fasta 0.6.0.0 → 0.6.1.0
raw patch · 3 files changed
+61/−8 lines, 3 filesdep +foldldep +lensdep +pipes-groupdep ~basePVP ok
version bump matches the API change (PVP)
Dependencies added: foldl, lens, pipes-group, pipes-text
Dependency ranges changed: base
API changes (from Hackage documentation)
+ Data.Fasta.Text.Lazy.Parse: pipesFasta :: MonadIO m => Producer Text m () -> Producer FastaSequence m ()
+ Data.Fasta.Text.Parse: pipesFasta :: MonadIO m => Producer Text m () -> Producer FastaSequence m ()
Files
- fasta.cabal +6/−2
- src/Data/Fasta/Text/Lazy/Parse.hs +30/−0
- src/Data/Fasta/Text/Parse.hs +25/−6
fasta.cabal view
@@ -10,7 +10,7 @@ -- PVP summary: +-+------- breaking API changes -- | | +----- non-breaking API additions -- | | | +--- code changes with no API change-version: 0.6.0.0+version: 0.6.1.0 -- A short (one-line) description of the package. synopsis: A simple, mindless parser for fasta files.@@ -69,7 +69,11 @@ text >=1.1.0 && <1.4, containers >= 0.5 && <0.6, split >= 0.2 && <0.3,- pipes >= 4.1 && < 4.2+ pipes >= 4.1 && < 4.2,+ pipes-group >= 1.0 && < 1.1,+ pipes-text >= 0.0 && < 0.1,+ lens >= 4.9 && < 4.10,+ foldl >= 1.0 && < 1.1 -- Directories containing source files. hs-source-dirs: src
src/Data/Fasta/Text/Lazy/Parse.hs view
@@ -10,6 +10,7 @@ module Data.Fasta.Text.Lazy.Parse ( parseFasta , parseCLIPFasta+ , pipesFasta , removeNs , removeN , removeCLIPNs ) where@@ -20,8 +21,17 @@ import Text.Parsec import Text.Parsec.Text.Lazy import qualified Data.Map.Strict as Map+import qualified Data.Text as ST import qualified Data.Text.Lazy as T +-- Cabal+import Pipes+import qualified Pipes.Prelude as P+import qualified Pipes.Text as PT+import qualified Pipes.Group as PG+import Control.Lens (view)+import Control.Foldl (purely, mconcat)+ -- Local import Data.Fasta.Text.Lazy.Types @@ -80,6 +90,26 @@ where eToV (Right x) = x eToV (Left x) = error ("Unable to parse fasta file\n" ++ show x)++-- | Parse a standard fasta file into strict text sequences for pipes. This is+-- the highly recommeded way of parsing, as it is computationally fast and+-- uses memory based on line length+pipesFasta :: (MonadIO m)+ => Producer ST.Text m ()+ -> Producer FastaSequence m ()+pipesFasta p = purely PG.folds mconcat ( view (PT.splits '>')+ . PT.drop (1 :: Int)+ $ p )+ >-> P.map toFasta+ where+ toFasta x = FastaSequence { fastaHeader = T.fromChunks+ . take 1+ . ST.lines+ $ x+ , fastaSeq = T.fromChunks+ . tail+ . ST.lines+ $ x } -- | Remove Ns from a collection of sequences removeNs :: [FastaSequence] -> [FastaSequence]
src/Data/Fasta/Text/Parse.hs view
@@ -10,18 +10,26 @@ module Data.Fasta.Text.Parse ( parseFasta , parseCLIPFasta+ , pipesFasta , removeNs , removeN , removeCLIPNs ) where -- Built-in import Data.Char-import Control.Monad (void) import Text.Parsec import Text.Parsec.Text import qualified Data.Map.Strict as Map import qualified Data.Text as T +-- Cabal+import Pipes+import qualified Pipes.Prelude as P+import qualified Pipes.Text as PT+import qualified Pipes.Group as PG+import Control.Lens (view)+import Control.Foldl (purely, mconcat)+ -- Local import Data.Fasta.Text.Types @@ -29,8 +37,7 @@ eol = choice . map (try . string) $ ["\n\r", "\r\n", "\n", "\r"] eoe :: Parsec T.Text u ()-eoe = do- lookAhead (void $ char '>') <|> eof+eoe = lookAhead (void $ char '>') <|> eof fasta :: Parsec T.Text u FastaSequence fasta = do@@ -82,17 +89,29 @@ eToV (Right x) = x eToV (Left x) = error ("Unable to parse fasta file\n" ++ show x) +-- | Parse a standard fasta file into strict text sequences for pipes. This is+-- the highly recommeded way of parsing, as it is computationally fast and+-- uses memory based on line length+pipesFasta :: (MonadIO m) => Producer T.Text m () -> Producer FastaSequence m ()+pipesFasta p = purely PG.folds mconcat ( view (PT.splits '>')+ . PT.drop (1 :: Int)+ $ p )+ >-> P.map toFasta+ where+ toFasta x = FastaSequence { fastaHeader = head . T.lines $ x+ , fastaSeq = T.concat . tail . T.lines $ x }+ -- | Remove Ns from a collection of sequences removeNs :: [FastaSequence] -> [FastaSequence] removeNs = map (\x -> x { fastaSeq = noN . fastaSeq $ x }) where- noN = T.map (\y -> if (y /= 'N' && y /= 'n') then y else '-')+ noN = T.map (\y -> if y /= 'N' && y /= 'n' then y else '-') -- | Remove Ns from a sequence removeN :: FastaSequence -> FastaSequence removeN x = x { fastaSeq = noN . fastaSeq $ x } where- noN = T.map (\y -> if (y /= 'N' && y /= 'n') then y else '-')+ noN = T.map (\y -> if y /= 'N' && y /= 'n' then y else '-') -- | Remove Ns from a collection of CLIP fasta sequences removeCLIPNs :: CloneMap -> CloneMap@@ -100,4 +119,4 @@ where remove ((!x, !y), !z) = ((x, newSeq y), map newSeq z) newSeq !x = x { fastaSeq = noN . fastaSeq $ x }- noN = T.map (\y -> if (y /= 'N' && y /= 'n') then y else '-')+ noN = T.map (\y -> if y /= 'N' && y /= 'n' then y else '-')