note a few more changes

Conflicts:
	encoding.cabal

.gitignore

@@ -0,0 +1,22 @@
+### Haskell ###
+dist
+dist-*
+cabal-dev
+*.o
+*.hi
+*.chi
+*.chs.h
+*.dyn_o
+*.dyn_hi
+.hpc
+.hsenv
+.cabal-sandbox/
+cabal.sandbox.config
+*.prof
+*.aux
+*.hp
+*.eventlog
+.stack-work/
+cabal.project.local
+.HTF/
+

CHANGELOG

@@ -0,0 +1,112 @@
+Changes from 0.8 to 0.8.2
+-------------------------
+
+* Deprecated support for very old GHCs
+* Updated cabal file to differentiate between build dependencies and setup dependencies
+* Add upper and lower bounds to build dependencies
+* Stack compatibility
+
+Changes from 0.8 to 0.8.1
+-------------------------
+
+* Added the ShiftJIS and CP932 encodings
+
+Changes from 0.7.0.2 to 0.8
+---------------------------
+
+* GHC-7.10/AMP compatibility
+
+Changes from 0.7.0.1 to 0.7.0.2
+-------------------------------
+
+* Flesh out the MacOSRoman encoding, which was missing 33 code points
+
+Changes from 0.7 to 0.7.0.1
+---------------------------
+
+* GHC-7.8 compatibility
+
+Changes from 0.6.7 to 0.7
+-------------------------
+
+* the type of ByteSource's fetchAhead method changed to accomodate updates to the binary package
+
+Changes from 0.6.5 to 0.6.7
+---------------------------
+
+* Skipped version 0.6.6 due to rogue upload on Hackage
+* GHC-7 and HaXml-1.22 compatibility
+* add -systemEncoding flag for Windows builds
+
+Changes from 0.6.4 to 0.6.5
+---------------------------
+
+* Make package work with >=base-4.3.0.0 and mtl-2
+
+Changes from 0.6.3 to 0.6.4
+---------------------------
+
+* Throw an error when encoding non-ascii chars with ascii
+* Fix compilation with mtl-2
+
+Changes from 0.6.2 to 0.6.3
+---------------------------
+
+* Use new QuickCheck version 2 for tests
+* Fixed UTF16 encoding range
+
+Changes from 0.6.0 to 0.6.1
+---------------------------
+
+* Support for many MSDOS codepages
+* Show instance for DynEncoding
+* More IO functions
+* Fancy translation tables for the documentation of auto-generated modules
+
+Changes from 0.5.2 to 0.6.0
+---------------------------
+
+* Moved from TemplateHaskell to a custom pre-processor for code-generation.
+  This is necessary because:
+  - TemplateHaskell is really slow for large data structures
+  - TemplateHaskell doesn't yet support the MagicHash extension that is useful for the library
+* Use efficient, static data structures for encoding/decoding
+* Fixed bug in UTF-8 that could call 'chr' with bad arguments
+
+Changes from 0.5 to 0.5.2
+-------------------------
+
+* Export function encodingFromStringExplicit
+
+Changes from 0.4 to 0.5
+-----------------------
+
+* Complete rewrite of the Encoding class to allow for
+  - On-the-fly changing of the encoding while en-/decoding
+  - Ability to en-/decode from/to any data structure
+* A general module to help specify encodings based on ISO 2022
+* New encodings:
+  - JIS X 0201
+  - JIS X 0208
+  - ISO 2022-JP
+* More test cases
+
+Changes from 0.3 to 0.4
+-----------------------
+
+* A new, strict UTF-8 decoder
+* Minor bugs fixed in UTF-16 and BootString
+* Test cases for UTF-8, UTF-16 and BootString
+* Added KOI8U encoding
+
+Changes from 0.2 to 0.3
+-----------------------
+
+* Converted to new cabal interface
+* Support for GHC 6.8
+* Support for new bytestring interface
+
+Changes from 0.1 to 0.2
+-----------------------
+
+* Implemented GB18030 encoding

Data/Array/Static.hs

@@ -0,0 +1,15 @@
+{-# LANGUAGE MagicHash,BangPatterns #-}
+module Data.Array.Static where
+
+import Data.Static
+import GHC.Exts
+import Data.Ix
+
+data StaticArray i e = StaticArray i i Addr#
+
+bounds :: Ix i => StaticArray i e -> (i,i)
+bounds (StaticArray s e _) = (s,e)
+
+(!) :: (StaticElement e,Ix i) => StaticArray i e -> i -> e
+(!) (StaticArray s e addr) i = let !(I# ri) = index (s,e) i
+                               in extract addr ri

Data/Array/Static/Builder.hs

@@ -0,0 +1,12 @@
+{-# LANGUAGE MagicHash #-}
+module Data.Array.Static.Builder where
+
+import Data.Static
+
+buildStaticArray :: (StaticElement e,Show i) => (i,i) -> [e] -> String
+buildStaticArray (s,e) els = "StaticArray ("++show s++") ("++show e++") \""
+                             ++concat (map (\w -> '\\':show w) (concat (map gen els)))
+                             ++"\"#"
+
+buildStaticArray' :: (StaticElement e) => [e] -> String
+buildStaticArray' els = buildStaticArray (0,length els-1) els

Data/CharMap.hs

@@ -0,0 +1,73 @@
+module Data.CharMap where
+
+import Data.Map.Static
+import Data.Encoding.ByteSink
+import Data.Encoding.Exception
+
+import Control.Throws
+import Data.Word
+import Data.Char
+import Prelude hiding (lookup)
+
+data CharMap
+    = Node       !Char !CharMap !CharMap
+    | DeadEnd
+    | LeafRange1 !Int !Word8
+    | LeafRange2 !Int !Word8 !Word8 !Word8
+    | LeafRange3 !Int !Word8 !Word8 !Word8 !Word8 !Word8
+    | LeafRange4 !Int !Word8 !Word8 !Word8 !Word8 !Word8 !Word8 !Word8
+    | LeafMap1 (StaticMap Char Word8)
+    | LeafMap2 (StaticMap Char Word16)
+    | LeafMap4 (StaticMap Char Word32)
+
+mapEncode :: ByteSink m => Char -> CharMap -> m ()
+mapEncode ch (Node rch l r)
+              | ch < rch  = mapEncode ch l
+              | otherwise = mapEncode ch r
+mapEncode ch DeadEnd = throwException (HasNoRepresentation ch)
+mapEncode ch (LeafRange1 bch st)
+    = pushWord8 $ st + (fromIntegral ((ord ch) - bch))
+mapEncode ch (LeafRange2 bch min1 min2 r2)
+    = let v = (ord ch) - bch
+          (w1,w2) = v `divMod` (fromIntegral r2)
+      in do
+        pushWord8 (fromIntegral w1 + min1)
+        pushWord8 (fromIntegral w2 + min2)
+mapEncode ch (LeafRange3 bch min1 min2 r2 min3 r3)
+    = let v = (ord ch) - bch
+          (v1,w3) = v  `divMod` (fromIntegral r3)
+          (w1,w2) = v1 `divMod` (fromIntegral r2)
+      in do
+        pushWord8 (fromIntegral w1 + min1)
+        pushWord8 (fromIntegral w2 + min2)
+        pushWord8 (fromIntegral w3 + min3)
+mapEncode ch (LeafRange4 bch min1 min2 r2 min3 r3 min4 r4)
+    = let v = (ord ch) - bch
+          (v1,w4) = v  `divMod` (fromIntegral r4)
+          (v2,w3) = v1 `divMod` (fromIntegral r3)
+          (w1,w2) = v2 `divMod` (fromIntegral r2)
+      in do
+        pushWord8 (fromIntegral w1 + min1)
+        pushWord8 (fromIntegral w2 + min2)
+        pushWord8 (fromIntegral w3 + min3)
+        pushWord8 (fromIntegral w4 + min4)
+mapEncode ch (LeafMap1 mp) = case lookup ch mp of
+                               Nothing -> throwException (HasNoRepresentation ch)
+                               Just v -> pushWord8 v
+mapEncode ch (LeafMap2 mp) = case lookup ch mp of
+                               Nothing -> throwException (HasNoRepresentation ch)
+                               Just v -> pushWord16be v
+mapEncode ch (LeafMap4 mp) = case lookup ch mp of
+                               Nothing -> throwException (HasNoRepresentation ch)
+                               Just v -> pushWord32be v
+
+
+mapMember :: Char -> CharMap -> Bool
+mapMember c (Node rc l r)
+    | c < rc = mapMember c l
+    | otherwise = mapMember c r
+mapMember c DeadEnd = False
+mapMember c (LeafMap1 mp) = member c mp
+mapMember c (LeafMap2 mp) = member c mp
+mapMember c (LeafMap4 mp) = member c mp
+mapMember c _ = True

Data/CharMap/Builder.hs

@@ -0,0 +1,64 @@
+module Data.CharMap.Builder where
+
+import Data.Map.Static.Builder
+
+import Data.List
+import Data.Ord
+import Data.Char
+import Data.Bits
+import Data.Word
+
+data BuildingBlock
+    = SingleMapping Char [Word8]
+    | RangeMapping Char Char Int [(Word8,Word8)]
+
+charRange :: BuildingBlock -> (Char,Char)
+charRange (SingleMapping c _) = (c,c)
+charRange (RangeMapping s e _ _) = (s,e)
+
+mappingLength :: BuildingBlock -> Int
+mappingLength (SingleMapping _ w) = length w
+mappingLength (RangeMapping _ _ _ ws) = length ws
+
+isRange :: BuildingBlock -> Bool
+isRange (SingleMapping _ _) = False
+isRange (RangeMapping _ _ _ _) = True
+
+buildCharMap :: [BuildingBlock] -> String
+buildCharMap lst = let slst = sortBy (comparing (fst.charRange)) lst
+                       grps = groupBy (\x y -> (not (isRange x || isRange y))
+                                              && mappingLength x == mappingLength y
+                                      ) slst
+
+                       split' xs = splitAt (length xs `div` 2) xs
+                       
+                       build' [] _ _ = "DeadEnd"
+                       build' [[RangeMapping st end off (x:xs)]] bl br
+                           = let e1 = if bl < st
+                                      then "Node ("++show st++") DeadEnd ("++e2++")"
+                                      else e2
+                                 e2 = if br>end
+                                      then "Node ("++show end++") ("++e3++") DeadEnd"
+                                      else e3
+                                 e3 = "LeafRange"++show (length xs+1)++" ("++show (ord st - off)++") "
+                                      ++show (fst x)++concat (map (\(w,r) -> " "++show w++" "++show r) xs)
+                             in e1
+                       build' [mps@((SingleMapping _ w):_)] bl br
+                           = "LeafMap"++show (length w)++" ("
+                             ++(case length w of
+                                  1 -> buildStaticMap (map (\(SingleMapping c [w]) -> (c,w)) mps)
+                                  2 -> buildStaticMap $ map (\(SingleMapping c [w1,w2])
+                                                               -> (c,((fromIntegral w1) `shiftL` 8) .|. (fromIntegral w2)::Word16)
+                                                           ) mps
+                                  4 -> buildStaticMap $ map (\(SingleMapping c [w1,w2,w3,w4])
+                                                                -> (c,((fromIntegral w1) `shiftL` 24)
+                                                                   .|. ((fromIntegral w2) `shiftL` 16)
+                                                                   .|. ((fromIntegral w3) `shiftL` 8)
+                                                                   .|. (fromIntegral w4)::Word32)
+                                                           ) mps)++")"
+                       build' mps bl br = let (l,r@((spl:_):_)) = split' mps
+                                              (el,_) = charRange spl
+                                          in "Node ("++show el++") ("++build' l bl (pred el)++") ("++
+                                             build' r el br++")"
+                                               
+                   in build' grps minBound maxBound

Data/Encoding.hs

@@ -1,4 +1,4 @@
-{-# LANGUAGE FlexibleContexts,ExistentialQuantification #-}
+{-# LANGUAGE FlexibleContexts #-}
 module Data.Encoding
     (module Data.Encoding.Exception
     ,module Data.Encoding.ByteSource
@@ -19,6 +19,7 @@ module Data.Encoding
     ,decodeStrictByteString
     ,decodeStrictByteStringExplicit
     ,encodingFromString
+    ,encodingFromStringExplicit
     )
     where
 
@@ -71,17 +72,31 @@ import Data.Encoding.CP1258
 import Data.Encoding.KOI8R
 import Data.Encoding.KOI8U
 import Data.Encoding.GB18030
+import Data.Encoding.MacOSRoman
+import Data.Encoding.JISX0201
+import Data.Encoding.JISX0208
+import Data.Encoding.ISO2022JP
+import Data.Encoding.ShiftJIS
+import Data.Encoding.CP437
+import Data.Encoding.CP737
+import Data.Encoding.CP775
+import Data.Encoding.CP850
+import Data.Encoding.CP852
+import Data.Encoding.CP855
+import Data.Encoding.CP857
+import Data.Encoding.CP860
+import Data.Encoding.CP861
+import Data.Encoding.CP862
+import Data.Encoding.CP863
+import Data.Encoding.CP864
+import Data.Encoding.CP865
+import Data.Encoding.CP866
+import Data.Encoding.CP869
+import Data.Encoding.CP874
+import Data.Encoding.CP932
 import Data.Char
 import Text.Regex
 
-data DynEncoding = forall enc. Encoding enc => DynEncoding enc
-
-instance Encoding DynEncoding where
-    decodeChar (DynEncoding e) = decodeChar e
-    encodeChar (DynEncoding e) = encodeChar e
-    decode (DynEncoding e) = decode e
-    encode (DynEncoding e) = encode e
-
 recode :: (Encoding enc1,Encoding enc2,ByteSource m,ByteSink m) => enc1 -> enc2 -> m ()
 recode e1 e2 = untilM_ sourceEmpty (decodeChar e1 >>= encodeChar e2)
 
@@ -129,8 +144,8 @@ decodeStrictByteStringExplicit :: Encoding enc => enc -> BS.ByteString -> Either
 decodeStrictByteStringExplicit e str = evalStateT (decode e) str
 
 -- | Like 'encodingFromString' but returns 'Nothing' instead of throwing an error
-encodingFromStringMaybe :: String -> Maybe DynEncoding
-encodingFromStringMaybe codeName = case (normalizeEncoding codeName) of
+encodingFromStringExplicit :: String -> Maybe DynEncoding
+encodingFromStringExplicit codeName = case (normalizeEncoding codeName) of
     -- ASCII
     "ascii"              -> Just $ DynEncoding ASCII
     "646"                -> Just $ DynEncoding ASCII
@@ -306,6 +321,35 @@ encodingFromStringMaybe codeName = case (normalizeEncoding codeName) of
     -- GB18030
     "gb18030"            -> Just $ DynEncoding GB18030
     "gb18030_2000"       -> Just $ DynEncoding GB18030
+    -- MacOSRoman
+    "macintosh"          -> Just $ DynEncoding MacOSRoman
+    -- JIS X 0201
+    "jis_x_0201"         -> Just $ DynEncoding JISX0201
+    -- JIS X 0208
+    "jis_x_0208"         -> Just $ DynEncoding JISX0208
+    -- ISO 2022-JP
+    "iso_2022_jp"        -> Just $ DynEncoding ISO2022JP
+    -- Shift JIS
+    "shift_jis"          -> Just $ DynEncoding ShiftJIS
+    "sjis"               -> Just $ DynEncoding ShiftJIS
+    -- MSDOS codepages
+    "cp437"              -> Just $ DynEncoding CP437
+    "cp737"              -> Just $ DynEncoding CP737
+    "cp775"              -> Just $ DynEncoding CP775
+    "cp850"              -> Just $ DynEncoding CP850
+    "cp852"              -> Just $ DynEncoding CP852
+    "cp855"              -> Just $ DynEncoding CP855
+    "cp857"              -> Just $ DynEncoding CP857
+    "cp860"              -> Just $ DynEncoding CP860
+    "cp861"              -> Just $ DynEncoding CP861
+    "cp862"              -> Just $ DynEncoding CP862
+    "cp863"              -> Just $ DynEncoding CP863
+    "cp864"              -> Just $ DynEncoding CP864
+    "cp865"              -> Just $ DynEncoding CP865
+    "cp866"              -> Just $ DynEncoding CP866
+    "cp869"              -> Just $ DynEncoding CP869
+    "cp874"              -> Just $ DynEncoding CP874
+    "cp932"              -> Just $ DynEncoding CP932
     -- defaults to nothing
     _                    -> Nothing
   where
@@ -317,4 +361,4 @@ encodingFromString :: String -> DynEncoding
 encodingFromString str = maybe
 	(error $ "Data.Encoding.encodingFromString: Unknown encoding: "++show str)
 	id
-	(encodingFromStringMaybe str)
+	(encodingFromStringExplicit str)

Data/Encoding/ASCII.hs

@@ -1,10 +1,12 @@
 {-# LANGUAGE DeriveDataTypeable #-}
 module Data.Encoding.ASCII where
 
+import Control.Throws
 import Data.Char
 import Data.Encoding.Base
 import Data.Encoding.ByteSource
 import Data.Encoding.ByteSink
+import Data.Encoding.Exception
 import Data.Typeable
 
 data ASCII = ASCII deriving (Show,Eq,Typeable)
@@ -13,5 +15,7 @@ instance Encoding ASCII where
     decodeChar _ = do
       w <- fetchWord8
       return $ chr $ fromIntegral w
-    encodeChar _ c = do
-      pushWord8 $ fromIntegral $ ord c
+    encodeChar enc c
+      | encodeable enc c = pushWord8 . fromIntegral . ord $ c
+      | otherwise        = throwException . HasNoRepresentation $ c
+    encodeable _ c = c < '\128'

Data/Encoding/Base.hs

@@ -1,3 +1,4 @@
+{-# LANGUAGE ExistentialQuantification #-}
 module Data.Encoding.Base where
 
 import Data.Encoding.Exception
@@ -5,18 +6,49 @@ import Data.Encoding.ByteSource
 import Data.Encoding.ByteSink
 
 import Control.Throws
-import Data.Array as Array
+import Data.Array.Unboxed as Array
 import Data.Map as Map hiding ((!))
 import Data.Word
 import Data.Char
+import Data.Typeable
 
+{- | The base class for all encodings. At least decodeChar, encodeChar and encodeable must be implemented.
+ -}
 class Encoding enc where
+    -- | Read a single character of a ByteSource
     decodeChar :: ByteSource m => enc -> m Char
+    -- | Encode a single character and write it to a ByteSink
     encodeChar :: ByteSink m => enc -> Char -> m ()
+    -- | Read characters from a ByteSource until it is empty
     decode :: ByteSource m => enc -> m String
     decode e = untilM sourceEmpty (decodeChar e)
+    -- | Encode a String and write it to a ByteSink
     encode :: ByteSink m => enc -> String -> m ()
     encode e = mapM_ (encodeChar e)
+    -- | Tests whether a given character is representable in the Encoding.
+    --   If this yields True, encodeChar must not fail.
+    --   If it yields False, encodeChar _must_ throw an exception.
+    encodeable :: enc -> Char -> Bool
+
+{- | Wraps all possible encoding types into one data type.
+     Used when a function needs to return an encoding.
+ -}
+data DynEncoding = forall enc. (Encoding enc,Eq enc,Typeable enc,Show enc) => DynEncoding enc
+
+instance Show DynEncoding where
+    show (DynEncoding enc) = show enc
+
+instance Encoding DynEncoding where
+    decodeChar (DynEncoding e) = decodeChar e
+    encodeChar (DynEncoding e) = encodeChar e
+    decode (DynEncoding e) = decode e
+    encode (DynEncoding e) = encode e
+    encodeable (DynEncoding e) = encodeable e
+
+instance Eq DynEncoding where
+    (DynEncoding e1) == (DynEncoding e2) = case cast e2 of
+                                             Nothing -> False
+                                             Just e2' -> e1==e2'
 
 untilM :: Monad m => m Bool -> m a -> m [a]
 untilM check act = do
@@ -27,7 +59,7 @@ untilM check act = do
            x <- act
            xs <- untilM check act
            return (x:xs)
-           )
+         )
 
 untilM_ :: Monad m => m Bool -> m a -> m ()
 untilM_ check act = untilM check act >> return ()
@@ -37,9 +69,33 @@ encodeWithMap mp c = case Map.lookup c mp of
                        Nothing -> throwException $ HasNoRepresentation c
                        Just v -> pushWord8 v
 
-decodeWithArray :: ByteSource m => Array Word8 (Maybe Char) -> m Char
+encodeWithMap2 :: ByteSink m => Map Char (Word8,Word8) -> Char -> m ()
+encodeWithMap2 mp c = case Map.lookup c mp of
+                        Nothing -> throwException $ HasNoRepresentation c
+                        Just (w1,w2) -> do
+                          pushWord8 w1
+                          pushWord8 w2
+
+encodeableWithMap :: Map Char a -> Char -> Bool
+encodeableWithMap = flip Map.member
+
+decodeWithArray :: ByteSource m => UArray Word8 Int -> m Char
 decodeWithArray arr = do
   w <- fetchWord8
-  case arr!w of
-    Nothing -> throwException $ IllegalCharacter w
-    Just c -> return c
+  let res = arr!w
+  if res < 0
+    then throwException $ IllegalCharacter w
+    else return $ chr res
+
+decodeWithArray2 :: ByteSource m => UArray (Word8,Word8) Int -> m Char
+decodeWithArray2 arr = do
+  w1 <- fetchWord8
+  w2 <- fetchWord8
+  if inRange (bounds arr) (w1,w2)
+    then (do
+           let res = arr!(w1,w2)
+           if res < 0
+             then throwException $ IllegalCharacter w1
+             else return $ chr res
+         )
+    else throwException $ IllegalCharacter w1

Data/Encoding/BootString.hs

@@ -182,3 +182,4 @@ instance Encoding BootString where
                                 Nothing -> punyDecode base nbase
                                 Just ww -> throwException (IllegalCharacter ww)
 	Nothing -> punyDecode [] wrds
+    encodeable bs c = True -- XXX: hm, really?

Data/Encoding/ByteSink.hs

@@ -1,4 +1,4 @@
-{-# LANGUAGE FlexibleInstances,FlexibleContexts,MultiParamTypeClasses #-}
+{-# LANGUAGE FlexibleInstances,FlexibleContexts,MultiParamTypeClasses,CPP #-}
 module Data.Encoding.ByteSink where
 
 import Data.Encoding.Exception
@@ -11,6 +11,7 @@ import Data.Word
 import Data.Foldable (toList)
 import Control.Throws
 import Control.Exception.Extensible
+import Control.Applicative
 import Control.Monad.State
 import Control.Monad.Identity
 import Control.Monad.Reader
@@ -80,6 +81,13 @@ instance ByteSink PutM where
 
 newtype PutME a = PutME (Either EncodingException (PutM (),a))
 
+instance Functor PutME where
+  fmap = liftM
+
+instance Applicative PutME where
+  pure = return
+  (<*>) = ap
+
 instance Monad PutME where
     return x = PutME $ Right (return (),x)
     (PutME x) >>= g = PutME $ do
@@ -101,22 +109,26 @@ instance ByteSink PutME where
     pushWord64be w = PutME $ Right (putWord64be w,())
     pushWord64le w = PutME $ Right (putWord64le w,())
 
+#if MIN_VERSION_base(4,3,0)
+#else
 instance Monad (Either EncodingException) where
     return x = Right x
     Left err >>= g = Left err
     Right x >>= g = g x
+#endif
 
-instance Throws EncodingException (State (Seq Char)) where
-    throwException = throw
-
-instance ByteSink (State (Seq Char)) where
-    pushWord8 x = modify (|> (chr $ fromIntegral x))
-
-instance ByteSink (StateT (Seq Char) (Either EncodingException)) where
+instance (Monad m,Throws EncodingException m) => ByteSink (StateT (Seq Char) m) where
     pushWord8 x = modify (|> (chr $ fromIntegral x))
 
 newtype StrictSink a = StrictS (Ptr Word8 -> Int -> Int -> IO (a,Ptr Word8,Int,Int))
 
+instance Functor StrictSink where
+  fmap = liftM
+
+instance Applicative StrictSink where
+  pure = return
+  (<*>) = ap
+
 instance Monad StrictSink where
     return x = StrictS $ \cstr pos max -> return (x,cstr,pos,max)
     (StrictS f) >>= g = StrictS (\cstr pos max -> do
@@ -143,6 +155,13 @@ instance ByteSink StrictSink where
 
 newtype StrictSinkE a = StrictSinkE (StrictSink (Either EncodingException a))
 
+instance Functor StrictSinkE where
+  fmap = liftM
+
+instance Applicative StrictSinkE where
+  pure = return
+  (<*>) = ap
+
 instance Monad StrictSinkE where
     return = StrictSinkE . return . Right
     (StrictSinkE s) >>= g = StrictSinkE $ do
@@ -170,6 +189,13 @@ createStrict sink = createStrictWithLen sink 32
 
 newtype StrictSinkExplicit a = StrictSinkExplicit  (StrictSink (Either EncodingException a))
 
+instance Functor StrictSinkExplicit where
+  fmap = liftM
+
+instance Applicative StrictSinkExplicit where
+  pure = return
+  (<*>) = ap
+
 instance Monad StrictSinkExplicit where
     return = (StrictSinkExplicit).return.Right
     (StrictSinkExplicit sink) >>= f
@@ -192,4 +218,4 @@ instance ByteSink (ReaderT Handle IO) where
     pushWord8 x = do
       h <- ask
       liftIO $ do
-        hPutChar h (chr $ fromIntegral x)
+        hPutChar h (chr $ fromIntegral x)

Data/Encoding/ByteSource.hs

@@ -1,4 +1,4 @@
-{-# LANGUAGE FlexibleInstances,FlexibleContexts,MultiParamTypeClasses #-}
+{-# LANGUAGE FlexibleInstances,FlexibleContexts,MultiParamTypeClasses,CPP #-}
 module Data.Encoding.ByteSource where
 
 import Data.Encoding.Exception
@@ -6,7 +6,9 @@ import Data.Encoding.Exception
 import Data.Bits
 import Data.Binary.Get
 import Data.Char
+import Data.Maybe
 import Data.Word
+import Control.Applicative as A
 import Control.Monad.State
 import Control.Monad.Identity
 import Control.Monad.Reader
@@ -19,6 +21,9 @@ import System.IO
 class (Monad m,Throws DecodingException m) => ByteSource m where
     sourceEmpty :: m Bool
     fetchWord8 :: m Word8
+    -- 'fetchAhead act' should return the same thing 'act' does, but should
+    -- only consume input if 'act' returns a 'Just' value
+    fetchAhead :: m (Maybe a) -> m (Maybe a)
     fetchWord16be :: m Word16
     fetchWord16be = do
       w1 <- fetchWord8
@@ -94,6 +99,20 @@ instance Throws DecodingException Get where
 instance ByteSource Get where
     sourceEmpty = isEmpty
     fetchWord8 = getWord8
+#if MIN_VERSION_binary(0,6,0)
+    fetchAhead act = (do
+        res <- act
+        case res of
+            Nothing -> A.empty
+            Just a  -> return res
+        ) <|> return Nothing
+#else
+    fetchAhead act = do
+        res <- lookAhead act
+        case res of
+            Nothing -> return Nothing
+            Just a  -> act
+#endif
     fetchWord16be = getWord16be
     fetchWord16le = getWord16le
     fetchWord32be = getWord32be
@@ -101,54 +120,55 @@ instance ByteSource Get where
     fetchWord64be = getWord64be
     fetchWord64le = getWord64le
 
-instance Throws DecodingException (State [Char]) where
-    throwException = throw
+fetchAheadState act = do
+    chs <- get
+    res <- act
+    when (isNothing res) (put chs)
+    return res
 
-instance ByteSource (State [Char]) where
+instance ByteSource (StateT [Char] Identity) where
     sourceEmpty = gets null
     fetchWord8 = do
       chs <- get
       case chs of
-        [] -> throw UnexpectedEnd
+        [] -> throwException UnexpectedEnd
         c:cs -> do
           put cs
           return (fromIntegral $ ord c)
+    fetchAhead = fetchAheadState
 
+#if MIN_VERSION_base(4,3,0)
+#else
 instance Monad (Either DecodingException) where
     return = Right
     (Left err) >>= g = Left err
     (Right x) >>= g = g x
+#endif
 
 instance ByteSource (StateT [Char] (Either DecodingException)) where
     sourceEmpty = gets null
     fetchWord8 = do
       chs <- get
       case chs of
-        [] -> throwException UnexpectedEnd --handleDecodingError UnexpectedEnd
+        [] -> throwException UnexpectedEnd
         c:cs -> do
           put cs
           return (fromIntegral $ ord c)
+    fetchAhead = fetchAheadState
 
-instance Throws DecodingException (State BS.ByteString) where
-    throwException = throw
-
-instance ByteSource (State BS.ByteString) where
-    sourceEmpty = gets BS.null
-    fetchWord8 = State (\str -> case BS.uncons str of
-                                  Nothing -> throw UnexpectedEnd
-                                  Just (c,cs) -> (c,cs))
-
-instance ByteSource (StateT BS.ByteString (Either DecodingException)) where
+instance (Monad m,Throws DecodingException m) => ByteSource (StateT BS.ByteString m) where
     sourceEmpty = gets BS.null
     fetchWord8 = StateT (\str -> case BS.uncons str of
-                                  Nothing -> Left UnexpectedEnd
-                                  Just ns -> Right ns)
+                                  Nothing -> throwException UnexpectedEnd
+                                  Just (c,cs) -> return (c,cs))
+    fetchAhead = fetchAheadState
 
 instance ByteSource (StateT LBS.ByteString (Either DecodingException)) where
     sourceEmpty = gets LBS.null
     fetchWord8 = StateT (\str -> case LBS.uncons str of
                                   Nothing -> Left UnexpectedEnd
                                   Just ns -> Right ns)
+    fetchAhead = fetchAheadState
 
 instance ByteSource (ReaderT Handle IO) where
     sourceEmpty = do
@@ -158,4 +178,10 @@ instance ByteSource (ReaderT Handle IO) where
       h <- ask
       liftIO $ do
         ch <- hGetChar h
-        return (fromIntegral $ ord ch)
+        return (fromIntegral $ ord ch)
+    fetchAhead act = do
+      h <- ask
+      pos <- liftIO $ hGetPosn h
+      res <- act
+      when (isNothing res) (liftIO $ hSetPosn pos)
+      return res

Data/Encoding/CP1250.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.CP1250 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "CP1250" "CP1250.TXT" )

Data/Encoding/CP1250.mapping

@@ -1,21 +1,5 @@
-#
-#    Name:     cp1250 to Unicode table
-#    Unicode version: 2.0
-#    Table version: 2.01
-#    Table format:  Format A
-#    Date:          04/15/98
-#
-#    Contact:       Shawn.Steele@microsoft.com
-#
-#    General notes: none
-#
-#    Format: Three tab-separated columns
-#        Column #1 is the cp1250 code (in hex)
-#        Column #2 is the Unicode (in hex as 0xXXXX)
-#        Column #3 is the Unicode name (follows a comment sign, '#')
-#
-#    The entries are in cp1250 order
-#
+#Implements the Windows-1250 encoding.
+#For details, refer to <http://en.wikipedia.org/wiki/Windows-1250>.
 0x00	0x0000	#NULL
 0x01	0x0001	#START OF HEADING
 0x02	0x0002	#START OF TEXT

Data/Encoding/CP1251.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.CP1251 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "CP1251" "CP1251.TXT" )

Data/Encoding/CP1251.mapping

@@ -1,21 +1,3 @@
-#
-#    Name:     cp1251 to Unicode table
-#    Unicode version: 2.0
-#    Table version: 2.01
-#    Table format:  Format A
-#    Date:          04/15/98
-#
-#    Contact:       Shawn.Steele@microsoft.com
-#
-#    General notes: none
-#
-#    Format: Three tab-separated columns
-#        Column #1 is the cp1251 code (in hex)
-#        Column #2 is the Unicode (in hex as 0xXXXX)
-#        Column #3 is the Unicode name (follows a comment sign, '#')
-#
-#    The entries are in cp1251 order
-#
 0x00	0x0000	#NULL
 0x01	0x0001	#START OF HEADING
 0x02	0x0002	#START OF TEXT

Data/Encoding/CP1252.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.CP1252 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "CP1252" "CP1252.TXT" )

Data/Encoding/CP1252.mapping

@@ -1,21 +1,3 @@
-#
-#    Name:     cp1252 to Unicode table
-#    Unicode version: 2.0
-#    Table version: 2.01
-#    Table format:  Format A
-#    Date:          04/15/98
-#
-#    Contact:       Shawn.Steele@microsoft.com
-#
-#    General notes: none
-#
-#    Format: Three tab-separated columns
-#        Column #1 is the cp1252 code (in hex)
-#        Column #2 is the Unicode (in hex as 0xXXXX)
-#        Column #3 is the Unicode name (follows a comment sign, '#')
-#
-#    The entries are in cp1252 order
-#
 0x00	0x0000	#NULL
 0x01	0x0001	#START OF HEADING
 0x02	0x0002	#START OF TEXT

Data/Encoding/CP1253.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.CP1253 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "CP1253" "CP1253.TXT" )

Data/Encoding/CP1253.mapping

@@ -1,21 +1,3 @@
-#
-#    Name:     cp1253 to Unicode table
-#    Unicode version: 2.0
-#    Table version: 2.01
-#    Table format:  Format A
-#    Date:          04/15/98
-#
-#    Contact:       Shawn.Steele@microsoft.com
-#
-#    General notes: none
-#
-#    Format: Three tab-separated columns
-#        Column #1 is the cp1253 code (in hex)
-#        Column #2 is the Unicode (in hex as 0xXXXX)
-#        Column #3 is the Unicode name (follows a comment sign, '#')
-#
-#    The entries are in cp1253 order
-#
 0x00	0x0000	#NULL
 0x01	0x0001	#START OF HEADING
 0x02	0x0002	#START OF TEXT

