diff --git a/Biobase/Primary/AA.hs b/Biobase/Primary/AA.hs --- a/Biobase/Primary/AA.hs +++ b/Biobase/Primary/AA.hs @@ -6,6 +6,7 @@ module Biobase.Primary.AA where import Control.Arrow ((***),first) +import Data.Aeson import Data.Hashable import Data.Ix (Ix(..)) import Data.Map.Strict (Map) @@ -13,15 +14,17 @@ import Data.Tuple (swap) import Data.Vector.Unboxed.Deriving import GHC.Base (remInt,quotInt) +import qualified GHC.Exts as GHC import GHC.Generics (Generic) +import qualified Data.Bijection.HashMap as B import qualified Data.ByteString.Char8 as BS import qualified Data.ByteString.Lazy.Char8 as BSL +import qualified Data.Foldable as F import qualified Data.Map.Strict as M import qualified Data.Text as T import qualified Data.Vector.Generic as VG import qualified Data.Vector.Generic.Mutable as VGM import qualified Data.Vector.Unboxed as VU -import qualified Data.Bijection.Map as B import Biobase.Primary.Letter @@ -65,6 +68,19 @@ aaRange = [Stop .. pred Undef] +instance LetterChar AA where + letterChar = aaChar + charLetter = charAA + +instance ToJSON (Letter AA) where + toJSON = toJSON . letterChar + +instance FromJSON (Letter AA) where + parseJSON = fmap charLetter . parseJSON + +--instance (GHC.IsString f) => ToJSON (Pretty f (Letter AA)) where +-- toJSON = toJSON . T.pack . map letterChar . GHC.toList . getPretty + -- | Translate 'Char' amino acid representation into efficient 'AA' newtype. charAA :: Char -> Letter AA @@ -79,7 +95,7 @@ -- * lookup tables -charBaa :: B.Bimap Char (Letter AA) +charBaa :: B.Bimap (B.HashMap Char (Letter AA)) (B.HashMap (Letter AA) Char) charBaa = B.fromList [ ('*',Stop) , ('A',A) diff --git a/Biobase/Primary/Letter.hs b/Biobase/Primary/Letter.hs --- a/Biobase/Primary/Letter.hs +++ b/Biobase/Primary/Letter.hs @@ -34,12 +34,18 @@ instance Binary (Letter t) instance Serialize (Letter t) -instance FromJSON (Letter t) -instance ToJSON (Letter t) instance NFData (Letter t) type Primary t = VU.Vector (Letter t) + +-- | Convert 'Letter' types into character forms. @DNA@, @RNA@, and @amino +-- acid@ sequences can make use of this. Other @Letter@ types only if they +-- have single-char representations. + +class LetterChar t where + letterChar :: Letter t -> Char + charLetter :: Char -> Letter t -- | Conversion from a large number of sequence-like inputs to primary -- sequences. diff --git a/Biobase/Primary/Nuc/DNA.hs b/Biobase/Primary/Nuc/DNA.hs --- a/Biobase/Primary/Nuc/DNA.hs +++ b/Biobase/Primary/Nuc/DNA.hs @@ -1,6 +1,7 @@ module Biobase.Primary.Nuc.DNA where +import Data.Aeson import Data.Char (toUpper) import Data.Ix (Ix(..)) import Data.Primitive.Types @@ -41,6 +42,16 @@ toEnum k = error $ "toEnum/Letter DNA " ++ show k fromEnum (Letter k) = k +instance LetterChar DNA where + letterChar = dnaChar + charLetter = charDNA + +instance (LetterChar DNA) => ToJSON (Primary DNA) where + toJSON = toJSON . VU.toList . VU.map letterChar + +instance (MkPrimary (VU.Vector Char) DNA) => FromJSON (Primary DNA) where + parseJSON = fmap (primary :: String -> Primary DNA) . parseJSON + acgt :: [Letter DNA] acgt = [A .. T] @@ -58,7 +69,7 @@ G -> 'G' T -> 'T' N -> 'N' -{-# INLINE dnaChar #-} +{-# INLINE dnaChar #-} instance Show (Letter DNA) where show c = [dnaChar c] diff --git a/Biobase/Primary/Nuc/RNA.hs b/Biobase/Primary/Nuc/RNA.hs --- a/Biobase/Primary/Nuc/RNA.hs +++ b/Biobase/Primary/Nuc/RNA.hs @@ -1,6 +1,7 @@ module Biobase.Primary.Nuc.RNA where +import Data.Aeson import Data.Char (toUpper) import Data.Ix (Ix(..)) import Data.Primitive.Types @@ -14,6 +15,7 @@ import qualified Data.Vector.Generic.Mutable as VGM import qualified Data.Vector.Unboxed as VU import Control.Category ((>>>)) +import qualified Data.ByteString.Builder as BB import Biobase.Primary.Bounds import Biobase.Primary.Letter @@ -42,6 +44,27 @@ toEnum k | k>=0 && k<=4 = Letter k toEnum k = error $ "toEnum/Letter RNA " ++ show k fromEnum (Letter k) = k + +instance LetterChar RNA where + letterChar = rnaChar + charLetter = charRNA + +instance ToJSON (Letter RNA) where + toJSON = toJSON . letterChar + +instance FromJSON (Letter RNA) where + parseJSON = fmap charLetter . parseJSON + +-- We encode 'Primary RNA' directly as a string. +-- +-- TODO we can't anymore, because this is not a newtype, just a type. + +--instance ToJSON (Primary RNA) where +-- toJSON = toJSON . VU.toList . VU.map letterChar +-- +--instance FromJSON (Primary RNA) where +-- parseJSON = fmap (primary :: String -> Primary RNA) . parseJSON + acgu :: [Letter RNA] acgu = [A .. U] diff --git a/Biobase/Primary/Nuc/XNA.hs b/Biobase/Primary/Nuc/XNA.hs --- a/Biobase/Primary/Nuc/XNA.hs +++ b/Biobase/Primary/Nuc/XNA.hs @@ -1,6 +1,7 @@ module Biobase.Primary.Nuc.XNA where +import Data.Aeson import Data.Char (toUpper) import Data.Ix (Ix(..)) import Data.Primitive.Types @@ -43,6 +44,16 @@ toEnum k | k>=0 && k<=5 = Letter k toEnum k = error $ "toEnum/Letter XNA " ++ show k fromEnum (Letter k) = k + +instance LetterChar XNA where + letterChar = xnaChar + charLetter = charXNA + +instance (LetterChar XNA) => ToJSON (Primary XNA) where + toJSON = toJSON . VU.toList . VU.map letterChar + +instance (MkPrimary (VU.Vector Char) XNA) => FromJSON (Primary XNA) where + parseJSON = fmap (primary :: String -> Primary XNA) . parseJSON charXNA = toUpper >>> \case 'A' -> A diff --git a/Biobase/Primary/Pretty.hs b/Biobase/Primary/Pretty.hs new file mode 100644 --- /dev/null +++ b/Biobase/Primary/Pretty.hs @@ -0,0 +1,30 @@ + +-- | Wrapper newtype to simplify pretty and short encoding of primary +-- sequences. + +module Biobase.Primary.Pretty where + +import Data.Aeson +import qualified Data.Vector.Unboxed as VU +import qualified Data.Vector as V +import qualified Data.Vector.Storable as VS +import qualified Data.Text as T + +import Biobase.Primary.Letter + + + +newtype Pretty f a = Pretty { getPretty :: f a } + +instance (LetterChar x) => ToJSON (Pretty VU.Vector (Letter x)) where + toJSON = String . T.pack . map letterChar . VU.toList . getPretty + +instance (LetterChar x) => ToJSON (Pretty V.Vector (Letter x)) where + toJSON = String . T.pack . map letterChar . V.toList . getPretty + +instance (LetterChar x, VS.Storable (Letter x)) => ToJSON (Pretty VS.Vector (Letter x)) where + toJSON = String . T.pack . map letterChar . VS.toList . getPretty + +instance (LetterChar x) => ToJSON (Pretty [] (Letter x)) where + toJSON = String . T.pack . map letterChar . getPretty + diff --git a/Biobase/Primary/Unknown.hs b/Biobase/Primary/Unknown.hs --- a/Biobase/Primary/Unknown.hs +++ b/Biobase/Primary/Unknown.hs @@ -8,6 +8,7 @@ module Biobase.Primary.Unknown where +import Data.Aeson import Control.Applicative ((<$>)) import