Files
mostlymatter/vendor/code.sajari.com/docconv/tidy.go
Jesús Espino b9cceb70ae Making doc extraction more reliable (#17842)
* Making doc extraction more reliable

* fix error message

* Adding test doc file

* Removing test that not works on CI because the lack of a binary

Co-authored-by: Mattermod <mattermod@users.noreply.github.com>
2021-07-29 11:57:51 +02:00

33 строки
725 B
Go

package docconv
import (
"io"
"io/ioutil"
"os"
"os/exec"
)
// Tidy attempts to tidy up XML.
// Errors & warnings are deliberately suppressed as underlying tools
// throw warnings very easily.
func Tidy(r io.Reader, xmlIn bool) ([]byte, error) {
f, err := ioutil.TempFile(os.TempDir(), "docconv")
if err != nil {
return nil, err
}
defer os.Remove(f.Name())
io.Copy(f, r)
var output []byte
if xmlIn {
output, err = exec.Command("tidy", "-xml", "-numeric", "-asxml", "-quiet", "-utf8", f.Name()).Output()
} else {
output, err = exec.Command("tidy", "-numeric", "-asxml", "-quiet", "-utf8", f.Name()).Output()
}
if err != nil && err.Error() != "exit status 1" {
return nil, err
}
return output, nil
}