Vellum/internal/modules/ebooks/epub_test.go

package ebooks

import (
	"archive/zip"
	"encoding/xml"
	"os"
	"path/filepath"
	"testing"
)

const testOPF = `<?xml version="1.0" encoding="UTF-8"?>
<package xmlns="http://www.idpf.org/2007/opf" version="3.0" unique-identifier="pub-id">
  <metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
    <dc:title>The Test Book</dc:title>
    <dc:creator>Ada Lovelace</dc:creator>
    <dc:creator>Charles Babbage</dc:creator>
    <dc:language>en</dc:language>
    <dc:identifier id="pub-id">urn:uuid:abc</dc:identifier>
    <dc:publisher>Vellum Press</dc:publisher>
    <dc:date>2026-01-01</dc:date>
    <meta name="cover" content="cover-img"/>
  </metadata>
  <manifest>
    <item id="cover-img" href="images/cover.png" media-type="image/png" properties="cover-image"/>
    <item id="ch1" href="chapter1.xhtml" media-type="application/xhtml+xml"/>
    <item id="ch2" href="chapter2.xhtml" media-type="application/xhtml+xml"/>
  </manifest>
  <spine>
    <itemref idref="ch1"/>
    <itemref idref="ch2"/>
  </spine>
</package>`

const testContainer = `<?xml version="1.0"?>
<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
  <rootfiles><rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/></rootfiles>
</container>`

func writeEPUB(t *testing.T, opf, container string) string {
	t.Helper()
	p := filepath.Join(t.TempDir(), "test.epub")
	f, err := os.Create(p)
	if err != nil {
		t.Fatal(err)
	}
	defer f.Close()

	zw := zip.NewWriter(f)
	add := func(name, body string) {
		w, err := zw.Create(name)
		if err != nil {
			t.Fatal(err)
		}
		if _, err := w.Write([]byte(body)); err != nil {
			t.Fatal(err)
		}
	}
	add("mimetype", "application/epub+zip")
	add("META-INF/container.xml", container)
	add("OEBPS/content.opf", opf)
	add("OEBPS/images/cover.png", "not-a-real-png")
	add("OEBPS/chapter1.xhtml", "<html/>")
	if err := zw.Close(); err != nil {
		t.Fatal(err)
	}
	return p
}

func TestParseMetadata(t *testing.T) {
	md, err := Parse(writeEPUB(t, testOPF, testContainer))
	if err != nil {
		t.Fatalf("Parse: %v", err)
	}
	if md.Title != "The Test Book" {
		t.Errorf("Title = %q", md.Title)
	}
	if len(md.Authors) != 2 || md.Authors[0] != "Ada Lovelace" {
		t.Errorf("Authors = %v", md.Authors)
	}
	if md.Language != "en" || md.Publisher != "Vellum Press" || md.Date != "2026-01-01" {
		t.Errorf("metadata = %+v", md)
	}
	if md.SpineLength != 2 {
		t.Errorf("SpineLength = %d, want 2", md.SpineLength)
	}
	// CoverHref must be resolved relative to the OPF directory.
	if md.CoverHref != "OEBPS/images/cover.png" {
		t.Errorf("CoverHref = %q, want OEBPS/images/cover.png", md.CoverHref)
	}
}

func TestCoverHrefFallbacks(t *testing.T) {
	// No properties="cover-image"; rely on <meta name="cover">.
	opfMeta := `<package><metadata><title>x</title><meta name="cover" content="c"/></metadata>
	  <manifest><item id="c" href="c.jpg" media-type="image/jpeg"/></manifest><spine/></package>`
	if got := coverHref(mustParseOPF(t, opfMeta)); got != "c.jpg" {
		t.Errorf("meta cover fallback = %q, want c.jpg", got)
	}

	// No marker at all; fall back to an image whose href mentions cover.
	opfPlain := `<package><metadata><title>x</title></metadata>
	  <manifest><item id="i1" href="images/my-cover.png" media-type="image/png"/></manifest><spine/></package>`
	if got := coverHref(mustParseOPF(t, opfPlain)); got != "images/my-cover.png" {
		t.Errorf("href heuristics = %q, want images/my-cover.png", got)
	}

	// No candidate at all.
	opfNone := `<package><metadata><title>x</title></metadata>
	  <manifest><item id="i1" href="a.png" media-type="image/png"/></manifest><spine/></package>`
	if got := coverHref(mustParseOPF(t, opfNone)); got != "" {
		t.Errorf("no-cover case = %q, want empty", got)
	}
}

func TestJoinOPFRefusesEscape(t *testing.T) {
	if got := joinOPF("OEBPS", "../../etc/passwd"); got != "" {
		t.Errorf("joinOPF escaped the archive: %q", got)
	}
	if got := joinOPF("OEBPS", "images/c.png"); got != "OEBPS/images/c.png" {
		t.Errorf("joinOPF = %q", got)
	}
}

func TestParseRejectsNonEPUB(t *testing.T) {
	p := filepath.Join(t.TempDir(), "not.epub")
	if err := os.WriteFile(p, []byte("this is not a zip"), 0o644); err != nil {
		t.Fatal(err)
	}
	if _, err := Parse(p); err == nil {
		t.Error("Parse succeeded on a non-zip file")
	}
}

func mustParseOPF(t *testing.T, s string) opfXML {
	t.Helper()
	var o opfXML
	if err := xml.Unmarshal([]byte(s), &o); err != nil {
		t.Fatal(err)
	}
	return o
}