Data/Encoding/CP1254.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.CP1254 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "CP1254" "CP1254.TXT" )

Data/Encoding/CP1254.mapping

@@ -1,21 +1,3 @@
-#
-#    Name:     cp1254 to Unicode table
-#    Unicode version: 2.0
-#    Table version: 2.01
-#    Table format:  Format A
-#    Date:          04/15/98
-#
-#    Contact:       Shawn.Steele@microsoft.com
-#
-#    General notes: none
-#
-#    Format: Three tab-separated columns
-#        Column #1 is the cp1254 code (in hex)
-#        Column #2 is the Unicode (in hex as 0xXXXX)
-#        Column #3 is the Unicode name (follows a comment sign, '#')
-#
-#    The entries are in cp1254 order
-#
 0x00	0x0000	#NULL
 0x01	0x0001	#START OF HEADING
 0x02	0x0002	#START OF TEXT

Data/Encoding/CP1255.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.CP1255 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "CP1255" "CP1255.TXT" )

Data/Encoding/CP1255.mapping

@@ -1,21 +1,3 @@
-#
-#    Name:     cp1255 to Unicode table
-#    Unicode version: 2.0
-#    Table version: 2.01
-#    Table format:  Format A
-#    Date:          1/7/2000
-#
-#    Contact:       Shawn.Steele@microsoft.com
-#
-#    General notes: none
-#
-#    Format: Three tab-separated columns
-#        Column #1 is the cp1255 code (in hex)
-#        Column #2 is the Unicode (in hex as 0xXXXX)
-#        Column #3 is the Unicode name (follows a comment sign, '#')
-#
-#    The entries are in cp1255 order
-#
 0x00	0x0000	#NULL
 0x01	0x0001	#START OF HEADING
 0x02	0x0002	#START OF TEXT

Data/Encoding/CP1256.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.CP1256 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "CP1256" "CP1256.TXT" )

Data/Encoding/CP1256.mapping

@@ -1,21 +1,3 @@
-#
-#    Name:     cp1256 to Unicode table
-#    Unicode version: 2.1
-#    Table version: 2.01
-#    Table format:  Format A
-#    Date:          01/5/99
-#
-#    Contact:       Shawn.Steele@microsoft.com
-#
-#    General notes: none
-#
-#    Format: Three tab-separated columns
-#        Column #1 is the cp1256 code (in hex)
-#        Column #2 is the Unicode (in hex as 0xXXXX)
-#        Column #3 is the Unicode name (follows a comment sign, '#')
-#
-#    The entries are in cp1256 order
-#
 0x00	0x0000	#NULL
 0x01	0x0001	#START OF HEADING
 0x02	0x0002	#START OF TEXT

Data/Encoding/CP1257.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.CP1257 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "CP1257" "CP1257.TXT" )

Data/Encoding/CP1257.mapping

@@ -1,21 +1,3 @@
-#
-#    Name:     cp1257 to Unicode table
-#    Unicode version: 2.0
-#    Table version: 2.01
-#    Table format:  Format A
-#    Date:          04/15/98
-#
-#    Contact:       Shawn.Steele@microsoft.com
-#
-#    General notes: none
-#
-#    Format: Three tab-separated columns
-#        Column #1 is the cp1257 code (in hex)
-#        Column #2 is the Unicode (in hex as 0xXXXX)
-#        Column #3 is the Unicode name (follows a comment sign, '#')
-#
-#    The entries are in cp1257 order
-#
 0x00	0x0000	#NULL
 0x01	0x0001	#START OF HEADING
 0x02	0x0002	#START OF TEXT

Data/Encoding/CP1258.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.CP1258 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "CP1258" "CP1258.TXT" )

Data/Encoding/CP1258.mapping

@@ -1,21 +1,3 @@
-#
-#    Name:     cp1258 to Unicode table
-#    Unicode version: 2.0
-#    Table version: 2.01
-#    Table format:  Format A
-#    Date:          04/15/98
-#
-#    Contact:       Shawn.Steele@microsoft.com
-#
-#    General notes: none
-#
-#    Format: Three tab-separated columns
-#        Column #1 is the cp1258 code (in hex)
-#        Column #2 is the Unicode (in hex as 0xXXXX)
-#        Column #3 is the Unicode name (follows a comment sign, '#')
-#
-#    The entries are in cp1258 order
-#
 0x00	0x0000	#NULL
 0x01	0x0001	#START OF HEADING
 0x02	0x0002	#START OF TEXT

