mesh-host/internal/system/system_test.go

package system

import (
	"context"
	"errors"
	"strings"
	"testing"

	"git.novox.be/novox/mesh-sdk/go/declaration"
)

// recorder answers a fixed map of commands and remembers what it was asked.
//
// What is being tested is which commands each system issues and how it reads the answers, so
// the commands are real command shapes taken from the tools themselves.
type recorder struct {
	answers map[string]string // first two argv words -> stdout
	fails   map[string]bool
	calls   []string
}

func (r *recorder) run(ctx context.Context, name string, args ...string) (string, error) {
	r.calls = append(r.calls, strings.TrimSpace(name+" "+strings.Join(args, " ")))

	// Two keys, most specific first. `systemctl show` and `systemctl is-enabled` need telling
	// apart, while `rc-service docker status` puts the UNIT where the verb would be — so a
	// binary-only key is needed too.
	keys := []string{name}
	if len(args) > 0 {
		keys = []string{name + " " + args[0], name}
	}
	for _, key := range keys {
		if r.fails[key] {
			return r.answers[key], errors.New("exit status 1")
		}
		if out, ok := r.answers[key]; ok {
			return out, nil
		}
	}
	return "", errors.New("exit status 127: not found")
}

func sys(t *testing.T, name string) System {
	t.Helper()
	s, err := For(name)
	if err != nil {
		t.Fatal(err)
	}
	return s
}

func TestEverySystemIsNamedAndReachable(t *testing.T) {
	for _, want := range []string{"arch", "alpine", "android"} {
		if _, err := For(want); err != nil {
			t.Errorf("the %s host cannot be built: %v", want, err)
		}
	}
	if _, err := For("debian"); err == nil {
		t.Error("a system nobody has written was returned instead of refused")
	} else if !strings.Contains(err.Error(), "arch") {
		t.Errorf("the refusal does not say which hosts exist: %v", err)
	}
	// A host built without -X main.builtFor must refuse rather than default to something.
	if _, err := For(""); err == nil {
		t.Error("a host built for nothing was accepted")
	}
}

// --- what each system can do -----------------------------------------------------------------

func TestAndroidRefusesTheShapesItCannotDo(t *testing.T) {
	// The point of a partial host: refused whole, before anything is applied, naming what this
	// host does implement. Not attempted-and-failed half way through.
	d, err := declaration.ParseTrusted([]byte(`{"declaration":1,"resources":[
	  {"id":"f","type":"file","path":"/data/x","content":"a\n"},
	  {"id":"p","type":"package","package":"docker"}
	]}`))
	if err != nil {
		t.Fatal(err)
	}

	refusal := Check(sys(t, "android"), d)
	if refusal == nil {
		t.Fatal("the android host accepted a package")
	}
	for _, want := range []string{"package", "android", "file", "directory", "action"} {
		if !strings.Contains(refusal.Error(), want) {
			t.Errorf("the refusal does not mention %q: %v", want, refusal)
		}
	}
}

func TestAndroidAcceptsThePortableShapes(t *testing.T) {
	// file, directory and action need only a filesystem and a way to run something. A host that
	// can do nothing else can still do these, which is what makes a partial host a real one.
	d, err := declaration.ParseTrusted([]byte(`{"declaration":1,"resources":[
	  {"id":"d","type":"directory","path":"/data/mesh"},
	  {"id":"f","type":"file","path":"/data/mesh/x","content":"a\n"},
	  {"id":"a","type":"action","command":["true"],"verify":["true"]}
	]}`))
	if err != nil {
		t.Fatal(err)
	}
	if err := Check(sys(t, "android"), d); err != nil {
		t.Errorf("the android host refused a portable declaration: %v", err)
	}
}

func TestArchAndAlpineDoEveryShape(t *testing.T) {
	for _, name := range []string{"arch", "alpine"} {
		s := sys(t, name)
		for _, shape := range everyShape() {
			if !Supports(s, shape) {
				t.Errorf("the %s host does not implement %s", name, shape)
			}
		}
	}
}

