flatparse 0.2.0.0 → 0.2.1.0

raw patch · 5 files changed

+87/−23 lines, 5 filesPVP ok

version bump matches the API change (PVP)

API changes (from Hackage documentation)

Files

• bench/Bytesmith.hs +1/−1
• flatparse.cabal +27/−6
• src/FlatParse/Basic.hs +31/−12
• src/FlatParse/Examples/BasicLambda/Parser.hs +7/−3
• src/FlatParse/Stateful.hs +21/−1

@@ -53,7 +53,7 @@ src     = sexp >> P.endOfInput U runSexp = parseByteArray src -longw     = P.cstring U (Ptr "thisisalongkeyword"#)+longw     = P.cstring U (Ptr "thisisalongkeyword\NUL"#) longws    = some_ (longw >> ws) >> P.endOfInput U runLongws = parseByteArray longws 

@@ -1,13 +1,13 @@ cabal-version: 1.12 --- This file has been generated from package.yaml by hpack version 0.33.0.+-- This file has been generated from package.yaml by hpack version 0.34.4. -- -- see: https://github.com/sol/hpack ----- hash: dd4124fa98babb251701a98ec5a31a5016b54b6af73c2732c85c9e13fdb07478+-- hash: 2ba3a084128297d0d1b6136ac0a6aff88c0a67a3998844684ae951a9e56aa339  name:           flatparse-version:        0.2.0.0+version:        0.2.1.0 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:@@ -20,7 +20,8 @@ copyright:      2021 András Kovács license:        MIT license-file:   LICENSE-tested-with:    GHC == 8.8.4+tested-with:+    GHC == 8.8.4 build-type:     Simple extra-source-files:     README.md@@ -39,7 +40,17 @@       Paths_flatparse   hs-source-dirs:       src-  default-extensions: BangPatterns BlockArguments ExplicitNamespaces LambdaCase MagicHash OverloadedStrings PatternSynonyms TemplateHaskell TupleSections UnboxedTuples+  default-extensions:+      BangPatterns+      BlockArguments+      ExplicitNamespaces+      LambdaCase+      MagicHash+      OverloadedStrings+      PatternSynonyms+      TemplateHaskell+      TupleSections+      UnboxedTuples   ghc-options: -Wall -Wno-name-shadowing -Wno-unused-binds -Wno-unused-matches -Wno-missing-signatures -O2   build-depends:       base >=4.7 && <5@@ -61,7 +72,17 @@       Paths_flatparse   hs-source-dirs:       bench-  default-extensions: BangPatterns BlockArguments ExplicitNamespaces LambdaCase MagicHash OverloadedStrings PatternSynonyms TemplateHaskell TupleSections UnboxedTuples+  default-extensions:+      BangPatterns+      BlockArguments+      ExplicitNamespaces+      LambdaCase+      MagicHash+      OverloadedStrings+      PatternSynonyms+      TemplateHaskell+      TupleSections+      UnboxedTuples   ghc-options: -Wall -Wno-name-shadowing -Wno-unused-binds -Wno-unused-matches -Wno-missing-signatures -O2   build-depends:       attoparsec

