Skip to content

feat: extract EPUB subjects for OPDS category tags #61

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
dubyte merged 1 commit into from
Jul 11, 2026
Merged

feat: extract EPUB subjects for OPDS category tags #61

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions internal/service/internal_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,8 +86,8 @@ func TestSortEntries(t *testing.T) {
func TestExtractMetadata(t *testing.T) {
t.Run("Extract EPUB", func(t *testing.T) {
path := filepath.Join("testdata", "mybook", "mybook.epub")
title, author, coverPath, description, series, seriesIndex := extractEpubMetadata(path)
t.Logf("EPUB Title: %q, Author: %q, CoverPath: %q, Description: %q, Series: %q, SeriesIndex: %q", title, author, coverPath, description, series, seriesIndex)
title, author, coverPath, description, series, seriesIndex, subjects := extractEpubMetadata(path)
t.Logf("EPUB Title: %q, Author: %q, CoverPath: %q, Description: %q, Series: %q, SeriesIndex: %q, Subjects: %v", title, author, coverPath, description, series, seriesIndex, subjects)
})

t.Run("Parse PDF value", func(t *testing.T) {
Expand Down
50 changes: 33 additions & 17 deletions internal/service/service.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,7 @@ type CatalogEntry struct {
Description string
Series string
SeriesIndex string
Subjects []string
}

type IsDirer interface {
Expand Down Expand Up @@ -206,7 +207,7 @@ func (s OPDS) Scan(fPath string, urlPath string, page int) (*Catalog, error) {

if s.ExtractMetadata && !entry.IsDir() {
idx := len(catalog.Entries) - 1
title, author, coverPath, description, series, seriesIndex := extractMetadata(entryPath)
title, author, coverPath, description, series, seriesIndex, subjects := extractMetadata(entryPath)
if title != "" {
catalog.Entries[idx].Title = title
}
Expand All @@ -225,6 +226,9 @@ func (s OPDS) Scan(fPath string, urlPath string, page int) (*Catalog, error) {
if seriesIndex != "" {
catalog.Entries[idx].SeriesIndex = seriesIndex
}
if len(subjects) > 0 {
catalog.Entries[idx].Subjects = subjects
}
}
}

Expand Down Expand Up @@ -261,22 +265,22 @@ func (s OPDS) Scan(fPath string, urlPath string, page int) (*Catalog, error) {
return catalog, nil
}

func extractMetadata(path string) (string, string, string, string, string, string) {
func extractMetadata(path string) (string, string, string, string, string, string, []string) {
ext := strings.ToLower(filepath.Ext(path))
switch ext {
case ".epub":
return extractEpubMetadata(path)
case ".pdf":
title, author := extractPdfMetadata(path)
return title, author, "", "", "", ""
return title, author, "", "", "", "", nil
}
return "", "", "", "", "", ""
return "", "", "", "", "", "", nil
}

func extractEpubMetadata(path string) (string, string, string, string, string, string) {
func extractEpubMetadata(path string) (string, string, string, string, string, string, []string) {
r, err := zip.OpenReader(path)
if err != nil {
return "", "", "", "", "", ""
return "", "", "", "", "", "", nil
}
defer r.Close()

Expand All @@ -289,25 +293,26 @@ func extractEpubMetadata(path string) (string, string, string, string, string, s
}

if opfPath == "" {
return "", "", "", "", "", ""
return "", "", "", "", "", "", nil
}

f, err := r.Open(opfPath)
if err != nil {
return "", "", "", "", "", ""
return "", "", "", "", "", "", nil
}
defer f.Close()

opfContent, err := io.ReadAll(f)
if err != nil {
return "", "", "", "", "", ""
return "", "", "", "", "", "", nil
}

var opf struct {
Metadata struct {
Title string `xml:"title"`
Creator string `xml:"creator"`
Description string `xml:"description"`
Title string `xml:"title"`
Creator string `xml:"creator"`
Description string `xml:"description"`
Subject []string `xml:"subject"`
Meta []struct {
Name string `xml:"name,attr"`
Content string `xml:"content,attr"`
Expand All @@ -324,7 +329,7 @@ func extractEpubMetadata(path string) (string, string, string, string, string, s

decoder := xml.NewDecoder(bytes.NewReader(opfContent))
if err := decoder.Decode(&opf); err != nil {
return "", "", "", "", "", ""
return "", "", "", "", "", "", nil
}

