DEV Community

Akash Joshi
Akash Joshi

Posted on

A Better Way to Structure React Projects

Photo by Ferenc Almasi on Unsplash

So 2020 has just come to an end, it was a great year for me personally, I have written more about it on my previous blog post here. To everyone who read through it, thanks a lot. I am trying to share more of my life through my writing and that blog-post was an experiment in that. For further updates you can subscribe to this blog with your email, or follow me on Twitter here.

Apart from it, several people have questions about where I work full-time at. It’s DelightChat, and I couldn’t ask for a better work. Building products from scratch and sharing knowledge across the team without arbitrary constraints is what I thrive in doing.

Because of a far better control over the frontend stack, and having the freedom to experiment with new technologies, I’ve had a better and more deeper understanding of how a React project should be structured for complex applications like the one we’re building here.

And since a lot of e-ink has already been spilt on the relatively easier pickings of “Doing X in React” or “Using React with technology X”, I thought of writing on this topic, which requires a more deeper understanding of React and extended usage in a production setting.

Introduction

In a nutshell, a complex React project should be structured like this. Although I use NextJS in production, this file structure should be quite useful in any React setting.

src
|---adapters
|---contexts
|---components
|---styles
|---pages
Enter fullscreen mode Exit fullscreen mode

Note: In the above file structure, the assets or static files should be placed in whatever the variant of public *folder for your framework is.*

For each of the above folders, let’s discuss each of them in order of precedence.

1. Adapters

Adapters are the connectors of your application with the outside world. Any form of API call or websocket interaction which needs to happen, to share data with an external service or client, should happen within the adapter itself.

In cases where some data is always shared between all the adapters. Eg, sharing of cookies, base URL and headers across your AJAX (XHR) adapters, it can be initialized in the xhr folder, and then imported inside of your other adapters to be used further.

This structure will look like:

adapters
|---xhr
|---page1Adapter
|---page2Adapter
Enter fullscreen mode Exit fullscreen mode

In the case of axios, you can use axios.create to create a base adapter, and either export this initialized instance, or create different functions for get, post, patch and delete to abstract it further. This would look like:

// adapters/xhr/index.tsx

import Axios from "axios";

function returnAxiosInstance() {
  return Axios.create(initializers);
}

export function get(url){
  const axios = returnAxiosInstance();
  return axios.get(url);
}

export function post(url, requestData){
  const axios = returnAxiosInstance();
  return axios.post(url, requestData);
}

... and so on ...
Enter fullscreen mode Exit fullscreen mode

After you have your base file (or files) ready, create a seperate adapter file for each page, or each set of functionalities, depending on how complex your app is. A well-named function makes it very easy to understand what each API call does and what it should accomplish.

// adapters/page1Adapter/index.tsx

import { get, post } from "adapters/xhr";
import socket from "socketio";

// well-named functions
export function getData(){
  return get(someUrl);
}

export function setData(requestData){
  return post(someUrl, requestData);
}

... and so on ...
Enter fullscreen mode Exit fullscreen mode

But how will these adapters be of any use? Let’s find out in the next section.

2. Components

Although in this section, we should talk about contexts, I want to talk about components first. This is to understand why context is required (and needed) in complex applications.

Components are the life-blood of your application. They will hold the UI for your application, and can sometimes hold the Business Logic and also any State which has to be maintained.

In case a component becomes too complex to express Business Logic with your UI, it is good to be able to split it into a seperate bl.tsx file, with your root index.tsx importing all of the functions and handlers from it.

This structure would look like:

components
|---page1Components
        |--Component1
        |--Component2
|---page2Component
        |--Component1
               |---index.tsx
               |---bl.tsx
Enter fullscreen mode Exit fullscreen mode

In this structure, each page gets its own folder inside of components, so that it’s easy to figure out which component affects what.

It’s also important to limit the scope of a component. Hence, a component should only use adapters for data-fetching, have a seperate file for complex Business Logic, and only focus on the UI part.

// components/page1Components/Component1/index.tsx

import businessLogic from "./bl.tsx";

export default function Component2() {

  const { state and functions } = businessLogic();

  return {
    // JSX
  }
}
Enter fullscreen mode Exit fullscreen mode

While the BL file only imports data and returns it

// components/page1Components/Component1/bl.tsx

import React, {useState, useEffect} from "react";
import { adapters } from "adapters/path_to_adapter";

export default function Component1Bl(){
  const [state, setState] = useState(initialState);

  useEffect(() => {
    fetchDataFromAdapter().then(updateState);
  }, [])
}

Enter fullscreen mode Exit fullscreen mode

However, there’s a problem which is common across all complex apps. State Management, and how to share state across distant components. Eg, consider the following file structure:

components
|---page1Components
        |--Component1
               |---ComponentA
|---page2Component
        |--ComponentB
Enter fullscreen mode Exit fullscreen mode

If some state has to be shared across ComponentA and B in the above example, it will have to be passed through all the intermediate components, and also to any other components who want to interact with the state.

