diff --git a/ChangeLog.md b/ChangeLog.md --- a/ChangeLog.md +++ b/ChangeLog.md @@ -2,6 +2,11 @@ ## [Unreleased] +## [0.1.4.4] - 2022-06-02 +### Changed +- Update more dependencies; +- Fix new warnings in GHC-9. + ## [0.1.4.3] - 2022-03-23 ### Changed - Support GHC-9.2 packages in dependencies. diff --git a/cobot-io.cabal b/cobot-io.cabal --- a/cobot-io.cabal +++ b/cobot-io.cabal @@ -5,7 +5,7 @@ -- see: https://github.com/sol/hpack name: cobot-io -version: 0.1.4.3 +version: 0.1.4.4 synopsis: Biological data file formats and IO description: Please see the README on GitHub at category: Bio @@ -192,8 +192,10 @@ , mtl >=2.2.1 && <2.3.0 , parser-combinators >=1.2.1 , split - , text >=1.2.2.1 && <1.3 + , text >=1.2.2.1 && <2.1 , vector + if impl(ghc >= 9.0) + ghc-options: -haddock -Winvalid-haddock default-language: Haskell2010 test-suite cobot-io-test @@ -236,7 +238,7 @@ , data-msgpack >=0.0.9 && <0.1 , deepseq ==1.4.* , directory - , hspec >=2.4.1 && <2.9 + , hspec >=2.4.1 && <2.11 , http-conduit ==2.3.* , hyraxAbif >=0.2.3.27 && <0.2.4.0 , lens >=4.16 && <5.2 @@ -246,6 +248,6 @@ , neat-interpolation >=0.3 , parser-combinators >=1.2.1 , split - , text >=1.2.2.1 && <1.3 + , text >=1.2.2.1 && <2.1 , vector default-language: Haskell2010 diff --git a/src/Bio/GB/Writer.hs b/src/Bio/GB/Writer.hs --- a/src/Bio/GB/Writer.hs +++ b/src/Bio/GB/Writer.hs @@ -108,8 +108,8 @@ mainPart = processMany featuresIndent mempty ("/" <> nameF <> "=\"" <> textF <> "\"") featureRangeToText :: Range -> Text -featureRangeToText (Point pos) = showText pos -featureRangeToText (Span (RangeBorder rbLo lo) (RangeBorder rbHi hi)) = borderToText True rbLo <> showText lo <> ".." <> borderToText False rbHi <> showText hi +featureRangeToText (Point pos) = showText pos +featureRangeToText (Span (RangeBorder rbLo lo) (RangeBorder rbHi hi)) = borderToText True rbLo <> showText lo <> ".." <> borderToText False rbHi <> showText hi where borderToText :: Bool -> Border -> Text borderToText _ Precise = "" @@ -146,12 +146,12 @@ where indText = showText startInd - -- | Number of nucleotides in one chunk. + -- Number of nucleotides in one chunk. -- lengthOfChunk :: Int lengthOfChunk = 10 - -- | Number of chunks per line of sequence in ORIGIN section. + -- Number of chunks per line of sequence in ORIGIN section. -- lengthOfLineChunk :: Int lengthOfLineChunk = 6 @@ -166,13 +166,14 @@ -------------------------------------------------------------------------------- processMany :: Int -> Text -> Text -> Text -processMany indent name "" = toIndent indent name -processMany indent name text = interNewLine resLines - where - (x : xs) = T.lines text - - resLines = toIndent indent name <> x - : fmap (prependIndent indent) xs +processMany indent name text = + case T.lines text of + [] -> toIndent indent name + (x:xs) -> + let + resLines = toIndent indent name <> x + : fmap (prependIndent indent) xs + in interNewLine resLines interNewLine :: [Text] -> Text interNewLine = T.intercalate "\n" . filter (not . T.null) @@ -181,7 +182,7 @@ textFromMaybe = fromMaybe mempty toIndent :: Int -> Text -> Text -toIndent indent name = name <> (spaces $ indent - (T.length name)) +toIndent indent name = name <> spaces (indent - T.length name) prependIndent :: Int -> Text -> Text prependIndent = T.append . spaces diff --git a/src/Bio/MAE.hs b/src/Bio/MAE.hs --- a/src/Bio/MAE.hs +++ b/src/Bio/MAE.hs @@ -1,5 +1,5 @@ -{-# LANGUAGE AllowAmbiguousTypes #-} -{-# LANGUAGE CPP #-} +{-# LANGUAGE AllowAmbiguousTypes #-} +{-# LANGUAGE CPP #-} {-# OPTIONS_GHC -fno-warn-orphans #-} module Bio.MAE @@ -14,35 +14,33 @@ ) where import Bio.MAE.Parser -import Bio.MAE.Type (Block (..), FromMaeValue (..), - Mae (..), MaeValue (..), Table (..)) -import Bio.Structure (Atom (..), Bond (..), Chain (..), Model (..), - GlobalID (..), LocalID (..), - Model (..), Residue (..), - SecondaryStructure (..), - StructureModels (..)) +import Bio.MAE.Type (Block (..), FromMaeValue (..), Mae (..), MaeValue (..), + Table (..)) +import Bio.Structure (Atom (..), Bond (..), Chain (..), GlobalID (..), + LocalID (..), Model (..), Residue (..), + SecondaryStructure (..), StructureModels (..)) import qualified Bio.Utils.Map as M ((!?!)) import Control.Monad (join) import Control.Monad.IO.Class (MonadIO, liftIO) import Data.Attoparsec.Text (parseOnly) import Data.Bifunctor (bimap, first) import Data.Function (on) -import qualified Data.List as L (find, groupBy, sortOn) +import qualified Data.List as L (find, sortOn) +import qualified Data.List.NonEmpty as NE import Data.Map.Strict (Map) import qualified Data.Map.Strict as M (fromList, lookup) import Data.Maybe (catMaybes, fromJust) import Data.Text (Text) -import qualified Data.Text as T (head, init, last, null, pack, - strip, tail) +import qualified Data.Text as T (head, init, last, null, pack, strip, tail) import qualified Data.Text.IO as TIO (readFile) import Data.Vector (Vector) import qualified Data.Vector as V (fromList) import Linear.V3 (V3 (..)) -#if !MIN_VERSION_base(4,13,0) -import Control.Monad.Fail (MonadFail (..)) -import Prelude hiding (fail) -#endif + + + + -- | Reads 'Mae' from givem file. -- fromFile :: (MonadFail m, MonadIO m) => FilePath -> m Mae @@ -84,8 +82,8 @@ stripQuotes t | not (T.null t) && T.head t == T.last t, T.last t == '\"' = T.strip $ T.init $ T.tail t | otherwise = T.strip t - toGroupsOn :: (Eq b, Ord b) => (a -> b) -> [a] -> [[a]] - toGroupsOn f = L.groupBy ((==) `on` f) . L.sortOn f + toGroupsOn :: (Eq b, Ord b) => (a -> b) -> [a] -> [NE.NonEmpty a] + toGroupsOn f = NE.groupBy ((==) `on` f) . L.sortOn f bondsTableToGlobalBonds :: Map Text [MaeValue] -> (Map Int [(Int, Int)], Vector (Bond GlobalID)) bondsTableToGlobalBonds m = bimap toMap V.fromList bonds' @@ -94,7 +92,7 @@ bonds' = unzip $ fmap indexToBond [0 .. numberOfBonds - 1] toMap :: [(Int, (Int, Int))] -> Map Int [(Int, Int)] - toMap = M.fromList . fmap (\l@((k, _) : _) -> (k, fmap snd l)) . toGroupsOn fst + toMap = M.fromList . fmap (\l@((k, _) NE.:| _) -> (k, snd <$> NE.toList l)) . toGroupsOn fst indexToBond :: Int -> ((Int, (Int, Int)), Bond GlobalID) indexToBond i = ((x, (y, o)), Bond (GlobalID x) (GlobalID y) o) @@ -117,13 +115,12 @@ unsafeGetFromContents :: FromMaeValue a => Text -> Int -> a unsafeGetFromContents = unsafeGetFromContentsMap m - groupToChain :: [Int] -> Chain - groupToChain [] = error "Group that is result of List.groupBy can't be empty." - groupToChain group@(h : _) = Chain name residues + groupToChain :: NE.NonEmpty Int -> Chain + groupToChain group@(h NE.:| _) = Chain name residues where name = stripQuotes $ getFromContents defaultChainName "s_m_chain_name" h - groupedByResidues = toGroupsOn by group + groupedByResidues = toGroupsOn by $ NE.toList group residues = V.fromList $ fmap groupToResidue groupedByResidues by :: Int -> (Int, Char) @@ -135,10 +132,10 @@ defaultInsertionCode :: Char defaultInsertionCode = ' ' - groupToResidue :: [Int] -> Residue - groupToResidue [] = error "Group that is result of List.groupBy can't be empty." - groupToResidue group@(h : _) = Residue name residueNumber insertionCode atoms (V.fromList localBonds) secondary chemCompType + groupToResidue :: NE.NonEmpty Int -> Residue + groupToResidue groupNE@(h NE.:| _) = Residue name residueNumber insertionCode atoms (V.fromList localBonds) secondary chemCompType where + group = NE.toList groupNE name = stripQuotes $ unsafeGetFromContents "s_m_pdb_residue_name" h residueNumber = unsafeGetFromContents "i_m_residue_number" h insertionCode = getFromContents defaultInsertionCode "s_m_insertion_code" h @@ -190,3 +187,4 @@ , "Md", "No", "Lr", "Rf", "Db", "Sg", "Bh", "Hs", "Mt", "Ds" , "Rg", "Cn", "Nh", "Fl", "Mc", "Lv", "Ts", "Og" ] + diff --git a/src/Bio/Uniprot/Parser.hs b/src/Bio/Uniprot/Parser.hs --- a/src/Bio/Uniprot/Parser.hs +++ b/src/Bio/Uniprot/Parser.hs @@ -86,7 +86,7 @@ flags <- option [] (endOfLine *> parseFlagsDE) pure DE{..