packages feed

BiobaseTypes 0.0.2.2 → 0.2.1.0

raw patch · 28 files changed

Files

+ Biobase/Types/Accession.hs view
@@ -0,0 +1,128 @@++-- | Accession numbers. These /numbers/ are not really numbers because they+-- they are made up of alphanumeric characters.++module Biobase.Types.Accession where++import Control.DeepSeq+import Data.Aeson+import Data.Binary+import Data.Char (isLetter)+import Data.Hashable (Hashable)+import Data.Ix (Ix)+import Data.Serialize+import Data.Serialize.Text+import Data.String+import Data.String.Conversions (ConvertibleStrings(..), cs)+import Data.String.Conversions.Monomorphic (toST, fromST)+import Data.Text.Binary+import Data.Text (Text, span, length)+import GHC.Generics (Generic)+import Prelude hiding (length,span)++++-- * 'Accession' with phantom types.+--+-- <http://www.ncbi.nlm.nih.gov/Sequin/acc.html>+--+-- <http://www.uniprot.org/help/accession_numbers>+--+-- <http://en.wikipedia.org/wiki/Accession_number_%28bioinformatics%29>++-- | The accession number is a unique identifier in bioinformatics.+--+-- Depending on the source, accession numbers follow different alphanumeric+-- formats! While letters-than-numbers is quite common, swissprot uses+-- a mix. Hence, we just use a text string as accession.+--+-- A phantom type is provided to enable type safety annotations. Helper+-- functions provide smart construction from the @Accession@ tagged generic+-- type.++newtype Accession t = Accession { _getAccession :: Text }+  deriving (Eq,Ord,Read,Show,Generic)++-- | Generate an accession with an explicit phantom type: @accession'+-- Nucleotide "Bla"@ has type @:: Accession Nucleotide@.++accession' :: ConvertibleStrings s Text => t -> s -> Accession t+accession' t = Accession . toST++-- | Generate an accession when the type @Accession t@ is clear from the+-- context.++accession :: ConvertibleStrings s Text => s -> Accession t+accession = Accession . toST+{-# Inline accession #-}++-- | Retag an accession++retagAccession :: Accession f -> Accession t+retagAccession = Accession . _getAccession+{-# Inline retagAccession #-}++instance IsString (Accession t) where+  fromString = accession+  {-# Inline fromString #-}++instance Binary    (Accession t)+instance FromJSON  (Accession t)+instance Hashable  (Accession t)+instance Serialize (Accession t)+instance ToJSON    (Accession t)+instance NFData    (Accession t)++++-- * Phantom types. All with an excliti data constructor to guide+-- 'accession''.++-- ** NCBI phantom types++-- | nucleotide sequence++data Nucleotide = Nucleotide++-- | protein sequence++data Protein = Protein++-- ** Rfam phantom types+--+-- The format is RFxxxxx, PFxxxxx, or CLxxxxx.++-- | Tag as being a clan.++data Clan = Clan++-- | Tag as being a Pfam model.++data Pfam = Pfam++-- | Tag as being an Rfam model. Used for Stockholm and CM files.++data Rfam = Rfam++-- | Species have an accession number, too.++data Species = Species++++-- * Helper functions++-- | Guess the type of accession number. Returns @Nothing@ if unknown+-- structure.++guessAccessionType :: Accession t -> Maybe Text+guessAccessionType (Accession a) = case (length l, length d) of+  (1,5)                   -> Just "Nucleotide"+  (2,6)                   -> Just "Nucleotide"+  (3,5)                   -> Just "Protein"+  (3,k) | 8<= k && k<= 10 -> Just "WGS"+  (5,7)                   -> Just "MGA"+  _                       -> Nothing+  where (l,d) = span isLetter a++
+ Biobase/Types/BioSequence.hs view
@@ -0,0 +1,409 @@++-- | Abstraction over bio sequences encoded as one-ascii character as one+-- symbol. We phantom-type the exact bio-sequence type and provide type classes+-- that act on known types.+--+-- Unknown bio sequences should be tagged with @Void@.+--+-- TODO give (lens) usage examples++module Biobase.Types.BioSequence where++import           Control.DeepSeq+import           Control.Lens+import           Data.ByteString.Char8 (ByteString)+import           Data.Char (ord,chr,toUpper)+import           Data.Data (Data)+import           Data.Hashable+import           Data.Typeable (Typeable)+import           Data.Void+import           GHC.Exts (IsString(..))+import           GHC.Generics (Generic)+import qualified Data.ByteString.Char8 as BS+import qualified Data.ByteString.UTF8 as BSU+import qualified Streaming.Prelude as SP+import qualified Streaming as S+import qualified Streaming.Internal as SI+import qualified Test.QuickCheck as TQ+import           Test.QuickCheck (Arbitrary(..))+import Data.Coerce+import Debug.Trace++import Biobase.Types.Strand+import qualified Biobase.Types.Index as BTI+import Data.Info++++-- * Lens operations on biosequences++{-+class BioSeqLenses b where+  -- | Lens into the first @k@ characters.+  bsTake :: Int -> Lens' b b+  -- | Lens into the last @k@ characters+  bsTakeEnd :: Int -> Lens' b b+  -- | Lens into all but the first @k@ characters+  bsDrop :: Int -> Lens' b b+  -- | Lens into all but the last @k@ characters+  bsDropEnd :: Int -> Lens' b b+  -- | Lens that splits at a position+  bsSplitAt :: Int -> Lens' b (b,b)+  -- | length of this biosequence+  bsLength :: Getter b Int+-}++-- * Sequence identifiers++newtype SequenceIdentifier (which :: k) = SequenceIdentifier { _sequenceIdentifier :: ByteString }+  deriving stock (Data, Typeable, Generic, Eq, Ord, Read, Show)+makeWrapped ''SequenceIdentifier+makePrisms ''SequenceIdentifier++instance NFData (SequenceIdentifier w)++instance IsString (SequenceIdentifier w) where+  fromString = SequenceIdentifier . BSU.fromString++++-- * Bio-Sequences++data RNA++data DNA++data XNA++data AA++++-- |+-- TODO provide extended annotation information on biosequences, too!++newtype BioSequence (which :: k) = BioSequence {_bioSequence :: ByteString}+  deriving stock (Data, Typeable, Generic, Eq, Ord, Read, Show)+  deriving newtype (Semigroup)+makeWrapped ''BioSequence+makePrisms ''BioSequence+makeLenses ''BioSequence++instance Hashable (BioSequence (which :: k))++instance NFData (BioSequence w)++type instance Index (BioSequence w) = Int++type instance IxValue (BioSequence w) = Char++instance Ixed (BioSequence w) where+  ix k = _BioSequence . ix k . iso (chr . fromIntegral) (fromIntegral . ord)+  {-# Inline ix #-}++deriving newtype instance Reversing (BioSequence w)++instance IsString (BioSequence Void) where+  fromString = BioSequence . BS.pack++instance Info (BioSequence w) where+  info (BioSequence s)+    | BS.length s <= 18 = BS.unpack s+    | otherwise         = BS.unpack h ++ ".." ++ BS.unpack l+    where (h,tl) = BS.splitAt 9 s+          (_,l ) = BS.splitAt (BS.length tl-9) tl++{-+instance BioSeqLenses (BioSequence w) where+  {-# Inline bsTake #-}+  bsTake k = lens (over _BioSequence (BS.take k)) (\old new -> new <> over _BioSequence (BS.drop k) old)+  {-# Inline bsTakeEnd #-}+  bsTakeEnd k = lens (over _BioSequence (\s -> BS.drop (BS.length s -k) s)) (\old new -> over _BioSequence (\s -> BS.take (BS.length s-k) s) old <> new)+  {-# Inline bsLength #-}+  bsLength = _BioSequence.to BS.length+  {-# Inline bsDrop #-}+  bsDrop k = lens (over _BioSequence (BS.drop k)) (\old new -> over _BioSequence (BS.take k) old <> new)+  {-# Inline bsDropEnd #-}+  bsDropEnd k = lens (over _BioSequence (\s -> BS.take (BS.length s -k) s)) (\old new -> over _BioSequence (\s -> BS.take (BS.length s-k) s) old <> new)+  {-# Inline bsSplitAt #-}+  bsSplitAt k = lens (\b -> (view (bsTake k) b, view (bsDrop k) b)) (\old (h,t) -> h <> t)+-}++++-- * RNA++-- |+--+-- TODO write that converts explicitly++mkRNAseq :: ByteString -> BioSequence RNA+mkRNAseq = BioSequence . BS.map go . BS.map toUpper+  where go x | x `elem` acgu = x+             | otherwise     = 'N'+        acgu :: String+        acgu = "ACGU"++instance IsString (BioSequence RNA) where+  fromString = mkRNAseq . BS.pack++instance Arbitrary (BioSequence RNA) where+  arbitrary = do+    k ← TQ.choose (0,30)+    xs ← TQ.vectorOf k $ TQ.elements "ACGU"+    return . BioSequence $ BS.pack xs+  shrink = shrinkBioSequence++shrinkBioSequence (BioSequence b) = fmap BioSequence+  [ let (l,BS.drop 1 -> r) = BS.splitAt k b+    in BS.append l r | k <- [0 .. BS.length b -1] ]+++-- * DNA++mkDNAseq :: ByteString -> (BioSequence DNA)+mkDNAseq = BioSequence . BS.map go . BS.map toUpper+  where go x | x `elem` acgt = x+             | otherwise     = 'N'+        acgt :: String+        acgt = "ACGT"++instance IsString (BioSequence DNA) where+  fromString = mkDNAseq . BS.pack++instance Arbitrary (BioSequence DNA) where+  arbitrary = do+    k ← TQ.choose (0,100)+    xs ← TQ.vectorOf k $ TQ.elements "ACGT"+    return . BioSequence $ BS.pack xs+  shrink = view (to shrink)++++-- * XNA++mkXNAseq :: ByteString -> (BioSequence XNA)+mkXNAseq = BioSequence . BS.map go . BS.map toUpper+  where go x | x `elem` acgtu = x+             | otherwise      = 'N'+        acgtu :: String+        acgtu = "ACGTU"++instance IsString (BioSequence XNA) where+  fromString = mkXNAseq . BS.pack++instance Arbitrary (BioSequence XNA) where+  arbitrary = do+    k ← TQ.choose (0,100)+    xs ← TQ.vectorOf k $ TQ.elements "ACGTU"+    return . BioSequence $ BS.pack xs+  shrink = view (to shrink)++++-- * Amino acid sequences++mkAAseq :: ByteString -> (BioSequence AA)+mkAAseq = BioSequence . BS.map go . BS.map toUpper+  where go x | x `elem` aas = x+             | otherwise    = 'X'+        aas :: String+        aas = "ARNDCEQGHILKMFPSTWYVUO"++instance IsString (BioSequence AA) where+  fromString = mkAAseq . BS.pack++instance Arbitrary (BioSequence AA) where+  arbitrary = do+    k ← TQ.choose (0,100)+    xs ← TQ.vectorOf k $ TQ.elements "ARNDCEQGHILKMFPSTWYVUO"+    return . BioSequence $ BS.pack xs+  shrink = view (to shrink)++++{-++-- * A window into a longer sequence with prefix/suffix information.++-- | Phantom-typed over two types, the type @w@ of the identifier, which can be+-- descriptive ("FirstInput") and the second type, identifying what kind of+-- sequence types we are dealing with. Finally, the third type provides+-- location information and should be location or streamed location.++data BioSequenceWindow w ty loc = BioSequenceWindow+  { _bswIdentifier    :: !(SequenceIdentifier w)+    -- ^ Identifier for this window. Typically some fasta identifier+  , _bswPrefix        :: !(BioSequence ty)+  , _bswInfix         :: !(BioSequence ty)+  , _bswSuffix        :: !(BioSequence ty)+  , _bswInfixLocation :: !loc+    -- ^ Location of the infix sequence+  }+  deriving (Data, Typeable, Generic, Eq, Ord, Read, Show)+makeLenses ''BioSequenceWindow++-- | Lens into the full sequence. May not change the sequence length++bswSequence :: Lens (BioSequenceWindow w ty loc) (BioSequenceWindow w ty' loc) (BioSequence ty) (BioSequence ty')+{-# Inlinable bswSequence #-}+bswSequence = lens (\w -> _bswPrefix w <> _bswInfix w <> _bswSuffix w)+                   (\w bs -> let (p,is) = bs^.bsSplitAt (w^.bswPrefix.bsLength)+                                 (i,s ) = is^.bsSplitAt (w^.bswInfix.bsLength)+                             in w { _bswPrefix = p, _bswInfix = i, _bswSuffix = s } )++-- | Get the position of the whole sequence++bswLocation :: ModifyLocation loc => Getter (BioSequenceWindow w ty loc) loc+{-# Inlinable bswLocation #-}+bswLocation = to $ \w -> locMoveLeftEnd (w^.bswPrefix.bsLength.to negate)+                 . locMoveRightEnd (w^.bswSuffix.bsLength) $ w^.bswInfixLocation++bswRetagW :: BioSequenceWindow w ty loc -> BioSequenceWindow v ty loc+{-# Inlinable bswRetagW #-}+bswRetagW = over bswIdentifier coerce++instance NFData loc => NFData (BioSequenceWindow w ty loc)++instance (Reversing loc) => Reversing (BioSequenceWindow w ty loc) where+  {-# Inlinable reversing #-}+  reversing bsw = bsw+                & bswPrefix .~ (bsw^.bswSuffix.reversed)+                & bswSuffix .~ (bsw^.bswPrefix.reversed)+                & bswInfix  .~ (bsw^.bswInfix.reversed)+                & bswInfixLocation .~ (bsw^.bswInfixLocation.reversed)++++-- | Provides an informative string indicating the current window being worked on. Requires length+-- of pretty string requested. Not for computers, but for logging what is being worked on. Should be+-- one line at most, not produce line breaks.+--+-- @...PFX [Start] IFX...IFX [End] SFX ...@+--+-- TODO possibly be better as a @Doc@ for prettier printing.++instance Info (BioSequenceWindow w ty loc) where+  info bsw = "todo: info bsw"++-}++++-- * DNA/RNA++-- | Simple case translation from @U@ to @T@. with upper and lower-case+-- awareness.++rna2dna :: Char -> Char+rna2dna = \case+  'U' -> 'T'+  'u' -> 't'+  x   -> x+{-# Inline rna2dna #-}++-- | Single character RNA complement.++rnaComplement :: Char -> Char+rnaComplement = \case+  'A' -> 'U'+  'a' -> 'u'+  'C' -> 'G'+  'c' -> 'g'+  'G' -> 'C'+  'g' -> 'c'+  'U' -> 'A'+  'u' -> 'a'+  x   -> x+{-# Inline rnaComplement #-}++-- | Simple case translation from @T@ to @U@ with upper- and lower-case+-- awareness.++dna2rna :: Char -> Char+dna2rna = \case+  'T' -> 'U'+  't' -> 'u'+  x   -> x+{-# Inline dna2rna #-}++-- | Single character DNA complement.++dnaComplement :: Char -> Char+dnaComplement = \case+  'A' -> 'T'+  'a' -> 't'+  'C' -> 'G'+  'c' -> 'g'+  'G' -> 'C'+  'g' -> 'c'+  'T' -> 'A'+  't' -> 'a'+  x   -> x+{-# Inline dnaComplement #-}++++-- | Transcribes a DNA sequence into an RNA sequence. Note that 'transcribe' is+-- actually very generic. We just define its semantics to be that of+-- biomolecular transcription.+--+-- 'transcribe' makes the assumption that, given @DNA -> RNA@, we transcribe+-- the coding strand.+-- <http://hyperphysics.phy-astr.gsu.edu/hbase/Organic/transcription.html>+--+-- @@ DNAseq "ACGT" ^. transcribe == RNAseq "ACGU" RNAseq "ACGU" ^. transcribe+-- == DNAseq "ACGT" RNAseq "ACGU" ^. from transcribe :: DNAseq == DNAseq "ACGT"+-- @@++class Transcribe f where+  type TranscribeTo f :: *+  transcribe :: Iso' f (TranscribeTo f)++-- | Transcribe a DNA sequence into an RNA sequence. This does not @reverse@+-- the sequence!++instance Transcribe (BioSequence DNA) where+  type TranscribeTo (BioSequence DNA) = (BioSequence RNA)+  transcribe = iso (over _BioSequence (BS.map dna2rna)) (over _BioSequence (BS.map rna2dna))+  {-# Inline transcribe #-}++-- | Transcribe a RNA sequence into an DNA sequence. This does not @reverse@+-- the sequence!++instance Transcribe (BioSequence RNA) where+  type TranscribeTo (BioSequence RNA) = (BioSequence DNA)+  transcribe = from transcribe+  {-# Inline transcribe #-}++++-- | The complement of a biosequence.++class Complement f where+  complement :: Iso' f f++instance Complement (BioSequence DNA) where+  {-# Inline complement #-}+  complement = let f = (over _BioSequence (BS.map dnaComplement))+                   {-# Inline f #-}+               in  iso f f++instance Complement (BioSequence RNA) where+  {-# Inline complement #-}+  complement = let f = (over _BioSequence (BS.map rnaComplement))+                   {-# Inline f #-}+               in  iso f f++{-+instance (Complement (BioSequence ty)) => Complement (BioSequenceWindow w ty k) where+  {-# Inline complement #-}+  complement = let f = over bswPrefix (view complement) . over bswInfix (view complement) . over bswSuffix (view complement)+                   {-# Inline f #-}+               in  iso f f+-}++reverseComplement :: (Complement f, Reversing f) => Iso' f f+{-# Inline reverseComplement #-}+reverseComplement = reversed . complement+
