diff --git a/CHANGES.md b/CHANGES.md new file mode 100644 --- /dev/null +++ b/CHANGES.md @@ -0,0 +1,68 @@ +## Version 0.4.5.0 + + * Support for GHC 8.0 added; support for GHC 7.4 dropped + + * Fix defect in `Foldable(foldr)` implementation failing to skip + unconvertable records (#102) + + * Documentation fixes + + * Maintainer changed + +## Version 0.4.4.0 + + * Added record instances for larger tuples. + + * Support attoparsec 0.13. + + * Add field instances for short bytestrings. + +## Version 0.4.3.0 + + * Documentation overhaul with more examples. + + * Add Data.Csv.Builder, a low-level bytestring builder API. + + * Add a high-level builder API to Data.Csv.Incremental. + + * Generalize the default FromNamedRecord/ToNamedRecord instances. + + * Improved support for deriving instances using GHC.Generics. + + * Added some control over quoting. + +## Version 0.4.2.4 + + * Support attoparsec 0.13. + +## Version 0.4.2.3 + + * Support GHC 7.10. + +## Version 0.4.2.2 + + * Support blaze-builder 0.4. + + * Make sure inlining doesn't prevent rules from firing. + + * Fix incorrect INLINE pragmas. + +## Version 0.4.2.1 + + * Support deepseq-1.4. + +## Version 0.4.2.0 + + * Minor performance improvements. + + * Add 8 and 9 tuple instances for From/ToRecord. + + * Support text-1.2. + +## Version 0.4.1.0 + + * Ignore whitespace when converting numeric fields. + + * Accept \r as a line terminator. + + * Support attoparsec-0.12. diff --git a/Data/Csv.hs b/Data/Csv.hs --- a/Data/Csv.hs +++ b/Data/Csv.hs @@ -26,7 +26,7 @@ -- * Treating CSV data as opaque byte strings -- $generic-processing - -- * Custom type conversions + -- * Custom type conversions for fields -- $customtypeconversions -- ** Dealing with bad data @@ -37,7 +37,6 @@ HasHeader(..) , decode , decodeByName - , Quoting(..) , encode , encodeByName , encodeDefaultOrderedByName @@ -50,6 +49,7 @@ , decodeWith , decodeByNameWith , EncodeOptions(..) + , Quoting(..) , defaultEncodeOptions , encodeWith , encodeByNameWith @@ -130,7 +130,7 @@ -- To encode and decode your own data types you need to defined -- instances of either 'ToRecord' and 'FromRecord' or 'ToNamedRecord' -- and 'FromNamedRecord'. The former is used for encoding/decoding --- using the column index and the latter using column name. +-- using the column index and the latter using the column name. -- -- There are two ways to to define these instances, either by manually -- defining them or by using GHC generics to derive them automatically. @@ -170,7 +170,7 @@ -- Decoding: -- -- > >>> decode NoHeader "John,27\r\n" :: Either String (Vector Person) --- > Right (["name","salary"],[Person {name = "John", salary = 27}]) +-- > Right [Person {name = "John", salary = 27}] -- -- $example-named-instance @@ -192,11 +192,11 @@ -- > -- > instance FromNamedRecord Person where -- > parseNamedRecord m = Person <$> m .: "name" <*> m .: "salary" --- > instance ToNamedRecord Person +-- > instance ToNamedRecord Person where -- > toNamedRecord (Person name salary) = namedRecord [ -- > "name" .= name, "salary" .= salary] --- > instance DefaultOrdered Person --- > where headerOrder = header ["name", "salary"] +-- > instance DefaultOrdered Person where +-- > headerOrder _ = header ["name", "salary"] -- -- We can now use e.g. 