scanner: fix library isolation, file mtime, force rescan, and deletion handling

Fix 1 - File modification time for created_at:
- Get file.ModTime() in processMediaFile and pass to CreateMediaItem
- Modified SQL INSERT to include created_at column

Fix 2 - Force rescan UPDATE instead of DELETE+INSERT:
- Changed force rescan logic to call updateMediaItem instead of delete + create
- Preserves created_at timestamp on force rescan

Fix 3 - GetMediaItemByFilePath filters by library_id:
- Added library_id to WHERE clause in SQL query
- Created GetMediaItemByFilePathAnyLibrary for cross-library lookups (KOReader)
- Added SetLibraryID method to MediaScanner
- Updated handler to call SetLibraryID for watch mode

Fix 4 - File deletion handling with persistent logging:
- Added fsnotify.Remove handler in WatchChanges
- Added orphan cleanup in ScanFolders after scan completes
- Created scanner_logger.go with daily log rotation (7 days)
- Logs to /app/logs/scanner-deletes-YYYY-MM-DD.log and scanner-errors-YYYY-MM-DD.log
- Individual deletes with enhanced safety logging

Note: Integration tests can now safely scan /app/uploads because
GetMediaItemByFilePath now filters by library_id, preventing
cross-library interference.
This commit is contained in:
2026-02-26 16:39:42 -05:00
parent 56c80fbe14
commit d802236874
14 changed files with 1432 additions and 83 deletions
+95 -32
View File
@@ -549,39 +549,40 @@ func (q *Queries) CreateMediaHighlight(ctx context.Context, arg CreateMediaHighl
}
const CreateMediaItem = `-- name: CreateMediaItem :one
INSERT INTO media_items (library_id, title, author, isbn, description, file_path, file_size, mime_type, cover_image_path, series, series_number, tags, tags_search, asin, date_published, publisher, contributors, contributors_search, language, edition, page_count, genre, copyright_year, goodreads_id, openlibrary_id, google_books_id, added_by_admin_id)
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12, $13, $14, $15, $16, $17, $18, $19, $20, $21, $22, $23, $24, $25, $26, $27)
INSERT INTO media_items (library_id, title, author, isbn, description, file_path, file_size, mime_type, cover_image_path, series, series_number, tags, tags_search, asin, date_published, publisher, contributors, contributors_search, language, edition, page_count, genre, copyright_year, goodreads_id, openlibrary_id, google_books_id, added_by_admin_id, created_at)
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12, $13, $14, $15, $16, $17, $18, $19, $20, $21, $22, $23, $24, $25, $26, $27, $28)
RETURNING id, library_id, title, author, isbn, description, file_path, file_size, mime_type, cover_image_path, series, series_number, tags, asin, date_published, publisher, contributors, language, edition, page_count, genre, copyright_year, goodreads_id, openlibrary_id, google_books_id, added_by_admin_id, created_at, updated_at, format_group, format_mimetype, is_reflowable, has_fixed_layout, total_characters, chapter_count, entitlement_id, revision_number, kobo_content_id, kobo_metadata, tags_search, contributors_search, file_sha256, opf_identifier, opf_uuid, hash_confidence
`
type CreateMediaItemParams struct {
LibraryID pgtype.UUID `db:"library_id" json:"library_id"`
Title string `db:"title" json:"title"`
Author pgtype.Text `db:"author" json:"author"`
Isbn pgtype.Text `db:"isbn" json:"isbn"`
Description pgtype.Text `db:"description" json:"description"`
FilePath string `db:"file_path" json:"file_path"`
FileSize pgtype.Int8 `db:"file_size" json:"file_size"`
MimeType pgtype.Text `db:"mime_type" json:"mime_type"`
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
Series pgtype.Text `db:"series" json:"series"`
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
Tags []string `db:"tags" json:"tags"`
TagsSearch []string `db:"tags_search" json:"tags_search"`
Asin pgtype.Text `db:"asin" json:"asin"`
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
Publisher pgtype.Text `db:"publisher" json:"publisher"`
Contributors []string `db:"contributors" json:"contributors"`
ContributorsSearch []string `db:"contributors_search" json:"contributors_search"`
Language pgtype.Text `db:"language" json:"language"`
Edition pgtype.Text `db:"edition" json:"edition"`
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
Genre pgtype.Text `db:"genre" json:"genre"`
CopyrightYear pgtype.Int4 `db:"copyright_year" json:"copyright_year"`
GoodreadsID pgtype.Text `db:"goodreads_id" json:"goodreads_id"`
OpenlibraryID pgtype.Text `db:"openlibrary_id" json:"openlibrary_id"`
GoogleBooksID pgtype.Text `db:"google_books_id" json:"google_books_id"`
AddedByAdminID pgtype.UUID `db:"added_by_admin_id" json:"added_by_admin_id"`
LibraryID pgtype.UUID `db:"library_id" json:"library_id"`
Title string `db:"title" json:"title"`
Author pgtype.Text `db:"author" json:"author"`
Isbn pgtype.Text `db:"isbn" json:"isbn"`
Description pgtype.Text `db:"description" json:"description"`
FilePath string `db:"file_path" json:"file_path"`
FileSize pgtype.Int8 `db:"file_size" json:"file_size"`
