From e9de3f30db77d73238320d794e584a788f0a0420 Mon Sep 17 00:00:00 2001 From: Andrew Martin Date: Thu, 27 Feb 2020 12:17:23 -0500 Subject: [PATCH] Add copy2 to help avoid multiple length checks --- CHANGELOG.md | 1 + src/Data/ByteArray/Builder.hs | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index bef093f..9f68755 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,7 @@ * Add `reversedOnto` and `commitsOntoChunks`. * Add `ascii(2|3|4|5|6)`. * Add `cstringLen` unbounded builder. +* Add `copy2`. ## 0.3.3.0 -- 2020-02-10 diff --git a/src/Data/ByteArray/Builder.hs b/src/Data/ByteArray/Builder.hs index 2b96d33..5aab322 100644 --- a/src/Data/ByteArray/Builder.hs +++ b/src/Data/ByteArray/Builder.hs @@ -20,6 +20,7 @@ module Data.ByteArray.Builder -- * Materialized Byte Sequences , bytes , copy + , copy2 , insert , byteArray , shortByteString @@ -384,6 +385,25 @@ cstringLen (Exts.Ptr src#, I# slen# ) = Builder where !(I# newSz) = max (I# slen#) 4080 +-- | Create a builder from two byte sequences. This always results in two +-- calls to @memcpy@. This is beneficial when the byte sequences are +-- known to be small (less than 256 bytes). +copy2 :: Bytes -> Bytes -> Builder +copy2 (Bytes (ByteArray srcA# ) (I# soffA# ) (I# slenA# )) + (Bytes (ByteArray srcB# ) (I# soffB# ) (I# slenB# )) = Builder + (\buf0 off0 len0 cs0 s0 -> case len0 <# slen# of + 1# -> case Exts.newByteArray# newSz s0 of + (# s1, buf1 #) -> case Exts.copyByteArray# srcA# soffA# buf1 0# slenA# s1 of + s2 -> case Exts.copyByteArray# srcB# soffB# buf1 slenA# slenB# s2 of + s3 -> (# s3, buf1, slen#, newSz -# slen#, Mutable buf0 off0 cs0 #) + _ -> let !s1 = Exts.copyByteArray# srcA# soffA# buf0 off0 slenA# s0 + !s2 = Exts.copyByteArray# srcB# soffB# buf0 (off0 +# slenA# ) slenB# s1 in + (# s2, buf0, off0 +# slen#, len0 -# slen#, cs0 #) + ) + where + !slen# = slenA# +# slenB# + !(I# newSz) = max (I# slen#) 4080 + -- | Create a builder from a byte sequence. This never calls @memcpy@. -- Instead, it pushes a chunk that references the argument byte sequence. -- This wastes the remaining space in the active chunk, so it may adversely