flower 0.4 → 0.5

raw patch · 2 files changed

+49/−2 lines, 2 files

Files

• flower.cabal +1/−1
• src/Flower.hs +48/−1

@@ -1,5 +1,5 @@ Name:           flower-Version:        0.4+Version:        0.5 License:        GPL Cabal-Version:  >= 1.6 Author:         Ketil Malde

@@ -9,6 +9,7 @@ import Bio.Util (countIO)  import Print+import Text.Printf  import System.IO (stdout) import System.Environment (getArgs)@@ -18,6 +19,7 @@ import Data.ByteString.Char8 (pack,unpack,ByteString) import qualified Data.ByteString.Char8 as B import qualified Data.ByteString as B1+import qualified Data.ByteString.Lazy.Char8 as L import qualified Data.ByteString.Lazy as L1  import Data.Array.Unboxed@@ -47,7 +49,7 @@                  ["-H"] -> putStr . sffToHistogramClip                  ["-i"] -> putStr . getHeader                  ["-s"] -> summarize-+                 []     -> dumpText                  _ -> error ("Usage: flower -[f|h|H|i|q|r|R|s] <file.sff> [<file2.sff> ..]\n"                              ++"  -r  output reads in Fasta format\n"                              ++"  -R  output reads in Fasta format with associated .qual\n"@@ -64,6 +66,51 @@ -- trim keys if they match, eliminate reads that don't. trim_keys _ [] = [] trim_keys ch (s:ss) = maybe id ((:) . id) (trimKey ch s) $ trim_keys ch ss++-- ------------------------------------------------------------+-- No option - dump as text format+-- ------------------------------------------------------------+dumpText :: SFF -> IO ()+dumpText (SFF _ rs) = putStr . concat . map toText $ rs+  where toText :: ReadBlock -> String+        toText r = concat [ gt, B.unpack (read_name rh), nl+                          , maybe "" ((\s->info++s++nl) . formatRN) $ decodeReadName (read_name rh)+                          , let (lf,rt) = (clip_adapter_right rh, clip_adapter_left rh) +                            in if lf /= 0 || rt /= 0 then adapter ++ show lf ++ sp++ show rt else ""+                          , clip,     show (clip_qual_left rh), sp, show (clip_qual_right rh), nl+                          , flows,    unwords $ map show $ flowgram r, nl+                          , index,    unwords $ map show $ cumulative_index' r, nl+                          , base,     L.unpack (masked_bases' r), nl+                          , qual,     unwords $ map show $ L1.unpack (quality r), nl+                             ]+          where rh = read_header r+                gt = ">"+                nl = "\n"+                sp = " "+                info     = "  Info: \t"+                clip     = "  Clip: \t"+                adapter  = "  Adap: \t"+                flows    = "  Flows:\t"+                index    = "  Index:\t"+                base     = "  Bases:\t"+                qual     = "  Quals:\t"+                formatRN (ReadName (yr,mo,dy) (h,m,s) r x y) = +                  printf "%4d-%02d-%02d %02d:%02d:%02d R%d (%d,%d)" yr mo dy h m s r x y+++-- Get the bases, but lower case masked bases.  Also in biolib's SFF.hs (sans prime),+-- so this is only for backwards compatibility with biolib <= 0.4.6.+masked_bases' :: ReadBlock -> SeqData+masked_bases' rb = let+  l = fromIntegral $ clip_qual_left $ read_header rb+  r = fromIntegral $ clip_qual_right $ read_header rb+  s = bases rb+  in L.concat [ L.map toLower $ L.take (l-1) s+              , L.take r (L.drop (l-1) s)+              , L.map toLower $ L.drop r s]++cumulative_index' :: ReadBlock -> [Int]+cumulative_index' = scanl1 (+) . map fromIntegral . B1.unpack . flow_index  -- ------------------------------------------------------------ -- The -i option: Print header info