Optimize /api/similar

Previously, there was no way of removing images from the database.

.gitignore

@@ -0,0 +1,11 @@
+/gallery
+/initialize.go
+/public/mithril.js
+
+/gallery.cflags
+/gallery.config
+/gallery.creator
+/gallery.creator.user
+/gallery.cxxflags
+/gallery.files
+/gallery.includes

deeptagger/README.adoc

@@ -53,7 +53,7 @@ Tagging galleries
 The appropriate invocation depends on your machine, and the chosen model.
 Unless you have a powerful machine, or use a fast model, it may take forever.
 
- $ find "$GALLERY/images" -type f \
+ $ find "$GALLERY/images" -type l \
    | build/deeptagger --pipe -b 16 -t 0.5 \
      models/ml_caformer_m36_dec-5-97527.model \
    | sed 's|[^\t]*/||' \

deeptagger/bench.sh

@@ -28,11 +28,9 @@ run() {
 for model in models/*.model
 do
 	name=$(sed -n 's/^name=//p' "$model")
-	run ""     1 "$model" "$@"
-	run ""     4 "$model" "$@"
-	run ""    16 "$model" "$@"
-
-	run --cpu  1 "$model" "$@"
-	run --cpu  4 "$model" "$@"
-	run --cpu 16 "$model" "$@"
+	for batch in 1 4 16
+	do
+		run ""    $batch "$model" "$@"
+		run --cpu $batch "$model" "$@"
+	done
 done

deeptagger/deeptagger.cpp

@@ -315,6 +315,7 @@ run(std::vector<Magick::Image> &images, const Config &config,
 			}
 		}
 	}
+	fflush(stdout);
 }
 
 // - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

initialize.sql

@@ -23,6 +23,7 @@ CREATE TABLE IF NOT EXISTS node(
 ) STRICT;
 
 CREATE INDEX IF NOT EXISTS node__sha1 ON node(sha1);
+CREATE INDEX IF NOT EXISTS node__parent ON node(parent);
 CREATE UNIQUE INDEX IF NOT EXISTS node__parent_name
 ON node(IFNULL(parent, 0), name);
 

main.go

@@ -94,10 +94,15 @@ func init() {
 }
 
 func openDB(directory string) error {
+	galleryDirectory = directory
+
 	var err error
 	db, err = sql.Open("sqlite3_custom", "file:"+filepath.Join(directory,
 		nameOfDB+"?_foreign_keys=1&_busy_timeout=1000"))
-	galleryDirectory = directory
+	if err != nil {
+		return err
+	}
+	_, err = db.Exec(initializeSQL)
 	return err
 }
 
@@ -296,11 +301,10 @@ func cmdInit(fs *flag.FlagSet, args []string) error {
 	if fs.NArg() != 1 {
 		return errWrongUsage
 	}
-	if err := openDB(fs.Arg(0)); err != nil {
+	if err := os.MkdirAll(fs.Arg(0), 0755); err != nil {
 		return err
 	}
-
-	if _, err := db.Exec(initializeSQL); err != nil {
+	if err := openDB(fs.Arg(0)); err != nil {
 		return err
 	}
 
@@ -654,7 +658,9 @@ func getOrphanReplacement(webPath string) (*webOrphanImage, error) {
 	}
 
 	parent, err := idForDirectoryPath(tx, path[:len(path)-1], false)
-	if err != nil {
+	if errors.Is(err, sql.ErrNoRows) {
+		return nil, nil
+	} else if err != nil {
 		return nil, err
 	}
 
@@ -681,7 +687,8 @@ func getOrphans() (result []webOrphan, err error) {
 		FROM orphan AS o
 		JOIN image AS i ON o.sha1 = i.sha1
 		LEFT JOIN tag_assignment AS ta ON o.sha1 = ta.sha1
-		GROUP BY o.sha1`)
+		GROUP BY o.sha1
+		ORDER BY path`)
 	if err != nil {
 		return nil, err
 	}
@@ -838,15 +845,17 @@ type webSimilarImage struct {
 
