diversity 0.6.3.0 → 0.7.0.0

raw patch · 3 files changed

+30/−8 lines, 3 filesPVP ok

version bump matches the API change (PVP)

API changes (from Hackage documentation)

Files

• diversity.cabal +1/−1
• src/src-exec/Main.hs +14/−1
• src/src-lib/Math/Diversity/GenerateDiversity.hs +15/−6

@@ -2,7 +2,7 @@ -- documentation, see http://haskell.org/cabal/users-guide/  name:                diversity-version:             0.6.3.0+version:             0.7.0.0 synopsis:            Return the diversity at each position for all sequences in a fasta file description:         Find the diversity of a collection of entities, mainly for use with fasta sequences. Produces a binary which works on fasta files to find the diversity of any order and rarefaction curves for a sliding window across all positions in the sequences. To analyze just a collection of entities, just use the whole sequences and list flag. homepage:            https://github.com/GregorySchwartz/diversity

@@ -28,6 +28,7 @@                        , inputWindow            :: Int                        , inputFasta             :: String                        , inputSampleField       :: Int+                       , inputCountField        :: Int                        , inputSubsampling       :: String                        , inputG                 :: Double                        , fastBin                :: Bool@@ -78,6 +79,17 @@          <> value 1          <> help "The index for the sample ID in the header separated by '|'\                  \ (1 indexed)" )+      <*> option auto+          ( long "input-count-field"+         <> short 'C'+         <> metavar "INT"+         <> value 0+         <> help "The index for the number of this type in the header separated\+                 \ by '|' (1 indexed). Used if there are multiple copies\+                 \ of one entry, so a '4' in the header would indicate that\+                 \ this entity occurred 4 times. Defaults to 0, meaning that\+                 \ this field is ignored and count each sequence as occurring\+                 \ just once" )       <*> strOption           ( long "input-subsampling"          <> short 'I'@@ -168,7 +180,7 @@          <> metavar "FILE"          <> value ""          <> help "The csv file containing the diversities at each position.\-                 \ expects a string, so you need a string wven with std" )+                 \ expects a string, so you need a string even with std" )  parseSampling :: (Num a, Read a) => String -> [a] parseSampling = map read . parsing . words@@ -188,6 +200,7 @@         >-> P.map ( generatePositionMap                     (sample opts)                     (inputSampleField opts)+                    (inputCountField opts)                     (wholeSeq opts)                     (inputWindow opts)                   . removals )

@@ -23,10 +23,15 @@ -- Local import Math.Diversity.Types --- | Get the sample ID of a sequence-getSample :: Int -> FastaSequence -> Sample-getSample x = (!! (x - 1)) . Split.splitOn "|" . fastaHeader+-- | Get the field of a fasta sequence header+getField :: Int -> FastaSequence -> String+getField x = (!! (x - 1)) . Split.splitOn "|" . fastaHeader +-- | Get the count field of a fasta sequence header+getCount :: Int -> FastaSequence -> Int+getCount 0 = const 1+getCount x = read . getField x+ -- | Generates fragment list from string of "win" length. This version -- differs from normal as it takes a tuple with the position as the first -- entry. Is in tail recursive form@@ -46,19 +51,23 @@ -- | Generate the frequency from a FastaSequence generatePositionMap :: Bool                     -> Int+                    -> Int                     -> Bool                     -> Window                     -> FastaSequence                     -> PositionMap-generatePositionMap !sample !sampleField !whole !win = posSeqList+generatePositionMap !sample !sampleField !countField !whole !win = posSeqList   where     posSeqList !x       = Map.fromList-                        . map (\(!p, !f) -> (p, Map.singleton (sampleIt sample x f) 1))+                        . map ( \(!p, !f) -> ( p+                                             , Map.singleton (sampleIt sample x f)+                                             . getCount countField+                                             $ x ) )                         . fragmentPos whole win                         . filter (noGaps . snd)                         . zip [1..]                         . fastaSeq                         $ x     noGaps y            = y /= '-' && y /= '.'-    sampleIt True !s !f = (getSample sampleField s, f)+    sampleIt True !s !f = (getField sampleField s, f)     sampleIt False _ !f = ("Sample", f)