flatparse 0.3.1.0 → 0.3.2.0

raw patch · 5 files changed

+81/−69 lines, 5 filesPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

API changes (from Hackage documentation)

Files

• flatparse.cabal +1/−1
• src/FlatParse/Basic.hs +17/−19
• src/FlatParse/Examples/BasicLambda/Lexer.hs +1/−1
• src/FlatParse/Internal.hs +30/−12
• src/FlatParse/Stateful.hs +32/−36

@@ -5,7 +5,7 @@ -- see: https://github.com/sol/hpack  name:           flatparse-version:        0.3.1.0+version:        0.3.2.0 synopsis:       High-performance parsing from strict bytestrings description:    @Flatparse@ is a high-performance parsing library, focusing on programming languages and                 human-readable data formats. See the README for more information:

@@ -201,9 +201,7 @@     OK# a s -> runParser# (f a) fp eob s     x       -> unsafeCoerce# x   {-# inline (>>=) #-}-  Parser fa >> Parser fb = Parser \fp eob s -> case fa fp eob s of-    OK# a s -> fb fp eob s-    x       -> unsafeCoerce# x+  (>>) = (*>)   {-# inline (>>) #-}  -- | Higher-level boxed data type for parsing results.@@ -336,13 +334,13 @@ char c = string [c]  -- | Read a `Word8`.-byte :: Word8 -> Parser e ()-byte (W8# w) = ensureBytes# 1 >> scan8# (W# w)+byte :: Word -> Parser e ()+byte (W# w) = ensureBytes# 1 >> scan8# (W# w) {-# inline byte #-}  -- | Read a sequence of bytes. This is a template function, you can use it as @$(bytes [3, 4, 5])@, --   for example, and the splice has type @Parser e ()@.-bytes :: [Word8] -> Q Exp+bytes :: [Word] -> Q Exp bytes bytes = do   let !len = length bytes   [| ensureBytes# len >> $(scanBytes# bytes) |]@@ -523,11 +521,11 @@ {-# inline anyWord8_ #-}  -- | Parse any `Word16`.-anyWord16 :: Parser e Word16+anyWord16 :: Parser e Word anyWord16 = Parser \fp eob buf -> case 2# <=# minusAddr# eob buf of   0# -> Fail#-  _  -> case indexWord16OffAddr# buf 0# of-    w -> OK# (W16# w) (plusAddr# buf 2#)+  _  -> case indexWord16OffAddr buf 0# of+    w -> OK# (W# w) (plusAddr# buf 2#) {-# inline anyWord16 #-}  -- | Skip any `Word16`.@@ -536,11 +534,11 @@ {-# inline anyWord16_ #-}  -- | Parse any `Word32`.-anyWord32 :: Parser e Word32+anyWord32 :: Parser e Word anyWord32 = Parser \fp eob buf -> case 4# <=# minusAddr# eob buf of   0# -> Fail#-  _  -> case indexWord32OffAddr# buf 0# of-    w -> OK# (W32# w) (plusAddr# buf 4#)+  _  -> case indexWord32OffAddr buf 0# of+    w -> OK# (W# w) (plusAddr# buf 4#) {-# inline anyWord32 #-}  -- | Skip any `Word32`.@@ -906,7 +904,7 @@ --   enough bytes. scan8# :: Word -> Parser e () scan8# (W# c) = Parser \fp eob s ->-  case indexWord8OffAddr# s 0# of+  case indexWord8OffAddr s 0# of     c' -> case eqWord# c c' of       1# -> OK# () (plusAddr# s 1#)       _  -> Fail#@@ -916,7 +914,7 @@ --   enough bytes. scan16# :: Word -> Parser e () scan16# (W# c) = Parser \fp eob s ->-  case indexWord16OffAddr# s 0# of+  case indexWord16OffAddr s 0# of     c' -> case eqWord# c c' of       1# -> OK# () (plusAddr# s 2#)       _  -> Fail#@@ -926,7 +924,7 @@ --   enough bytes. scan32# :: Word -> Parser e () scan32# (W# c) = Parser \fp eob s ->-  case indexWord32OffAddr# s 0# of+  case indexWord32OffAddr s 0# of     c' -> case eqWord# c c' of       1# -> OK# () (plusAddr# s 4#)       _  -> Fail#@@ -936,15 +934,15 @@ --   enough bytes. scan64# :: Word -> Parser e () scan64# (W# c) = Parser \fp eob s ->-  case indexWord64OffAddr# s 0# of+  case indexWord64OffAddr s 0# of     c' -> case eqWord# c c' of       1# -> OK# () (plusAddr# s 8#)       _  -> Fail# {-# inline scan64# #-}  -- | Unsafely read and return a byte from the input. It's not checked that the input is non-empty.-scanAny8# :: Parser e Word8-scanAny8# = Parser \fp eob s -> OK# (W8# (indexWord8OffAddr# s 0#)) (plusAddr# s 1#)+scanAny8# :: Parser e Word+scanAny8# = Parser \fp eob s -> OK# (W# (indexWord8OffAddr s 0#)) (plusAddr# s 1#) {-# inline scanAny8# #-}  scanPartial64# :: Int -> Word -> Parser e ()@@ -966,7 +964,7 @@  -- | Template function, creates a @Parser e ()@ which unsafely scans a given --   sequence of bytes.-scanBytes# :: [Word8] -> Q Exp+scanBytes# :: [Word] -> Q Exp scanBytes# bytes = do   let !(leading, w8s) = splitBytes bytes       !scanw8s        = go w8s where

