For the CN-EN version I’m almost there I believe.
I’ve found a grep on this site

[^\x{3000}-\x{efff}\x{4E00}-\x{9FD5}\x{3300}-\x{33FF}][^.,;:?!]+

It works fine untill their are punctuation or a space between two words. The part after the white space or for ex. ‘?’ he can’t recognise the Chinese characters anymore.

You can look into a basic file with the grep here:
https://indd.adobe.com/view/091c9dde-4eee-4faa-93b6-0a8b775a37d3