Control.Arrow ((***),first) import Data.Hashable @@ -69,4 +70,18 @@ instance MkPrimary (VU.Vector Int) Unknown where primary = VU.map Letter {-# Inline primary #-} + +instance ToJSON (Letter Unknown) where + toJSON = toJSON . getLetter + +instance FromJSON (Letter Unknown) where + parseJSON = fmap Letter . parseJSON + +{- +instance ToJSON (Primary Unknown) where + toJSON = toJSON . map (show . getLetter) . VU.toList + +instance FromJSON (Primary Unknown) where + parseJSON = fmap (VU.fromList . map (Letter . read)) . parseJSON +-} diff --git a/Biobase/Secondary/Diagrams.hs b/Biobase/Secondary/Diagrams.hs --- a/Biobase/Secondary/Diagrams.hs +++ b/Biobase/Secondary/Diagrams.hs @@ -16,7 +16,7 @@ import Data.Tuple.Select (sel1,sel2) import Data.Tuple (swap) import Data.Vector.Binary -import Data.Vector.Cereal +import Data.Vector.Serialize import GHC.Generics import qualified Data.Vector.Unboxed as VU import Text.Printf diff --git a/BiobaseXNA.cabal b/BiobaseXNA.cabal --- a/BiobaseXNA.cabal +++ b/BiobaseXNA.cabal @@ -1,5 +1,5 @@ name: BiobaseXNA -version: 0.9.2.1 +version: 0.9.3.0 author: Christian Hoener zu Siederdissen maintainer: choener@bioinf.uni-leipzig.de homepage: https://github.com/choener/BiobaseXNA @@ -11,7 +11,7 @@ license-file: LICENSE build-type: Simple stability: experimental -tested-with: GHC == 7.8.4, GHC == 7.10.1 +tested-with: GHC == 7.8.4, GHC == 7.10.3, GHC == 8.0.1 cabal-version: >= 1.10.0 description: This is a base library for bioinformatics with emphasis on RNA @@ -47,28 +47,29 @@ library - build-depends: base >= 4.7 && < 4.9 - , aeson >= 0.8 && < 0.11 - , bimaps >= 0.0.0.2 && < 0.0.1.0 - , binary >= 0.7 && < 0.8 - , bytes >= 0.15 && < 0.16 - , bytestring >= 0.10 && < 0.11 - , cereal >= 0.4 && < 0.5 - , cereal-vector >= 0.2 && < 0.3 - , containers >= 0.5 && < 0.6 - , csv >= 0.1 && < 0.2 - , deepseq >= 1.3 && < 1.5 - , file-embed >= 0.0.8 && < 0.0.10 - , hashable >= 1.2 && < 1.3 - , lens >= 4.0 && < 4.14 - , primitive >= 0.5 && < 0.7 - , PrimitiveArray >= 0.7.0 && < 0.7.1 - , split >= 0.2 && < 0.3 - , text >= 1.0 && < 1.3 - , tuple >= 0.3 && < 0.4 - , vector >= 0.10 && < 0.12 - , vector-binary-instances >= 0.2 && < 0.3 - , vector-th-unbox >= 0.2 && < 0.3 + build-depends: base >= 4.7 && < 5.0 + , aeson >= 0.8 && < 1.1 + , binary >= 0.7 && < 0.8 + , bytes >= 0.15 && < 0.16 + , bytestring >= 0.10 && < 0.11 + , cereal >= 0.4 && < 0.6 + , cereal-vector >= 0.2 && < 0.3 + , containers >= 0.5 && < 0.6 + , csv >= 0.1 && < 0.2 + , deepseq >= 1.3 && < 1.5 + , file-embed >= 0.0.8 && < 0.1 + , hashable >= 1.2 && < 1.3 + , lens >= 4.0 && < 5.0 + , primitive >= 0.5 && < 0.7 + , split >= 0.2 && < 0.3 + , text >= 1.0 && < 1.3 + , tuple >= 0.3 && < 0.4 + , vector >= 0.10 && < 0.12 + , vector-binary-instances >= 0.2 && < 0.3 + , vector-th-unbox >= 0.2 && < 0.3 + -- + , bimaps == 0.1.0.* + , PrimitiveArray == 0.7.1.* exposed-modules: Biobase.Primary Biobase.Primary.AA @@ -81,6 +82,7 @@ Biobase.Primary.Nuc.DNA Biobase.Primary.Nuc.RNA Biobase.Primary.Nuc.XNA + Biobase.Primary.Pretty Biobase.Primary.Trans Biobase.Primary.Unknown Biobase.Secondary diff --git a/changelog.md b/changelog.md --- a/changelog.md +++ b/changelog.md @@ -1,4 +1,10 @@ +0.9.3.0 +------- + +- bigger version bump together with multiple ghc compatibility + 0.9.2.1 +------- - stack.yaml, some version bumping