I'm following the instructions to build a "hello world" extension for Visual Studio as outlined here. I've got the Yeoman generator installed, but it seems buggy. For one thing, unless I immediately select one of the initial options when generating a new extension, I'm unable to select an option. Further, if I do immediately select an option (i.e. before enter stops working), I'm prompted to give a name to the extension. However, no matter how furiously I pound on my keyboard, no characters shows seem to be registered by the generator application.
Has anyone else experienced these issues with the generator? I'd really like to start experimenting with VS Code extensions, but if the generator doesn't work I'm not sure where to start.
This is an issue with yo in node 7.1.0. You have to upgrade or downgrade node.js.
Related
Currently I am trying to use Visual Studio Code with Ionide to build a F# Solution. To describe my problem, i first describe what i have done, and what works.
I created a solution with two Projects. One Project is a Queue that contains a F# library. Another project is Queue.Test that is a console application that uses the Queue library, and should contain the Tests for the Queue library.
I'm using .Net6 and created the solution and Project with the dotnet cli tool.
In general, i can build the project with dotnet and i also can use everything in Visual Studio Code. I load the Folder that contains both projects, and Visual Studio Code loads the library.
I am able to edit the Library and my Console application. In my Console application i also can access the Queue and so on. Autocompletion works, and so on.
But, there is one problem. When i add a new function to my library, let's say Queue.help then in my Console application, i cannot see that function. It doesn't show in autocomplete, and when I write code that uses that function i get a compiler error telling me that function doesn't exists.
I can Build/Rebuild from VS Code or from CLI but the problem goes not away.
The only way Ionide starts to see the new function is by building the library AND restarting VS Code. As long i don't restart, it seems to not update the generated dll (i guess).
This is sure annoying, as i don't want to reload/restart VSCode everytime I add a new function to my library.
So my question: How i can I fix this?
What i want is to be able to change my library, and at the same time write tests in the other project and get full Code autocompletion.
Does somebody else have the same problem, or should I change my workflow?
What can i do, to debug this problem on my own?
Some tips?
This issue is fixed by the recent version of Ionide 5.10.1
This is a long post, sorry.
I have been trying to start a project, using Rust, but ran into a problem: it just does not work correctly on Linux in VSCode/Atom.
Wasted 3 days, searching online, trying different tutorials/videos - nothing worked + most of the material is from 2017. I have tried Matrix chat, but no one knew what to do. Git too has no solution as people keep suggesting very random things, like "change this variable in toml file to something else, and back again"
Git: https://github.com/rust-lang/rls-vscode/issues/513
I installed (and re-installed rust many times in the last 3 days), and it works just fine from the terminal, but not in the Editor.
Two Issues:
Editors don't see any crates, so you can't run your code from the editor.
Autocomplete does not work (only works on std, not on extra crates you add).
What I did (out of many other things):
install Rust (on Manjaro and Debian computers): curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
Tried stable, beta, nightly (for racer)
Just did a clean install again:
stable installed - rustc 1.40.0 (73528e339 2019-12-16)
Rust is installed now. Great!
Installed Rust (rls) rust-lang.rust extension in VSCode (and rust in Atom)
Created a new project: cargo new test_proj and added new rand = "0.6" to [dependencies] and used cargo build. It did build rand
Added "rust-client.enableMultiProjectSetup": true to the settings file to avoid a warning: A Cargo.toml file must be at the root of the workspace in order to support all features. Alternatively set rust-client.enableMultiProjectSetup=true in settings. by Rust (rls)
I also install 'code runner' extension that I use with Python, C++, and Java, to run the code from within the editor.
So now I have just the main func and it runs just fine from the editor:
Now I add rand and it seems to work, and does SOME auto-completion...
But now it stops working:
OK, I will finish the code and try running it, And now we can't run it anymore as the crate is missing:
OK, let's try Ctrl + Shift + B and try cargo build:
For some odd reason, it is looking in /media/Work/Work/rust_code and not in /media/Work/Work/rust_code/test_proj/
One last thing: let's try running in the terminal:
So it does work just fine.
Sorry for the long post, but I have wasted 3 days now and it still can't get it up and running. Did anyone manage to set this up at all?
It has to be Atom or VSCode as I have all of the other languages/projects setup there + VSCode is listed on the official Rust website, so I presume it should work.
Basically, out of two editors (VSCode and Atom), that have Debugging capabilities, unlike Intellij Rust, both don't work for me and I just can't code in Rust as tools are literally broken/not mature enough for productive work. Please let me know if I am wrong and it is just a case of one little flag, that everyone forgets to mention, is missing in some config.
Short Version
Assuming I understand the issue correctly. Then the various build issues boil down to different ways you're trying to build the project, and attempting to do so in different directories.
