Puedes leer la versión en español aquí.

On this episode we will build our own implementation of an observable. I hope that by the end of this post we gain a better understanding of this pattern that is used in libraries like RxJS.

About Observables

What is it?

Lets start with my definition of observable.

An Observable is a function that follows a convention and is used to connect a data source with a consumer.

In our case a data source is something that produces values. And, a consumer is something that receives values from a data source.

Fun facts

Observables are lazy

That means that they would not do any kind of work until it's absolutely necessary. Nothing will happen until you subscribe to them.

They can emit multiple values

Depending on the data source you can receive a finite number of values or an infinite stream of values.

They can be synchronous or asynchronous

It all depends on their internal implementation. You can setup an observable that process some stream of data in a synchronous way or create one from an event that can happen over time.

Some rules

Remember when I said that observables follow a convention? Well, we are going to make our own arbitrary rules that our implementation will follow. These will be important because we are going to build a little ecosystem around our observables.

Here we go:

1. An observable instance will have a subscribe method.
2. The observable "factory" will take a subscriber function as a parameter.
3. The subscriber function will take an observer object as a parameter.
4. The observer object can implement these methods next, error and complete.

Now, lets do stuff.

The code

Factory function

function Observable(subscriber) {
  return {
    subscribe: observer => subscriber(observer)
  };
}

// I swear to you, this works.

That is less magical than I thought. What we see here is that the Observable factory is just a way to postpone the work that has to be done until you call subscribe. The subscriber function is doing the heavy lifting, that's good because we can do whatever we want in there, is what will make our observables useful.

So far I haven't done a really good job explaining the observer and the subscriber roles. I hope it'll become clear when you see them in action.

A use case

Say that we want to convert an array into an Observable. How can we do this?

Lets think about what we know:

• We can do all of our logic inside the subscriber function.
• We can expect an observer object with three methods, next, error and complete

We can use the methods of the observer object as communication channels. The next function will receive the values that our data source gives us. The error will handle any errors we throw at it, it will be like the catch function in the Promise class. And, we will use the complete method when the data source is done producing values.

Our array to observable function could look like this.

function fromArray(arr) {
  return Observable(function(observer) {
    try {
      arr.forEach(value => observer.next(value));
      observer.complete();
    } catch (e) {
      observer.error(e);
    }
  });
}

// This is how we use it

var arrayStream = fromArray([1, 2, 3, 4]);

arrayStream.subscribe({
  next: value => console.log(value),
  error: err => console.error(err),
  complete: () => console.info('Nothing more to give')
});

// And now watch all the action on the console

Be safe

Right now the observer object is basically a lawless town, we could do all sorts of weird stuff like sending yet another value to next even after we call the complete method. Ideally our observables should give us some guarantees, like:

• The methods on the observer object should be optional.
• The complete and error methods need to call the unsubscribe function (if there is one).
• If you unsubscribe, you can't call next, complete or error.
• If the complete or error method were called, no more values are emitted.

Interactive example

We can actually start doing some interesting things with what we learned so far. In this example I made a helper function that let me create an observable from a DOM event.

Conclusion

Observables are a powerful thing, with a little bit of creativity you can turn anything you want into an observable. Really. A promise, an AJAX request, a DOM event, an array, a time interval... another observable (think about that for a second)... anything you can imagine can be a source of data that can be wrapped in an observable.

Other sources

• Learning Observable By Building Observable
• Observables, just powerful functions?

You can see part 2 of this post in here.

Thank you for your time. If you find this article useful and want to support my efforts, consider leaving a tip in ko-fi.com/vonheikemen.