+ Biobase/Types/Bitscore.hs view
@@ -0,0 +1,94 @@++-- | Bit scores as used by different algorithms in bioinformatics,+-- linguistics, and probably elsewhere.+--+-- Basically, the base-2 logarithm of the probability of the input given+-- the model vs the probability of the input given the null model.+--+-- @+-- S = log_2 (P(seq|model) / P(seq|null))+-- @+--++module Biobase.Types.Bitscore where++import           Control.DeepSeq+import           Data.Aeson+import           Data.Binary+import           Data.Default+import           Data.Hashable (Hashable)+import           Data.Primitive.Types+import           Data.Serialize+import           Data.Vector.Unboxed.Base+import           Data.Vector.Unboxed.Deriving+import           GHC.Generics (Generic)+import qualified Data.Vector.Generic as VG+import qualified Data.Vector.Generic.Mutable as VGM+import qualified Data.Vector.Unboxed as VU++import           Algebra.Structure.Semiring+import           Numeric.Limits++++-- | Bit score; behaves like a double (deriving Num). In particular, the+-- algebraic operations behave as expected @Bitscore a + Bitscore b ==+-- Bitscore (a+b)@.+--+-- Currently geared towards use as in @Infernal@ and @HMMER@.+--+-- Infernal users guide, p.42: log-odds score in log_2 (aka bits).++newtype Bitscore = Bitscore { getBitscore :: Double }+  deriving stock (Eq,Ord,Read,Show,Generic)+  deriving newtype (Num,Fractional)++instance Semiring Bitscore where+  plus = (+)+  times = (*)+  zero = 0+  one = 1+  {-# Inline plus  #-}+  {-# Inline times #-}+  {-# Inline zero  #-}+  {-# Inline one   #-}++instance Binary    Bitscore+instance FromJSON  Bitscore+instance Hashable  Bitscore+instance Serialize Bitscore+instance ToJSON    Bitscore+instance NFData    Bitscore++deriving newtype instance NumericLimits Bitscore++derivingUnbox "Bitscore"+  [t| Bitscore -> Double |] [| getBitscore |] [| Bitscore |]++-- | A default bitscore of "-infinity", but with @10-1@ wiggle room.+--+-- TODO Check out the different "defaults" Infernal uses++instance Default Bitscore where+  def = Bitscore minFinite / 100+  {-# Inline def #-}++-- | Given a null model and a probability, calculate the corresponding+-- 'BitScore'.+--+-- TODO @x<=epsilon@ ?++prob2Score :: Double -> Double -> Bitscore+prob2Score null x+  | x==0      = minFinite / 100+  | otherwise = Bitscore $ log (x/null) / log 2+{-# Inline prob2Score #-}++-- | Given a null model and a 'BitScore' return the corresponding probability.++score2Prob :: Double -> Bitscore -> Double+score2Prob null (Bitscore x)+  | x <= minFinite / 100 = 0+  | otherwise     = null * exp (x * log 2)+{-# Inline score2Prob #-}+
+ Biobase/Types/Codon.hs view
@@ -0,0 +1,20 @@++module Biobase.Types.Codon where++import Control.Lens+import GHC.Generics (Generic)++++-- | A single codon.+--+-- TODO needs to go into its own place++data Codon c = Codon !c !c !c+  deriving (Eq,Ord,Read,Show,Generic,Functor,Foldable,Traversable)++instance Field1 (Codon c) (Codon c) c c+instance Field2 (Codon c) (Codon c) c c+instance Field3 (Codon c) (Codon c) c c+instance Each (Codon c) (Codon c') c c'+
− Biobase/Types/Convert.hs 
@@ -1,36 +0,0 @@-{-# LANGUAGE MultiParamTypeClasses #-}---- | Provides a converting function between different types. Most useful--- conversions are instanced here.--module Biobase.Types.Convert where--import Biobase.Types.Ring-import Biobase.Types.Energy-import Biobase.Types.Score-import Biobase.Types.Partition------ | How to convert between different values.--class Convert a b c where-  convert :: a -> b -> c------ | From (Gibbs free) energy to partition function values.------ TODO temperature is running around here: move to some library later on--newtype Kelvin = Kelvin {unKelvin :: Double}--constR = undefined--instance Convert Kelvin Energy Partition where-  convert (Kelvin k) (Energy a) = Partition . exp $ (fromIntegral $ negate a) / (constR * k)---- | From log-odd scores to partition function.---- instance Convert Temperature Score Partition where---   convert (Score a) = Partition . exp $ (fromIntegral $ neg a) / (constR * constT)
Biobase/Types/Energy.hs view
@@ -1,51 +1,95 @@-{-# LANGUAGE StandaloneDeriving #-}-{-# LANGUAGE MultiParamTypeClasses #-}-{-# LANGUAGE GeneralizedNewtypeDeriving #-} +-- | Different types of energies and conversion between.+--+-- TODO enthalpy+-- TODO entropy+ module Biobase.Types.Energy where -import qualified Data.Vector.Unboxed as VU-import qualified Data.Vector.Generic as VG-import qualified Data.Vector.Generic.Mutable as VGM-import Data.Primitive.Types+import Control.DeepSeq+import Control.Lens+import Data.Aeson (FromJSON, ToJSON)+import Data.Binary (Binary)+import Data.Data+import Data.Default+import Data.Hashable+import GHC.Real+import Data.Serialize (Serialize)+import Data.Vector.Unboxed.Deriving+import GHC.Generics -import Biobase.Types.Ring+import Algebra.Structure.Semiring+import Numeric.Discretized+import Numeric.Limits   --- | Some default instances. Left out the Num one, so that you have to--- explicitly instanciate if you want to go around the Ring structure.+-- | Gibbs free energy change.+--+-- For RNA structure, the change in energy from the unfolded structure to+-- the given structure.+--+-- In units of @kcal / mol@.+--+-- TODO shall we phantom-type the actual units? -newtype Energy = Energy {unEnergy :: Int}-  deriving (Show, Read, Eq, Ord)+newtype DG = DG { dG :: Double }+  deriving (Eq,Ord,Num,Fractional,Read,Show,Generic,Data,Typeable)+makeLenses ''DG +derivingUnbox "DG"+  [t| DG -> Double |]  [| dG |]  [| DG |] +instance Hashable  DG+instance Binary    DG+instance Serialize DG+instance FromJSON  DG+instance ToJSON    DG+instance NFData    DG --- | Ring operations over Energy values.+deriving instance NumericLimits DG+deriving instance NumericEpsilon  DG -instance Ring Energy where-  (Energy a) .+. (Energy b) = Energy $ a `min` b-  {-# INLINE (.+.) #-}-  (Energy a) .*. (Energy b) = Energy $ a + b-  {-# INLINE (.*.) #-}-  (Energy a) .^. k = Energy $ a * k-  {-# INLINE (.^.) #-}-  (Energy a) .^^. k = Energy . round $ fromIntegral a * k-  {-# INLINE (.^^.) #-}-  neg (Energy a) = Energy $ negate a-  {-# INLINE neg #-}-  one = Energy 0-  {-# INLINE one #-}-  zero = Energy 10000000-  {-# INLINE zero #-}-  isZero (Energy a) = a >= 1000000-  {-# INLINE isZero #-}+instance Default DG where+  def = maxFinite / 100+  {-# Inline def #-}   --- * Vector instances.+-- | Discretized @DG@. -deriving instance VGM.MVector VU.MVector Energy-deriving instance VG.Vector VU.Vector Energy-deriving instance VU.Unbox Energy-deriving instance Prim Energy+newtype DDG = DDG { dDG ∷ Discretized (1 :% 100) }+  deriving (Eq,Ord,Num,Read,Generic,Real,Enum)++instance Show DDG where+  show (DDG e) = show e++ddg2Int :: DDG -> Int+ddg2Int (DDG (Discretized e)) = e++derivingUnbox "DDG"+  [t| DDG -> Int |]  [| getDiscretized . dDG |]  [| DDG . Discretized |]++instance Semiring DDG where+  plus  (DDG x) (DDG y) = DDG $ min x y+  times (DDG x) (DDG y) = DDG $ x `plus` y+  zero = DDG maxFinite+  one  = DDG zero+  {-# Inline plus  #-}+  {-# Inline times #-}+  {-# Inline zero  #-}+  {-# Inline one   #-}++--instance Hashable  DeltaDekaGibbs+--instance Binary    DeltaDekaGibbs+--instance Serialize DeltaDekaGibbs+--instance FromJSON  DeltaDekaGibbs+--instance ToJSON    DeltaDekaGibbs+--instance NFData    DeltaDekaGibbs+--+--deriving instance NumericLimits DeltaDekaGibbs+--+--instance Default DeltaDekaGibbs where+--  def = maxFinite `div` 100+--  {-# Inline def #-}+--
+ Biobase/Types/Evalue.hs view
@@ -0,0 +1,56 @@++-- | Encode the number of hits to expect. This is typically dependent on+-- some "database size". Evalues are bounded by @[0,infinity)@.+--+-- TODO Evalues close to zero are more interesting. We should strongly+-- consider log-conversion here.++module Biobase.Types.Evalue where++import           Control.DeepSeq+import           Control.Lens+import           Data.Aeson+import           Data.Binary+import           Data.Default+import           Data.Hashable (Hashable)+import           Data.Primitive.Types+import           Data.Serialize+import           Data.Vector.Unboxed.Base+import           Data.Vector.Unboxed.Deriving+import           GHC.Generics (Generic)+import qualified Data.Vector.Generic as VG+import qualified Data.Vector.Generic.Mutable as VGM+import qualified Data.Vector.Unboxed as VU++import           Numeric.Limits++++-- | Type-safe wrapper for e-values.++newtype Evalue = Evalue { getEvalue :: Double }+  deriving (Eq,Ord,Read,Show,Num,Generic)+makeWrapped ''Evalue++instance Binary    Evalue+instance FromJSON  Evalue+instance Hashable  Evalue+instance Serialize Evalue+instance ToJSON    Evalue+instance NFData    Evalue++derivingUnbox "Evalue"+  [t| Evalue -> Double |] [| getEvalue |] [| Evalue |]++-- | By default, we expect no hits.++instance Default Evalue where+  def = Evalue 0+  {-# Inline def #-}++instance NumericLimits Evalue where+  maxFinite   = Evalue maxFinite+  minFinite   = Evalue 0+  {-# Inline maxFinite  #-}+  {-# Inline minFinite  #-}+
+ Biobase/Types/Index.hs view
@@ -0,0 +1,116 @@++-- | Biological sequence data is oftentimes indexed either @0-@ or+-- @1-@based. The @Index@ type developed provides static guarantees that+-- there is no confusion what index is in use.+--+-- This module does not export the ctor @Index@. If you want to (unsafely)+-- use it, import @Biobase.Types.Index.Type@ directly. Use @fromInt0@ to+-- make clear that you count from 0 and transform to an @Index t@. I.e.+-- @fromInt0 0 :: Index 1@ yields the lowest 1-base index.+--+-- Note that internally, every lowest index starts at @0 :: Int@.++module Biobase.Types.Index+  ( module Biobase.Types.Index+  , getIndex+  , index+  , maybeIndex+  , Index+  ) where++import Data.Coerce+import Data.Proxy+import GHC.TypeLits+import Text.Printf++import Biobase.Types.Index.Type -- hiding (getIndex)+import qualified Biobase.Types.Index.Type as IT++++-- | Uses 'index' to guarantee that the 'Index' is ok.++checkIndex :: forall t . KnownNat t => Index t -> Index t+checkIndex i@(Index z)+  | z >= 0    = i+  | otherwise = error $ printf "%d < Index %d\n" (z+n) n+  where n :: Int = fromIntegral $ natVal (Proxy :: Proxy t)+{-# Inline checkIndex #-}++-- | Re-Index an index of type @Index n@ as @Index m@. This is always safe,+-- as @0 :: Index 0@ gives @1 :: Index 1@ for example. I.e. valid indices+-- become valid indices.++reIndex ∷ Index n → Index m+{-# Inline reIndex #-}+reIndex = coerce+--reIndex :: forall n m . (KnownNat n, KnownNat m) => Index n -> Index m+--reIndex (Index i) = Index $ i - n + m+--  where n = fromIntegral $ natVal (Proxy :: Proxy n)+--        m = fromIntegral $ natVal (Proxy :: Proxy m)++-- | Helper function that allows @addition@ of an 'Index' and an 'Int',+-- with the 'Int' on the right.++(+.) :: forall t . KnownNat t => Index t -> Int -> Index t+(+.) i n = checkIndex $ unsafePlus i n+{-# Inline (+.) #-}++-- | Helper function that allows @subtraction@ of an 'Index' and an 'Int',+-- with the 'Int' on the right.++(-.) :: forall t . KnownNat t => Index t -> Int -> Index t+(-.) i n = checkIndex $ unsafePlus i (negate n)+{-# Inline (-.) #-}++-- | Unsafe plus.++unsafePlus :: forall t . KnownNat t => Index t -> Int -> Index t+unsafePlus i n = Index $ IT.getIndex i + n+{-# Inline unsafePlus #-}++-- | Delta between two 'Index' points.++delta :: forall t . KnownNat t => Index t -> Index t -> Int+delta (Index i) (Index j) = abs $ i - j+{-# Inline delta #-}++toInt ∷ forall t . KnownNat t ⇒ Index t → Int+{-# Inline toInt #-}+toInt i = IT.getIndex i + (fromIntegral $ natVal (Proxy ∷ Proxy t))++-- | Return the index as an @Int@-style index that is zero-based.++toInt0 :: forall t . KnownNat t => Index t -> Int+toInt0 = IT.getIndex+{-# Inline toInt0 #-}++-- | Return the index as an @Int@-style index that is one-based.++toInt1 ∷ forall t . KnownNat t ⇒ Index t → Int+{-# Inline toInt1 #-}+toInt1 = (+1) . toInt0++fromInt1 ∷ forall t . KnownNat t ⇒ Int → Index t+{-# Inline fromInt1 #-}+fromInt1 = fromInt0 . (subtract 1)++-- | As an index from an @Int@-style zero-based one.+--+-- TODO We might want to check that the argument is @[0..]@.++fromInt0 :: forall t . KnownNat t => Int -> Index t+fromInt0 i+  | i >= 0    = Index i+  | otherwise = error "fromInt0 needs an Int >= 0"+  where t = fromIntegral $ natVal (Proxy :: Proxy t)+{-# Inline fromInt0 #-}++-- | Zero-based indices.++type I0 = Index 0++-- | One-based indices.++type I1 = Index 1+
+ Biobase/Types/Index/Type.hs view