Data/Encoding/CP437.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x00c7	#LATIN CAPITAL LETTER C WITH CEDILLA
+0x81	0x00fc	#LATIN SMALL LETTER U WITH DIAERESIS
+0x82	0x00e9	#LATIN SMALL LETTER E WITH ACUTE
+0x83	0x00e2	#LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x84	0x00e4	#LATIN SMALL LETTER A WITH DIAERESIS
+0x85	0x00e0	#LATIN SMALL LETTER A WITH GRAVE
+0x86	0x00e5	#LATIN SMALL LETTER A WITH RING ABOVE
+0x87	0x00e7	#LATIN SMALL LETTER C WITH CEDILLA
+0x88	0x00ea	#LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x89	0x00eb	#LATIN SMALL LETTER E WITH DIAERESIS
+0x8a	0x00e8	#LATIN SMALL LETTER E WITH GRAVE
+0x8b	0x00ef	#LATIN SMALL LETTER I WITH DIAERESIS
+0x8c	0x00ee	#LATIN SMALL LETTER I WITH CIRCUMFLEX
+0x8d	0x00ec	#LATIN SMALL LETTER I WITH GRAVE
+0x8e	0x00c4	#LATIN CAPITAL LETTER A WITH DIAERESIS
+0x8f	0x00c5	#LATIN CAPITAL LETTER A WITH RING ABOVE
+0x90	0x00c9	#LATIN CAPITAL LETTER E WITH ACUTE
+0x91	0x00e6	#LATIN SMALL LIGATURE AE
+0x92	0x00c6	#LATIN CAPITAL LIGATURE AE
+0x93	0x00f4	#LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x94	0x00f6	#LATIN SMALL LETTER O WITH DIAERESIS
+0x95	0x00f2	#LATIN SMALL LETTER O WITH GRAVE
+0x96	0x00fb	#LATIN SMALL LETTER U WITH CIRCUMFLEX
+0x97	0x00f9	#LATIN SMALL LETTER U WITH GRAVE
+0x98	0x00ff	#LATIN SMALL LETTER Y WITH DIAERESIS
+0x99	0x00d6	#LATIN CAPITAL LETTER O WITH DIAERESIS
+0x9a	0x00dc	#LATIN CAPITAL LETTER U WITH DIAERESIS
+0x9b	0x00a2	#CENT SIGN
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x00a5	#YEN SIGN
+0x9e	0x20a7	#PESETA SIGN
+0x9f	0x0192	#LATIN SMALL LETTER F WITH HOOK
+0xa0	0x00e1	#LATIN SMALL LETTER A WITH ACUTE
+0xa1	0x00ed	#LATIN SMALL LETTER I WITH ACUTE
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x00fa	#LATIN SMALL LETTER U WITH ACUTE
+0xa4	0x00f1	#LATIN SMALL LETTER N WITH TILDE
+0xa5	0x00d1	#LATIN CAPITAL LETTER N WITH TILDE
+0xa6	0x00aa	#FEMININE ORDINAL INDICATOR
+0xa7	0x00ba	#MASCULINE ORDINAL INDICATOR
+0xa8	0x00bf	#INVERTED QUESTION MARK
+0xa9	0x2310	#REVERSED NOT SIGN
+0xaa	0x00ac	#NOT SIGN
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x00bc	#VULGAR FRACTION ONE QUARTER
+0xad	0x00a1	#INVERTED EXCLAMATION MARK
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x2561	#BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xb6	0x2562	#BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+0xb7	0x2556	#BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+0xb8	0x2555	#BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x255c	#BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+0xbe	0x255b	#BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x255e	#BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xc7	0x255f	#BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x2567	#BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xd0	0x2568	#BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xd1	0x2564	#BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+0xd2	0x2565	#BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+0xd3	0x2559	#BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xd4	0x2558	#BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xd5	0x2552	#BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xd6	0x2553	#BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+0xd7	0x256b	#BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+0xd8	0x256a	#BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x258c	#LEFT HALF BLOCK
+0xde	0x2590	#RIGHT HALF BLOCK
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x03b1	#GREEK SMALL LETTER ALPHA
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S
+0xe2	0x0393	#GREEK CAPITAL LETTER GAMMA
+0xe3	0x03c0	#GREEK SMALL LETTER PI
+0xe4	0x03a3	#GREEK CAPITAL LETTER SIGMA
+0xe5	0x03c3	#GREEK SMALL LETTER SIGMA
+0xe6	0x00b5	#MICRO SIGN
+0xe7	0x03c4	#GREEK SMALL LETTER TAU
+0xe8	0x03a6	#GREEK CAPITAL LETTER PHI
+0xe9	0x0398	#GREEK CAPITAL LETTER THETA
+0xea	0x03a9	#GREEK CAPITAL LETTER OMEGA
+0xeb	0x03b4	#GREEK SMALL LETTER DELTA
+0xec	0x221e	#INFINITY
+0xed	0x03c6	#GREEK SMALL LETTER PHI
+0xee	0x03b5	#GREEK SMALL LETTER EPSILON
+0xef	0x2229	#INTERSECTION
+0xf0	0x2261	#IDENTICAL TO
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x2265	#GREATER-THAN OR EQUAL TO
+0xf3	0x2264	#LESS-THAN OR EQUAL TO
+0xf4	0x2320	#TOP HALF INTEGRAL
+0xf5	0x2321	#BOTTOM HALF INTEGRAL
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x2248	#ALMOST EQUAL TO
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x2219	#BULLET OPERATOR
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x221a	#SQUARE ROOT
+0xfc	0x207f	#SUPERSCRIPT LATIN SMALL LETTER N
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP737.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x0391	#GREEK CAPITAL LETTER ALPHA
+0x81	0x0392	#GREEK CAPITAL LETTER BETA
+0x82	0x0393	#GREEK CAPITAL LETTER GAMMA
+0x83	0x0394	#GREEK CAPITAL LETTER DELTA
+0x84	0x0395	#GREEK CAPITAL LETTER EPSILON
+0x85	0x0396	#GREEK CAPITAL LETTER ZETA
+0x86	0x0397	#GREEK CAPITAL LETTER ETA
+0x87	0x0398	#GREEK CAPITAL LETTER THETA
+0x88	0x0399	#GREEK CAPITAL LETTER IOTA
+0x89	0x039a	#GREEK CAPITAL LETTER KAPPA
+0x8a	0x039b	#GREEK CAPITAL LETTER LAMDA
+0x8b	0x039c	#GREEK CAPITAL LETTER MU
+0x8c	0x039d	#GREEK CAPITAL LETTER NU
+0x8d	0x039e	#GREEK CAPITAL LETTER XI
+0x8e	0x039f	#GREEK CAPITAL LETTER OMICRON
+0x8f	0x03a0	#GREEK CAPITAL LETTER PI
+0x90	0x03a1	#GREEK CAPITAL LETTER RHO
+0x91	0x03a3	#GREEK CAPITAL LETTER SIGMA
+0x92	0x03a4	#GREEK CAPITAL LETTER TAU
+0x93	0x03a5	#GREEK CAPITAL LETTER UPSILON
+0x94	0x03a6	#GREEK CAPITAL LETTER PHI
+0x95	0x03a7	#GREEK CAPITAL LETTER CHI
+0x96	0x03a8	#GREEK CAPITAL LETTER PSI
+0x97	0x03a9	#GREEK CAPITAL LETTER OMEGA
+0x98	0x03b1	#GREEK SMALL LETTER ALPHA
+0x99	0x03b2	#GREEK SMALL LETTER BETA
+0x9a	0x03b3	#GREEK SMALL LETTER GAMMA
+0x9b	0x03b4	#GREEK SMALL LETTER DELTA
+0x9c	0x03b5	#GREEK SMALL LETTER EPSILON
+0x9d	0x03b6	#GREEK SMALL LETTER ZETA
+0x9e	0x03b7	#GREEK SMALL LETTER ETA
+0x9f	0x03b8	#GREEK SMALL LETTER THETA
+0xa0	0x03b9	#GREEK SMALL LETTER IOTA
+0xa1	0x03ba	#GREEK SMALL LETTER KAPPA
+0xa2	0x03bb	#GREEK SMALL LETTER LAMDA
+0xa3	0x03bc	#GREEK SMALL LETTER MU
+0xa4	0x03bd	#GREEK SMALL LETTER NU
+0xa5	0x03be	#GREEK SMALL LETTER XI
+0xa6	0x03bf	#GREEK SMALL LETTER OMICRON
+0xa7	0x03c0	#GREEK SMALL LETTER PI
+0xa8	0x03c1	#GREEK SMALL LETTER RHO
+0xa9	0x03c3	#GREEK SMALL LETTER SIGMA
+0xaa	0x03c2	#GREEK SMALL LETTER FINAL SIGMA
+0xab	0x03c4	#GREEK SMALL LETTER TAU
+0xac	0x03c5	#GREEK SMALL LETTER UPSILON
+0xad	0x03c6	#GREEK SMALL LETTER PHI
+0xae	0x03c7	#GREEK SMALL LETTER CHI
+0xaf	0x03c8	#GREEK SMALL LETTER PSI
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x2561	#BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xb6	0x2562	#BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+0xb7	0x2556	#BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+0xb8	0x2555	#BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x255c	#BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+0xbe	0x255b	#BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x255e	#BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xc7	0x255f	#BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x2567	#BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xd0	0x2568	#BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xd1	0x2564	#BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+0xd2	0x2565	#BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+0xd3	0x2559	#BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xd4	0x2558	#BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xd5	0x2552	#BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xd6	0x2553	#BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+0xd7	0x256b	#BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+0xd8	0x256a	#BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x258c	#LEFT HALF BLOCK
+0xde	0x2590	#RIGHT HALF BLOCK
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x03c9	#GREEK SMALL LETTER OMEGA
+0xe1	0x03ac	#GREEK SMALL LETTER ALPHA WITH TONOS
+0xe2	0x03ad	#GREEK SMALL LETTER EPSILON WITH TONOS
+0xe3	0x03ae	#GREEK SMALL LETTER ETA WITH TONOS
+0xe4	0x03ca	#GREEK SMALL LETTER IOTA WITH DIALYTIKA
+0xe5	0x03af	#GREEK SMALL LETTER IOTA WITH TONOS
+0xe6	0x03cc	#GREEK SMALL LETTER OMICRON WITH TONOS
+0xe7	0x03cd	#GREEK SMALL LETTER UPSILON WITH TONOS
+0xe8	0x03cb	#GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+0xe9	0x03ce	#GREEK SMALL LETTER OMEGA WITH TONOS
+0xea	0x0386	#GREEK CAPITAL LETTER ALPHA WITH TONOS
+0xeb	0x0388	#GREEK CAPITAL LETTER EPSILON WITH TONOS
+0xec	0x0389	#GREEK CAPITAL LETTER ETA WITH TONOS
+0xed	0x038a	#GREEK CAPITAL LETTER IOTA WITH TONOS
+0xee	0x038c	#GREEK CAPITAL LETTER OMICRON WITH TONOS
+0xef	0x038e	#GREEK CAPITAL LETTER UPSILON WITH TONOS
+0xf0	0x038f	#GREEK CAPITAL LETTER OMEGA WITH TONOS
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x2265	#GREATER-THAN OR EQUAL TO
+0xf3	0x2264	#LESS-THAN OR EQUAL TO
+0xf4	0x03aa	#GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+0xf5	0x03ab	#GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x2248	#ALMOST EQUAL TO
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x2219	#BULLET OPERATOR
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x221a	#SQUARE ROOT
+0xfc	0x207f	#SUPERSCRIPT LATIN SMALL LETTER N
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP775.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x0106	#LATIN CAPITAL LETTER C WITH ACUTE
+0x81	0x00fc	#LATIN SMALL LETTER U WITH DIAERESIS
+0x82	0x00e9	#LATIN SMALL LETTER E WITH ACUTE
+0x83	0x0101	#LATIN SMALL LETTER A WITH MACRON
+0x84	0x00e4	#LATIN SMALL LETTER A WITH DIAERESIS
+0x85	0x0123	#LATIN SMALL LETTER G WITH CEDILLA
+0x86	0x00e5	#LATIN SMALL LETTER A WITH RING ABOVE
+0x87	0x0107	#LATIN SMALL LETTER C WITH ACUTE
+0x88	0x0142	#LATIN SMALL LETTER L WITH STROKE
+0x89	0x0113	#LATIN SMALL LETTER E WITH MACRON
+0x8a	0x0156	#LATIN CAPITAL LETTER R WITH CEDILLA
+0x8b	0x0157	#LATIN SMALL LETTER R WITH CEDILLA
+0x8c	0x012b	#LATIN SMALL LETTER I WITH MACRON
+0x8d	0x0179	#LATIN CAPITAL LETTER Z WITH ACUTE
+0x8e	0x00c4	#LATIN CAPITAL LETTER A WITH DIAERESIS
+0x8f	0x00c5	#LATIN CAPITAL LETTER A WITH RING ABOVE
+0x90	0x00c9	#LATIN CAPITAL LETTER E WITH ACUTE
+0x91	0x00e6	#LATIN SMALL LIGATURE AE
+0x92	0x00c6	#LATIN CAPITAL LIGATURE AE
+0x93	0x014d	#LATIN SMALL LETTER O WITH MACRON
+0x94	0x00f6	#LATIN SMALL LETTER O WITH DIAERESIS
+0x95	0x0122	#LATIN CAPITAL LETTER G WITH CEDILLA
+0x96	0x00a2	#CENT SIGN
+0x97	0x015a	#LATIN CAPITAL LETTER S WITH ACUTE
+0x98	0x015b	#LATIN SMALL LETTER S WITH ACUTE
+0x99	0x00d6	#LATIN CAPITAL LETTER O WITH DIAERESIS
+0x9a	0x00dc	#LATIN CAPITAL LETTER U WITH DIAERESIS
+0x9b	0x00f8	#LATIN SMALL LETTER O WITH STROKE
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x00d8	#LATIN CAPITAL LETTER O WITH STROKE
+0x9e	0x00d7	#MULTIPLICATION SIGN
+0x9f	0x00a4	#CURRENCY SIGN
+0xa0	0x0100	#LATIN CAPITAL LETTER A WITH MACRON
+0xa1	0x012a	#LATIN CAPITAL LETTER I WITH MACRON
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x017b	#LATIN CAPITAL LETTER Z WITH DOT ABOVE
+0xa4	0x017c	#LATIN SMALL LETTER Z WITH DOT ABOVE
+0xa5	0x017a	#LATIN SMALL LETTER Z WITH ACUTE
+0xa6	0x201d	#RIGHT DOUBLE QUOTATION MARK
+0xa7	0x00a6	#BROKEN BAR
+0xa8	0x00a9	#COPYRIGHT SIGN
+0xa9	0x00ae	#REGISTERED SIGN
+0xaa	0x00ac	#NOT SIGN
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x00bc	#VULGAR FRACTION ONE QUARTER
+0xad	0x0141	#LATIN CAPITAL LETTER L WITH STROKE
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x0104	#LATIN CAPITAL LETTER A WITH OGONEK
+0xb6	0x010c	#LATIN CAPITAL LETTER C WITH CARON
+0xb7	0x0118	#LATIN CAPITAL LETTER E WITH OGONEK
+0xb8	0x0116	#LATIN CAPITAL LETTER E WITH DOT ABOVE
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x012e	#LATIN CAPITAL LETTER I WITH OGONEK
+0xbe	0x0160	#LATIN CAPITAL LETTER S WITH CARON
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x0172	#LATIN CAPITAL LETTER U WITH OGONEK
+0xc7	0x016a	#LATIN CAPITAL LETTER U WITH MACRON
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x017d	#LATIN CAPITAL LETTER Z WITH CARON
+0xd0	0x0105	#LATIN SMALL LETTER A WITH OGONEK
+0xd1	0x010d	#LATIN SMALL LETTER C WITH CARON
+0xd2	0x0119	#LATIN SMALL LETTER E WITH OGONEK
+0xd3	0x0117	#LATIN SMALL LETTER E WITH DOT ABOVE
+0xd4	0x012f	#LATIN SMALL LETTER I WITH OGONEK
+0xd5	0x0161	#LATIN SMALL LETTER S WITH CARON
+0xd6	0x0173	#LATIN SMALL LETTER U WITH OGONEK
+0xd7	0x016b	#LATIN SMALL LETTER U WITH MACRON
+0xd8	0x017e	#LATIN SMALL LETTER Z WITH CARON
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x258c	#LEFT HALF BLOCK
+0xde	0x2590	#RIGHT HALF BLOCK
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x00d3	#LATIN CAPITAL LETTER O WITH ACUTE
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S (GERMAN)
+0xe2	0x014c	#LATIN CAPITAL LETTER O WITH MACRON
+0xe3	0x0143	#LATIN CAPITAL LETTER N WITH ACUTE
+0xe4	0x00f5	#LATIN SMALL LETTER O WITH TILDE
+0xe5	0x00d5	#LATIN CAPITAL LETTER O WITH TILDE
+0xe6	0x00b5	#MICRO SIGN
+0xe7	0x0144	#LATIN SMALL LETTER N WITH ACUTE
+0xe8	0x0136	#LATIN CAPITAL LETTER K WITH CEDILLA
+0xe9	0x0137	#LATIN SMALL LETTER K WITH CEDILLA
+0xea	0x013b	#LATIN CAPITAL LETTER L WITH CEDILLA
+0xeb	0x013c	#LATIN SMALL LETTER L WITH CEDILLA
+0xec	0x0146	#LATIN SMALL LETTER N WITH CEDILLA
+0xed	0x0112	#LATIN CAPITAL LETTER E WITH MACRON
+0xee	0x0145	#LATIN CAPITAL LETTER N WITH CEDILLA
+0xef	0x2019	#RIGHT SINGLE QUOTATION MARK
+0xf0	0x00ad	#SOFT HYPHEN
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x201c	#LEFT DOUBLE QUOTATION MARK
+0xf3	0x00be	#VULGAR FRACTION THREE QUARTERS
+0xf4	0x00b6	#PILCROW SIGN
+0xf5	0x00a7	#SECTION SIGN
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x201e	#DOUBLE LOW-9 QUOTATION MARK
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x2219	#BULLET OPERATOR
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x00b9	#SUPERSCRIPT ONE
+0xfc	0x00b3	#SUPERSCRIPT THREE
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP850.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x00c7	#LATIN CAPITAL LETTER C WITH CEDILLA
+0x81	0x00fc	#LATIN SMALL LETTER U WITH DIAERESIS
+0x82	0x00e9	#LATIN SMALL LETTER E WITH ACUTE
+0x83	0x00e2	#LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x84	0x00e4	#LATIN SMALL LETTER A WITH DIAERESIS
+0x85	0x00e0	#LATIN SMALL LETTER A WITH GRAVE
+0x86	0x00e5	#LATIN SMALL LETTER A WITH RING ABOVE
+0x87	0x00e7	#LATIN SMALL LETTER C WITH CEDILLA
+0x88	0x00ea	#LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x89	0x00eb	#LATIN SMALL LETTER E WITH DIAERESIS
+0x8a	0x00e8	#LATIN SMALL LETTER E WITH GRAVE
+0x8b	0x00ef	#LATIN SMALL LETTER I WITH DIAERESIS
+0x8c	0x00ee	#LATIN SMALL LETTER I WITH CIRCUMFLEX
+0x8d	0x00ec	#LATIN SMALL LETTER I WITH GRAVE
+0x8e	0x00c4	#LATIN CAPITAL LETTER A WITH DIAERESIS
+0x8f	0x00c5	#LATIN CAPITAL LETTER A WITH RING ABOVE
+0x90	0x00c9	#LATIN CAPITAL LETTER E WITH ACUTE
+0x91	0x00e6	#LATIN SMALL LIGATURE AE
+0x92	0x00c6	#LATIN CAPITAL LIGATURE AE
+0x93	0x00f4	#LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x94	0x00f6	#LATIN SMALL LETTER O WITH DIAERESIS
+0x95	0x00f2	#LATIN SMALL LETTER O WITH GRAVE
+0x96	0x00fb	#LATIN SMALL LETTER U WITH CIRCUMFLEX
+0x97	0x00f9	#LATIN SMALL LETTER U WITH GRAVE
+0x98	0x00ff	#LATIN SMALL LETTER Y WITH DIAERESIS
+0x99	0x00d6	#LATIN CAPITAL LETTER O WITH DIAERESIS
+0x9a	0x00dc	#LATIN CAPITAL LETTER U WITH DIAERESIS
+0x9b	0x00f8	#LATIN SMALL LETTER O WITH STROKE
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x00d8	#LATIN CAPITAL LETTER O WITH STROKE
+0x9e	0x00d7	#MULTIPLICATION SIGN
+0x9f	0x0192	#LATIN SMALL LETTER F WITH HOOK
+0xa0	0x00e1	#LATIN SMALL LETTER A WITH ACUTE
+0xa1	0x00ed	#LATIN SMALL LETTER I WITH ACUTE
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x00fa	#LATIN SMALL LETTER U WITH ACUTE
+0xa4	0x00f1	#LATIN SMALL LETTER N WITH TILDE
+0xa5	0x00d1	#LATIN CAPITAL LETTER N WITH TILDE
+0xa6	0x00aa	#FEMININE ORDINAL INDICATOR
+0xa7	0x00ba	#MASCULINE ORDINAL INDICATOR
+0xa8	0x00bf	#INVERTED QUESTION MARK
+0xa9	0x00ae	#REGISTERED SIGN
+0xaa	0x00ac	#NOT SIGN
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x00bc	#VULGAR FRACTION ONE QUARTER
+0xad	0x00a1	#INVERTED EXCLAMATION MARK
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x00c1	#LATIN CAPITAL LETTER A WITH ACUTE
+0xb6	0x00c2	#LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+0xb7	0x00c0	#LATIN CAPITAL LETTER A WITH GRAVE
+0xb8	0x00a9	#COPYRIGHT SIGN
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x00a2	#CENT SIGN
+0xbe	0x00a5	#YEN SIGN
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x00e3	#LATIN SMALL LETTER A WITH TILDE
+0xc7	0x00c3	#LATIN CAPITAL LETTER A WITH TILDE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x00a4	#CURRENCY SIGN
+0xd0	0x00f0	#LATIN SMALL LETTER ETH
+0xd1	0x00d0	#LATIN CAPITAL LETTER ETH
+0xd2	0x00ca	#LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+0xd3	0x00cb	#LATIN CAPITAL LETTER E WITH DIAERESIS
+0xd4	0x00c8	#LATIN CAPITAL LETTER E WITH GRAVE
+0xd5	0x0131	#LATIN SMALL LETTER DOTLESS I
+0xd6	0x00cd	#LATIN CAPITAL LETTER I WITH ACUTE
+0xd7	0x00ce	#LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+0xd8	0x00cf	#LATIN CAPITAL LETTER I WITH DIAERESIS
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x00a6	#BROKEN BAR
+0xde	0x00cc	#LATIN CAPITAL LETTER I WITH GRAVE
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x00d3	#LATIN CAPITAL LETTER O WITH ACUTE
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S
+0xe2	0x00d4	#LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+0xe3	0x00d2	#LATIN CAPITAL LETTER O WITH GRAVE
+0xe4	0x00f5	#LATIN SMALL LETTER O WITH TILDE
+0xe5	0x00d5	#LATIN CAPITAL LETTER O WITH TILDE
+0xe6	0x00b5	#MICRO SIGN
+0xe7	0x00fe	#LATIN SMALL LETTER THORN
+0xe8	0x00de	#LATIN CAPITAL LETTER THORN
+0xe9	0x00da	#LATIN CAPITAL LETTER U WITH ACUTE
+0xea	0x00db	#LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+0xeb	0x00d9	#LATIN CAPITAL LETTER U WITH GRAVE
+0xec	0x00fd	#LATIN SMALL LETTER Y WITH ACUTE
+0xed	0x00dd	#LATIN CAPITAL LETTER Y WITH ACUTE
+0xee	0x00af	#MACRON
+0xef	0x00b4	#ACUTE ACCENT
+0xf0	0x00ad	#SOFT HYPHEN
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x2017	#DOUBLE LOW LINE
+0xf3	0x00be	#VULGAR FRACTION THREE QUARTERS
+0xf4	0x00b6	#PILCROW SIGN
+0xf5	0x00a7	#SECTION SIGN
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x00b8	#CEDILLA
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x00a8	#DIAERESIS
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x00b9	#SUPERSCRIPT ONE
+0xfc	0x00b3	#SUPERSCRIPT THREE
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP852.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x00c7	#LATIN CAPITAL LETTER C WITH CEDILLA
+0x81	0x00fc	#LATIN SMALL LETTER U WITH DIAERESIS
+0x82	0x00e9	#LATIN SMALL LETTER E WITH ACUTE
+0x83	0x00e2	#LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x84	0x00e4	#LATIN SMALL LETTER A WITH DIAERESIS
+0x85	0x016f	#LATIN SMALL LETTER U WITH RING ABOVE
+0x86	0x0107	#LATIN SMALL LETTER C WITH ACUTE
+0x87	0x00e7	#LATIN SMALL LETTER C WITH CEDILLA
+0x88	0x0142	#LATIN SMALL LETTER L WITH STROKE
+0x89	0x00eb	#LATIN SMALL LETTER E WITH DIAERESIS
+0x8a	0x0150	#LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
+0x8b	0x0151	#LATIN SMALL LETTER O WITH DOUBLE ACUTE
+0x8c	0x00ee	#LATIN SMALL LETTER I WITH CIRCUMFLEX
+0x8d	0x0179	#LATIN CAPITAL LETTER Z WITH ACUTE
+0x8e	0x00c4	#LATIN CAPITAL LETTER A WITH DIAERESIS
+0x8f	0x0106	#LATIN CAPITAL LETTER C WITH ACUTE
+0x90	0x00c9	#LATIN CAPITAL LETTER E WITH ACUTE
+0x91	0x0139	#LATIN CAPITAL LETTER L WITH ACUTE
+0x92	0x013a	#LATIN SMALL LETTER L WITH ACUTE
+0x93	0x00f4	#LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x94	0x00f6	#LATIN SMALL LETTER O WITH DIAERESIS
+0x95	0x013d	#LATIN CAPITAL LETTER L WITH CARON
+0x96	0x013e	#LATIN SMALL LETTER L WITH CARON
+0x97	0x015a	#LATIN CAPITAL LETTER S WITH ACUTE
+0x98	0x015b	#LATIN SMALL LETTER S WITH ACUTE
+0x99	0x00d6	#LATIN CAPITAL LETTER O WITH DIAERESIS
+0x9a	0x00dc	#LATIN CAPITAL LETTER U WITH DIAERESIS
+0x9b	0x0164	#LATIN CAPITAL LETTER T WITH CARON
+0x9c	0x0165	#LATIN SMALL LETTER T WITH CARON
+0x9d	0x0141	#LATIN CAPITAL LETTER L WITH STROKE
+0x9e	0x00d7	#MULTIPLICATION SIGN
+0x9f	0x010d	#LATIN SMALL LETTER C WITH CARON
+0xa0	0x00e1	#LATIN SMALL LETTER A WITH ACUTE
+0xa1	0x00ed	#LATIN SMALL LETTER I WITH ACUTE
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x00fa	#LATIN SMALL LETTER U WITH ACUTE
+0xa4	0x0104	#LATIN CAPITAL LETTER A WITH OGONEK
+0xa5	0x0105	#LATIN SMALL LETTER A WITH OGONEK
+0xa6	0x017d	#LATIN CAPITAL LETTER Z WITH CARON
+0xa7	0x017e	#LATIN SMALL LETTER Z WITH CARON
+0xa8	0x0118	#LATIN CAPITAL LETTER E WITH OGONEK
+0xa9	0x0119	#LATIN SMALL LETTER E WITH OGONEK
+0xaa	0x00ac	#NOT SIGN
+0xab	0x017a	#LATIN SMALL LETTER Z WITH ACUTE
+0xac	0x010c	#LATIN CAPITAL LETTER C WITH CARON
+0xad	0x015f	#LATIN SMALL LETTER S WITH CEDILLA
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x00c1	#LATIN CAPITAL LETTER A WITH ACUTE
+0xb6	0x00c2	#LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+0xb7	0x011a	#LATIN CAPITAL LETTER E WITH CARON
+0xb8	0x015e	#LATIN CAPITAL LETTER S WITH CEDILLA
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x017b	#LATIN CAPITAL LETTER Z WITH DOT ABOVE
+0xbe	0x017c	#LATIN SMALL LETTER Z WITH DOT ABOVE
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x0102	#LATIN CAPITAL LETTER A WITH BREVE
+0xc7	0x0103	#LATIN SMALL LETTER A WITH BREVE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x00a4	#CURRENCY SIGN
+0xd0	0x0111	#LATIN SMALL LETTER D WITH STROKE
+0xd1	0x0110	#LATIN CAPITAL LETTER D WITH STROKE
+0xd2	0x010e	#LATIN CAPITAL LETTER D WITH CARON
+0xd3	0x00cb	#LATIN CAPITAL LETTER E WITH DIAERESIS
+0xd4	0x010f	#LATIN SMALL LETTER D WITH CARON
+0xd5	0x0147	#LATIN CAPITAL LETTER N WITH CARON
+0xd6	0x00cd	#LATIN CAPITAL LETTER I WITH ACUTE
+0xd7	0x00ce	#LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+0xd8	0x011b	#LATIN SMALL LETTER E WITH CARON
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x0162	#LATIN CAPITAL LETTER T WITH CEDILLA
+0xde	0x016e	#LATIN CAPITAL LETTER U WITH RING ABOVE
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x00d3	#LATIN CAPITAL LETTER O WITH ACUTE
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S
+0xe2	0x00d4	#LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+0xe3	0x0143	#LATIN CAPITAL LETTER N WITH ACUTE
+0xe4	0x0144	#LATIN SMALL LETTER N WITH ACUTE
+0xe5	0x0148	#LATIN SMALL LETTER N WITH CARON
+0xe6	0x0160	#LATIN CAPITAL LETTER S WITH CARON
+0xe7	0x0161	#LATIN SMALL LETTER S WITH CARON
+0xe8	0x0154	#LATIN CAPITAL LETTER R WITH ACUTE
+0xe9	0x00da	#LATIN CAPITAL LETTER U WITH ACUTE
+0xea	0x0155	#LATIN SMALL LETTER R WITH ACUTE
+0xeb	0x0170	#LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
+0xec	0x00fd	#LATIN SMALL LETTER Y WITH ACUTE
+0xed	0x00dd	#LATIN CAPITAL LETTER Y WITH ACUTE
+0xee	0x0163	#LATIN SMALL LETTER T WITH CEDILLA
+0xef	0x00b4	#ACUTE ACCENT
+0xf0	0x00ad	#SOFT HYPHEN
+0xf1	0x02dd	#DOUBLE ACUTE ACCENT
+0xf2	0x02db	#OGONEK
+0xf3	0x02c7	#CARON
+0xf4	0x02d8	#BREVE
+0xf5	0x00a7	#SECTION SIGN
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x00b8	#CEDILLA
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x00a8	#DIAERESIS
+0xfa	0x02d9	#DOT ABOVE
+0xfb	0x0171	#LATIN SMALL LETTER U WITH DOUBLE ACUTE
+0xfc	0x0158	#LATIN CAPITAL LETTER R WITH CARON
+0xfd	0x0159	#LATIN SMALL LETTER R WITH CARON
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP855.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x0452	#CYRILLIC SMALL LETTER DJE
+0x81	0x0402	#CYRILLIC CAPITAL LETTER DJE
+0x82	0x0453	#CYRILLIC SMALL LETTER GJE
+0x83	0x0403	#CYRILLIC CAPITAL LETTER GJE
+0x84	0x0451	#CYRILLIC SMALL LETTER IO
+0x85	0x0401	#CYRILLIC CAPITAL LETTER IO
+0x86	0x0454	#CYRILLIC SMALL LETTER UKRAINIAN IE
+0x87	0x0404	#CYRILLIC CAPITAL LETTER UKRAINIAN IE
+0x88	0x0455	#CYRILLIC SMALL LETTER DZE
+0x89	0x0405	#CYRILLIC CAPITAL LETTER DZE
+0x8a	0x0456	#CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+0x8b	0x0406	#CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+0x8c	0x0457	#CYRILLIC SMALL LETTER YI
+0x8d	0x0407	#CYRILLIC CAPITAL LETTER YI
+0x8e	0x0458	#CYRILLIC SMALL LETTER JE
+0x8f	0x0408	#CYRILLIC CAPITAL LETTER JE
+0x90	0x0459	#CYRILLIC SMALL LETTER LJE
+0x91	0x0409	#CYRILLIC CAPITAL LETTER LJE
+0x92	0x045a	#CYRILLIC SMALL LETTER NJE
+0x93	0x040a	#CYRILLIC CAPITAL LETTER NJE
+0x94	0x045b	#CYRILLIC SMALL LETTER TSHE
+0x95	0x040b	#CYRILLIC CAPITAL LETTER TSHE
+0x96	0x045c	#CYRILLIC SMALL LETTER KJE
+0x97	0x040c	#CYRILLIC CAPITAL LETTER KJE
+0x98	0x045e	#CYRILLIC SMALL LETTER SHORT U
+0x99	0x040e	#CYRILLIC CAPITAL LETTER SHORT U
+0x9a	0x045f	#CYRILLIC SMALL LETTER DZHE
+0x9b	0x040f	#CYRILLIC CAPITAL LETTER DZHE
+0x9c	0x044e	#CYRILLIC SMALL LETTER YU
+0x9d	0x042e	#CYRILLIC CAPITAL LETTER YU
+0x9e	0x044a	#CYRILLIC SMALL LETTER HARD SIGN
+0x9f	0x042a	#CYRILLIC CAPITAL LETTER HARD SIGN
+0xa0	0x0430	#CYRILLIC SMALL LETTER A
+0xa1	0x0410	#CYRILLIC CAPITAL LETTER A
+0xa2	0x0431	#CYRILLIC SMALL LETTER BE
+0xa3	0x0411	#CYRILLIC CAPITAL LETTER BE
+0xa4	0x0446	#CYRILLIC SMALL LETTER TSE
+0xa5	0x0426	#CYRILLIC CAPITAL LETTER TSE
+0xa6	0x0434	#CYRILLIC SMALL LETTER DE
+0xa7	0x0414	#CYRILLIC CAPITAL LETTER DE
+0xa8	0x0435	#CYRILLIC SMALL LETTER IE
+0xa9	0x0415	#CYRILLIC CAPITAL LETTER IE
+0xaa	0x0444	#CYRILLIC SMALL LETTER EF
+0xab	0x0424	#CYRILLIC CAPITAL LETTER EF
+0xac	0x0433	#CYRILLIC SMALL LETTER GHE
+0xad	0x0413	#CYRILLIC CAPITAL LETTER GHE
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x0445	#CYRILLIC SMALL LETTER HA
+0xb6	0x0425	#CYRILLIC CAPITAL LETTER HA
+0xb7	0x0438	#CYRILLIC SMALL LETTER I
+0xb8	0x0418	#CYRILLIC CAPITAL LETTER I
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x0439	#CYRILLIC SMALL LETTER SHORT I
+0xbe	0x0419	#CYRILLIC CAPITAL LETTER SHORT I
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x043a	#CYRILLIC SMALL LETTER KA
+0xc7	0x041a	#CYRILLIC CAPITAL LETTER KA
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x00a4	#CURRENCY SIGN
+0xd0	0x043b	#CYRILLIC SMALL LETTER EL
+0xd1	0x041b	#CYRILLIC CAPITAL LETTER EL
+0xd2	0x043c	#CYRILLIC SMALL LETTER EM
+0xd3	0x041c	#CYRILLIC CAPITAL LETTER EM
+0xd4	0x043d	#CYRILLIC SMALL LETTER EN
+0xd5	0x041d	#CYRILLIC CAPITAL LETTER EN
+0xd6	0x043e	#CYRILLIC SMALL LETTER O
+0xd7	0x041e	#CYRILLIC CAPITAL LETTER O
+0xd8	0x043f	#CYRILLIC SMALL LETTER PE
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x041f	#CYRILLIC CAPITAL LETTER PE
+0xde	0x044f	#CYRILLIC SMALL LETTER YA
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x042f	#CYRILLIC CAPITAL LETTER YA
+0xe1	0x0440	#CYRILLIC SMALL LETTER ER
+0xe2	0x0420	#CYRILLIC CAPITAL LETTER ER
+0xe3	0x0441	#CYRILLIC SMALL LETTER ES
+0xe4	0x0421	#CYRILLIC CAPITAL LETTER ES
+0xe5	0x0442	#CYRILLIC SMALL LETTER TE
+0xe6	0x0422	#CYRILLIC CAPITAL LETTER TE
+0xe7	0x0443	#CYRILLIC SMALL LETTER U
+0xe8	0x0423	#CYRILLIC CAPITAL LETTER U
+0xe9	0x0436	#CYRILLIC SMALL LETTER ZHE
+0xea	0x0416	#CYRILLIC CAPITAL LETTER ZHE
+0xeb	0x0432	#CYRILLIC SMALL LETTER VE
+0xec	0x0412	#CYRILLIC CAPITAL LETTER VE
+0xed	0x044c	#CYRILLIC SMALL LETTER SOFT SIGN
+0xee	0x042c	#CYRILLIC CAPITAL LETTER SOFT SIGN
+0xef	0x2116	#NUMERO SIGN
+0xf0	0x00ad	#SOFT HYPHEN
+0xf1	0x044b	#CYRILLIC SMALL LETTER YERU
+0xf2	0x042b	#CYRILLIC CAPITAL LETTER YERU
+0xf3	0x0437	#CYRILLIC SMALL LETTER ZE
+0xf4	0x0417	#CYRILLIC CAPITAL LETTER ZE
+0xf5	0x0448	#CYRILLIC SMALL LETTER SHA
+0xf6	0x0428	#CYRILLIC CAPITAL LETTER SHA
+0xf7	0x044d	#CYRILLIC SMALL LETTER E
+0xf8	0x042d	#CYRILLIC CAPITAL LETTER E
+0xf9	0x0449	#CYRILLIC SMALL LETTER SHCHA
+0xfa	0x0429	#CYRILLIC CAPITAL LETTER SHCHA
+0xfb	0x0447	#CYRILLIC SMALL LETTER CHE
+0xfc	0x0427	#CYRILLIC CAPITAL LETTER CHE
+0xfd	0x00a7	#SECTION SIGN
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP857.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x00c7	#LATIN CAPITAL LETTER C WITH CEDILLA
+0x81	0x00fc	#LATIN SMALL LETTER U WITH DIAERESIS
+0x82	0x00e9	#LATIN SMALL LETTER E WITH ACUTE
+0x83	0x00e2	#LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x84	0x00e4	#LATIN SMALL LETTER A WITH DIAERESIS
+0x85	0x00e0	#LATIN SMALL LETTER A WITH GRAVE
+0x86	0x00e5	#LATIN SMALL LETTER A WITH RING ABOVE
+0x87	0x00e7	#LATIN SMALL LETTER C WITH CEDILLA
+0x88	0x00ea	#LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x89	0x00eb	#LATIN SMALL LETTER E WITH DIAERESIS
+0x8a	0x00e8	#LATIN SMALL LETTER E WITH GRAVE
+0x8b	0x00ef	#LATIN SMALL LETTER I WITH DIAERESIS
+0x8c	0x00ee	#LATIN SMALL LETTER I WITH CIRCUMFLEX
+0x8d	0x0131	#LATIN SMALL LETTER DOTLESS I
+0x8e	0x00c4	#LATIN CAPITAL LETTER A WITH DIAERESIS
+0x8f	0x00c5	#LATIN CAPITAL LETTER A WITH RING ABOVE
+0x90	0x00c9	#LATIN CAPITAL LETTER E WITH ACUTE
+0x91	0x00e6	#LATIN SMALL LIGATURE AE
+0x92	0x00c6	#LATIN CAPITAL LIGATURE AE
+0x93	0x00f4	#LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x94	0x00f6	#LATIN SMALL LETTER O WITH DIAERESIS
+0x95	0x00f2	#LATIN SMALL LETTER O WITH GRAVE
+0x96	0x00fb	#LATIN SMALL LETTER U WITH CIRCUMFLEX
+0x97	0x00f9	#LATIN SMALL LETTER U WITH GRAVE
+0x98	0x0130	#LATIN CAPITAL LETTER I WITH DOT ABOVE
+0x99	0x00d6	#LATIN CAPITAL LETTER O WITH DIAERESIS
+0x9a	0x00dc	#LATIN CAPITAL LETTER U WITH DIAERESIS
+0x9b	0x00f8	#LATIN SMALL LETTER O WITH STROKE
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x00d8	#LATIN CAPITAL LETTER O WITH STROKE
+0x9e	0x015e	#LATIN CAPITAL LETTER S WITH CEDILLA
+0x9f	0x015f	#LATIN SMALL LETTER S WITH CEDILLA
+0xa0	0x00e1	#LATIN SMALL LETTER A WITH ACUTE
+0xa1	0x00ed	#LATIN SMALL LETTER I WITH ACUTE
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x00fa	#LATIN SMALL LETTER U WITH ACUTE
+0xa4	0x00f1	#LATIN SMALL LETTER N WITH TILDE
+0xa5	0x00d1	#LATIN CAPITAL LETTER N WITH TILDE
+0xa6	0x011e	#LATIN CAPITAL LETTER G WITH BREVE
+0xa7	0x011f	#LATIN SMALL LETTER G WITH BREVE
+0xa8	0x00bf	#INVERTED QUESTION MARK
+0xa9	0x00ae	#REGISTERED SIGN
+0xaa	0x00ac	#NOT SIGN
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x00bc	#VULGAR FRACTION ONE QUARTER
+0xad	0x00a1	#INVERTED EXCLAMATION MARK
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x00c1	#LATIN CAPITAL LETTER A WITH ACUTE
+0xb6	0x00c2	#LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+0xb7	0x00c0	#LATIN CAPITAL LETTER A WITH GRAVE
+0xb8	0x00a9	#COPYRIGHT SIGN
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x00a2	#CENT SIGN
+0xbe	0x00a5	#YEN SIGN
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x00e3	#LATIN SMALL LETTER A WITH TILDE
+0xc7	0x00c3	#LATIN CAPITAL LETTER A WITH TILDE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x00a4	#CURRENCY SIGN
+0xd0	0x00ba	#MASCULINE ORDINAL INDICATOR
+0xd1	0x00aa	#FEMININE ORDINAL INDICATOR
+0xd2	0x00ca	#LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+0xd3	0x00cb	#LATIN CAPITAL LETTER E WITH DIAERESIS
+0xd4	0x00c8	#LATIN CAPITAL LETTER E WITH GRAVE
+0xd5		#UNDEFINED
+0xd6	0x00cd	#LATIN CAPITAL LETTER I WITH ACUTE
+0xd7	0x00ce	#LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+0xd8	0x00cf	#LATIN CAPITAL LETTER I WITH DIAERESIS
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x00a6	#BROKEN BAR
+0xde	0x00cc	#LATIN CAPITAL LETTER I WITH GRAVE
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x00d3	#LATIN CAPITAL LETTER O WITH ACUTE
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S
+0xe2	0x00d4	#LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+0xe3	0x00d2	#LATIN CAPITAL LETTER O WITH GRAVE
+0xe4	0x00f5	#LATIN SMALL LETTER O WITH TILDE
+0xe5	0x00d5	#LATIN CAPITAL LETTER O WITH TILDE
+0xe6	0x00b5	#MICRO SIGN
+0xe7		#UNDEFINED
+0xe8	0x00d7	#MULTIPLICATION SIGN
+0xe9	0x00da	#LATIN CAPITAL LETTER U WITH ACUTE
+0xea	0x00db	#LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+0xeb	0x00d9	#LATIN CAPITAL LETTER U WITH GRAVE
+0xec	0x00ec	#LATIN SMALL LETTER I WITH GRAVE
+0xed	0x00ff	#LATIN SMALL LETTER Y WITH DIAERESIS
+0xee	0x00af	#MACRON
+0xef	0x00b4	#ACUTE ACCENT
+0xf0	0x00ad	#SOFT HYPHEN
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2		#UNDEFINED
+0xf3	0x00be	#VULGAR FRACTION THREE QUARTERS
+0xf4	0x00b6	#PILCROW SIGN
+0xf5	0x00a7	#SECTION SIGN
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x00b8	#CEDILLA
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x00a8	#DIAERESIS
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x00b9	#SUPERSCRIPT ONE
+0xfc	0x00b3	#SUPERSCRIPT THREE
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP860.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x00c7	#LATIN CAPITAL LETTER C WITH CEDILLA
+0x81	0x00fc	#LATIN SMALL LETTER U WITH DIAERESIS
+0x82	0x00e9	#LATIN SMALL LETTER E WITH ACUTE
+0x83	0x00e2	#LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x84	0x00e3	#LATIN SMALL LETTER A WITH TILDE
+0x85	0x00e0	#LATIN SMALL LETTER A WITH GRAVE
+0x86	0x00c1	#LATIN CAPITAL LETTER A WITH ACUTE
+0x87	0x00e7	#LATIN SMALL LETTER C WITH CEDILLA
+0x88	0x00ea	#LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x89	0x00ca	#LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+0x8a	0x00e8	#LATIN SMALL LETTER E WITH GRAVE
+0x8b	0x00cd	#LATIN CAPITAL LETTER I WITH ACUTE
+0x8c	0x00d4	#LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+0x8d	0x00ec	#LATIN SMALL LETTER I WITH GRAVE
+0x8e	0x00c3	#LATIN CAPITAL LETTER A WITH TILDE
+0x8f	0x00c2	#LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+0x90	0x00c9	#LATIN CAPITAL LETTER E WITH ACUTE
+0x91	0x00c0	#LATIN CAPITAL LETTER A WITH GRAVE
+0x92	0x00c8	#LATIN CAPITAL LETTER E WITH GRAVE
+0x93	0x00f4	#LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x94	0x00f5	#LATIN SMALL LETTER O WITH TILDE
+0x95	0x00f2	#LATIN SMALL LETTER O WITH GRAVE
+0x96	0x00da	#LATIN CAPITAL LETTER U WITH ACUTE
+0x97	0x00f9	#LATIN SMALL LETTER U WITH GRAVE
+0x98	0x00cc	#LATIN CAPITAL LETTER I WITH GRAVE
+0x99	0x00d5	#LATIN CAPITAL LETTER O WITH TILDE
+0x9a	0x00dc	#LATIN CAPITAL LETTER U WITH DIAERESIS
+0x9b	0x00a2	#CENT SIGN
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x00d9	#LATIN CAPITAL LETTER U WITH GRAVE
+0x9e	0x20a7	#PESETA SIGN
+0x9f	0x00d3	#LATIN CAPITAL LETTER O WITH ACUTE
+0xa0	0x00e1	#LATIN SMALL LETTER A WITH ACUTE
+0xa1	0x00ed	#LATIN SMALL LETTER I WITH ACUTE
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x00fa	#LATIN SMALL LETTER U WITH ACUTE
+0xa4	0x00f1	#LATIN SMALL LETTER N WITH TILDE
+0xa5	0x00d1	#LATIN CAPITAL LETTER N WITH TILDE
+0xa6	0x00aa	#FEMININE ORDINAL INDICATOR
+0xa7	0x00ba	#MASCULINE ORDINAL INDICATOR
+0xa8	0x00bf	#INVERTED QUESTION MARK
+0xa9	0x00d2	#LATIN CAPITAL LETTER O WITH GRAVE
+0xaa	0x00ac	#NOT SIGN
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x00bc	#VULGAR FRACTION ONE QUARTER
+0xad	0x00a1	#INVERTED EXCLAMATION MARK
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x2561	#BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xb6	0x2562	#BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+0xb7	0x2556	#BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+0xb8	0x2555	#BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x255c	#BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+0xbe	0x255b	#BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x255e	#BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xc7	0x255f	#BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x2567	#BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xd0	0x2568	#BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xd1	0x2564	#BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+0xd2	0x2565	#BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+0xd3	0x2559	#BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xd4	0x2558	#BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xd5	0x2552	#BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xd6	0x2553	#BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+0xd7	0x256b	#BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+0xd8	0x256a	#BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x258c	#LEFT HALF BLOCK
+0xde	0x2590	#RIGHT HALF BLOCK
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x03b1	#GREEK SMALL LETTER ALPHA
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S
+0xe2	0x0393	#GREEK CAPITAL LETTER GAMMA
+0xe3	0x03c0	#GREEK SMALL LETTER PI
+0xe4	0x03a3	#GREEK CAPITAL LETTER SIGMA
+0xe5	0x03c3	#GREEK SMALL LETTER SIGMA
+0xe6	0x00b5	#MICRO SIGN
+0xe7	0x03c4	#GREEK SMALL LETTER TAU
+0xe8	0x03a6	#GREEK CAPITAL LETTER PHI
+0xe9	0x0398	#GREEK CAPITAL LETTER THETA
+0xea	0x03a9	#GREEK CAPITAL LETTER OMEGA
+0xeb	0x03b4	#GREEK SMALL LETTER DELTA
+0xec	0x221e	#INFINITY
+0xed	0x03c6	#GREEK SMALL LETTER PHI
+0xee	0x03b5	#GREEK SMALL LETTER EPSILON
+0xef	0x2229	#INTERSECTION
+0xf0	0x2261	#IDENTICAL TO
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x2265	#GREATER-THAN OR EQUAL TO
+0xf3	0x2264	#LESS-THAN OR EQUAL TO
+0xf4	0x2320	#TOP HALF INTEGRAL
+0xf5	0x2321	#BOTTOM HALF INTEGRAL
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x2248	#ALMOST EQUAL TO
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x2219	#BULLET OPERATOR
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x221a	#SQUARE ROOT
+0xfc	0x207f	#SUPERSCRIPT LATIN SMALL LETTER N
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP861.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x00c7	#LATIN CAPITAL LETTER C WITH CEDILLA
+0x81	0x00fc	#LATIN SMALL LETTER U WITH DIAERESIS
+0x82	0x00e9	#LATIN SMALL LETTER E WITH ACUTE
+0x83	0x00e2	#LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x84	0x00e4	#LATIN SMALL LETTER A WITH DIAERESIS
+0x85	0x00e0	#LATIN SMALL LETTER A WITH GRAVE
+0x86	0x00e5	#LATIN SMALL LETTER A WITH RING ABOVE
+0x87	0x00e7	#LATIN SMALL LETTER C WITH CEDILLA
+0x88	0x00ea	#LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x89	0x00eb	#LATIN SMALL LETTER E WITH DIAERESIS
+0x8a	0x00e8	#LATIN SMALL LETTER E WITH GRAVE
+0x8b	0x00d0	#LATIN CAPITAL LETTER ETH
+0x8c	0x00f0	#LATIN SMALL LETTER ETH
+0x8d	0x00de	#LATIN CAPITAL LETTER THORN
+0x8e	0x00c4	#LATIN CAPITAL LETTER A WITH DIAERESIS
+0x8f	0x00c5	#LATIN CAPITAL LETTER A WITH RING ABOVE
+0x90	0x00c9	#LATIN CAPITAL LETTER E WITH ACUTE
+0x91	0x00e6	#LATIN SMALL LIGATURE AE
+0x92	0x00c6	#LATIN CAPITAL LIGATURE AE
+0x93	0x00f4	#LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x94	0x00f6	#LATIN SMALL LETTER O WITH DIAERESIS
+0x95	0x00fe	#LATIN SMALL LETTER THORN
+0x96	0x00fb	#LATIN SMALL LETTER U WITH CIRCUMFLEX
+0x97	0x00dd	#LATIN CAPITAL LETTER Y WITH ACUTE
+0x98	0x00fd	#LATIN SMALL LETTER Y WITH ACUTE
+0x99	0x00d6	#LATIN CAPITAL LETTER O WITH DIAERESIS
+0x9a	0x00dc	#LATIN CAPITAL LETTER U WITH DIAERESIS
+0x9b	0x00f8	#LATIN SMALL LETTER O WITH STROKE
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x00d8	#LATIN CAPITAL LETTER O WITH STROKE
+0x9e	0x20a7	#PESETA SIGN
+0x9f	0x0192	#LATIN SMALL LETTER F WITH HOOK
+0xa0	0x00e1	#LATIN SMALL LETTER A WITH ACUTE
+0xa1	0x00ed	#LATIN SMALL LETTER I WITH ACUTE
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x00fa	#LATIN SMALL LETTER U WITH ACUTE
+0xa4	0x00c1	#LATIN CAPITAL LETTER A WITH ACUTE
+0xa5	0x00cd	#LATIN CAPITAL LETTER I WITH ACUTE
+0xa6	0x00d3	#LATIN CAPITAL LETTER O WITH ACUTE
+0xa7	0x00da	#LATIN CAPITAL LETTER U WITH ACUTE
+0xa8	0x00bf	#INVERTED QUESTION MARK
+0xa9	0x2310	#REVERSED NOT SIGN
+0xaa	0x00ac	#NOT SIGN
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x00bc	#VULGAR FRACTION ONE QUARTER
+0xad	0x00a1	#INVERTED EXCLAMATION MARK
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x2561	#BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xb6	0x2562	#BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+0xb7	0x2556	#BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+0xb8	0x2555	#BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x255c	#BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+0xbe	0x255b	#BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x255e	#BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xc7	0x255f	#BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x2567	#BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xd0	0x2568	#BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xd1	0x2564	#BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+0xd2	0x2565	#BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+0xd3	0x2559	#BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xd4	0x2558	#BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xd5	0x2552	#BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xd6	0x2553	#BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+0xd7	0x256b	#BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+0xd8	0x256a	#BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x258c	#LEFT HALF BLOCK
+0xde	0x2590	#RIGHT HALF BLOCK
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x03b1	#GREEK SMALL LETTER ALPHA
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S
+0xe2	0x0393	#GREEK CAPITAL LETTER GAMMA
+0xe3	0x03c0	#GREEK SMALL LETTER PI
+0xe4	0x03a3	#GREEK CAPITAL LETTER SIGMA
+0xe5	0x03c3	#GREEK SMALL LETTER SIGMA
+0xe6	0x00b5	#MICRO SIGN
+0xe7	0x03c4	#GREEK SMALL LETTER TAU
+0xe8	0x03a6	#GREEK CAPITAL LETTER PHI
+0xe9	0x0398	#GREEK CAPITAL LETTER THETA
+0xea	0x03a9	#GREEK CAPITAL LETTER OMEGA
+0xeb	0x03b4	#GREEK SMALL LETTER DELTA
+0xec	0x221e	#INFINITY
+0xed	0x03c6	#GREEK SMALL LETTER PHI
+0xee	0x03b5	#GREEK SMALL LETTER EPSILON
+0xef	0x2229	#INTERSECTION
+0xf0	0x2261	#IDENTICAL TO
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x2265	#GREATER-THAN OR EQUAL TO
+0xf3	0x2264	#LESS-THAN OR EQUAL TO
+0xf4	0x2320	#TOP HALF INTEGRAL
+0xf5	0x2321	#BOTTOM HALF INTEGRAL
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x2248	#ALMOST EQUAL TO
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x2219	#BULLET OPERATOR
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x221a	#SQUARE ROOT
+0xfc	0x207f	#SUPERSCRIPT LATIN SMALL LETTER N
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP862.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x05d0	#HEBREW LETTER ALEF
+0x81	0x05d1	#HEBREW LETTER BET
+0x82	0x05d2	#HEBREW LETTER GIMEL
+0x83	0x05d3	#HEBREW LETTER DALET
+0x84	0x05d4	#HEBREW LETTER HE
+0x85	0x05d5	#HEBREW LETTER VAV
+0x86	0x05d6	#HEBREW LETTER ZAYIN
+0x87	0x05d7	#HEBREW LETTER HET
+0x88	0x05d8	#HEBREW LETTER TET
+0x89	0x05d9	#HEBREW LETTER YOD
+0x8a	0x05da	#HEBREW LETTER FINAL KAF
+0x8b	0x05db	#HEBREW LETTER KAF
+0x8c	0x05dc	#HEBREW LETTER LAMED
+0x8d	0x05dd	#HEBREW LETTER FINAL MEM
+0x8e	0x05de	#HEBREW LETTER MEM
+0x8f	0x05df	#HEBREW LETTER FINAL NUN
+0x90	0x05e0	#HEBREW LETTER NUN
+0x91	0x05e1	#HEBREW LETTER SAMEKH
+0x92	0x05e2	#HEBREW LETTER AYIN
+0x93	0x05e3	#HEBREW LETTER FINAL PE
+0x94	0x05e4	#HEBREW LETTER PE
+0x95	0x05e5	#HEBREW LETTER FINAL TSADI
+0x96	0x05e6	#HEBREW LETTER TSADI
+0x97	0x05e7	#HEBREW LETTER QOF
+0x98	0x05e8	#HEBREW LETTER RESH
+0x99	0x05e9	#HEBREW LETTER SHIN
+0x9a	0x05ea	#HEBREW LETTER TAV
+0x9b	0x00a2	#CENT SIGN
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x00a5	#YEN SIGN
+0x9e	0x20a7	#PESETA SIGN
+0x9f	0x0192	#LATIN SMALL LETTER F WITH HOOK
+0xa0	0x00e1	#LATIN SMALL LETTER A WITH ACUTE
+0xa1	0x00ed	#LATIN SMALL LETTER I WITH ACUTE
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x00fa	#LATIN SMALL LETTER U WITH ACUTE
+0xa4	0x00f1	#LATIN SMALL LETTER N WITH TILDE
+0xa5	0x00d1	#LATIN CAPITAL LETTER N WITH TILDE
+0xa6	0x00aa	#FEMININE ORDINAL INDICATOR
+0xa7	0x00ba	#MASCULINE ORDINAL INDICATOR
+0xa8	0x00bf	#INVERTED QUESTION MARK
+0xa9	0x2310	#REVERSED NOT SIGN
+0xaa	0x00ac	#NOT SIGN
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x00bc	#VULGAR FRACTION ONE QUARTER
+0xad	0x00a1	#INVERTED EXCLAMATION MARK
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x2561	#BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xb6	0x2562	#BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+0xb7	0x2556	#BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+0xb8	0x2555	#BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x255c	#BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+0xbe	0x255b	#BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x255e	#BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xc7	0x255f	#BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x2567	#BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xd0	0x2568	#BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xd1	0x2564	#BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+0xd2	0x2565	#BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+0xd3	0x2559	#BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xd4	0x2558	#BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xd5	0x2552	#BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xd6	0x2553	#BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+0xd7	0x256b	#BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+0xd8	0x256a	#BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x258c	#LEFT HALF BLOCK
+0xde	0x2590	#RIGHT HALF BLOCK
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x03b1	#GREEK SMALL LETTER ALPHA
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S (GERMAN)
+0xe2	0x0393	#GREEK CAPITAL LETTER GAMMA
+0xe3	0x03c0	#GREEK SMALL LETTER PI
+0xe4	0x03a3	#GREEK CAPITAL LETTER SIGMA
+0xe5	0x03c3	#GREEK SMALL LETTER SIGMA
+0xe6	0x00b5	#MICRO SIGN
+0xe7	0x03c4	#GREEK SMALL LETTER TAU
+0xe8	0x03a6	#GREEK CAPITAL LETTER PHI
+0xe9	0x0398	#GREEK CAPITAL LETTER THETA
+0xea	0x03a9	#GREEK CAPITAL LETTER OMEGA
+0xeb	0x03b4	#GREEK SMALL LETTER DELTA
+0xec	0x221e	#INFINITY
+0xed	0x03c6	#GREEK SMALL LETTER PHI
+0xee	0x03b5	#GREEK SMALL LETTER EPSILON
+0xef	0x2229	#INTERSECTION
+0xf0	0x2261	#IDENTICAL TO
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x2265	#GREATER-THAN OR EQUAL TO
+0xf3	0x2264	#LESS-THAN OR EQUAL TO
+0xf4	0x2320	#TOP HALF INTEGRAL
+0xf5	0x2321	#BOTTOM HALF INTEGRAL
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x2248	#ALMOST EQUAL TO
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x2219	#BULLET OPERATOR
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x221a	#SQUARE ROOT
+0xfc	0x207f	#SUPERSCRIPT LATIN SMALL LETTER N
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP863.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x00c7	#LATIN CAPITAL LETTER C WITH CEDILLA
+0x81	0x00fc	#LATIN SMALL LETTER U WITH DIAERESIS
+0x82	0x00e9	#LATIN SMALL LETTER E WITH ACUTE
+0x83	0x00e2	#LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x84	0x00c2	#LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+0x85	0x00e0	#LATIN SMALL LETTER A WITH GRAVE
+0x86	0x00b6	#PILCROW SIGN
+0x87	0x00e7	#LATIN SMALL LETTER C WITH CEDILLA
+0x88	0x00ea	#LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x89	0x00eb	#LATIN SMALL LETTER E WITH DIAERESIS
+0x8a	0x00e8	#LATIN SMALL LETTER E WITH GRAVE
+0x8b	0x00ef	#LATIN SMALL LETTER I WITH DIAERESIS
+0x8c	0x00ee	#LATIN SMALL LETTER I WITH CIRCUMFLEX
+0x8d	0x2017	#DOUBLE LOW LINE
+0x8e	0x00c0	#LATIN CAPITAL LETTER A WITH GRAVE
+0x8f	0x00a7	#SECTION SIGN
+0x90	0x00c9	#LATIN CAPITAL LETTER E WITH ACUTE
+0x91	0x00c8	#LATIN CAPITAL LETTER E WITH GRAVE
+0x92	0x00ca	#LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+0x93	0x00f4	#LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x94	0x00cb	#LATIN CAPITAL LETTER E WITH DIAERESIS
+0x95	0x00cf	#LATIN CAPITAL LETTER I WITH DIAERESIS
+0x96	0x00fb	#LATIN SMALL LETTER U WITH CIRCUMFLEX
+0x97	0x00f9	#LATIN SMALL LETTER U WITH GRAVE
+0x98	0x00a4	#CURRENCY SIGN
+0x99	0x00d4	#LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+0x9a	0x00dc	#LATIN CAPITAL LETTER U WITH DIAERESIS
+0x9b	0x00a2	#CENT SIGN
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x00d9	#LATIN CAPITAL LETTER U WITH GRAVE
+0x9e	0x00db	#LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+0x9f	0x0192	#LATIN SMALL LETTER F WITH HOOK
+0xa0	0x00a6	#BROKEN BAR
+0xa1	0x00b4	#ACUTE ACCENT
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x00fa	#LATIN SMALL LETTER U WITH ACUTE
+0xa4	0x00a8	#DIAERESIS
+0xa5	0x00b8	#CEDILLA
+0xa6	0x00b3	#SUPERSCRIPT THREE
+0xa7	0x00af	#MACRON
+0xa8	0x00ce	#LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+0xa9	0x2310	#REVERSED NOT SIGN
+0xaa	0x00ac	#NOT SIGN
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x00bc	#VULGAR FRACTION ONE QUARTER
+0xad	0x00be	#VULGAR FRACTION THREE QUARTERS
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x2561	#BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xb6	0x2562	#BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+0xb7	0x2556	#BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+0xb8	0x2555	#BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x255c	#BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+0xbe	0x255b	#BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x255e	#BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xc7	0x255f	#BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x2567	#BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xd0	0x2568	#BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xd1	0x2564	#BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+0xd2	0x2565	#BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+0xd3	0x2559	#BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xd4	0x2558	#BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xd5	0x2552	#BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xd6	0x2553	#BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+0xd7	0x256b	#BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+0xd8	0x256a	#BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x258c	#LEFT HALF BLOCK
+0xde	0x2590	#RIGHT HALF BLOCK
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x03b1	#GREEK SMALL LETTER ALPHA
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S
+0xe2	0x0393	#GREEK CAPITAL LETTER GAMMA
+0xe3	0x03c0	#GREEK SMALL LETTER PI
+0xe4	0x03a3	#GREEK CAPITAL LETTER SIGMA
+0xe5	0x03c3	#GREEK SMALL LETTER SIGMA
+0xe6	0x00b5	#MICRO SIGN
+0xe7	0x03c4	#GREEK SMALL LETTER TAU
+0xe8	0x03a6	#GREEK CAPITAL LETTER PHI
+0xe9	0x0398	#GREEK CAPITAL LETTER THETA
+0xea	0x03a9	#GREEK CAPITAL LETTER OMEGA
+0xeb	0x03b4	#GREEK SMALL LETTER DELTA
+0xec	0x221e	#INFINITY
+0xed	0x03c6	#GREEK SMALL LETTER PHI
+0xee	0x03b5	#GREEK SMALL LETTER EPSILON
+0xef	0x2229	#INTERSECTION
+0xf0	0x2261	#IDENTICAL TO
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x2265	#GREATER-THAN OR EQUAL TO
+0xf3	0x2264	#LESS-THAN OR EQUAL TO
+0xf4	0x2320	#TOP HALF INTEGRAL
+0xf5	0x2321	#BOTTOM HALF INTEGRAL
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x2248	#ALMOST EQUAL TO
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x2219	#BULLET OPERATOR
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x221a	#SQUARE ROOT
+0xfc	0x207f	#SUPERSCRIPT LATIN SMALL LETTER N
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP864.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x066a	#ARABIC PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x00b0	#DEGREE SIGN
+0x81	0x00b7	#MIDDLE DOT
+0x82	0x2219	#BULLET OPERATOR
+0x83	0x221a	#SQUARE ROOT
+0x84	0x2592	#MEDIUM SHADE
+0x85	0x2500	#FORMS LIGHT HORIZONTAL
+0x86	0x2502	#FORMS LIGHT VERTICAL
+0x87	0x253c	#FORMS LIGHT VERTICAL AND HORIZONTAL
+0x88	0x2524	#FORMS LIGHT VERTICAL AND LEFT
+0x89	0x252c	#FORMS LIGHT DOWN AND HORIZONTAL
+0x8a	0x251c	#FORMS LIGHT VERTICAL AND RIGHT
+0x8b	0x2534	#FORMS LIGHT UP AND HORIZONTAL
+0x8c	0x2510	#FORMS LIGHT DOWN AND LEFT
+0x8d	0x250c	#FORMS LIGHT DOWN AND RIGHT
+0x8e	0x2514	#FORMS LIGHT UP AND RIGHT
+0x8f	0x2518	#FORMS LIGHT UP AND LEFT
+0x90	0x03b2	#GREEK SMALL BETA
+0x91	0x221e	#INFINITY
+0x92	0x03c6	#GREEK SMALL PHI
+0x93	0x00b1	#PLUS-OR-MINUS SIGN
+0x94	0x00bd	#FRACTION 1/2
+0x95	0x00bc	#FRACTION 1/4
+0x96	0x2248	#ALMOST EQUAL TO
+0x97	0x00ab	#LEFT POINTING GUILLEMET
+0x98	0x00bb	#RIGHT POINTING GUILLEMET
+0x99	0xfef7	#ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM
+0x9a	0xfef8	#ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM
+0x9b		#UNDEFINED
+0x9c		#UNDEFINED
+0x9d	0xfefb	#ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM
+0x9e	0xfefc	#ARABIC LIGATURE LAM WITH ALEF FINAL FORM
+0x9f		#UNDEFINED
+0xa0	0x00a0	#NON-BREAKING SPACE
+0xa1	0x00ad	#SOFT HYPHEN
+0xa2	0xfe82	#ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM
+0xa3	0x00a3	#POUND SIGN
+0xa4	0x00a4	#CURRENCY SIGN
+0xa5	0xfe84	#ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM
+0xa6		#UNDEFINED
+0xa7		#UNDEFINED
+0xa8	0xfe8e	#ARABIC LETTER ALEF FINAL FORM
+0xa9	0xfe8f	#ARABIC LETTER BEH ISOLATED FORM
+0xaa	0xfe95	#ARABIC LETTER TEH ISOLATED FORM
+0xab	0xfe99	#ARABIC LETTER THEH ISOLATED FORM
+0xac	0x060c	#ARABIC COMMA
+0xad	0xfe9d	#ARABIC LETTER JEEM ISOLATED FORM
+0xae	0xfea1	#ARABIC LETTER HAH ISOLATED FORM
+0xaf	0xfea5	#ARABIC LETTER KHAH ISOLATED FORM
+0xb0	0x0660	#ARABIC-INDIC DIGIT ZERO
+0xb1	0x0661	#ARABIC-INDIC DIGIT ONE
+0xb2	0x0662	#ARABIC-INDIC DIGIT TWO
+0xb3	0x0663	#ARABIC-INDIC DIGIT THREE
+0xb4	0x0664	#ARABIC-INDIC DIGIT FOUR
+0xb5	0x0665	#ARABIC-INDIC DIGIT FIVE
+0xb6	0x0666	#ARABIC-INDIC DIGIT SIX
+0xb7	0x0667	#ARABIC-INDIC DIGIT SEVEN
+0xb8	0x0668	#ARABIC-INDIC DIGIT EIGHT
+0xb9	0x0669	#ARABIC-INDIC DIGIT NINE
+0xba	0xfed1	#ARABIC LETTER FEH ISOLATED FORM
+0xbb	0x061b	#ARABIC SEMICOLON
+0xbc	0xfeb1	#ARABIC LETTER SEEN ISOLATED FORM
+0xbd	0xfeb5	#ARABIC LETTER SHEEN ISOLATED FORM
+0xbe	0xfeb9	#ARABIC LETTER SAD ISOLATED FORM
+0xbf	0x061f	#ARABIC QUESTION MARK
+0xc0	0x00a2	#CENT SIGN
+0xc1	0xfe80	#ARABIC LETTER HAMZA ISOLATED FORM
+0xc2	0xfe81	#ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
+0xc3	0xfe83	#ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM
+0xc4	0xfe85	#ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
+0xc5	0xfeca	#ARABIC LETTER AIN FINAL FORM
+0xc6	0xfe8b	#ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
+0xc7	0xfe8d	#ARABIC LETTER ALEF ISOLATED FORM
+0xc8	0xfe91	#ARABIC LETTER BEH INITIAL FORM
+0xc9	0xfe93	#ARABIC LETTER TEH MARBUTA ISOLATED FORM
+0xca	0xfe97	#ARABIC LETTER TEH INITIAL FORM
+0xcb	0xfe9b	#ARABIC LETTER THEH INITIAL FORM
+0xcc	0xfe9f	#ARABIC LETTER JEEM INITIAL FORM
+0xcd	0xfea3	#ARABIC LETTER HAH INITIAL FORM
+0xce	0xfea7	#ARABIC LETTER KHAH INITIAL FORM
+0xcf	0xfea9	#ARABIC LETTER DAL ISOLATED FORM
+0xd0	0xfeab	#ARABIC LETTER THAL ISOLATED FORM
+0xd1	0xfead	#ARABIC LETTER REH ISOLATED FORM
+0xd2	0xfeaf	#ARABIC LETTER ZAIN ISOLATED FORM
+0xd3	0xfeb3	#ARABIC LETTER SEEN INITIAL FORM
+0xd4	0xfeb7	#ARABIC LETTER SHEEN INITIAL FORM
+0xd5	0xfebb	#ARABIC LETTER SAD INITIAL FORM
+0xd6	0xfebf	#ARABIC LETTER DAD INITIAL FORM
+0xd7	0xfec1	#ARABIC LETTER TAH ISOLATED FORM
+0xd8	0xfec5	#ARABIC LETTER ZAH ISOLATED FORM
+0xd9	0xfecb	#ARABIC LETTER AIN INITIAL FORM
+0xda	0xfecf	#ARABIC LETTER GHAIN INITIAL FORM
+0xdb	0x00a6	#BROKEN VERTICAL BAR
+0xdc	0x00ac	#NOT SIGN
+0xdd	0x00f7	#DIVISION SIGN
+0xde	0x00d7	#MULTIPLICATION SIGN
+0xdf	0xfec9	#ARABIC LETTER AIN ISOLATED FORM
+0xe0	0x0640	#ARABIC TATWEEL
+0xe1	0xfed3	#ARABIC LETTER FEH INITIAL FORM
+0xe2	0xfed7	#ARABIC LETTER QAF INITIAL FORM
+0xe3	0xfedb	#ARABIC LETTER KAF INITIAL FORM
+0xe4	0xfedf	#ARABIC LETTER LAM INITIAL FORM
+0xe5	0xfee3	#ARABIC LETTER MEEM INITIAL FORM
+0xe6	0xfee7	#ARABIC LETTER NOON INITIAL FORM
+0xe7	0xfeeb	#ARABIC LETTER HEH INITIAL FORM
+0xe8	0xfeed	#ARABIC LETTER WAW ISOLATED FORM
+0xe9	0xfeef	#ARABIC LETTER ALEF MAKSURA ISOLATED FORM
+0xea	0xfef3	#ARABIC LETTER YEH INITIAL FORM
+0xeb	0xfebd	#ARABIC LETTER DAD ISOLATED FORM
+0xec	0xfecc	#ARABIC LETTER AIN MEDIAL FORM
+0xed	0xfece	#ARABIC LETTER GHAIN FINAL FORM
+0xee	0xfecd	#ARABIC LETTER GHAIN ISOLATED FORM
+0xef	0xfee1	#ARABIC LETTER MEEM ISOLATED FORM
+0xf0	0xfe7d	#ARABIC SHADDA MEDIAL FORM
+0xf1	0x0651	#ARABIC SHADDAH
+0xf2	0xfee5	#ARABIC LETTER NOON ISOLATED FORM
+0xf3	0xfee9	#ARABIC LETTER HEH ISOLATED FORM
+0xf4	0xfeec	#ARABIC LETTER HEH MEDIAL FORM
+0xf5	0xfef0	#ARABIC LETTER ALEF MAKSURA FINAL FORM
+0xf6	0xfef2	#ARABIC LETTER YEH FINAL FORM
+0xf7	0xfed0	#ARABIC LETTER GHAIN MEDIAL FORM
+0xf8	0xfed5	#ARABIC LETTER QAF ISOLATED FORM
+0xf9	0xfef5	#ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM
+0xfa	0xfef6	#ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM
+0xfb	0xfedd	#ARABIC LETTER LAM ISOLATED FORM
+0xfc	0xfed9	#ARABIC LETTER KAF ISOLATED FORM
+0xfd	0xfef1	#ARABIC LETTER YEH ISOLATED FORM
+0xfe	0x25a0	#BLACK SQUARE
+0xff		#UNDEFINED

