msa-agent/internal/install/uninstall_test.go

package install

import (
	"errors"
	"fmt"
	"os"
	"path/filepath"
	"strings"
	"testing"
)

// recorder stands in for systemctl and userdel, so the sequence can be tested without systemd.
type recorder struct {
	calls []string
	// failOn makes a named command fail, for the cases where a missing unit or an absent user must not
	// abort the uninstall.
	failOn string
}

func (r *recorder) Run(name string, args ...string) error {
	call := name + " " + strings.Join(args, " ")
	r.calls = append(r.calls, call)
	if r.failOn != "" && strings.HasPrefix(call, r.failOn) {
		return fmt.Errorf("simulated failure")
	}
	return nil
}

// installed creates the layout an install leaves behind, so the test removes real files.
func installed(t *testing.T) Paths {
	t.Helper()
	root := t.TempDir()
	paths := Paths{
		ServiceName: "msa-agent",
		UnitPath:    filepath.Join(root, "etc/systemd/system/msa-agent.service"),
		ConfigPath:  filepath.Join(root, "etc/msa-agent/config.json"),
		LogDir:      filepath.Join(root, "var/log/msa-agent"),
		BinaryPath:  filepath.Join(root, "opt/msa-agent/msa-agent"),
		User:        "msa-agent",
	}
	for _, path := range []string{paths.UnitPath, paths.ConfigPath, filepath.Join(paths.LogDir, "audit.log"), paths.BinaryPath} {
		if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
			t.Fatal(err)
		}
		if err := os.WriteFile(path, []byte("x"), 0o600); err != nil {
			t.Fatal(err)
		}
	}
	return paths
}

func TestUninstallRemovesEverythingTheInstallPlaced(t *testing.T) {
	paths := installed(t)
	runner := &recorder{}
	var lines []string
	err := Uninstall(Options{
		Paths:  paths,
		Runner: runner,
		Log:    func(format string, args ...any) { lines = append(lines, fmt.Sprintf(format, args...)) },
		NotifyRelay: func() error {
			lines = append(lines, "relay notified")
			return nil
		},
	})
	if err != nil {
		t.Fatalf("Uninstall: %v", err)
	}
	for _, path := range []string{paths.UnitPath, paths.ConfigPath, paths.LogDir, paths.BinaryPath} {
		if _, err := os.Stat(path); !errors.Is(err, os.ErrNotExist) {
			t.Fatalf("%s survived the uninstall", path)
		}
	}
	// The config directory goes with the config: it holds relay-ca.pem and anything else the operator
	// put beside it.
	if _, err := os.Stat(filepath.Dir(paths.ConfigPath)); !errors.Is(err, os.ErrNotExist) {
		t.Fatal("the config directory survived; it may still hold pinned CA material")
	}
	joined := strings.Join(runner.calls, "\n")
	for _, want := range []string{"systemctl disable --now msa-agent", "systemctl daemon-reload", "userdel msa-agent"} {
		if !strings.Contains(joined, want) {
			t.Fatalf("expected %q among the commands, got:\n%s", want, joined)
		}
	}
}

// The order is the point: the relay has to be told before the node stops existing, or it keeps routing
// to a node that is gone and a phone that believes it is paired points at nothing.
func TestUninstallTellsTheRelayBeforeItRemovesAnything(t *testing.T) {
	paths := installed(t)
	configStillThere := false
	err := Uninstall(Options{
		Paths:  paths,
		Runner: &recorder{},
		Log:    func(string, ...any) {},
		NotifyRelay: func() error {
			// At the moment the relay is told, the config must still exist: the notification reads it.
			_, statErr := os.Stat(paths.ConfigPath)
			configStillThere = statErr == nil
			return nil
		},
	})
	if err != nil {
		t.Fatalf("Uninstall: %v", err)
	}
	if !configStillThere {
		t.Fatal("the config was removed before the relay was told; the device list could not be read")
	}
}

