feat(ingestion): symlink tripwire for the Syncthing-shared brain dir (#157) (#159)

Co-authored-by: Mathias <mthbqv@gmail.com>

ingestion/internal/symlinkguard/symlinkguard_test.go

@@ -0,0 +1,189 @@
+package symlinkguard
+
+import (
+	"context"
+	"errors"
+	"os"
+	"path/filepath"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// hyperguild#157: the brain dir is a Syncthing sendreceive folder and
+// Syncthing syncs symlinks; several readers follow them out of the brain.
+// Until every reader goes through an os.Root, a symlink anywhere in the brain,
+// or a directory the scan cannot read (which could hide one), is an incident.
+
+func TestScanReportsSymlinksAtEveryDepthIncludingNestedGit(t *testing.T) {
+	brain := t.TempDir()
+	outside := t.TempDir()
+	require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki", "w", "facts", ".git"), 0o755))
+	require.NoError(t, os.MkdirAll(filepath.Join(brain, ".git", "objects"), 0o755))
+	require.NoError(t, os.Symlink(filepath.Join(outside, "f"), filepath.Join(brain, "wiki", "w", "facts", "leak.md")))
+	require.NoError(t, os.Symlink(outside, filepath.Join(brain, "wiki", "dirlink")))
+	// PR #159 review: only the ROOT .git is skipped; a nested .git is not
+	// special to the brain readers, which walk into it.
+	require.NoError(t, os.Symlink(filepath.Join(outside, "g"), filepath.Join(brain, "wiki", "w", "facts", ".git", "leak.md")))
+	require.NoError(t, os.Symlink(outside, filepath.Join(brain, ".git", "objects", "alt")))
+
+	r, err := Scan(brain)
+	require.NoError(t, err)
+	assert.ElementsMatch(t, []string{"wiki/w/facts/leak.md", "wiki/dirlink", "wiki/w/facts/.git/leak.md"}, r.Symlinks)
+	assert.Empty(t, r.Unreadable)
+}
+
+// PR #159 review: WalkDir stopped at the first unreadable directory and the
+// startup check passed, while search (which keeps walking) served a planted
+// symlink. Scan now records the unreadable dir and keeps going.
+func TestScanReportsUnreadableDirsAndKeepsWalkingPastThem(t *testing.T) {
+	if os.Geteuid() == 0 {
+		t.Skip("root reads mode-000 directories")
+	}
+	brain := t.TempDir()
+	locked := filepath.Join(brain, "aaa")
+	require.NoError(t, os.MkdirAll(locked, 0o755))
+	require.NoError(t, os.Chmod(locked, 0o000))
+	t.Cleanup(func() { _ = os.Chmod(locked, 0o755) })
+	require.NoError(t, os.Symlink(t.TempDir(), filepath.Join(brain, "zzz-planted")))
+
+	r, err := Scan(brain)
+	require.NoError(t, err)
+	assert.Equal(t, []string{"aaa"}, r.Unreadable)
+	assert.Equal(t, []string{"zzz-planted"}, r.Symlinks, "the walk continues past the unreadable dir")
+}
+
+func TestScanResolvesASymlinkedRootAndReportsSymlinkedEntriesInsideIt(t *testing.T) {
+	real := t.TempDir()
+	link := filepath.Join(t.TempDir(), "brain")
+	require.NoError(t, os.Symlink(real, link))
+	require.NoError(t, os.WriteFile(filepath.Join(real, "n.md"), []byte("x"), 0o644))
+	require.NoError(t, os.Symlink(t.TempDir(), filepath.Join(real, "inner")))
+	r, err := Scan(link)
+	require.NoError(t, err)
+	assert.Equal(t, []string{"inner"}, r.Symlinks)
+}
+
+func TestScanOfAMissingRootIsErrNotExist(t *testing.T) {
+	_, err := Scan(filepath.Join(t.TempDir(), "nope"))
+	assert.True(t, errors.Is(err, os.ErrNotExist), "got %v", err)
+}
+
+type recNotifier struct {
+	mu   sync.Mutex
+	msgs []string
+	fail int // fail the first N calls
+}
+
+func (r *recNotifier) Notify(_ context.Context, m string) error {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	r.msgs = append(r.msgs, m)
+	if r.fail > 0 {
+		r.fail--
+		return errors.New("ntfy down")
+	}
+	return nil
+}
+
+func (r *recNotifier) count() int { r.mu.Lock(); defer r.mu.Unlock(); return len(r.msgs) }
+
+func TestWatchNotifiesOncePerDistinctSetAndAgainForANewSet(t *testing.T) {
+	brain := t.TempDir()
+	n := &recNotifier{}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	go Watch(ctx, brain, 10*time.Millisecond, n)
