Vellum/internal/library/scan.go

package library

import (
	"context"
	"database/sql"
	"fmt"
	"io/fs"
	"log/slog"
	"os"
	"path/filepath"
	"strings"
	"syscall"
	"time"
)

// ScanResult summarises one scan pass.
type ScanResult struct {
	LibraryID int64    `json:"library_id"`
	Scanned   int      `json:"scanned"`
	Added     int      `json:"added"`
	Updated   int      `json:"updated"`
	Restored  int      `json:"restored"`
	Missing   int      `json:"missing"`
	Unchanged int      `json:"unchanged"`
	Duration  int64    `json:"duration_ms"`
	Errors    []string `json:"errors,omitempty"`
}

// candidate is a supported file found on disk.
type candidate struct {
	relPath string
	size    int64
	mtime   int64
	inode   int64
	ext     string
}

// knownFile is an existing row for this library.
type knownFile struct {
	itemID  int64
	fileID  int64
	size    int64
	mtime   int64
	missing bool
}

// Scan walks a library's root and reconciles it with the database.
//
// Files that changed are re-upserted; files that vanished are marked missing
// rather than deleted, so their progress survives a temporarily unavailable
// mount. A scan never fails because of a single unreadable file — it records
// the error and continues, because a partial library is better than none.
func Scan(ctx context.Context, db *sql.DB, lib Library, log *slog.Logger) (ScanResult, error) {
	start := time.Now()
	res := ScanResult{LibraryID: lib.ID}

	exts := extensionsFor(lib.Kind)
	if len(exts) == 0 {
		return res, fmt.Errorf("library %d: no extensions registered for kind %q", lib.ID, lib.Kind)
	}

	// 1. What do we already know?
	known, err := loadKnownFiles(ctx, db, lib.ID)
	if err != nil {
		return res, err
	}

	// 2. What is on disk?
	found, errs := walkRoot(lib.RootPath, exts)
	res.Errors = errs

	// 3. Reconcile in one transaction.
	tx, err := db.BeginTx(ctx, nil)
	if err != nil {
		return res, err
	}
	defer tx.Rollback() //nolint:errcheck

	now := time.Now().UTC().Format(time.RFC3339Nano)
	for rel, c := range found {
		res.Scanned++
		prev, exists := known[rel]

		switch {
		case exists && !prev.missing && prev.size == c.size && prev.mtime == c.mtime:
			res.Unchanged++
			continue

		case exists && prev.missing:
			res.Restored++
		case exists:
			res.Updated++
		default:
			res.Added++
		}

		itemID, err := upsertItem(ctx, tx, lib, rel, c)
		if err != nil {
			res.Errors = append(res.Errors, fmt.Sprintf("%s: %v", rel, err))
			continue
		}
		if err := upsertFile(ctx, tx, itemID, rel, c); err != nil {
			res.Errors = append(res.Errors, fmt.Sprintf("%s: %v", rel, err))
			continue
		}
	}

	// 4. Anything we knew about that is gone.
	for rel := range known {
		if _, ok := found[rel]; ok {
			continue
		}
		if err := markMissing(ctx, tx, lib.ID, rel, now); err != nil {
			res.Errors = append(res.Errors, fmt.Sprintf("%s: %v", rel, err))
			continue
		}
		res.Missing++
	}

	if err := tx.Commit(); err != nil {
		return res, fmt.Errorf("library: commit scan: %w", err)
	}

	res.Duration = time.Since(start).Milliseconds()
	log.Info("scan complete",
		"library", lib.Name, "kind", lib.Kind,
		"scanned", res.Scanned, "added", res.Added, "updated", res.Updated,
		"restored", res.Restored, "missing", res.Missing, "unchanged", res.Unchanged,
		"duration_ms", res.Duration, "errors", len(res.Errors))
	return res, nil
}