} where - -- | Parses name section like RecName, AltName or SubName. + -- Parses name section like RecName, AltName or SubName. parseNameDE :: Int -> NameType -> Parser Name parseNameDE indent nameType = do fullName <- parseDELine indent nameType "Full" @@ -94,12 +94,12 @@ ecNumber <- many' $ endOfLine *> parseDELine indent None "EC" pure Name{..} - -- | Parses flag line of DE section + -- Parses flag line of DE section parseFlagsDE :: Parser [Flag] parseFlagsDE = fmap (read . unpack) . ("; " `splitOn`) <$> parseDELine 0 Flags "" - -- | Parses AltName lines of DE section + -- Parses AltName lines of DE section parseAltDE :: Int -> Parser AltName parseAltDE indent = (Simple <$> parseNameDE indent AltName) <|> @@ -108,7 +108,7 @@ (CDAntigen <$> parseDELine indent AltName "CD_antigen") <|> (INN <$> parseDELine indent AltName "INN") - -- | Parses any DE line + -- Parses any DE line parseDELine :: Int -> NameType -> Text -> Parser Text parseDELine indent nameType tpe = do string "DE " @@ -123,7 +123,7 @@ result <- pack . P.init <$> many1 (satisfy (not . isEndOfLine)) pure . head $ " {ECO" `splitOn` result - -- | Parses internal DE entities + -- Parses internal DE entities parseInternal :: Text -> Parser DE parseInternal name = do string "DE " >> string name >> char ':' @@ -148,7 +148,7 @@ rest <- option [] $ string "and" *> endOfLine *> parseGN pure $ gn:rest where - -- | Parses any list item of GN line (like `Synonyms` or `ORFNames`) + -- Parses any list item of GN line (like `Synonyms` or `ORFNames`) parseGNList :: Text -> Parser [Text] parseGNList name = splitOn ", " <$> parseDefItem name @@ -356,7 +356,7 @@ (hyphenConcat <$> parseMultiLine "FT" 32)) pure FT{..} where - -- | Parse FT endpoint + -- Parse FT endpoint parseFTEndpoint :: Parser Endpoint parseFTEndpoint = (UncertainEP <$> (char '?' *> decimal)) <|> (NTerminalEP <$> (char '<' *> decimal)) <|> @@ -364,7 +364,7 @@ (ExactEP <$> decimal) <|> (char '?' $> UnknownEP) - -- | Split string to tokens by periods outside brackets. + -- Split string to tokens by periods outside brackets. splitByMagic :: String -> [Text] splitByMagic txt = pack <$> splitStr 0 [] txt where diff --git a/test/ABISpec.hs b/test/ABISpec.hs --- a/test/ABISpec.hs +++ b/test/ABISpec.hs @@ -66,7 +66,10 @@ Right dat <- readData path S.length dat `shouldBe` lengthBefore - let Just cleaned = clean dat + let cleaned = + case clean dat of + Just c -> c + Nothing -> error "clean failed" S.length cleaned `shouldBe` lengthAfter S.toList cleaned `shouldStartWith` start diff --git a/test/StructureSpec.hs b/test/StructureSpec.hs --- a/test/StructureSpec.hs +++ b/test/StructureSpec.hs @@ -1,7 +1,7 @@ {-# LANGUAGE FlexibleInstances #-} {-# LANGUAGE OverloadedStrings #-} {-# LANGUAGE RecordWildCards #-} -{-# OPTIONS_GHC -fno-warn-orphans #-} +{-# OPTIONS_GHC -fno-warn-orphans -Wno-incomplete-uni-patterns #-} module StructureSpec where @@ -23,7 +23,7 @@ structureSpec :: Spec structureSpec = describe "Structure spec." $ do - let mIO = V.toList . modelsOf <$> fromFile "test/MAE/Capri.mae" >>= \[x] -> pure x + let mIO = fromFile "test/MAE/Capri.mae" >>= (\[x] -> pure x) . V.toList . modelsOf beforeAll mIO $ do it "atoms filtering works correctly. only N, CA, C" $ \m -> checkFiltering m $ (`elem` ["N", "CA", "C"]) . atomName it "atoms filtering works correctly. only CA" $ \m -> checkFiltering m $ (== "CA") . atomName