Optimize /api/similar

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

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
 }
 
@@ -303,10 +308,6 @@ func cmdInit(fs *flag.FlagSet, args []string) error {
 		return err
 	}
 
-	if _, err := db.Exec(initializeSQL); err != nil {
-		return err
-	}
-
 	// XXX: There's technically no reason to keep images as symlinks,
 	// we might just keep absolute paths in the database as well.
 	if err := os.MkdirAll(
@@ -657,7 +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
 	}
 
@@ -684,7 +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
 	}
@@ -841,15 +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.
+	// If there's a dhash, there should also be thumbnail dimensions.
-	// In exchange, it's generic.
+	var rows *sql.Rows
-	//
+	common := `SELECT sha1, width * height, IFNULL(thumbw, 0), IFNULL(thumbh, 0)
-	// If there's a dhash, there should also be thumbnail dimensions,
+		FROM image WHERE sha1 <> ? AND `
-	// so not bothering with IFNULL on them.
+	if distance == 0 {
-	rows, err := db.Query(`
+		rows, err = db.Query(common+`dhash = ?`, sha1, dhash)
-		SELECT sha1, width * height, IFNULL(thumbw, 0), IFNULL(thumbh, 0)
+	} else {
-		FROM image WHERE sha1 <> ? AND dhash IS NOT NULL
+		// 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
 	}
@@ -2026,6 +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
@@ -2637,6 +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."},
@@ -2700,6 +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)
 		}