Data/Encoding/CP865.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x00c7	#LATIN CAPITAL LETTER C WITH CEDILLA
+0x81	0x00fc	#LATIN SMALL LETTER U WITH DIAERESIS
+0x82	0x00e9	#LATIN SMALL LETTER E WITH ACUTE
+0x83	0x00e2	#LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x84	0x00e4	#LATIN SMALL LETTER A WITH DIAERESIS
+0x85	0x00e0	#LATIN SMALL LETTER A WITH GRAVE
+0x86	0x00e5	#LATIN SMALL LETTER A WITH RING ABOVE
+0x87	0x00e7	#LATIN SMALL LETTER C WITH CEDILLA
+0x88	0x00ea	#LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x89	0x00eb	#LATIN SMALL LETTER E WITH DIAERESIS
+0x8a	0x00e8	#LATIN SMALL LETTER E WITH GRAVE
+0x8b	0x00ef	#LATIN SMALL LETTER I WITH DIAERESIS
+0x8c	0x00ee	#LATIN SMALL LETTER I WITH CIRCUMFLEX
+0x8d	0x00ec	#LATIN SMALL LETTER I WITH GRAVE
+0x8e	0x00c4	#LATIN CAPITAL LETTER A WITH DIAERESIS
+0x8f	0x00c5	#LATIN CAPITAL LETTER A WITH RING ABOVE
+0x90	0x00c9	#LATIN CAPITAL LETTER E WITH ACUTE
+0x91	0x00e6	#LATIN SMALL LIGATURE AE
+0x92	0x00c6	#LATIN CAPITAL LIGATURE AE
+0x93	0x00f4	#LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x94	0x00f6	#LATIN SMALL LETTER O WITH DIAERESIS
+0x95	0x00f2	#LATIN SMALL LETTER O WITH GRAVE
+0x96	0x00fb	#LATIN SMALL LETTER U WITH CIRCUMFLEX
+0x97	0x00f9	#LATIN SMALL LETTER U WITH GRAVE
+0x98	0x00ff	#LATIN SMALL LETTER Y WITH DIAERESIS
+0x99	0x00d6	#LATIN CAPITAL LETTER O WITH DIAERESIS
+0x9a	0x00dc	#LATIN CAPITAL LETTER U WITH DIAERESIS
+0x9b	0x00f8	#LATIN SMALL LETTER O WITH STROKE
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x00d8	#LATIN CAPITAL LETTER O WITH STROKE
+0x9e	0x20a7	#PESETA SIGN
+0x9f	0x0192	#LATIN SMALL LETTER F WITH HOOK
+0xa0	0x00e1	#LATIN SMALL LETTER A WITH ACUTE
+0xa1	0x00ed	#LATIN SMALL LETTER I WITH ACUTE
+0xa2	0x00f3	#LATIN SMALL LETTER O WITH ACUTE
+0xa3	0x00fa	#LATIN SMALL LETTER U WITH ACUTE
+0xa4	0x00f1	#LATIN SMALL LETTER N WITH TILDE
+0xa5	0x00d1	#LATIN CAPITAL LETTER N WITH TILDE
+0xa6	0x00aa	#FEMININE ORDINAL INDICATOR
+0xa7	0x00ba	#MASCULINE ORDINAL INDICATOR
+0xa8	0x00bf	#INVERTED QUESTION MARK
+0xa9	0x2310	#REVERSED NOT SIGN
+0xaa	0x00ac	#NOT SIGN
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x00bc	#VULGAR FRACTION ONE QUARTER
+0xad	0x00a1	#INVERTED EXCLAMATION MARK
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00a4	#CURRENCY SIGN
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x2561	#BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xb6	0x2562	#BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+0xb7	0x2556	#BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+0xb8	0x2555	#BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x255c	#BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+0xbe	0x255b	#BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x255e	#BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xc7	0x255f	#BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x2567	#BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xd0	0x2568	#BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xd1	0x2564	#BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+0xd2	0x2565	#BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+0xd3	0x2559	#BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xd4	0x2558	#BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xd5	0x2552	#BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xd6	0x2553	#BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+0xd7	0x256b	#BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+0xd8	0x256a	#BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x258c	#LEFT HALF BLOCK
+0xde	0x2590	#RIGHT HALF BLOCK
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x03b1	#GREEK SMALL LETTER ALPHA
+0xe1	0x00df	#LATIN SMALL LETTER SHARP S
+0xe2	0x0393	#GREEK CAPITAL LETTER GAMMA
+0xe3	0x03c0	#GREEK SMALL LETTER PI
+0xe4	0x03a3	#GREEK CAPITAL LETTER SIGMA
+0xe5	0x03c3	#GREEK SMALL LETTER SIGMA
+0xe6	0x00b5	#MICRO SIGN
+0xe7	0x03c4	#GREEK SMALL LETTER TAU
+0xe8	0x03a6	#GREEK CAPITAL LETTER PHI
+0xe9	0x0398	#GREEK CAPITAL LETTER THETA
+0xea	0x03a9	#GREEK CAPITAL LETTER OMEGA
+0xeb	0x03b4	#GREEK SMALL LETTER DELTA
+0xec	0x221e	#INFINITY
+0xed	0x03c6	#GREEK SMALL LETTER PHI
+0xee	0x03b5	#GREEK SMALL LETTER EPSILON
+0xef	0x2229	#INTERSECTION
+0xf0	0x2261	#IDENTICAL TO
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x2265	#GREATER-THAN OR EQUAL TO
+0xf3	0x2264	#LESS-THAN OR EQUAL TO
+0xf4	0x2320	#TOP HALF INTEGRAL
+0xf5	0x2321	#BOTTOM HALF INTEGRAL
+0xf6	0x00f7	#DIVISION SIGN
+0xf7	0x2248	#ALMOST EQUAL TO
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x2219	#BULLET OPERATOR
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x221a	#SQUARE ROOT
+0xfc	0x207f	#SUPERSCRIPT LATIN SMALL LETTER N
+0xfd	0x00b2	#SUPERSCRIPT TWO
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP866.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80	0x0410	#CYRILLIC CAPITAL LETTER A
+0x81	0x0411	#CYRILLIC CAPITAL LETTER BE
+0x82	0x0412	#CYRILLIC CAPITAL LETTER VE
+0x83	0x0413	#CYRILLIC CAPITAL LETTER GHE
+0x84	0x0414	#CYRILLIC CAPITAL LETTER DE
+0x85	0x0415	#CYRILLIC CAPITAL LETTER IE
+0x86	0x0416	#CYRILLIC CAPITAL LETTER ZHE
+0x87	0x0417	#CYRILLIC CAPITAL LETTER ZE
+0x88	0x0418	#CYRILLIC CAPITAL LETTER I
+0x89	0x0419	#CYRILLIC CAPITAL LETTER SHORT I
+0x8a	0x041a	#CYRILLIC CAPITAL LETTER KA
+0x8b	0x041b	#CYRILLIC CAPITAL LETTER EL
+0x8c	0x041c	#CYRILLIC CAPITAL LETTER EM
+0x8d	0x041d	#CYRILLIC CAPITAL LETTER EN
+0x8e	0x041e	#CYRILLIC CAPITAL LETTER O
+0x8f	0x041f	#CYRILLIC CAPITAL LETTER PE
+0x90	0x0420	#CYRILLIC CAPITAL LETTER ER
+0x91	0x0421	#CYRILLIC CAPITAL LETTER ES
+0x92	0x0422	#CYRILLIC CAPITAL LETTER TE
+0x93	0x0423	#CYRILLIC CAPITAL LETTER U
+0x94	0x0424	#CYRILLIC CAPITAL LETTER EF
+0x95	0x0425	#CYRILLIC CAPITAL LETTER HA
+0x96	0x0426	#CYRILLIC CAPITAL LETTER TSE
+0x97	0x0427	#CYRILLIC CAPITAL LETTER CHE
+0x98	0x0428	#CYRILLIC CAPITAL LETTER SHA
+0x99	0x0429	#CYRILLIC CAPITAL LETTER SHCHA
+0x9a	0x042a	#CYRILLIC CAPITAL LETTER HARD SIGN
+0x9b	0x042b	#CYRILLIC CAPITAL LETTER YERU
+0x9c	0x042c	#CYRILLIC CAPITAL LETTER SOFT SIGN
+0x9d	0x042d	#CYRILLIC CAPITAL LETTER E
+0x9e	0x042e	#CYRILLIC CAPITAL LETTER YU
+0x9f	0x042f	#CYRILLIC CAPITAL LETTER YA
+0xa0	0x0430	#CYRILLIC SMALL LETTER A
+0xa1	0x0431	#CYRILLIC SMALL LETTER BE
+0xa2	0x0432	#CYRILLIC SMALL LETTER VE
+0xa3	0x0433	#CYRILLIC SMALL LETTER GHE
+0xa4	0x0434	#CYRILLIC SMALL LETTER DE
+0xa5	0x0435	#CYRILLIC SMALL LETTER IE
+0xa6	0x0436	#CYRILLIC SMALL LETTER ZHE
+0xa7	0x0437	#CYRILLIC SMALL LETTER ZE
+0xa8	0x0438	#CYRILLIC SMALL LETTER I
+0xa9	0x0439	#CYRILLIC SMALL LETTER SHORT I
+0xaa	0x043a	#CYRILLIC SMALL LETTER KA
+0xab	0x043b	#CYRILLIC SMALL LETTER EL
+0xac	0x043c	#CYRILLIC SMALL LETTER EM
+0xad	0x043d	#CYRILLIC SMALL LETTER EN
+0xae	0x043e	#CYRILLIC SMALL LETTER O
+0xaf	0x043f	#CYRILLIC SMALL LETTER PE
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x2561	#BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xb6	0x2562	#BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+0xb7	0x2556	#BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+0xb8	0x2555	#BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x255c	#BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+0xbe	0x255b	#BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x255e	#BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xc7	0x255f	#BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x2567	#BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xd0	0x2568	#BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xd1	0x2564	#BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+0xd2	0x2565	#BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+0xd3	0x2559	#BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xd4	0x2558	#BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xd5	0x2552	#BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xd6	0x2553	#BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+0xd7	0x256b	#BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+0xd8	0x256a	#BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x258c	#LEFT HALF BLOCK
+0xde	0x2590	#RIGHT HALF BLOCK
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x0440	#CYRILLIC SMALL LETTER ER
+0xe1	0x0441	#CYRILLIC SMALL LETTER ES
+0xe2	0x0442	#CYRILLIC SMALL LETTER TE
+0xe3	0x0443	#CYRILLIC SMALL LETTER U
+0xe4	0x0444	#CYRILLIC SMALL LETTER EF
+0xe5	0x0445	#CYRILLIC SMALL LETTER HA
+0xe6	0x0446	#CYRILLIC SMALL LETTER TSE
+0xe7	0x0447	#CYRILLIC SMALL LETTER CHE
+0xe8	0x0448	#CYRILLIC SMALL LETTER SHA
+0xe9	0x0449	#CYRILLIC SMALL LETTER SHCHA
+0xea	0x044a	#CYRILLIC SMALL LETTER HARD SIGN
+0xeb	0x044b	#CYRILLIC SMALL LETTER YERU
+0xec	0x044c	#CYRILLIC SMALL LETTER SOFT SIGN
+0xed	0x044d	#CYRILLIC SMALL LETTER E
+0xee	0x044e	#CYRILLIC SMALL LETTER YU
+0xef	0x044f	#CYRILLIC SMALL LETTER YA
+0xf0	0x0401	#CYRILLIC CAPITAL LETTER IO
+0xf1	0x0451	#CYRILLIC SMALL LETTER IO
+0xf2	0x0404	#CYRILLIC CAPITAL LETTER UKRAINIAN IE
+0xf3	0x0454	#CYRILLIC SMALL LETTER UKRAINIAN IE
+0xf4	0x0407	#CYRILLIC CAPITAL LETTER YI
+0xf5	0x0457	#CYRILLIC SMALL LETTER YI
+0xf6	0x040e	#CYRILLIC CAPITAL LETTER SHORT U
+0xf7	0x045e	#CYRILLIC SMALL LETTER SHORT U
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x2219	#BULLET OPERATOR
+0xfa	0x00b7	#MIDDLE DOT
+0xfb	0x221a	#SQUARE ROOT
+0xfc	0x2116	#NUMERO SIGN
+0xfd	0x00a4	#CURRENCY SIGN
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP869.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0a	0x000a	#LINE FEED
+0x0b	0x000b	#VERTICAL TABULATION
+0x0c	0x000c	#FORM FEED
+0x0d	0x000d	#CARRIAGE RETURN
+0x0e	0x000e	#SHIFT OUT
+0x0f	0x000f	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1a	0x001a	#SUBSTITUTE
+0x1b	0x001b	#ESCAPE
+0x1c	0x001c	#FILE SEPARATOR
+0x1d	0x001d	#GROUP SEPARATOR
+0x1e	0x001e	#RECORD SEPARATOR
+0x1f	0x001f	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2a	0x002a	#ASTERISK
+0x2b	0x002b	#PLUS SIGN
+0x2c	0x002c	#COMMA
+0x2d	0x002d	#HYPHEN-MINUS
+0x2e	0x002e	#FULL STOP
+0x2f	0x002f	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3a	0x003a	#COLON
+0x3b	0x003b	#SEMICOLON
+0x3c	0x003c	#LESS-THAN SIGN
+0x3d	0x003d	#EQUALS SIGN
+0x3e	0x003e	#GREATER-THAN SIGN
+0x3f	0x003f	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4a	0x004a	#LATIN CAPITAL LETTER J
+0x4b	0x004b	#LATIN CAPITAL LETTER K
+0x4c	0x004c	#LATIN CAPITAL LETTER L
+0x4d	0x004d	#LATIN CAPITAL LETTER M
+0x4e	0x004e	#LATIN CAPITAL LETTER N
+0x4f	0x004f	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5a	0x005a	#LATIN CAPITAL LETTER Z
+0x5b	0x005b	#LEFT SQUARE BRACKET
+0x5c	0x005c	#REVERSE SOLIDUS
+0x5d	0x005d	#RIGHT SQUARE BRACKET
+0x5e	0x005e	#CIRCUMFLEX ACCENT
+0x5f	0x005f	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6a	0x006a	#LATIN SMALL LETTER J
+0x6b	0x006b	#LATIN SMALL LETTER K
+0x6c	0x006c	#LATIN SMALL LETTER L
+0x6d	0x006d	#LATIN SMALL LETTER M
+0x6e	0x006e	#LATIN SMALL LETTER N
+0x6f	0x006f	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7a	0x007a	#LATIN SMALL LETTER Z
+0x7b	0x007b	#LEFT CURLY BRACKET
+0x7c	0x007c	#VERTICAL LINE
+0x7d	0x007d	#RIGHT CURLY BRACKET
+0x7e	0x007e	#TILDE
+0x7f	0x007f	#DELETE
+0x80		#UNDEFINED
+0x81		#UNDEFINED
+0x82		#UNDEFINED
+0x83		#UNDEFINED
+0x84		#UNDEFINED
+0x85		#UNDEFINED
+0x86	0x0386	#GREEK CAPITAL LETTER ALPHA WITH TONOS
+0x87		#UNDEFINED
+0x88	0x00b7	#MIDDLE DOT
+0x89	0x00ac	#NOT SIGN
+0x8a	0x00a6	#BROKEN BAR
+0x8b	0x2018	#LEFT SINGLE QUOTATION MARK
+0x8c	0x2019	#RIGHT SINGLE QUOTATION MARK
+0x8d	0x0388	#GREEK CAPITAL LETTER EPSILON WITH TONOS
+0x8e	0x2015	#HORIZONTAL BAR
+0x8f	0x0389	#GREEK CAPITAL LETTER ETA WITH TONOS
+0x90	0x038a	#GREEK CAPITAL LETTER IOTA WITH TONOS
+0x91	0x03aa	#GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+0x92	0x038c	#GREEK CAPITAL LETTER OMICRON WITH TONOS
+0x93		#UNDEFINED
+0x94		#UNDEFINED
+0x95	0x038e	#GREEK CAPITAL LETTER UPSILON WITH TONOS
+0x96	0x03ab	#GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+0x97	0x00a9	#COPYRIGHT SIGN
+0x98	0x038f	#GREEK CAPITAL LETTER OMEGA WITH TONOS
+0x99	0x00b2	#SUPERSCRIPT TWO
+0x9a	0x00b3	#SUPERSCRIPT THREE
+0x9b	0x03ac	#GREEK SMALL LETTER ALPHA WITH TONOS
+0x9c	0x00a3	#POUND SIGN
+0x9d	0x03ad	#GREEK SMALL LETTER EPSILON WITH TONOS
+0x9e	0x03ae	#GREEK SMALL LETTER ETA WITH TONOS
+0x9f	0x03af	#GREEK SMALL LETTER IOTA WITH TONOS
+0xa0	0x03ca	#GREEK SMALL LETTER IOTA WITH DIALYTIKA
+0xa1	0x0390	#GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+0xa2	0x03cc	#GREEK SMALL LETTER OMICRON WITH TONOS
+0xa3	0x03cd	#GREEK SMALL LETTER UPSILON WITH TONOS
+0xa4	0x0391	#GREEK CAPITAL LETTER ALPHA
+0xa5	0x0392	#GREEK CAPITAL LETTER BETA
+0xa6	0x0393	#GREEK CAPITAL LETTER GAMMA
+0xa7	0x0394	#GREEK CAPITAL LETTER DELTA
+0xa8	0x0395	#GREEK CAPITAL LETTER EPSILON
+0xa9	0x0396	#GREEK CAPITAL LETTER ZETA
+0xaa	0x0397	#GREEK CAPITAL LETTER ETA
+0xab	0x00bd	#VULGAR FRACTION ONE HALF
+0xac	0x0398	#GREEK CAPITAL LETTER THETA
+0xad	0x0399	#GREEK CAPITAL LETTER IOTA
+0xae	0x00ab	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xaf	0x00bb	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xb0	0x2591	#LIGHT SHADE
+0xb1	0x2592	#MEDIUM SHADE
+0xb2	0x2593	#DARK SHADE
+0xb3	0x2502	#BOX DRAWINGS LIGHT VERTICAL
+0xb4	0x2524	#BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0xb5	0x039a	#GREEK CAPITAL LETTER KAPPA
+0xb6	0x039b	#GREEK CAPITAL LETTER LAMDA
+0xb7	0x039c	#GREEK CAPITAL LETTER MU
+0xb8	0x039d	#GREEK CAPITAL LETTER NU
+0xb9	0x2563	#BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xba	0x2551	#BOX DRAWINGS DOUBLE VERTICAL
+0xbb	0x2557	#BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xbc	0x255d	#BOX DRAWINGS DOUBLE UP AND LEFT
+0xbd	0x039e	#GREEK CAPITAL LETTER XI
+0xbe	0x039f	#GREEK CAPITAL LETTER OMICRON
+0xbf	0x2510	#BOX DRAWINGS LIGHT DOWN AND LEFT
+0xc0	0x2514	#BOX DRAWINGS LIGHT UP AND RIGHT
+0xc1	0x2534	#BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0xc2	0x252c	#BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0xc3	0x251c	#BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0xc4	0x2500	#BOX DRAWINGS LIGHT HORIZONTAL
+0xc5	0x253c	#BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0xc6	0x03a0	#GREEK CAPITAL LETTER PI
+0xc7	0x03a1	#GREEK CAPITAL LETTER RHO
+0xc8	0x255a	#BOX DRAWINGS DOUBLE UP AND RIGHT
+0xc9	0x2554	#BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xca	0x2569	#BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xcb	0x2566	#BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xcc	0x2560	#BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xcd	0x2550	#BOX DRAWINGS DOUBLE HORIZONTAL
+0xce	0x256c	#BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xcf	0x03a3	#GREEK CAPITAL LETTER SIGMA
+0xd0	0x03a4	#GREEK CAPITAL LETTER TAU
+0xd1	0x03a5	#GREEK CAPITAL LETTER UPSILON
+0xd2	0x03a6	#GREEK CAPITAL LETTER PHI
+0xd3	0x03a7	#GREEK CAPITAL LETTER CHI
+0xd4	0x03a8	#GREEK CAPITAL LETTER PSI
+0xd5	0x03a9	#GREEK CAPITAL LETTER OMEGA
+0xd6	0x03b1	#GREEK SMALL LETTER ALPHA
+0xd7	0x03b2	#GREEK SMALL LETTER BETA
+0xd8	0x03b3	#GREEK SMALL LETTER GAMMA
+0xd9	0x2518	#BOX DRAWINGS LIGHT UP AND LEFT
+0xda	0x250c	#BOX DRAWINGS LIGHT DOWN AND RIGHT
+0xdb	0x2588	#FULL BLOCK
+0xdc	0x2584	#LOWER HALF BLOCK
+0xdd	0x03b4	#GREEK SMALL LETTER DELTA
+0xde	0x03b5	#GREEK SMALL LETTER EPSILON
+0xdf	0x2580	#UPPER HALF BLOCK
+0xe0	0x03b6	#GREEK SMALL LETTER ZETA
+0xe1	0x03b7	#GREEK SMALL LETTER ETA
+0xe2	0x03b8	#GREEK SMALL LETTER THETA
+0xe3	0x03b9	#GREEK SMALL LETTER IOTA
+0xe4	0x03ba	#GREEK SMALL LETTER KAPPA
+0xe5	0x03bb	#GREEK SMALL LETTER LAMDA
+0xe6	0x03bc	#GREEK SMALL LETTER MU
+0xe7	0x03bd	#GREEK SMALL LETTER NU
+0xe8	0x03be	#GREEK SMALL LETTER XI
+0xe9	0x03bf	#GREEK SMALL LETTER OMICRON
+0xea	0x03c0	#GREEK SMALL LETTER PI
+0xeb	0x03c1	#GREEK SMALL LETTER RHO
+0xec	0x03c3	#GREEK SMALL LETTER SIGMA
+0xed	0x03c2	#GREEK SMALL LETTER FINAL SIGMA
+0xee	0x03c4	#GREEK SMALL LETTER TAU
+0xef	0x0384	#GREEK TONOS
+0xf0	0x00ad	#SOFT HYPHEN
+0xf1	0x00b1	#PLUS-MINUS SIGN
+0xf2	0x03c5	#GREEK SMALL LETTER UPSILON
+0xf3	0x03c6	#GREEK SMALL LETTER PHI
+0xf4	0x03c7	#GREEK SMALL LETTER CHI
+0xf5	0x00a7	#SECTION SIGN
+0xf6	0x03c8	#GREEK SMALL LETTER PSI
+0xf7	0x0385	#GREEK DIALYTIKA TONOS
+0xf8	0x00b0	#DEGREE SIGN
+0xf9	0x00a8	#DIAERESIS
+0xfa	0x03c9	#GREEK SMALL LETTER OMEGA
+0xfb	0x03cb	#GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+0xfc	0x03b0	#GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+0xfd	0x03ce	#GREEK SMALL LETTER OMEGA WITH TONOS
+0xfe	0x25a0	#BLACK SQUARE
+0xff	0x00a0	#NO-BREAK SPACE

