Preface: Why?
Environment variables are very useful for configuring your app depending on the environment, without having to hardcode any value in the source.
At my current company we are building a microservice infrastructure, where the frontend and the backend are completely decoupled applications. We also use Docker to manage these microservices and link them together. Turns out that storing the configuration in the environment—as opposed to storing it in the database or in the code itself—is quite valuable, as described also in the twelve-factor methodology.
Advantages:
- Language and OS agnostic;
- Easy to change between deploys without changing any code;
- Impossible to accidentally check in source control.
How?
A web page doesn’t have access to OS variables, so you can’t normally use them.
The solution is pretty simple: you just need to generate a file that contains them.
For such a trivial task you could be tempted to use your language of choice, e.g. in JavaScript (Node.js) you have access to process.env.SOME_VAR. In Python you would probably do os.getenv('SOME_VAR') and in Ruby you’d use ENV['SOME_VAR']—but what about some old-school shell scripting? The script could be as simple as:
# bin/env.sh
echo "env = {"
echo " USER: '$USER',"
echo " HOSTNAME: '$HOSTNAME'"
echo "}"
That, when executed, will become:
// env.js
env = {
USER: 'yourname',
HOSTNAME: 'ubuntu'
}
And the script to execute on the shell is:
Pretty straightforward, isn’t it?
Test it:
<!DOCTYPE html>
<html>
<head>
...
</head>
<body>
<script src="env.js"></script>
<script>
console.log(env.USER, env.HOSTNAME);
</script>
</body>
</html>
One downside to this approach is that you have to “make a build” every time you change the variables. If you know any workarounds or better solutions, please let me know!
Source and download
Find the source code on GitHub. Download the zip file here.
Have fun!