@@ -65,7 +65,7 @@       pos      = case e of Imprecise pos e -> pos                            Precise pos e   -> pos       ls       = FP.lines b-      [(l, c)] = posLineCols b [pos]+      (l, c)   = head $ posLineCols b [pos]       line     = if l < length ls then ls !! l else ""       linum    = show l       lpad     = map (const ' ') linum

@@ -6,7 +6,6 @@ import Data.Char import Data.Foldable (foldl') import Data.Map (Map)-import Data.Word import GHC.Exts import GHC.ForeignPtr @@ -27,12 +26,28 @@ shortInteger :: Int# -> Integer #if MIN_VERSION_base(4,15,0) shortInteger = IS-{-# inline shortInteger #-} #else shortInteger = S# #endif+{-# inline shortInteger #-} +#if MIN_VERSION_base(4,16,0)+indexWord8OffAddr s x = word8ToWord# (indexWord8OffAddr# s x)+indexWord16OffAddr s x = word16ToWord# (indexWord16OffAddr# s x)+indexWord32OffAddr s x = word32ToWord# (indexWord32OffAddr# s x)+indexWord64OffAddr s x = indexWord64OffAddr# s x+#else+indexWord8OffAddr  = indexWord8OffAddr#+indexWord16OffAddr = indexWord16OffAddr#+indexWord32OffAddr = indexWord32OffAddr#+indexWord64OffAddr = indexWord64OffAddr#+#endif+{-# inline indexWord8OffAddr #-}+{-# inline indexWord16OffAddr #-}+{-# inline indexWord32OffAddr #-}+{-# inline indexWord64OffAddr #-} + -- Char predicates -------------------------------------------------------------------------------- @@ -61,7 +76,7 @@ readInt' :: Int# -> Addr# -> Addr# -> (# Int#, Addr# #) readInt' acc s end = case eqAddr# s end of   1# -> (# acc, s #)-  _  -> case indexWord8OffAddr# s 0# of+  _  -> case indexWord8OffAddr s 0# of     w | 1# <- leWord# 48## w, 1# <- leWord# w 57## ->       readInt' (mul10 acc +# (word2Int# w -# 48#)) (plusAddr# s 1#) end     _ -> (# acc, s #)@@ -128,9 +143,12 @@  -- | Convert a `String` to an UTF-8-coded `B.ByteString`. packUTF8 :: String -> B.ByteString-packUTF8 = B.pack . concatMap charToBytes+packUTF8 str = B.pack $ do+  c <- str+  w <- charToBytes c+  pure (fromIntegral w) -charToBytes :: Char -> [Word8]+charToBytes :: Char -> [Word] charToBytes c'     | c <= 0x7f     = [fromIntegral c]     | c <= 0x7ff    = [0xc0 .|. y, 0x80 .|. z]@@ -144,16 +162,16 @@     x = fromIntegral (unsafeShiftR c 12 .&. 0x3f)     w = fromIntegral (unsafeShiftR c 18 .&. 0x7) -strToBytes :: String -> [Word8]+strToBytes :: String -> [Word] strToBytes = concatMap charToBytes {-# inline strToBytes #-} -packBytes :: [Word8] -> Word+packBytes :: [Word] -> Word packBytes = fst . foldl' go (0, 0) where   go (acc, shift) w | shift == 64 = error "packWords: too many bytes"   go (acc, shift) w = (unsafeShiftL (fromIntegral w) shift .|. acc, shift+8) -splitBytes :: [Word8] -> ([Word8], [Word])+splitBytes :: [Word] -> ([Word], [Word]) splitBytes ws = case quotRem (length ws) 8 of   (0, _) -> (ws, [])   (_, r) -> (as, chunk8s bs) where@@ -169,7 +187,7 @@ -- Switch trie compilation -------------------------------------------------------------------------------- -data Trie a = Branch !a !(Map Word8 (Trie a))+data Trie a = Branch !a !(Map Word (Trie a))   deriving Show  type Rule = Maybe Int@@ -180,7 +198,7 @@ updRule :: Int -> Maybe Int -> Maybe Int updRule rule = Just . maybe rule (min rule) -insert :: Int -> [Word8] -> Trie Rule -> Trie Rule+insert :: Int -> [Word] -> Trie Rule -> Trie Rule insert rule = go where   go [] (Branch rule' ts) =     Branch (updRule rule rule') ts@@ -204,8 +222,8 @@       ts'  data Trie' a-  = Branch' !a !(Map Word8 (Trie' a))-  | Path !a ![Word8] !(Trie' a)+  = Branch' !a !(Map Word (Trie' a))+  | Path !a ![Word] !(Trie' a)   deriving Show  -- | Compress linear paths.

