Fail loudly on an unparseable SENTRY_DSN and a malformed .env (closes #283)

internal/server/sentry_failure_test.go

@@ -0,0 +1,99 @@
+package server_test
+
+import (
+	"context"
+	"net"
+	"strconv"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+	"go.uber.org/fx"
+	"sneak.berlin/go/webhooker/internal/config"
+	"sneak.berlin/go/webhooker/internal/globals"
+	"sneak.berlin/go/webhooker/internal/server"
+)
+
+// TestSentryInitFailure_ShutsDownTheApp pins that error reporting
+// which is configured and cannot be started ends the application
+// instead of serving without it.
+//
+// The measured defect logged `sentry init failure` and kept running,
+// so the deployment served traffic with reporting off while every
+// other signal — SENTRY_DSN still set, the startup summary's own
+// field — said it was on. Nothing later in the process can notice
+// that reports are going nowhere, which is why this exits rather than
+// degrades.
+//
+// The DSN is placed on a hand-built Config, which is the only way to
+// reach this branch at all: loadFromEnv now parses SENTRY_DSN with
+// sentry.NewDsn, the same call sentry.Init makes, so a DSN that
+// survives configuration cannot fail initialisation in the SDK
+// version this pins. The branch stays because that is a property of
+// the SDK's current implementation rather than of its contract.
+func TestSentryInitFailure_ShutsDownTheApp(t *testing.T) {
+	t.Parallel()
+
+	port := freePort(t)
+
+	env := newTestEnvWithConfig(t, &config.Config{
+		DataDir:     t.TempDir(),
+		Environment: config.EnvironmentDev,
+		BindAddress: loopbackV4,
+		Port:        port,
+		SentryDSN:   "not-a-dsn",
+	})
+
+	app := fx.New(
+		fx.NopLogger,
+		fx.Supply(env.log, env.cfg, env.mw, env.hnd),
+		fx.Provide(globals.New, server.New),
+		fx.Invoke(func(*server.Server) {}),
+	)
+
+	startCtx, cancelStart := context.WithTimeout(
+		context.Background(), lifecycleTimeout,
+	)
+	defer cancelStart()
+
+	require.NoError(t, app.Start(startCtx))
+
+	select {
+	case sig := <-app.Wait():
+		require.Equal(
+			t, server.StartupFailureExitCode, sig.ExitCode,
+			"a sentry failure must exit non-zero",
+		)
+	case <-time.After(listenFailureDeadline):
+		t.Fatal("a sentry failure left the app running")
+	}
+
+	// The stop sequence still has to complete: the failure must reach
+	// shutdown through fx rather than around it.
+	stopCtx, cancelStop := context.WithTimeout(
+		context.Background(), lifecycleTimeout,
+	)
+	defer cancelStop()
+
+	require.NoError(t, app.Stop(stopCtx))
+
+	// And it must give up before it listens. A process that bound the
+	// port and then exited would have accepted requests it could not
+	// report on, which is the state under test in miniature.
+	requireBindable(t, port)
+}
+
+// requireBindable asserts that the port is free, which it is only if
+// the server under test never claimed it.
+func requireBindable(t *testing.T, port int) {
+	t.Helper()
+
+	var listenCfg net.ListenConfig
+
+	listener, err := listenCfg.Listen(
+		t.Context(), "tcp",
+		net.JoinHostPort(loopbackV4, strconv.Itoa(port)),
+	)
+	require.NoError(t, err, "the server bound a port it then gave up")
+	require.NoError(t, listener.Close())
+}