bookhoard/internal/services/media_scanner_opf.go

package services

import (
	"bytes"
	"encoding/xml"
	"strconv"
	"strings"
)

// Calibre-modeled OPF parsing. The scanner previously scraped OPF content
// with attribute-order-sensitive regexes; real books serialize attributes in
// any order (e.g. Pragmatic/Pattinson EPUBs put id before properties and
// content before name), which silently defeated cover detection. Everything
// here is parsed with encoding/xml so attribute order and namespace prefix
// choices are irrelevant.

type opfDCValue struct {
	ID    string `xml:"id,attr"`
	Value string `xml:",chardata"`
}

type opfIdentifier struct {
	Scheme string `xml:"http://www.idpf.org/2007/opf scheme,attr"`
	Value  string `xml:",chardata"`
}

type opfMeta struct {
	ID       string `xml:"id,attr"`
	Name     string `xml:"name,attr"`
	Content  string `xml:"content,attr"`
	Property string `xml:"property,attr"`
	Refines  string `xml:"refines,attr"`
	Value    string `xml:",chardata"`
}

type opfItem struct {
	ID         string `xml:"id,attr"`
	Href       string `xml:"href,attr"`
	MediaType  string `xml:"media-type,attr"`
	Properties string `xml:"properties,attr"`
}

// opfDocument is a structured view of an OPF package document.
type opfDocument struct {
	Metadata struct {
		Titles       []opfDCValue    `xml:"http://purl.org/dc/elements/1.1/ title"`
		Creators     []string        `xml:"http://purl.org/dc/elements/1.1/ creator"`
		Subjects     []string        `xml:"http://purl.org/dc/elements/1.1/ subject"`
		Descriptions []string        `xml:"http://purl.org/dc/elements/1.1/ description"`
		Publishers   []string        `xml:"http://purl.org/dc/elements/1.1/ publisher"`
		Dates        []string        `xml:"http://purl.org/dc/elements/1.1/ date"`
		Languages    []string        `xml:"http://purl.org/dc/elements/1.1/ language"`
		Identifiers  []opfIdentifier `xml:"http://purl.org/dc/elements/1.1/ identifier"`
		Contributors []string        `xml:"http://purl.org/dc/elements/1.1/ contributor"`
		Metas        []opfMeta       `xml:"meta"`
	} `xml:"metadata"`
	Manifest struct {
		Items []opfItem `xml:"item"`
	} `xml:"manifest"`
	Spine struct {
		Itemrefs []struct {
			IDRef string `xml:"idref,attr"`
		} `xml:"itemref"`
	} `xml:"spine"`
	Guide struct {
		References []struct {
			Type string `xml:"type,attr"`
			Href string `xml:"href,attr"`
		} `xml:"reference"`
	} `xml:"guide"`
}

func parseOPFXML(content []byte) (*opfDocument, error) {
	var doc opfDocument
	if err := xml.Unmarshal(content, &doc); err != nil {
		return nil, err
	}
	return &doc, nil
}

// refinesFor maps an element id to its EPUB3 refining metas
// (those whose refines attribute starts with '#').
func (d *opfDocument) refinesFor(id string) []opfMeta {
	var out []opfMeta
	if id == "" {
		return out
	}
	for _, m := range d.Metadata.Metas {
		if strings.HasPrefix(m.Refines, "#") && m.Refines[1:] == id {
			out = append(out, m)
		}
	}
	return out
}

// refinesProperty returns the value of the first refining meta carrying the
// given property (e.g. "title-type", "collection-type", "group-position").
func refinesProperty(metas []opfMeta, property string) (string, bool) {
	for _, m := range metas {
		if strings.EqualFold(m.Property, property) {
			if v := strings.TrimSpace(m.Value); v != "" {
				return v, true
			}
		}
	}
	return "", false
}

// selectTitle ports Calibre's read_title: prefer the dc:title refined as
// title-type "main"; fall back to the first non-empty title. A distinct
// subtitle (title-type containing "subtitle"/"sub-title") is joined onto the
// main title with ": ", exactly as Calibre stores it.
func (d *opfDocument) selectTitle() string {
	var first, main, subtitle string
	for _, t := range d.Metadata.Titles {
		v := strings.TrimSpace(t.Value)
		if v == "" {
			continue
		}
		if first == "" {
			first = v
		}
		tt, ok := refinesProperty(d.refinesFor(t.ID), "title-type")
		if !ok {
			continue
		}
		switch strings.ToLower(tt) {
		case "main":
			if main == "" {
				main = v
			}
		default:
			l := strings.ToLower(tt)
			if strings.Contains(l, "subtitle") || strings.Contains(l, "sub-title") {
				if subtitle == "" {
					subtitle = v
				}
			}
		}
	}
	title := main
	if title == "" {
		title = first
	}
	if subtitle != "" && subtitle != title {
		title = title + ": " + subtitle
	}
	return title
}

