Stop scan cleanly on SIGINT or SIGTERM (closes #5)

A first SIGINT or SIGTERM cancels the scan. It commits the hashed
records still in its batch, with a context that is not cancelled for
that one write, and starts no other write or deletion; deletions need
a complete walk, so records under paths an interrupted walk never
reached are kept. A batch whose commit failed is now kept for that
final commit instead of dropped. The progress display is finished (a
bar stopped short is no longer filled up), `scan: interrupted after N
files` goes to stderr, and the exit code is 1. A second signal ends the
process at once. A SIGINT inherited as ignored stays ignored.

Model: opus-5-5

scan.go

@@ -11,6 +11,7 @@ import (
 	"io"
 	"io/fs"
 	"os"
+	"os/signal"
 	"path/filepath"
 	"slices"
 	"strings"
@@ -57,6 +58,10 @@ const sampleWindow = 1024 * 1024
 // and hash worker pools.
 const workQueueDepth = 1024
 
+// errInterrupted reports a scan stopped by SIGINT or SIGTERM. runScan
+// has already printed its line, so run prints nothing more.
+var errInterrupted = errors.New("scan interrupted")
+
 // fileRec carries one statted file between the scan phases. dev and
 // ino identify the underlying inode so hard-linked paths can share
 // one read; both are zero when the platform exposes no inode.
@@ -90,8 +95,10 @@ type fileMeta struct {
 // scan fails before it walks the filesystem or opens the database.
 // Errors are returned rather than exiting, so that the deferred close —
 // which takes the database out of WAL mode — always runs, and the lock
-// is released after it. Cancelling ctx unwinds the worker pools and
-// aborts the scan with the context's error.
+// is released after it. When ctx is cancelled, as by the SIGINT or
+// SIGTERM that interruptContext catches, the scan keeps what it has
+// hashed (see syncScan), prints how many files its walk reached, and
+// returns errInterrupted.
 func runScan(ctx context.Context, roots []string, workers int,
 	oneFS bool,
 ) error {
@@ -114,6 +121,12 @@ func runScan(ctx context.Context, roots []string, workers int,
 	defer func() { _ = lock.Close() }()
 
 	db, err := openScanDatabase(ctx, dbPath)
+	if err != nil && ctx.Err() != nil {
+		// Interrupted while opening; SQLite may report that with an
+		// error of its own rather than the context's.
+		return interrupted(0)
+	}
+
 	if err != nil {
 		return err
 	}
@@ -121,6 +134,10 @@ func runScan(ctx context.Context, roots []string, workers int,
 	defer closeScanDatabase(ctx, db, dbPath)
 
 	st, err := syncScan(ctx, db, roots, workers, oneFS)
+	if errors.Is(err, context.Canceled) {
+		return interrupted(st.walked)
+	}
+
 	if err != nil {
 		return fmt.Errorf("update database %s: %w", dbPath, err)
 	}
@@ -134,6 +151,34 @@ func runScan(ctx context.Context, roots []string, workers int,
 	return nil
 }
 
+// interruptContext returns a copy of ctx that the first SIGINT or
+// SIGTERM cancels; the scan command runs the scan under it. stop
+// releases the signals.
+func interruptContext(ctx context.Context) (context.Context, func()) {
+	// A SIGINT ignored from the start, as by a script's background job,
+	// stays ignored.
+	signals := []os.Signal{syscall.SIGTERM}
+	if !signal.Ignored(syscall.SIGINT) {
+		signals = append(signals, syscall.SIGINT)
+	}
+
+	ctx, stop := signal.NotifyContext(ctx, signals...)
+
+	// Stopping restores the default handling, so a second signal ends
+	// the process at once.
+	context.AfterFunc(ctx, stop)
+
+	return ctx, stop
+}
+
+// interrupted prints the line for a scan stopped by a signal after its
+// walk reached walked files, and returns errInterrupted.
+func interrupted(walked int) error {
+	fmt.Fprintf(os.Stderr, "scan: interrupted after %d files\n", walked)
+
+	return errInterrupted
+}
+
 // resolveRoots converts each PATH operand to an absolute, lexically
 // cleaned path (symlinks are not resolved) and verifies that it
 // exists. Database records are keyed by absolute path, so scan results
@@ -187,8 +232,9 @@ func pruneRoots(roots []string) []string {
 }
 
 // scanStats summarizes one scan's database synchronization for the
-// final stderr summary.
+// final stderr summary, or for the line an interrupted scan prints.
 type scanStats struct {
+	walked    int // files the walk reached
 	added     int
 	updated   int
 	removed   int
@@ -210,7 +256,30 @@ type scanState struct {
 	st        scanStats
 }
 
