From eb8f83e1b94919e5c2580e4254373fdcb0a60c9b Mon Sep 17 00:00:00 2001
From: John O'Keefe <jrokeefe@protonmail.com>
Date: Sun, 8 Feb 2026 11:05:29 -0500
Subject: [PATCH] feat: update ebook scanner to normalize metadata

Update extractEPUBMetadata:
- Normalize tags for display using NormalizeTags()
- Normalize contributors for display using NormalizeContributors()
- Preserves extracted metadata formatting while ensuring consistency

Update processEbookFile:
- Add normalization before database insert
- Generate tags_search using NormalizeTagsSearch()
- Generate contributors_search using NormalizeContributorsSearch()
- Pass both display and search fields to CreateMediaItem

Scanner now produces normalized metadata matching user input normalization,
ensuring consistency between scanned and manually entered media items.

Relates to Tags & Contributors Migration Phase 7
---
 internal/services/ebook_scanner.go | 52 ++++++++++++++++++------------
 1 file changed, 31 insertions(+), 21 deletions(-)

diff --git a/internal/services/ebook_scanner.go b/internal/services/ebook_scanner.go
index f3165b5..9197220 100644
--- a/internal/services/ebook_scanner.go
+++ b/internal/services/ebook_scanner.go
@@ -452,25 +452,35 @@ func (s *EbookScanner) processEbookFile(ctx context.Context, path string) error
 		return fmt.Errorf("no library found for file path: %s", path)
 	}
 
+	// Normalize metadata fields for display
+	metadata.Contributors = utils.NormalizeContributors(metadata.Contributors)
+	metadata.Tags = utils.NormalizeTags(metadata.Tags)
+
+	// Normalize search fields
+	contributorsSearch := utils.NormalizeContributorsSearch(metadata.Contributors)
+	tagsSearch := utils.NormalizeTagsSearch(metadata.Tags)
+
 	// Create media item in database
 	createdItem, err := s.db.CreateMediaItem(ctx, database.CreateMediaItemParams{
-		LibraryID:      libraryID,
-		Title:          metadata.Title,
-		Author:         pgtype.Text{String: metadata.Author, Valid: metadata.Author != ""},
-		Isbn:           pgtype.Text{String: utils.NormalizeISBN(metadata.ISBN), Valid: metadata.ISBN != ""},
-		Asin:           pgtype.Text{String: metadata.ASIN, Valid: metadata.ASIN != ""},
-		Description:    pgtype.Text{String: metadata.Description, Valid: metadata.Description != ""},
-		FilePath:       path,
-		FileSize:       pgtype.Int8{Int64: info.Size(), Valid: true},
-		MimeType:       pgtype.Text{String: s.getMimeType(path), Valid: true},
-		CoverImagePath: pgtype.Text{String: metadata.CoverPath, Valid: metadata.CoverPath != ""},
-		Series:         pgtype.Text{String: metadata.Series, Valid: metadata.Series != ""},
-		SeriesNumber:   pgtype.Int4{Int32: metadata.SeriesNumber, Valid: metadata.SeriesNumber > 0},
-		Publisher:      pgtype.Text{String: metadata.Publisher, Valid: metadata.Publisher != ""},
-		DatePublished:  pgtype.Date{Time: metadata.PublishDate, Valid: !metadata.PublishDate.IsZero()},
-		Contributors:   metadata.Contributors,
-		Tags:           metadata.Tags,
-		AddedByAdminID: s.adminID,
+		LibraryID:          libraryID,
+		Title:              metadata.Title,
+		Author:             pgtype.Text{String: metadata.Author, Valid: metadata.Author != ""},
+		Isbn:               pgtype.Text{String: utils.NormalizeISBN(metadata.ISBN), Valid: metadata.ISBN != ""},
+		Asin:               pgtype.Text{String: metadata.ASIN, Valid: metadata.ASIN != ""},
+		Description:        pgtype.Text{String: metadata.Description, Valid: metadata.Description != ""},
+		FilePath:           path,
+		FileSize:           pgtype.Int8{Int64: info.Size(), Valid: true},
+		MimeType:           pgtype.Text{String: s.getMimeType(path), Valid: true},
+		CoverImagePath:     pgtype.Text{String: metadata.CoverPath, Valid: metadata.CoverPath != ""},
+		Series:             pgtype.Text{String: metadata.Series, Valid: metadata.Series != ""},
+		SeriesNumber:       pgtype.Int4{Int32: metadata.SeriesNumber, Valid: metadata.SeriesNumber > 0},
+		Publisher:          pgtype.Text{String: metadata.Publisher, Valid: metadata.Publisher != ""},
+		DatePublished:      pgtype.Date{Time: metadata.PublishDate, Valid: !metadata.PublishDate.IsZero()},
+		Contributors:       metadata.Contributors,
+		ContributorsSearch: contributorsSearch,
+		Tags:               metadata.Tags,
+		TagsSearch:         tagsSearch,
+		AddedByAdminID:     s.adminID,
 	})
 	if err != nil {
 		return fmt.Errorf("failed to create media item: %v", err)
@@ -576,8 +586,8 @@ func (s *EbookScanner) extractEPUBMetadata(path string) (*EbookMetadata, error)
 
 	// Contributors
 	if contributors, err := book.MetadataByKey("contributor"); err == nil && len(contributors) > 0 {
-		// Already a []string from xml parsing, just assign
-		metadata.Contributors = contributors
+		// Normalize contributors for display
+		metadata.Contributors = utils.NormalizeContributors(contributors)
 	}
 
 	// ISBN
@@ -603,8 +613,8 @@ func (s *EbookScanner) extractEPUBMetadata(path string) (*EbookMetadata, error)
 
 	// Tags
 	if tags, err := book.MetadataByKey("subject"); err == nil && len(tags) > 0 {
-		// Already a []string from xml parsing, just assign
-		metadata.Tags = tags
+		// Normalize tags for display
+		metadata.Tags = utils.NormalizeTags(tags)
 	}
 
 	return metadata, nil