Data/Encoding/CP874.mapping

@@ -0,0 +1,256 @@
+0x00	0x0000	#NULL
+0x01	0x0001	#START OF HEADING
+0x02	0x0002	#START OF TEXT
+0x03	0x0003	#END OF TEXT
+0x04	0x0004	#END OF TRANSMISSION
+0x05	0x0005	#ENQUIRY
+0x06	0x0006	#ACKNOWLEDGE
+0x07	0x0007	#BELL
+0x08	0x0008	#BACKSPACE
+0x09	0x0009	#HORIZONTAL TABULATION
+0x0A	0x000A	#LINE FEED
+0x0B	0x000B	#VERTICAL TABULATION
+0x0C	0x000C	#FORM FEED
+0x0D	0x000D	#CARRIAGE RETURN
+0x0E	0x000E	#SHIFT OUT
+0x0F	0x000F	#SHIFT IN
+0x10	0x0010	#DATA LINK ESCAPE
+0x11	0x0011	#DEVICE CONTROL ONE
+0x12	0x0012	#DEVICE CONTROL TWO
+0x13	0x0013	#DEVICE CONTROL THREE
+0x14	0x0014	#DEVICE CONTROL FOUR
+0x15	0x0015	#NEGATIVE ACKNOWLEDGE
+0x16	0x0016	#SYNCHRONOUS IDLE
+0x17	0x0017	#END OF TRANSMISSION BLOCK
+0x18	0x0018	#CANCEL
+0x19	0x0019	#END OF MEDIUM
+0x1A	0x001A	#SUBSTITUTE
+0x1B	0x001B	#ESCAPE
+0x1C	0x001C	#FILE SEPARATOR
+0x1D	0x001D	#GROUP SEPARATOR
+0x1E	0x001E	#RECORD SEPARATOR
+0x1F	0x001F	#UNIT SEPARATOR
+0x20	0x0020	#SPACE
+0x21	0x0021	#EXCLAMATION MARK
+0x22	0x0022	#QUOTATION MARK
+0x23	0x0023	#NUMBER SIGN
+0x24	0x0024	#DOLLAR SIGN
+0x25	0x0025	#PERCENT SIGN
+0x26	0x0026	#AMPERSAND
+0x27	0x0027	#APOSTROPHE
+0x28	0x0028	#LEFT PARENTHESIS
+0x29	0x0029	#RIGHT PARENTHESIS
+0x2A	0x002A	#ASTERISK
+0x2B	0x002B	#PLUS SIGN
+0x2C	0x002C	#COMMA
+0x2D	0x002D	#HYPHEN-MINUS
+0x2E	0x002E	#FULL STOP
+0x2F	0x002F	#SOLIDUS
+0x30	0x0030	#DIGIT ZERO
+0x31	0x0031	#DIGIT ONE
+0x32	0x0032	#DIGIT TWO
+0x33	0x0033	#DIGIT THREE
+0x34	0x0034	#DIGIT FOUR
+0x35	0x0035	#DIGIT FIVE
+0x36	0x0036	#DIGIT SIX
+0x37	0x0037	#DIGIT SEVEN
+0x38	0x0038	#DIGIT EIGHT
+0x39	0x0039	#DIGIT NINE
+0x3A	0x003A	#COLON
+0x3B	0x003B	#SEMICOLON
+0x3C	0x003C	#LESS-THAN SIGN
+0x3D	0x003D	#EQUALS SIGN
+0x3E	0x003E	#GREATER-THAN SIGN
+0x3F	0x003F	#QUESTION MARK
+0x40	0x0040	#COMMERCIAL AT
+0x41	0x0041	#LATIN CAPITAL LETTER A
+0x42	0x0042	#LATIN CAPITAL LETTER B
+0x43	0x0043	#LATIN CAPITAL LETTER C
+0x44	0x0044	#LATIN CAPITAL LETTER D
+0x45	0x0045	#LATIN CAPITAL LETTER E
+0x46	0x0046	#LATIN CAPITAL LETTER F
+0x47	0x0047	#LATIN CAPITAL LETTER G
+0x48	0x0048	#LATIN CAPITAL LETTER H
+0x49	0x0049	#LATIN CAPITAL LETTER I
+0x4A	0x004A	#LATIN CAPITAL LETTER J
+0x4B	0x004B	#LATIN CAPITAL LETTER K
+0x4C	0x004C	#LATIN CAPITAL LETTER L
+0x4D	0x004D	#LATIN CAPITAL LETTER M
+0x4E	0x004E	#LATIN CAPITAL LETTER N
+0x4F	0x004F	#LATIN CAPITAL LETTER O
+0x50	0x0050	#LATIN CAPITAL LETTER P
+0x51	0x0051	#LATIN CAPITAL LETTER Q
+0x52	0x0052	#LATIN CAPITAL LETTER R
+0x53	0x0053	#LATIN CAPITAL LETTER S
+0x54	0x0054	#LATIN CAPITAL LETTER T
+0x55	0x0055	#LATIN CAPITAL LETTER U
+0x56	0x0056	#LATIN CAPITAL LETTER V
+0x57	0x0057	#LATIN CAPITAL LETTER W
+0x58	0x0058	#LATIN CAPITAL LETTER X
+0x59	0x0059	#LATIN CAPITAL LETTER Y
+0x5A	0x005A	#LATIN CAPITAL LETTER Z
+0x5B	0x005B	#LEFT SQUARE BRACKET
+0x5C	0x005C	#REVERSE SOLIDUS
+0x5D	0x005D	#RIGHT SQUARE BRACKET
+0x5E	0x005E	#CIRCUMFLEX ACCENT
+0x5F	0x005F	#LOW LINE
+0x60	0x0060	#GRAVE ACCENT
+0x61	0x0061	#LATIN SMALL LETTER A
+0x62	0x0062	#LATIN SMALL LETTER B
+0x63	0x0063	#LATIN SMALL LETTER C
+0x64	0x0064	#LATIN SMALL LETTER D
+0x65	0x0065	#LATIN SMALL LETTER E
+0x66	0x0066	#LATIN SMALL LETTER F
+0x67	0x0067	#LATIN SMALL LETTER G
+0x68	0x0068	#LATIN SMALL LETTER H
+0x69	0x0069	#LATIN SMALL LETTER I
+0x6A	0x006A	#LATIN SMALL LETTER J
+0x6B	0x006B	#LATIN SMALL LETTER K
+0x6C	0x006C	#LATIN SMALL LETTER L
+0x6D	0x006D	#LATIN SMALL LETTER M
+0x6E	0x006E	#LATIN SMALL LETTER N
+0x6F	0x006F	#LATIN SMALL LETTER O
+0x70	0x0070	#LATIN SMALL LETTER P
+0x71	0x0071	#LATIN SMALL LETTER Q
+0x72	0x0072	#LATIN SMALL LETTER R
+0x73	0x0073	#LATIN SMALL LETTER S
+0x74	0x0074	#LATIN SMALL LETTER T
+0x75	0x0075	#LATIN SMALL LETTER U
+0x76	0x0076	#LATIN SMALL LETTER V
+0x77	0x0077	#LATIN SMALL LETTER W
+0x78	0x0078	#LATIN SMALL LETTER X
+0x79	0x0079	#LATIN SMALL LETTER Y
+0x7A	0x007A	#LATIN SMALL LETTER Z
+0x7B	0x007B	#LEFT CURLY BRACKET
+0x7C	0x007C	#VERTICAL LINE
+0x7D	0x007D	#RIGHT CURLY BRACKET
+0x7E	0x007E	#TILDE
+0x7F	0x007F	#DELETE
+0x80	0x20AC	#EURO SIGN
+0x81	      	#UNDEFINED
+0x82	      	#UNDEFINED
+0x83	      	#UNDEFINED
+0x84	      	#UNDEFINED
+0x85	0x2026	#HORIZONTAL ELLIPSIS
+0x86	      	#UNDEFINED
+0x87	      	#UNDEFINED
+0x88	      	#UNDEFINED
+0x89	      	#UNDEFINED
+0x8A	      	#UNDEFINED
+0x8B	      	#UNDEFINED
+0x8C	      	#UNDEFINED
+0x8D	      	#UNDEFINED
+0x8E	      	#UNDEFINED
+0x8F	      	#UNDEFINED
+0x90	      	#UNDEFINED
+0x91	0x2018	#LEFT SINGLE QUOTATION MARK
+0x92	0x2019	#RIGHT SINGLE QUOTATION MARK
+0x93	0x201C	#LEFT DOUBLE QUOTATION MARK
+0x94	0x201D	#RIGHT DOUBLE QUOTATION MARK
+0x95	0x2022	#BULLET
+0x96	0x2013	#EN DASH
+0x97	0x2014	#EM DASH
+0x98	      	#UNDEFINED
+0x99	      	#UNDEFINED
+0x9A	      	#UNDEFINED
+0x9B	      	#UNDEFINED
+0x9C	      	#UNDEFINED
+0x9D	      	#UNDEFINED
+0x9E	      	#UNDEFINED
+0x9F	      	#UNDEFINED
+0xA0	0x00A0	#NO-BREAK SPACE
+0xA1	0x0E01	#THAI CHARACTER KO KAI
+0xA2	0x0E02	#THAI CHARACTER KHO KHAI
+0xA3	0x0E03	#THAI CHARACTER KHO KHUAT
+0xA4	0x0E04	#THAI CHARACTER KHO KHWAI
+0xA5	0x0E05	#THAI CHARACTER KHO KHON
+0xA6	0x0E06	#THAI CHARACTER KHO RAKHANG
+0xA7	0x0E07	#THAI CHARACTER NGO NGU
+0xA8	0x0E08	#THAI CHARACTER CHO CHAN
+0xA9	0x0E09	#THAI CHARACTER CHO CHING
+0xAA	0x0E0A	#THAI CHARACTER CHO CHANG
+0xAB	0x0E0B	#THAI CHARACTER SO SO
+0xAC	0x0E0C	#THAI CHARACTER CHO CHOE
+0xAD	0x0E0D	#THAI CHARACTER YO YING
+0xAE	0x0E0E	#THAI CHARACTER DO CHADA
+0xAF	0x0E0F	#THAI CHARACTER TO PATAK
+0xB0	0x0E10	#THAI CHARACTER THO THAN
+0xB1	0x0E11	#THAI CHARACTER THO NANGMONTHO
+0xB2	0x0E12	#THAI CHARACTER THO PHUTHAO
+0xB3	0x0E13	#THAI CHARACTER NO NEN
+0xB4	0x0E14	#THAI CHARACTER DO DEK
+0xB5	0x0E15	#THAI CHARACTER TO TAO
+0xB6	0x0E16	#THAI CHARACTER THO THUNG
+0xB7	0x0E17	#THAI CHARACTER THO THAHAN
+0xB8	0x0E18	#THAI CHARACTER THO THONG
+0xB9	0x0E19	#THAI CHARACTER NO NU
+0xBA	0x0E1A	#THAI CHARACTER BO BAIMAI
+0xBB	0x0E1B	#THAI CHARACTER PO PLA
+0xBC	0x0E1C	#THAI CHARACTER PHO PHUNG
+0xBD	0x0E1D	#THAI CHARACTER FO FA
+0xBE	0x0E1E	#THAI CHARACTER PHO PHAN
+0xBF	0x0E1F	#THAI CHARACTER FO FAN
+0xC0	0x0E20	#THAI CHARACTER PHO SAMPHAO
+0xC1	0x0E21	#THAI CHARACTER MO MA
+0xC2	0x0E22	#THAI CHARACTER YO YAK
+0xC3	0x0E23	#THAI CHARACTER RO RUA
+0xC4	0x0E24	#THAI CHARACTER RU
+0xC5	0x0E25	#THAI CHARACTER LO LING
+0xC6	0x0E26	#THAI CHARACTER LU
+0xC7	0x0E27	#THAI CHARACTER WO WAEN
+0xC8	0x0E28	#THAI CHARACTER SO SALA
+0xC9	0x0E29	#THAI CHARACTER SO RUSI
+0xCA	0x0E2A	#THAI CHARACTER SO SUA
+0xCB	0x0E2B	#THAI CHARACTER HO HIP
+0xCC	0x0E2C	#THAI CHARACTER LO CHULA
+0xCD	0x0E2D	#THAI CHARACTER O ANG
+0xCE	0x0E2E	#THAI CHARACTER HO NOKHUK
+0xCF	0x0E2F	#THAI CHARACTER PAIYANNOI
+0xD0	0x0E30	#THAI CHARACTER SARA A
+0xD1	0x0E31	#THAI CHARACTER MAI HAN-AKAT
+0xD2	0x0E32	#THAI CHARACTER SARA AA
+0xD3	0x0E33	#THAI CHARACTER SARA AM
+0xD4	0x0E34	#THAI CHARACTER SARA I
+0xD5	0x0E35	#THAI CHARACTER SARA II
+0xD6	0x0E36	#THAI CHARACTER SARA UE
+0xD7	0x0E37	#THAI CHARACTER SARA UEE
+0xD8	0x0E38	#THAI CHARACTER SARA U
+0xD9	0x0E39	#THAI CHARACTER SARA UU
+0xDA	0x0E3A	#THAI CHARACTER PHINTHU
+0xDB	      	#UNDEFINED
+0xDC	      	#UNDEFINED
+0xDD	      	#UNDEFINED
+0xDE	      	#UNDEFINED
+0xDF	0x0E3F	#THAI CURRENCY SYMBOL BAHT
+0xE0	0x0E40	#THAI CHARACTER SARA E
+0xE1	0x0E41	#THAI CHARACTER SARA AE
+0xE2	0x0E42	#THAI CHARACTER SARA O
+0xE3	0x0E43	#THAI CHARACTER SARA AI MAIMUAN
+0xE4	0x0E44	#THAI CHARACTER SARA AI MAIMALAI
+0xE5	0x0E45	#THAI CHARACTER LAKKHANGYAO
+0xE6	0x0E46	#THAI CHARACTER MAIYAMOK
+0xE7	0x0E47	#THAI CHARACTER MAITAIKHU
+0xE8	0x0E48	#THAI CHARACTER MAI EK
+0xE9	0x0E49	#THAI CHARACTER MAI THO
+0xEA	0x0E4A	#THAI CHARACTER MAI TRI
+0xEB	0x0E4B	#THAI CHARACTER MAI CHATTAWA
+0xEC	0x0E4C	#THAI CHARACTER THANTHAKHAT
+0xED	0x0E4D	#THAI CHARACTER NIKHAHIT
+0xEE	0x0E4E	#THAI CHARACTER YAMAKKAN
+0xEF	0x0E4F	#THAI CHARACTER FONGMAN
+0xF0	0x0E50	#THAI DIGIT ZERO
+0xF1	0x0E51	#THAI DIGIT ONE
+0xF2	0x0E52	#THAI DIGIT TWO
+0xF3	0x0E53	#THAI DIGIT THREE
+0xF4	0x0E54	#THAI DIGIT FOUR
+0xF5	0x0E55	#THAI DIGIT FIVE
+0xF6	0x0E56	#THAI DIGIT SIX
+0xF7	0x0E57	#THAI DIGIT SEVEN
+0xF8	0x0E58	#THAI DIGIT EIGHT
+0xF9	0x0E59	#THAI DIGIT NINE
+0xFA	0x0E5A	#THAI CHARACTER ANGKHANKHU
+0xFB	0x0E5B	#THAI CHARACTER KHOMUT
+0xFC	      	#UNDEFINED
+0xFD	      	#UNDEFINED
+0xFE	      	#UNDEFINED
+0xFF	      	#UNDEFINED

Data/Encoding/Exception.hs

@@ -11,7 +11,7 @@ import Control.Monad.Identity
 data EncodingException
     = HasNoRepresentation Char	-- ^ Thrown if a specific character
 				--   is not representable in an encoding.
-    deriving (Eq,Show,Typeable)
+    deriving (Eq,Ord,Show,Read,Typeable)
 
 instance Exception EncodingException
 
@@ -25,6 +25,6 @@ data DecodingException
     | OutOfRange		-- ^ the decoded value was out of the unicode range
     | IllegalRepresentation [Word8]	-- ^ The character sequence encodes a
 					--   character, but is illegal.
-    deriving (Eq,Show,Typeable)
+    deriving (Eq,Ord,Show,Read,Typeable)
 
 instance Exception DecodingException

Data/Encoding/GB18030.hs

@@ -1,236 +0,0 @@
-{-# LANGUAGE CPP,DeriveDataTypeable #-}
-{- | GB18030 is a chinese character encoding that is mandatory in china (if you
- -   don\'t implement it, you\'re not allowed to sell your software there).
- -}
-
-module Data.Encoding.GB18030
-	(GB18030(..))
-	where
-
-import Control.Throws
-import Data.Char (chr,ord)
-import Data.Word
-import Data.Bits
-import Data.Encoding.Base
-import Data.Encoding.ByteSource
-import Data.Encoding.ByteSink
-import Data.Encoding.Exception
-import Data.ByteString (ByteString)
-import qualified Data.ByteString as BS
-import Data.Typeable
-
-#if __GLASGOW_HASKELL__>=608
-import Data.ByteString.Unsafe (unsafeIndex)
-#else
-import Data.ByteString.Base (unsafeIndex)
-#endif
-
-import Data.Encoding.GB18030Data
-
-data GB18030 = GB18030 deriving (Eq,Show,Typeable)
-
-instance Encoding GB18030 where
-    decodeChar _ = do
-      w1 <- fetchWord8
-      case () of
-        _
-          | w1 <= 0x80 -> return (chr $ fromIntegral w1) -- it's ascii
-          | w1 <= 0xFE -> do
-                     w2 <- fetchWord8
-                     case () of
-                       _
-                         | w2 < 0x30 -> throwException (IllegalCharacter w2)
-                         | w2 <= 0x39 -> do
-                               w3 <- fetchWord8
-                               case () of
-                                 _
-                                   | w3 < 0x81 -> throwException (IllegalCharacter w3)
-                                   | w3 <= 0xFE -> do
-                                          w4 <- fetchWord8
-                                          case () of
-                                            _
-                                              | w4 < 0x30 -> throwException (IllegalCharacter w4)
-                                              | w4 <= 0x39 -> decodeGBFour $ linear w1 w2 w3 w4
-                                              | otherwise -> throwException (IllegalCharacter w4)
-                                   | otherwise -> throwException (IllegalCharacter w3)
-                         | w2 <= 0x7E -> return $ decodeGBTwo $ linear2 w1 w2
-                         | w2 == 0x7F -> throwException (IllegalCharacter w2)
-                         | w2 <= 0xFE -> return $ decodeGBTwo $ linear2 w1 w2
-                         | otherwise -> throwException (IllegalCharacter w2)
-          | otherwise -> throwException (IllegalCharacter w1)
-    {- How this works: The nested if-structures form an binary tree over the
-     - encoding range.
-     -}
-    encodeChar _ ch = if ch<='\x4946'					-- 1
-	              then (if ch<='\x4055'					-- 2
-		            then (if ch<='\x2E80'				-- 3
-			          then (if ch<='\x200F'			-- 4
-				        then (if ch<'\x0452'
-					      then arr 0x0000 arr1
-					      else range range1)
-				        else (if ch<'\x2643'
-					      then arr 0x2010 arr2
-					else range range2))
-			else (if ch<='\x3917'			-- 4
-			      then (if ch<'\x361B'
-				    then arr 0x2E81 arr3
-				    else range range3)
-			      else (if ch<'\x3CE1'
-				    then arr 0x3918 arr4
-				    else range range4)))
-		else (if ch<='\x464B'				-- 3
-		      then (if ch<='\x4336'			-- 4
-			    then (if ch<'\x4160'
-				  then arr 0x4056 arr5
-				  else range range5)
-			    else (if ch<'\x44D7'
-				  then arr 0x4337 arr6
-				  else range range6))
-			else (if ch<'\x478E'
-			      then arr 0x464C arr7
-			      else range range7)))
-	else (if ch<='\xF92B'					-- 2
-	      then (if ch<='\xD7FF'				-- 3
-		    then (if ch<='\x4C76'			-- 4
-			  then (if ch<'\x49B8'
-				then arr 0x4947 arr8
-				else range range8)
-			  else (if ch<'\x9FA6'
-				then arr 0x4C77 arr9
-				else range range9))
-			else (if ch<'\xE865'
-			      then arr 0xD800 arr10
-			      else range range10))
-		else (if ch<='\xFFFF'				-- 3
-		      then (if ch<='\xFE2F'			-- 4
-			    then (if ch<'\xFA2A'
-				  then arr 0xF92C arr11
-				  else range range11)
-			    else (if ch<'\xFFE6'
-				  then arr 0xFE30 arr12
-				  else range range12))
-			else (if ch<='\x10FFFF'			-- 4
-			      then range range13
-			      else throwException (HasNoRepresentation ch))))
-        where
-	  range r = let (w1,w2,w3,w4) = delinear (ord ch + r)
-	            in pushWord8 w1 >> pushWord8 w2 >> pushWord8 w3 >> pushWord8 w4
-	  arr off a = let ind = (ord ch - off)*5
-	                  w1 = unsafeIndex a (ind+1)
-	                  w2 = unsafeIndex a (ind+2)
-	                  w3 = unsafeIndex a (ind+3)
-	                  w4 = unsafeIndex a (ind+4)
-		      in do
-                        pushWord8 w1
-                        case unsafeIndex a ind of
-		          1 -> return ()
-	                  2 -> pushWord8 w2
-	                  3 -> pushWord8 w2 >> pushWord8 w3
-	                  4 -> pushWord8 w2 >> pushWord8 w3 >> pushWord8 w4
-
-linear :: Word8 -> Word8 -> Word8 -> Word8 -> Int
-linear w1 w2 w3 w4
-	= (fromIntegral (w4-0x30))
-	+ (fromIntegral (w3-0x81))*10
-	+ (fromIntegral (w2-0x30))*1260
-	+ (fromIntegral (w1-0x81))*12600
-
-linear2 :: Word8 -> Word8 -> Int
-linear2 w1 w2 = (fromIntegral (w2 - (if w2<=0x7E
-	then 0x40
-	else 0x41)))
-	+ (fromIntegral (w1-0x81))*190
-
-delinear :: Int -> (Word8,Word8,Word8,Word8)
-delinear n = let
-	(w1,n1) = n  `divMod` 12600
-	(w2,n2) = n1 `divMod`  1260
-	(w3,n3) = n2 `divMod`    10
-	w4      = n3
-	in (fromIntegral w1+0x81
-	   ,fromIntegral w2+0x30
-	   ,fromIntegral w3+0x81
-	   ,fromIntegral w4+0x30)
-
-decodeGBTwo :: Int -> Char
-decodeGBTwo n = let
-	rn = n*2
-	w1 = unsafeIndex rrarr rn
-	w2 = unsafeIndex rrarr (rn+1)
-	in chr $ ((fromIntegral w1) `shiftL` 8) .|. (fromIntegral w2)
-
-decodeGBFour :: ByteSource m => Int -> m Char
-decodeGBFour v = if v<=17858				-- 1
-	then (if v<=15582					-- 2
-		then (if v<=11328				-- 3
-			then (if v<=7921			-- 4
-				then (if v<820
-					then arr 0 rarr1
-					else range range1)
-				else (if v<9219
-					then arr 7922 rarr2
-					else range range2))
-			else (if v<=13737			-- 4
-				then (if v<12973
-					then arr 11329 rarr3
-					else range range3)
-				else (if v<14698
-					then arr 13738 rarr4
-					else range range4)))
-		else (if v<=17101				-- 3
-			then (if v<=16317			-- 4
-				then (if v<15847
-					then arr 15583 rarr5
-					else range range5)
-				else (if v<16729
-					then arr 16318 rarr6
-					else range range6))
-			else (if v<17418
-				then arr 17102 rarr7
-				else range range7)))
-	else (if v<=37844					-- 2
-		then (if v<=33468				-- 3
-			then (if v<=18663			-- 4
-				then (if v<17961
-					then arr 17859 rarr8
-					else range range8)
-				else (if v<19043
-					then arr 18664 rarr9
-					else range range9))
-			else (if v<33550
-				then arr 33469 rarr10
-				else range range10))
-		else (if v<=39419				-- 3
-			then (if v<=39107			-- 4
-				then (if v<38078
-					then arr 37845 rarr11
-					else range range11)
-				else (if v<39394
-					then arr 39108 rarr12
-					else range range12))
-			else (if v<=1237575 && v>=189000
-				then range range13
-				else throwException OutOfRange)))
-	where
-	arr off a = let
-		v' = (v-off)*2
-		w1 = unsafeIndex a v'
-		w2 = unsafeIndex a (v'+1)
-		in return $ chr $ ((fromIntegral w1) `shiftL` 8)
-		      .|. (fromIntegral w2)
-	range r = return $ chr (v-r)
-
-range1,range2,range3,range4,range5,range6,range7,range8,range9,range10,range11,range12,range13 :: Int
-range1 = -286
-range2 = -576
-range3 = -878
-range4 = -887
-range5 = -889
-range6 = -894
-range7 = -900
-range8 = -911
-range9 = -21827
-range10 = -25943
-range11 = -25964
-range12 = -26116
-range13 = 123464

Data/Encoding/GB18030.xml

@@ -1,6 +1,8 @@
 <?xml version="1.0" encoding="UTF-8" ?>
 <!DOCTYPE characterMapping SYSTEM "http://www.unicode.org/unicode/reports/tr22/CharacterMapping.dtd">
-<characterMapping id="gb-18030-2000" version="3">
+<characterMapping
+   id="gb-18030-2000" version="3"
+   description="GB18030 is a chinese character encoding that is mandatory in china (if you - don't implement it, you're not allowed to sell your software there).">
  <history>
   <modified version="3" date="2001-02-21">
    0x80 appears to be a valid (and unassigned) single-byte code, added to the validity.

Data/Encoding/Helper/Data.hs

@@ -1,116 +0,0 @@
-{- This module is used to create a haskell file with static address-arrays in it -}
-
-module Data.Encoding.Helper.Data where
-
-import Data.Char (ord)
-import Data.Word (Word8)
-import Data.Ord (comparing)
-import Data.Bits (shiftR)
-import Data.List (sortBy,genericLength)
-import Data.Encoding.Helper.XML
-
-linear :: Word8 -> Word8 -> Word8 -> Word8 -> Int
-linear w1 w2 w3 w4
-	= (fromIntegral (w4-0x30))
-	+ (fromIntegral (w3-0x81))*10
-	+ (fromIntegral (w2-0x30))*1260
-	+ (fromIntegral (w1-0x81))*12600
-
-linear2 :: Word8 -> Word8 -> Int
-linear2 w1 w2 = (fromIntegral (w2 - (if w2<=0x7E
-	then 0x40
-	else 0x41)))
-	+ (fromIntegral (w1-0x81))*190
-
-createStandardModule :: IO ()
-createStandardModule = do
-	let fn = "gb-18030-2000.xml"
-	str <- readFile fn
-	writeFile "Data/Encoding/GB18030Data.hs" $ createModuleFromFile fn str standardRanges standardRRanges
-
-standardRanges =
-	[('\x0000','\x0451')
-	,('\x2010','\x2642')
-	,('\x2E81','\x361A')
-	,('\x3918','\x3CE0')
-	,('\x4056','\x415F')
-	,('\x4337','\x44D6')
-	,('\x464C','\x478D')
-	,('\x4947','\x49B7')
-	,('\x4C77','\x9FA5')
-	,('\xD800','\xE864')
-	,('\xF92C','\xFA29')
-	,('\xFE30','\xFFE5')
-	]
-
-standardRRanges =
-	[(    0,  819)
-	,( 7922, 9218)
-	,(11329,12972)
-	,(13738,14697)
-	,(15583,15846)
-	,(16318,16728)
-	,(17102,17417)
-	,(17859,17960)
-	,(18664,19042)
-	,(33469,33549)
-	,(37845,38077)
-	,(39108,39393)
-	,(39420,188999)]
-
-createModuleFromFile :: String -> String -> [(Char,Char)] -> [(Int,Int)] -> String
-createModuleFromFile name str = createModule (readDecodeTable name str)
-
-createModule :: [(Char,[Word8])] -> [(Char,Char)] -> [(Int,Int)] -> String
-createModule mp ranges rranges = unlines $
-	["{-# LANGUAGE CPP,MagicHash #-}"
-	,"module Data.Encoding.GB18030Data where"
-	,""
-	,"import Data.ByteString(ByteString)"
-	,"#if __GLASGOW_HASKELL__>=608"
-	,"import Data.ByteString.Unsafe(unsafePackAddressLen)"
-	,"#else"
-	,"import Data.ByteString.Base(unsafePackAddressLen)"
-	,"#endif"
-	,"import System.IO.Unsafe(unsafePerformIO)"]
-	++ (createAddrVars "arr" (map (uncurry $ createAddr mp) ranges))
-	++ (createAddrVars "rarr" (map (uncurry $ createRAddr4 mp) rranges))
-	++ (createAddrVar "rrarr" (createRAddr2 mp))
-
-createAddrVars :: String -> [[Word8]] -> [String]
-createAddrVars base conts = concatMap (\(n,cont) ->
-	createAddrVar (base++show n) cont) (zip [1..] conts)
-
-createAddrVar :: String -> [Word8] -> [String]
-createAddrVar name cont =
-	[""
-	,name++" :: ByteString"
-	,name++" = unsafePerformIO $ unsafePackAddressLen "++show (length cont)++" \""++addr cont++"\"#"
-	]
-
-createAddr :: [(Char,[Word8])] -> Char -> Char -> [Word8]
-createAddr mp f t = let
-	lst = sortBy (comparing fst) [el | el@(ch,_) <- mp, ch>=f, ch<=t]
-	in concatMap (\(ch,seq) -> let
-		l = length seq
-		in [fromIntegral l]++seq++(replicate (4-l) 0)) lst
-
-createRAddr2 :: [(Char,[Word8])] -> [Word8]
-createRAddr2 mp = let
-	lst = sortBy (comparing snd)
-		[ (ch,v) | (ch,[w1,w2]) <- mp,let v = linear2 w1 w2]
-	in concatMap (\(ch,_) -> let i = ord ch
-		in [fromIntegral (i `shiftR` 8)
-		   ,fromIntegral i]) lst
-
-createRAddr4 :: [(Char,[Word8])] -> Int -> Int -> [Word8]
-createRAddr4 mp f t = let
-	lst = sortBy (comparing snd)
-		[ (ch,v) | (ch,[w1,w2,w3,w4]) <- mp,
-		let v = linear w1 w2 w3 w4, v>=f, v<=t ]
-	in concatMap (\(ch,_) -> let i = ord ch
-		in [fromIntegral (i `shiftR` 8)
-		   ,fromIntegral i]) lst
-
-addr :: [Word8] -> String
-addr = concatMap (\w -> "\\"++show w)

Data/Encoding/Helper/Template.hs

@@ -1,75 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.Helper.Template where
-
-import Data.Encoding.Base
-import Data.Char
-import Data.Maybe (mapMaybe)
-import Data.Map as Map (fromList,lookup)
-import Data.Array
-import Language.Haskell.TH
-
-makeISOInstance :: String -> FilePath -> Q [Dec]
-makeISOInstance name file = do
-  let rname = mkName name
-  trans <- runIO (readTranslation file)
-  mp <- encodingMap (validTranslations trans)
-  arr <- decodingArray (fillTranslations trans)
-  return [ DataD [] rname [] [NormalC rname []] [''Show]
-         , InstanceD [] (AppT (ConT ''Encoding) (ConT rname))
-                     [FunD 'encodeChar
-                               [Clause [WildP] (NormalB $ AppE (VarE 'encodeWithMap) (VarE $ mkName "mp"))
-                                [ValD (VarP $ mkName "mp") (NormalB mp) []]
-                               ]
-                     ,FunD 'decodeChar
-                               [Clause [WildP] (NormalB $ AppE (VarE 'decodeWithArray) (VarE $ mkName "arr"))
-                                [ValD (VarP $ mkName "arr") (NormalB arr) []]
-                               ]
-                     ]
-         ]
-  
-createCharArray :: [(Integer,Maybe Char)] -> Integer -> Integer -> Q Exp
-createCharArray lst = createArray (map (\(x,y) -> (x,case y of
-                                                      Nothing -> ConE 'Nothing
-                                                      Just c -> AppE (ConE 'Just) (LitE $ CharL c))
-                                       ) lst)
-
-
-createArray :: [(Integer,Exp)] -> Integer -> Integer -> Q Exp
-createArray lst from to = return $ AppE
-	(AppE
-		(VarE 'array)
-		(TupE [LitE $ IntegerL from,LitE $ IntegerL to]))
-	(ListE [ TupE [LitE $ IntegerL x,y]
-		| (x,y) <- lst ])
-
-decodingArray :: [(Integer,Maybe Char)] -> Q Exp
-decodingArray trans = createCharArray trans 0 255
-
-encodingMap :: [(Integer,Char)] -> Q Exp
-encodingMap trans = return $ AppE
-                    (VarE 'fromList)
-		    (ListE [ TupE [LitE $ CharL to,LitE $ IntegerL from]
-			     | (from,to) <- trans])
-
-readTranslation :: FilePath -> IO [(Integer,Maybe Char)]
-readTranslation file = do
-	cont <- readFile file
-	return $ mapMaybe (\ln -> case ln of
-		[] -> Nothing
-		('#':xs) -> Nothing
-		_ -> case words ln of
-			(src:"#UNDEFINED":_) -> Just (read src,Nothing) -- XXX: Find a better way to handle this
-			(src:trg:_) -> Just (read src,Just $ chr $ read trg)
-			_ -> Nothing
-			) (lines cont)
-
-fillTranslations :: [(Integer,Maybe Char)] -> [(Integer,Maybe Char)]
-fillTranslations = fillTranslations' (-1)
-    where
-      fillTranslations' n ((n',c):cs) = (map (\i -> (i,Nothing)) [n+1..n'-1])++((n',c):fillTranslations' n' cs)
-      fillTranslations' n [] = map (\i -> (i,Nothing)) [n+1..255]
-
-validTranslations :: [(Integer,Maybe Char)] -> [(Integer,Char)]
-validTranslations = mapMaybe (\(n,mc) -> case mc of
-                                          Nothing -> Nothing
-                                          Just c -> Just (n,c))