// walkRoot collects supported files under root, keyed by slash-separated
// path relative to root.
func walkRoot(root string, exts map[string]bool) (map[string]candidate, []string) {
	out := make(map[string]candidate)
	var errs []string

	err := filepath.WalkDir(root, func(path string, d fs.DirEntry, err error) error {
		if err != nil {
			errs = append(errs, fmt.Sprintf("%s: %v", path, err))
			// An unreadable directory should not abort the walk.
			if d != nil && d.IsDir() {
				return fs.SkipDir
			}
			return nil
		}

		name := d.Name()
		if d.IsDir() {
			if path != root && strings.HasPrefix(name, ".") {
				return fs.SkipDir
			}
			return nil
		}
		if strings.HasPrefix(name, ".") {
			return nil
		}

		ext := strings.ToLower(filepath.Ext(name))
		if !exts[ext] {
			return nil
		}

		info, err := d.Info()
		if err != nil {
			errs = append(errs, fmt.Sprintf("%s: %v", path, err))
			return nil
		}
		if !info.Mode().IsRegular() {
			return nil
		}

		rel, err := filepath.Rel(root, path)
		if err != nil {
			errs = append(errs, fmt.Sprintf("%s: %v", path, err))
			return nil
		}

		c := candidate{
			relPath: filepath.ToSlash(rel),
			size:    info.Size(),
			mtime:   info.ModTime().UnixNano(),
			ext:     strings.TrimPrefix(ext, "."),
		}
		if st, ok := info.Sys().(*syscall.Stat_t); ok {
			c.inode = int64(st.Ino)
		}
		out[c.relPath] = c
		return nil
	})
	if err != nil {
		errs = append(errs, fmt.Sprintf("%s: %v", root, err))
	}
	return out, errs
}

func loadKnownFiles(ctx context.Context, db *sql.DB, libraryID int64) (map[string]knownFile, error) {
	rows, err := db.QueryContext(ctx, `
		SELECT f.path, f.item_id, f.id, f.size, f.mtime, f.missing
		FROM media_files f
		JOIN media_items i ON i.id = f.item_id
		WHERE i.library_id = ?`, libraryID)
	if err != nil {
		return nil, fmt.Errorf("library: load known files: %w", err)
	}
	defer rows.Close()

	out := make(map[string]knownFile)
	for rows.Next() {
		var (
			absPath string
			kf      knownFile
			mtime   string
			missing int
		)
		if err := rows.Scan(&absPath, &kf.itemID, &kf.fileID, &kf.size, &mtime, &missing); err != nil {
			return nil, err
		}
		kf.mtime = parseUnixNano(mtime)
		kf.missing = missing == 1
		out[absPath] = kf
	}
	return out, rows.Err()
}

func upsertItem(ctx context.Context, tx *sql.Tx, lib Library, rel string, c candidate) (int64, error) {
	title := CleanTitle(rel)
	var id int64
	err := tx.QueryRowContext(ctx, `
		INSERT INTO media_items (library_id, kind, path, title, sort_title, missing)
		VALUES (?, ?, ?, ?, ?, 0)
		ON CONFLICT (library_id, path)
		DO UPDATE SET missing = 0
		RETURNING id`,
		lib.ID, lib.Kind, rel, title, strings.ToLower(title),
	).Scan(&id)
	if err != nil {
		return 0, fmt.Errorf("upsert item: %w", err)
	}
	return id, nil
}

func upsertFile(ctx context.Context, tx *sql.Tx, itemID int64, rel string, c candidate) error {
	_, err := tx.ExecContext(ctx, `
		INSERT INTO media_files (item_id, path, size, mtime, inode, container, missing)
		VALUES (?, ?, ?, ?, ?, ?, 0)
		ON CONFLICT (path)
		DO UPDATE SET item_id = excluded.item_id, size = excluded.size,
		              mtime = excluded.mtime, inode = excluded.inode,
		              container = excluded.container, missing = 0`,
		itemID, rel, c.size, fmt.Sprint(c.mtime), c.inode, c.ext)
	if err != nil {
		return fmt.Errorf("upsert file: %w", err)
	}
	return nil
}

func markMissing(ctx context.Context, tx *sql.Tx, libraryID int64, rel, now string) error {
	if _, err := tx.ExecContext(ctx,
		`UPDATE media_files SET missing = 1 WHERE path = ?`, rel); err != nil {
		return err
	}
	_, err := tx.ExecContext(ctx, `
		UPDATE media_items SET missing = 1
		WHERE library_id = ? AND path = ?`, libraryID, rel)
	return err
}

func parseUnixNano(s string) int64 {
	var n int64
	for i := 0; i < len(s); i++ {
		if s[i] < '0' || s[i] > '9' {
			return 0
		}
		n = n*10 + int64(s[i]-'0')
	}
	return n
}

// RootExists reports whether a library's root is currently reachable.
func RootExists(lib Library) bool {
	info, err := os.Stat(lib.RootPath)
	return err == nil && info.IsDir()
}