Error Handling

Error handling

Fetch is used for reading data from remote sources and the queries we perform can and will fail at some point. There are many things that can go wrong:

  • an exception can be thrown by client code of certain data sources
  • an identity may be missing
  • the data source may be temporarily available

Since the error cases are plenty and can’t be anticipated Fetch errors are represented by the 'FetchException' trait, which extends Throwable. Currently fetch defines FetchException cases for missing identities and arbitrary exceptions but you can extend FetchException with any error you want.

Exceptions

What happens if we run a fetch and fails with an exception? We’ll create a fetch that always fails to learn about it.

def fetchException[F[_]: Concurrent]: Fetch[F, User] =
  Fetch.error(new Exception("Oh noes"))

If we try to execute to IO the exception will be thrown wrapped in a fetch.UnhandledException.

Fetch.run[IO](fetchException).unsafeRunTimed(5.seconds)
//fetch.package$UnhandledException

A safer version would use Cats' .attempt method: 

val safeResult = Fetch.run[IO](fetchException).attempt.unsafeRunSync()

safeResult.isLeft shouldBe res0

Debugging exceptions

Using fetch’s debugging facilities, we can visualize a failed fetch’s execution up until the point where it failed. Let’s create a fetch that fails after a couple rounds to see it in action:

def failingFetch[F[_]: Concurrent]: Fetch[F, String] = for {
  a <- getUser(1)
  b <- getUser(2)
  c <- fetchException
} yield s"${a.username} loves ${b.username}"

val result: IO[Either[Throwable, (Log, String)]] = Fetch.runLog[IO](failingFetch).attempt

Now let’s use the fetch.debug.describe function for describing the error if we find one: 

import fetch.debug.describe

val value: Either[Throwable, (Log, String)] = result.unsafeRunSync()
value.isLeft shouldBe res0

println(value.fold(describe, identity))

// [ERROR] Unhandled `java.lang.Exception`: 'Oh noes', fetch interrupted after 2 rounds
// Fetch execution 🕛 0.21 seconds
//
//     [Round 1] 🕛 0.10 seconds
//       [Fetch one] From `Users` with id 1 🕛 0.10 seconds
//     [Round 2] 🕛 0.11 seconds
//       [Fetch one] From `Users` with id 2 🕛 0.11 seconds

As you can see in the output from describe, the fetch stopped due to a java.lang.Exception after successfully executing two rounds for getting users 1 and 2.

Missing identities

You’ve probably noticed that DataSource.fetch and DataSource.batch return types help Fetch know if any requested identity was not found. Whenever an identity cannot be found, the fetch execution will fail with an instance of MissingIdentity. 

import fetch.debug.describe

def missingUser[F[_]: Concurrent] = getUser(5)

val result: IO[Either[Throwable, (Log, User)]] = Fetch.runLog[IO](missingUser).attempt

//And now we can execute the fetch and describe its execution:

val value: Either[Throwable, (Log, User)] = result.unsafeRunSync()
value.isLeft shouldBe res0
println(value.fold(describe, identity))

As you can see in the output, the identity 5 for the user source was not found, thus the fetch failed without executing any rounds. MissingIdentity also allows you to access the fetch request that was in progress when the error happened. 

import fetch.debug.describe

Fetch.runLog[IO](getUser(5)).attempt.unsafeRunSync() match {
  case Left(mi @ MissingIdentity(id, q, log)) => {
    q.data.name shouldBe res0
    id shouldBe res1

    println(describe(log))
  }
  case _ =>
}