@@ -82,6 +82,7 @@   , validPos   , posLineCols   , unsafeSpanToByteString+  , unsafeSlice   , mkPos   , FlatParse.Basic.lines @@ -91,6 +92,10 @@   , takeRest   , traceRest +  -- * `String` conversions+  , packUTF8+  , unpackUTF8+   -- * Internal functions   , ensureBytes#   , scan8#@@ -100,7 +105,6 @@   , scanAny8#   , scanBytes#   , setBack#-  , packUTF8    ) where @@ -591,7 +595,7 @@  -- | @isLatinLetter c = (\'A\' <= c && c <= \'Z\') || (\'a\' <= c && c <= \'z\')@ isLatinLetter :: Char -> Bool-isLatinLetter c = ('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z')+isLatinLetter c = ('a' <= c && c <= 'z') || ('A' <= c && c <= 'Z') {-# inline isLatinLetter #-}  -- | @isGreekLetter c = (\'Α\' <= c && c <= \'Ω\') || (\'α\' <= c && c <= \'ω\')@@@ -634,9 +638,9 @@ --   combine the results in a right-nested way using the @a -> b -> b@ function. Note: this is not --   the usual `chainr` function from the parsec libraries! chainr :: (a -> b -> b) -> Parser e a -> Parser e b -> Parser e b-chainr f (Parser elem) (Parser end) = go where-  go = Parser \fp eob s -> case elem fp eob s of-    OK# a s -> case runParser# go fp eob s of+chainr f (Parser elem) (Parser end) = Parser go where+  go fp eob s = case elem fp eob s of+    OK# a s -> case go fp eob s of       OK# b s -> let !b' = f a b in OK# b' s       x       -> x     Fail# -> end fp eob s@@ -647,9 +651,9 @@ --   try to avoid this. Often it is possible to get rid of the intermediate list by using a --   combinator or a custom parser. many :: Parser e a -> Parser e [a]-many (Parser f) = go where-  go = Parser \fp eob s -> case f fp eob s of-    OK# a s -> case runParser# go fp eob s of+many (Parser f) = Parser go where+  go fp eob s = case f fp eob s of+    OK# a s -> case go fp eob s of                  OK# as s -> OK# (a:as) s                  x        -> x     Fail#  -> OK# [] s@@ -658,9 +662,9 @@  -- | Skip a parser zero or more times. many_ :: Parser e a -> Parser e ()-many_ (Parser f) = go where-  go = Parser \fp eob s -> case f fp eob s of-    OK# a s -> runParser# go fp eob s+many_ (Parser f) = Parser go where+  go fp eob s = case f fp eob s of+    OK# a s -> go fp eob s     Fail#   -> OK# () s     Err# e  -> Err# e {-# inline many_ #-}@@ -799,13 +803,22 @@        OK res _ -> snd <$> sortBy (comparing fst) res        _        -> error "invalid position" --- | Create a `B.ByteString` from a `Span`. The result is invalid is the `Span` points+-- | Create a `B.ByteString` from a `Span`. The result is invalid if 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 #-} +-- | Slice into a `B.ByteString` using a `Span`. The result is invalid if the `Span`+--   is not a valid slice of the first argument.+unsafeSlice :: B.ByteString -> Span -> B.ByteString+unsafeSlice (B.PS (ForeignPtr addr fp) (I# start) (I# len))+            (Span (Pos (I# o1)) (Pos (I# o2))) =+  let end = addr `plusAddr#` start `plusAddr#` len+  in B.PS (ForeignPtr (plusAddr# end (negateInt# o1)) fp) (I# 0#) (I# (o1 -# o2))+{-# inline unsafeSlice #-}+ -- | Create a `Pos` from a line and column number. Throws an error on out-of-bounds --   line and column numbers. mkPos :: B.ByteString -> (Int, Int) -> Pos@@ -869,6 +882,12 @@ -- | Convert a `String` to an UTF-8-coded `B.ByteString`. packUTF8 :: String -> B.ByteString packUTF8 = B.pack . concatMap charToBytes++-- | Convert an UTF-8-coded `B.ByteString` to a `String`.+unpackUTF8 :: B.ByteString -> String+unpackUTF8 str = case runParser takeRest str of+  OK a _ -> a+  _      -> error "unpackUTF8: invalid encoding"  charToBytes :: Char -> [Word8] charToBytes c'

@@ -59,9 +59,13 @@ digit = (\c -> ord c - ord '0') <$> satisfyASCII isDigit  int :: Parser Int-int = token $-  snd <$> chainr (\n (!place, !acc) -> (place*10,acc+place*n)) digit ((10,) <$> digit) +int = token do+  (place, n) <- chainr (\n (!place, !acc) -> (place*10,acc+place*n)) digit (pure (1, 0))+  case place of+    1 -> empty+    _ -> pure n+ -- | Parse a literal, identifier or parenthesized expression. atom :: Parser Tm atom =@@ -135,7 +139,6 @@ src' = ws *> tm' <* eof `cut` [Msg "end of input (lexical error)"]  - -- Examples -------------------------------------------------------------------------------- @@ -144,5 +147,6 @@ p1 = unlines [   "let f = lam x. lam y. x (x (x y)) in",   "let g = if f true then false else true in",+  "let h = f x y + 200 in",   "f g g h"   ]

@@ -88,6 +88,7 @@   , validPos   , posLineCols   , unsafeSpanToByteString+  , unsafeSlice   , mkPos   , FlatParse.Stateful.lines @@ -97,6 +98,10 @@   , takeRest   , traceRest +  -- * `String` conversions+  , packUTF8+  , unpackUTF8+   -- * Internal functions   , ensureBytes#   , scan8#@@ -106,8 +111,8 @@   , scanAny8#   , scanBytes#   , setBack#-  , packUTF8 +   ) where  import Control.Monad@@ -842,7 +847,16 @@   lookahead (setPos l >> byteStringOf (setPos r)) {-# inline unsafeSpanToByteString #-} +-- | Slice into a `B.ByteString` using a `Span`. The result is invalid if the `Span`+--   is not a valid slice of the first argument.+unsafeSlice :: B.ByteString -> Span -> B.ByteString+unsafeSlice (B.PS (ForeignPtr addr fp) (I# start) (I# len))+            (Span (Pos (I# o1)) (Pos (I# o2))) =+  let end = addr `plusAddr#` start `plusAddr#` len+  in B.PS (ForeignPtr (plusAddr# end (negateInt# o1)) fp) (I# 0#) (I# (o1 -# o2))+{-# inline unsafeSlice #-} + -- | Create a `Pos` from a line and column number. Throws an error on out-of-bounds --   line and column numbers. mkPos :: B.ByteString -> (Int, Int) -> Pos@@ -908,6 +922,12 @@ -- | Convert a `String` to an UTF-8-coded `B.ByteString`. packUTF8 :: String -> B.ByteString packUTF8 = B.pack . concatMap charToBytes++-- | Convert an UTF-8-coded `B.ByteString` to a `String`.+unpackUTF8 :: B.ByteString -> String+unpackUTF8 str = case runParser takeRest 0 0 str of+  OK a _ _ -> a+  _        -> error "unpackUTF8: invalid encoding"  charToBytes :: Char -> [Word8] charToBytes c'