-- Hoogle documentation, generated by Haddock
-- See Hoogle, http://www.haskell.org/hoogle/


-- | Iteratee-based FASTA parser
--   
--   Enumeratees for FASTA-handling and convenience functions. In a typical
--   application, the user should write an enumeratee to extract
--   information to allow for efficient low-memory handling of queries.
--   
--   Facilities for fast, efficient linear scans are provided. These
--   functions are not yet stable and could move to another library, if
--   more data sources require efficient scans.
--   
--   The library is, in general, in a <a>preview</a> state. In cases where
--   you need to scan large FASTA files fast and with low memory overhead,
--   the enumeratees should, however, already be useable enough.
@package BiobaseFasta
@version 0.0.0.2

module Biobase.Fasta
data Fasta
Fasta :: Fasta

module Biobase.Fasta.Import

-- | This is the type of the conversion function from FASTA data to the
--   data <tt>z</tt>. Make certain that all input is used strictly!
--   BangPatterns are the easiest to do. In order, the function expects the
--   current FASTA header, then a data segment, and finally the starting
--   position of the data segment within the full FASTA data.
--   
--   If you need the conversion to run in constant time, do not use the
--   convenience functions and replace the final conversion to a strict
--   stream by your own conversion (or output) function.
type FastaFunction z = FastaHeader -> StartPos -> WindowSize -> PeekSize -> FastaData -> z

-- | Starting position in FASTA entry.
type StartPos = Int

-- | Current header (the line starting with <a>&gt;</a>)
type FastaHeader = ByteString

-- | FASTA data
type FastaData = ByteString

-- | Window
type WindowSize = Int

-- | How many characters to peek forward
type PeekSize = Int

-- | Takes a bytestring sequence, applies <tt>f</tt> to each bytestring of
--   windowsize and returns the results z.
rollingIter :: (Monad m, Functor m, Nullable z, Monoid z) => (StartPos -> WindowSize -> PeekSize -> FastaData -> z) -> WindowSize -> PeekSize -> Enumeratee ByteString z m a

-- | Outer enumeratee. See the two convenience functions for how to use it
--   (just like any enumeratee, basically).
--   
--   The fasta function <tt>f</tt> manipulates small stretches of fasta
--   data and has arguments: fasta header, fasta data, start position (all
--   filled by eneeFasta).
--   
--   Next we have the window size, how many characters to read at once,
--   
--   followed by the the number of characters to read in addition.
--   
--   The work is actually done by <a>rollingIter</a>.
eneeFasta :: (Monad m, Functor m, Nullable z, NullPoint z, Monoid z) => FastaFunction z -> WindowSize -> PeekSize -> Enumeratee ByteString z m a

-- | From an uncompressed file.
fromFile :: (Monoid z, Nullable z) => FastaFunction z -> Int -> Int -> FilePath -> IO z

-- | From a gzip-compressed file.
fromFileZip :: (Monoid z, Nullable z) => FastaFunction z -> Int -> Int -> FilePath -> IO z