Hello,
this depends on what you are expecting here and what document types you are talking about.
Extracting text from text files or HTML could be made using the "out of the box" toolset of Fusion, if you e.g. want to extract text or pictures from a PDF file, you will need to use something like Adobe PDF Services, or another 3rd party online service.
Fusion itself is more of a tool for mediating between different services and pulling the strings. The actual processing of files is usually done by the services used, for which there are some ready-made apps and modules, or which can be addressed by the HTTP module, for example.
Regards
Lars