Data/Encoding/Helper/XML.hs

@@ -1,41 +0,0 @@
-module Data.Encoding.Helper.XML where
-
-import Data.Char
-import Data.List (find)
-import Data.Word
-import Data.Maybe (mapMaybe)
-import Text.XML.HaXml.Parse
-import Text.XML.HaXml.Types
-import Text.XML.HaXml.Verbatim
-import Numeric
-
-readDecodeTable :: String -> String -> [(Char,[Word8])]
-readDecodeTable name str = let
-	Document _ _ (Elem root_name _ conts) _ = xmlParse name str
-	in concat $ mapMaybe findAssignments conts
-
-findAssignments :: Content i -> Maybe [(Char,[Word8])]
-findAssignments (CElem (Elem "assignments" _ conts) _)
-	= Just $ mapMaybe findAssignment conts
-findAssignments _ = Nothing
-
-findAssignment :: Content i -> Maybe (Char,[Word8])
-findAssignment (CElem (Elem "a" attrs _) _) = do
-	u <- lookup "u" attrs
-	b <- lookup "b" attrs
-	return (chr $ readHexInt (showAttValue u),parseBinary b)
-findAssignment _ = Nothing
-
-parseBinary :: AttValue -> [Word8]
-parseBinary val = map (fromIntegral.readHexInt) (words (showAttValue val))
-
-showAttValue :: AttValue -> String
-showAttValue (AttValue lst) = concat $ map (\el -> case el of
-	Left str -> str
-	Right ref -> verbatim ref) lst
-
-readHexInt :: String -> Int
-readHexInt str = case find (\x -> snd x == "") (readHex str) of
-	Nothing -> error "Not a hex"
-	Just (x,_) -> x
-	

Data/Encoding/ISO2022.hs

@@ -0,0 +1,60 @@
+module Data.Encoding.ISO2022 where
+
+import Data.Encoding.Base
+import Data.Encoding.ByteSource
+import Data.Encoding.ByteSink
+import Data.Encoding.Exception
+import Data.Encoding.ASCII
+
+import Data.Word
+import Control.Throws
+
+class ISO2022 e where
+    readEscape :: ByteSource m => e -> m (Maybe DynEncoding)
+    encodingForChar :: e -> Char -> Maybe (DynEncoding,[Word8])
+
+encodeCharISO2022 :: (ISO2022 e,ByteSink m) => e -> Char -> m ()
+encodeCharISO2022 e c = case encodingForChar e c of
+                          Nothing -> throwException (HasNoRepresentation c)
+                          Just (enc,esc) -> do
+                                            mapM_ pushWord8 esc
+                                            encodeChar enc c
+
+decodeCharISO2022 :: (ISO2022 e,ByteSource m) => e -> m Char
+decodeCharISO2022 e = do
+  enc <- readEscape e
+  case enc of
+    Nothing -> decodeChar ASCII
+    Just renc -> decodeChar renc
+
+encodeISO2022 :: (ISO2022 e,ByteSink m) => e -> String -> m ()
+encodeISO2022 e = encode' (DynEncoding ASCII)
+    where
+      encode' _ [] = return ()
+      encode' enc (c:cs) = case encodingForChar e c of
+                             Nothing -> throwException (HasNoRepresentation c)
+                             Just (nenc,esc)
+                                  | enc==nenc -> do
+                                                 encodeChar enc c
+                                                 encode' enc cs
+                                  | otherwise -> do
+                                                 mapM_ pushWord8 esc
+                                                 encodeChar nenc c
+                                                 encode' nenc cs
+
+decodeISO2022 :: (ISO2022 e,ByteSource m) => e -> m String
+decodeISO2022 e = decode' (DynEncoding ASCII)
+    where
+      decode' enc = do
+        empty <- sourceEmpty
+        if empty
+          then return []
+          else (do
+                 nenc <- readEscape e
+                 case nenc of
+                   Just renc -> decode' renc
+                   Nothing -> do
+                             c <- decodeChar enc
+                             cs <- decode' enc
+                             return (c:cs)
+               )

Data/Encoding/ISO2022JP.hs

@@ -0,0 +1,51 @@
+{-# LANGUAGE DeriveDataTypeable #-}
+{- | Implements the japanese character encoding ISO 2022-JP.
+     See http://tools.ietf.org/html/rfc1468 for reference.
+ -}
+module Data.Encoding.ISO2022JP where
+
+import Data.Typeable
+
+import Data.Encoding.Base
+import Data.Encoding.Exception
+import Data.Encoding.ByteSource
+import Data.Encoding.ISO2022
+import Data.Encoding.ASCII
+import Data.Encoding.JISX0201
+import Data.Encoding.JISX0208
+
+import Control.Throws
+
+data ISO2022JP = ISO2022JP deriving (Eq,Show,Typeable)
+
+instance Encoding ISO2022JP where
+    encodeChar = encodeCharISO2022
+    decodeChar = decodeCharISO2022
+    encode = encodeISO2022
+    decode = decodeISO2022
+    encodeable _ c = encodeable ASCII c || encodeable JISX0201 c || encodeable JISX0208 c
+
+instance ISO2022 ISO2022JP where
+    readEscape _ = fetchAhead $ do
+      w <- fetchWord8
+      if w == 27
+        then (do
+               w2 <- fetchWord8
+               w3 <- fetchWord8
+               case w2 of
+                 40 -> case w3 of
+                        66 -> return $ Just $ DynEncoding ASCII
+                        74 -> return $ Just $ DynEncoding JISX0201
+                        _ -> throwException (IllegalCharacter w3)
+                 36 -> case w3 of
+                        64 -> return $ Just $ DynEncoding JISX0208 -- XXX: this actually has to be the 1978 version of the standard... too bad I can't find it
+                        66 -> return $ Just $ DynEncoding JISX0208
+                        _ -> throwException (IllegalCharacter w3)
+                 _ -> throwException (IllegalCharacter w2)
+             )
+        else return Nothing
+    encodingForChar _ c
+        | encodeable ASCII c = Just (DynEncoding ASCII,[27,40,66])
+        | encodeable JISX0201 c = Just (DynEncoding JISX0201,[27,40,74])
+        | encodeable JISX0208 c = Just (DynEncoding JISX0208,[27,36,66])
+        | otherwise  = Nothing

Data/Encoding/ISO88591.hs

@@ -1,3 +1,6 @@
+{-# LANGUAGE DeriveDataTypeable #-}
+{- | Implements ISO\/IEC 8859-1 alias latin-1 encoding. See <http://en.wikipedia.org/wiki/ISO/IEC_8859-1> for further information.
+ -}
 module Data.Encoding.ISO88591 where
 
 import Control.Throws
@@ -6,8 +9,9 @@ import Data.Encoding.Exception
 import Data.Encoding.ByteSource
 import Data.Encoding.ByteSink
 import Data.Char (ord,chr)
+import Data.Typeable
 
-data ISO88591 = ISO88591 deriving (Show)
+data ISO88591 = ISO88591 deriving (Show,Eq,Typeable)
 
 instance Encoding ISO88591 where
     encodeChar _ c
@@ -15,4 +19,5 @@ instance Encoding ISO88591 where
                | otherwise = pushWord8 (fromIntegral $ ord c)
     decodeChar _ = do
       w <- fetchWord8
-      return (chr $ fromIntegral w)
+      return (chr $ fromIntegral w)
+    encodeable _ c = c <= '\255'

Data/Encoding/ISO885910.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO885910 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO885910" "8859-10.TXT" )

Data/Encoding/ISO885910.mapping

@@ -1,50 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-10:1998 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.1
-#	Table format:     Format A
-#	Date:             1999 October 11
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-10:1998 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-10 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-10 order.
-#
-#	Version history
-#	1.0 version new.
-#       1.1 corrected mistake in mapping of 0xA4
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO885911.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO885911 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO885911" "8859-11.TXT" )

Data/Encoding/ISO885911.mapping

@@ -1,52 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-11:2001 to Unicode
-#	Unicode version:  3.2
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             2002 October 7
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 2002 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-11:2001 characters map into Unicode.
-#
-#	ISO/IEC 8859-11:2001 is equivalent to TIS 620-2533 (1990) with
-#	the addition of 0xA0 NO-BREAK SPACE.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-11 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-11 order.
-#
-#	Version history:
-#		2002 October 7  Created
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	For any comments or problems, please use the Unicode
-#	web contact form at:
-#		http://www.unicode.org/unicode/reporting.html
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT
@@ -294,4 +245,4 @@
 0xF8	0x0E58	#	THAI DIGIT EIGHT
 0xF9	0x0E59	#	THAI DIGIT NINE
 0xFA	0x0E5A	#	THAI CHARACTER ANGKHANKHU
-0xFB	0x0E5B	#	THAI CHARACTER KHOMUT
+0xFB	0x0E5B	#	THAI CHARACTER KHOMUT

Data/Encoding/ISO885913.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO885913 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO885913" "8859-13.TXT" )

Data/Encoding/ISO885913.mapping

@@ -1,46 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-13:1998  to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             1999 July 27
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1998 - 1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-13:1998 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-13 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-13 order.
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO885914.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO885914 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO885914" "8859-14.TXT" )

Data/Encoding/ISO885914.mapping

@@ -1,47 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-14:1998 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             1999 July 27
-#	Authors:          Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/>
-#			  Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1998 - 1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-14:1998 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-14 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-14 order.
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO885915.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO885915 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO885915" "8859-15.TXT" )

Data/Encoding/ISO885915.mapping

@@ -1,49 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-15:1999 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             1999 July 27
-#	Authors:          Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/>
-#			  Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1998 - 1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-15:1999 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-15 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-15 order.
-#
-#	Version history
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO885916.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO885916 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO885916" "8859-16.TXT" )

Data/Encoding/ISO885916.mapping

@@ -1,46 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-16:2001 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             2001 July 26
-#	Authors:          Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/>
-#
-#	Copyright (c) 1999-2001 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-16:2001 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-16 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-16 order.
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO88592.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO88592 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO88592" "8859-2.TXT" )

Data/Encoding/ISO88592.mapping

@@ -1,50 +1,3 @@
-#
-#	Name:             ISO 8859-2:1999 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             1999 July 27
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1991-1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-2:1999 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-2 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-2 order.
-#
-#	Version history
-#	1.0 version updates 0.1 version by adding mappings for all
-#	control characters.
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO88593.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO88593 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO88593" "8859-3.TXT" )

Data/Encoding/ISO88593.mapping

@@ -1,50 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-3:1999 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             1999 July 27
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1991-1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-3:1999 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-3 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-3 order.
-#
-#	Version history
-#	1.0 version updates 0.1 version by adding mappings for all
-#	control characters.
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO88594.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO88594 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO88594" "8859-4.TXT" )

Data/Encoding/ISO88594.mapping

@@ -1,50 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-4:1998 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             1999 July 27
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1991-1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-4:1998 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-4 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-4 order.
-#
-#	Version history
-#	1.0 version updates 0.1 version by adding mappings for all
-#	control characters.
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO88595.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO88595 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO88595" "8859-5.TXT" )

Data/Encoding/ISO88595.mapping

@@ -1,50 +1,3 @@
-#
-#	Name:             ISO 8859-5:1999 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             1999 July 27
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1991-1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-5:1999 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-5 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-5 order.
-#
-#	Version history
-#	1.0 version updates 0.1 version by adding mappings for all
-#	control characters.
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO88596.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO88596 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO88596" "8859-6.TXT" )

Data/Encoding/ISO88596.mapping

@@ -1,52 +1,3 @@
-#
-#	Name:             ISO 8859-6:1999 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             1999 July 27
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1991-1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-6:1999 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-6 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-6 order.
-#
-#	Version history
-#	1.0 version updates 0.1 version by adding mappings for all
-#	control characters.
-#	0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead
-#	of the Arabic digits (U+0660..U+0669).
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO88597.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO88597 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO88597" "8859-7.TXT" )

Data/Encoding/ISO88597.mapping

@@ -1,58 +1,3 @@
-#
-#	Name:             ISO 8859-7:2003 to Unicode
-#	Unicode version:  4.0
-#	Table version:    2.0
-#	Table format:     Format A
-#	Date:             2003-Nov-12
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1991-2003 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO 8859-7:2003 characters map into Unicode.
-#
-#	ISO 8859-7:1987 is equivalent to ISO-IR-126, ELOT 928,
-#	and ECMA 118. ISO 8859-7:2003 adds two currency signs 
-#	and one other character not in the earlier standard.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO 8859-7 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO 8859-7 order.
-#
-#	Version history
-#	1.0 version updates 0.1 version by adding mappings for all
-#	control characters.
-#	Remap 0xA1 to U+2018 (instead of 0x02BD) to match text of 8859-7
-#	Remap 0xA2 to U+2019 (instead of 0x02BC) to match text of 8859-7
-#
-#	2.0 version updates 1.0 version by adding mappings for the
-#	three newly added characters 0xA4, 0xA5, 0xAA.
-#
-#	Updated versions of this file may be found in:
-#		<http://www.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact the Unicode Consortium at:
-#	        <http://www.unicode.org/reporting.html>
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO88598.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO88598 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO88598" "8859-8.TXT" )

Data/Encoding/ISO88598.mapping

@@ -1,52 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-8:1999 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.1
-#	Table format:     Format A
-#	Date:             2000-Jan-03
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1991-1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on optical media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-8:1999 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-8 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-8 order.
-#
-#	Version history
-#	1.0 version updates 0.1 version by adding mappings for all
-#	control characters.
-#       1.1 version updates to the published 8859-8:1999, correcting
-#          the mapping of 0xAF and adding mappings for LRM and RLM.
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/ISO88599.hs

@@ -1,6 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-module Data.Encoding.ISO88599 where
-
-import Data.Encoding.Helper.Template (makeISOInstance)
-
-$( makeISOInstance "ISO88599" "8859-9.TXT" )

Data/Encoding/ISO88599.mapping

@@ -1,52 +1,3 @@
-#
-#	Name:             ISO/IEC 8859-9:1999 to Unicode
-#	Unicode version:  3.0
-#	Table version:    1.0
-#	Table format:     Format A
-#	Date:             1999 July 27
-#	Authors:          Ken Whistler <kenw@sybase.com>
-#
-#	Copyright (c) 1991-1999 Unicode, Inc.  All Rights reserved.
-#
-#	This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
-#	No claims are made as to fitness for any particular purpose.  No
-#	warranties of any kind are expressed or implied.  The recipient
-#	agrees to determine applicability of information provided.  If this
-#	file has been provided on magnetic media by Unicode, Inc., the sole
-#	remedy for any claim will be exchange of defective media within 90
-#	days of receipt.
-#
-#	Unicode, Inc. hereby grants the right to freely use the information
-#	supplied in this file in the creation of products supporting the
-#	Unicode Standard, and to make copies of this file in any form for
-#	internal or external distribution as long as this notice remains
-#	attached.
-#
-#	General notes:
-#
-#	This table contains the data the Unicode Consortium has on how
-#       ISO/IEC 8859-9:1999 characters map into Unicode.
-#
-#	Format:  Three tab-separated columns
-#		 Column #1 is the ISO/IEC 8859-9 code (in hex as 0xXX)
-#		 Column #2 is the Unicode (in hex as 0xXXXX)
-#		 Column #3 the Unicode name (follows a comment sign, '#')
-#
-#	The entries are in ISO/IEC 8859-9 order.
-#
-#	ISO/IEC 8859-9 is also equivalent to ISO-IR-148.
-#
-#	Version history
-#	1.0 version updates 0.1 version by adding mappings for all
-#	control characters.
-#
-#	Updated versions of this file may be found in:
-#		<ftp://ftp.unicode.org/Public/MAPPINGS/>
-#
-#	Any comments or problems, contact <errata@unicode.org>
-#	Please note that <errata@unicode.org> is an archival address;
-#	notices will be checked, but do not expect an immediate response.
-#
 0x00	0x0000	#	NULL
 0x01	0x0001	#	START OF HEADING
 0x02	0x0002	#	START OF TEXT

Data/Encoding/JISX0201.mapping

@@ -0,0 +1,158 @@
+0x20	0x0020	# SPACE
+0x21	0x0021	# EXCLAMATION MARK
+0x22	0x0022	# QUOTATION MARK
+0x23	0x0023	# NUMBER SIGN
+0x24	0x0024	# DOLLAR SIGN
+0x25	0x0025	# PERCENT SIGN
+0x26	0x0026	# AMPERSAND
+0x27	0x0027	# APOSTROPHE
+0x28	0x0028	# LEFT PARENTHESIS
+0x29	0x0029	# RIGHT PARENTHESIS
+0x2A	0x002A	# ASTERISK
+0x2B	0x002B	# PLUS SIGN
+0x2C	0x002C	# COMMA
+0x2D	0x002D	# HYPHEN-MINUS
+0x2E	0x002E	# FULL STOP
+0x2F	0x002F	# SOLIDUS
+0x30	0x0030	# DIGIT ZERO
+0x31	0x0031	# DIGIT ONE
+0x32	0x0032	# DIGIT TWO
+0x33	0x0033	# DIGIT THREE
+0x34	0x0034	# DIGIT FOUR
+0x35	0x0035	# DIGIT FIVE
+0x36	0x0036	# DIGIT SIX
+0x37	0x0037	# DIGIT SEVEN
+0x38	0x0038	# DIGIT EIGHT
+0x39	0x0039	# DIGIT NINE
+0x3A	0x003A	# COLON
+0x3B	0x003B	# SEMICOLON
+0x3C	0x003C	# LESS-THAN SIGN
+0x3D	0x003D	# EQUALS SIGN
+0x3E	0x003E	# GREATER-THAN SIGN
+0x3F	0x003F	# QUESTION MARK
+0x40	0x0040	# COMMERCIAL AT
+0x41	0x0041	# LATIN CAPITAL LETTER A
+0x42	0x0042	# LATIN CAPITAL LETTER B
+0x43	0x0043	# LATIN CAPITAL LETTER C
+0x44	0x0044	# LATIN CAPITAL LETTER D
+0x45	0x0045	# LATIN CAPITAL LETTER E
+0x46	0x0046	# LATIN CAPITAL LETTER F
+0x47	0x0047	# LATIN CAPITAL LETTER G
+0x48	0x0048	# LATIN CAPITAL LETTER H
+0x49	0x0049	# LATIN CAPITAL LETTER I
+0x4A	0x004A	# LATIN CAPITAL LETTER J
+0x4B	0x004B	# LATIN CAPITAL LETTER K
+0x4C	0x004C	# LATIN CAPITAL LETTER L
+0x4D	0x004D	# LATIN CAPITAL LETTER M
+0x4E	0x004E	# LATIN CAPITAL LETTER N
+0x4F	0x004F	# LATIN CAPITAL LETTER O
+0x50	0x0050	# LATIN CAPITAL LETTER P
+0x51	0x0051	# LATIN CAPITAL LETTER Q
+0x52	0x0052	# LATIN CAPITAL LETTER R
+0x53	0x0053	# LATIN CAPITAL LETTER S
+0x54	0x0054	# LATIN CAPITAL LETTER T
+0x55	0x0055	# LATIN CAPITAL LETTER U
+0x56	0x0056	# LATIN CAPITAL LETTER V
+0x57	0x0057	# LATIN CAPITAL LETTER W
+0x58	0x0058	# LATIN CAPITAL LETTER X
+0x59	0x0059	# LATIN CAPITAL LETTER Y
+0x5A	0x005A	# LATIN CAPITAL LETTER Z
+0x5B	0x005B	# LEFT SQUARE BRACKET
+0x5C	0x00A5	# YEN SIGN
+0x5D	0x005D	# RIGHT SQUARE BRACKET
+0x5E	0x005E	# CIRCUMFLEX ACCENT
+0x5F	0x005F	# LOW LINE
+0x60	0x0060	# GRAVE ACCENT
+0x61	0x0061	# LATIN SMALL LETTER A
+0x62	0x0062	# LATIN SMALL LETTER B
+0x63	0x0063	# LATIN SMALL LETTER C
+0x64	0x0064	# LATIN SMALL LETTER D
+0x65	0x0065	# LATIN SMALL LETTER E
+0x66	0x0066	# LATIN SMALL LETTER F
+0x67	0x0067	# LATIN SMALL LETTER G
+0x68	0x0068	# LATIN SMALL LETTER H
+0x69	0x0069	# LATIN SMALL LETTER I
+0x6A	0x006A	# LATIN SMALL LETTER J
+0x6B	0x006B	# LATIN SMALL LETTER K
+0x6C	0x006C	# LATIN SMALL LETTER L
+0x6D	0x006D	# LATIN SMALL LETTER M
+0x6E	0x006E	# LATIN SMALL LETTER N
+0x6F	0x006F	# LATIN SMALL LETTER O
+0x70	0x0070	# LATIN SMALL LETTER P
+0x71	0x0071	# LATIN SMALL LETTER Q
+0x72	0x0072	# LATIN SMALL LETTER R
+0x73	0x0073	# LATIN SMALL LETTER S
+0x74	0x0074	# LATIN SMALL LETTER T
+0x75	0x0075	# LATIN SMALL LETTER U
+0x76	0x0076	# LATIN SMALL LETTER V
+0x77	0x0077	# LATIN SMALL LETTER W
+0x78	0x0078	# LATIN SMALL LETTER X
+0x79	0x0079	# LATIN SMALL LETTER Y
+0x7A	0x007A	# LATIN SMALL LETTER Z
+0x7B	0x007B	# LEFT CURLY BRACKET
+0x7C	0x007C	# VERTICAL LINE
+0x7D	0x007D	# RIGHT CURLY BRACKET
+0x7E	0x203E	# OVERLINE
+0xA1	0xFF61	# HALFWIDTH IDEOGRAPHIC FULL STOP
+0xA2	0xFF62	# HALFWIDTH LEFT CORNER BRACKET
+0xA3	0xFF63	# HALFWIDTH RIGHT CORNER BRACKET
+0xA4	0xFF64	# HALFWIDTH IDEOGRAPHIC COMMA
+0xA5	0xFF65	# HALFWIDTH KATAKANA MIDDLE DOT
+0xA6	0xFF66	# HALFWIDTH KATAKANA LETTER WO
+0xA7	0xFF67	# HALFWIDTH KATAKANA LETTER SMALL A
+0xA8	0xFF68	# HALFWIDTH KATAKANA LETTER SMALL I
+0xA9	0xFF69	# HALFWIDTH KATAKANA LETTER SMALL U
+0xAA	0xFF6A	# HALFWIDTH KATAKANA LETTER SMALL E
+0xAB	0xFF6B	# HALFWIDTH KATAKANA LETTER SMALL O
+0xAC	0xFF6C	# HALFWIDTH KATAKANA LETTER SMALL YA
+0xAD	0xFF6D	# HALFWIDTH KATAKANA LETTER SMALL YU
+0xAE	0xFF6E	# HALFWIDTH KATAKANA LETTER SMALL YO
+0xAF	0xFF6F	# HALFWIDTH KATAKANA LETTER SMALL TU
+0xB0	0xFF70	# HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
+0xB1	0xFF71	# HALFWIDTH KATAKANA LETTER A
+0xB2	0xFF72	# HALFWIDTH KATAKANA LETTER I
+0xB3	0xFF73	# HALFWIDTH KATAKANA LETTER U
+0xB4	0xFF74	# HALFWIDTH KATAKANA LETTER E
+0xB5	0xFF75	# HALFWIDTH KATAKANA LETTER O
+0xB6	0xFF76	# HALFWIDTH KATAKANA LETTER KA
+0xB7	0xFF77	# HALFWIDTH KATAKANA LETTER KI
+0xB8	0xFF78	# HALFWIDTH KATAKANA LETTER KU
+0xB9	0xFF79	# HALFWIDTH KATAKANA LETTER KE
+0xBA	0xFF7A	# HALFWIDTH KATAKANA LETTER KO
+0xBB	0xFF7B	# HALFWIDTH KATAKANA LETTER SA
+0xBC	0xFF7C	# HALFWIDTH KATAKANA LETTER SI
+0xBD	0xFF7D	# HALFWIDTH KATAKANA LETTER SU
+0xBE	0xFF7E	# HALFWIDTH KATAKANA LETTER SE
+0xBF	0xFF7F	# HALFWIDTH KATAKANA LETTER SO
+0xC0	0xFF80	# HALFWIDTH KATAKANA LETTER TA
+0xC1	0xFF81	# HALFWIDTH KATAKANA LETTER TI
+0xC2	0xFF82	# HALFWIDTH KATAKANA LETTER TU
+0xC3	0xFF83	# HALFWIDTH KATAKANA LETTER TE
+0xC4	0xFF84	# HALFWIDTH KATAKANA LETTER TO
+0xC5	0xFF85	# HALFWIDTH KATAKANA LETTER NA
+0xC6	0xFF86	# HALFWIDTH KATAKANA LETTER NI
+0xC7	0xFF87	# HALFWIDTH KATAKANA LETTER NU
+0xC8	0xFF88	# HALFWIDTH KATAKANA LETTER NE
+0xC9	0xFF89	# HALFWIDTH KATAKANA LETTER NO
+0xCA	0xFF8A	# HALFWIDTH KATAKANA LETTER HA
+0xCB	0xFF8B	# HALFWIDTH KATAKANA LETTER HI
+0xCC	0xFF8C	# HALFWIDTH KATAKANA LETTER HU
+0xCD	0xFF8D	# HALFWIDTH KATAKANA LETTER HE
+0xCE	0xFF8E	# HALFWIDTH KATAKANA LETTER HO
+0xCF	0xFF8F	# HALFWIDTH KATAKANA LETTER MA
+0xD0	0xFF90	# HALFWIDTH KATAKANA LETTER MI
+0xD1	0xFF91	# HALFWIDTH KATAKANA LETTER MU
+0xD2	0xFF92	# HALFWIDTH KATAKANA LETTER ME
+0xD3	0xFF93	# HALFWIDTH KATAKANA LETTER MO
+0xD4	0xFF94	# HALFWIDTH KATAKANA LETTER YA
+0xD5	0xFF95	# HALFWIDTH KATAKANA LETTER YU
+0xD6	0xFF96	# HALFWIDTH KATAKANA LETTER YO
+0xD7	0xFF97	# HALFWIDTH KATAKANA LETTER RA
+0xD8	0xFF98	# HALFWIDTH KATAKANA LETTER RI
+0xD9	0xFF99	# HALFWIDTH KATAKANA LETTER RU
+0xDA	0xFF9A	# HALFWIDTH KATAKANA LETTER RE
+0xDB	0xFF9B	# HALFWIDTH KATAKANA LETTER RO
+0xDC	0xFF9C	# HALFWIDTH KATAKANA LETTER WA
+0xDD	0xFF9D	# HALFWIDTH KATAKANA LETTER N
+0xDE	0xFF9E	# HALFWIDTH KATAKANA VOICED SOUND MARK
+0xDF	0xFF9F	# HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK

Data/Encoding/KOI8R.hs

@@ -56,4 +56,5 @@ instance Encoding KOI8R where
 	| ch < '\128' = pushWord8 $ fromIntegral $ ord ch
 	| otherwise   = case lookup ch koi8rMap of
 		Just w -> pushWord8 w
-		Nothing -> throwException (HasNoRepresentation ch)
+		Nothing -> throwException (HasNoRepresentation ch)
+    encodeable _ c = member c koi8rMap

Data/Encoding/KOI8U.hs

@@ -56,4 +56,5 @@ instance Encoding KOI8U where
 	| ch < '\128' = pushWord8 $ fromIntegral $ ord ch
 	| otherwise   = case lookup ch koi8uMap of
 		Just w  -> pushWord8 w
-		Nothing -> throwException (HasNoRepresentation ch)
+		Nothing -> throwException (HasNoRepresentation ch)
+    encodeable _ c = member c koi8uMap