@@ -0,0 +1,117 @@++module Biobase.Types.Index.Type where++import           Control.Applicative ((<$>))+import           Control.DeepSeq+import           Data.Aeson+import           Data.Binary+import           Data.Data (Data)+import           Data.Hashable (Hashable)+import           Data.Proxy+import           Data.Serialize (Serialize)+import           Data.Typeable (Typeable)+import           Data.Vector.Fusion.Stream.Monadic (Step(..), flatten)+import           Data.Vector.Unboxed.Deriving+import           GHC.Generics+import           GHC.TypeLits+import qualified Data.Ix as Ix+import qualified Data.Vector.Fusion.Stream.Monadic as SM+import           Test.QuickCheck+import           Text.Printf++import           Data.PrimitiveArray.Index.Class hiding (Index)+import qualified Data.PrimitiveArray.Index.Class as PA++++-- | A linear @Int@-based index type.++newtype Index (t :: Nat) = Index { getIndex :: Int }+  deriving (Show,Read,Eq,Ord,Generic,Ix.Ix,Data,Typeable)++-- | Turn an 'Int' into an 'Index' safely.++index :: forall t . KnownNat t => Int -> Index t+index i = maybe (error $ printf "%d < Index %d\n" i n) id $ maybeIndex i+  where n = natVal (Proxy :: Proxy t)+{-# Inline index #-}++-- | Produce 'Just' and 'Index' or 'Nothing'.++maybeIndex :: forall t . KnownNat t => Int -> Maybe (Index t)+maybeIndex i+  | i >= n    = Just . Index $ i - n+  | otherwise = Nothing+  where n = fromIntegral $ natVal (Proxy :: Proxy t)+{-# Inline maybeIndex #-}++instance KnownNat t => Num (Index t) where+  Index a + Index b = error $ show (" Index.(+) not implemented, use (+.)",a,b) -- index $ a + b+  Index a - Index b = error $ show (" Index.(-) not implemented, use (-.)",a,b) -- index $ a - b+  Index a * Index b = error $ show (" Index.(*) not implemented", a,b) -- index $ a * b+  negate = error "Indices are natural numbers"+  abs = id+  signum = index . signum . getIndex+  fromInteger = index . fromIntegral+  {-# Inline fromInteger #-}++instance NFData (Index t) where+  rnf = rnf . getIndex+  {-# Inline rnf #-}++instance Binary    (Index t)+instance Serialize (Index t)+instance ToJSON    (Index t)+instance FromJSON  (Index t)+instance Hashable  (Index t)++derivingUnbox "Index"+  [t| forall t . Index t -> Int |]  [| getIndex |]  [| Index |]++instance forall t . KnownNat t => PA.Index (Index t) where+  newtype LimitType (Index t) = LtIndex Int+  linearIndex (LtIndex k) (Index z) = z+  {-# INLINE linearIndex #-}+  size (LtIndex h) = h + 1+  {-# INLINE size #-}+  inBounds (LtIndex h) (Index x) = 0<=x && x<=h+  {-# INLINE inBounds #-}+  zeroBound = Index 0+  {-# Inline zeroBound #-}+  zeroBound' = LtIndex 0+  {-# Inline zeroBound' #-}+  totalSize (LtIndex k) = [fromIntegral k]+  {-# Inline totalSize #-}+  fromLinearIndex _ = Index+  {-# Inline [0] fromLinearIndex #-}+  showBound (LtIndex k) = ["LtIndex " ++ show k]+  showIndex (Index k) = ["Index " ++ show k]++instance (KnownNat t, IndexStream z) ⇒ IndexStream (z:.Index t) where+  streamUp (ls:..LtIndex lf) (hs:..LtIndex ht) = flatten mk step $ streamUp ls hs+    where mk z = return (z,lf)+          step (z,k)+            | k > ht    = return $ Done+            | otherwise = return $ Yield (z:.Index k) (z,k+1)+          {-# Inline [0] mk   #-}+          {-# Inline [0] step #-}+  {-# Inline streamUp #-}+  streamDown (ls:..LtIndex lf) (hs:..LtIndex ht) = flatten mk step $ streamDown ls hs+    where mk z = return (z,ht)+          step (z,k)+            | k < lf    = return $ Done+            | otherwise = return $ Yield (z:.Index k) (z,k-1)+          {-# Inline [0] mk   #-}+          {-# Inline [0] step #-}+  {-# Inline streamDown #-}++instance (KnownNat t) ⇒ IndexStream (Index t) where+  streamUp l h = SM.map (\(Z:.i) -> i) $ streamUp (ZZ:..l) (ZZ:..h)+  {-# INLINE streamUp #-}+  streamDown l h = SM.map (\(Z:.i) -> i) $ streamDown (ZZ:..l) (ZZ:..h)+  {-# INLINE streamDown #-}++instance Arbitrary (Index t) where+  arbitrary = Index <$> arbitrary+  shrink (Index j) = map Index $ shrink j+
+ Biobase/Types/Location.hs view
@@ -0,0 +1,253 @@++-- | Annotate the genomic @Location@ of features or elements. A @Location@ is+-- always contiguous, using strand, 0-based position, and length.+-- Transformation to different systems of annotation is made possible.++module Biobase.Types.Location where++import Control.DeepSeq+import Control.Lens hiding (Index, index)+import Data.Coerce+import Data.Data+import Data.Data.Lens+import GHC.Generics (Generic)+import GHC.TypeNats+import Prelude hiding (length)+import qualified Data.ByteString as BS+import qualified Streaming.Internal as SI+import qualified Streaming.Prelude as SP+import Text.Printf++import Biobase.Types.BioSequence+import Biobase.Types.Index+import Biobase.Types.Position+import Biobase.Types.Strand+import Data.Info+++++-- | Operations on locations.++class ModifyLocation posTy seqTy where+  -- | Append to the left.+  locAppendLeft  :: seqTy -> Location i posTy seqTy -> Location i posTy seqTy+  -- | Append to the right.+  locAppendRight :: seqTy -> Location i posTy seqTy -> Location i posTy seqTy+  -- | Split a location.+  locSplitAt  :: Int -> Location i posTy seqTy -> (Location i posTy seqTy, Location i posTy seqTy)+  -- | Length of location+  locLength :: Location i posTy seqTy -> Int++locTake k = fst . locSplitAt k++locTakeEnd k loc = let l = locLength loc in snd $ locSplitAt (l-k) loc++locDrop k = snd . locSplitAt k++locDropEnd k loc = let l = locLength loc in fst $ locSplitAt (l-k) loc++locSplitEndAt k loc = let l = locLength loc in locSplitAt (l-k) loc++++data Location ident posTy seqTy = Location+  { _locIdentifier  :: !(SequenceIdentifier ident)+  , _locPosition    :: !posTy+  , _locSequence    :: !seqTy+  }+  deriving stock (Show,Data,Typeable,Generic)+makeLenses ''Location++instance (NFData p, NFData s) => NFData (Location i p s)++retagLocation :: Location i posTy seqTy -> Location j posTy seqTy+{-# Inline retagLocation #-}+retagLocation = over locIdentifier coerce++instance ModifyLocation FwdPosition (BioSequence w) where+  {-# Inline locAppendLeft #-}+  locAppendLeft s loc = let l = s^._BioSequence.to BS.length+    in loc & locSequence %~ (s <>) & locPosition %~ (\p -> if p^.fwdStrand == PlusStrand then p & fwdStart %~ (-. l) else p)+  {-# Inline locAppendRight #-}+  locAppendRight s loc = let l = s^._BioSequence.to BS.length+    in loc & locSequence %~ (<> s) & locPosition %~ (\p -> if p^.fwdStrand == MinusStrand then p & fwdStart %~ (-. l) else p)+  {-# Inline locSplitAt #-}+  locSplitAt k loc =+    let (h',t') = loc^.locSequence._BioSequence.to (BS.splitAt k)+        hl = BS.length h' ; tl = BS.length t'+        h = loc & locSequence._BioSequence .~ h' & locPosition %~ (\p -> if p^.fwdStrand == MinusStrand then p & fwdStart %~ (+. tl) else p)+        t = loc & locSequence._BioSequence .~ t' & locPosition %~ (\p -> if p^.fwdStrand == PlusStrand then p & fwdStart %~ (+. hl) else p)+    in  (h,t)+  {-# Inline locLength #-}+  locLength = view (locSequence._BioSequence.to BS.length)++instance ModifyLocation FwdPosition Int where+  {-# Inline locAppendLeft #-}+  locAppendLeft k' loc = let k = max 0 $ min (loc^.locPosition.fwdStart.to toInt0) k' in+    loc & locSequence %~ (+ k) & locPosition %~ (\p -> if p^.fwdStrand == PlusStrand then p & fwdStart %~ (-. k) else p)+  {-# Inline locAppendRight #-}+  locAppendRight k' loc = let k = max 0 $ min (loc^.locPosition.fwdStart.to toInt0) k' in+    loc & locSequence %~ (+ k) & locPosition %~ (\p -> if p^.fwdStrand == MinusStrand then p & fwdStart %~ (-. k) else p)+  {-# Inline locSplitAt #-}+  locSplitAt k loc =+    let h' = max 0 . min k $ locLength loc+        t' = locLength loc - h'+        h = loc & locSequence .~ h' & locPosition %~ (\p -> if p^.fwdStrand == MinusStrand then p & fwdStart %~(+. t') else p)+        t = loc & locSequence .~ t' & locPosition %~ (\p -> if p^.fwdStrand == PlusStrand then p & fwdStart %~ (+. h') else p)+    in  (h,t)+  {-# Inline locLength #-}+  locLength = view locSequence++instance Reversing (Location i FwdPosition (BioSequence w)) where+  {-# Inline reversing #-}+  reversing = over (locSequence._BioSequence) BS.reverse . over (locPosition) reversing++instance Complement (BioSequence w) => Complement (Location i FwdPosition (BioSequence w)) where+  {-# Inline complement #-}+  complement = iso f f+    where f = over locSequence (view complement)++instance (Info (BioSequence w)) => Info (Location i FwdPosition (BioSequence w)) where+  info loc = printf "%s %s %s" (loc^.locIdentifier^.to show) (show $ loc^.locPosition) (loc^.locSequence.to info)++-- | Will extract a substring for a given biosequence. It is allowed to hand in partially or not at+-- all overlapping locational information. This will yield empty resulting locations.+--+-- This will convert the @FwdPosition@ strand, which in turn allows dealing with reverse-complement+-- searches.+--+-- @+-- 0123456789+--    3.3+-- @++subLocation :: Location i FwdPosition (BioSequence w) -> (FwdPosition, Int) -> Location i FwdPosition (BioSequence w)+{-# Inline subLocation #-}+subLocation s (p',l)+  | ss==PlusStrand = locTake l $ locDrop d s+  | ss==MinusStrand = locTakeEnd l $ locDropEnd d s+  where ss = s^.locPosition.fwdStrand+        p = if ss == p'^.fwdStrand then p' else reversing p'+        d = delta (s^.locPosition.fwdStart) (p^.fwdStart)++data PIS i p s = PIS+  { _pisPrefix  :: Maybe (Location i p s)+  , _pisInfix   :: !(Location i p s)+  , _pisSuffix  :: Maybe (Location i p s)+  }+  deriving stock (Show, Data)+makeLenses ''PIS++pis ifx = PIS Nothing ifx Nothing++retagPis :: PIS i p s -> PIS j p s+retagPis (PIS p i s) = PIS (fmap retagLocation p) (retagLocation i) (fmap retagLocation s)++-- | Given a @PIS@, this will return the @substring@ indicated by the location in the 2nd argument.+-- Allows for easy substring extraction, and retains the system of prefix/infix/suffix.+--+-- It is allowed to hand locations that only partially (or not at all) correspond to the @PIS@, but+-- then the resulting @PIS@ will be empty!++subPisLocation :: PIS i FwdPosition (BioSequence w) -> (FwdPosition, Int) -> PIS i FwdPosition (BioSequence w)+{-# Inline subPisLocation #-}+subPisLocation pis loc =+  let f z = subLocation z loc+  in  over (pisPrefix._Just) f . over pisInfix f $ over (pisSuffix._Just) f pis++instance (Reversing (Location i FwdPosition (BioSequence w))) => Reversing (PIS i FwdPosition (BioSequence w)) where+  {-# Inline reversing #-}+  reversing pis+    = over (pisPrefix._Just) reversing . over pisInfix reversing . over (pisSuffix._Just) reversing+    . set pisPrefix (pis^.pisSuffix) . set pisSuffix (pis^.pisPrefix) $ pis++instance Complement (BioSequence w) => Complement (PIS i FwdPosition (BioSequence w)) where+  {-# Inline complement #-}+  complement =+    let f = over pisInfix (view complement) . over (pisPrefix._Just) (view complement) . over (pisSuffix._Just) (view complement)+    in  iso f f++pisSequence :: Lens (PIS i p (BioSequence s)) (PIS i p (BioSequence t)) (BioSequence s) (BioSequence t)+{-# Inline pisSequence #-}+pisSequence = lens f t where+  v = view (locSequence.bioSequence)+  f (PIS p i s) = BioSequence $ maybe BS.empty v p `BS.append` v i `BS.append` maybe BS.empty v s+  t (PIS p i s) (BioSequence str) =+    let (pfx,ifxsfx) = over _1 BioSequence   $ BS.splitAt (maybe 0 (BS.length . v) p) str+        (ifx,sfx   ) = over both BioSequence $ BS.splitAt (BS.length $ v i) ifxsfx+    in  PIS (set (_Just . locSequence) pfx p) (set locSequence ifx i) (set (_Just . locSequence) sfx s)++++-- | Given a @Location@ with a @BioSequence@, replace the sequence with its length.++locAsLength :: Location i FwdPosition (BioSequence w) -> Location i FwdPosition Int+{-# Inline locAsLength #-}+locAsLength = over locSequence (view (_BioSequence.to BS.length))++++-- | Provides a range in a notation as used by blast, for example. This+-- isomorphism can translate back as well. @FwdLocation - 8 4 ^. blastRange1 ==+-- 9 6 MinusStrand@, since these ranges are 1-based and start and end included.++blastRange1 :: (Location i FwdPosition Int) -> (Int,Int,Strand)+{-# Inline blastRange1 #-}+blastRange1 = f -- iso f t+  where+    f loc =+      let s = loc^.locPosition.fwdStart.to toInt1+          l = loc^.locSequence+          pm = loc^.locPosition.fwdStrand+      in  case pm of PlusStrand -> (s,s+l,pm) ; MinusStrand -> (s+l,s,pm)+--    t (x,y,pm) =+--      let s = fromInt1 x+--          l = 1 + abs (x-y)+--      in  Location (FwdPosition pm s) l++++-- | For each element, attach the prefix as well. The @Int@ indicates the maximal prefix length to+-- attach.+--+-- @1 2 3 4@ -> @01 12 23 34@+--+-- TODO are we sure this is correct for @MinusStrand@?++attachPrefixes+  :: ( Monad m, ModifyLocation p s )+  => Int+  -> SP.Stream (SP.Of (PIS i p s)) m r+  -> SP.Stream (SP.Of (PIS i p s)) m r+{-# Inlinable attachPrefixes #-}+attachPrefixes k = SP.map (\(Just w) -> w) . SP.drop 1 . SP.scan go Nothing id+  where+    go Nothing = Just+    go (Just p) = Just . set pisPrefix (Just . locTakeEnd k $ view pisInfix p)++++-- | For each element, attach the suffix as well.+--+-- @1 2 3 4@ -> @12 23 34 40@++attachSuffixes+  :: ( Monad m, ModifyLocation p s )+  => Int+  -> SP.Stream (SP.Of (PIS i p s)) m r+  -> SP.Stream (SP.Of (PIS i p s)) m r+{-# Inlinable attachSuffixes #-}+attachSuffixes k = loop Nothing+  where+    loop Nothing = \case+      SI.Return r -> SI.Return r+      SI.Effect m -> SI.Effect $ fmap (loop Nothing) m+      SI.Step (a SP.:> rest) -> loop (Just a) rest+    loop (Just p) = \case+      SI.Return r -> SI.Step (p SP.:> SI.Return r)+      SI.Effect m -> SI.Effect $ fmap (loop (Just p)) m+      SI.Step (a SP.:> rest) ->+        let p' = p & set pisSuffix (Just . locTake k $ view pisInfix a)+        in  SI.Step (p' SP.:> loop (Just a) rest)+
+ Biobase/Types/Names.hs view