// If standard unmarshal fails to get values due to namespaces
Expand All @@ -333,9 +338,10 @@ func extractEpubMetadata(path string) (string, string, string, string, string, s
decoder.DefaultSpace = "http://purl.org/dc/elements/1.1/"
var opf2 struct {
Metadata struct {
Title string `xml:"title"`
Creator string `xml:"creator"`
Description string `xml:"description"`
Title string `xml:"title"`
Creator string `xml:"creator"`
Description string `xml:"description"`
Subject []string `xml:"subject"`
Meta []struct {
Name string `xml:"name,attr"`
Content string `xml:"content,attr"`
Expand All @@ -352,6 +358,9 @@ func extractEpubMetadata(path string) (string, string, string, string, string, s
if opf2.Metadata.Description != "" {
opf.Metadata.Description = opf2.Metadata.Description
}
if len(opf2.Metadata.Subject) > 0 && len(opf.Metadata.Subject) == 0 {
opf.Metadata.Subject = opf2.Metadata.Subject
}
if len(opf2.Metadata.Meta) > 0 && len(opf.Metadata.Meta) == 0 {
opf.Metadata.Meta = opf2.Metadata.Meta
}
Expand All @@ -370,7 +379,7 @@ func extractEpubMetadata(path string) (string, string, string, string, string, s
// Find cover image in manifest
coverPath := findEpubCover(r, opf.Manifest.Items, opfPath)

return opf.Metadata.Title, opf.Metadata.Creator, coverPath, opf.Metadata.Description, series, seriesIndex
return opf.Metadata.Title, opf.Metadata.Creator, coverPath, opf.Metadata.Description, series, seriesIndex, opf.Metadata.Subject
}

func findEpubCover(r *zip.ReadCloser, items []struct {
Expand Down Expand Up @@ -1008,6 +1017,13 @@ func (s OPDS) makeFeed(catalog *Catalog, req *http.Request) opds.Feed {
Build())
}

for _, subject := range entry.Subjects {
entryBuilder = entryBuilder.AddCategory(opds.Category{
Term: subject,
Label: subject,
})
}

feedBuilder = feedBuilder.AddEntry(entryBuilder.Build())
}
return feedBuilder.Build()
Expand Down
28 changes: 17 additions & 11 deletions opds/atom.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,18 +25,24 @@ type Feed struct {
Opds string `xml:"xmlns:opds,attr,omitempty"`
}

// Entry is an Atom entry.
type Entry struct {
Title string `xml:"title"`
ID string `xml:"id"`
Link []Link `xml:"link"`
Published TimeStr `xml:"published"`
Updated TimeStr `xml:"updated"`
Author *Person `xml:"author"`
Summary *Text `xml:"summary"`
Content *Text `xml:"content"`
DcSeries string `xml:"dc:series,omitempty"`
DcSeriesPosition string `xml:"dc:seriesPosition,omitempty"`
Title string `xml:"title"`
ID string `xml:"id"`
Link []Link `xml:"link"`
Published TimeStr `xml:"published"`
Updated TimeStr `xml:"updated"`
Author *Person `xml:"author"`
Summary *Text `xml:"summary"`
Content *Text `xml:"content"`
DcSeries string `xml:"dc:series,omitempty"`
DcSeriesPosition string `xml:"dc:seriesPosition,omitempty"`
Categories []Category `xml:"category"`
}

type Category struct {
Term string `xml:"term,attr"`
Label string `xml:"label,attr,omitempty"`
Scheme string `xml:"scheme,attr,omitempty"`
}

// Link is an Atom link with optional OPDS 1.2 facet attributes.
Expand Down
4 changes: 4 additions & 0 deletions opds/entry_builder.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,10 @@ func (e entryBuilder) SeriesPosition(pos string) entryBuilder {
return builder.Set(e, "DcSeriesPosition", pos).(entryBuilder)
}

func (e entryBuilder) AddCategory(category Category) entryBuilder {
return builder.Append(e, "Categories", category).(entryBuilder)
}

func (e entryBuilder) Build() Entry {
return builder.GetStruct(e).(Entry)
}
Expand Down
Loading