textmachine/backend/internal/chunk/chunktest/epub.go

90 lines
3.1 KiB
Go

// Package chunktest builds the on-disk source fixtures the ingest path reads. It lives in its own
// package because two packages need the SAME epub shape: the ingest unit tests and the runner's
// end-to-end tests. Duplicating a zip/OPF builder in both would let the two drift apart, and the
// whole point of the e2e fixture is that it is the file the unit tests already pin.
package chunktest
import (
"archive/zip"
"os"
"path/filepath"
"strings"
"testing"
)
type Chapter struct {
ID string
Href string // relative to the OPF dir (OEBPS/)
MType string // "" → application/xhtml+xml
Body string // inner xhtml of <body>
}
// BuildEPUB writes a minimal but real epub (container.xml → OPF → spine → xhtml)
// to a temp .epub file and returns its path. spineIDs gives the reading order
// (may differ from manifest order to prove the spine drives it).
func BuildEPUB(t *testing.T, chapters []Chapter, spineIDs []string) string {
t.Helper()
path := filepath.Join(t.TempDir(), "book.epub")
BuildEPUBAt(t, path, chapters, spineIDs)
return path
}
// BuildEPUBAt writes the epub to a caller-chosen path (used by the runner e2e).
func BuildEPUBAt(t *testing.T, path string, chapters []Chapter, spineIDs []string) {
t.Helper()
f, err := os.Create(path)
if err != nil {
t.Fatal(err)
}
defer f.Close()
zw := zip.NewWriter(f)
add := func(name, content string) {
w, err := zw.Create(name)
if err != nil {
t.Fatal(err)
}
if _, err := w.Write([]byte(content)); err != nil {
t.Fatal(err)
}
}
add("mimetype", "application/epub+zip")
add("META-INF/container.xml", `<?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>`)
var manifest, spine strings.Builder
for _, c := range chapters {
mt := c.MType
if mt == "" {
mt = "application/xhtml+xml"
}
manifest.WriteString(`<item id="` + c.ID + `" href="` + c.Href + `" media-type="` + mt + `"/>` + "\n")
}
for _, id := range spineIDs {
spine.WriteString(`<itemref idref="` + id + `"/>` + "\n")
}
add("OEBPS/content.opf", `<?xml version="1.0" encoding="utf-8"?>
<package xmlns="http://www.idpf.org/2007/opf" version="3.0" unique-identifier="uid">
<metadata xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:title>Test</dc:title></metadata>
<manifest>`+manifest.String()+`</manifest>
<spine>`+spine.String()+`</spine>
</package>`)
for _, c := range chapters {
// The FILE is (x)html when its href says so, regardless of how the manifest
// media-type labels it — real epubs mislabel xhtml as application/xml, etc.
switch strings.ToLower(filepath.Ext(c.Href)) {
case ".xhtml", ".html", ".htm", ".xml":
add("OEBPS/"+c.Href, `<?xml version="1.0" encoding="utf-8"?>
<html xmlns="http://www.w3.org/1999/xhtml"><head><title>c</title><style>.x{color:red}</style></head>
<body>`+c.Body+`</body></html>`)
default:
add("OEBPS/"+c.Href, c.Body) // non-xhtml asset (e.g. image bytes stand-in)
}
}
if err := zw.Close(); err != nil {
t.Fatal(err)
}
}