develop and debug multiple VSCode extensions at once - visual-studio-code

I am currently developing some custom VSCode extensions and would like to have separate optional extensions that build on a core extension. Currently it is a bit of a hassle to develop these congruently and I am currently aware of the following options:
1) Develop the extensions separately with separate debug instances
The downside here is that until the extensions is published or moved to your ~/.vscode/extensions folder the two extensions have no knowledge of the development versions of each other, making the debugging and rapid additions quite difficult.
2) Move extensions into ~/.vscode/extensions folder
The downside with this is that there is constant window reloading, sometimes it can be tricky to know when the main process has fully loaded the updated version and it has definitely been less convenient than the experience when developing one extension
3) Merge the two extensions into one extension
This makes debugging and rapid feature builds easier, but goes against some of the original modularization i was hoping for, so i haven't switch to this as of yet.
My question is, is there a better way people have found to accomplish this apart from the above 3 options i'm aware of? I've combed quite a bit through google, forums, and the vscode docs looking for options or other people hitting the same situation but haven't found anything as of yet.
From the VSCode docs, it appears that --extensionDevelopmentPath "might" support multiple paths somehow, but i have yet to find anything conclusive or with examples of that to get it to work.

One method that I have used is to pull in the 'core' extension in as a submodule into a subdirectory, for example, .dependencies. Remember to npm install the 'core' extension from within its directory.
Then I would adjust your package.json on the working extension to use the following scripts:
"scripts": {
...truncated for brevity...
"compile:core": "tsc -p .dependencies/{dep-folder}"
"compile:me": "tsc -p ./"
"compile": "npm run compile:core && npm run compile:me"
...truncated for brevity...
}
Finally, add the following to your launch.json which will override VSCode's default extension folder to your .dependencies folder.
"args": [
"--extensions-dir=${workspaceFolder}/.dependencies"
"--extensionDevelopmentPath=${workspaceFolder}"
]

Related

Is there a VSCode configuration variable for the bundled extensions folder?

I'm authoring an extension and running it in the debugger, which is mostly working smoothly.
But I'd like to disable debugging other extensions while I'm debugging mine.
I've been able to disable debugging for installed extensions using this, in my launch.json:
skipFiles: [
"${env:HOME}/.vscode/extensions/**"
]
(Incidentally, I don't know whether that's the right location on Windows -- it might be -- but I'm on macOS. It's probably correct for Linux also.)
But I can't seem to disable it for bundled extensions without hard-coding my VSCode installation location:
skipFiles: [
// Below does not work for some reason
"${execPath}/../../Resources/app/extensions/**",
// Below works if we have correctly guessed the install location
"${env:HOME}/Applications/Visual Studio Code.app/Contents/Resources/app/extensions/**"
]
I dumped the VSCode environment and I have a bunch of variables that look fairly unreliable, like VSCODE_GIT_ASKPASS_MAIN, that basically lead me to the same problem. I'm not sure why the execPath variable above doesn't work, but even if it did, it'd be macOS-specific. My other solution requires me to guess the install location (which I guess I could try to do with versions for Windows / macOS / Linux and dealing with common installation locations for those, but even this would not be foolproof).
Is there another, more directly applicable configuration variable I could use for this purpose? My question is similar to this one, but in that one the need was to access an extension's own path from its implementation; mine is from the launch.json configuration file (and I want the path for all extensions, not my extension).

Full Rust setup in VSCode/Atom Issue

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?

How can you launch VSCode with multiple extensionDevelopmentPath sources?

I'm trying to test local changes of omnisharp-vscode in conjunction with my own local extension. I can't for the life of me figure out how to boot the VSCode experimental instance with more than 1 extension.
I've tried:
Providing multiple extensionDevelopmentPath arguments when booting
vscode
Running omnisharp-vscode and then opening and running my other extension in the experimental instance.
None of the above have worked for me.
The easiest solution would probably be to simply move one (or both) extensions into your .vscode/extensions directory. This might require you to remove the marketplace installs of those extensions if present. Even though "development installations" of extensions like this are not officially supported yet, they work just fine regardless.