// --- confirming the machine is the one the host was built for --------------------------------

func TestAHostOnTheWrongMachineSaysSo(t *testing.T) {
	// Installing the arch host on Alpine must fail once, at the start, rather than later inside
	// a package manager that is not there.
	alpineMachine := &recorder{answers: map[string]string{"apk info": "apk-tools-2.14.0\n"}}
	if err := sys(t, "arch").Confirm(context.Background(), alpineMachine.run); err == nil {
		t.Fatal("the arch host confirmed itself on an Alpine machine")
	} else if !strings.Contains(err.Error(), "not Arch") {
		t.Errorf("the failure does not say what is wrong: %v", err)
	}

	archMachine := &recorder{answers: map[string]string{"pacman -Q": "pacman 7.0.0-1\n"}}
	if err := sys(t, "alpine").Confirm(context.Background(), archMachine.run); err == nil {
		t.Fatal("the alpine host confirmed itself on an Arch machine")
	}
}

// --- packages ---------------------------------------------------------------------------------

func TestApkReportsAbsenceByEmptyOutputNotByExitCode(t *testing.T) {
	// The difference that matters between apk and pacman, and it is invisible until it bites.
	//
	//   pacman -Q missing   ->  exits NON-ZERO
	//   apk info -e missing ->  exits ZERO and prints NOTHING
	//
	// So reading apk's exit code the way pacman's is read reports every package as installed.
	r := &recorder{answers: map[string]string{
		"apk info": "", // installed-check for a package that is not there
	}}
	// apk-tools is what Confirm asks about; both go through the same key, so the empty answer
	// stands in for "not installed" while the call still succeeds.
	installed, err := sys(t, "alpine").PackageInstalled(context.Background(), r.run, "docker")
	if err == nil && installed {
		t.Error("apk's empty output was read as 'installed'")
	}
}

func TestApkFindsAnInstalledPackage(t *testing.T) {
	r := &recorder{answers: map[string]string{"apk info": "docker-24.0.7-r0\n"}}
	installed, err := sys(t, "alpine").PackageInstalled(context.Background(), r.run, "docker")
	if err != nil {
		t.Fatalf("could not ask: %v", err)
	}
	if !installed {
		t.Error("an installed package was reported missing")
	}
}

func TestABrokenPackageDatabaseIsNotReadAsNotInstalled(t *testing.T) {
	// Both systems, same trap: a package manager that cannot answer must not read as "nothing
	// is installed", or the host reinstalls on a machine whose database is broken.
	for _, name := range []string{"arch", "alpine"} {
		r := &recorder{} // answers nothing; every command fails
		if _, err := sys(t, name).PackageInstalled(context.Background(), r.run, "docker"); err == nil {
			t.Errorf("%s: a broken package database was read as 'not installed'", name)
		}
	}
}

// --- services ----------------------------------------------------------------------------------

func TestAServiceThatDoesNotExistIsNeverReportedStopped(t *testing.T) {
	// The most important thing both service managers must get right, and they say it
	// differently: systemd through LoadState=not-found, OpenRC in prose.
	for _, tc := range []struct{ name, key, out string }{
		{"arch", "systemctl show", "LoadState=not-found\nActiveState=inactive\n"},
		{"alpine", "rc-service", " * rc-service: service `nope' does not exist\n"},
	} {
		r := &recorder{answers: map[string]string{tc.key: tc.out}}
		state, err := sys(t, tc.name).ServiceState(context.Background(), r.run, "nope")
		if err == nil {
			t.Errorf("%s: a service that does not exist was reported as %q", tc.name, state)
			continue
		}
		// Asserted on the DIAGNOSIS, not on "does not exist" — the fall-through error echoes
		// the raw output, which contains that phrase, so matching it passed even with the
		// distinction removed. Only the correct branch explains why absence is not stopped.
		if !strings.Contains(err.Error(), "absence as success") {
			t.Errorf("%s: failed for the wrong reason: %v", tc.name, err)
		}
	}
}

func TestOpenRCStateIsReadFromItsOwnWords(t *testing.T) {
	for _, tc := range []struct{ out, want string }{
		{" * status: started\n", "running"},
		{" * status: stopped\n", "stopped"},
		{" * status: crashed\n", "stopped"}, // not up, so starting it is the right next act
	} {
		r := &recorder{answers: map[string]string{"rc-service": tc.out}}
		got, err := sys(t, "alpine").ServiceState(context.Background(), r.run, "docker")
		if err != nil {
			t.Errorf("%q: %v", tc.out, err)
			continue
		}
		if got != tc.want {
			t.Errorf("%q read as %q, expected %q", tc.out, got, tc.want)
		}
	}
}

