Alphabet characters recognition in the detection?

[pavhofman]

Hi, please can I tell lingua somehow to take into account character sets in the input text? I use computeLanguageConfidenceValues() for further analysis. E.g. a mix of mostly english with one czech sentence with non-ascii letters reports English 1.0 and Czech some 0.7. Can I tell lingua to never return English if the text contains non-english characters?

Thanks a lot for your great work!

With regards,

Pavel.