Guess the natural language of a text
Project description
Example usage
>>> from guess_language import guess_language, UNKNOWN
>>> guess_language("I’ve been feeling déjà vu all morning.")
'en'
>>> guess_language("Tienes que seguir tu corazón.")
'es'
>>> guess_language("いいえ!忍者がいます")
'ja'
If text is very short and PyEnchant is available, check against installed spelling dictionaries.
>>> guess_language("Hello, World!")
'en'
Installation
You can use the setup script:
$ ./setup.py install
On Windows, you can use one of the MSI binary packages provided on the download page.
Requirements
Python 3.2+ (or 2.7, using lib3to2)
PyEnchant (optional)
This is basically my branch of guess-language, ported to Python 3 and optimized for my own needs.