+
+	time.Sleep(50 * time.Millisecond)
+	assert.Zero(t, n.count(), "a clean brain raises nothing")
+	require.NoError(t, os.Symlink(t.TempDir(), filepath.Join(brain, "first")))
+	require.Eventually(t, func() bool { return n.count() == 1 }, 2*time.Second, 10*time.Millisecond)
+	time.Sleep(60 * time.Millisecond)
+	assert.Equal(t, 1, n.count(), "the same set is reported once, not every tick")
+	require.NoError(t, os.Symlink(t.TempDir(), filepath.Join(brain, "second")))
+	require.Eventually(t, func() bool { return n.count() == 2 }, 2*time.Second, 10*time.Millisecond)
+}
+
+// PR #159 review: last was recorded before Notify, so an alert lost to an
+// ntfy outage was never retried while the symlink stayed.
+func TestWatchRetriesAnAlertThatFailedToSend(t *testing.T) {
+	brain := t.TempDir()
+	require.NoError(t, os.Symlink(t.TempDir(), filepath.Join(brain, "planted")))
+	n := &recNotifier{fail: 2}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	go Watch(ctx, brain, 10*time.Millisecond, n)
+	require.Eventually(t, func() bool { return n.count() == 3 }, 2*time.Second, 10*time.Millisecond)
+	time.Sleep(60 * time.Millisecond)
+	assert.Equal(t, 3, n.count(), "after one successful send, no more")
+}
+
+func TestWatchAlertsOnAnUnreadableDir(t *testing.T) {
+	if os.Geteuid() == 0 {
+		t.Skip("root reads mode-000 directories")
+	}
+	brain := t.TempDir()
+	locked := filepath.Join(brain, "locked")
+	require.NoError(t, os.MkdirAll(locked, 0o755))
+	require.NoError(t, os.Chmod(locked, 0o000))
+	t.Cleanup(func() { _ = os.Chmod(locked, 0o755) })
+	n := &recNotifier{}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	go Watch(ctx, brain, 10*time.Millisecond, n)
+	require.Eventually(t, func() bool { return n.count() == 1 }, 2*time.Second, 10*time.Millisecond)
+	assert.Contains(t, n.msgs[0], "locked")
+}
+
+// PR #159 review: a non-positive interval panicked time.NewTicker inside the
+// goroutine and crashlooped the server.
+func TestWatchToleratesANonPositiveInterval(t *testing.T) {
+	brain := t.TempDir()
+	ctx, cancel := context.WithCancel(context.Background())
+	done := make(chan struct{})
+	go func() { Watch(ctx, brain, 0, nil); close(done) }()
+	cancel()
+	select {
+	case <-done:
+	case <-time.After(2 * time.Second):
+		t.Fatal("Watch did not return on cancel")
+	}
+}
+
+// PR #159 round 2: a brain root that can be entered but not listed (mode
+// 0100) made WalkDir fail at the root; the error was discarded and Scan
+// reported clean, while search (which goes straight into wiki/) still served
+// a planted symlink. A root that cannot be listed is now an error.
+func TestScanOfAnUnlistableRootIsAnError(t *testing.T) {
+	if os.Geteuid() == 0 {
+		t.Skip("root lists mode-0100 directories")
+	}
+	brain := t.TempDir()
+	require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki"), 0o755))
+	require.NoError(t, os.Symlink(t.TempDir(), filepath.Join(brain, "wiki", "leak.md")))
+	require.NoError(t, os.Chmod(brain, 0o100))
+	t.Cleanup(func() { _ = os.Chmod(brain, 0o755) })
+	_, err := Scan(brain)
+	require.Error(t, err)
+	assert.False(t, errors.Is(err, os.ErrNotExist), "an unlistable root is not a missing root")
+}
+
+// The same set that disappears and comes back is reported again.
+func TestWatchReportsASetAgainAfterItWasCleared(t *testing.T) {
+	brain := t.TempDir()
+	link := filepath.Join(brain, "planted")
+	n := &recNotifier{}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	go Watch(ctx, brain, 10*time.Millisecond, n)
+	require.NoError(t, os.Symlink(t.TempDir(), link))
+	require.Eventually(t, func() bool { return n.count() == 1 }, 2*time.Second, 10*time.Millisecond)
+	require.NoError(t, os.Remove(link))
+	time.Sleep(60 * time.Millisecond)
+	require.NoError(t, os.Symlink(t.TempDir(), link))
+	require.Eventually(t, func() bool { return n.count() == 2 }, 2*time.Second, 10*time.Millisecond)
+}