Bookhoard/bookhoard
0
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases 25 Wiki Activity

feat(scanner): fill sparse sidecars from embedded EPUB metadata

Browse Source 
A sparse metadata.opf/metadata.json (title only, no description) left
books thin even when the file itself carried rich data: the embedded
extractors only ran when no sidecar existed at all. Now mergeMetadata
fills blanks from the book's own OPF - title, author, description,
publisher, language, ISBN, ASIN, series/number, publish date, tags,
contributors - while sidecar values always win and unparseable files
skip silently. Also covers .kepub, which the merge previously ignored
while the extractor already supported it.

Adds TestMergeMetadataEPUBGapFill asserting both directions: sidecar
title/author survive, embedded description/publisher/language fill in.
This commit is contained in:
John O'Keefe
2026-09-13 13:05:37 -04:00
parent aac7c72900
commit 708598687e
2 changed files with 104 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/services/media_scanner.go
+43 -1
View File
@@ -1161,7 +1161,7 @@ func (s *MediaScanner) mergeMetadata(path string, calibreMetadata *MediaMetadata
ext := strings.ToLower(filepath.Ext(path))
// For EPUB files
if ext == ".epub" {
if ext == ".epub" || ext == ".kepub" {
book, err := epub.ReadBook(path)
if err == nil {
genreTags := extractGenreTagsFromEPUB(book)
@@ -1177,6 +1177,48 @@ func (s *MediaScanner) mergeMetadata(path string, calibreMetadata *MediaMetadata
metadata.PageCount = int32(pageCount)
}
}
// Gap-fill: sidecar-sourced metadata wins, but blanks are filled from
// the book's own OPF so a sparse metadata.opf/metadata.json doesn't
// hide data the file carries. Never overwrites sidecar values.
if embedded, err := s.extractEPUBMetadata(path); err == nil && embedded != nil {
if metadata.Title == "" && embedded.Title != "" {
metadata.Title = embedded.Title
}
if metadata.Author == "" && embedded.Author != "" {
metadata.Author = embedded.Author
}
if metadata.Description == "" && embedded.Description != "" {
metadata.Description = embedded.Description
}
if metadata.Publisher == "" && embedded.Publisher != "" {
metadata.Publisher = embedded.Publisher
}
if metadata.Language == "" && embedded.Language != "" {
metadata.Language = embedded.Language
}
if metadata.ISBN == "" && embedded.ISBN != "" {
metadata.ISBN = embedded.ISBN
}
if metadata.ASIN == "" && embedded.ASIN != "" {
metadata.ASIN = embedded.ASIN
}
if metadata.Series == "" && embedded.Series != "" {
metadata.Series = embedded.Series
}
if metadata.SeriesNumber == 0 && embedded.SeriesNumber != 0 {
metadata.SeriesNumber = embedded.SeriesNumber
}
if metadata.PublishDate.IsZero() && !embedded.PublishDate.IsZero() {
metadata.PublishDate = embedded.PublishDate
}
if len(metadata.Tags) == 0 && len(embedded.Tags) > 0 {
metadata.Tags = embedded.Tags
}
if len(metadata.Contributors) == 0 && len(embedded.Contributors) > 0 {
metadata.Contributors = embedded.Contributors
}
}
}
// For comic archives, try to extract ComicInfo.xml