[fork validation] Windows portability in library and app code

app/LazyBenchmark.hs

@@ -8,7 +8,7 @@
      Usage:
        cabal run lazy-bench [-- [OPTIONS]]        (+RTS -s -RTS for heap stats)
        --rows N     rows to generate (default 1_000_000_000)
-       --file PATH  output CSV path (default /tmp/lazy_1b.csv)
+       --file PATH  output CSV path (default: lazy_1b.csv in the system temp dir)
        --skip-gen   reuse the file if it already exists
 -}
 module Main where
@@ -22,7 +22,7 @@ import qualified DataFrame as D
 import qualified DataFrame.Lazy as L
 import DataFrame.Operators
 import DataFrame.Schema (Schema (..), schemaType)
-import System.Directory (doesFileExist, getFileSize)
+import System.Directory (doesFileExist, getFileSize, getTemporaryDirectory)
 import System.Environment (getArgs)
 import System.Exit (exitFailure)
 import System.IO (
@@ -42,8 +42,9 @@ import System.Random.Stateful
 defaultRows :: Int
 defaultRows = 1_000_000_000
 
-defaultFile :: FilePath
-defaultFile = "/tmp/lazy_1b.csv"
+-- /tmp does not exist on Windows.
+defaultFile :: IO FilePath
+defaultFile = (<> "/lazy_1b.csv") <$> getTemporaryDirectory
 
 -- Rows written per Builder flush to disk.
 chunkSize :: Int
@@ -59,8 +60,8 @@ data Opts = Opts
     , optSkipGen :: Bool
     }
 
-parseArgs :: [String] -> Either String Opts
-parseArgs = go (Opts defaultRows defaultFile False)
+parseArgs :: FilePath -> [String] -> Either String Opts
+parseArgs defFile = go (Opts defaultRows defFile False)
   where
     go opts [] = Right opts
     go opts ("--rows" : n : rest) = case reads n of
@@ -170,7 +171,8 @@ main :: IO ()
 main = do
     hSetBuffering stdout LineBuffering
     args <- getArgs
-    opts <- case parseArgs args of
+    defFile <- defaultFile
+    opts <- case parseArgs defFile args of
         Left err -> putStrLn ("Error: " ++ err) >> exitFailure
         Right o -> return o
 

dataframe-csv/src/DataFrame/IO/CSV.hs

@@ -35,7 +35,9 @@ import qualified Data.ByteString.Lazy as BL
 import qualified Data.Map.Strict as M
 import qualified Data.Text as T
 import qualified Data.Text.Encoding as TE
-import qualified Data.Text.IO as TIO
+
+-- UTF-8 byte mode; locale handles corrupt output on Windows.
+import qualified Data.Text.IO.Utf8 as TIO
 
 import Control.Exception (SomeException, catch)
 import Data.Maybe (fromMaybe)

dataframe-lazy/src/DataFrame/Lazy/IO/CSV.hs

@@ -103,6 +103,8 @@ readSeparated c opts path = do
             Nothing -> (0, totalRows')
             Just (start, len'') -> (start, min len'' (totalRows' - rowsRead opts))
     withFile path ReadMode $ \handle -> do
+        -- Decode UTF-8, not the locale.
+        hSetEncoding handle utf8
         firstRow <- fmap T.strip . parseSep c <$> TIO.hGetLine handle
         let columnNames =
                 if hasHeader opts
@@ -256,6 +258,7 @@ openCsvStream ::
 openCsvStream sep schema path = do
     handle <- openFile path ReadMode
     hSetBuffering handle (BlockBuffering (Just (8 * 1024 * 1024)))
+    hSetEncoding handle utf8
     headerLine <- TIO.hGetLine handle
     let headerCols = fmap (T.filter (/= '"') . T.strip) (parseSep sep headerLine)
     let schemaMap = elements schema

dataframe-parsing/src-internal/DataFrame/Internal/Parsing.hs

@@ -17,7 +17,15 @@ import Data.Foldable (fold)
 import Data.Text.Read (decimal, double, signed)
 import Data.Time (Day, defaultTimeLocale, parseTimeM)
 import GHC.Stack (HasCallStack)
-import System.IO (Handle, IOMode (..), hIsEOF, hTell, withFile)
+import System.IO (
+    Handle,
+    IOMode (..),
+    hIsEOF,
+    hSetEncoding,
+    hTell,
+    utf8,
+    withFile,
+ )
 import Prelude hiding (takeWhile)
 
 isNullish :: T.Text -> Bool
@@ -187,7 +195,9 @@ lineEnd =
 
 -- | First pass to count rows for exact allocation.
 countRows :: Char -> FilePath -> IO Int
-countRows c path = withFile path ReadMode $! go 0 ""
+countRows c path = withFile path ReadMode $ \h ->
+    -- Decode UTF-8, not the locale.
+    hSetEncoding h utf8 >> go 0 "" h
   where
     go n input h = do
         isEOF <- hIsEOF h

dataframe-viz/src/DataFrame/Display/Web/Plot.hs

@@ -66,15 +66,19 @@ import Data.Char (chr)
 import qualified Data.List as L
 import qualified Data.Maybe
 import qualified Data.Text as T
-import qualified Data.Text.IO as T
+
+-- UTF-8 byte mode; locale handles corrupt output on Windows.
+import qualified Data.Text.IO.Utf8 as T
 import GHC.Stack (HasCallStack)
 import Numeric (showFFloat)
 import System.Directory (getHomeDirectory)
 import System.Info (os)
 import System.Process (
+    CreateProcess,
     StdStream (NoStream),
     createProcess,
     proc,
+    shell,
     std_err,
     std_in,
     std_out,
@@ -471,15 +475,16 @@ showInDefaultBrowser p = do
     putStrLn fullPath
     T.writeFile fullPath (T.pack p)
     case os of
-        "mingw32" -> openFileSilently "start" fullPath
-        "darwin" -> openFileSilently "open" fullPath
-        _ -> openFileSilently "xdg-open" fullPath
+        -- 'start' is a cmd builtin; it needs a shell.
+        "mingw32" -> launchSilently (shell ("start \"\" \"" <> fullPath <> "\""))
+        "darwin" -> launchSilently (proc "open" [fullPath])
+        _ -> launchSilently (proc "xdg-open" [fullPath])
 
-openFileSilently :: FilePath -> FilePath -> IO ()
-openFileSilently program path = do
+launchSilently :: CreateProcess -> IO ()
+launchSilently cp = do
     (_, _, _, ph) <-
         createProcess
-            (proc program [path])
+            cp
                 { std_in = NoStream
                 , std_out = NoStream
                 , std_err = NoStream