework. Ping me if you have any questions. kurt@medulla.net

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

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

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

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).

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

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

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

Hi All, I'm looking for a good resource that explains LabVIEW's Execution System / Thread Allocation / Thread Priority system. As a background to the reason for my request: I have an application with over 50 parallel loops running at fixed but configurable times. Twenty of these loops are calling a .net Dll and are thus not in a Timed Loop (there is a known issue according to NI support with calling a .net dll in a timed loop where the call time is large ie. upwards of a second). The remaining loops are performing other data acquisition. Each loop is what I call a Task Controller - it looks after a specific piece of hardware, taking requests for data (via queues), performing data acquisition and then pumping the result back to the requester. In order to seperate the timing of the functionality (and allow multiple requesters access to the same data), this process is not sequential but occurs in parallel loops. So there is a lot of parallel activity going on. I notice that as more of these loops fire up, the slower the remaining loops are. The CPU usage tends to stay around 7-8% during this time irrespective of how many loops are executing. Note that the .net dll calls (up to 20) are reasonably slow calls and each could take up to 6 seconds to execute. The .net dll has been written to handle multi-threading. The PC is a hyper-threaded quad core (ie 8 logical cores) @ 3.3GHz. Kinda a meaty machine. I should also mention that the majority of the VIs are re-entrant. The only non-rentrant VIs are some FGVs and a few User Interface VIs that reference the data in these FGVs. And before you ask the FGVs are simply Get/Set for a handful of cluster points. So I figure it's a simple case of thread starvation. Every VI is currently set to the Standard Execution System (via Same as Caller) with Normal Priority. I figure that adjusting these settings on the top level Task Controller vis may assist in spreading the load to the remaining available, but not executing, threads. The SubVIs under each Task Controller will continue to use the Same As Caller setting, allowing me to seperate logically each Task into appropriate Execution Systems. Any thoughts?

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