Data/Encoding/MacOSRoman.mapping

@@ -0,0 +1,319 @@
+# /Notes on Mac OS Roman:/
+#
+#   This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa
+#   environments, it is only supported directly in programming
+#   interfaces for QuickDraw Text, the Script Manager, and related
+#   Text Utilities. For other purposes it is supported via transcoding
+#   to and from Unicode.
+#
+#   This character set is used for at least the following Mac OS
+#   localizations: U.S., British, Canadian French, French, Swiss
+#   French, German, Swiss German, Italian, Swiss Italian, Dutch,
+#   Swedish, Norwegian, Danish, Finnish, Spanish, Catalan,
+#   Portuguese, Brazilian, and the default International system.
+#
+#   Variants of Mac OS Roman are used for Croatian, Icelandic,
+#   Turkish, Romanian, and other encodings. Separate mapping tables
+#   are available for these encodings.
+#
+#   Before Mac OS 8.5, code point 0xDB was CURRENCY SIGN, and was
+#   mapped to U+00A4. In Mac OS 8.5 and later versions, code point
+#   0xDB is changed to EURO SIGN and maps to U+20AC; the standard
+#   Apple fonts are updated for Mac OS 8.5 to reflect this. There is
+#   a "currency sign" variant of the Mac OS Roman encoding that still
+#   maps 0xDB to U+00A4; this can be used for older fonts.
+#
+#   Before Mac OS 8.5, the ROM bitmap versions of the fonts Chicago,
+#   New York, Geneva, and Monaco did not implement the full Mac OS
+#   Roman character set; they only supported character codes up to
+#   0xD8. The TrueType versions of these fonts have always implemented
+#   the full character set, as with the bitmap and TrueType versions
+#   of the other standard Roman fonts.
+#
+#   In all Mac OS encodings, fonts such as Chicago which are used
+#   as "system" fonts (for menus, dialogs, etc.) have four glyphs
+#   at code points 0x11-0x14 for transient use by the Menu Manager.
+#   These glyphs are not intended as characters for use in normal
+#   text, and the associated code points are not generally
+#   interpreted as associated with these glyphs; they are usually
+#   interpreted (if at all) as the control codes DC1-DC4.
+#
+# /Unicode mapping issues and notes:/
+#
+#   The following corporate zone Unicode character is used in this
+#   mapping:
+#
+#     0xF8FF  Apple logo
+#
+#   NOTE: The graphic image associated with the Apple logo character
+#   is not authorized for use without permission of Apple, and
+#   unauthorized use might constitute trademark infringement.
+#
+# /Details of mapping changes in each version:/
+#
+#   Changes from version n08 to version b02:
+#
+#   * Encoding changed for Mac OS 8.5; change mapping of 0xDB from
+#   CURRENCY SIGN (U+00A4) to EURO SIGN (U+20AC).
+#
+#   Changes from version n03 to version n04:
+#
+#   * Change mapping of 0xBD from U+2126 to its canonical
+#     decomposition, U+03A9.
+
+0x00	0x0000	# NULL
+0x01	0x0001	# START OF HEADING
+0x02	0x0002	# START OF TEXT
+0x03	0x0003	# END OF TEXT
+0x04	0x0004	# END OF TRANSMISSION
+0x05	0x0005	# ENQUIRY
+0x06	0x0006	# ACKNOWLEDGE
+0x07	0x0007	# BELL
+0x08	0x0008	# BACKSPACE
+0x09	0x0009	# HORIZONTAL TABULATION
+0x0A	0x000A	# LINE FEED
+0x0B	0x000B	# VERTICAL TABULATION
+0x0C	0x000C	# FORM FEED
+0x0D	0x000D	# CARRIAGE RETURN
+0x0E	0x000E	# SHIFT OUT
+0x0F	0x000F	# SHIFT IN
+0x10	0x0010	# DATA LINK ESCAPE
+0x11	0x0011	# DEVICE CONTROL ONE
+0x12	0x0012	# DEVICE CONTROL TWO
+0x13	0x0013	# DEVICE CONTROL THREE
+0x14	0x0014	# DEVICE CONTROL FOUR
+0x15	0x0015	# NEGATIVE ACKNOWLEDGE
+0x16	0x0016	# SYNCHRONOUS IDLE
+0x17	0x0017	# END OF TRANSMISSION BLOCK
+0x18	0x0018	# CANCEL
+0x19	0x0019	# END OF MEDIUM
+0x1A	0x001A	# SUBSTITUTE
+0x1B	0x001B	# ESCAPE
+0x1C	0x001C	# FILE SEPARATOR
+0x1D	0x001D	# GROUP SEPARATOR
+0x1E	0x001E	# RECORD SEPARATOR
+0x1F	0x001F	# UNIT SEPARATOR
+0x20	0x0020	# SPACE
+0x21	0x0021	# EXCLAMATION MARK
+0x22	0x0022	# QUOTATION MARK
+0x23	0x0023	# NUMBER SIGN
+0x24	0x0024	# DOLLAR SIGN
+0x25	0x0025	# PERCENT SIGN
+0x26	0x0026	# AMPERSAND
+0x27	0x0027	# APOSTROPHE
+0x28	0x0028	# LEFT PARENTHESIS
+0x29	0x0029	# RIGHT PARENTHESIS
+0x2A	0x002A	# ASTERISK
+0x2B	0x002B	# PLUS SIGN
+0x2C	0x002C	# COMMA
+0x2D	0x002D	# HYPHEN-MINUS
+0x2E	0x002E	# FULL STOP
+0x2F	0x002F	# SOLIDUS
+0x30	0x0030	# DIGIT ZERO
+0x31	0x0031	# DIGIT ONE
+0x32	0x0032	# DIGIT TWO
+0x33	0x0033	# DIGIT THREE
+0x34	0x0034	# DIGIT FOUR
+0x35	0x0035	# DIGIT FIVE
+0x36	0x0036	# DIGIT SIX
+0x37	0x0037	# DIGIT SEVEN
+0x38	0x0038	# DIGIT EIGHT
+0x39	0x0039	# DIGIT NINE
+0x3A	0x003A	# COLON
+0x3B	0x003B	# SEMICOLON
+0x3C	0x003C	# LESS-THAN SIGN
+0x3D	0x003D	# EQUALS SIGN
+0x3E	0x003E	# GREATER-THAN SIGN
+0x3F	0x003F	# QUESTION MARK
+0x40	0x0040	# COMMERCIAL AT
+0x41	0x0041	# LATIN CAPITAL LETTER A
+0x42	0x0042	# LATIN CAPITAL LETTER B
+0x43	0x0043	# LATIN CAPITAL LETTER C
+0x44	0x0044	# LATIN CAPITAL LETTER D
+0x45	0x0045	# LATIN CAPITAL LETTER E
+0x46	0x0046	# LATIN CAPITAL LETTER F
+0x47	0x0047	# LATIN CAPITAL LETTER G
+0x48	0x0048	# LATIN CAPITAL LETTER H
+0x49	0x0049	# LATIN CAPITAL LETTER I
+0x4A	0x004A	# LATIN CAPITAL LETTER J
+0x4B	0x004B	# LATIN CAPITAL LETTER K
+0x4C	0x004C	# LATIN CAPITAL LETTER L
+0x4D	0x004D	# LATIN CAPITAL LETTER M
+0x4E	0x004E	# LATIN CAPITAL LETTER N
+0x4F	0x004F	# LATIN CAPITAL LETTER O
+0x50	0x0050	# LATIN CAPITAL LETTER P
+0x51	0x0051	# LATIN CAPITAL LETTER Q
+0x52	0x0052	# LATIN CAPITAL LETTER R
+0x53	0x0053	# LATIN CAPITAL LETTER S
+0x54	0x0054	# LATIN CAPITAL LETTER T
+0x55	0x0055	# LATIN CAPITAL LETTER U
+0x56	0x0056	# LATIN CAPITAL LETTER V
+0x57	0x0057	# LATIN CAPITAL LETTER W
+0x58	0x0058	# LATIN CAPITAL LETTER X
+0x59	0x0059	# LATIN CAPITAL LETTER Y
+0x5A	0x005A	# LATIN CAPITAL LETTER Z
+0x5B	0x005B	# LEFT SQUARE BRACKET
+0x5C	0x005C	# REVERSE SOLIDUS
+0x5D	0x005D	# RIGHT SQUARE BRACKET
+0x5E	0x005E	# CIRCUMFLEX ACCENT
+0x5F	0x005F	# LOW LINE
+0x60	0x0060	# GRAVE ACCENT
+0x61	0x0061	# LATIN SMALL LETTER A
+0x62	0x0062	# LATIN SMALL LETTER B
+0x63	0x0063	# LATIN SMALL LETTER C
+0x64	0x0064	# LATIN SMALL LETTER D
+0x65	0x0065	# LATIN SMALL LETTER E
+0x66	0x0066	# LATIN SMALL LETTER F
+0x67	0x0067	# LATIN SMALL LETTER G
+0x68	0x0068	# LATIN SMALL LETTER H
+0x69	0x0069	# LATIN SMALL LETTER I
+0x6A	0x006A	# LATIN SMALL LETTER J
+0x6B	0x006B	# LATIN SMALL LETTER K
+0x6C	0x006C	# LATIN SMALL LETTER L
+0x6D	0x006D	# LATIN SMALL LETTER M
+0x6E	0x006E	# LATIN SMALL LETTER N
+0x6F	0x006F	# LATIN SMALL LETTER O
+0x70	0x0070	# LATIN SMALL LETTER P
+0x71	0x0071	# LATIN SMALL LETTER Q
+0x72	0x0072	# LATIN SMALL LETTER R
+0x73	0x0073	# LATIN SMALL LETTER S
+0x74	0x0074	# LATIN SMALL LETTER T
+0x75	0x0075	# LATIN SMALL LETTER U
+0x76	0x0076	# LATIN SMALL LETTER V
+0x77	0x0077	# LATIN SMALL LETTER W
+0x78	0x0078	# LATIN SMALL LETTER X
+0x79	0x0079	# LATIN SMALL LETTER Y
+0x7A	0x007A	# LATIN SMALL LETTER Z
+0x7B	0x007B	# LEFT CURLY BRACKET
+0x7C	0x007C	# VERTICAL LINE
+0x7D	0x007D	# RIGHT CURLY BRACKET
+0x7E	0x007E	# TILDE
+0x7F	0x007F	# DELETE
+0x80	0x00C4	# LATIN CAPITAL LETTER A WITH DIAERESIS
+0x81	0x00C5	# LATIN CAPITAL LETTER A WITH RING ABOVE
+0x82	0x00C7	# LATIN CAPITAL LETTER C WITH CEDILLA
+0x83	0x00C9	# LATIN CAPITAL LETTER E WITH ACUTE
+0x84	0x00D1	# LATIN CAPITAL LETTER N WITH TILDE
+0x85	0x00D6	# LATIN CAPITAL LETTER O WITH DIAERESIS
+0x86	0x00DC	# LATIN CAPITAL LETTER U WITH DIAERESIS
+0x87	0x00E1	# LATIN SMALL LETTER A WITH ACUTE
+0x88	0x00E0	# LATIN SMALL LETTER A WITH GRAVE
+0x89	0x00E2	# LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x8A	0x00E4	# LATIN SMALL LETTER A WITH DIAERESIS
+0x8B	0x00E3	# LATIN SMALL LETTER A WITH TILDE
+0x8C	0x00E5	# LATIN SMALL LETTER A WITH RING ABOVE
+0x8D	0x00E7	# LATIN SMALL LETTER C WITH CEDILLA
+0x8E	0x00E9	# LATIN SMALL LETTER E WITH ACUTE
+0x8F	0x00E8	# LATIN SMALL LETTER E WITH GRAVE
+0x90	0x00EA	# LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x91	0x00EB	# LATIN SMALL LETTER E WITH DIAERESIS
+0x92	0x00ED	# LATIN SMALL LETTER I WITH ACUTE
+0x93	0x00EC	# LATIN SMALL LETTER I WITH GRAVE
+0x94	0x00EE	# LATIN SMALL LETTER I WITH CIRCUMFLEX
+0x95	0x00EF	# LATIN SMALL LETTER I WITH DIAERESIS
+0x96	0x00F1	# LATIN SMALL LETTER N WITH TILDE
+0x97	0x00F3	# LATIN SMALL LETTER O WITH ACUTE
+0x98	0x00F2	# LATIN SMALL LETTER O WITH GRAVE
+0x99	0x00F4	# LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x9A	0x00F6	# LATIN SMALL LETTER O WITH DIAERESIS
+0x9B	0x00F5	# LATIN SMALL LETTER O WITH TILDE
+0x9C	0x00FA	# LATIN SMALL LETTER U WITH ACUTE
+0x9D	0x00F9	# LATIN SMALL LETTER U WITH GRAVE
+0x9E	0x00FB	# LATIN SMALL LETTER U WITH CIRCUMFLEX
+0x9F	0x00FC	# LATIN SMALL LETTER U WITH DIAERESIS
+0xA0	0x2020	# DAGGER
+0xA1	0x00B0	# DEGREE SIGN
+0xA2	0x00A2	# CENT SIGN
+0xA3	0x00A3	# POUND SIGN
+0xA4	0x00A7	# SECTION SIGN
+0xA5	0x2022	# BULLET
+0xA6	0x00B6	# PILCROW SIGN
+0xA7	0x00DF	# LATIN SMALL LETTER SHARP S
+0xA8	0x00AE	# REGISTERED SIGN
+0xA9	0x00A9	# COPYRIGHT SIGN
+0xAA	0x2122	# TRADE MARK SIGN
+0xAB	0x00B4	# ACUTE ACCENT
+0xAC	0x00A8	# DIAERESIS
+0xAD	0x2260	# NOT EQUAL TO
+0xAE	0x00C6	# LATIN CAPITAL LETTER AE
+0xAF	0x00D8	# LATIN CAPITAL LETTER O WITH STROKE
+0xB0	0x221E	# INFINITY
+0xB1	0x00B1	# PLUS-MINUS SIGN
+0xB2	0x2264	# LESS-THAN OR EQUAL TO
+0xB3	0x2265	# GREATER-THAN OR EQUAL TO
+0xB4	0x00A5	# YEN SIGN
+0xB5	0x00B5	# MICRO SIGN
+0xB6	0x2202	# PARTIAL DIFFERENTIAL
+0xB7	0x2211	# N-ARY SUMMATION
+0xB8	0x220F	# N-ARY PRODUCT
+0xB9	0x03C0	# GREEK SMALL LETTER PI
+0xBA	0x222B	# INTEGRAL
+0xBB	0x00AA	# FEMININE ORDINAL INDICATOR
+0xBC	0x00BA	# MASCULINE ORDINAL INDICATOR
+0xBD	0x03A9	# GREEK CAPITAL LETTER OMEGA
+0xBE	0x00E6	# LATIN SMALL LETTER AE
+0xBF	0x00F8	# LATIN SMALL LETTER O WITH STROKE
+0xC0	0x00BF	# INVERTED QUESTION MARK
+0xC1	0x00A1	# INVERTED EXCLAMATION MARK
+0xC2	0x00AC	# NOT SIGN
+0xC3	0x221A	# SQUARE ROOT
+0xC4	0x0192	# LATIN SMALL LETTER F WITH HOOK
+0xC5	0x2248	# ALMOST EQUAL TO
+0xC6	0x2206	# INCREMENT
+0xC7	0x00AB	# LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xC8	0x00BB	# RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xC9	0x2026	# HORIZONTAL ELLIPSIS
+0xCA	0x00A0	# NO-BREAK SPACE
+0xCB	0x00C0	# LATIN CAPITAL LETTER A WITH GRAVE
+0xCC	0x00C3	# LATIN CAPITAL LETTER A WITH TILDE
+0xCD	0x00D5	# LATIN CAPITAL LETTER O WITH TILDE
+0xCE	0x0152	# LATIN CAPITAL LIGATURE OE
+0xCF	0x0153	# LATIN SMALL LIGATURE OE
+0xD0	0x2013	# EN DASH
+0xD1	0x2014	# EM DASH
+0xD2	0x201C	# LEFT DOUBLE QUOTATION MARK
+0xD3	0x201D	# RIGHT DOUBLE QUOTATION MARK
+0xD4	0x2018	# LEFT SINGLE QUOTATION MARK
+0xD5	0x2019	# RIGHT SINGLE QUOTATION MARK
+0xD6	0x00F7	# DIVISION SIGN
+0xD7	0x25CA	# LOZENGE
+0xD8	0x00FF	# LATIN SMALL LETTER Y WITH DIAERESIS
+0xD9	0x0178	# LATIN CAPITAL LETTER Y WITH DIAERESIS
+0xDA	0x2044	# FRACTION SLASH
+0xDB	0x20AC	# EURO SIGN
+0xDC	0x2039	# SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+0xDD	0x203A	# SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+0xDE	0xFB01	# LATIN SMALL LIGATURE FI
+0xDF	0xFB02	# LATIN SMALL LIGATURE FL
+0xE0	0x2021	# DOUBLE DAGGER
+0xE1	0x00B7	# MIDDLE DOT
+0xE2	0x201A	# SINGLE LOW-9 QUOTATION MARK
+0xE3	0x201E	# DOUBLE LOW-9 QUOTATION MARK
+0xE4	0x2030	# PER MILLE SIGN
+0xE5	0x00C2	# LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+0xE6	0x00CA	# LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+0xE7	0x00C1	# LATIN CAPITAL LETTER A WITH ACUTE
+0xE8	0x00CB	# LATIN CAPITAL LETTER E WITH DIAERESIS
+0xE9	0x00C8	# LATIN CAPITAL LETTER E WITH GRAVE
+0xEA	0x00CD	# LATIN CAPITAL LETTER I WITH ACUTE
+0xEB	0x00CE	# LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+0xEC	0x00CF	# LATIN CAPITAL LETTER I WITH DIAERESIS
+0xED	0x00CC	# LATIN CAPITAL LETTER I WITH GRAVE
+0xEE	0x00D3	# LATIN CAPITAL LETTER O WITH ACUTE
+0xEF	0x00D4	# LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+0xF0	0xF8FF	# Apple logo
+0xF1	0x00D2	# LATIN CAPITAL LETTER O WITH GRAVE
+0xF2	0x00DA	# LATIN CAPITAL LETTER U WITH ACUTE
+0xF3	0x00DB	# LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+0xF4	0x00D9	# LATIN CAPITAL LETTER U WITH GRAVE
+0xF5	0x0131	# LATIN SMALL LETTER DOTLESS I
+0xF6	0x02C6	# MODIFIER LETTER CIRCUMFLEX ACCENT
+0xF7	0x02DC	# SMALL TILDE
+0xF8	0x00AF	# MACRON
+0xF9	0x02D8	# BREVE
+0xFA	0x02D9	# DOT ABOVE
+0xFB	0x02DA	# RING ABOVE
+0xFC	0x00B8	# CEDILLA
+0xFD	0x02DD	# DOUBLE ACUTE ACCENT
+0xFE	0x02DB	# OGONEK
+0xFF	0x02C7	# CARON

Data/Encoding/Preprocessor/Mapping.hs

@@ -0,0 +1,160 @@
+module Data.Encoding.Preprocessor.Mapping where
+
+import Distribution.Simple.PreProcess
+import Distribution.Simple.Utils
+import System.IO
+import System.FilePath
+import Data.List (intersperse,unfoldr)
+import Data.Maybe
+import Data.Char
+import Data.Word
+import Data.Ix
+import Data.Bits
+import Data.Array.Static.Builder
+import Data.CharMap.Builder
+
+data MappingType
+    = ISOMapping
+    | JISMapping
+    deriving (Eq,Ord,Show,Read)
+
+readTranslation :: Int -> FilePath -> IO ([(Integer,Maybe Char)],[String])
+readTranslation offset file = do
+  cont <- fmap parseTranslationTable $ readFile file
+  let docstr = mapMaybe snd (takeWhile (null.fst) cont)
+  let trans =  mapMaybe (\(ln,comm) -> case drop offset ln of
+                                        [src] -> Just (src,Nothing)
+                                        [src,trg] -> Just (src,Just $ chr $ fromIntegral trg)
+                                        _ ->  Nothing) cont
+  return (trans,docstr)
+
+parseTranslationTable :: String -> [([Integer],Maybe String)]
+parseTranslationTable cont = map (\ln -> let (trans,comm) = break (=='#') ln
+                                         in (map read (words trans),case comm of
+                                                                      "" -> Nothing
+                                                                      _ -> Just (tail comm))
+                                 ) (lines cont)
+
+buildDocTable :: [(Integer,Maybe Char)] -> [String]
+buildDocTable = intersperse "".
+                map (\(i,mbc) -> show i ++ (case mbc of
+                                             Nothing -> ""
+                                             Just c -> "\t = &#"++show (ord c)++"; ("++show (ord c)++")"))
+
+{-fillTranslations :: (Ix a,Show a) => a -> a -> [(a,Maybe Char)] -> [(a,Maybe Char)]
+fillTranslations f t = merge (range (f,t))
+    where
+      merge xs [] = map (\x -> (x,Nothing)) xs
+      merge [] cs  = error $ "Data.Encoding.Helper.Template.fillTranslations: Character translations out of range: " ++ show cs
+      merge (x:xs) (y:ys) = if x < fst y
+                            then (x,Nothing):(merge xs (y:ys))
+                            else y:(merge xs ys)-}
+
+fillTranslations :: (Enum a,Eq a) => [(a,Maybe Char)] -> (a,a,[Maybe Char])
+fillTranslations [] = error "fillTranslations: zero elements"
+fillTranslations ((s,c):rest) = let (e,r) = fill' s rest
+                                    fill' cur [] = (cur,[])
+                                    fill' cur all@((n,c):rest2) = if succ cur == n
+                                                                  then (let (e',res) = fill' n rest2
+                                                                        in (e',c:res))
+                                                                  else (let (e',res) = fill' (succ cur) all
+                                                                        in (e',Nothing:res))
+                                in (s,e,c:r)
+
+validTranslations :: [(a,Maybe Char)] -> [(a,Char)]
+validTranslations = mapMaybe (\(n,mc) -> case mc of
+                                          Nothing -> Nothing
+                                          Just c -> Just (n,c))
+
+mappingPreprocessor :: PreProcessor
+mappingPreprocessor = PreProcessor
+                  {platformIndependent = True
+                  ,runPreProcessor = \(sbase,sfile) (tbase,tfile) verb -> do
+                                       let (dir,fn) = splitFileName sfile
+                                       let (bname,ext) = splitExtensions fn
+                                       let dirs = splitDirectories dir
+                                       let tp = case ext of
+                                                  ".mapping" -> ISOMapping
+                                                  ".mapping2" -> JISMapping
+                                       info verb (tfile++" generated from mapping "++sfile)
+                                       preprocessMapping tp (sbase </> sfile) (tbase </> tfile) dirs bname
+                  }
+
+preprocessMapping :: MappingType -> FilePath -> FilePath -> [String] -> String -> IO ()
+preprocessMapping tp src trg mods name = do
+  (trans,doc) <- readTranslation 0 src
+  let mod = concat $ intersperse "." (mods++[name])
+  let wsize = case tp of
+                ISOMapping -> 1
+                JISMapping -> 2
+  let bsize = show (wsize*8) ++ (if wsize > 1 then "be" else "")
+
+  --let (larr,off,arr) = staticArray32 trans
+  let (sarr,earr,els) = fillTranslations trans
+  {-let (lmp,idx,val) = staticMap wsize trans-}
+  let arrname = "decoding_array_"++name
+  let mpname = "encoding_map_"++name
+  let bcheck exp = if sarr/=0 || earr/=255
+                   then ("(if "++
+                         concat (intersperse "||" $ (if sarr/=0 then ["w<"++show sarr] else [])++(if earr/=255 then ["w>"++show earr] else []))++
+                         " then throwException $ IllegalCharacter $ fromIntegral w else "++exp++")"
+                        ) else exp
+  let mp = buildCharMap (mapMaybe (\(i,c) -> do
+                                     rc <- c
+                                     return $ SingleMapping 
+                                            rc 
+                                            (reverse $ unfoldr (\(w,n) -> if n == 0 
+                                                                         then Nothing 
+                                                                         else Just (fromIntegral w,(w `shiftR` 8,n-1))) (i,wsize))
+                             ) trans
+                        )
+  {-let mp = case wsize of
+             1 -> buildStaticMap (mapMaybe (\(i,c) -> case c of
+                                                      Nothing -> Nothing
+                                                      Just rc -> Just (rc,fromIntegral i::Word8)) trans)
+             2 -> buildStaticMap (mapMaybe (\(i,c) -> case c of
+                                                      Nothing -> Nothing
+                                                      Just rc -> Just (rc,fromIntegral i::Word16)) trans)-}
+  writeFile trg $ unlines $
+                ["{- This file has been auto-generated. Do not edit it. -}"
+                ,"{-# LANGUAGE MagicHash,DeriveDataTypeable #-}"
+                ]++(case doc of
+                      [] -> ["{- |"]
+                      _ -> ("{- | "++head doc):(map (\ln -> "     "++ln) (tail doc)))
+                ++[""]
+                ++buildDocTable trans
+                ++[" -}"]
+                ++
+                ["module "++mod++"("++name++"(..)) where"
+                ,""
+                ,"import Data.Encoding.Base"
+                ,"import Data.Encoding.ByteSource"
+                ,"import Data.Encoding.ByteSink"
+                ,"import Data.Encoding.Exception"
+                ,"import Data.CharMap"
+                ,"import Data.Array.Static"
+                ,"import Data.Map.Static"
+                ,"import Control.Throws"
+                ,"import Prelude hiding (lookup)"
+                ,"import Data.Word"
+                ,""
+                ,"import Data.Typeable"
+                ,""
+                ,"data "++name++" = "++name
+                ,"  deriving (Show,Eq,Typeable)"
+                ,""
+                ,arrname++" = "++buildStaticArray (sarr,earr) els
+                ,""
+                ,mpname++" :: CharMap"
+                ,mpname++" = "++mp
+                ,""
+                ,"instance Encoding "++name++" where"
+                ,"  decodeChar _ = do"
+                ,"    w <- fetchWord"++bsize
+                ,"    "++bcheck "return ()"
+                ,"    case "++arrname++"!w of"
+                ,"      Nothing -> throwException $ IllegalCharacter $ fromIntegral w"
+                ,"      Just c -> return c"
+                ,"  encodeChar _ c = mapEncode c "++mpname
+                ,"  encodeable _ c = mapMember c "++mpname
+                ]