TL;DR: The directory you have open in VSCode is the rust_code directory. Close it and instead open rust_code/test_proj. Now the Rust: cargo build (or Rust: cargo run) should work.
Long Version
Editors don't see any crates, so you can't run your code from the editor.
The Rust: cargo build task isn't working, because the directory you have open isn't a "Rust project" (Cargo package), it's a directory containing another directory, which is a Rust project.
Looking at your screenshot shows this, look at how the top line says rust_code/test_proj:
When you execute the task, Cargo is complaining that rust_code/Cargo.toml doesn't exist, which is true since it's located in rust_code/test_proj/Cargo.toml
If you look at the output of this screenshot, you can see that is the case:
Here you're executing cargo run manually. But the important difference is that you're inside the rust_code/test_proj directory.
Lastly simply executing rustc main.rs is failing since you aren't passing the arguments needed. So rustc doesn't know anything about your dependencies.
Try executing cargo build -v then you can see all the arguments that Cargo is passing to rustc.
Autocomplete does not work (only works on std, not on extra crates you add).
Try and open a directory that contains a Cargo.toml, then code completion should work for dependencies. If I don't, then I get the following notification, and code completion only works for the standard library as you said. That being said, RLS is weird sometimes.
If I had to guess, then I think RLS compiles the code, and at some stage extracts the needed information. Thus if the code doesn't compile, then code completion could be affected. But this is 100% an educated guess.
Alternatively, I have heard praise about using IntelliJ + the Rust plugin, but I haven't used it myself yet.
I have figured out one part: problems with running your code from within the VSCode. I had to modify default code-runner command for rust:
Original command:
"rust": "cd $dir && rustc $fileName && $dir$fileNameWithoutExt",
Changed to:
"rust": "if [ $(basename $dir) = 'examples' ]; then cargo run --example $fileNameWithoutExt; else cargo run; fi",
And now it works, and I can run my code quickly.
Part 2: Autocomplete still is very very bad, unfortunately. I am using RLS. there is this thing racer. Is it a better choice?
Alternatively, I have heard praise about using IntelliJ + the Rust
plugin, but I haven't used it myself yet.
As I mentioned in my previous post, IntelliJ, free edition does not have a debugger from what I can see. I need it.
I am wondering how people get a good autocomplete from Rust?
Why do I have the same suggestions while typing expression?
Example:
I had exactly the same problem. After a week or so, it get really annoying.
basically, as the comments hint to, there are probably multiple linting or intelisense tools. In my case (for python) i had the pylance extension added.
When i disabled this, the problem went away, but features were missing. So i added it back...
For some reason (i dont know why), this fixed the problem !!!
I can only hypothesise that in some way the extension was corrupted. Nevertheless, it worked.
EDIT:
I can also confirm that unchecking this setting appears to work:
Jupyter: Pylance Handles Notebooks
My current system is Windows 11, with python 3.10.
Final edit (8 Dec 2022):
This is resolved here:
Please could you install VS Code 1.74 and the latest Jupyter, PyLance and Python extension and confirm this still exists.
Visual Studio Code provides an API so third-party extensions and built-in modules can contribute suggestions for auto-completion pop-ups. The system is currently designed so suggestions are merely appended—there's no duplicate detection or removal (perhaps because extensions can also take care of sorting suggestions and such algorithm would get on the way). That means that if you have more than one extension or module for a given language you can easily get duplicate entries.
Having several extensions for PHP is not necessarily a bad idea since they can address different needs (for instance, PHP DocBlocker just creates annotations, it doesn't provide auto-completion suggestions) but you have at least two extensions (PHP Intelephense and PHP Intellisense) that do exactly the same things. That's likely to hurt performance (all your workspace files will be scanned several times) and just adds noise.
I suggest you read the extension descriptions carefully to learn what they do exactly and then figure out which ones you need. Remember that extensions can be enabled/disabled in a per-workspace basis.
The following is just my own totally subjective opinion. Among the PHP extensions that provide code intelligence only two of them seem mature enough:
PHP Intelephense
PHP Intellisense
I've tried both. PHP Intelephense works best for me than PHP Intellisense so that's the one I've kept. I've also disabled php.suggest.basic following the installation instructions because basic suggestions didn't add any value to me (they were blind string matching):
Turn off the php.suggest.basic setting for best results.
... as well as taming builtin Emmet support, which was providing really dumb suggestions:
"emmet.showExpandedAbbreviation": "inMarkupAndStylesheetFilesOnly"
YMMV.
TLDR; Installing pre-release version of Jupyter solves (v2022.11...)