@@ -96,7 +96,7 @@   -- ** Position and span conversions   , Basic.validPos   , Basic.posLineCols-  , Basic.unsafeSpanToByteString+  , unsafeSpanToByteString   , Basic.unsafeSlice   , Basic.mkPos   , Basic.lines@@ -126,9 +126,7 @@ import Control.Monad import Data.Foldable import Data.Map (Map)-import Data.Word import GHC.Exts-import GHC.Word import Language.Haskell.TH import System.IO.Unsafe import GHC.ForeignPtr@@ -208,9 +206,7 @@     OK# a s n -> runParser# (f a) fp r eob s n     x         -> unsafeCoerce# x   {-# inline (>>=) #-}-  Parser fa >> Parser fb = Parser \fp !r eob s n -> case fa fp r eob s n of-    OK# a s n -> fb fp r eob s n-    x         -> unsafeCoerce# x+  (>>) = (*>)   {-# inline (>>) #-}  -- | Higher-level boxed data type for parsing results.@@ -370,14 +366,14 @@ char :: Char -> Q Exp char c = string [c] --- | Read a `Word8`.-byte :: Word8 -> Parser e ()-byte (W8# w) = ensureBytes# 1 >> scan8# (W# w)+-- | Read a byte.+byte :: Word -> Parser e ()+byte (W# w) = ensureBytes# 1 >> scan8# (W# w) {-# inline byte #-}  -- | Read a sequence of bytes. This is a template function, you can use it as @$(bytes [3, 4, 5])@, --   for example, and the splice has type @Parser e ()@.-bytes :: [Word8] -> Q Exp+bytes :: [Word] -> Q Exp bytes bytes = do   let !len = length bytes   [| ensureBytes# len >> $(scanBytes# bytes) |]@@ -540,25 +536,25 @@ fusedSatisfy_ f1 f2 f3 f4 = () <$ fusedSatisfy f1 f2 f3 f4 {-# inline fusedSatisfy_ #-} --- | Parse any `Word8`.-anyWord8 :: Parser e Word8+-- | Parse any byte.+anyWord8 :: Parser e Word anyWord8 = Parser \fp !r eob buf n -> case eqAddr# eob buf of   1# -> Fail#-  _  -> case indexWord8OffAddr# buf 0# of-    w -> OK# (W8# w) (plusAddr# buf 1#) n+  _  -> case indexWord8OffAddr buf 0# of+    w -> OK# (W# w) (plusAddr# buf 1#) n {-# inline anyWord8 #-} --- | Skip any `Word8`.+-- | Skip any byte. anyWord8_ :: Parser e () anyWord8_ = () <$ anyWord8 {-# inline anyWord8_ #-}  -- | Parse any `Word16`.-anyWord16 :: Parser e Word16+anyWord16 :: Parser e Word anyWord16 = Parser \fp !r eob buf n -> case 2# <=# minusAddr# eob buf of   0# -> Fail#-  _  -> case indexWord16OffAddr# buf 0# of-    w -> OK# (W16# w) (plusAddr# buf 2#) n+  _  -> case indexWord16OffAddr buf 0# of+    w -> OK# (W# w) (plusAddr# buf 2#) n {-# inline anyWord16 #-}  -- | Skip any `Word16`.@@ -567,11 +563,11 @@ {-# inline anyWord16_ #-}  -- | Parse any `Word32`.-anyWord32 :: Parser e Word32+anyWord32 :: Parser e Word anyWord32 = Parser \fp !r eob buf n -> case 4# <=# minusAddr# eob buf of   0# -> Fail#-  _  -> case indexWord32OffAddr# buf 0# of-    w -> OK# (W32# w) (plusAddr# buf 4#) n+  _  -> case indexWord32OffAddr buf 0# of+    w -> OK# (W# w) (plusAddr# buf 4#) n {-# inline anyWord32 #-}  -- | Skip any `Word32`.@@ -815,6 +811,14 @@   x          -> unsafeCoerce# x {-# inline byteStringed #-} +-- | Create a `B.ByteString` from a `Span`. The result is invalid is the `Span` points+--   outside the current buffer, or if the `Span` start is greater than the end position.