bytesmith 0.3.2.0 → 0.3.3.0

raw patch · 3 files changed

+95/−4 lines, 3 filesPVP ok

version bump matches the API change (PVP)

API changes (from Hackage documentation)

Files

• CHANGELOG.md +4/−1
• bytesmith.cabal +2/−2
• src/Data/Bytes/Parser/Latin.hs +89/−1

@@ -1,6 +1,9 @@ # Revision history for bytesmith -## 0.3.2.0 -- 2019-??-??+## 0.3.3.0 -- 2020-01-22+* Add `hexWord8`, `hexWord16`, and `hexFixedWord8`.++## 0.3.2.0 -- 2019-12-27  * Add `parseBytesEither` and `parseBytesMaybe`. * Add common idioms from other parser libaries. This includes: `satisfy`,

@@ -1,6 +1,6 @@ cabal-version: 2.2 name: bytesmith-version: 0.3.2.0+version: 0.3.3.0 synopsis: Nonresumable byte parser description:   Parse bytes as fast as possible. This is a nonresumable parser@@ -31,7 +31,7 @@   build-depends:     , base >=4.12 && <5     , bytestring >=0.10.8 && <0.11-    , byteslice >=0.1.3 && <0.3+    , byteslice >=0.1.4 && <0.3     , contiguous >= 0.4 && < 0.6     , primitive >=0.7 && <0.8     , text-short >=0.1.3 && <0.2

@@ -66,7 +66,13 @@   , decUnsignedInteger   , decTrailingInteger     -- ** Hexadecimal+    -- *** Variable Length+  , hexWord8+  , hexWord16+    -- *** Fixed Length+  , hexFixedWord8   , hexFixedWord16+    -- *** Digit   , hexNibbleLower   , tryHexNibbleLower   , hexNibble@@ -398,6 +404,26 @@     (# s1, r #) -> (# s1, upcastWord8Result r #)   ) +-- | Parse a hexadecimal-encoded 8-bit word. If the number is larger+-- than 255, this parser fails. This allows leading zeroes and is+-- insensitive to case. For example, @00A@, @0a@ and @A@ would all+-- be accepted as the same number.+hexWord8 :: e -> Parser e s Word8+hexWord8 e = Parser+  (\chunk0 s0 -> case hexSmallWordStart e 256 (boxBytes chunk0) s0 of+    (# s1, r #) -> (# s1, upcastWord8Result r #)+  )++-- | Parse a hexadecimal-encoded 16-bit word. If the number is larger+-- than 65535, this parser fails. This allows leading zeroes and is+-- insensitive to case. For example, @0100a@ and @100A@ would both+-- be accepted as the same number.+hexWord16 :: e -> Parser e s Word16+hexWord16 e = Parser+  (\chunk0 s0 -> case hexSmallWordStart e 65536 (boxBytes chunk0) s0 of+    (# s1, r #) -> (# s1, upcastWord16Result r #)+  )+ -- | Parse a decimal-encoded 16-bit word. If the number is larger -- than 65535, this parser fails. decWord16 :: e -> Parser e s Word16@@ -434,6 +460,17 @@     (# s1, r #) -> (# s1, upcastWord64Result r #)   ) +hexSmallWordStart ::+     e -- Error message+  -> Word -- Upper Bound+  -> Bytes -- Chunk+  -> ST# s (Result# e Word# )+hexSmallWordStart e !limit !chunk0 s0 = if length chunk0 > 0+  then case oneHexMaybe (PM.indexByteArray (array chunk0) (offset chunk0)) of+    Nothing -> (# s0, (# e | #) #)+    Just w -> (# s0, hexSmallWordMore e w limit (Bytes.unsafeDrop 1 chunk0) #)+  else (# s0, (# e | #) #)+ decSmallWordStart ::      e -- Error message   -> Word -- Upper Bound@@ -479,6 +516,21 @@ upcastWord64Result (# e | #) = (# e | #) upcastWord64Result (# | (# a, b, c #) #) = (# | (# W64# a, b, c #) #) +hexSmallWordMore ::+     e -- Error message+  -> Word -- Accumulator+  -> Word -- Upper Bound+  -> Bytes -- Chunk+  -> Result# e Word#+hexSmallWordMore e !acc !limit !chunk0 = if length chunk0 > 0+  then case oneHexMaybe (PM.indexByteArray (array chunk0) (offset chunk0)) of+    Nothing -> (# | (# unW acc, unI (offset chunk0), unI (length chunk0)  #) #)+    Just w -> let w' = acc * 16 + w in+      if w' < limit+        then hexSmallWordMore e w' limit (Bytes.unsafeDrop 1 chunk0)+        else (# e | #)+  else (# | (# unW acc, unI (offset chunk0), 0# #) #)+ decSmallWordMore ::      e -- Error message   -> Word -- Accumulator@@ -842,7 +894,7 @@     else (# | (# (), unI (offset c + 1), unI (length c - 1) #) #)  -- | Parse exactly four ASCII-encoded characters, interpretting--- them as the hexadecimal encoding of a 32-bit number. Note that+-- them as the hexadecimal encoding of a 16-bit number. Note that -- this rejects a sequence such as @5A9@, requiring @05A9@ instead. -- This is insensitive to case. This is particularly useful when -- parsing escape sequences in C or JSON, which allow encoding@@ -875,6 +927,34 @@            | otherwise -> (# e | #)   else (# e | #) +-- | Parse exactly two ASCII-encoded characters, interpretting+-- them as the hexadecimal encoding of a 8-bit number. Note that+-- this rejects a sequence such as @A@, requiring @0A@ instead.+-- This is insensitive to case.+hexFixedWord8 :: e -> Parser e s Word8+{-# inline hexFixedWord8 #-}+hexFixedWord8 e = Parser+  (\x s0 -> case runParser (hexFixedWord8# e) x s0 of+    (# s1, r #) -> case r of+      (# err | #) -> (# s1, (# err | #) #)+      (# | (# a, b, c #) #) -> (# s1, (# | (# W8# a, b, c #) #) #)+  )++hexFixedWord8# :: e -> Parser e s Word#+{-# noinline hexFixedWord8# #-}+hexFixedWord8# e = uneffectfulWord# $ \chunk -> if length chunk >= 2+  then+    let !w0@(W# n0) = oneHex $ PM.indexByteArray (array chunk) (offset chunk)+        !w1@(W# n1) = oneHex $ PM.indexByteArray (array chunk) (offset chunk + 1)+     in if | w0 .|. w1 /= maxBound ->+             (# |+                (# (n0 `Exts.timesWord#` 16##) `Exts.plusWord#`+                   n1+                ,  unI (offset chunk) +# 2#+                ,  unI (length chunk) -# 2# #) #)+           | otherwise -> (# e | #)+  else (# e | #)+ -- | Consume a single character that is the lowercase hexadecimal -- encoding of a 4-bit word. Fails if the character is not in the class -- @[a-f0-9]@.@@ -935,6 +1015,14 @@   | w >= 65 && w < 71 = (fromIntegral w - 55)   | w >= 97 && w < 103 = (fromIntegral w - 87)   | otherwise = maxBound++oneHexMaybe :: Word8 -> Maybe Word+{-# inline oneHexMaybe #-}+oneHexMaybe w+  | w >= 48 && w < 58 = Just (fromIntegral w - 48)+  | w >= 65 && w < 71 = Just (fromIntegral w - 55)+  | w >= 97 && w < 103 = Just (fromIntegral w - 87)+  | otherwise = Nothing  uneffectfulWord# :: (Bytes -> Result# e Word#) -> Parser e s Word# uneffectfulWord# f = Parser