-// syncScan synchronizes the database with the filesystem under roots
+// syncScan synchronizes the database with the filesystem under roots;
+// see runPhases. When ctx is cancelled, as by an interrupt, it commits
+// the hashed records still waiting in the batch, starts no other write
+// or deletion, and returns the cancellation.
+func syncScan(ctx context.Context, db *sql.DB, roots []string,
+	workers int, oneFS bool,
+) (scanStats, error) {
+	s := &scanState{db: db}
+
+	err := s.runPhases(ctx, roots, workers, oneFS)
+	if err == nil || ctx.Err() == nil {
+		return s.st, err
+	}
+
+	// The one write made after the cancellation, so it cannot use ctx.
+	err = applyChanges(context.WithoutCancel(ctx), db, s.batch, nil, nil)
+	if err != nil {
+		return s.st, err
+	}
+
+	return s.st, ctx.Err()
+}
+
+// runPhases synchronizes the database with the filesystem under roots
 // in four sequential phases: walk (enumerate and stat every file,
 // building a complete size census), hash (read only the new or
 // changed — or previously unhashed — files whose size at least one
@@ -223,48 +292,41 @@ type scanState struct {
 // their content hash. Operands the walk cannot start from are dropped
 // first, so the records beneath them count as outside the roots unless
 // they lie under another root.
-func syncScan(ctx context.Context, db *sql.DB, roots []string,
+func (s *scanState) runPhases(ctx context.Context, roots []string,
 	workers int, oneFS bool,
-) (scanStats, error) {
-	s := &scanState{db: db}
-
+) error {
 	// Types are checked before pruning so that an operand under a
 	// dropped one is still scanned, not dropped as lying under it.
 	roots = pruneRoots(s.walkableRoots(roots))
 
 	err := s.loadIndex(ctx, roots)
 	if err != nil {
-		return s.st, err
+		return err
 	}
 
 	changed, unhashed := s.walkPhase(startWalk(ctx, roots, oneFS, workers))
 
 	// A cancelled walk stops early, so its size census covers only part
-	// of the roots, and every file it never reached looks vanished to
-	// the update phase. Defence in depth rather than the only barrier:
-	// that phase would today fail on its first BeginTx with the same
-	// cancelled context before deleting anything. But it is the barrier
-	// that survives a later decision to let an interrupted scan commit
-	// what it has, and it turns a confusing failure deep in the update
-	// phase into a clean abort at the phase boundary.
+	// of the roots, and every file it never reached would look vanished
+	// to the update phase. Stop before anything is written or deleted.
 	err = ctx.Err()
 	if err != nil {
-		return s.st, err
+		return err
 	}
 
 	s.partition(changed, unhashed)
 
 	err = s.hashPhase(ctx, workers)
 	if err != nil {
-		return s.st, err
+		return err
 	}
 
 	err = s.updatePhase(ctx)
 	if err != nil {
-		return s.st, err
+		return err
 	}
 
-	return s.st, s.contentPhase(ctx, workers)
+	return s.contentPhase(ctx, workers)
 }
 
 // walkableRoots returns the operands the walk can start from: regular
@@ -349,6 +411,7 @@ func (s *scanState) walkPhase(
 		}
 
 		s.sizes = append(s.sizes, ev.rec.size)
+		s.st.walked++
 
 		prog.increment()
 
@@ -552,16 +615,22 @@ func (s *scanState) recordRun(ctx context.Context, r hashResult) error {
 }
 
 // commitFullBatch commits the running batch once it holds
-// updateBatchSize records.
+// updateBatchSize records. A batch that fails to commit is kept: the
+// commit fails when the scan is interrupted, and syncScan then commits
+// the batch itself.
 func (s *scanState) commitFullBatch(ctx context.Context) error {
 	if len(s.batch) < updateBatchSize {
 		return nil
 	}
 
 	err := applyBatch(ctx, s.db, s.batch, nil, nil)
+	if err != nil {
+		return err
+	}
+
 	s.batch = s.batch[:0]
 
-	return err
+	return nil
 }
 
 // updatePhase writes the scan's tail under one progress display: the
@@ -1004,6 +1073,12 @@ func walkOneDir(ctx context.Context, job dirJob, oneFS bool,
 	var subs []dirJob
 
 	for _, e := range entries {
+		// A cancelled scan wants nothing more from this directory: stop
+		// rather than lstat the rest of a large one.
+		if ctx.Err() != nil {
+			return nil
+		}
+
 		p := filepath.Join(job.path, e.Name())
 
 		if e.IsDir() {