 func getSimilar(sha1 string, dhash int64, pixels int64, distance int) (
 	result []webSimilarImage, err error) {
-	// For distance ∈ {0, 1}, this query is quite inefficient.
-	// In exchange, it's generic.
-	//
-	// If there's a dhash, there should also be thumbnail dimensions,
-	// so not bothering with IFNULL on them.
-	rows, err := db.Query(`
-		SELECT sha1, width * height, IFNULL(thumbw, 0), IFNULL(thumbh, 0)
-		FROM image WHERE sha1 <> ? AND dhash IS NOT NULL
-		AND hamming(dhash, ?) = ?`, sha1, dhash, distance)
+	// If there's a dhash, there should also be thumbnail dimensions.
+	var rows *sql.Rows
+	common := `SELECT sha1, width * height, IFNULL(thumbw, 0), IFNULL(thumbh, 0)
+		FROM image WHERE sha1 <> ? AND `
+	if distance == 0 {
+		rows, err = db.Query(common+`dhash = ?`, sha1, dhash)
+	} else {
+		// This is generic, but quite inefficient for distance ∈ {0, 1}.
+		rows, err = db.Query(common+`dhash IS NOT NULL
+			AND hamming(dhash, ?) = ?`, sha1, dhash, distance)
+	}
 	if err != nil {
 		return nil, err
 	}
@@ -1283,6 +1292,9 @@ type syncContext struct {
 	stmtDisposeSub *sql.Stmt
 	stmtDisposeAll *sql.Stmt
 
+	// exclude specifies filesystem paths that should be seen as missing.
+	exclude *regexp.Regexp
+
 	// linked tracks which image hashes we've checked so far in the run.
 	linked map[string]struct{}
 }
@@ -1691,6 +1703,12 @@ func syncDirectory(c *syncContext, dbParent int64, fsPath string) error {
 		fs = nil
 	}
 
+	if c.exclude != nil {
+		fs = slices.DeleteFunc(fs, func(f syncFile) bool {
+			return c.exclude.MatchString(filepath.Join(fsPath, f.fsName))
+		})
+	}
+
 	// Convert differences to a form more convenient for processing.
 	iDB, iFS, pairs := 0, 0, []syncPair{}
 	for iDB < len(db) && iFS < len(fs) {
@@ -1866,9 +1884,21 @@ const disposeCTE = `WITH RECURSIVE
 		HAVING count = total
 	)`
 
+type excludeRE struct{ re *regexp.Regexp }
+
+func (re *excludeRE) String() string { return fmt.Sprintf("%v", re.re) }
+
+func (re *excludeRE) Set(value string) error {
+	var err error
+	re.re, err = regexp.Compile(value)
+	return err
+}
+
 // cmdSync ensures the given (sub)roots are accurately reflected
 // in the database.
 func cmdSync(fs *flag.FlagSet, args []string) error {
+	var exclude excludeRE
+	fs.Var(&exclude, "exclude", "exclude paths matching regular expression")
 	fullpaths := fs.Bool("fullpaths", false, "don't basename arguments")
 	if err := fs.Parse(args); err != nil {
 		return err
@@ -1906,7 +1936,7 @@ func cmdSync(fs *flag.FlagSet, args []string) error {
 	}
 
 	c := syncContext{ctx: ctx, tx: tx, pb: newProgressBar(-1),
-		linked: make(map[string]struct{})}
+		exclude: exclude.re, linked: make(map[string]struct{})}
 	defer c.pb.Stop()
 
 	if c.stmtOrphan, err = c.tx.Prepare(disposeCTE + `
@@ -2002,6 +2032,88 @@ func cmdRemove(fs *flag.FlagSet, args []string) error {
 	return tx.Commit()
 }
 