@@ -0,0 +1,143 @@++-- | Names for biological things.+--+-- Species names are internalized and represented as an @Int@. This allows+-- using them in structures like an @IntMap@.+--+-- For other names, we newtype-wrap normal text internalization.+--++module Biobase.Types.Names where++import Control.Applicative+import Control.DeepSeq (NFData(..))+import Data.Aeson as A+import Data.Binary      as DB+import Data.Hashable+import Data.Interned+import Data.Interned.Text+import Data.Serialize   as DS+import Data.Serialize.Text+import Data.String as IS+import Data.String.Conversions (ConvertibleStrings(..), cs)+import Data.String.Conversions.Monomorphic (toST, fromST)+import Data.Text.Binary+import Data.Text (Text, pack, unpack)+import Data.Vector.Unboxed.Deriving+import GHC.Generics++import Biobase.Types.Names.Internal++++-- * Int-internalized species names.++-- | A species name. Represented with an @Int@, but behaves like a @Text@.++newtype SpeciesName = SpeciesName { getSpeciesNameRep :: Int }+  deriving (Eq,Generic)++derivingUnbox "SpeciesName"+  [t| SpeciesName -> Int |]+  [|  getSpeciesNameRep  |]+  [|  SpeciesName        |]++instance Ord SpeciesName where+  SpeciesName l `compare` SpeciesName r = speciesNameBimapLookupInt l `compare` speciesNameBimapLookupInt r+  {-# Inline compare #-}++-- | Smart constructor that performs the correct internalization.++speciesName :: Text -> SpeciesName+speciesName = SpeciesName . speciesNameBimapAdd+{-# Inline speciesName #-}++instance IsString SpeciesName where+  fromString = speciesName . IS.fromString+  {-# Inline fromString #-}++instance Show SpeciesName where+  showsPrec p i r = showsPrec p (unpack $ toST i) r+  {-# Inline showsPrec #-}++instance Read SpeciesName where+  readsPrec p str = [ (speciesName $ IS.fromString s, y) | (s,y) <- readsPrec p str ]+  {-# Inline readsPrec #-}++instance Hashable SpeciesName++instance ConvertibleStrings Text SpeciesName where+  convertString = speciesName++instance ConvertibleStrings SpeciesName Text where+  convertString = speciesNameBimapLookupInt . getSpeciesNameRep++instance NFData SpeciesName++instance Binary SpeciesName where+  put = DB.put . toST+  get = fromST <$> DB.get+  {-# Inline put #-}+  {-# Inline get #-}++instance Serialize SpeciesName where+  put = DS.put . toST+  get = fromST <$> DS.get+  {-# Inline put #-}+  {-# Inline get #-}++instance FromJSON SpeciesName where+  parseJSON s = fromST <$> parseJSON s+  {-# Inline parseJSON #-}++instance ToJSON SpeciesName where+  toJSON = toJSON . toST+  {-# Inline toJSON #-}++++-- * Internalize taxonomic rank names++-- | The taxonomic rank. This encodes the name for a given rank.++newtype TaxonomicRank = TaxonomicRank { getTaxonomicRank :: InternedText }+  deriving (IsString,Eq,Ord,Show,Generic)++instance NFData TaxonomicRank where+  rnf (TaxonomicRank it) = rnf (internedTextId it)+  {-# Inline rnf #-}++instance ConvertibleStrings Text TaxonomicRank where+  convertString = TaxonomicRank . intern++instance ConvertibleStrings TaxonomicRank Text where+  convertString = unintern . getTaxonomicRank++instance Hashable TaxonomicRank where+  hashWithSalt s (TaxonomicRank it) = hashWithSalt s (internedTextId it)+  {-# Inline hashWithSalt #-}++instance Read TaxonomicRank where+  readsPrec p str = [ (IS.fromString s, y) | (s,y) <- readsPrec p str ]+  {-# Inline readsPrec #-}++instance Binary TaxonomicRank where+  put = DB.put . toST+  get = fromST <$> DB.get+  {-# Inline put #-}+  {-# Inline get #-}++instance Serialize TaxonomicRank where+  put = DS.put . toST+  get = fromST <$> DS.get+  {-# Inline put #-}+  {-# Inline get #-}++instance FromJSON TaxonomicRank where+  parseJSON s = fromST <$> parseJSON s+  {-# Inline parseJSON #-}++instance ToJSON TaxonomicRank where+  toJSON = toJSON . toST+  {-# Inline toJSON #-}+
+ Biobase/Types/Names/Internal.hs view
@@ -0,0 +1,36 @@++module Biobase.Types.Names.Internal where++import Data.IORef (newIORef,IORef,readIORef,atomicWriteIORef,atomicModifyIORef')+import Data.Text (Text)+import System.IO.Unsafe (unsafePerformIO,unsafeDupablePerformIO)++import Data.Bijection.HashMap+import Data.Bijection.Vector++++speciesNameBimap :: IORef (Bimap (HashMap Text Int) (Vector Text))+speciesNameBimap = unsafePerformIO $ newIORef empty+{-# NoInline speciesNameBimap #-}++-- | Add @Text@ and return @Int@ key. Will return key for+-- existing string and thereby serves for lookup in left-to-right+-- direction.++speciesNameBimapAdd :: Text -> Int+speciesNameBimapAdd k = unsafeDupablePerformIO $ atomicModifyIORef' speciesNameBimap $ \m ->+  case lookupL m k of Just i  -> (m,i)+                      Nothing -> let s = size m+                                 in  (insert m (k,s) , s)+{-# Inline speciesNameBimapAdd #-}++-- | Lookup the @InternedMultiChar@ based on an @Int@ key. Unsafe totality+-- assumption.++speciesNameBimapLookupInt :: Int -> Text+speciesNameBimapLookupInt r = seq r . unsafeDupablePerformIO $ atomicModifyIORef' speciesNameBimap $ \m ->+  case lookupR m r of Just l  -> (m,l)+                      Nothing -> error "speciesNameBimapLookupInt: totality assumption invalidated"+{-# Inline speciesNameBimapLookupInt #-}+
− Biobase/Types/Partition.hs 
@@ -1,84 +0,0 @@--{-# LANGUAGE ForeignFunctionInterface #-}-{-# LANGUAGE StandaloneDeriving #-}-{-# LANGUAGE MultiParamTypeClasses #-}-{-# LANGUAGE GeneralizedNewtypeDeriving #-}--module Biobase.Types.Partition where--import qualified Data.Vector.Unboxed as VU-import qualified Data.Vector.Generic as VG-import qualified Data.Vector.Generic.Mutable as VGM-import Data.Primitive.Types--import Biobase.Types.Ring------ | Some default instances. Left out the Num one, so that you have to--- explicitly instanciate if you want to go around the Ring structure.--newtype Partition = Partition {unPartition' :: Double}-  deriving (Show, Read, Eq, Ord)---- |--mkPartition :: Double -> Partition-mkPartition x-  | x < 0     = error $ "mkPartition: prob <0: " ++ show x-  | x > 1     = error $ "mkPartition: prob >1: " ++ show x-  | otherwise = Partition $ log x--unPartition :: Partition -> Double-unPartition (Partition x) = exp x----- | Ring operations over Partition values.--instance Ring Partition where-  (Partition a) .+. (Partition b) = Partition $ logSum a b-  {-# INLINE (.+.) #-}-  (Partition a) .*. (Partition b) = Partition $ a + b-  {-# INLINE (.*.) #-}-  (Partition a) .^. k = Partition $ a * fromIntegral k-  {-# INLINE (.^.) #-}-  (Partition a) .^^. k = error ".^^. not defined for Partition" -- Partition $ a ^^ k-  {-# INLINE (.^^.) #-}-  neg (Partition a) = error $ "negate partition? " ++ show a -- Partition $ negate a-  {-# INLINE neg #-}-  one = Partition 1-  {-# INLINE one #-}-  zero = Partition 0-  {-# INLINE zero #-}-  isZero (Partition a) = a == 0 -- TODO use some epsilon?-  {-# INLINE isZero #-}--logSum :: Double -> Double -> Double-logSum a b-  | a>b       = f a b-  | otherwise = f b a-  where-    f x y = x + log1p (exp $ y - x)-    {-# INLINE f #-}-{-# INLINE logSum #-}------ * Vector (and Prim) instances.--deriving instance VGM.MVector VU.MVector Partition-deriving instance VG.Vector VU.Vector Partition-deriving instance VU.Unbox Partition-deriving instance Prim Partition------ * math.h function for log/exp on pm1 are /much/ more efficient (what is--- haskell doing?)--foreign import ccall unsafe "math.h log1p"-    log1p :: Double -> Double--foreign import ccall unsafe "math.h expm1"-    expm1 :: Double -> Double-
+ Biobase/Types/Position.hs view
@@ -0,0 +1,163 @@++-- | Annotate the genomic @position@ of features or elements. A @position@ has strand information,+-- and different ways to encode where a feature is located. The @position@ points to the first+-- element (e.g. nucleotide).+--+-- Together with the 'Biobase.Types.Location' module, it becomes possible to annotate substrings.++module Biobase.Types.Position where++import Control.DeepSeq+import Control.Lens hiding (Index, index)+import Data.Data+import GHC.Generics (Generic)+import GHC.TypeNats+import Prelude hiding (length)+import Text.Printf++import Biobase.Types.Index+import Biobase.Types.Strand+import Data.Info++{-++-- | Location information.++data Location = Location+  { _lStrand :: !Strand+  -- ^ On which strand are we+  , _lStart  :: !(Index 0)+  -- ^ Start, 0-based+  , _lLength :: !Int+  -- ^ number of characters in this location+  , _lTotalLength :: !Int+  -- ^ the total length of the "contig" (or whatever) this location is positioned in.+  } deriving (Eq,Ord,Read,Show,Generic)+makeLenses ''Location+makePrisms ''Location++instance NFData Location++instance Semigroup Location where+  x <> y = let f z = z { _lLength = _lLength x + _lLength y }+    in case x^.lStrand of+      MinusStrand  -> f y+      _otherStrand -> f x+  {-# Inline (<>) #-}++--instance Reversing Location where+--  {-# Inline reversing #-}+--  reversing = undefined+++-- | An isomorphism between locations, and triples of @Strand,Start,End@, where+-- end is inclusive. For @length==0@ locations, this will mean @start<end@ on+-- the plus strand.+--+-- This should hold for all @k@, in @Index k@.++startEndInclusive :: (KnownNat k) => Iso' Location (Strand, (Index k, Index k), Int)+{-# Inline startEndInclusive #-}+startEndInclusive = iso l2r r2l+  where l2r z = let s = z^.lStrand; f = z^.lStart; l = z^.lLength+                in  (s, (reIndex f, reIndex $ f +. l -. 1), z^.lTotalLength)+        r2l (s,(f,t),ttl) = Location s (reIndex f) (delta f t + 1) ttl++-}++++-- | During streaming construction, it is possible that we know a feature is on the @-@ strand, but+-- the length of the contig is not known yet. In that case, 'FwdPosition' allows expressing the hit+-- in the coordinate system of the plus strand. Tools like blast do something similar, and express+-- locations on the minus as @y-x@ with @y>x@.+--+-- @+-- 0123456789+--  >-->+--      <--<+-- 9876543210+-- @+--+-- ++data FwdPosition+  -- | "Plus"-based location.+  = FwdPosition+      { _fwdStrand :: !Strand+      -- ^ Strand we are on+      , _fwdStart  :: !(Index 0)+      -- ^ Start of the hit on the plus strand+      }+  deriving (Eq,Ord,Read,Show,Data,Typeable,Generic)+makeLenses ''FwdPosition+makePrisms ''FwdPosition++instance NFData FwdPosition++instance Info FwdPosition where+  info (FwdPosition s x) = printf "%s %d" (show s) (toInt0 x)++-- | Reversing a reversible location means moving the start to the end.++instance Reversing FwdPosition where+  {-# Inline reversing #-}+  reversing x = case x^.fwdStrand of+    PlusStrand    -> set fwdStrand MinusStrand $ x+    MinusStrand   -> set fwdStrand PlusStrand  $ x+    UnknownStrand -> x++{-+++-- | Combining two FwdLocations yields the sum of their lengths. This assumes+-- that @x@ and @y@ are next to each other, or that it is ok if the @y@+-- @fwdStart@ information may be lost.+--+-- TODO provide associativity test in @properties@.++instance Semigroup FwdLocation where+  x <> y = over fwdLength (+ view fwdLength y) x+  {-# Inline (<>) #-}++instance ModifyLocation FwdLocation where+  locMoveLeftEnd k = over fwdStart (+. k) . over fwdLength (subtract k)+  locMoveRightEnd k = over fwdLength (+k)++-- | Given a location, take at most @k@ elements, and return a location after+-- this change.++fwdLocationTake :: Int -> FwdLocation -> FwdLocation+{-# Inline fwdLocationTake #-}+fwdLocationTake k' x =+  let l = x^.fwdLength+      k = max 0 $ min k' l      -- deal with at most the length of the location+  in case x^.fwdStrand of+    MinusStrand  -> set fwdLength k $ over fwdStart (+. (l-k)) x+    _otherStrand -> set fwdLength k $                          x++-- | Given a location, drop at most @k@ elements, and return a location after+-- this change.+--+-- Note that @fwdLocationDrop 4 (FwdLocation PlusStrand 0 4) == FwdLocation 4 0@++fwdLocationDrop :: Int -> FwdLocation -> FwdLocation+{-# Inline fwdLocationDrop #-}+fwdLocationDrop k' x =+  let l = x^.fwdLength+      k = max 0 $ min k' l+  in case x^.fwdStrand of+    MinusStrand  -> set fwdLength (l-k) $                            x+    _otherStrand -> set fwdLength (l-k) $ over fwdStart (+. min k l) x++-- -- An isomorphism between a 'Location' and the pair @('FwdLocation',Int)@+-- -- exists.+-- +-- locationPartial :: Iso' Location (FwdLocation,Int)+-- {-# Inline locationPartial #-}+-- locationPartial = iso l2r r2l where+--   l2r l = undefined+--   r2l (p,z) = undefined++-}+
+ Biobase/Types/ReadingFrame.hs view
@@ -0,0 +1,54 @@++-- | Stranded reading frames.++module Biobase.Types.ReadingFrame where++import Control.Lens hiding (Index)+import GHC.Generics hiding (from)++import Biobase.Types.Index (Index, toInt0)+import Biobase.Types.Strand++++-- | The Reading frame. Sequence indexing starts at position 1, which starts+-- reading frame 1. Reading frame 2 and 3 start at position 2 and 3+-- respectively.++newtype ReadingFrame = ReadingFrame { getReadingFrame ∷ Int }+  deriving (Eq,Ord,Generic,Show)+makeWrapped ''ReadingFrame++-- | Convert between @+1 ... +3@ and @ReadingFrame@.++rf ∷ Prism' Int ReadingFrame+{-# Inline rf #-}+rf = prism' getReadingFrame $ \k → let ak = abs k in+  if (ak <=  3 && ak >= 1) then Just (ReadingFrame k) else Nothing++-- | A lens for the strand++strandRF ∷ Lens' ReadingFrame Strand+{-# Inline strandRF #-}+strandRF = lens (\(ReadingFrame k) → if k < 0 then MinusStrand else PlusStrand)+                (\(ReadingFrame k) s → ReadingFrame $ if s == PlusStrand then abs k else (negate $ abs k))++-- |+--+-- @pred@ and @succ@ are correct, if the input is a legal 'ReadingFrame'.++instance Enum ReadingFrame where+  {-# Inline toEnum #-}+  toEnum k = case k^?rf of Just rf → rf ; Nothing → error $ show k ++ " is not a legal reading frame"+  {-# Inline fromEnum #-}+  fromEnum = getReadingFrame++-- |+--+-- TODO should this be a type class, since we might reasonably want to+-- construct from a number of possible indices?++fromIndex ∷ Index 1 → ReadingFrame+{-# Inline fromIndex #-}+fromIndex i = ReadingFrame $ (toInt0 i `mod` 3) + 1+
− Biobase/Types/Ring.hs 
@@ -1,22 +0,0 @@---- | Algebraic ring structure. Very similar to others found throughout hackage.------ TODO maybe use on of the already-written packages?--module Biobase.Types.Ring where------ | Define the basic operations on a ring.--class (Eq a, Ord a) => Ring a where-  (.+.), (.*.) :: a -> a -> a-  (.^.) :: a -> Int -> a-  (.^^.) :: a -> Double -> a-  neg :: a -> a-  one, zero :: a-  isZero :: a -> Bool -- ^ ==zero does not work well for min-plus-  infixl 6 .+.-  infixl 7 .*.-  infixr 8 .^.-  infixr 8 .^^.
