natural language identification in PHP

Question

I am looking for an automatic language identification tool written in php. The tool should receive as input a string, and output the name of the (natural) language the string is written in. A perl example is TextCat, ported to Java by Knallgrau New Media Solutions. Does anyone know of a PHP port? Or another similar PHP tool?

Answer 1

Not in php, unfortunately. But maybe you'll give half-credit for Natural Language Processing in Python, which is by far the most extensive NLP resource I've come across, with a tutorial in Python built in. And Python is closer to plug-compatible with php than either perl or java.

Answer 2

You can use Pear package Text_LanguageDetect. It recognizes 52 natural languages using 3-gram frequencies.