+// --- Forgetting --------------------------------------------------------------
+
+// cmdForget is for purging orphaned images from the database.
+func cmdForget(fs *flag.FlagSet, args []string) error {
+	if err := fs.Parse(args); err != nil {
+		return err
+	}
+	if fs.NArg() < 2 {
+		return errWrongUsage
+	}
+	if err := openDB(fs.Arg(0)); err != nil {
+		return err
+	}
+
+	tx, err := db.Begin()
+	if err != nil {
+		return err
+	}
+	defer tx.Rollback()
+
+	// Creating a temporary database seems justifiable in this case.
+	_, err = tx.Exec(
+		`CREATE TEMPORARY TABLE forgotten (sha1 TEXT PRIMARY KEY)`)
+	if err != nil {
+		return err
+	}
+	stmt, err := tx.Prepare(`INSERT INTO forgotten (sha1) VALUES (?)`)
+	if err != nil {
+		return err
+	}
+	defer stmt.Close()
+	for _, sha1 := range fs.Args()[1:] {
+		if _, err := stmt.Exec(sha1); err != nil {
+			return err
+		}
+	}
+
+	rows, err := tx.Query(`DELETE FROM forgotten
+		WHERE sha1 IN (SELECT sha1 FROM node)
+		OR sha1 NOT IN (SELECT sha1 FROM image)
+		RETURNING sha1`)
+	if err != nil {
+		return err
+	}
+	defer rows.Close()
+	for rows.Next() {
+		var sha1 string
+		if err := rows.Scan(&sha1); err != nil {
+			return err
+		}
+		log.Printf("not an orphan or not known at all: %s", sha1)
+	}
+	if _, err = tx.Exec(`
+		DELETE FROM tag_assignment WHERE sha1 IN (SELECT sha1 FROM forgotten);
+		DELETE FROM orphan WHERE sha1 IN (SELECT sha1 FROM forgotten);
+		DELETE FROM image WHERE sha1 IN (SELECT sha1 FROM forgotten);
+	 `); err != nil {
+		return err
+	}
+
+	rows, err = tx.Query(`SELECT sha1 FROM forgotten`)
+	if err != nil {
+		return err
+	}
+	defer rows.Close()
+	for rows.Next() {
+		var sha1 string
+		if err := rows.Scan(&sha1); err != nil {
+			return err
+		}
+		if err := os.Remove(imagePath(sha1)); err != nil &&
+			!os.IsNotExist(err) {
+			log.Printf("%s", err)
+		}
+		if err := os.Remove(thumbPath(sha1)); err != nil &&
+			!os.IsNotExist(err) {
+			log.Printf("%s", err)
+		}
+	}
+	return tx.Commit()
+}
+
 // --- Tagging -----------------------------------------------------------------
 
 // cmdTag mass imports tags from data passed on stdin as a TSV
@@ -2124,36 +2236,54 @@ func collectFileListing(root string) (paths []string, err error) {
 	return
 }
 
-func checkFiles(root, suffix string, hashes []string) (bool, []string, error) {
+func checkFiles(gc bool,
+	root, suffix string, hashes []string) (bool, []string, error) {
 	db := hashesToFileListing(root, suffix, hashes)
 	fs, err := collectFileListing(root)
 	if err != nil {
 		return false, nil, err
 	}
 
-	iDB, iFS, ok, intersection := 0, 0, true, []string{}
+	// There are two legitimate cases of FS-only database files:
+	//  1. There is no code to unlink images at all
+	//     (although sync should create orphan records for everything).
+	//  2. thumbnail: failures may result in an unreferenced garbage image.
+	ok := true
+	onlyDB := func(path string) {
+		ok = false
+		fmt.Printf("only in DB: %s\n", path)
+	}
+	onlyFS := func(path string) {
+		if !gc {
+			ok = false
+			fmt.Printf("only in FS: %s\n", path)
+		} else if err := os.Remove(path); err != nil {
+			ok = false
+			fmt.Printf("only in FS (removing failed): %s: %s\n", path, err)
+		} else {
+			fmt.Printf("only in FS (removing): %s\n", path)
+		}
+	}
+
+	iDB, iFS, intersection := 0, 0, []string{}
 	for iDB < len(db) && iFS < len(fs) {
 		if db[iDB] == fs[iFS] {
 			intersection = append(intersection, db[iDB])
 			iDB++
 			iFS++
 		} else if db[iDB] < fs[iFS] {
-			ok = false
-			fmt.Printf("only in DB: %s\n", db[iDB])
+			onlyDB(db[iDB])
 			iDB++
 		} else {
-			ok = false
-			fmt.Printf("only in FS: %s\n", fs[iFS])
+			onlyFS(fs[iFS])
 			iFS++
 		}
 	}
 	for _, path := range db[iDB:] {
-		ok = false
-		fmt.Printf("only in DB: %s\n", path)
+		onlyDB(path)
 	}
 	for _, path := range fs[iFS:] {
-		ok = false
-		fmt.Printf("only in FS: %s\n", path)
+		onlyFS(path)
 	}
 	return ok, intersection, nil
 }
@@ -2201,6 +2331,7 @@ func checkHashes(paths []string) (bool, error) {
 // cmdCheck carries out various database consistency checks.
 func cmdCheck(fs *flag.FlagSet, args []string) error {
 	full := fs.Bool("full", false, "verify image hashes")
+	gc := fs.Bool("gc", false, "garbage collect database files")
 	if err := fs.Parse(args); err != nil {
 		return err
 	}
@@ -2237,13 +2368,13 @@ func cmdCheck(fs *flag.FlagSet, args []string) error {
 