− Biobase/Types/Score.hs 
@@ -1,48 +0,0 @@--{-# LANGUAGE StandaloneDeriving #-}-{-# LANGUAGE MultiParamTypeClasses #-}-{-# LANGUAGE GeneralizedNewtypeDeriving #-}--module Biobase.Types.Score where--import qualified Data.Vector.Unboxed as VU-import qualified Data.Vector.Generic as VG-import qualified Data.Vector.Generic.Mutable as VGM-import Data.Primitive.Types--import Biobase.Types.Ring------ | Some default instances. Left out the Num one, so that you have to--- explicitly instanciate if you want to go around the Ring structure.--newtype Score = Score {unScore :: Int}-  deriving (Show, Read, Eq, Ord)------ | Ring operations over Score values.--instance Ring Score where-  (Score a) .+. (Score b) = Score $ a `min` b-  {-# INLINE (.+.) #-}-  (Score a) .*. (Score b) = Score $ a + b-  {-# INLINE (.*.) #-}-  neg (Score a) = Score $ negate a-  {-# INLINE neg #-}-  one = Score 0-  {-# INLINE one #-}-  zero = Score 10000000-  {-# INLINE zero #-}-  isZero (Score a) = a >= 1000000-  {-# INLINE isZero #-}------ * Vector instances.--deriving instance VGM.MVector VU.MVector Score-deriving instance VG.Vector VU.Vector Score-deriving instance VU.Unbox Score-deriving instance Prim Score
+ Biobase/Types/Shape.hs view
@@ -0,0 +1,202 @@++-- | Shape abstractions of structures.+--+-- Shapes do not preserve sizes of structures (say unpaired regions or stem+-- length). As such, distance measures provided here are to be used carefully!+--+-- TODO consider how to handle the different shape levels. One option would be+-- to phantom-type everything.++module Biobase.Types.Shape where++import           Control.DeepSeq+import           Control.Lens+import           Control.Monad.Error.Class+import           Control.Monad (foldM,unless)+import           Data.ByteString (ByteString)+import           Data.Data+import           Data.List (foldl1')+import           Data.Monoid ((<>))+import           Data.Set (Set)+import           GHC.Generics (Generic)+import qualified Data.ByteString.Char8 as BS8+import qualified Data.List as L+import qualified Data.Set as Set++import           Data.Forest.StructuredPaired++import qualified Biobase.Types.Structure as TS++++-- | Shape levels are hardcoded according to their specification.+--+-- TODO Allow compile-time check on accepted shape levels?++data ShapeLevel+  = SL1+  | SL2+  | SL3+  | SL4+  | SL5+  deriving (Eq,Ord,Show,Read,Data,Typeable,Generic)++instance NFData ShapeLevel++++-- | The type of RNA shapes. Keeps the type ++data RNAshape+  = RNAshape+    { _rnashapelevel  ∷ !ShapeLevel+    -- ^ The type of shape encoded here.+    , _rnashape       ∷ !ByteString+    -- ^ The actual shape as a string.+    }+  deriving (Eq,Ord,Show,Read,Data,Typeable,Generic)+makeLenses ''RNAshape++instance NFData RNAshape++++-- | Given a compactified 'SPForest', creates a shape forest of the given level.+--+--+--+-- TODO needs newtyping++shapeForest+  ∷ ShapeLevel+  → SPForest ByteString ByteString+  → SPForest Char Char+shapeForest = preStem+  where+    -- | In @preStem@, we aim to close in on the next stem. @SPE@ means that we+    -- reached an end in a stem.+    preStem s SPE = SPE+    -- | The start of a tree structure. The forest is compact, which means that+    -- the element in @xs@ is, by definition, not a continuation of a stack.+    preStem s (SPT _ xs _) = SPT '[' (inStem s xs) ']'+    -- |+    preStem s spr@(SPR rs) = inStem s spr -- = error $ "preStem/SPR " ++ show rs+    -- |+    preStem s (SPJ xs)+      | [x] ← xs  = preStem s x+      -- left bulge+      | [l@SPR{},x@SPT{}] ← xs = if s <= SL2 then (SPJ [SPR '_', preStem s x]) else preStem s x+      -- right bulge+      | [x@SPT{},r@SPR{}] ← xs = if s <= SL2 then (SPJ [preStem s x, SPR '_']) else preStem s x+      | otherwise = SPJ $ map (preStem s) xs -- error $ "preStem/SPJ " ++ show xs+    --+    -- | After a stem, there could be an @SPE@ element.+    inStem s SPE = SPE+    -- | This case happens when eradicating unstructured regions with high+    -- abstraction levels.+    inStem s (SPT _ xs _) = inStem s xs+    inStem s (SPR rs)+      | s == SL1  = SPR '_' -- = error $ "inStem / SPR " ++ show rs+      | otherwise = SPE+    inStem s (SPJ xs)+      | [x] ← xs = error "x"+      -- left bulge+      | [l@SPR{},x] ← xs = if s <= SL3 then preStem s (SPJ xs) else inStem s x+      -- right bulge+      | [x,r@SPR{}] ← xs = if s <= SL3 then preStem s (SPJ xs) else inStem s x+      -- interior loop+      | [l@SPR{},x,r@SPR{}] ← xs = if s == SL5 then inStem s x else preStem s (SPJ xs)+--      | s == SL1  = error $ "inStem / SPJ " ++ show xs+--      | s == SL2  = error $ "inStem / SPJ " ++ show xs+      -- multibranched loop+      | otherwise = SPJ $ map (preStem s) xs++rnass2shape lvl s = shapeForestshape lvl . shapeForest lvl . TS.compactifySPForest+                . either (\e → error $ show (e,s)) id . TS.rnassSPForest $ s++-- | turn into unit test. also reverse of the input should give reverse shape!+-- this then gives a quickcheck test, reversing the input should reverse the shape+--+-- TODO requires generating secondary structures via @Arbitrary@.++test lvl = shapeForestshape lvl . shapeForest lvl $ TS.compactifySPForest $ either error id $ TS.rnassSPForest $ TS.RNAss "(((((...(((..(((...))))))...(((..((.....))..)))))))).."++{-+shapeForest SL5 = go+  where+    go SPE = SPE+    go (SPT _ xs _)+      | SPE ← xs, SPR{} ← xs, [] ← ts = SPT '[' SPE ']'+      | [t] ← ts = go t+      | otherwise = SPT '[' (SPJ $ map go ts) ']'+      where (SPJ ys) = xs+            ts = [ t | t@SPT{} ← ys ]+    -- should only happen on a single unfolded structure+    go (SPR _) = SPR '_'+    go (SPJ xs)+      | [] ← ts   = SPR '_'+      | [t] ← ts  = go t+      | otherwise = SPJ $ map go ts+      where ts = [ t | t@SPT{} ← xs ]+    go xs = error $ show xs ++ " should no be reached"+-}++-- | ++shapeForestshape+  ∷ ShapeLevel+  → SPForest Char Char+  → RNAshape+shapeForestshape lvl = RNAshape lvl . go+  where+    go SPE = ""+    go (SPT l x r) = BS8.singleton l <> go x <> BS8.singleton r+    go (SPJ xs   ) = mconcat $ map go xs+    go (SPR   x  ) = BS8.singleton x -- error "should not be reached" -- BS8.singleton x++generateShape ∷ ShapeLevel → TS.RNAss → RNAshape+generateShape = undefined+++-- * Distance measures on the shape string itself.++-- | Wrapper for string-positional shapes. Intentionally chosen long name.++data RNAshapepset = RNAshapepset { _rnashapepsetlevel ∷ ShapeLevel, _rnashapepset ∷ Set (Int,Int) }+  deriving (Read,Show,Eq,Ord,Generic)+makeLenses ''RNAshapepset++instance NFData RNAshapepset++-- | Transform an 'RNAss' into a set of base pairs @(i,j)@. The pairs are+-- 0-based.++rnashapePairSet+  ∷ (MonadError String m)+  ⇒ RNAshape+  → m RNAshapepset+rnashapePairSet (RNAshape lvl s2) = do+  let go (set,ks  ) (i,'[') = return (set,i:ks)+      go (set,i:is) (j,']') = return (Set.insert (i,j) set, is)+      go (set,[]  ) (j,']') = throwError $ "unequal brackets in \"" ++ BS8.unpack s2 ++ "\" at position: " ++ show j+      go (set,ks  ) (_,'_') = return (set,ks)+  (set,ss) ← foldM go (Set.empty,[]) . L.zip [0..] $ BS8.unpack s2+  unless (null ss) $ throwError $ "unequal brackets in \"" ++ BS8.unpack s2 ++ "\" with opening bracket(s): " ++ show ss+  return $ RNAshapepset lvl set+{-# Inlinable rnashapePairSet #-}++-- | RNA pair set, but a transformation error calls @error@.++rnassPairSet' ∷ RNAshape → RNAshapepset+rnassPairSet' = either error id . rnashapePairSet++-- | Calculates the number of different base pairs betwwen two structures.+--+-- TODO error out on different shape levels++shapePairDist ∷ RNAshapepset → RNAshapepset → Int+shapePairDist (RNAshapepset lvl1 p1) (RNAshapepset lvl2 p2) = Set.size z1 + Set.size z2+  where i = Set.intersection p1 p2+        z1 = p1 `Set.difference` i+        z2 = p2 `Set.difference` i+
+ Biobase/Types/Strand.hs view
@@ -0,0 +1,147 @@++-- | Strand information. A newtyped version, complete with serialization,+-- pattern synonyms, being a @PrimitiveArray@ index type, etc. The strand+-- information includes @+@, @-@, as well as the (GFF3) @.@ not stranded, and+-- @?@ for unknown strand information.+--+-- TODO will be expanded to encode biological sense information more clearly:+-- <http://en.wikipedia.org/wiki/Sense_%28molecular_biology%29>.++module Biobase.Types.Strand where++import Control.DeepSeq+import Control.Lens hiding (Index)+import Control.Monad (guard)+import Data.Aeson+import Data.Binary+import Data.Data (Data)+import Data.Hashable (Hashable)+import Data.Serialize (Serialize)+import Data.Typeable (Typeable)+import Data.Vector.Fusion.Stream.Monadic (Step(..), flatten)+import Data.Vector.Unboxed.Deriving+import GHC.Generics+import Test.QuickCheck+import Text.Printf++import Data.PrimitiveArray.Index.Class++++-- | Encode strand information. 'PlusStrand' is defined as the strand encoded+-- in, say, the FASTA file. 'MinusStrand' hence is the reverse complement.++newtype Strand = Strand { getStrand :: Int }+  deriving (Eq,Ord,Generic,Data,Typeable)++instance Show Strand where+  show PlusStrand    = "PlusStrand"+  show MinusStrand   = "MinusStrand"+  show NotStranded   = "NotStranded"+  show UnknownStrand = "UnknownStrand"++instance Read Strand where+  readsPrec _ xs = do+    (pm,s) <- lex xs+    case pm of+      "PlusStrand" -> return (PlusStrand, s)+      "MinusStrand" -> return (MinusStrand, s)+      "NotStranded" -> return (NotStranded, s)+      "UnknownStrand" -> return (UnknownStrand, s)+      [x] | x `elem` ("+Pp" :: String) -> return (PlusStrand,s)+          | x `elem` ("-Mm" :: String) -> return (MinusStrand,s)+          | x `elem` ("."   :: String) -> return (NotStranded,s)+          | x `elem` ("?"   :: String) -> return (UnknownStrand,s)+      _ -> []++instance Bounded Strand where+  minBound = PlusStrand+  maxBound = UnknownStrand++instance Enum Strand where+  succ (Strand k)+    | k <  0 = error "succ undefined strand"+    | k == 3 = error "succ UnknownStrand"+    | k >  3 = error "succ undefined strand"+    | otherwise = Strand (k+1)+  pred (Strand k)+    | k <  0 = error "pred undefined strand"+    | k == 0 = error "pred UnknownStrand"+    | k >  3 = error "pred undefined strand"+    | otherwise = Strand (k-1)+  toEnum i | i>=0 && i<=3 = Strand i+  toEnum i                = error $ "toEnum (Strand)" ++ show i+  fromEnum = getStrand++instance Reversing Strand where+  reversing PlusStrand  = MinusStrand+  reversing MinusStrand = PlusStrand+  reversing x           = x++pattern PlusStrand    = Strand 0+pattern MinusStrand   = Strand 1+pattern NotStranded   = Strand 2+pattern UnknownStrand = Strand 3++-- TODO Sense and Antisense are somewhat different++--pattern Sense     = P+--pattern AntiSense = M++instance Binary    Strand+instance Serialize Strand+instance ToJSON    Strand+instance FromJSON  Strand+instance Hashable  Strand+instance NFData    Strand++derivingUnbox "Strand"+  [t| Strand -> Int |]  [| getStrand |]  [| Strand |]++instance Index Strand where+  newtype (LimitType Strand) = LtStrand Strand+  linearIndex _ (Strand z) = z+  {-# INLINE linearIndex #-}+  size (LtStrand (Strand h)) = h + 1+  {-# INLINE size #-}+  inBounds (LtStrand (Strand h)) (Strand x) = 0<=x && x<=h+  {-# INLINE inBounds #-}+  zeroBound = Strand 0+  {-# Inline zeroBound #-}+  zeroBound' = LtStrand zeroBound+  {-# Inline zeroBound' #-}+  totalSize (LtStrand (Strand k)) = [ fromIntegral (fromEnum k + 1) ]+  {-# Inline totalSize #-}+  fromLinearIndex _ = Strand+  {-# Inline [0] fromLinearIndex #-}+  showBound (LtStrand k) = ["LtStrand " ++ show k]+  showIndex (Strand k) = ["Strand " ++ show k]++instance IndexStream z => IndexStream (z:.Strand) where+  streamUp (ls:..LtStrand (Strand lf)) (hs:..LtStrand (Strand ht)) = flatten mk step $ streamUp ls hs+    where mk z = return (z,lf)+          step (z,k)+            | k > ht    = return $ Done+            | otherwise = return $ Yield (z:.Strand k) (z,k+1)+          {-# Inline [0] mk   #-}+          {-# Inline [0] step #-}+  {-# Inline streamUp #-}+  streamDown (ls:..LtStrand (Strand lf)) (hs:..LtStrand (Strand ht)) = flatten mk step $ streamDown ls hs+    where mk z = return (z,ht)+          step (z,k)+            | k < lf    = return $ Done+            | otherwise = return $ Yield (z:.Strand k) (z,k-1)+          {-# Inline [0] mk   #-}+          {-# Inline [0] step #-}+  {-# Inline streamDown #-}++-- instance IndexStream Strand++instance Arbitrary Strand where+  arbitrary = do+    b <- choose (0,3)+    return $ Strand b+  shrink (Strand j)+    | 0<j = [Strand $ j-1]+    | otherwise = []+
+ Biobase/Types/Structure.hs view
@@ -0,0 +1,225 @@++-- | Wrappers for structural data. Encoded as bytestrings. This differs from+-- @BiobaseXNA@, where specialized encodings are used. These structures are+-- supposedly "short", they need to fit into a strict bytestring.+--+-- TODO Consider where to move each type. There are merge possibilities between+-- BiobaseXNA and BiobaseTypes.+--+-- TODO QuickCheck @Arbitrary@ for @RNAss@.++module Biobase.Types.Structure where++import           Control.Applicative+import           Control.DeepSeq+import           Control.Lens+import           Control.Monad.Error.Class+import           Control.Monad (foldM,unless)+import           Data.Attoparsec.ByteString.Char8+import           Data.Attoparsec.Combinator+import           Data.Bifunctor (second)+import           Data.ByteString (ByteString)+import           Data.Data+import           Data.List (foldl1',foldl')+import           Data.Monoid ((<>))+import           Data.Set (Set)+import           GHC.Generics (Generic)+import qualified Data.ByteString.Char8 as BS8+import qualified Data.List as L+import qualified Data.Set as S+import qualified Data.Set as Set+import qualified Data.Vector.Unboxed as VU+import qualified Test.QuickCheck as Q++import           Data.Forest.StructuredPaired++++-- | Secondary structure using @()@ for paired elements, and @.@ for unpaired+-- ones. It is assumed that the @()@ match up. These structures from a Monoid.++newtype RNAss = RNAss { _rnass ∷ ByteString }+  deriving (Eq,Ord,Show,Read,Data,Typeable,Generic,Semigroup,Monoid)+makeLenses ''RNAss++instance NFData RNAss++-- | Ensemble structure encoding. *Very* different type ctor name chosen! The+-- structure of this string makes verification much more complicated.+--+-- TODO describe encoding used by RNAfold for the ensemble string.++newtype RNAensembleStructure = RNAes { _rnaes ∷ ByteString }+  deriving (Eq,Ord,Show,Read,Data,Typeable,Generic)+makeLenses ''RNAensembleStructure++instance NFData RNAensembleStructure++-- | Cofolded structure.++data RNAds = RNAds+  { _rnadsL ∷ !ByteString+  , _rnadsR ∷ !ByteString+  }+  deriving (Eq,Ord,Show,Read,Data,Typeable,Generic)+makeLenses ''RNAds++instance NFData RNAds++-- | A Prism that turns ByteStrings with a single @&@ into @RNAds@.++rnads ∷ Prism' ByteString RNAds+rnads = prism (\(RNAds l r) → BS8.concat [l, "&", r])+              (\s → case BS8.split '&' s of [l,r] → Right (RNAds l r) ; _ → Left s)+{-# Inline rnads #-}++-- | Isomorphism from @RNAds@ to @(RNAss,RNAss)@. The @RNAss@ are only+-- legal if taken both: @rnassFromDimer . both@.++rnads2rnassPair ∷ Iso' RNAds (RNAss, RNAss)+rnads2rnassPair = iso (\(RNAds l r) → (RNAss l, RNAss r)) (\(RNAss l, RNAss r) → RNAds l r)+{-# Inline rnads2rnassPair #-}++-- | Try to create a dimeric structure.++mkRNAds ∷ (Monad m, MonadError RNAStructureError m) ⇒ ByteString → m RNAds+mkRNAds q = BS8.split '&' q & \case+    [l,r] → do+      -- TODO can still fail with unmatched brackets.+      return $ RNAds+        { _rnadsL = l+        , _rnadsR = r+        }+    _     → throwError $ RNAStructureError "mkRNAds: not a dimer" q+{-# Inline mkRNAds #-}++-- | Capture what might be wrong with the RNAss.++data RNAStructureError = RNAStructureError+  { _rnaStructureError  ∷ String+  , _rnaOffender        ∷ ByteString+  }+  deriving (Show,Generic)++instance NFData RNAStructureError++-- | Verifies that the given RNAss is properly formatted. Otherwise, error out.+--+-- TODO Implement! Check with BiobaseXNA and the stack effort in there. This+-- might influence if the verification goes into BiobaseXNA and happens via an+-- @Iso'@.++verifyRNAss ∷ (Monad m, MonadError RNAStructureError m) ⇒ RNAss → m RNAss+verifyRNAss ss = do+  return ss++-- | The set of nucleotide pairs, together with the sequence length.++data RNApset = RNApset+  { _rnapset      ∷ !(Set (Int,Int))+    -- ^ the set of nucleotide pairs.+  , _rnapsetSLen  ∷ !Int+    -- ^ length of the underlying nucleotide sequence.+  }+  deriving (Read,Show,Eq,Ord,Generic)+makeLenses ''RNApset++instance NFData RNApset++-- | Transform an 'RNAss' into a set of base pairs @(i,j)@. The pairs are+-- 0-based.++rnassPairSet+  ∷ (MonadError String m)+  ⇒ RNAss+  → m RNApset+rnassPairSet (RNAss s2) = do+  let go (set,ks  ) (i,'(') = return (set,i:ks)+      go (set,i:is) (j,')') = return (Set.insert (i,j) set, is)+      go (set,[]  ) (j,')') = throwError $ "unequal brackets in \"" ++ BS8.unpack s2 ++ "\" at position: " ++ show j+      go (set,ks  ) (_,'.') = return (set,ks)+  (set,ss) ← foldM go (Set.empty,[]) . L.zip [0..] $ BS8.unpack s2+  unless (null ss) $ throwError $ "unequal brackets in \"" ++ BS8.unpack s2 ++ "\" with opening bracket(s): " ++ show ss+  return $ RNApset set (BS8.length s2)+{-# Inlinable rnassPairSet #-}++-- | Genereate a simple structured/paired forest from a secondary structure string.++rnassSPForest+  ∷ (MonadError String m)+  ⇒ RNAss+  → m (SPForest ByteString Char)+rnassSPForest (RNAss s2) = either throwError return $ parseOnly (manyElems <* endOfInput) s2+  where+    tree = SPT <$> char '(' <*> someElems <*> char ')' <?> "SPT"+    unpaired  = SPR <$> takeWhile1 (=='.') <?> "SPR"+    someElems = SPJ <$> many1 (tree <|> unpaired) <?> "many1 SPT / SPR"+    manyElems = (\case {[] → SPE; xs → SPJ xs}) <$> many  (tree <|> unpaired) <?> "many0 SPT / SPR"+{-# Inlinable rnassSPForest #-}++-- | Compactify such an SPForest. This means that all stems are now represented+-- by a single 'SPT' data constructor.++compactifySPForest+  ∷ SPForest ByteString Char+  → SPForest ByteString ByteString+compactifySPForest = go . second BS8.singleton+  where go SPE      = SPE+        go (SPR x)  = SPR x+        go (SPJ xs) = SPJ (map go xs)+        go (SPT l (SPJ [x]) r) = go $ SPT l x r+        go (SPT l (SPT l' t r') r) = go $ SPT (l <> l') t (r' <> r)+        go (SPT l t             r) = SPT l (go t) r++-- | RNA pair set, but a transformation error calls @error@.++rnassPairSet' ∷ RNAss → RNApset+rnassPairSet' = either error id . rnassPairSet++rnapsetRNAss ∷ RNApset → RNAss+rnapsetRNAss (RNApset ps l) = RNAss $ BS8.pack $ VU.toList xs+  where xs = VU.replicate l '.' VU.// ls VU.// rs+        ls = L.map ((,'(') . fst) $ S.toList ps+        rs = L.map ((,')') . snd) $ S.toList ps++-- | Calculates the number of different base pairs between two structures. This+-- ignores the length of the underlying sequences.++pairDist ∷ RNApset → RNApset → Int+pairDist (RNApset p1 _) (RNApset p2 _) = Set.size z1 + Set.size z2+  where i = Set.intersection p1 p2+        z1 = p1 `Set.difference` i+        z2 = p2 `Set.difference` i++++-- * Arbitrary instances. This only creates legal instances, but does *not*+-- take into account ViennaRNA rules like three unpaired nucleotides in the+-- hairpin.+--+-- TODO @shrink@ is a bit more complicated, but can be done via a set of pairs.++instance Q.Arbitrary RNApset where+  arbitrary = do+    -- Given left and right bounds, create pairs.+    let go ∷ Int → Int → Q.Gen (Set (Int,Int))+        go l r+          | l >= r    = return S.empty+          | otherwise = do+            -- right border of stack+            c ∷ Int ← Q.oneof [ Q.choose (l+1,r)  -- wide jump+                              , Q.choose (l+1, min r $ l+20)  -- short jump+                              ]+            -- with @1..10@ stack length+            z ∷ Int ← Q.choose (0,5)+            let stack = S.fromList [(l+k,c-k) | k ← [0..z-1], l+k+1 < c-k]+            right ← go (c+1) r+            return $ S.union stack right+    -- generate RNA structures between 0 and 100 nucleotides.+    l ∷ Int ← Q.choose (0,199)+    s ← go 0 l+    return $ RNApset s (l+1)++instance Q.Arbitrary RNAss where+  arbitrary = rnapsetRNAss <$> Q.arbitrary+