To solve this, their are several solutions which can be used like Redux, Easy-Peasy and React Context, each of them having their own pros & cons. Generally, React Context should be “good enough” to solve this problem. We store all of the files related to context in contexts.

3. Contexts

The contexts folder is a bare minimum folder only containing the state which has to be shared across these components. Each page can have several nested contexts, with each context only passing the data forward in a downward direction, but to avoid complexity, it is best to only have a single context file. This structure will look like:

contexts
|---page1Context
        |---index.tsx (Exports consumers, providers, ...)
        |---Context1.tsx (Contains part of the state)
        |---Context2.tsx (Contains part of the state)
|---page2Context
        |---index.tsx (Simple enough to also have state)
Enter fullscreen mode Exit fullscreen mode

In the above case, since page1 may be a bit more complex, we allow some nested context by passing the child context as a child to the parent. However, generally a single index.tsx file containing state, and exporting relevant files should be enough.

I won’t go into the implementation part of React state management libraries since each of them are their own beasts and have their own upsides and downsides. So, I recommend going through the tutorial of whatever you decide to use to learn their best practises.

The context is allowed to import from adapters to fetch and react to external effects. In case of React Context, the providers are imported inside pages to share state across all components, and something like useContext is used inside these components to be able to utilize this data.

Moving on to the final major puzzle-piece, pages.

4. Pages

I want to avoid being biased to a framework for this piece, but in general, having a specific folder for route-level components to be placed is a good practise. Gatsby & NextJS enforce having all routes in a folder named pages. This is quie a readable way of defining route-level components, and mimicking this in your CRA-generated application would also result in better code readability.

A centralized location for routes also helps you utilize the “Go To File” functionality of most IDEs by jumping to a file by using (Cmd or Ctrl) + Click on an import, which helps you move through the code quickly and with clarity of what belongs where. It also sets a clear hierarchy of differentiation between pages and components, where a page can import a component to display it and do nothing else, not even Business Logic.

However, it’s possible to import Context Providers inside of your page so the child components can consume it. Or, in the case of NextJS, write some server-side code which can pass data to your components using getServerSideProps or getStaticProps.

5. Styles

Finally, we come to styles. Although my go-to way is to just embed styles inside of the UI by using a CSS-in-JS solution like Styled-Components, it’s sometimes helpful to have a global set of styles in a CSS file. A plain old CSS file is more shareable across projects, and can also affect the CSS of components which styled-components can’t reach (eg, third-party components).

So, you can store all of these CSS files inside of the styles folder, and import or link to them freely from wherever you wish.

So those were my thoughts. Feel free to email me in case you want to discuss something or have any more inputs on how this can be improved!

For further updates you can subscribe to this blog with your email, or follow me on Twitter here.

Top comments (5)

Collapse
 
jakecarpenter profile image
Jake Carpenter • Edited

I think you would be surprised how much harder you make things on yourself by doing as you've described.

Colocation by feature makes things easier to find. I don't like to scour a pages folder then the components folder and finally some random place because that's where someone decided "business logic" goes to modify a single feature. I like to put them in the same place until it is proven that they don't belong together or are shared by many areas. Then they get moved into a shared location that is dictated by circumstance.

This enforces good refactoring approaches. This is the biggest reason I like to do it that way. There is no one good project structure or one good pattern that fits all purposes, only patterns that evolve as your project and needs do.

Collapse
 
thewritingdev profile image
Akash Joshi • Edited

This might make sense if you have direct control over the codebase, but I've experienced it first-hand that having an easily enforcable and readable convention (whatever it might be for you) is a good way of scaling a project across a team :)

Collapse
 
kevinast profile image
Kevin Bridges • Edited

Take a peek at this article: Are you using features?

Collapse
 
jackmellis profile image
Jack

Very nice article. I'm always surprised how little concern is given to front end structure and architecture. I follow a pretty similar setup, where the external contact points are kept separate to the ui, and the ui in fact should have little-to-no understanding of the underlying technologies. I also keep my core business logic separate to the ui as well, so if you need to understand why or how something is decided from a business point of view, you dont have to search through components to find it.

Collapse
 
thewritingdev profile image
Akash Joshi

Thank you for the kind words and sharing your setup :)