Is there a way to split English words in a domain?

Question

I have a list of 10 million domains and want to be able to programmatically separate English words in domains, for example:

getheadphones.com leads to "get headphones"

I know that when I put getheadphones on Google, I get "headphones", but I'm not sure how they do it and how they know that it is not "get head phones"

Any ideas? Preferably in php.

Answer 1

google is famous for its spell checking, and it does a lot more to figure out what you want to find, however this problem has already been addressed in this question.

to get a list of English words in OSX and some Linux boxes, one of the available ones: / usr / share / dict / words otherwise you can get one of them ( sourceforge )