 	// This somewhat duplicates {image,thumb}Path().
 	log.Println("checking SQL against filesystem")
-	okImages, intersection, err := checkFiles(
+	okImages, intersection, err := checkFiles(*gc,
 		filepath.Join(galleryDirectory, nameOfImageRoot), "", allSHA1)
 	if err != nil {
 		return err
 	}
 
-	okThumbs, _, err := checkFiles(
+	okThumbs, _, err := checkFiles(*gc,
 		filepath.Join(galleryDirectory, nameOfThumbRoot), ".webp", thumbSHA1)
 	if err != nil {
 		return err
@@ -2252,11 +2383,11 @@ func cmdCheck(fs *flag.FlagSet, args []string) error {
 		ok = false
 	}
 
-	log.Println("checking for dead symlinks")
+	log.Println("checking for dead symlinks (should become orphans on sync)")
 	for _, path := range intersection {
 		if _, err := os.Stat(path); err != nil {
 			ok = false
-			fmt.Printf("%s: %s\n", path, err)
+			fmt.Printf("%s: %s\n", path, err.(*os.PathError).Unwrap())
 		}
 	}
 
@@ -2594,6 +2725,7 @@ var commands = map[string]struct {
 	"tag":       {cmdTag, "GD SPACE [DESCRIPTION]", "Import tags."},
 	"sync":      {cmdSync, "GD ROOT...", "Synchronise with the filesystem."},
 	"remove":    {cmdRemove, "GD PATH...", "Remove database subtrees."},
+	"forget":    {cmdForget, "GD SHA1...", "Dispose of orphans."},
 	"check":     {cmdCheck, "GD", "Run consistency checks."},
 	"thumbnail": {cmdThumbnail, "GD [SHA1...]", "Generate thumbnails."},
 	"dhash":     {cmdDhash, "GD [SHA1...]", "Compute perceptual hashes."},
@@ -2657,6 +2789,9 @@ func main() {
 	// Note that the database object has a closing finalizer,
 	// we just additionally print any errors coming from there.
 	if db != nil {
+		if _, err := db.Exec(`PRAGMA optimize`); err != nil {
+			log.Println(err)
+		}
 		if err := db.Close(); err != nil {
 			log.Println(err)
 		}

test.sh

@@ -16,6 +16,9 @@ sha1duplicate=$sha1
 cp $input/Test/dhash.png \
 	$input/Test/multiple-paths.png
 
+gen -seed 15 -size 256x256 plasma:fractal \
+	$input/Test/excluded.png
+
 gen -seed 20 -size 160x128 plasma:fractal \
 	-bordercolor transparent -border 64 \
 	$input/Test/transparent-wide.png
@@ -36,7 +39,7 @@ gen $input/Test/animation-small.gif \
 	$input/Test/video.mp4
 
 ./gallery init $target
-./gallery sync $target $input "$@"
+./gallery sync -exclude '/excluded[.]' $target $input "$@"
 ./gallery thumbnail $target
 ./gallery dhash $target
 ./gallery tag $target test "Test space" <<-END
@@ -47,7 +50,7 @@ END
 
 # TODO: Test all the various possible sync transitions.
 mv $input/Test $input/Plasma
-./gallery sync $target $input
+./gallery sync -exclude '/excluded[.]' $target $input
 
 ./gallery web $target :8080 &
 web=$!