MimeType pgtype.Text `db:"mime_type" json:"mime_type"`
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
Series pgtype.Text `db:"series" json:"series"`
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
Tags []string `db:"tags" json:"tags"`
TagsSearch []string `db:"tags_search" json:"tags_search"`
Asin pgtype.Text `db:"asin" json:"asin"`
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
Publisher pgtype.Text `db:"publisher" json:"publisher"`
Contributors []string `db:"contributors" json:"contributors"`
ContributorsSearch []string `db:"contributors_search" json:"contributors_search"`
Language pgtype.Text `db:"language" json:"language"`
Edition pgtype.Text `db:"edition" json:"edition"`
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
Genre pgtype.Text `db:"genre" json:"genre"`
CopyrightYear pgtype.Int4 `db:"copyright_year" json:"copyright_year"`
GoodreadsID pgtype.Text `db:"goodreads_id" json:"goodreads_id"`
OpenlibraryID pgtype.Text `db:"openlibrary_id" json:"openlibrary_id"`
GoogleBooksID pgtype.Text `db:"google_books_id" json:"google_books_id"`
AddedByAdminID pgtype.UUID `db:"added_by_admin_id" json:"added_by_admin_id"`
CreatedAt pgtype.Timestamptz `db:"created_at" json:"created_at"`
}
// Media Items queries
@@ -614,6 +615,7 @@ func (q *Queries) CreateMediaItem(ctx context.Context, arg CreateMediaItemParams
arg.OpenlibraryID,
arg.GoogleBooksID,
arg.AddedByAdminID,
arg.CreatedAt,
)
var i MediaItems
err := row.Scan(
@@ -3250,11 +3252,72 @@ func (q *Queries) GetMediaItem(ctx context.Context, id pgtype.UUID) (MediaItems,
}
const GetMediaItemByFilePath = `-- name: GetMediaItemByFilePath :one
SELECT id, library_id, title, author, isbn, description, file_path, file_size, mime_type, cover_image_path, series, series_number, tags, asin, date_published, publisher, contributors, language, edition, page_count, genre, copyright_year, goodreads_id, openlibrary_id, google_books_id, added_by_admin_id, created_at, updated_at, format_group, format_mimetype, is_reflowable, has_fixed_layout, total_characters, chapter_count, entitlement_id, revision_number, kobo_content_id, kobo_metadata, tags_search, contributors_search, file_sha256, opf_identifier, opf_uuid, hash_confidence FROM media_items WHERE file_path = $1
SELECT id, library_id, title, author, isbn, description, file_path, file_size, mime_type, cover_image_path, series, series_number, tags, asin, date_published, publisher, contributors, language, edition, page_count, genre, copyright_year, goodreads_id, openlibrary_id, google_books_id, added_by_admin_id, created_at, updated_at, format_group, format_mimetype, is_reflowable, has_fixed_layout, total_characters, chapter_count, entitlement_id, revision_number, kobo_content_id, kobo_metadata, tags_search, contributors_search, file_sha256, opf_identifier, opf_uuid, hash_confidence FROM media_items WHERE file_path = $1 AND library_id = $2
`
func (q *Queries) GetMediaItemByFilePath(ctx context.Context, filePath string) (MediaItems, error) {
row := q.db.QueryRow(ctx, GetMediaItemByFilePath, filePath)
type GetMediaItemByFilePathParams struct {
FilePath string `db:"file_path" json:"file_path"`
LibraryID pgtype.UUID `db:"library_id" json:"library_id"`
}
func (q *Queries) GetMediaItemByFilePath(ctx context.Context, arg GetMediaItemByFilePathParams) (MediaItems, error) {
row := q.db.QueryRow(ctx, GetMediaItemByFilePath, arg.FilePath, arg.LibraryID)
var i MediaItems
err := row.Scan(
&i.ID,
&i.LibraryID,
&i.Title,
&i.Author,
&i.Isbn,
&i.Description,
&i.FilePath,
&i.FileSize,
&i.MimeType,
&i.CoverImagePath,
&i.Series,
&i.SeriesNumber,
&i.Tags,
&i.Asin,
&i.DatePublished,
&i.Publisher,
&i.Contributors,
&i.Language,
&i.Edition,
&i.PageCount,
&i.Genre,
&i.CopyrightYear,
&i.GoodreadsID,
&i.OpenlibraryID,
&i.GoogleBooksID,
&i.AddedByAdminID,
&i.CreatedAt,
&i.UpdatedAt,
&i.FormatGroup,
&i.FormatMimetype,
&i.IsReflowable,
&i.HasFixedLayout,
&i.TotalCharacters,
&i.ChapterCount,
&i.EntitlementID,
&i.RevisionNumber,
&i.KoboContentID,
&i.KoboMetadata,
&i.TagsSearch,
&i.ContributorsSearch,
&i.FileSha256,
&i.OpfIdentifier,
&i.OpfUuid,
&i.HashConfidence,
)
return i, err
}
const GetMediaItemByFilePathAnyLibrary = `-- name: GetMediaItemByFilePathAnyLibrary :one
SELECT id, library_id, title, author, isbn, description, file_path, file_size, mime_type, cover_image_path, series, series_number, tags, asin, date_published, publisher, contributors, language, edition, page_count, genre, copyright_year, goodreads_id, openlibrary_id, google_books_id, added_by_admin_id, created_at, updated_at, format_group, format_mimetype, is_reflowable, has_fixed_layout, total_characters, chapter_count, entitlement_id, revision_number, kobo_content_id, kobo_metadata, tags_search, contributors_search, file_sha256, opf_identifier, opf_uuid, hash_confidence FROM media_items WHERE file_path = $1 LIMIT 1
`
func (q *Queries) GetMediaItemByFilePathAnyLibrary(ctx context.Context, filePath string) (MediaItems, error) {
row := q.db.QueryRow(ctx, GetMediaItemByFilePathAnyLibrary, filePath)
var i MediaItems
err := row.Scan(
&i.ID,