Change how GF deals with character encodings in grammar files

1. The default encoding is changed from Latin-1 to UTF-8.

2. Alternate encodings should be specified as "--# -coding=enc", the old
   "flags coding=enc" declarations have no effect but are still checked for
   consistency.

3. A transitional warning is generated for files that contain non-ASCII
   characters without specifying a character encoding:

	"Warning: default encoding has changed from Latin-1 to UTF-8"

4. Conversion to Unicode is now done *before* lexing. This makes it possible
   to allow arbitrary Unicode characters in identifiers. But identifiers are
   still stored as ByteStrings, so they are limited to Latin-1 characters
   for now.

5. Lexer.hs is no longer part of the repository. We now generate the lexer
   from Lexer.x with alex>=3. Some workarounds for bugs in alex-3.0 were
   needed. These bugs might already be fixed in newer versions of alex, but
   we should be compatible with what is shipped in the Haskell Platform.

1 files changed, 6 insertions, 9 deletions

diff --git a/src/compiler/GFC.hs b/src/compiler/GFC.hs
index dd9f1771b..99156e16d 100644
--- a/src/compiler/GFC.hs
+++ b/src/compiler/GFC.hs
@@ -24,7 +24,7 @@ import qualified Data.ByteString.Lazy as BSL
 import System.FilePath
 import System.IO
 import Control.Exception
-
+import Control.Monad(unless)
 
 mainGFC :: Options -> [FilePath] -> IO ()
 mainGFC opts fs = do
@@ -46,9 +46,8 @@ compileSourceFiles :: Options -> [FilePath] -> IOE ()
 compileSourceFiles opts fs = 
     do gr <- batchCompile opts fs
        let cnc = justModuleName (last fs)
-       if flag optStopAfterPhase opts == Compile 
-         then return ()
-         else do pgf <- link opts (identS cnc) gr
+       unless (flag optStopAfterPhase opts == Compile) $
+              do pgf <- link opts (identS cnc) gr
                  writePGF opts pgf
                  writeByteCode opts pgf
                  writeOutputs opts pgf
@@ -57,11 +56,9 @@ compileCFFiles :: Options -> [FilePath] -> IOE ()
 compileCFFiles opts fs = 
     do s  <- liftIO $ fmap unlines $ mapM readFile fs
        let cnc = justModuleName (last fs)
-       gf <- getCF cnc s
-       gr <- compileSourceGrammar opts gf
-       if flag optStopAfterPhase opts == Compile 
-         then return ()
-         else do pgf <- link opts (identS cnc) gr
+       gr <- compileSourceGrammar opts =<< getCF cnc s
+       unless (flag optStopAfterPhase opts == Compile) $
+              do pgf <- link opts (identS cnc) gr
                  writePGF opts pgf
                  writeOutputs opts pgf