// readSeries ports Calibre's read_series: EPUB3 belongs-to-collection (with a
// collection-type=series refine and group-position index) first, then the
// classic calibre:series / calibre:series_index metas.
func (d *opfDocument) readSeries() (series string, index float64) {
	for _, m := range d.Metadata.Metas {
		if !strings.EqualFold(m.Property, "belongs-to-collection") {
			continue
		}
		name := strings.TrimSpace(m.Value)
		if name == "" {
			continue
		}
		refines := d.refinesFor(m.ID)
		if ct, ok := refinesProperty(refines, "collection-type"); !ok || !strings.EqualFold(ct, "series") {
			continue
		}
		if gp, ok := refinesProperty(refines, "group-position"); ok {
			if v, err := strconv.ParseFloat(strings.TrimSpace(gp), 64); err == nil {
				index = v
			}
		}
		return name, index
	}
	for _, m := range d.Metadata.Metas {
		switch m.Name {
		case "calibre:series":
			series = m.Content
		case "calibre:series_index":
			if v, err := strconv.ParseFloat(strings.TrimSpace(m.Content), 64); err == nil {
				index = v
			}
		}
	}
	return series, index
}

// itemByID returns manifest items with id, href and media-type, keyed by id.
func (d *opfDocument) itemByID() map[string]opfItem {
	m := make(map[string]opfItem, len(d.Manifest.Items))
	for _, it := range d.Manifest.Items {
		if it.ID != "" && it.Href != "" && it.MediaType != "" {
			m[it.ID] = it
		}
	}
	return m
}

// firstSpineItem returns the manifest item for the first spine idref.
func (d *opfDocument) firstSpineItem() (opfItem, bool) {
	if len(d.Spine.Itemrefs) == 0 {
		return opfItem{}, false
	}
	item, ok := d.itemByID()[d.Spine.Itemrefs[0].IDRef]
	return item, ok
}

// isRasterMedia reports whether a manifest media-type is an image but not an
// (X)HTML document - Calibre's guard against cover *pages* masquerading as
// cover images.
func isRasterMedia(mediaType string) bool {
	mt := strings.ToLower(strings.TrimSpace(mediaType))
	if mt == "" {
		return false
	}
	if strings.Contains(mt, "xml") || strings.Contains(mt, "html") {
		return false
	}
	return strings.HasPrefix(mt, "image/")
}

// findRasterCoverInOPF ports Calibre's read_raster_cover resolution order:
//  1. manifest item with properties containing "cover-image"
//  2. <meta name="cover" content="ID"> resolved through the manifest
//  3. the first spine item being a raster image itself (store manga)
//
// Returns the OPF-relative href of the cover image, or "".
func (d *opfDocument) findRasterCoverInOPF() string {
	// 1. properties="cover-image" (space-separated property list)
	for _, it := range d.Manifest.Items {
		for _, prop := range strings.Fields(it.Properties) {
			if strings.EqualFold(prop, "cover-image") && isRasterMedia(it.MediaType) {
				return it.Href
			}
		}
	}

	// 2. meta name="cover" content=<manifest image id>
	byID := d.itemByID()
	for _, m := range d.Metadata.Metas {
		if !strings.EqualFold(m.Name, "cover") {
			continue
		}
		if it, ok := byID[strings.TrimSpace(m.Content)]; ok && isRasterMedia(it.MediaType) {
			return it.Href
		}
	}

	// 3. first spine item is itself an image (jpeg/webp/png per Calibre)
	if it, ok := d.firstSpineItem(); ok {
		mt := strings.ToLower(it.MediaType)
		if mt == "image/jpeg" || mt == "image/webp" || mt == "image/png" {
			return it.Href
		}
	}

	return ""
}

// coverPageHref returns the OPF-relative href of the cover *page* document to
// mine for an embedded image: the guide's type="cover" reference when
// present, otherwise the first spine item (Calibre renders the latter).
func (d *opfDocument) coverPageHref() string {
	for _, ref := range d.Guide.References {
		if strings.EqualFold(ref.Type, "cover") && ref.Href != "" {
			return ref.Href
		}
	}
	if it, ok := d.firstSpineItem(); ok {
		if it.Href != "" && !isRasterMedia(it.MediaType) {
			return it.Href
		}
	}
	return ""
}

// isISBNLike reports whether a bare identifier value is shaped like an ISBN
// (digits, optional hyphens/spaces, optional trailing X; 10 or 13
// significant characters). Guards the scheme-less dc:identifier fallback
// against URLs and UUIDs sharing the same slot.
func isISBNLike(v string) bool {
	digits := 0
	for i, r := range v {
		switch {
		case r >= '0' && r <= '9':
			digits++
		case r == '-' || r == ' ':
			// separator
		case (r == 'X' || r == 'x') && i == len(v)-1:
			digits++ // ISBN-10 check character
		default:
			return false
		}
	}
	return digits == 10 || digits == 13
}

// findImageReferenceInPage extracts the first raster image reference from a
// cover (X)HTML page: <img src="..."> or SVG <image xlink:href="...">.
// Token-based parsing keeps it tolerant of mixed namespaces and fragments.
// Returns the reference relative to the page document, or "".
func findImageReferenceInPage(pageContent []byte) string {
	decoder := xml.NewDecoder(bytes.NewReader(pageContent))
	for {
		tok, err := decoder.Token()
		if err != nil {
			return ""
		}
		start, ok := tok.(xml.StartElement)
		if !ok {
			continue
		}
		switch strings.ToLower(start.Name.Local) {
		case "img":
			for _, a := range start.Attr {
				if strings.EqualFold(a.Name.Local, "src") && strings.TrimSpace(a.Value) != "" {
					return strings.TrimSpace(a.Value)
				}
			}
		case "image":
			for _, a := range start.Attr {
				if strings.EqualFold(a.Name.Local, "href") && strings.TrimSpace(a.Value) != "" {
					return strings.TrimSpace(a.Value)
				}
			}
		}
	}
}