+ Biobase/Types/Taxonomy.hs view
@@ -0,0 +1,71 @@++-- | Biological classification of species.++module Biobase.Types.Taxonomy where++import Control.DeepSeq+import Data.Aeson+import Data.Binary+import Data.Hashable (Hashable, hashWithSalt)+import Data.Primitive.Types+import Data.Serialize+import Data.Text (Text)+import Data.Vector.Binary+import Data.Vector.Serialize+import Data.Vector.Unboxed.Deriving+import Data.Vector (Vector)+import GHC.Generics (Generic)++import Biobase.Types.Accession (Accession,Species)+import Biobase.Types.Names (SpeciesName, TaxonomicRank)++++-- | Taxonomic classification. @Enum@ together with a final @Unknown@ is+-- somewhat fishy.+--+-- TODO What should the order be? Kingdom > Species or Kingdom < Species?++data Classification+  = Kingdom+  | Phylum+  | Class+  | Order+  | SubOrder+  | Family+  | Genus+  | Species+  | Unknown+  deriving (Eq,Ord,Read,Show,Enum,Generic)++instance Binary    Classification+instance FromJSON  Classification+instance Hashable  Classification+instance Serialize Classification+instance ToJSON    Classification+instance NFData    Classification++derivingUnbox "Classification"+  [t| Classification -> Int |] [| fromEnum |] [| toEnum |]++++-- | A somewhat generic representation of a species within a taxonomic+-- context.++data Taxon = Taxon+  { species         :: !SpeciesName                             -- ^ the full, formal name of a species+  , accession       :: !(Accession Species)                     -- ^ the accession for the species (or @""@ if unknown)+  , classification  :: !(Vector (TaxonomicRank,Classification)) -- ^ vector with classification information+  }+  deriving (Eq,Read,Show,Generic)++instance Binary    Taxon+instance FromJSON  Taxon+instance Serialize Taxon+instance ToJSON    Taxon+instance NFData    Taxon++instance Hashable Taxon where+  hashWithSalt h (Taxon s a _) = hashWithSalt h (s,a)+
BiobaseTypes.cabal view
@@ -1,37 +1,150 @@+cabal-version:  2.2 name:           BiobaseTypes-version:        0.0.2.2-author:         Christian Hoener zu Siederdissen-maintainer:     choener@tbi.univie.ac.at-copyright:      Christian Hoener zu Siederdissen, 2010-category:       Bioinformatics-synopsis:       (deprecated) Ring class, with several instances.-license:        GPL-3+version:        0.2.1.0+author:         Christian Hoener zu Siederdissen, 2015 - 2021+copyright:      Christian Hoener zu Siederdissen, 2015 - 2021+homepage:       https://github.com/choener/BiobaseTypes+bug-reports:    https://github.com/choener/BiobaseTypes/issues+maintainer:     choener@bioinf.uni-leipzig.de+category:       Data Structures, Bioinformatics+license:        BSD-3-Clause license-file:   LICENSE build-type:     Simple stability:      experimental-cabal-version:  >= 1.4.0+tested-with:    GHC == 8.8, GHC == 8.10, GHC == 9.0+synopsis:       Collection of types for bioinformatics description:-                Provides an algebraic ring class and instances for Gibbs free-                energy, partition function probabilities, and scores.-                Conversion between different entities is provided by a convert-                function. All entities are ready for the vector library.+                Types used in a number of bioinformatics libraries.                 .-                - Ignore everything except the Ring itself!+                * linear indices+                .+                * energies+                .+                * biostring wrappers   -library-  build-depends:-    base >=4 && <5,-    vector >=0.7 && <0.8,-    primitive >=0.3 && <0.4+Extra-Source-Files:+  README.md+  changelog.md +++common deps+  build-depends: base                     >= 4.7      &&  < 5.0+               , aeson                    >= 0.8+               , attoparsec               >= 0.13+               , binary                   >= 0.7+               , bytestring+               , cereal                   >= 0.4+               , cereal-text              >= 0.1+               , cereal-vector            >= 0.2+               , containers+               , data-default             >= 0.5+               , deepseq                  >= 1.4+               , hashable                 >= 1.2+               , intern                   >= 0.9+               , lens                     >= 4.0+               , mtl+               , primitive                >= 0.5+               , QuickCheck               >= 2.7+               , streaming                >= 0.1+               , string-conversions       >= 0.4+               , text                     >= 1.0+               , text-binary              >= 0.2+               , utf8-string              >= 1.0+               , vector                   >= 0.10+               , vector-binary-instances  >= 0.2+               , vector-th-unbox          >= 0.2+               --+               , bimaps                   == 0.1.0.*+               , DPutils                  == 0.1.1.*+               , ForestStructures         == 0.0.1.*+               , PrimitiveArray           >= 0.10.1.1 && < 0.10.2+               , SciBaseTypes             == 0.1.1.*+  default-language:+    Haskell2010+  default-extensions: BangPatterns+                    , DataKinds+                    , DeriveDataTypeable+                    , DeriveFoldable+                    , DeriveGeneric+                    , DeriveTraversable+                    , DerivingStrategies+                    , FlexibleContexts+                    , FlexibleInstances+                    , GeneralizedNewtypeDeriving+                    , KindSignatures+                    , LambdaCase+                    , MultiParamTypeClasses+                    , OverloadedStrings+                    , PatternSynonyms+                    , PolyKinds+                    , RankNTypes+                    , RecordWildCards+                    , ScopedTypeVariables+                    , StandaloneDeriving+                    , TemplateHaskell+                    , TypeApplications+                    , TypeFamilies+                    , TypeOperators+                    , TupleSections+                    , UndecidableInstances+                    , UnicodeSyntax+                    , ViewPatterns+  ghc-options:+    -O2 -funbox-strict-fields++++library+  import:+    deps   exposed-modules:-    Biobase.Types.Ring-    Biobase.Types.Convert+    Biobase.Types.Accession+    Biobase.Types.BioSequence+    Biobase.Types.Bitscore+    Biobase.Types.Codon     Biobase.Types.Energy-    Biobase.Types.Partition-    Biobase.Types.Score+    Biobase.Types.Evalue+    Biobase.Types.Index+    Biobase.Types.Index.Type+    Biobase.Types.Location+    Biobase.Types.Names+    Biobase.Types.Names.Internal+    Biobase.Types.Position+    Biobase.Types.ReadingFrame+    Biobase.Types.Shape+    Biobase.Types.Strand+    Biobase.Types.Structure+    Biobase.Types.Taxonomy+    DP.Backtraced.BioSequence+    DP.Backtraced.Codon -  ghc-options:-    -O2+++test-suite properties+  import:+    deps+  type:+    exitcode-stdio-1.0+  main-is:+    properties.hs+--  ghc-options:+--    -threaded -rtsopts -with-rtsopts=-N+  hs-source-dirs:+    tests+  build-depends: base+               , tasty              >= 0.11+               , tasty-hunit        >= 0.10+               , tasty-quickcheck   >= 0.8+               , tasty-th           >= 0.1+               --+               , BiobaseTypes++++source-repository head+  type: git+  location: git://github.com/choener/BiobaseTypes+
+ DP/Backtraced/BioSequence.hs view
@@ -0,0 +1,3 @@++module DP.Backtraced.BioSequence where+
+ DP/Backtraced/Codon.hs view
@@ -0,0 +1,46 @@++-- | The Backtraced column structure is for codon-based alignments, including+-- special cases.++module DP.Backtraced.Codon where++import Data.ByteString (ByteString)+import Data.Vector (Vector)+import GHC.Generics (Generic)++import Biobase.Types.Codon++++-- | A single 'Backtraced' column. Since such a column will be part of a+-- @Backtraced (Z:.BtCodon c aa:. ...)@ structure, it is always possible to+-- extend even further, by having more entries.++data BtCodon c aa+  -- | A canonical match. A codon and the translated amino acid need to be set.+  = Match+    { _codon  ∷ !(Codon c)+    , _aa     ∷ !aa+    }+  -- | A frameshifting match. The vector of frameshifted nucleotides will have+  -- a number of characters @c@, that encode for a single amino acid.+  | Frameshift+    { _frameshift ∷ !(Vector c)+    , _aa         ∷ !aa+    }+  | Insert+    { _codon  ∷ !(Codon c)+    , _aa     ∷ !aa+    }+  | Shifted+    { _frameshift ∷ !(Vector c)+    , _aa         ∷ !aa+    }+  | Region+    { _region     ∷ !(Vector c)+    , _annotation ∷ !ByteString+    }+  | Delete+    {+    }+
LICENSE view
@@ -1,675 +1,30 @@-              GNU GENERAL PUBLIC LICENSE-                Version 3, 29 June 2007-- Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>- Everyone is permitted to copy and distribute verbatim copies- of this license document, but changing it is not allowed.--                     Preamble--  The GNU General Public License is a free, copyleft license for-software and other kinds of works.--  The licenses for most software and other practical works are designed-to take away your freedom to share and change the works.  By contrast,-the GNU General Public License is intended to guarantee your freedom to-share and change all versions of a program--to make sure it remains free-software for all its users.  We, the Free Software Foundation, use the-GNU General Public License for most of our software; it applies also to-any other work released this way by its authors.  You can apply it to-your programs, too.--  When we speak of free software, we are referring to freedom, not-price.  Our General Public Licenses are designed to make sure that you-have the freedom to distribute copies of free software (and charge for-them if you wish), that you receive source code or can get it if you-want it, that you can change the software or use pieces of it in new-free programs, and that you know you can do these things.--  To protect your rights, we need to prevent others from denying you-these rights or asking you to surrender the rights.  Therefore, you have-certain responsibilities if you distribute copies of the software, or if-you modify it: responsibilities to respect the freedom of others.--  For example, if you distribute copies of such a program, whether-gratis or for a fee, you must pass on to the recipients the same-freedoms that you received.  You must make sure that they, too, receive-or can get the source code.  And you must show them these terms so they-know their rights.--  Developers that use the GNU GPL protect your rights with two steps:-(1) assert copyright on the software, and (2) offer you this License-giving you legal permission to copy, distribute and/or modify it.--  For the developers' and authors' protection, the GPL clearly explains-that there is no warranty for this free software.  For both users' and-authors' sake, the GPL requires that modified versions be marked as-changed, so that their problems will not be attributed erroneously to-authors of previous versions.--  Some devices are designed to deny users access to install or run-modified versions of the software inside them, although the manufacturer-can do so.  This is fundamentally incompatible with the aim of-protecting users' freedom to change the software.  The systematic-pattern of such abuse occurs in the area of products for individuals to-use, which is precisely where it is most unacceptable.  Therefore, we-have designed this version of the GPL to prohibit the practice for those-products.  If such problems arise substantially in other domains, we-stand ready to extend this provision to those domains in future versions-of the GPL, as needed to protect the freedom of users.--  Finally, every program is threatened constantly by software patents.-States should not allow patents to restrict development and use of-software on general-purpose computers, but in those that do, we wish to-avoid the special danger that patents applied to a free program could-make it effectively proprietary.  To prevent this, the GPL assures that-patents cannot be used to render the program non-free.--  The precise terms and conditions for copying, distribution and-modification follow.--                TERMS AND CONDITIONS--  0. Definitions.--  "This License" refers to version 3 of the GNU General Public License.--  "Copyright" also means copyright-like laws that apply to other kinds of-works, such as semiconductor masks.- -  "The Program" refers to any copyrightable work licensed under this-License.  Each licensee is addressed as "you".  "Licensees" and-"recipients" may be individuals or organizations.--  To "modify" a work means to copy from or adapt all or part of the work-in a fashion requiring copyright permission, other than the making of an-exact copy.  The resulting work is called a "modified version" of the-earlier work or a work "based on" the earlier work.--  A "covered work" means either the unmodified Program or a work based-on the Program.--  To "propagate" a work means to do anything with it that, without-permission, would make you directly or secondarily liable for-infringement under applicable copyright law, except executing it on a-computer or modifying a private copy.  Propagation includes copying,-distribution (with or without modification), making available to the-public, and in some countries other activities as well.--  To "convey" a work means any kind of propagation that enables other-parties to make or receive copies.  Mere interaction with a user through-a computer network, with no transfer of a copy, is not conveying.--  An interactive user interface displays "Appropriate Legal Notices"-to the extent that it includes a convenient and prominently visible-feature that (1) displays an appropriate copyright notice, and (2)-tells the user that there is no warranty for the work (except to the-extent that warranties are provided), that licensees may convey the-work under this License, and how to view a copy of this License.  If-the interface presents a list of user commands or options, such as a-menu, a prominent item in the list meets this criterion.--  1. Source Code.--  The "source code" for a work means the preferred form of the work-for making modifications to it.  "Object code" means any non-source-form of a work.--  A "Standard Interface" means an interface that either is an official-standard defined by a recognized standards body, or, in the case of-interfaces specified for a particular programming language, one that-is widely used among developers working in that language.--  The "System Libraries" of an executable work include anything, other-than the work as a whole, that (a) is included in the normal form of-packaging a Major Component, but which is not part of that Major-Component, and (b) serves only to enable use of the work with that-Major Component, or to implement a Standard Interface for which an-implementation is available to the public in source code form.  A-"Major Component", in this context, means a major essential component-(kernel, window system, and so on) of the specific operating system-(if any) on which the executable work runs, or a compiler used to-produce the work, or an object code interpreter used to run it.