Add a test for a very simple CSV encoding

bench/Cell.hs

@@ -0,0 +1,32 @@
+{-# language OverloadedLists #-}
+{-# language OverloadedStrings #-}
+
+module Cell
+  ( Cell(..)
+  , cells
+  ) where
+
+import Data.Word (Word32)
+import Data.Text.Short (ShortText)
+import Data.Primitive (SmallArray)
+
+-- A cell in a CSV file
+data Cell
+  = CellString !ShortText
+  | CellNumber !Word32
+
+-- Some sample data to encode as a CSV
+cells :: SmallArray (SmallArray Cell)
+cells =
+  [ [ CellString "Randy", CellString "Gutiérrez", CellNumber 41, CellNumber 343 ]
+  , [ CellString "Édith", CellString "Piaf", CellNumber 63, CellNumber 453 ]
+  , [ CellString "Martha", CellString "Washington", CellNumber 51, CellNumber 634 ]
+  , [ CellString "Julius", CellString "Caesar", CellNumber 1, CellNumber 6922 ]
+  , [ CellString "Robert", CellString "Redford", CellNumber 24, CellNumber 617 ]
+  , [ CellString "Violet", CellString "Crawley", CellNumber 71, CellNumber 150 ]
+  , [ CellString "Lázaro", CellString "Cárdenas", CellNumber 58, CellNumber 299 ]
+  , [ CellString "Anastasia", CellString "San Martin", CellNumber 103, CellNumber 3214 ]
+  , [ CellString "Mad", CellString "Max", CellNumber 37, CellNumber 918 ]
+  , [ CellString "Sidonie-Gabrielle", CellString "Collette", CellNumber 25, CellNumber 904 ]
+  ]
+

bench/Main.hs

@@ -1,11 +1,17 @@
+{-# language LambdaCase #-}
+{-# language OverloadedStrings #-}
+
 import Data.Primitive (ByteArray)
 import Data.Word (Word64)
 import Gauge (bgroup,bench,whnf)
 import Gauge.Main (defaultMain)
 
 import qualified Arithmetic.Nat as Nat
+import qualified Data.ByteArray.Builder as B
 import qualified Data.ByteArray.Builder.Bounded as U
 
+import qualified Cell
+import qualified SimpleCsv
 import qualified HexWord64
 
 main :: IO ()
@@ -16,6 +22,11 @@ main = defaultMain
       , bench "loop" (whnf encodeHexWord64sLoop w64s)
       ]
     ]
+  , bgroup "unbounded"
+    [ bench "csv-no-escape" $ whnf
+        (\x -> B.run 4080 (SimpleCsv.encodeRows x))
+        Cell.cells
+    ]
   ]
 
 w64s :: Word64s

bench/SimpleCsv.hs

@@ -0,0 +1,31 @@
+{-# language LambdaCase #-}
+
+-- A variant of CSV encoding that does not perform
+-- any escaping or quoting. This is in its own module
+-- to make it easy to analyze the GHC Core that it
+-- gets compiled to.
+module SimpleCsv
+  ( encodeRows
+  ) where
+
+import Cell (Cell(..))
+import Data.Primitive (SmallArray)
+
+import qualified Data.Foldable as F
+import qualified Data.ByteArray.Builder as B
+
+encodeRows :: SmallArray (SmallArray Cell) -> B.Builder
+encodeRows = F.foldr
+  (\r x -> encodeSimpleCsvRow r (B.ascii '\n' <> x))
+  mempty
+
+encodeSimpleCsvRow :: SmallArray Cell -> B.Builder -> B.Builder
+encodeSimpleCsvRow cs b = F.foldr
+  (\c x -> encodeSimpleCsvCell c <> B.ascii ',' <> x)
+  b
+  cs
+
+encodeSimpleCsvCell :: Cell -> B.Builder
+encodeSimpleCsvCell = \case
+  CellNumber n -> B.word32Dec n
+  CellString t -> B.shortTextUtf8 t