Ok, so after some more extensive experimentation I think I found what's causing this in my case. After looking at the processes I noticed that there were two Pylance processes running, and consistently this would only be a problem if I was working in a session with a jupyter notebook open or one that had been opened.
saun89 17740 37.3 0.3 1008004 199492 ? Sl 20:58 0:22 /home/saun89/.vscode-server-insiders/bin/fef85ea792f6627c83024d1df726ca729d8c9cb3/node /home/saun89/.vscode-server-insiders/extensions/ms-python.vscode-pylance-2022.11.32/dist/server.bundle.js --cancellationReceive=file:9178e897a2b78b36bfd167f79b36c3bdad2931d71b --node-ipc --clientProcessId=17651
saun89 18743 257 0.7 1304584 382288 ? Sl 20:59 0:20 /home/saun89/.vscode-server-insiders/bin/fef85ea792f6627c83024d1df726ca729d8c9cb3/node /home/saun89/.vscode-server-insiders/extensions/ms-python.vscode-pylance-2022.11.32/dist/server.bundle.js --cancellationReceive=file:8744a321767eed92821fd737be4dc7dcfb728284e5 --node-ipc --clientProcessId=17651
Pylance basically spins up a service for the workspace, and then spins up a separate service for the notebook.
Output from "Python Language Server" logs:
Disabling Jupyter removes the duplication, and after installing an earlier version of the extension (v2022.4) this appears to have fully resolved the issue. I'm going to go ahead and log the extension bug once I have something reproducible.
As of 11/30/22, Jupyter Extension Pre-Release version v2022.11.1003281132 is the latest version fixes this issue. Click the gear icon next to the extension and you should see "install another version..." Then you can select version v2022.11.1003281132.
So, I've been using Sublime for a while as a simple text editor, but I'm venturing into the land of plugins for work and I've run into an issue getting pylint to work. Specifically I have it installed and have the Sublime package manager working, but I'm not sure how to include paths in my sublime settings.
I haven't found very useful documentation on this point, but if you are willing to point me towards it that would be a perfectly acceptable answer. My basic issue is that currently every time I save a file, the following error message shows up:
"Please define the full path to 'lint.py' in the settings"
I understand this error message which is great, I just have no idea where the sublime settings are or what the standard format for defining a path is. Any help would be appreciated.
There are quite complete directions at the SublimeLinter GitHub page that should describe how to set everything up. Briefly, go to Preferences->Package Settings->SublimeLinter->Settings - Default to see where the different settings are defined. Then, open Preferences->Package Settings->SublimeLinter->Settings - User to change anything, as the main settings will be overwritten when the package is updated. Remember that settings files are in JSON format, so you'll need opening and closing curly brackets to enclose settings, and a comma between them:
{
"sublimelinter_delay": 30,
"sublimelinter_mark_style": "none"
}
I haven't gotten the error you have, are you sure you're using the regular SublimeLinter and not the new beta version? I just installed it fresh on my work machine (I've been using it for a while at home) and after restarting ST2 it's working like a charm with Python.
I had the same problem. I found it to be coming from the package "Pylinter". I removed Pylinter and added SublimeLinter, it covers more than python and is well used. I'm enjoying it quite a bit.
From your command line just run:
sudo easy_install pylint
sudo easy_install pep8
After that restart your sublime.
I encounter the same situation today. In my case, that is because I have not installed the 'pylint' in my system yet. It works fine after I installed the 'pylint' through pip.
Just for other people reference.
I'm using Vim on a Mac for front-end development and was recently hired at the company that uses Team Foundation Server as their version control system.
I would hate to have to switch to using Visual Studio on Windows because I'm so used to Vim and the Mac.
I found this and was hoping that would be a possible solution. I would still like to avoid editing code in Eclipse. However I wouldn't mind opening Eclipse to do version control stuff.
I'm very unfamiliar with Eclipse and Team Foundation Server (not VCS in general) and I need some advice on how to actually use it.
I'm able to connect to the server and find the project I have to work on, but from here I'm lost. This is the window I'm stuck at.
Anyone who are in a similar situation and could offer some help?
You've done the hard bit I think, firstly you should be able to safely ignore the Work Item and Build "folders" unless someone explicity tells you to use work items, at which point they can show you what you need to know as it works exactly the same as in Visual Studio.
If you double click on the Source Control folder it will open a new window which will show you the source "tree". To be able to Get, Checkout and add source files to the tree you'll need to set up a workspace. Once you've done this then you can get the code and check out.
With Team Explorer Everywhere You also have the option of using the tf command line in the Mac terminal. This would eliminate the need for eclipse. (I'm assuming that as a Vim user you're not afraid to use the terminal)
Another option might be svnBridge however I think you need the server version if you're using a Mac, and this requires a site to be installed in the TFS application server which might not be an option.
Finally TFS now offers support for integration with GIT.