--  The "Corresponding Source" for a work in object code form means all-the source code needed to generate, install, and (for an executable-work) run the object code and to modify the work, including scripts to-control those activities.  However, it does not include the work's-System Libraries, or general-purpose tools or generally available free-programs which are used unmodified in performing those activities but-which are not part of the work.  For example, Corresponding Source-includes interface definition files associated with source files for-the work, and the source code for shared libraries and dynamically-linked subprograms that the work is specifically designed to require,-such as by intimate data communication or control flow between those-subprograms and other parts of the work.--  The Corresponding Source need not include anything that users-can regenerate automatically from other parts of the Corresponding-Source.--  The Corresponding Source for a work in source code form is that-same work.--  2. Basic Permissions.--  All rights granted under this License are granted for the term of-copyright on the Program, and are irrevocable provided the stated-conditions are met.  This License explicitly affirms your unlimited-permission to run the unmodified Program.  The output from running a-covered work is covered by this License only if the output, given its-content, constitutes a covered work.  This License acknowledges your-rights of fair use or other equivalent, as provided by copyright law.--  You may make, run and propagate covered works that you do not-convey, without conditions so long as your license otherwise remains-in force.  You may convey covered works to others for the sole purpose-of having them make modifications exclusively for you, or provide you-with facilities for running those works, provided that you comply with-the terms of this License in conveying all material for which you do-not control copyright.  Those thus making or running the covered works-for you must do so exclusively on your behalf, under your direction-and control, on terms that prohibit them from making any copies of-your copyrighted material outside their relationship with you.--  Conveying under any other circumstances is permitted solely under-the conditions stated below.  Sublicensing is not allowed; section 10-makes it unnecessary.--  3. Protecting Users' Legal Rights From Anti-Circumvention Law.--  No covered work shall be deemed part of an effective technological-measure under any applicable law fulfilling obligations under article-11 of the WIPO copyright treaty adopted on 20 December 1996, or-similar laws prohibiting or restricting circumvention of such-measures.--  When you convey a covered work, you waive any legal power to forbid-circumvention of technological measures to the extent such circumvention-is effected by exercising rights under this License with respect to-the covered work, and you disclaim any intention to limit operation or-modification of the work as a means of enforcing, against the work's-users, your or third parties' legal rights to forbid circumvention of-technological measures.--  4. Conveying Verbatim Copies.--  You may convey verbatim copies of the Program's source code as you-receive it, in any medium, provided that you conspicuously and-appropriately publish on each copy an appropriate copyright notice;-keep intact all notices stating that this License and any-non-permissive terms added in accord with section 7 apply to the code;-keep intact all notices of the absence of any warranty; and give all-recipients a copy of this License along with the Program.--  You may charge any price or no price for each copy that you convey,-and you may offer support or warranty protection for a fee.--  5. Conveying Modified Source Versions.--  You may convey a work based on the Program, or the modifications to-produce it from the Program, in the form of source code under the-terms of section 4, provided that you also meet all of these conditions:--    a) The work must carry prominent notices stating that you modified-    it, and giving a relevant date.--    b) The work must carry prominent notices stating that it is-    released under this License and any conditions added under section-    7.  This requirement modifies the requirement in section 4 to-    "keep intact all notices".--    c) You must license the entire work, as a whole, under this-    License to anyone who comes into possession of a copy.  This-    License will therefore apply, along with any applicable section 7-    additional terms, to the whole of the work, and all its parts,-    regardless of how they are packaged.  This License gives no-    permission to license the work in any other way, but it does not-    invalidate such permission if you have separately received it.--    d) If the work has interactive user interfaces, each must display-    Appropriate Legal Notices; however, if the Program has interactive-    interfaces that do not display Appropriate Legal Notices, your-    work need not make them do so.--  A compilation of a covered work with other separate and independent-works, which are not by their nature extensions of the covered work,-and which are not combined with it such as to form a larger program,-in or on a volume of a storage or distribution medium, is called an-"aggregate" if the compilation and its resulting copyright are not-used to limit the access or legal rights of the compilation's users-beyond what the individual works permit.  Inclusion of a covered work-in an aggregate does not cause this License to apply to the other-parts of the aggregate.--  6. Conveying Non-Source Forms.--  You may convey a covered work in object code form under the terms-of sections 4 and 5, provided that you also convey the-machine-readable Corresponding Source under the terms of this License,-in one of these ways:--    a) Convey the object code in, or embodied in, a physical product-    (including a physical distribution medium), accompanied by the-    Corresponding Source fixed on a durable physical medium-    customarily used for software interchange.--    b) Convey the object code in, or embodied in, a physical product-    (including a physical distribution medium), accompanied by a-    written offer, valid for at least three years and valid for as-    long as you offer spare parts or customer support for that product-    model, to give anyone who possesses the object code either (1) a-    copy of the Corresponding Source for all the software in the-    product that is covered by this License, on a durable physical-    medium customarily used for software interchange, for a price no-    more than your reasonable cost of physically performing this-    conveying of source, or (2) access to copy the-    Corresponding Source from a network server at no charge.--    c) Convey individual copies of the object code with a copy of the-    written offer to provide the Corresponding Source.  This-    alternative is allowed only occasionally and noncommercially, and-    only if you received the object code with such an offer, in accord-    with subsection 6b.--    d) Convey the object code by offering access from a designated-    place (gratis or for a charge), and offer equivalent access to the-    Corresponding Source in the same way through the same place at no-    further charge.  You need not require recipients to copy the-    Corresponding Source along with the object code.  If the place to-    copy the object code is a network server, the Corresponding Source-    may be on a different server (operated by you or a third party)-    that supports equivalent copying facilities, provided you maintain-    clear directions next to the object code saying where to find the-    Corresponding Source.  Regardless of what server hosts the-    Corresponding Source, you remain obligated to ensure that it is-    available for as long as needed to satisfy these requirements.--    e) Convey the object code using peer-to-peer transmission, provided-    you inform other peers where the object code and Corresponding-    Source of the work are being offered to the general public at no-    charge under subsection 6d.--  A separable portion of the object code, whose source code is excluded-from the Corresponding Source as a System Library, need not be-included in conveying the object code work.--  A "User Product" is either (1) a "consumer product", which means any-tangible personal property which is normally used for personal, family,-or household purposes, or (2) anything designed or sold for incorporation-into a dwelling.  In determining whether a product is a consumer product,-doubtful cases shall be resolved in favor of coverage.  For a particular-product received by a particular user, "normally used" refers to a-typical or common use of that class of product, regardless of the status-of the particular user or of the way in which the particular user-actually uses, or expects or is expected to use, the product.  A product-is a consumer product regardless of whether the product has substantial-commercial, industrial or non-consumer uses, unless such uses represent-the only significant mode of use of the product.--  "Installation Information" for a User Product means any methods,-procedures, authorization keys, or other information required to install-and execute modified versions of a covered work in that User Product from-a modified version of its Corresponding Source.  The information must-suffice to ensure that the continued functioning of the modified object-code is in no case prevented or interfered with solely because-modification has been made.--  If you convey an object code work under this section in, or with, or-specifically for use in, a User Product, and the conveying occurs as-part of a transaction in which the right of possession and use of the-User Product is transferred to the recipient in perpetuity or for a-fixed term (regardless of how the transaction is characterized), the-Corresponding Source conveyed under this section must be accompanied-by the Installation Information.  But this requirement does not apply-if neither you nor any third party retains the ability to install-modified object code on the User Product (for example, the work has-been installed in ROM).--  The requirement to provide Installation Information does not include a-requirement to continue to provide support service, warranty, or updates-for a work that has been modified or installed by the recipient, or for-the User Product in which it has been modified or installed.  Access to a-network may be denied when the modification itself materially and-adversely affects the operation of the network or violates the rules and-protocols for communication across the network.--  Corresponding Source conveyed, and Installation Information provided,-in accord with this section must be in a format that is publicly-documented (and with an implementation available to the public in-source code form), and must require no special password or key for-unpacking, reading or copying.--  7. Additional Terms.--  "Additional permissions" are terms that supplement the terms of this-License by making exceptions from one or more of its conditions.-Additional permissions that are applicable to the entire Program shall-be treated as though they were included in this License, to the extent-that they are valid under applicable law.  If additional permissions-apply only to part of the Program, that part may be used separately-under those permissions, but the entire Program remains governed by-this License without regard to the additional permissions.--  When you convey a copy of a covered work, you may at your option-remove any additional permissions from that copy, or from any part of-it.  (Additional permissions may be written to require their own-removal in certain cases when you modify the work.)  You may place-additional permissions on material, added by you to a covered work,-for which you have or can give appropriate copyright permission.--  Notwithstanding any other provision of this License, for material you-add to a covered work, you may (if authorized by the copyright holders of-that material) supplement the terms of this License with terms:--    a) Disclaiming warranty or limiting liability differently from the-    terms of sections 15 and 16 of this License; or--    b) Requiring preservation of specified reasonable legal notices or-    author attributions in that material or in the Appropriate Legal-    Notices displayed by works containing it; or--    c) Prohibiting misrepresentation of the origin of that material, or-    requiring that modified versions of such material be marked in-    reasonable ways as different from the original version; or--    d) Limiting the use for publicity purposes of names of licensors or-    authors of the material; or--    e) Declining to grant rights under trademark law for use of some-    trade names, trademarks, or service marks; or--    f) Requiring indemnification of licensors and authors of that-    material by anyone who conveys the material (or modified versions of-    it) with contractual assumptions of liability to the recipient, for-    any liability that these contractual assumptions directly impose on-    those licensors and authors.--  All other non-permissive additional terms are considered "further-restrictions" within the meaning of section 10.  If the Program as you-received it, or any part of it, contains a notice stating that it is-governed by this License along with a term that is a further-restriction, you may remove that term.  If a license document contains-a further restriction but permits relicensing or conveying under this-License, you may add to a covered work material governed by the terms-of that license document, provided that the further restriction does-not survive such relicensing or conveying.--  If you add terms to a covered work in accord with this section, you-must place, in the relevant source files, a statement of the-additional terms that apply to those files, or a notice indicating-where to find the applicable terms.--  Additional terms, permissive or non-permissive, may be stated in the-form of a separately written license, or stated as exceptions;-the above requirements apply either way.--  8. Termination.--  You may not propagate or modify a covered work except as expressly-provided under this License.  Any attempt otherwise to propagate or-modify it is void, and will automatically terminate your rights under-this License (including any patent licenses granted under the third-paragraph of section 11).--  However, if you cease all violation of this License, then your-license from a particular copyright holder is reinstated (a)-provisionally, unless and until the copyright holder explicitly and-finally terminates your license, and (b) permanently, if the copyright-holder fails to notify you of the violation by some reasonable means-prior to 60 days after the cessation.--  Moreover, your license from a particular copyright holder is-reinstated permanently if the copyright holder notifies you of the-violation by some reasonable means, this is the first time you have-received notice of violation of this License (for any work) from that-copyright holder, and you cure the violation prior to 30 days after-your receipt of the notice.--  Termination of your rights under this section does not terminate the-licenses of parties who have received copies or rights from you under-this License.  If your rights have been terminated and not permanently-reinstated, you do not qualify to receive new licenses for the same-material under section 10.--  9. Acceptance Not Required for Having Copies.--  You are not required to accept this License in order to receive or-run a copy of the Program.  Ancillary propagation of a covered work-occurring solely as a consequence of using peer-to-peer transmission-to receive a copy likewise does not require acceptance.  However,-nothing other than this License grants you permission to propagate or-modify any covered work.  These actions infringe copyright if you do-not accept this License.  Therefore, by modifying or propagating a-covered work, you indicate your acceptance of this License to do so.--  10. Automatic Licensing of Downstream Recipients.--  Each time you convey a covered work, the recipient automatically-receives a license from the original licensors, to run, modify and-propagate that work, subject to this License.  You are not responsible-for enforcing compliance by third parties with this License.--  An "entity transaction" is a transaction transferring control of an-organization, or substantially all assets of one, or subdividing an-organization, or merging organizations.  If propagation of a covered-work results from an entity transaction, each party to that-transaction who receives a copy of the work also receives whatever-licenses to the work the party's predecessor in interest had or could-give under the previous paragraph, plus a right to possession of the-Corresponding Source of the work from the predecessor in interest, if-the predecessor has it or can get it with reasonable efforts.--  You may not impose any further restrictions on the exercise of the-rights granted or affirmed under this License.  For example, you may-not impose a license fee, royalty, or other charge for exercise of-rights granted under this License, and you may not initiate litigation-(including a cross-claim or counterclaim in a lawsuit) alleging that-any patent claim is infringed by making, using, selling, offering for-sale, or importing the Program or any portion of it.--  11. Patents.--  A "contributor" is a copyright holder who authorizes use under this-License of the Program or a work on which the Program is based.  The-work thus licensed is called the contributor's "contributor version".