// 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/), as the MANIFEST spells it MType string // "" → application/xhtml+xml Body string // inner xhtml of // EntryName is the zip entry the file is actually written to (relative to the OPF dir), // for fixtures whose manifest href does NOT spell the entry name: a percent-encoded href // or one carrying a #fragment. "" → the href itself, so every existing fixture is unchanged. EntryName string } // entryName is where this chapter's bytes are written inside OEBPS/. func (c Chapter) entryName() string { if c.EntryName != "" { return c.EntryName } return c.Href } // 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) } } // OCF requires "mimetype" first in the archive and STORED, not deflated. Nothing in ingest // reads it today; the fixture matches the spec so it stays a real epub as the reader grows. mw, err := zw.CreateHeader(&zip.FileHeader{Name: "mimetype", Method: zip.Store}) if err != nil { t.Fatal(err) } if _, err := mw.Write([]byte("application/epub+zip")); err != nil { t.Fatal(err) } add("META-INF/container.xml", ` `) var manifest, spine strings.Builder for _, c := range chapters { mt := c.MType if mt == "" { mt = "application/xhtml+xml" } manifest.WriteString(`` + "\n") } for _, id := range spineIDs { spine.WriteString(`` + "\n") } add("OEBPS/content.opf", ` Test `+manifest.String()+` `+spine.String()+` `) for _, c := range chapters { // The FILE is (x)html when its ENTRY name says so, regardless of how the manifest // media-type labels it — real epubs mislabel xhtml as application/xml, etc. The entry // name (not the href) decides, because an href may be percent-encoded or fragment-bearing. entry := c.entryName() switch strings.ToLower(filepath.Ext(entry)) { case ".xhtml", ".html", ".htm", ".xml": add("OEBPS/"+entry, ` c `+c.Body+``) default: add("OEBPS/"+entry, c.Body) // non-xhtml asset (e.g. image bytes stand-in) } } if err := zw.Close(); err != nil { t.Fatal(err) } }