Start a MAMP server with Grunt.js

I want to set my Grunt.js file to launch my MAMP server on grunt serve.
I have been trying to use this tutorial here to do this:
https://coderwall.com/p/kwne-g
I was then planning to use this tutorial to set up grunt watch:
http://darrenhall.info/development/yeoman-and-mamp
Now I am having trouble with step one. I have successfully installed grunt exec. However, grunt claims not to be able to find the task 'serverup'.
Here is my code:
grunt.task.run([
'clean:server',
'concurrent:server',
'autoprefixer',
'connect:livereload',
'serverup',
'watch',
'serverdown'
]);
If you followed the examples at the link, it looks like your targets should be exec:serverup and exec:serverdown for the tasks to work.
The problem here and with many other Grunt related questions is that without the full Gruntfile, "answers" are largely guesses. Configuration, task loading, and task registration are all related and without seeing all three, it is difficult to say "this is the answer".
Given that, here's a checklist I use for problems like this when using Grunt and packages from NPM:
Is the code that supports the task installed? Did I forget npm install? Did I miss
errors on install (check npm-debug.log if it exists)?
Have I correctly used grunt.loadNpmTasks for the plugin? Is the line in my Gruntfile and
did I get the plugin name spelled correctly? Did I or my IDE accidentally use to
grunt.loadTasks when I need loadNpmTasks?
Have I correctly named/used grunt.registerTask for the task? If I need to call a
specific target for a task, do I have the the name correctly specified?
If there are paths involved and things are broken, do I have my globbing patterns correctly specified? If a cwd
is involved, do I have the other paths or files correctly specified?
Did I get the configuration right? (This is where things get too plugin-specific for a
checklist.)

