fix XML parsing (#2)

- Use antchfx/xmlquery for easier XML parsing. No more regexp wrangling and the result is much more reliable over a variety of ebooks. Much good.
- fix chapter selection, look for `<?xml[...]` which is much more reliable
- add option `-x` to dump the XML ebook source for debugging
This commit is contained in:
T.v.Dein
2025-10-16 18:57:05 +02:00
committed by GitHub
parent 90d30cb3e1
commit b50c6acff0
13 changed files with 143 additions and 71 deletions

View File

@@ -1,36 +1,22 @@
package epub
import (
"log"
"testing"
)
func TestEpub(t *testing.T) {
bk, err := open(t, "test.epub")
_, err := open(t, "test.epub")
if err != nil {
t.Fatal(err)
}
defer func() {
if err := bk.Close(); err != nil {
log.Fatal(err)
}
}()
}
func open(t *testing.T, f string) (*Book, error) {
bk, err := Open(f)
bk, err := Open(f, false)
if err != nil {
return nil, err
}
defer func() {
if err := bk.Close(); err != nil {
log.Fatal(err)
}
}()
t.Logf("files: %+v", bk.Files())
t.Logf("book: %+v", bk)