--  A contributor's "essential patent claims" are all patent claims-owned or controlled by the contributor, whether already acquired or-hereafter acquired, that would be infringed by some manner, permitted-by this License, of making, using, or selling its contributor version,-but do not include claims that would be infringed only as a-consequence of further modification of the contributor version.  For-purposes of this definition, "control" includes the right to grant-patent sublicenses in a manner consistent with the requirements of-this License.--  Each contributor grants you a non-exclusive, worldwide, royalty-free-patent license under the contributor's essential patent claims, to-make, use, sell, offer for sale, import and otherwise run, modify and-propagate the contents of its contributor version.--  In the following three paragraphs, a "patent license" is any express-agreement or commitment, however denominated, not to enforce a patent-(such as an express permission to practice a patent or covenant not to-sue for patent infringement).  To "grant" such a patent license to a-party means to make such an agreement or commitment not to enforce a-patent against the party.--  If you convey a covered work, knowingly relying on a patent license,-and the Corresponding Source of the work is not available for anyone-to copy, free of charge and under the terms of this License, through a-publicly available network server or other readily accessible means,-then you must either (1) cause the Corresponding Source to be so-available, or (2) arrange to deprive yourself of the benefit of the-patent license for this particular work, or (3) arrange, in a manner-consistent with the requirements of this License, to extend the patent-license to downstream recipients.  "Knowingly relying" means you have-actual knowledge that, but for the patent license, your conveying the-covered work in a country, or your recipient's use of the covered work-in a country, would infringe one or more identifiable patents in that-country that you have reason to believe are valid.-  -  If, pursuant to or in connection with a single transaction or-arrangement, you convey, or propagate by procuring conveyance of, a-covered work, and grant a patent license to some of the parties-receiving the covered work authorizing them to use, propagate, modify-or convey a specific copy of the covered work, then the patent license-you grant is automatically extended to all recipients of the covered-work and works based on it.--  A patent license is "discriminatory" if it does not include within-the scope of its coverage, prohibits the exercise of, or is-conditioned on the non-exercise of one or more of the rights that are-specifically granted under this License.  You may not convey a covered-work if you are a party to an arrangement with a third party that is-in the business of distributing software, under which you make payment-to the third party based on the extent of your activity of conveying-the work, and under which the third party grants, to any of the-parties who would receive the covered work from you, a discriminatory-patent license (a) in connection with copies of the covered work-conveyed by you (or copies made from those copies), or (b) primarily-for and in connection with specific products or compilations that-contain the covered work, unless you entered into that arrangement,-or that patent license was granted, prior to 28 March 2007.--  Nothing in this License shall be construed as excluding or limiting-any implied license or other defenses to infringement that may-otherwise be available to you under applicable patent law.--  12. No Surrender of Others' Freedom.--  If conditions are imposed on you (whether by court order, agreement or-otherwise) that contradict the conditions of this License, they do not-excuse you from the conditions of this License.  If you cannot convey a-covered work so as to satisfy simultaneously your obligations under this-License and any other pertinent obligations, then as a consequence you may-not convey it at all.  For example, if you agree to terms that obligate you-to collect a royalty for further conveying from those to whom you convey-the Program, the only way you could satisfy both those terms and this-License would be to refrain entirely from conveying the Program.--  13. Use with the GNU Affero General Public License.--  Notwithstanding any other provision of this License, you have-permission to link or combine any covered work with a work licensed-under version 3 of the GNU Affero General Public License into a single-combined work, and to convey the resulting work.  The terms of this-License will continue to apply to the part which is the covered work,-but the special requirements of the GNU Affero General Public License,-section 13, concerning interaction through a network will apply to the-combination as such.--  14. Revised Versions of this License.--  The Free Software Foundation may publish revised and/or new versions of-the GNU General Public License from time to time.  Such new versions will-be similar in spirit to the present version, but may differ in detail to-address new problems or concerns.--  Each version is given a distinguishing version number.  If the-Program specifies that a certain numbered version of the GNU General-Public License "or any later version" applies to it, you have the-option of following the terms and conditions either of that numbered-version or of any later version published by the Free Software-Foundation.  If the Program does not specify a version number of the-GNU General Public License, you may choose any version ever published-by the Free Software Foundation.--  If the Program specifies that a proxy can decide which future-versions of the GNU General Public License can be used, that proxy's-public statement of acceptance of a version permanently authorizes you-to choose that version for the Program.--  Later license versions may give you additional or different-permissions.  However, no additional obligations are imposed on any-author or copyright holder as a result of your choosing to follow a-later version.--  15. Disclaimer of Warranty.--  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY-APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT-HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY-OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,-THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR-PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM-IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF-ALL NECESSARY SERVICING, REPAIR OR CORRECTION.--  16. Limitation of Liability.--  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS-THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY-GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE-USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF-DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD-PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),-EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF-SUCH DAMAGES.--  17. Interpretation of Sections 15 and 16.--  If the disclaimer of warranty and limitation of liability provided-above cannot be given local legal effect according to their terms,-reviewing courts shall apply local law that most closely approximates-an absolute waiver of all civil liability in connection with the-Program, unless a warranty or assumption of liability accompanies a-copy of the Program in return for a fee.--              END OF TERMS AND CONDITIONS--     How to Apply These Terms to Your New Programs--  If you develop a new program, and you want it to be of the greatest-possible use to the public, the best way to achieve this is to make it-free software which everyone can redistribute and change under these terms.--  To do so, attach the following notices to the program.  It is safest-to attach them to the start of each source file to most effectively-state the exclusion of warranty; and each file should have at least-the "copyright" line and a pointer to where the full notice is found.--    <one line to give the program's name and a brief idea of what it does.>-    Copyright (C) <year>  <name of author>--    This program is free software: you can redistribute it and/or modify-    it under the terms of the GNU General Public License as published by-    the Free Software Foundation, either version 3 of the License, or-    (at your option) any later version.--    This program is distributed in the hope that it will be useful,-    but WITHOUT ANY WARRANTY; without even the implied warranty of-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the-    GNU General Public License for more details.--    You should have received a copy of the GNU General Public License-    along with this program.  If not, see <http://www.gnu.org/licenses/>.--Also add information on how to contact you by electronic and paper mail.+Copyright Christian Hoener zu Siederdissen 2015-2019 -  If the program does terminal interaction, make it output a short-notice like this when it starts in an interactive mode:+All rights reserved. -    <program>  Copyright (C) <year>  <name of author>-    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.-    This is free software, and you are welcome to redistribute it-    under certain conditions; type `show c' for details.+Redistribution and use in source and binary forms, with or without+modification, are permitted provided that the following conditions are met: -The hypothetical commands `show w' and `show c' should show the appropriate-parts of the General Public License.  Of course, your program's commands-might be different; for a GUI interface, you would use an "about box".+    * Redistributions of source code must retain the above copyright+      notice, this list of conditions and the following disclaimer. -  You should also get your employer (if you work as a programmer) or school,-if any, to sign a "copyright disclaimer" for the program, if necessary.-For more information on this, and how to apply and follow the GNU GPL, see-<http://www.gnu.org/licenses/>.+    * Redistributions in binary form must reproduce the above+      copyright notice, this list of conditions and the following+      disclaimer in the documentation and/or other materials provided+      with the distribution. -  The GNU General Public License does not permit incorporating your program-into proprietary programs.  If your program is a subroutine library, you-may consider it more useful to permit linking proprietary applications with-the library.  If this is what you want to do, use the GNU Lesser General-Public License instead of this License.  But first, please read-<http://www.gnu.org/philosophy/why-not-lgpl.html>.+    * Neither the name of Christian Hoener zu Siederdissen nor the names of other+      contributors may be used to endorse or promote products derived+      from this software without specific prior written permission. +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ README.md view
@@ -0,0 +1,21 @@+![github action: master](https://github.com/choener/BiobaseTypes/actions/workflows/ci.yml/badge.svg?branch=master)+![github action: hackage](https://github.com/choener/BiobaseTypes/actions/workflows/hackage.yml/badge.svg)++# BiobaseTypes++A bunch of types in use in different modules:++- numerical small and large numbers+- Gibbs free energy change+- phantom-typed linear indices: these encode the (rather annoying) habit of+  computational biology of having both 0-based and 1-based data++++#### Contact++Christian Hoener zu Siederdissen  +Leipzig University, Leipzig, Germany  +choener@bioinf.uni-leipzig.de  +http://www.bioinf.uni-leipzig.de/~choener/  +
+ changelog.md view
@@ -0,0 +1,55 @@+0.2.1.0+-------++- CI/hackage github actions+- dependency updates++0.2.0.1+-------++- minor version bumped due to OrderedBits++0.2.0.0+-------++- unified treatment of bio sequences with one phantom-typed newtype.++0.1.4.0+-------++- changes to indexing and others+- some changes that probably require a bump++0.1.3.0+-------++- "biostring" wrappers (ByteString based RNA, DNA, ... sequences)++0.1.2.1+-------++- increased minimal required PrimitiveArray version+- removed almost all upper bounds+- removed ghc 7.8.4 as viable compiler++0.1.2.0+-------++- NFData instances++0.1.1.0+-------++- added Biobase.Types.Odds module (from the BiobaseBlast package)++0.1.0.0+-------++- re-introduced the types library for bioinformatics+- travis-ci integration++0.0.x,y+-------++- old variant; completely rewritten by now+
+ tests/properties.hs view
@@ -0,0 +1,134 @@++module Main where++import           Control.Lens+import           Debug.Trace+import qualified Data.ByteString.Char8 as BS8+import           Test.QuickCheck.Modifiers+import           Test.QuickCheck.Property ()+import           Test.Tasty+import           Test.Tasty.HUnit+import           Test.Tasty.QuickCheck (testProperty)+import           Test.Tasty.TH++import           Biobase.Types.BioSequence+import           Biobase.Types.Bitscore+import           Biobase.Types.Location+import           Biobase.Types.Shape+import           Biobase.Types.Strand+import           Biobase.Types.Structure+import           Biobase.Types.Index as I++{-++-- * Bitscore conversions++prop_ProbScore (Positive null) (Positive x) = x ~= score2Prob null (prob2Score null x)++--prop_ScoreProb (Positive null) x = Bitscore x ~= prob2Score null (score2Prob null $ Bitscore x)++++-- * sequence properties++-- complement twice++prop_complement_twice_DNA (dna ∷ BioSequence DNA) = dna == dna^.complement.complement++prop_complement_twice_RNA (rna ∷ BioSequence RNA) = rna == rna^.complement.complement++prop_transcribe_twice_DNA (dna ∷ BioSequence DNA) = dna == dna^.transcribe.transcribe++--prop_transcribe_twice_DNA (rna ∷ RNAseq) = rna == rna^.transcribe.transcribe++-- * shape properties++-- ** unit tests for known rna secondary structures++-- ** quickcheck++-- | reversing a secondary structure means reversing the shape++prop_StructureShape_5_Reverse = fun_StructureShape_k_Reverse SL5+prop_StructureShape_4_Reverse = fun_StructureShape_k_Reverse SL4+prop_StructureShape_3_Reverse = fun_StructureShape_k_Reverse SL3+prop_StructureShape_2_Reverse = fun_StructureShape_k_Reverse SL2+prop_StructureShape_1_Reverse = fun_StructureShape_k_Reverse SL1++fun_StructureShape_k_Reverse lvl rnass@(RNAss s2)+  | shp == fshp = True+  | otherwise = traceShow (s2,shp,rshp,fshp) False+  where shp  = rnass2shape lvl rnass+        rshp = rnass2shape lvl $ RNAss $ BS8.map flp $ BS8.reverse s2+        fshp = over rnashape (BS8.map flp . BS8.reverse) rshp+        flp '(' = ')'+        flp ')' = '('+        flp '[' = ']'+        flp ']' = '['+        flp x   = x++prop_FwdLocationPlusTake (NonNegative (p ∷ Int), NonNegative (l ∷ Int), NonNegative (k ∷ Int))+  | check       = True+  | otherwise   = traceShow (p,l,k,fwdloc,taken,manual) check+  where fwdloc  = FwdLocation PlusStrand (I.index p) l+        check   = taken == manual+        taken   = fwdLocationTake k fwdloc+        manual  = FwdLocation PlusStrand (I.index p) (max 0 $ min l k)++prop_FwdLocationPlusDrop (NonNegative (p ∷ Int), NonNegative (l ∷ Int), NonNegative (k ∷ Int))+  | check       = True+  | otherwise   = traceShow (p,l,k,fwdloc,dropped,manual) check+  where fwdloc  = FwdLocation PlusStrand (I.index p) l+        check   = dropped == manual+        dropped = fwdLocationDrop k fwdloc+        manual  = FwdLocation PlusStrand (I.index $ p + min l k) (max 0 $ l-k)++-- | Given a BioSequenceWindow, and different takes and drops, check wether what we have corresponds to what we want++case_bswTakeDrop ∷ Assertion+case_bswTakeDrop = do+  let wp = BioSequenceWindow @"DNA" @DNA "test" 1 "ACGTAC" 3 (FwdLocation PlusStrand 0 6)+      wm = BioSequenceWindow @"DNA" @DNA "test" 3 "CATGCA" 1 (FwdLocation MinusStrand 0 6)+  --+  bswTake 0 wp @?= BioSequenceWindow "test" 0 ""       0 (FwdLocation PlusStrand 0 0)+  bswTake 1 wp @?= BioSequenceWindow "test" 1 "A"      0 (FwdLocation PlusStrand 0 1)+  bswTake 2 wp @?= BioSequenceWindow "test" 1 "AC"     0 (FwdLocation PlusStrand 0 2)+  bswTake 6 wp @?= BioSequenceWindow "test" 1 "ACGTAC" 3 (FwdLocation PlusStrand 0 6)+  --+  bswDrop 0 wp @?= BioSequenceWindow "test" 1 "ACGTAC" 3 (FwdLocation PlusStrand 0 6)+  bswDrop 1 wp @?= BioSequenceWindow "test" 0  "CGTAC" 3 (FwdLocation PlusStrand 1 5)+  bswDrop 6 wp @?= BioSequenceWindow "test" 0       "" 0 (FwdLocation PlusStrand 6 0)+  --+  bswTake 0 wm @?= BioSequenceWindow "test" 0 ""       0 (FwdLocation MinusStrand 6 0)+  bswTake 1 wm @?= BioSequenceWindow "test" 1 "C"      0 (FwdLocation MinusStrand 5 1)+  bswTake 2 wm @?= BioSequenceWindow "test" 2 "CA"     0 (FwdLocation MinusStrand 4 2)+  bswTake 3 wm @?= BioSequenceWindow "test" 3 "CAT"    0 (FwdLocation MinusStrand 3 3)+  bswTake 4 wm @?= BioSequenceWindow "test" 3 "CATG"   0 (FwdLocation MinusStrand 2 4)+  bswTake 5 wm @?= BioSequenceWindow "test" 3 "CATGC"  0 (FwdLocation MinusStrand 1 5)+  bswTake 6 wm @?= BioSequenceWindow "test" 3 "CATGCA" 1 (FwdLocation MinusStrand 0 6)+  --+  bswDrop 0 wm @?= BioSequenceWindow "test" 3 "CATGCA" 1 (FwdLocation MinusStrand 0 6)+  bswDrop 1 wm @?= BioSequenceWindow "test" 2  "ATGCA" 1 (FwdLocation MinusStrand 0 5)+  bswDrop 2 wm @?= BioSequenceWindow "test" 1   "TGCA" 1 (FwdLocation MinusStrand 0 4)+  bswDrop 5 wm @?= BioSequenceWindow "test" 0      "A" 1 (FwdLocation MinusStrand 0 1)+  bswDrop 6 wm @?= BioSequenceWindow "test" 0       "" 0 (FwdLocation MinusStrand 0 0)+  --+  -- TODO consider having [take,take,drop,drop], generate all permutations;+  -- they should all yield the same result.+  --+++++-- * generic stuff++a ~= b = abs (b-a) <= 10e-6++main :: IO ()+main = $(defaultMainGenerator)++-}++main :: IO ()+main = return ()+