A good development environment setup for Web2Py

Have been trying out Web2Py for a couple of days now and I decided it to be a keeper. But there is one thing that concerns me a lot and that might be a showstopper in the end. I need a nice development environment & setup I can trust and be productive with. Coming from the MS Visual Studio world I'm looking for something with good autocomplete / intellisense + functions for versioning and deployment.
I did some attempts to edit my code in Eclipse but it needs additional setup to run with autocomplete, and for debugging I dont know if it's possible. (Noticed there was a Django project template in Eclipse which is a bit tempting I must say.)
Wing Ide has a instruction on how to get web2py up and running and I am up to testing that one. Not free, but very cheap compared to much in the Windows world.
I also want a good versioning (hg) setup, and preferably a semi-automatic FTP-deployment-method.
What IDE do Web2Py developers use, and how do your setup look like?
A complete setup script for a project in a good IDE would be awesome! (Just like the installation is, one click to get it running 100%).
Pycharm looks good, perhaps that one can add web2py support http://youtrack.jetbrains.net/issue/PY-1648
Thanks a lot!
OS: Windows 7/Windows XP
IDE: NetBeans
Version control: TortoiseHg/NetBeans
Debugger: winpdb
Shell: IPython
Publish: WinSCP/PuTTY/TortoiseHg
Scripts
Once I create a new project in web2py I add a few scripts to my main app folder:
web2py\applications\myapp\DebugWinpdb.bat:
C:\Python25\Scripts\winpdb.bat ..\..\web2py.py -i 127.0.0.1 -p8000 -mypassword
web2py\applications\myapp\DebugShell.bat:
C:\Python25\Scripts\winpdb.bat ..\..\web2py.py -S myapp -M
web2py\applications\myapp\Shell.bat:
python ..\..\web2py.py -S myapp -M
IDE
As others have stated you need to do some extra stuff to get autocomplete/intellisense for web2py no matter what IDE you use.
For me NetBeans was a good compromise between does-everything-if-only-you-can-figure-out-how (Eclipse/PyDev) and does-the-basics-but-few-extras (PyScripter).
NetBeans Setup (Project Properties):
Python Category
Python Platform: Python 2.x (default is Jython)
Run Category
Main Module: web2py.py
Application Arguments: -i 127.0.0.1 -p 8000 -a mypassword
NetBeans Pros:
Tight Mercurial integration
Highlights which lines have been added, changed, or deleted in your source file as you edit it
Selective rollback of individual changes you've made since your last commit
One of the nicest visual diff viewers I have used
Python PEP8 style hints (fully customizable)
Name "foo" is not a valid class name according to your code style (CapitalizedWords)
Name "Bar" is not a valid function name according to your code style (lowercase_with_underscores)
Auto-format hotkey (corrects spacing around operators, etc)
Navigation within source file
semantically indexes current source file
organizes alphabetically by type (Class, method, attribute, etc)
makes even enormous style sheets manageable
NetBeans Cons:
Integrated Debugger doesn't work with web2py (that one really hurts)
Long startup time (but acceptably snappy for me once up and running)
Version Control
I use and highly recommend Mercurial for source control. As mentioned earlier, NetBeans has great support for Mercurial but there are some things I'd just rather do in TortoiseHg.
TortoiseHg Pros:
Shell overlay icons
Repository Explorer
view repos history with graphical display of branching/merging
one stop shop for Incoming, Outgoing, Push, Pull, Update, etc with button for Commit tool
Commit tool
Hunk Selection: cherry pick changes from within a file for more focused Commits
Add, Remove, Diff, Revert, Move, Remove, Forget
TortoiseHg Cons:
No easy way to drop directly into a command line
Bug that regularly prevents files from being removed during commit (waits indef for a lock to be released; running hg addremove from command line is a reliable workaround)
Publishing
I use a combination of WinSCP (for browsing), PuTTY (for terminal commands), and TortoiseHg (for push/pull of my repos) to work with my shared hosting account on Webfaction.
The first thing I do is set up public/private key encryption. If you are having trouble getting this set up between Windows and Linux, try these instructions from Andre Molnar. Short story is you need to generate your private key using ssh-keygen on Linux, copy it down to your Windows machine using WinSCP, then convert it for use with WinSCP and PuTTY.
Then add the following lines to your global mercurial.ini file:
[ui]
ssh = "C:\Program Files\TortoiseHg\TortoisePlink.exe" -ssh -2 -i "c:\path\to\your\privatekey.ppk"
Even if you have to connect to multiple servers, you need only copy your public key to each of the different servers. You'll also want to let WinSCP and PuTTY know where your private key is located, but those are fairly easy to figure out.
Try the new web2py admin interface in trunk. It has a web based mercurial interface and a google deploy interface.
In web2py you can edit applications/admin/models/0.py and set
TEXT_EDITOR = 'amy'
And you will get the web based Amy editor with autocompletion. It is not default because because it does not work with some browsers and because autocompletion is not as good as eclipse. It may work for you.
You can use web2py with Eclipse but you need a minor workaround to let Eclipse know about the web2py environment. It is explained here.
I know other users have used other IDEs with web2py, for example WinIDE and pyCharm. I suggest you ask on the web2py mailing list where people are very helpful.
I'm pretty sure that the 'one-click setup script' to do all that you are looking for does not exist (at the moment). But don't be put off - you can achieve a nice development environment to suit your needs and there are lots of choices.
Although I develop on Windows, I like the setup I have as it's more of a 'Unixy' way of thinking whereby I have a number of tools each doing a specific task. Once you get a workflow setup you can be very productive - although I realise it may look a bit confusing initially coming from a Visual Studio world.
Below I outline what I've settled on. I'm sure others will have their own recommendations. Pick the options you like best.
(There should be hyperlinks to useful software below but I don't have enough reputation to include more than 1 link...)
For developing on Windows I'm enjoying using Pyscripter. It's free, fast (compared to Aptana / Eclipse / Netbeans etc) and has some nice features (dark theme, integrated python console and code explorer to name a few).
To get code completion / intellisense to work for web2py you need to add some code to your model / controller files because of the way web2py works. There are some instructions in this discussion topic on the web2py group.
web2py has a great error ticketing system built in (see the web2py book chapter 3). For more comprehensive debugging, pydb seems to be the way to go. Just put the code below as a breakpoint:
import pydb
pydb.debugger()
and it'll take you to the debugger.
I use TortoiseHg for Mercurial integration and it works wonderfully. Combine that with winscp and you can deploy easily.
Caveats: I work in OS X, and do most of my coding in BBEdit.
That said, I've used both Wing and Komodo IDE for web2py debugging, and they've both worked quite well for me. I haven't tried NetBeans in a while now; when I did the Python support seemed a little rough around the edges. And I've never had the time or patience to come up to speed with Eclipse; it's filed in my mental file cabinet with Emacs, no doubt unjustly to Eclipse and/or Emacs.
(And I'll echo mdipierro's recommendation to try the web2py mailing list; it's really indispensable--one of web2py's strongest points.)
Have you considered using fewer tools? Both Python and web2py don't require a whole lot of code to get a lot accomplished. web2py only adds 10 or 15 new function calls (besides the HTML helpers and validators). You might find that Eclipse and other IDEs actually get in the way. Setting up new apps in web2py is simple through the admin system. Since the new app scaffolding copies the welcome app, you can customize new app setup by editing the welcome app. With Mercurial (or Git, Subversion or Bazaar) you can set up a server on your machine or with one of the public sites and either push or pull updates to your production server. Keep it simple, I say.
we are using web2py framework for all our web application needs and this is our setup :
OS - Ubuntu up-to-date
IDE - Aptana Studio 3.0 with pyDev
Version Control - git
Python 2.7
Browser for developing phase : Chrome
I've found the Wing IDE debugger to be very useful. It's a powerful debugger across the board, and also can be configured to do remote debugging, which is really important when you are running web2py on a no-GUI remote machine (e.g. at Amazon Web Services).