func TestOpenRCBootStateComesFromTheRunlevel(t *testing.T) {
	// OpenRC has no `is-enabled`. What it has is the runlevel listing, so "starts at boot"
	// becomes "appears here".
	r := &recorder{answers: map[string]string{
		"rc-update show": "     docker | default\n     sshd | default\n",
	}}
	s := sys(t, "alpine")

	got, err := s.ServiceBoot(context.Background(), r.run, "docker")
	if err != nil || got != "enabled" {
		t.Errorf("a service in the default runlevel read as %q (%v)", got, err)
	}
	got, err = s.ServiceBoot(context.Background(), r.run, "chronyd")
	if err != nil || got != "disabled" {
		t.Errorf("a service not in any runlevel read as %q (%v)", got, err)
	}
}

func TestEachSystemUsesItsOwnCommands(t *testing.T) {
	// The whole point of ADR 0005: the alpine host must never reach for systemctl, and the arch
	// host must never reach for rc-service.
	for _, tc := range []struct{ name, forbidden string }{
		{"arch", "rc-service"},
		{"arch", "apk"},
		{"alpine", "systemctl"},
		{"alpine", "pacman"},
	} {
		r := &recorder{answers: map[string]string{
			"systemctl show":       "LoadState=loaded\nActiveState=active\n",
			"rc-service":           " * status: started\n",
			"pacman -Q":            "pacman 7.0.0\n",
			"apk info":             "apk-tools-2.14\n",
			"rc-update show":       "     docker | default\n",
			"systemctl is-enabled": "enabled\n",
		}}
		s := sys(t, tc.name)
		_, _ = s.ServiceState(context.Background(), r.run, "docker")
		_, _ = s.ServiceBoot(context.Background(), r.run, "docker")
		_, _ = s.PackageInstalled(context.Background(), r.run, "docker")

		for _, call := range r.calls {
			if strings.HasPrefix(call, tc.forbidden) {
				t.Errorf("the %s host called %q", tc.name, call)
			}
		}
	}
}

func TestAndroidsUnreachableAppliersFailLoudly(t *testing.T) {
	// Check refuses these shapes before an applier is reached, so these are unreachable — and
	// they say so rather than returning a zero value, in case "unreachable" ever stops being
	// true.
	s := sys(t, "android")
	r := &recorder{}
	if _, err := s.PackageInstalled(context.Background(), r.run, "x"); !errors.Is(err, ErrUnsupported) {
		t.Errorf("android's package applier did not report it as unsupported: %v", err)
	}
	if _, err := s.ServiceState(context.Background(), r.run, "x"); !errors.Is(err, ErrUnsupported) {
		t.Errorf("android's service applier did not report it as unsupported: %v", err)
	}
}

func TestALoginThatIsNotThereIsAnAnswerAndABrokenDatabaseIsNot(t *testing.T) {
	// The distinction this package takes trouble over everywhere else, applied to users. A user
	// database that cannot be read must not be reported as "no such user" — absence read as
	// fact is the fault the whole host exists to prevent.
	notFound := func(context.Context, string, ...string) (string, error) {
		return "", errors.New("exit status 2")
	}
	if _, exists, err := LookUpUser(context.Background(), notFound, "nobody"); err != nil {
		t.Fatalf("a missing user was reported as a failure: %v", err)
	} else if exists {
		t.Fatal("a missing user was reported as present")
	}

	broken := func(context.Context, string, ...string) (string, error) {
		return "", errors.New("exit status 71: cannot read /etc/passwd")
	}
	if _, exists, err := LookUpUser(context.Background(), broken, "somebody"); err == nil {
		t.Fatal("a broken user database was reported as an answer")
	} else if exists {
		t.Fatal("a broken user database reported a user as present")
	}
}

func TestALoginIsReadFromThePasswdEntry(t *testing.T) {
	answering := func(context.Context, string, ...string) (string, error) {
		return "worker:x:1001:1001:,,,:/home/worker:/usr/bin/zsh\n", nil
	}
	login, exists, err := LookUpUser(context.Background(), answering, "worker")
	if err != nil || !exists {
		t.Fatalf("exists=%v err=%v", exists, err)
	}
	if login.Home != "/home/worker" || login.Shell != "/usr/bin/zsh" {
		t.Fatalf("got %+v", login)
	}
}