'encodeDefaultOrderedByName' (or 'encodeByName' -- with an explicit header order) and 'decodeByName' to encode and diff --git a/Data/Csv/Compat/Monoid.hs b/Data/Csv/Compat/Monoid.hs deleted file mode 100644 --- a/Data/Csv/Compat/Monoid.hs +++ /dev/null @@ -1,14 +0,0 @@ -{-# LANGUAGE CPP #-} -module Data.Csv.Compat.Monoid - ( (<>) - ) where - -import Data.Monoid - -#if !MIN_VERSION_base(4,5,0) -infixr 6 <> --- | An infix synonym for 'mappend'. -(<>) :: Monoid m => m -> m -> m -(<>) = mappend -{-# INLINE (<>) #-} -#endif diff --git a/Data/Csv/Conversion.hs b/Data/Csv/Conversion.hs --- a/Data/Csv/Conversion.hs +++ b/Data/Csv/Conversion.hs @@ -2,17 +2,19 @@ BangPatterns, CPP, DefaultSignatures, + DataKinds, + PolyKinds, FlexibleContexts, FlexibleInstances, KindSignatures, MultiParamTypeClasses, - OverlappingInstances, OverloadedStrings, Rank2Types, ScopedTypeVariables, TypeOperators, UndecidableInstances #-} + module Data.Csv.Conversion ( -- * Type conversion @@ -1018,7 +1020,7 @@ -- lets you compose several field conversions together in such a way -- that if any of them fail, the whole record conversion fails. newtype Parser a = Parser { - unParser :: forall f r. + unParser :: forall (f :: * -> *) (r :: *). Failure f r -> Success a f r -> f r @@ -1028,7 +1030,9 @@ m >>= g = Parser $ \kf ks -> let ks' a = unParser (g a) kf ks in unParser m kf ks' {-# INLINE (>>=) #-} - return a = Parser $ \_kf ks -> ks a + (>>) = (*>) + {-# INLINE (>>) #-} + return = pure {-# INLINE return #-} fail msg = Parser $ \kf _ks -> kf msg {-# INLINE fail #-} @@ -1039,7 +1043,7 @@ {-# INLINE fmap #-} instance Applicative Parser where - pure = return + pure a = Parser $ \_kf ks -> ks a {-# INLINE pure #-} (<*>) = apP {-# INLINE (<*>) #-} @@ -1067,7 +1071,7 @@ apP d e = do b <- d a <- e - return (b a) + pure (b a) {-# INLINE apP #-} -- | Run a 'Parser', returning either @'Left' errMsg@ or @'Right' @@ -1200,7 +1204,12 @@ -- | Instance to ensure that you cannot derive DefaultOrdered for -- constructors without selectors. +#if MIN_VERSION_base(4,9,0) +instance DefaultOrdered (M1 S ('MetaSel 'Nothing srcpk srcstr decstr) a ()) + => GToNamedRecordHeader (M1 S ('MetaSel 'Nothing srcpk srcstr decstr) a) +#else instance DefaultOrdered (M1 S NoSelector a ()) => GToNamedRecordHeader (M1 S NoSelector a) +#endif where gtoNamedRecordHeader _ = error "You cannot derive DefaultOrdered for constructors without selectors." diff --git a/Data/Csv/Conversion/Internal.hs b/Data/Csv/Conversion/Internal.hs --- a/Data/Csv/Conversion/Internal.hs +++ b/Data/Csv/Conversion/Internal.hs @@ -10,9 +10,8 @@ import qualified Data.ByteString as B import Data.Char (ord) import Data.Int +import Data.Monoid import Data.Word - -import Data.Csv.Compat.Monoid ((<>)) ------------------------------------------------------------------------ -- Integers diff --git a/Data/Csv/Encoding.hs b/Data/Csv/Encoding.hs --- a/Data/Csv/Encoding.hs +++ b/Data/Csv/Encoding.hs @@ -1,4 +1,4 @@ -{-# LANGUAGE BangPatterns, CPP, OverloadedStrings, ScopedTypeVariables #-} +{-# LANGUAGE BangPatterns, OverloadedStrings, ScopedTypeVariables #-} -- Module: Data.Csv.Encoding -- Copyright: (c) 2011 MailRank, Inc. @@ -40,7 +40,7 @@ import Blaze.ByteString.Builder (Builder, fromByteString, fromWord8, toLazyByteString, toByteString) import Blaze.ByteString.Builder.Char8 (fromString) -import Control.Applicative ((<|>), optional) +import Control.Applicative as AP (Applicative(..), (<|>), optional) import Data.Attoparsec.ByteString.Char8 (endOfInput) import qualified Data.Attoparsec.ByteString.Lazy as AL import qualified Data.ByteString as B @@ -51,9 +51,9 @@ import Data.Vector (Vector) import qualified Data.Vector as V import Data.Word (Word8) +import Data.Monoid import Prelude hiding (unlines) -import Data.Csv.Compat.Monoid ((<>)) import qualified Data.Csv.Conversion as Conversion import Data.Csv.Conversion (FromNamedRecord, FromRecord, ToNamedRecord, ToRecord, parseNamedRecord, parseRecord, runParser, @@ -64,10 +64,6 @@ import qualified Data.Csv.Types as Types import Data.Csv.Util (blankLine, endOfLine) -#if !MIN_VERSION_base(4,8,0) -import Control.Applicative ((*>), pure) -import Data.Monoid (mconcat, mempty) -#endif -- TODO: 'encode' isn't as efficient as it could be. @@ -155,11 +151,11 @@ -> Either String (Header, Vector a) decodeByNameWith !opts = decodeWithP (csvWithHeader opts) --- | Should quoting be applied to fields, and at which level +-- | Should quoting be applied to fields, and at which level? data Quoting - = QuoteNone -- ^ No quotes - | QuoteMinimal -- ^ Quotes according to RFC 4180 - | QuoteAll -- ^ Always quote + = QuoteNone -- ^ No quotes. + | QuoteMinimal -- ^ Quotes according to RFC 4180. + | QuoteAll -- ^ Always quote. deriving (Eq, Show) -- | Options that controls how data is encoded. These options can be @@ -372,7 +368,7 @@ else case runParser (parseRecord r) of Left msg -> fail $ "conversion error: " ++ msg Right val -> do - !vals <- (endOfLine *> records) <|> pure [] + !vals <- (endOfLine *> records) <|> AP.pure [] return (val : vals) {-# INLINE csv #-} diff --git a/Data/Csv/Streaming.hs b/Data/Csv/Streaming.hs --- a/Data/Csv/Streaming.hs +++ b/Data/Csv/Streaming.hs @@ -106,6 +106,7 @@ foldrRecords f = go where go z (Cons (Right x) rs) = f x (go z rs) + go z (Cons (Left _) rs) = go z rs go z _ = z {-# INLINE foldrRecords #-} diff --git a/benchmarks/Benchmarks.hs b/benchmarks/Benchmarks.hs --- a/benchmarks/Benchmarks.hs +++ b/benchmarks/Benchmarks.hs @@ -4,7 +4,7 @@ module Main ( main ) where -import Control.Applicative +import Control.Applicative as AP import Control.Exception (evaluate) import Control.DeepSeq import Criterion.Main @@ -42,7 +42,7 @@ instance FromRecord President where parseRecord v | V.length v == 7 = President <$> - v .!! 0 <*> + v .!! 0 AP.<*> v .!! 1 <*> v .!! 2 <*> v .!! 3 <*> diff --git a/cassava.cabal b/cassava.cabal --- a/cassava.cabal +++ b/cassava.cabal @@ -1,25 +1,44 @@ Name: cassava -Version: 0.4.4.0 +Version: 0.4.5.0 Synopsis: A CSV parsing and encoding library Description: A CSV parsing and encoding library optimized for ease of use and high performance. -Homepage: https://github.com/tibbe/cassava +Homepage: https://github.com/hvr/cassava License: BSD3 License-file: LICENSE -Bug-reports: https://github.com/tibbe/cassava/issues +Bug-reports: https://github.com/hvr/cassava/issues Copyright: (c) 2012 Johan Tibell (c) 2012 Bryan O'Sullivan (c) 2011 MailRank, Inc. Author: Johan Tibell -Maintainer: johan.tibell@gmail.com +Maintainer: hvr@gnu.org Category: Text, Web, CSV Build-type: Simple -Cabal-version: >=1.8 -Extra-source-files: