From 9d7fdf7c9a525a3b5659a566f76d26d151dcd664 Mon Sep 17 00:00:00 2001
From: hallgren <hallgren@chalmers.se>
Date: Mon, 25 Nov 2013 21:12:11 +0000
Subject: 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.
---
 src/compiler/GF/Infra/Option.hs | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

(limited to 'src/compiler/GF/Infra')

diff --git a/src/compiler/GF/Infra/Option.hs b/src/compiler/GF/Infra/Option.hs
index 115665419..08f0df18b 100644
--- a/src/compiler/GF/Infra/Option.hs
+++ b/src/compiler/GF/Infra/Option.hs
@@ -20,7 +20,7 @@ module GF.Infra.Option
      helpMessage,
      -- * Checking specific options
      flag, cfgTransform, haskellOption, readOutputFormat,
-     isLexicalCat, isLiteralCat, renameEncoding,
+     isLexicalCat, isLiteralCat, renameEncoding, getEncoding, defaultEncoding,
      -- * Setting specific options
      setOptimization, setCFGTransform,
      -- * Convenience methods for checking options    
@@ -157,7 +157,7 @@ data Flags = Flags {
       optRetainResource  :: Bool,
       optName            :: Maybe String,
       optPreprocessors   :: [String],
-      optEncoding        :: String,
+      optEncoding        :: Maybe String,
       optPMCFG           :: Bool,
       optOptimizations   :: Set Optimization,
       optOptimizePGF     :: Bool,
@@ -213,7 +213,7 @@ fixRelativeLibPaths curr_dir lib_dir (Options o) = Options (fixPathFlags . o)
 -- | Pretty-print the options that are preserved in .gfo files.
 optionsGFO :: Options -> [(String,Literal)]
 optionsGFO opts = optionsPGF opts
-      ++ [("coding", LStr (flag optEncoding opts))]
+      ++ [("coding", LStr (getEncoding opts))]
 
 -- | Pretty-print the options that are preserved in .pgf files.
 optionsPGF :: Options -> [(String,Literal)]
@@ -241,6 +241,10 @@ concatOptions = foldr addOptions noOptions
 modifyFlags :: (Flags -> Flags) -> Options
 modifyFlags = Options
 
+getEncoding :: Options -> String
+getEncoding = renameEncoding . maybe defaultEncoding id . flag optEncoding
+defaultEncoding = "UTF-8"
+
 -- Default options
 
 defaultFlags :: Flags
@@ -264,7 +268,7 @@ defaultFlags = Flags {
 
       optName            = Nothing,
       optPreprocessors   = [],
-      optEncoding        = "latin1",
+      optEncoding        = Nothing,
       optPMCFG           = True,
       optOptimizations   = Set.fromList [OptStem,OptCSE,OptExpand,OptParametrize],
       optOptimizePGF     = False,
@@ -419,7 +423,7 @@ optDescr =
        addLibDir   x = set $ \o -> o { optLibraryPath = x:optLibraryPath o }
        setLibPath  x = set $ \o -> o { optLibraryPath = splitInModuleSearchPath x }
        preproc     x = set $ \o -> o { optPreprocessors = optPreprocessors o ++ [x] }
-       coding      x = set $ \o -> o { optEncoding = x }
+       coding      x = set $ \o -> o { optEncoding = Just x }
        startcat    x = set $ \o -> o { optStartCat = Just x }
        language    x = set $ \o -> o { optSpeechLanguage = Just x }
        lexer       x = set $ \o -> o { optLexer = Just x }
-- 
cgit v1.2.3