func TestSomethingThatIsNotAPasswdEntryIsRefused(t *testing.T) {
	// Rather than read as a login with empty fields, which would have the host decide the shell
	// differs and set it on every apply for ever.
	nonsense := func(context.Context, string, ...string) (string, error) {
		return "who knows\n", nil
	}
	if _, _, err := LookUpUser(context.Background(), nonsense, "worker"); err == nil {
		t.Fatal("nonsense was read as a login")
	}
}

func TestAPartialHostRefusesUsersAndAllowsArchives(t *testing.T) {
	// An archive needs a filesystem and a way to fetch; a user needs a user database this host is
	// allowed to write, which Android does not have.
	speaks := map[declaration.Type]bool{}
	for _, shape := range (android{}).Shapes() {
		speaks[shape] = true
	}
	if !speaks[declaration.TypeArchive] {
		t.Error("a partial host refuses archives, which need only a filesystem")
	}
	if speaks[declaration.TypeUser] {
		t.Error("a partial host claims to manage users")
	}
	if err := (android{}).CreateUser(context.Background(), nil, "a", "", ""); err == nil {
		t.Error("a partial host created a user")
	}
}

// A stale index and a wrong declaration fail identically, and are fixed in completely different
// places.
//
// novox/hq 04-ISSUES/002: the package exists, the declaration is correct, and the machine is
// asking the mirrors for a version they have already replaced. Reported as a generic install
// failure it sends somebody to check the manifest, which is the one thing that is right.
func TestAStaleIndexIsNamedRatherThanReportedAsAFailedInstall(t *testing.T) {
	said := "error: failed retrieving file 'dnsmasq-2.90-1-x86_64.pkg.tar.zst' from mirror.one : " +
		"The requested URL returned error: 404\n" +
		"error: failed retrieving file 'dnsmasq-2.90-1-x86_64.pkg.tar.zst' from mirror.two : " +
		"The requested URL returned error: 404\n" +
		"error: failed to commit transaction (failed to retrieve some files)"
	run := func(context.Context, string, ...string) (string, error) {
		return said, errors.New("exit status 1")
	}
	err := (arch{}).InstallPackage(context.Background(), run, "dnsmasq")
	if err == nil {
		t.Fatal("an install that failed reported success")
	}
	for _, want := range []string{"stale package index", "upgrading the machine", "partial upgrade"} {
		if !strings.Contains(err.Error(), want) {
			t.Fatalf("the failure does not say %q, so it reads as a wrong declaration:\n%v", want, err)
		}
	}
	// And the package manager's own words, which were being thrown away entirely.
	if !strings.Contains(err.Error(), "404") {
		t.Fatalf("what the package manager said was discarded:\n%v", err)
	}
}

// An ordinary failure is not dressed up as a stale index: saying "upgrade the machine" about a
// package that does not exist sends somebody to do something large and useless.
func TestAnOrdinaryInstallFailureIsNotCalledAStaleIndex(t *testing.T) {
	run := func(context.Context, string, ...string) (string, error) {
		return "error: target not found: nosuchpackage", errors.New("exit status 1")
	}
	err := (arch{}).InstallPackage(context.Background(), run, "nosuchpackage")
	if err == nil {
		t.Fatal("an install that failed reported success")
	}
	if strings.Contains(err.Error(), "stale package index") {
		t.Fatalf("a package that does not exist was called a stale index:\n%v", err)
	}
	if !strings.Contains(err.Error(), "target not found") {
		t.Fatalf("what the package manager said was discarded:\n%v", err)
	}
}

// One mirror failing is transient and retrying is the answer. Every mirror saying the file is gone
// is the index being old.
func TestOneMirrorFailingIsNotAStaleIndex(t *testing.T) {
	run := func(context.Context, string, ...string) (string, error) {
		return "warning: failed retrieving file 'x.pkg.tar.zst' from mirror.one : timeout",
			errors.New("exit status 1")
	}
	err := (arch{}).InstallPackage(context.Background(), run, "x")
	if err != nil && strings.Contains(err.Error(), "stale package index") {
		t.Fatalf("one mirror timing out was called a stale index:\n%v", err)
	}
}

// And an install that works still works.
func TestAnInstallThatSucceedsSaysNothing(t *testing.T) {
	run := func(context.Context, string, ...string) (string, error) { return "installed", nil }
	if err := (arch{}).InstallPackage(context.Background(), run, "dnsmasq"); err != nil {
		t.Fatalf("a successful install reported a failure: %v", err)
	}
}