+unsafeSpanToByteString :: Span -> Parser e B.ByteString+unsafeSpanToByteString (Span l r) =+  lookahead (setPos l >> byteStringOf (setPos r))+{-# inline unsafeSpanToByteString #-}++ -- | Run a parser in a given input span. The input position and the `Int` state is restored after --   the parser is finished, so `inSpan` does not consume input and has no side effect.  Warning: --   this operation may crash if the given span points outside the current parsing buffer. It's@@ -827,15 +831,7 @@     x         -> unsafeCoerce# x {-# inline inSpan #-} --------------------------------------------------------------------------------- --- | Create a `B.ByteString` from a `Span`. The result is invalid is the `Span` points---   outside the current buffer, or if the `Span` start is greater than the end position.-unsafeSpanToByteString :: Span -> Parser e B.ByteString-unsafeSpanToByteString (Span l r) =-  lookahead (setPos l >> byteStringOf (setPos r))-{-# inline unsafeSpanToByteString #-}- --------------------------------------------------------------------------------  -- | Parse the rest of the current line as a `String`. Assumes UTF-8 encoding,@@ -882,7 +878,7 @@ --   enough bytes. scan8# :: Word -> Parser e () scan8# (W# c) = Parser \fp !r eob s n ->-  case indexWord8OffAddr# s 0# of+  case indexWord8OffAddr s 0# of     c' -> case eqWord# c c' of       1# -> OK# () (plusAddr# s 1#) n       _  -> Fail#@@ -892,7 +888,7 @@ --   enough bytes. scan16# :: Word -> Parser e () scan16# (W# c) = Parser \fp !r eob s n ->-  case indexWord16OffAddr# s 0# of+  case indexWord16OffAddr s 0# of     c' -> case eqWord# c c' of       1# -> OK# () (plusAddr# s 2#) n       _  -> Fail#@@ -902,7 +898,7 @@ --   enough bytes. scan32# :: Word -> Parser e () scan32# (W# c) = Parser \fp !r eob s n ->-  case indexWord32OffAddr# s 0# of+  case indexWord32OffAddr s 0# of     c' -> case eqWord# c c' of       1# -> OK# () (plusAddr# s 4#) n       _  -> Fail#@@ -912,15 +908,15 @@ --   enough bytes. scan64# :: Word -> Parser e () scan64# (W# c) = Parser \fp !r eob s n ->-  case indexWord64OffAddr# s 0# of+  case indexWord64OffAddr s 0# of     c' -> case eqWord# c c' of       1# -> OK# () (plusAddr# s 8#) n       _  -> Fail# {-# inline scan64# #-}  -- | Unsafely read and return a byte from the input. It's not checked that the input is non-empty.-scanAny8# :: Parser e Word8-scanAny8# = Parser \fp !r eob s n -> OK# (W8# (indexWord8OffAddr# s 0#)) (plusAddr# s 1#) n+scanAny8# :: Parser e Word+scanAny8# = Parser \fp !r eob s n -> OK# (W# (indexWord8OffAddr s 0#)) (plusAddr# s 1#) n {-# inline scanAny8# #-}  scanPartial64# :: Int -> Word -> Parser e ()@@ -942,7 +938,7 @@  -- | Template function, creates a @Parser e ()@ which unsafely scans a given --   sequence of bytes.-scanBytes# :: [Word8] -> Q Exp+scanBytes# :: [Word] -> Q Exp scanBytes# bytes = do   let !(leading, w8s) = splitBytes bytes       !scanw8s        = go w8s where