From d55ce2a5f69a9b92b1e2825f48f2c68781aa64aa Mon Sep 17 00:00:00 2001
From: Herbert Valerio Riedel <hvr@gnu.org>
Date: Mon, 17 Dec 2018 20:23:59 +0100
Subject: [PATCH] Extend `Distribution.Simple.Utils.rewriteFileEx` from ASCII
 to UTF-8 encoding

This takes care of knock-off effects of #2557

Specifically, the `Paths_*.hs` and `cabal_macros.h` files would result being incorrectly
by a `rewriteFileEx` which isn't UTF-8 capable.

Now the `cabal_macros.h` file is written out exactly like the `.h` file generated
internally by `ghc` is generated; note however that standard CPP doesn't support
non-ASCII characters in CPP symbols and will thus not work with a standard CPP
preprocessor.
---
 Cabal/ChangeLog.md                 |  1 +
 Cabal/Distribution/Simple/Utils.hs | 19 +++++++++++--------
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/Cabal/ChangeLog.md b/Cabal/ChangeLog.md
index b614e9e7c1a..910a2116760 100644
--- a/Cabal/ChangeLog.md
+++ b/Cabal/ChangeLog.md
@@ -10,6 +10,7 @@
   * Add a `LibraryVisibility` field to `InstalledPackageInfo`
   * Fix corrupted config file header for non-ASCII package names
     ([2557](https://github.com/haskell/cabal/issues/2557)).
+  * Extend `Distribution.Simple.Utils.rewriteFileEx` from ASCII to UTF-8 encoding.
 
 ----
 
diff --git a/Cabal/Distribution/Simple/Utils.hs b/Cabal/Distribution/Simple/Utils.hs
index 7acd49befa1..17ed16e83fb 100644
--- a/Cabal/Distribution/Simple/Utils.hs
+++ b/Cabal/Distribution/Simple/Utils.hs
@@ -205,7 +205,7 @@ import Control.Concurrent.MVar
     ( newEmptyMVar, putMVar, takeMVar )
 import Data.Typeable
     ( cast )
-import qualified Data.ByteString.Lazy.Char8 as BS.Char8
+import qualified Data.ByteString.Lazy as BS
 
 import System.Directory
     ( Permissions(executable), getDirectoryContents, getPermissions
@@ -1401,19 +1401,22 @@ rewriteFile = rewriteFileEx normal
 -- the same as the existing content then leave the file as is so that we do not
 -- update the file's modification time.
 --
--- NB: the file is assumed to be ASCII-encoded.
+-- NB: Before Cabal-3.0 the file content was assumed to be
+--     ASCII-representable. Since Cabal-3.0 the file is assumed to be
+--     UTF-8 encoded.
 rewriteFileEx :: Verbosity -> FilePath -> String -> IO ()
 rewriteFileEx verbosity path newContent =
   flip catchIO mightNotExist $ do
-    existingContent <- annotateIO verbosity $ readFile path
-    _ <- evaluate (length existingContent)
-    unless (existingContent == newContent) $
+    existingContent <- annotateIO verbosity $ BS.readFile path
+    _ <- evaluate (BS.length existingContent)
+    unless (existingContent == newContent') $
       annotateIO verbosity $
-        writeFileAtomic path (BS.Char8.pack newContent)
+        writeFileAtomic path newContent'
   where
+    newContent' = toUTF8LBS newContent
+
     mightNotExist e | isDoesNotExistError e
-                    = annotateIO verbosity $ writeFileAtomic path
-                        (BS.Char8.pack newContent)
+                    = annotateIO verbosity $ writeFileAtomic path newContent'
                     | otherwise
                     = ioError e