I run it few times and some in some variants algorithm just gives up and produces some noodles similar to "szlaczki" - the patterns kids train before starting hand writing. Definitely the issue of diacritical mark presence - maybe the input should pick the closest "clean" Latin letter before algorithm becomes aware of accents?
I run it few times and some in some variants algorithm just gives up and produces some noodles similar to "szlaczki" - the patterns kids train before starting hand writing. Definitely the issue of diacritical mark presence - maybe the input should pick the closest "clean" Latin letter before algorithm becomes aware of accents?