Open-source made me a better developer, and can do the same for you.
TLDR;
This is our final stretch! We’ve navigated through building an Apps Script library, and now it’s time to discuss how you can contribute. Here’s a quick rundown of what we’ll cover:
GitHub Flow: Learn to fork the repository, create a feature branch, and make a pull request.
Guidelines: Tips on ensuring your pull request gets accepted.
Code of Conduct: We won’t delve into this, as respectful behavior is the default expectation.
License: Our library uses the MIT License, which is pretty much the one that lets you do anything you want with the code.
Issues: I will post issues that I consider a priority, but feel free to tackle any of them.
Process: Follow the steps outlined in our CONTRIBUTING.md file.
As a reminder, here are the links to the repo and the NPM page.
But first, let’s talk about what you should do before you open a pull request.
Everyone says use Google Apps Script libraries for easier maintenance — I found a better way. Here’s why NPM modules might change the game for you too.
Last time, we covered how to deploy our library as a native Google Apps Script (GAS) library using Vite, GitHub Actions, and clasp. This setup is efficient, but there’s a notable drawback to using Apps Script libraries.
According to the official guide: “Warning: A script that uses a library doesn’t run as quickly as it would if all the code were contained within a single script project. Although libraries can make development and maintenance more convenient, use them sparingly in projects where speed is critical. Because of this issue, library use should be limited in add-ons.”
Apps Script is not known for its speed, being a free runtime. Slowing it down further by using native GAS libraries is generally not advisable. Therefore, I prefer to avoid native GAS libraries whenever possible.
Instead, it’s much more efficient to bundle your dependencies directly into your source code, similar to how it’s done in Node.js. This is where NPM modules and Vite come into play.
In this post, we’ll cover:
Which NPM modules are compatible with Google Apps Script and which ones are not.
How to use NPM modules in your Apps Script projects.
Forget everything you know about deploying Google Apps Script, because the typical ‘Deploy’ button is not part of our strategy.
TLDR;
In the previous posts in this series, we focused on preparing our tools and setting the stage. We reviewed our project’s functionality, explored the project structure, and delved into the source code. We also discussed the pros and cons of using JSDoc versus TypeScript and covered essential developer tooling.
Today, we’re finally getting to the fun part—deploying something! We’ll start by deploying our library as a native Google Apps Script library. But there’s a twist: we will do it the proper CI/CD way, avoiding the typical “Deploy” button in the online IDE.
Side note: I always avoid the online IDE as it feels like my hands are tied when I use it.
Instead, we’ll use Vite with a custom plugin to bundle our library and GitHub Actions to handle the deployment.
In this series about deploying Google Apps Script libraries, Part 2 dove deep into Test-Driven Development (TDD) and highlighted jest as my go-to tool for outstanding outcomes. Now, let’s broaden our toolkit with additional essentials that not only elevate our development standards but also make our codebase more welcoming to collaborators.
First up, we’ve got ESLint. Linting, for those unfamiliar, is the process of running a program that will check your code for potential errors.
Next, we introduce Prettier, which takes our code and formats it into a structured style that you define. Think of Prettier as the stylist of your codebase, making sure everything looks ‘pretty’ and readable by cleaning up those messy or inconsistent styles left behind.
We also employ Husky, a tool for managing git hooks. Git hooks are scripts you can set to run before or after events like commits, push, and receive. Husky ensures that tools like ESLint, Prettier and Jest run every time you commit changes, helping catch issues before they hit production.
These tools are indispensable not just for solo developers but also for teams looking to contribute to the library. By maintaining consistent, pre-defined high standards of code hygiene, we ensure that our library remains robust, clean, and maintainable.
Prerequisites: You should be familiar with git, an essential skill for any developer. If you’re not, I recommend checking out the beginner’s guide at FreeCodeCamp. Additionally, being able to code locally and understanding clasp is crucial. If you need a refresher on this, visit my earlier post on setting up your local environment. Once you’re set, we can dive into making our development process even smoother and more efficient!
Here are the links to the repo and the NPM page again.
About a year ago, a notable shift occurred in the developer community when SvelteKit made the decision to transition from TypeScript to JSDoc, specifically stating that TypeScript was not the ideal choice for developing libraries. This move definitely raised some eyebrows and stirred the pot among developers. Initially, I was skeptical, perceiving it as a regression rather than progress. TypeScript was even featured in one of my previous blog posts as a recommended tool. However, this decision began to resonate with me over time, leading me to adopt a similar approach in Google Apps Script. The reasons for this shift are manifold, with some being universally applicable and others specific to the peculiarities of Apps Script.
Here are the links to the repo and the NPM page again.
Let’s dive into why TypeScript was chosen in the first place and what has changed to endorse JSDoc over it.
Following up from last week, we get into how I built the table() method in our ConsolAS class, using test-driven development (TDD). This is a cool way to make sure everything works perfectly by testing each part before we fully build it. We’re aiming to make it work just like the console.table() function in Google Chrome, which is pretty handy.
Here’s the scoop: While tinkering with a project, I needed a way to pinpoint the last row of data in various sheets — essentially to catch any “orphan” values lurking there. Typically, something like console.table() would be the hero of the day, allowing me to effortlessly display data like so:
I tried to see if an AI that’s good at writing could also make smart moves in a game. I chose Battleship and set it up in Google Sheets to play against Gemini, the AI. The result was mixed. On one hand, yes, Gemini could play the game. It followed the basic rules and even managed to sink some of my ships. This was a big deal, especially since it took me a ridiculous number of days of coding to get there, and I nearly gave up at one point.
Dmitry Kostyuk has shared a blog post detailing his experiment pitting the Gemini API against himself in a game of Battleship. As explained by Dmitry while Gemini could follow the rules and even sink some ships, it needed help to avoid basic mistakes, revealing that AI still has room to grow in the realm of strategic games.
Dmitry built the game in Google Sheets and the source code is linked from the post. To guide Gemini, Kostyuk crafted detailed prompts outlining the game’s mechanics and decision-making logic. However, he encountered challenges due to Gemini’s limitations in providing strategic responses. Despite these hurdles, the project yielded valuable insights into prompting techniques for AI decision-making.
I recently faced a frustrating issue when writing data to a CloudSQL database with the JDBC class in Apps Script. I kept getting the following error:
Exception: Argument too large: SQL
I also observed that it only happened when my SQL query reached a certain length. I considered breaking it down into multiple queries, but I was still puzzled 🤔 because I was only sending a few dozen kilobytes of data.
Now, the thing is, the official documentation could be more helpful; even though the solution is there, it needs to be better explained. So, I turned to StackOverflow. There was a discussion on this exact topic, but to my surprise, I was still waiting for an answer. Until, well, I wrote it 😉
Well, well, well! Look who’s back for another session of “Weaving Magic with Code”! 😄 Today, we’re diving head-first into the magical world of unit testing. You might be wondering: “Why the fuss about unit testing?” 🤔
Unit testing, my friends, is the silent hero of software development. Picture it as a mini-pit stop where your code gets a once-over before it hits the road. The automated tests ensure that our code does exactly what we expect it to. The benefits?
Makes us ponder deeply about our app’s architecture, like a philosopher musing about the meaning of life 🧐
Forces us to clarify our expectations from functions and classes.
Ensures that as we revamp and update our code, we aren’t unknowingly playing host to bugs, much like a surprise party you didn’t want 🐛