examples/*.hs -Tested-with: GHC == 7.10.2, GHC == 7.8.4, GHC == 7.6.3 +Cabal-version: >=1.10 +Extra-source-files: examples/*.hs, + CHANGES.md +Tested-with: GHC ==8.0.1, GHC ==7.10.3, GHC ==7.8.4, GHC ==7.6.3 Library + default-language: Haskell2010 + other-extensions: + BangPatterns + CPP + DataKinds + DefaultSignatures + DeriveFunctor + FlexibleContexts + FlexibleInstances + KindSignatures + MultiParamTypeClasses + OverloadedStrings + PolyKinds + Rank2Types + ScopedTypeVariables + TypeOperators + UndecidableInstances + Exposed-modules: Data.Csv Data.Csv.Builder @@ -28,7 +47,6 @@ Data.Csv.Streaming Other-modules: - Data.Csv.Compat.Monoid Data.Csv.Conversion Data.Csv.Conversion.Internal Data.Csv.Encoding @@ -38,11 +56,11 @@ Build-depends: array < 0.6, attoparsec >= 0.10.2 && < 0.14, - base >= 4.5 && < 5, + base >= 4.6 && < 5, blaze-builder < 0.5, bytestring < 0.11, containers < 0.6, - deepseq < 1.5, + deepseq >= 1.1 && < 1.5, hashable < 1.3, text < 1.3, unordered-containers < 0.3, @@ -50,16 +68,14 @@ ghc-options: -Wall -O2 - -- GHC.Generics lived in `ghc-prim` for GHC 7.2 & GHC 7.4 only - if impl(ghc < 7.6) - build-depends: ghc-prim == 0.2.* - Test-suite unit-tests + default-language: Haskell2010 + Type: exitcode-stdio-1.0 Main-is: UnitTests.hs Build-depends: attoparsec, - base >= 4.5, + base >= 4.6, bytestring, cassava, hashable < 1.3, @@ -76,12 +92,13 @@ ghc-options: -Wall Benchmark benchmarks + default-language: Haskell2010 + Type: exitcode-stdio-1.0 Main-is: Benchmarks.hs Other-modules: Data.Csv - Data.Csv.Compat.Monoid Data.Csv.Conversion Data.Csv.Conversion.Internal Data.Csv.Encoding @@ -94,7 +111,7 @@ Build-depends: array < 0.6, attoparsec >= 0.10.2 && < 0.14, - base >= 4.5 && < 5, + base >= 4.6 && < 5, blaze-builder < 0.5, bytestring < 0.11, containers < 0.6, @@ -109,17 +126,10 @@ ghc-options: -Wall -O2 - if impl(ghc >= 7.2.1) - cpp-options: -DGENERICS - - -- GHC.Generics lived in `ghc-prim` for GHC 7.2 & GHC 7.4 only - if impl(ghc < 7.6) - build-depends: ghc-prim == 0.2.* - -- We cannot depend on the library directly as that creates a -- dependency cycle. hs-source-dirs: . benchmarks source-repository head type: git - location: https://github.com/tibbe/cassava.git + location: https://github.com/hvr/cassava.git diff --git a/tests/UnitTests.hs b/tests/UnitTests.hs --- a/tests/UnitTests.hs +++ b/tests/UnitTests.hs @@ -13,6 +13,7 @@ import qualified Data.Text as T import qualified Data.Text.Lazy as LT import qualified Data.Vector as V +import qualified Data.Foldable as F import Data.Word import Test.HUnit import Test.Framework as TF @@ -362,6 +363,21 @@ ] ------------------------------------------------------------------------ +-- Instance tests + +instanceTests :: [TF.Test] +instanceTests = + [ + testGroup "Records instances" + [ testCase "foldr Foldable" (expected @=? F.foldr (:) [] input) + ] + ] + where + input = S.Cons (Left "empty") ( + S.Cons (Right ("a" :: String)) (S.Nil Nothing BL8.empty)) + expected = ["a" :: String] + +------------------------------------------------------------------------ -- Test harness allTests :: [TF.Test] @@ -369,6 +385,7 @@ , testGroup "named" nameBasedTests , testGroup "conversion" conversionTests , testGroup "custom-options" customOptionsTests + , testGroup "instances" instanceTests ] main :: IO ()