From 57efa64f18deea5f0629297dfa2a22a64985e60f Mon Sep 17 00:00:00 2001
From: sneak <sneak@sneak.berlin>
Date: Sat, 25 Jul 2026 14:28:11 +0700
Subject: [PATCH] Show progress while loading the record index

On a database with tens of millions of records, indexing the existing
rows before the walk takes real single-core time with no output,
which is indistinguishable from a hang. Give the load its own
spinner, and render every phase display the moment the phase starts
instead of waiting for its first completed item.
---
 README.md   | 8 +++++---
 progress.go | 3 +++
 scan.go     | 7 +++++++
 3 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 1ac1476..d7bd657 100644
--- a/README.md
+++ b/README.md
@@ -395,9 +395,11 @@ all dupe rows) in human units.
 Use the progress-bar library for all scan progress; rendering in the
 style of `pv` is the model. All progress goes to stderr.
 
-Each phase gets its own display. The walk has no known total while
-running: show a live file count, rate, and elapsed time
-(spinner-style, no percentage or ETA). The hash and update phases
+Each phase gets its own display, rendered the moment the phase
+starts — a scan must never look hung. Loading the existing-record
+index (`load`) and the walk have no known totals while running: show
+a live count, rate, and elapsed time (spinner-style, no percentage or
+ETA). The hash and update phases
 have exact totals — only files that actually need hashing appear in
 the hash total, so its ETA is meaningful. Required elements for the
 bars with known totals:
diff --git a/progress.go b/progress.go
index a168bf5..ecb0585 100644
--- a/progress.go
+++ b/progress.go
@@ -65,6 +65,9 @@ func newProgress(label string, total int64) *progress {
 		progressbar.OptionSetItsString("files"),
 		progressbar.OptionSetElapsedTime(true),
 		progressbar.OptionThrottle(barThrottle),
+		// Render at zero immediately: a phase must be visible the
+		// moment it starts, even before its first item completes.
+		progressbar.OptionSetRenderBlankState(true),
 	}
 	if total >= 0 {
 		opts = append(opts,
diff --git a/scan.go b/scan.go
index e618351..4e74278 100644
--- a/scan.go
+++ b/scan.go
@@ -186,10 +186,17 @@ func syncScan(db *sql.DB, roots []string, workers int,
 // can be recognized as a possible duplicate of a tree scanned
 // separately into the same database.
 func (s *scanState) loadIndex(roots []string) error {
+	// Indexing tens of millions of records takes real time; without a
+	// display the scan looks hung before the walk begins.
+	prog := newProgress("load", -1)
+	defer prog.finish()
+
 	s.existing = make(map[string]fileMeta)
 
 	return loadFileMeta(s.db,
 		func(path string, size, mtime int64, hashed bool) {
+			prog.increment()
+
 			if underAnyRoot(path, roots) {
 				s.existing[path] = fileMeta{
 					size: size, mtime: mtime, hashed: hashed,