// A relay that cannot be reached must not stop an uninstall. The operator is removing the node either
// way, and the alternative — aborting half way — leaves the machine in a state nobody described.
func TestUninstallCompletesWhenTheRelayIsUnreachable(t *testing.T) {
	paths := installed(t)
	var lines []string
	err := Uninstall(Options{
		Paths:       paths,
		Runner:      &recorder{},
		Log:         func(format string, args ...any) { lines = append(lines, fmt.Sprintf(format, args...)) },
		NotifyRelay: func() error { return fmt.Errorf("relay unreachable") },
	})
	if err != nil {
		t.Fatalf("Uninstall: %v", err)
	}
	if _, err := os.Stat(paths.ConfigPath); !errors.Is(err, os.ErrNotExist) {
		t.Fatal("the uninstall did not finish")
	}
	// And the operator is told what is left to do by hand, because the relay still lists this node.
	output := strings.Join(lines, "\n")
	if !strings.Contains(output, "WARNING") || !strings.Contains(output, "agents.json") {
		t.Fatalf("a failed relay notification was not explained:\n%s", output)
	}
}

// A dry run removes nothing, and that includes not stopping the service: an operator asking what an
// uninstall would do must not lose the node while they read the answer.
func TestDryRunRemovesNothingAndRunsNothing(t *testing.T) {
	paths := installed(t)
	runner := &recorder{}
	var lines []string
	err := Uninstall(Options{
		Paths:  paths,
		DryRun: true,
		Runner: runner,
		Log:    func(format string, args ...any) { lines = append(lines, fmt.Sprintf(format, args...)) },
	})
	if err != nil {
		t.Fatalf("Uninstall: %v", err)
	}
	if len(runner.calls) != 0 {
		t.Fatalf("a dry run ran commands: %v", runner.calls)
	}
	for _, path := range []string{paths.UnitPath, paths.ConfigPath, paths.BinaryPath} {
		if _, err := os.Stat(path); err != nil {
			t.Fatalf("a dry run removed %s", path)
		}
	}
	if !strings.Contains(strings.Join(lines, "\n"), "dry run: nothing was removed") {
		t.Fatal("a dry run did not say so")
	}
}

func TestKeepLogsLeavesTheAuditLog(t *testing.T) {
	paths := installed(t)
	audit := filepath.Join(paths.LogDir, "audit.log")
	err := Uninstall(Options{
		Paths:    paths,
		KeepLogs: true,
		Runner:   &recorder{},
		Log:      func(string, ...any) {},
	})
	if err != nil {
		t.Fatalf("Uninstall: %v", err)
	}
	if _, err := os.Stat(audit); err != nil {
		t.Fatalf("--keep-logs removed the audit log: %v", err)
	}
}

// A missing unit or an absent user is the normal case on a partially installed node, and it must not
// abort: reporting it as an error would train the operator to ignore the errors that matter.
func TestMissingPiecesDoNotAbortTheUninstall(t *testing.T) {
	paths := installed(t)
	// Remove the unit first, then uninstall.
	if err := os.Remove(paths.UnitPath); err != nil {
		t.Fatal(err)
	}
	runner := &recorder{failOn: "systemctl disable"}
	err := Uninstall(Options{
		Paths:  paths,
		Runner: runner,
		Log:    func(string, ...any) {},
	})
	if err != nil {
		t.Fatalf("a missing unit aborted the uninstall: %v", err)
	}
	if _, err := os.Stat(paths.ConfigPath); !errors.Is(err, os.ErrNotExist) {
		t.Fatal("the config survived")
	}
}

// The plan names every path, so an operator can check it before running anything.
func TestThePlanNamesEveryPath(t *testing.T) {
	plan := DefaultPaths().String()
	for _, want := range []string{"/etc/systemd/system/msa-agent.service", "/etc/msa-agent/config.json",
		"/var/log/msa-agent", "/opt/msa-agent/msa-agent", "msa-agent"} {
		if !strings.Contains(plan, want) {
			t.Fatalf("the plan does not mention %s:\n%s", want, plan)
		}
	}
}