Data/Encoding/Preprocessor/XMLMapping.hs

@@ -0,0 +1,582 @@
+module Data.Encoding.Preprocessor.XMLMapping where
+
+import Data.Word
+import Text.Read
+import Text.Show
+import Numeric
+import Data.List (find)
+import Data.Char
+import Text.XML.HaXml.XmlContent
+import Text.XML.HaXml.OneOfN
+import Text.XML.HaXml.Types
+
+testFile :: FilePath -> IO CharacterMapping
+testFile fp = fReadXml fp
+
+{-Type decls-}
+
+data CharacterMapping = CharacterMapping CharacterMapping_Attrs
+                                         (Maybe History)
+                                         (OneOf2 Validity Stateful_siso)
+                                         Assignments
+                      deriving (Eq,Show)
+data CharacterMapping_Attrs = CharacterMapping_Attrs
+    { characterMappingId :: String
+    , characterMappingVersion :: String
+    , characterMappingDescription :: (Maybe String)
+    , characterMappingContact :: (Maybe String)
+    , characterMappingRegistrationAuthority :: (Maybe String)
+    , characterMappingRegistrationName :: (Maybe String)
+    , characterMappingCopyright :: (Maybe String)
+    , characterMappingBidiOrder :: (Defaultable CharacterMapping_bidiOrder)
+    , characterMappingCombiningOrder :: (Defaultable CharacterMapping_combiningOrder)
+    , characterMappingNormalization :: (Defaultable CharacterMapping_normalization)
+    } deriving (Eq,Show)
+data CharacterMapping_bidiOrder = CharacterMapping_bidiOrder_logical
+                                   |  CharacterMapping_bidiOrder_RTL  | 
+                                  CharacterMapping_bidiOrder_LTR
+                                deriving (Eq,Show)
+data CharacterMapping_combiningOrder = CharacterMapping_combiningOrder_before
+                                        |  CharacterMapping_combiningOrder_after
+                                     deriving (Eq,Show)
+data CharacterMapping_normalization = CharacterMapping_normalization_undetermined
+                                       |  CharacterMapping_normalization_neither  | 
+                                      CharacterMapping_normalization_NFC  | 
+                                      CharacterMapping_normalization_NFD  | 
+                                      CharacterMapping_normalization_NFC_NFD
+                                    deriving (Eq,Show)
+data Stateful_siso = Stateful_siso Validity Validity
+                   deriving (Eq,Show)
+newtype History = History (List1 Modified) 		deriving (Eq,Show)
+data Modified = Modified Modified_Attrs String
+              deriving (Eq,Show)
+data Modified_Attrs = Modified_Attrs
+    { modifiedVersion :: String
+    , modifiedDate :: String
+    } deriving (Eq,Show)
+newtype Validity = Validity (List1 State) 		deriving (Eq,Show)
+data State = State
+    { stateType :: String
+    , stateNext :: String
+    , stateS :: ByteSequence
+    , stateE :: (Maybe ByteSequence)
+    , stateMax :: (Maybe String)
+    } deriving (Eq,Show)
+data Assignments = Assignments Assignments_Attrs [A] [Fub] [Fbu]
+                               [Sub1] [Range]
+                 deriving (Eq,Show)
+data Assignments_Attrs = Assignments_Attrs
+    { assignmentsSub :: (Defaultable String)
+    , assignmentsSub1 :: (Maybe String)
+    } deriving (Eq,Show)
+data A = A
+    { aB :: ByteSequence
+    , aU :: CodePoints
+    , aC :: (Maybe String)
+    , aV :: (Maybe String)
+    } deriving (Eq,Show)
+data Fub = Fub
+    { fubB :: ByteSequence
+    , fubU :: CodePoints
+    , fubC :: (Maybe String)
+    , fubRu :: (Maybe String)
+    , fubRc :: (Maybe String)
+    , fubV :: (Maybe String)
+    } deriving (Eq,Show)
+data Fbu = Fbu
+    { fbuB :: ByteSequence
+    , fbuU :: CodePoints
+    , fbuV :: (Maybe String)
+    } deriving (Eq,Show)
+data Sub1 = Sub1
+    { sub1U :: CodePoints
+    , sub1C :: (Maybe String)
+    , sub1V :: (Maybe String)
+    } deriving (Eq,Show)
+data Range = Range
+    { rangeBFirst :: ByteSequence
+    , rangeBLast :: ByteSequence
+    , rangeUFirst :: CodePoints
+    , rangeULast :: CodePoints
+    , rangeBMin :: ByteSequence
+    , rangeBMax :: ByteSequence
+    , rangeV :: (Maybe String)
+    } deriving (Eq,Show)
+data Iso2022 = Iso2022 (Maybe Default2022)
+                       (List1 (OneOf5 Escape Si So Ss2 Ss3))
+             deriving (Eq,Show)
+data Default2022 = Default2022
+    { default2022Name :: String
+    } deriving (Eq,Show)
+data Escape = Escape
+    { escapeSequence :: String
+    , escapeName :: String
+    } deriving (Eq,Show)
+newtype Si = Si (List1 Designator) 		deriving (Eq,Show)
+newtype So = So (List1 Designator) 		deriving (Eq,Show)
+newtype Ss2 = Ss2 (List1 Designator) 		deriving (Eq,Show)
+newtype Ss3 = Ss3 (List1 Designator) 		deriving (Eq,Show)
+data Designator = Designator
+    { designatorSequence :: String
+    , designatorName :: String
+    } deriving (Eq,Show)
+
+newtype ByteSequence = BS [Word8] deriving Eq
+
+newtype CodePoints = CP [Char] deriving Eq
+
+{-Instance decls-}
+
+instance HTypeable CharacterMapping where
+    toHType x = Defined "characterMapping" [] []
+instance XmlContent CharacterMapping where
+    toContents (CharacterMapping as a b c) =
+        [CElem (Elem (N "characterMapping") (toAttrs as) (maybe [] toContents a
+                                                      ++ toContents b
+                                                      ++ toContents c)) ()]
+    parseContents = do
+        { e@(Elem _ as _) <- element ["characterMapping"]
+        ; interior e $ return (CharacterMapping (fromAttrs as))
+                       `apply` optional parseContents `apply` parseContents `apply` parseContents
+        } `adjustErr` ("in <characterMapping>, "++)
+instance XmlAttributes CharacterMapping_Attrs where
+    fromAttrs as =
+        CharacterMapping_Attrs
+          { characterMappingId = definiteA fromAttrToStr "characterMapping" "id" as
+          , characterMappingVersion = definiteA fromAttrToStr "characterMapping" "version" as
+          , characterMappingDescription = possibleA fromAttrToStr "description" as
+          , characterMappingContact = possibleA fromAttrToStr "contact" as
+          , characterMappingRegistrationAuthority = possibleA fromAttrToStr "registrationAuthority" as
+          , characterMappingRegistrationName = possibleA fromAttrToStr "registrationName" as
+          , characterMappingCopyright = possibleA fromAttrToStr "copyright" as
+          , characterMappingBidiOrder = defaultA fromAttrToTyp CharacterMapping_bidiOrder_logical "bidiOrder" as
+          , characterMappingCombiningOrder = defaultA fromAttrToTyp CharacterMapping_combiningOrder_after "combiningOrder" as
+          , characterMappingNormalization = defaultA fromAttrToTyp CharacterMapping_normalization_undetermined "normalization" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrStr "id" (characterMappingId v)
+        , toAttrFrStr "version" (characterMappingVersion v)
+        , maybeToAttr toAttrFrStr "description" (characterMappingDescription v)
+        , maybeToAttr toAttrFrStr "contact" (characterMappingContact v)
+        , maybeToAttr toAttrFrStr "registrationAuthority" (characterMappingRegistrationAuthority v)
+        , maybeToAttr toAttrFrStr "registrationName" (characterMappingRegistrationName v)
+        , maybeToAttr toAttrFrStr "copyright" (characterMappingCopyright v)
+        , defaultToAttr toAttrFrTyp "bidiOrder" (characterMappingBidiOrder v)
+        , defaultToAttr toAttrFrTyp "combiningOrder" (characterMappingCombiningOrder v)
+        , defaultToAttr toAttrFrTyp "normalization" (characterMappingNormalization v)
+        ]
+
+instance XmlAttrType CharacterMapping_bidiOrder where
+    fromAttrToTyp n (n',v)
+        | N n==n'   = translate (attr2str v)
+        | otherwise = Nothing
+      where translate "logical" = Just CharacterMapping_bidiOrder_logical
+            translate "RTL" = Just CharacterMapping_bidiOrder_RTL
+            translate "LTR" = Just CharacterMapping_bidiOrder_LTR
+            translate _ = Nothing
+    toAttrFrTyp n CharacterMapping_bidiOrder_logical = Just (N n, str2attr "logical")
+    toAttrFrTyp n CharacterMapping_bidiOrder_RTL = Just (N n, str2attr "RTL")
+    toAttrFrTyp n CharacterMapping_bidiOrder_LTR = Just (N n, str2attr "LTR")
+
+instance XmlAttrType CharacterMapping_combiningOrder where
+    fromAttrToTyp n (n',v)
+        | N n==n'   = translate (attr2str v)
+        | otherwise = Nothing
+      where translate "before" = Just CharacterMapping_combiningOrder_before
+            translate "after" = Just CharacterMapping_combiningOrder_after
+            translate _ = Nothing
+    toAttrFrTyp n CharacterMapping_combiningOrder_before = Just (N n, str2attr "before")
+    toAttrFrTyp n CharacterMapping_combiningOrder_after = Just (N n, str2attr "after")
+
+instance XmlAttrType CharacterMapping_normalization where
+    fromAttrToTyp n (n',v)
+        | N n==n'   = translate (attr2str v)
+        | otherwise = Nothing
+      where translate "undetermined" = Just CharacterMapping_normalization_undetermined
+            translate "neither" = Just CharacterMapping_normalization_neither
+            translate "NFC" = Just CharacterMapping_normalization_NFC
+            translate "NFD" = Just CharacterMapping_normalization_NFD
+            translate "NFC_NFD" = Just CharacterMapping_normalization_NFC_NFD
+            translate _ = Nothing
+    toAttrFrTyp n CharacterMapping_normalization_undetermined = Just (N n, str2attr "undetermined")
+    toAttrFrTyp n CharacterMapping_normalization_neither = Just (N n, str2attr "neither")
+    toAttrFrTyp n CharacterMapping_normalization_NFC = Just (N n, str2attr "NFC")
+    toAttrFrTyp n CharacterMapping_normalization_NFD = Just (N n, str2attr "NFD")
+    toAttrFrTyp n CharacterMapping_normalization_NFC_NFD = Just (N n, str2attr "NFC_NFD")
+
+instance XmlAttrType ByteSequence where
+    fromAttrToTyp n (n',v)
+        | N n==n' = parseByteSequence (attr2str v)
+        | otherwise = Nothing
+    toAttrFrTyp n bs = Just (N n, str2attr $ show bs)
+
+parseByteSequence :: String -> Maybe ByteSequence
+parseByteSequence str = do
+  seq <- mapM (\w -> do
+                (res,_) <- find (null.snd) (readHex w)
+                return res
+             ) (words str)
+  return $ BS seq
+
+instance Show ByteSequence where
+    show (BS seq) = foldl (\f w -> f . (showChar ' ') . (showHex w)) id seq ""
+
+instance XmlAttrType CodePoints where
+    fromAttrToTyp n (n',v)
+        | N n==n' = parseCodePoints (attr2str v)
+        | otherwise = Nothing
+    toAttrFrTyp n bs = Just (N n, str2attr $ show bs)
+
+parseCodePoints :: String -> Maybe CodePoints
+parseCodePoints str = do
+  seq <- mapM (\w -> do
+                (res,_) <- find (null.snd) (readHex w)
+                return (chr res)
+             ) (words str)
+  return $ CP seq
+
+instance Show CodePoints where
+    show (CP seq) = foldl (\f w -> f . (showChar ' ') . (showHex (ord w))) id seq ""
+
+instance HTypeable Stateful_siso where
+    toHType x = Defined "stateful_siso" [] []
+instance XmlContent Stateful_siso where
+    toContents (Stateful_siso a b) =
+        [CElem (Elem (N "stateful_siso") [] (toContents a ++ toContents b)) ()]
+    parseContents = do
+        { e@(Elem _ [] _) <- element ["stateful_siso"]
+        ; interior e $ return (Stateful_siso) `apply` parseContents
+                       `apply` parseContents
+        } `adjustErr` ("in <stateful_siso>, "++)
+
+instance HTypeable History where
+    toHType x = Defined "history" [] []
+instance XmlContent History where
+    toContents (History a) =
+        [CElem (Elem (N "history") [] (toContents a)) ()]
+    parseContents = do
+        { e@(Elem _ [] _) <- element ["history"]
+        ; interior e $ return (History) `apply` parseContents
+        } `adjustErr` ("in <history>, "++)
+
+instance HTypeable Modified where
+    toHType x = Defined "modified" [] []
+instance XmlContent Modified where
+    toContents (Modified as a) =
+        [CElem (Elem (N "modified") (toAttrs as) (toText a)) ()]
+    parseContents = do
+        { e@(Elem _ as _) <- element ["modified"]
+        ; interior e $ return (Modified (fromAttrs as))
+                       `apply` (text `onFail` return "")
+        } `adjustErr` ("in <modified>, "++)
+instance XmlAttributes Modified_Attrs where
+    fromAttrs as =
+        Modified_Attrs
+          { modifiedVersion = definiteA fromAttrToStr "modified" "version" as
+          , modifiedDate = definiteA fromAttrToStr "modified" "date" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrStr "version" (modifiedVersion v)
+        , toAttrFrStr "date" (modifiedDate v)
+        ]
+
+instance HTypeable Validity where
+    toHType x = Defined "validity" [] []
+instance XmlContent Validity where
+    toContents (Validity a) =
+        [CElem (Elem (N "validity") [] (toContents a)) ()]
+    parseContents = do
+        { e@(Elem _ [] _) <- element ["validity"]
+        ; interior e $ return (Validity) `apply` parseContents
+        } `adjustErr` ("in <validity>, "++)
+
+instance HTypeable State where
+    toHType x = Defined "state" [] []
+instance XmlContent State where
+    toContents as =
+        [CElem (Elem (N "state") (toAttrs as) []) ()]
+    parseContents = do
+        { (Elem _ as []) <- element ["state"]
+        ; return (fromAttrs as)
+        } `adjustErr` ("in <state>, "++)
+instance XmlAttributes State where
+    fromAttrs as =
+        State
+          { stateType = definiteA fromAttrToStr "state" "type" as
+          , stateNext = definiteA fromAttrToStr "state" "next" as
+          , stateS = definiteA fromAttrToTyp "state" "s" as
+          , stateE = possibleA fromAttrToTyp "e" as
+          , stateMax = possibleA fromAttrToStr "max" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrStr "type" (stateType v)
+        , toAttrFrStr "next" (stateNext v)
+        , toAttrFrTyp "s" (stateS v)
+        , maybeToAttr toAttrFrTyp "e" (stateE v)
+        , maybeToAttr toAttrFrStr "max" (stateMax v)
+        ]
+
+instance HTypeable Assignments where
+    toHType x = Defined "assignments" [] []
+instance XmlContent Assignments where
+    toContents (Assignments as a b c d e) =
+        [CElem (Elem (N "assignments") (toAttrs as) (concatMap toContents a ++
+                                                 concatMap toContents b ++ concatMap toContents c ++
+                                                 concatMap toContents d ++
+                                                 concatMap toContents e)) ()]
+    parseContents = do
+        { e@(Elem _ as _) <- element ["assignments"]
+        ; interior e $ return (Assignments (fromAttrs as))
+                       `apply` many parseContents `apply` many parseContents
+                       `apply` many parseContents `apply` many parseContents
+                       `apply` many parseContents
+        } `adjustErr` ("in <assignments>, "++)
+instance XmlAttributes Assignments_Attrs where
+    fromAttrs as =
+        Assignments_Attrs
+          { assignmentsSub = defaultA fromAttrToStr "1A" "sub" as
+          , assignmentsSub1 = possibleA fromAttrToStr "sub1" as
+          }
+    toAttrs v = catMaybes 
+        [ defaultToAttr toAttrFrStr "sub" (assignmentsSub v)
+        , maybeToAttr toAttrFrStr "sub1" (assignmentsSub1 v)
+        ]
+
+instance HTypeable A where
+    toHType x = Defined "a" [] []
+instance XmlContent A where
+    toContents as =
+        [CElem (Elem (N "a") (toAttrs as) []) ()]
+    parseContents = do
+        { (Elem _ as []) <- element ["a"]
+        ; return (fromAttrs as)
+        } `adjustErr` ("in <a>, "++)
+instance XmlAttributes A where
+    fromAttrs as =
+        A { aB = definiteA fromAttrToTyp "a" "b" as
+          , aU = definiteA fromAttrToTyp "a" "u" as
+          , aC = possibleA fromAttrToStr "c" as
+          , aV = possibleA fromAttrToStr "v" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrTyp "b" (aB v)
+        , toAttrFrTyp "u" (aU v)
+        , maybeToAttr toAttrFrStr "c" (aC v)
+        , maybeToAttr toAttrFrStr "v" (aV v)
+        ]
+
+instance HTypeable Fub where
+    toHType x = Defined "fub" [] []
+instance XmlContent Fub where
+    toContents as =
+        [CElem (Elem (N "fub") (toAttrs as) []) ()]
+    parseContents = do
+        { (Elem _ as []) <- element ["fub"]
+        ; return (fromAttrs as)
+        } `adjustErr` ("in <fub>, "++)
+instance XmlAttributes Fub where
+    fromAttrs as =
+        Fub
+          { fubB = definiteA fromAttrToTyp "fub" "b" as
+          , fubU = definiteA fromAttrToTyp "fub" "u" as
+          , fubC = possibleA fromAttrToStr "c" as
+          , fubRu = possibleA fromAttrToStr "ru" as
+          , fubRc = possibleA fromAttrToStr "rc" as
+          , fubV = possibleA fromAttrToStr "v" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrTyp "b" (fubB v)
+        , toAttrFrTyp "u" (fubU v)
+        , maybeToAttr toAttrFrStr "c" (fubC v)
+        , maybeToAttr toAttrFrStr "ru" (fubRu v)
+        , maybeToAttr toAttrFrStr "rc" (fubRc v)
+        , maybeToAttr toAttrFrStr "v" (fubV v)
+        ]
+
+instance HTypeable Fbu where
+    toHType x = Defined "fbu" [] []
+instance XmlContent Fbu where
+    toContents as =
+        [CElem (Elem (N "fbu") (toAttrs as) []) ()]
+    parseContents = do
+        { (Elem _ as []) <- element ["fbu"]
+        ; return (fromAttrs as)
+        } `adjustErr` ("in <fbu>, "++)
+instance XmlAttributes Fbu where
+    fromAttrs as =
+        Fbu
+          { fbuB = definiteA fromAttrToTyp "fbu" "b" as
+          , fbuU = definiteA fromAttrToTyp "fbu" "u" as
+          , fbuV = possibleA fromAttrToStr "v" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrTyp "b" (fbuB v)
+        , toAttrFrTyp "u" (fbuU v)
+        , maybeToAttr toAttrFrStr "v" (fbuV v)
+        ]
+
+instance HTypeable Sub1 where
+    toHType x = Defined "sub1" [] []
+instance XmlContent Sub1 where
+    toContents as =
+        [CElem (Elem (N "sub1") (toAttrs as) []) ()]
+    parseContents = do
+        { (Elem _ as []) <- element ["sub1"]
+        ; return (fromAttrs as)
+        } `adjustErr` ("in <sub1>, "++)
+instance XmlAttributes Sub1 where
+    fromAttrs as =
+        Sub1
+          { sub1U = definiteA fromAttrToTyp "sub1" "u" as
+          , sub1C = possibleA fromAttrToStr "c" as
+          , sub1V = possibleA fromAttrToStr "v" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrTyp "u" (sub1U v)
+        , maybeToAttr toAttrFrStr "c" (sub1C v)
+        , maybeToAttr toAttrFrStr "v" (sub1V v)
+        ]
+
+instance HTypeable Range where
+    toHType x = Defined "range" [] []
+instance XmlContent Range where
+    toContents as =
+        [CElem (Elem (N "range") (toAttrs as) []) ()]
+    parseContents = do
+        { (Elem _ as []) <- element ["range"]
+        ; return (fromAttrs as)
+        } `adjustErr` ("in <range>, "++)
+instance XmlAttributes Range where
+    fromAttrs as =
+        Range
+          { rangeBFirst = definiteA fromAttrToTyp "range" "bFirst" as
+          , rangeBLast = definiteA fromAttrToTyp "range" "bLast" as
+          , rangeUFirst = definiteA fromAttrToTyp "range" "uFirst" as
+          , rangeULast = definiteA fromAttrToTyp "range" "uLast" as
+          , rangeBMin = definiteA fromAttrToTyp "range" "bMin" as
+          , rangeBMax = definiteA fromAttrToTyp "range" "bMax" as
+          , rangeV = possibleA fromAttrToStr "v" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrTyp "bFirst" (rangeBFirst v)
+        , toAttrFrTyp "bLast" (rangeBLast v)
+        , toAttrFrTyp "uFirst" (rangeUFirst v)
+        , toAttrFrTyp "uLast" (rangeULast v)
+        , toAttrFrTyp "bMin" (rangeBMin v)
+        , toAttrFrTyp "bMax" (rangeBMax v)
+        , maybeToAttr toAttrFrStr "v" (rangeV v)
+        ]
+
+instance HTypeable Iso2022 where
+    toHType x = Defined "iso2022" [] []
+instance XmlContent Iso2022 where
+    toContents (Iso2022 a b) =
+        [CElem (Elem (N "iso2022") [] (maybe [] toContents a ++
+                                   toContents b)) ()]
+    parseContents = do
+        { e@(Elem _ [] _) <- element ["iso2022"]
+        ; interior e $ return (Iso2022) `apply` optional parseContents
+                       `apply` parseContents
+        } `adjustErr` ("in <iso2022>, "++)
+
+instance HTypeable Default2022 where
+    toHType x = Defined "default2022" [] []
+instance XmlContent Default2022 where
+    toContents as =
+        [CElem (Elem (N "default2022") (toAttrs as) []) ()]
+    parseContents = do
+        { (Elem _ as []) <- element ["default2022"]
+        ; return (fromAttrs as)
+        } `adjustErr` ("in <default2022>, "++)
+instance XmlAttributes Default2022 where
+    fromAttrs as =
+        Default2022
+          { default2022Name = definiteA fromAttrToStr "default2022" "name" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrStr "name" (default2022Name v)
+        ]
+
+instance HTypeable Escape where
+    toHType x = Defined "escape" [] []
+instance XmlContent Escape where
+    toContents as =
+        [CElem (Elem (N "escape") (toAttrs as) []) ()]
+    parseContents = do
+        { (Elem _ as []) <- element ["escape"]
+        ; return (fromAttrs as)
+        } `adjustErr` ("in <escape>, "++)
+instance XmlAttributes Escape where
+    fromAttrs as =
+        Escape
+          { escapeSequence = definiteA fromAttrToStr "escape" "sequence" as
+          , escapeName = definiteA fromAttrToStr "escape" "name" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrStr "sequence" (escapeSequence v)
+        , toAttrFrStr "name" (escapeName v)
+        ]
+
+instance HTypeable Si where
+    toHType x = Defined "si" [] []
+instance XmlContent Si where
+    toContents (Si a) =
+        [CElem (Elem (N "si") [] (toContents a)) ()]
+    parseContents = do
+        { e@(Elem _ [] _) <- element ["si"]
+        ; interior e $ return (Si) `apply` parseContents
+        } `adjustErr` ("in <si>, "++)
+
+instance HTypeable So where
+    toHType x = Defined "so" [] []
+instance XmlContent So where
+    toContents (So a) =
+        [CElem (Elem (N "so") [] (toContents a)) ()]
+    parseContents = do
+        { e@(Elem _ [] _) <- element ["so"]
+        ; interior e $ return (So) `apply` parseContents
+        } `adjustErr` ("in <so>, "++)
+
+instance HTypeable Ss2 where
+    toHType x = Defined "ss2" [] []
+instance XmlContent Ss2 where
+    toContents (Ss2 a) =
+        [CElem (Elem (N "ss2") [] (toContents a)) ()]
+    parseContents = do
+        { e@(Elem _ [] _) <- element ["ss2"]
+        ; interior e $ return (Ss2) `apply` parseContents
+        } `adjustErr` ("in <ss2>, "++)
+
+instance HTypeable Ss3 where
+    toHType x = Defined "ss3" [] []
+instance XmlContent Ss3 where
+    toContents (Ss3 a) =
+        [CElem (Elem (N "ss3") [] (toContents a)) ()]
+    parseContents = do
+        { e@(Elem _ [] _) <- element ["ss3"]
+        ; interior e $ return (Ss3) `apply` parseContents
+        } `adjustErr` ("in <ss3>, "++)
+
+instance HTypeable Designator where
+    toHType x = Defined "designator" [] []
+instance XmlContent Designator where
+    toContents as =
+        [CElem (Elem (N "designator") (toAttrs as) []) ()]
+    parseContents = do
+        { (Elem _ as []) <- element ["designator"]
+        ; return (fromAttrs as)
+        } `adjustErr` ("in <designator>, "++)
+instance XmlAttributes Designator where
+    fromAttrs as =
+        Designator
+          { designatorSequence = definiteA fromAttrToStr "designator" "sequence" as
+          , designatorName = definiteA fromAttrToStr "designator" "name" as
+          }
+    toAttrs v = catMaybes 
+        [ toAttrFrStr "sequence" (designatorSequence v)
+        , toAttrFrStr "name" (designatorName v)
+        ]
+
+
+
+{-Done-}

Data/Encoding/Preprocessor/XMLMappingBuilder.hs

@@ -0,0 +1,316 @@
+{-# LANGUAGE ParallelListComp #-}
+module Data.Encoding.Preprocessor.XMLMappingBuilder where
+
+import Data.Word
+import Data.List
+import Data.Ord
+import Data.Char
+import Data.Map (Map)
+import qualified Data.Map as Map
+import Data.Array.Static.Builder
+import Data.CharMap.Builder
+import Data.Encoding.Preprocessor.XMLMapping
+import Distribution.Simple.PreProcess
+import System.FilePath
+import Text.XML.HaXml.OneOfN
+import Text.XML.HaXml.XmlContent
+import Control.Exception (assert)
+
+xmlPreprocessor :: PreProcessor
+xmlPreprocessor = PreProcessor
+                  { platformIndependent = True
+                  , runPreProcessor = \src trg verb -> do
+                                        createModuleFromFile src trg
+                  }
+
+description :: CharacterMapping -> Maybe String
+description (CharacterMapping attrs _ _ _) = characterMappingDescription attrs
+
+createModuleFromFile (sbase,sfile) (tbase,tfile) = do
+  xml <- testFile (sbase </> sfile)
+  let (dir,fn) = splitFileName sfile
+  let (bname,ext) = splitExtensions fn
+  let dirs = splitDirectories dir
+  let body = buildDecisionTree minBound maxBound "ch" (encodingElements xml)
+  let body2 = createDecoding (states xml) (decodingElements xml)
+  let mpname = "encoding_map_"++bname
+  let mp = buildCharMap $ [SingleMapping c w | (c,w) <- assignments xml]
+           ++[ RangeMapping
+               st end
+               (foldl (\v (w,mi,ma) -> v*((fromIntegral $ ma-mi)+1) + (fromIntegral (w-mi))) 0 (zip3 bfirst bmin bmax))
+               [(min,max-min+1) | min <- bmin | max <- bmax]
+               | (st,end,bfirst,blast,bmin,bmax) <- ranges xml ]
+  writeFile (tbase</>tfile) $ unlines $
+             ["{- This file has been auto-generated. Do not edit it. -}"
+             ,"{-# LANGUAGE MagicHash,DeriveDataTypeable #-}"]++
+                (case description xml of
+                   Nothing -> []
+                   Just str -> ["{- | "++str++" -}"]) ++
+                ["module "++concat (intersperse "." (dirs++[bname]))
+                ,"  ("++bname++"("++bname++"))"
+                ,"  where"
+                ,""
+                ,"import Control.Throws"
+                ,"import Data.Encoding.Base"
+                ,"import Data.Encoding.ByteSink"
+                ,"import Data.Encoding.ByteSource"
+                ,"import Data.Encoding.Exception"
+                ,"import Data.Array.Static"
+                ,"import Data.Map.Static"
+                ,"import Data.CharMap"
+                ,"import Data.Char"
+                ,"import Data.Word"
+                ,"import Data.Typeable"
+                ,""
+                ,"data "++bname++" = "++bname
+                ,"  deriving (Eq,Show,Typeable)"
+                ,""
+                ,mpname++" :: CharMap"
+                ,mpname++" = "++mp
+                ,""
+                ,"instance Encoding "++bname++" where"
+                ,"  encodeChar _ ch = mapEncode ch "++mpname
+                ,"  decodeChar _ = "++body2
+                ,"  encodeable _ ch = mapMember ch "++mpname
+                ]
+
+decodingValueRange :: [(Word8,Word8)] -> DecodingElement -> (Int,Int)
+decodingValueRange path (DecodingElement c ws)
+    = let v = foldl (\n (w,(lo,up)) -> n*((fromIntegral $ up-lo)+1) + (fromIntegral $ w - lo)) 0 (zip ws path)
+      in (v,v)
+decodingValueRange path (DecodingRange first last bfirst blast bmin bmax)
+    = assert (zip bmin bmax == path) $
+      (decodingValue path bfirst
+      ,decodingValue path blast)
+
+decodingValue :: [(Word8,Word8)] -> [Word8] -> Int
+decodingValue path ws
+    = foldl (\n (w,(lo,up)) -> n*((fromIntegral $ up-lo) + 1) + (fromIntegral $ w - lo))
+      0 (zip ws path)
+
+type StateMachine = Map String [(Word8,Word8,String)]
+
+createDecoding :: StateMachine -> [DecodingElement] -> String
+createDecoding sm els = create' els [] 0 "FIRST"
+    where
+      create' els path n st = let trans = sortBy (\(s1,e1,st1) (s2,e2,st2) -> compare s1 s2) $ sm Map.! st
+                              in "(fetchWord8 >>= \\w"++show n++" -> " ++ tree' n path els trans 0 255++")"
+
+      tree' :: Int -> [(Word8,Word8)] -> [DecodingElement] -> [(Word8,Word8,String)] -> Word8 -> Word8 -> String
+      tree' n path els [] _ _ = illWord $ "w"++show n
+      tree' n path els [(s,e,nst)] bl br
+          = let e1 = if s > bl
+                     then "(if w"++show n++" < "++show s++" then "++illWord ("w"++show n)++" else "++e2++")"
+                     else e2
+                e2 = if e < br
+                     then "(if w"++show n++" > "++show e++" then "++illWord ("w"++show n)++" else "++e3++")"
+                     else e3
+                e3 = if nst == "VALID"
+                     then array' rpath sels
+                     else "{- for "++nst++"-}" ++ create' nels npath (n+1) nst
+                npath = (s,e):path
+                rpath = reverse npath
+                sels = sortBy (comparing (decodingValueRange rpath)) nels
+                nels = filter (\el -> let (ll,lr) = (decodingLimits el)!!n in ll>=s && lr <= e) els
+            in e1
+      tree' n path els trans bl br
+          = let (left,right@((b,_,_):_)) = splitAt (length trans `div` 2) trans
+                (eleft,eright) = partition (\el -> fst ((decodingLimits el)!!n) < b) els
+            in "(if w"++show n++" < "++show b++" then "++tree' n path eleft left bl (b-1)
+                   ++" else "++tree' n path eright right b br++")"
+
+      array' path els = let grps = groupBy (\e1 e2 -> case e1 of
+                                                       DecodingRange _ _ _ _ _ _ -> False
+                                                       _ -> case e2 of
+                                                             DecodingRange _ _ _ _ _ _ -> False
+                                                             _ -> True
+                                           ) els
+                            ranges = map (\(l,u) -> (fromIntegral $ u-l)+1) path
+                            val = foldl (\expr (r,n,m) -> "("++expr++"*"++show r++"+(fromIntegral w"++show n++"-"++show m++"))")
+                                  "0"
+                                  (zip3 ranges [0..] (map fst path))
+                            offset = (product ranges)-1
+                        in "(let val = " ++ val ++ " in "++array'' path grps 0 offset++")"
+
+      array'' path [] _ _ = "throwException (IllegalRepresentation ["++concat (intersperse "," (zipWith (\n _ -> "w"++show n) [0..] path))++"])"
+      array'' path [grp] lo up
+          = case grp of
+              [DecodingRange first end bfirst bend bmin bmax] ->
+                  let ranges = map (\(l,u) -> (fromIntegral $ u-l)+1) path
+                      off = foldl (\v (r,c,m) -> v*r+(fromIntegral $ c-m)) 0 (zip3 ranges bfirst bmin)
+                      equalranges = and $ zipWith (==) path (zip bmin bmax)
+                  in if equalranges
+                     then "(return (chr (val + ("++show (ord first - off)++"))))"
+                     else error "Can't have a range that has a different range..."
+              _ -> let chars = fillRange lo $ map (\el@(DecodingElement c _) -> (c,fst $ decodingValueRange path el)) grp
+                  in "(return (("++buildStaticArray (lo,up) chars++")!val))"
+      array'' path grps lo up = let (left,right@(brk:_)) = splitAt (length grps `div` 2) grps
+                                    (off,_) = decodingValueRange path (head brk)
+                                in "(if val < "++show off++" then "++array'' path left lo (off-1)
+                                       ++" else "++array'' path right off up++")"
+
+fillRange :: Int -> [(Char,Int)] -> [Char]
+fillRange s [] = []
+fillRange s all@((c,i):cs) = case compare i s of
+                               GT -> '\0':fillRange (s+1) all
+                               LT -> error $ "Char out of range "++show (take 10 all)
+                               EQ -> c:fillRange (s+1) cs
+
+states :: CharacterMapping -> StateMachine
+states (CharacterMapping attrs hist val ass)
+    = case val of
+        OneOf2 (Validity (NonEmpty lst)) -> Map.fromListWith (++) $
+                                           map (\st -> let BS [start] = stateS st
+                                                           end = case stateE st of
+                                                                   Nothing -> start
+                                                                   Just (BS [rend]) -> rend
+                                                      in (stateType st,[(start,end,stateNext st)])) lst
+        _ -> error "Mapping doesn't contain validity section"
+
+decodingElements :: CharacterMapping -> [DecodingElement]
+decodingElements mp = map (\(c,ws) -> DecodingElement c ws) (assignments mp)
+                      ++ map (\(fi,la,bfi,bla,bmi,bma) -> DecodingRange fi la bfi bla bmi bma) (ranges mp)
+
+illWord :: String -> String
+illWord n = "throwException (IllegalCharacter "++n++")"
+
+decodingLimits :: DecodingElement -> [(Word8,Word8)]
+decodingLimits (DecodingElement _ ws) = map (\w -> (w,w)) ws
+decodingLimits (DecodingRange _ _ bfirst blast bmin bmax) = lim' False (zip4 bfirst blast bmin bmax)
+    where
+      lim' dec [] = []
+      lim' dec ((fi,la,mi,ma):xs) = if dec
+                                    then (mi,ma):(lim' dec xs)
+                                    else (fi,la):(lim' (fi/=la) xs)
+
+decodingLength :: DecodingElement -> Int
+decodingLength (DecodingRange _ _ first _ _ _) = length first
+decodingLength (DecodingElement _ ws) = length ws
+
+decodingElementCount :: DecodingElement -> Int
+decodingElementCount (DecodingRange s e _ _ _ _) = ord e - ord s
+decodingElementCount (DecodingElement _ _) = 1
+
+data DecodingElement
+    = DecodingRange Char Char [Word8] [Word8] [Word8] [Word8]
+    | DecodingElement Char [Word8]
+    deriving Show
+
+norep :: String -> String
+norep var = "(throwException $ HasNoRepresentation "++var++")"
+
+buildDecisionTree :: Char -> Char -> String -> [EncodingElement] -> String
+buildDecisionTree l r var [] = norep var
+buildDecisionTree l r var [el]
+    = let e1 = if l < startChar el
+               then "(if "++var++" < "++show (startChar el)++" then "++norep var++" else "++e2++")"
+               else e2
+          e2 = if r > endChar el
+               then "(if "++var++" > "++show (endChar el)++" then "++norep var++" else "++e3++")"
+               else e3
+          e3 = buildEncoding el var
+      in e1
+buildDecisionTree ll lr var els
+    = let (l,r@(sep:_)) = splitAt (length els `div` 2) els
+      in "(if "++var++" < "++show (startChar sep)
+             ++" then ("++(buildDecisionTree ll (pred $ startChar sep) var l)++")"
+             ++" else ("++(buildDecisionTree (endChar sep) lr var r)++")"
+             ++")"
+
+buildEncoding :: EncodingElement -> String -> String
+buildEncoding (EncodingRange start end bf bl bmin bmax) var
+    = let ranges :: [Int]
+          ranges = map fromIntegral $ zipWith (-) bmax bmin
+      in  "(let num = (ord "++var++") - ("++show (ord start - (foldl (\n (r,vf,vm) -> n*(r+1) + (fromIntegral (vf-vm))) 0 (zip3 ranges bf bmin)))++")"
+              ++concat ([ " ; (p"++show n++",r"++show n++") = "
+                          ++(if n==1 then "num" else "p"++show (n-1))
+                          ++" `divMod` "++show (r+1)
+                          | r <- reverse ranges | n <- [1..] ])
+              ++" in "
+              ++concat (intersperse " >> " (reverse ["pushWord8 (fromIntegral (r"++show n++" + "++show w++"))" | n <- [1..] | w <- reverse bmin]))
+              ++")"
+buildEncoding (EncodingGroup start end encs) var
+    = let findParams st []     = st
+          findParams st (x:xs) = findParams (case compare (length x) (fst st) of
+                                               LT -> (fst st,False)
+                                               GT -> (length x,False)
+                                               EQ -> st) xs
+          (mx,same) = findParams (length $ head encs,True) (tail encs)
+      in if same
+         then ("(let off = "++show mx++"*(ord "++var++" - "++show (ord start)++") ; arr = "
+               ++buildStaticArray (0,(length encs)*mx-1) (concat encs)
+               ++" in "
+               ++concat (intersperse " >> " ["pushWord8 (arr!(off+"++show (n-1)++"))" | n <- [1..mx]])
+               ++")")
+         else ("(let off = "++show (mx+1)++"*((ord "++var++") - "++show (ord start)++") ; arr = "
+               ++buildStaticArray (0,(length encs)*(mx+1)-1)
+                                      (concat [(fromIntegral $ length e)
+                                               :(e++replicate (mx-length e) 0) | e <- encs])
+               ++ "::StaticArray Int Word8"
+               ++" ; len = fromIntegral (arr!off)::Int ; bytes = map (\\n -> arr!(off+n)) [1..len]"
+               ++" in mapM_ pushWord8 bytes)") 
+
+data EncodingElement
+    = EncodingRange Char Char [Word8] [Word8] [Word8] [Word8]
+    | EncodingGroup Char Char [[Word8]]
+    deriving Show
+
+mergeBy :: (a -> a -> Ordering) -> [a] -> [a] -> [a]
+mergeBy f [] ys = ys
+mergeBy f xs [] = xs
+mergeBy f (x:xs) (y:ys)
+    = case f x y of
+        LT -> x:mergeBy f xs (y:ys)
+        _  -> y:mergeBy f (x:xs) ys
+
+startChar :: EncodingElement -> Char
+startChar (EncodingRange c _ _ _ _ _) = c
+startChar (EncodingGroup c _ _) = c
+
+endChar :: EncodingElement -> Char
+endChar (EncodingRange _ c _ _ _ _) = c
+endChar (EncodingGroup _ c _) = c
+
+
+encodingElements :: CharacterMapping -> [EncodingElement]
+encodingElements mp = mergeBy (comparing startChar)
+                      (buildGroups $ sortAssignments $ assignments mp)
+                      (encodingRanges $ ranges mp)
+
+assignments :: CharacterMapping -> [(Char,[Word8])]
+assignments (CharacterMapping _ _ _ (Assignments _ ass _ _ _ ranges))
+    = map (\a -> let CP [cp] = aU a
+                     BS bs = aB a
+                in (cp,bs)
+          ) ass
+
+encodingRanges :: [(Char,Char,[Word8],[Word8],[Word8],[Word8])] -> [EncodingElement]
+encodingRanges lst = sortBy (comparing (\(EncodingRange c _ _ _ _ _) -> c)) $
+                     map (\(ufirst,ulast,bfirst,blast,bmin,bmax) -> EncodingRange ufirst ulast bfirst blast bmin bmax) lst
+
+ranges :: CharacterMapping -> [(Char,Char,[Word8],[Word8],[Word8],[Word8])]
+ranges (CharacterMapping _ _ _ (Assignments _ ass _ _ _ ranges))
+    = map (\r -> let BS bfirst   = rangeBFirst r
+                     BS blast    = rangeBLast r
+                     CP [ufirst] = rangeUFirst r
+                     CP [ulast]  = rangeULast r
+                     BS bmin     = rangeBMin r
+                     BS bmax     = rangeBMax r
+                in (ufirst,ulast,bfirst,blast,bmin,bmax)
+          ) ranges
+
+
+sortAssignments :: [(Char,[Word8])] -> [(Char,[Word8])]
+sortAssignments = sortBy (comparing fst)
+
+buildGroups :: [(Char,[Word8])] -> [EncodingElement]
+buildGroups [] = []
+buildGroups ((c,bs):rest) = (EncodingGroup c end (bs:wrds)):buildGroups oth
+    where
+      (end,wrds,oth) = group c rest
+
+      group n [] = (n,[],[])
+      group n all@((c,bs):rest)
+          | succ n == c = let (e,res,oth) = group c rest
+                          in (e,bs:res,oth)
+          | otherwise = (n,[],all)

Data/Encoding/UTF16.hs

@@ -79,3 +79,4 @@ instance Encoding UTF16 where
                  return (c:cs)
         Right bom -> decode bom
     decode enc = untilM sourceEmpty (decodeChar enc)
+    encodeable _ c = (c > '\xDFFF' && c <= '\x10FFFF') || c < '\xD800'

Data/Encoding/UTF32.hs

@@ -44,3 +44,4 @@ instance Encoding UTF32 where
           rest <- untilM sourceEmpty (decodeChar UTF32)
           return ((chr $ fromIntegral ch):rest)
     decode enc = untilM sourceEmpty (decodeChar enc)
+    encodeable _ _ = True

Data/Encoding/UTF8.hs

@@ -38,6 +38,7 @@ instance Encoding UTF8 where
                where
                  n = ord c
                  p8 = pushWord8.fromIntegral
+    encodeable _ c = c <= '\x10FFFF'
     decodeChar UTF8 = do
       w1 <- fetchWord8
       case () of 
@@ -68,11 +69,13 @@ instance Encoding UTF8 where
                              v2 = w2 .&. 0x3F
                              v3 = w3 .&. 0x3F
                              v4 = w4 .&. 0x3F
-                         return $ chr $
-                                    ((fromIntegral v1) `shiftL` 18)
+                             v  = ((fromIntegral v1) `shiftL` 18)
                                     .|. ((fromIntegral v2) `shiftL` 12)
                                     .|. ((fromIntegral v3) `shiftL` 6)
                                     .|. (fromIntegral v4)
+                         if v <= 0x10FFFF
+                           then return $ chr v
+                           else throwException (IllegalRepresentation [w1,w2,w3,w4])
           | otherwise -> throwException (IllegalCharacter w1)
     decodeChar UTF8Strict = do
       w1 <- fetchWord8
@@ -108,13 +111,15 @@ instance Encoding UTF8 where
                              v2 = w2 .&. 0x3F
                              v3 = w3 .&. 0x3F
                              v4 = w4 .&. 0x3F
-                         if v1 == 0 && v2 < 0x10
-                           then throwException (IllegalRepresentation [w1,w2,w3,w4])
-                           else return $ chr $
-                                    ((fromIntegral v1) `shiftL` 18)
+                             v = ((fromIntegral v1) `shiftL` 18)
                                     .|. ((fromIntegral v2) `shiftL` 12)
                                     .|. ((fromIntegral v3) `shiftL` 6)
                                     .|. (fromIntegral v4)
+                         if v1 == 0 && v2 < 0x10
+                           then throwException (IllegalRepresentation [w1,w2,w3,w4])
+                           else (if v <= 0x10FFFF
+                                 then return $ chr v
+                                 else throwException (IllegalRepresentation [w1,w2,w3,w4]))
           | otherwise -> throwException (IllegalCharacter w1)
           where
             invalidExtend wrd = wrd .&. 0xC0 /= 0x80

Data/Map/Static.hs

@@ -0,0 +1,28 @@
+module Data.Map.Static where
+
+import Data.Static
+import Data.Array.Static
+
+import GHC.Exts
+
+data StaticMap i e = StaticMap (StaticArray Int i) (StaticArray Int e)
+
+lookup :: (StaticElement i,StaticElement e,Ord i) => i -> StaticMap i e -> Maybe e
+lookup ind (StaticMap idx els) = lookup' 1
+    where
+      lookup' n = if n > snd (bounds idx)
+                  then Nothing
+                  else case compare ind (idx!n) of
+                         LT -> lookup' (n * 2)
+                         GT -> lookup' ((n * 2) + 1)
+                         EQ -> Just $ els!n
+
+member :: (StaticElement i,StaticElement e,Ord i) => i -> StaticMap i e -> Bool
+member ind (StaticMap idx _) = lookup' 1
+    where
+      lookup' n = if n > snd (bounds idx)
+                  then False
+                  else case compare ind (idx!n) of
+                         LT -> lookup' (n * 2)
+                         GT -> lookup' ((n * 2) + 1)
+                         EQ -> True

Data/Map/Static/Builder.hs

@@ -0,0 +1,42 @@
+module Data.Map.Static.Builder where
+
+import Data.Static
+import Data.Array.Static.Builder
+
+import Data.List
+import Data.Ord
+import Data.Bits
+
+buildStaticMap :: (StaticElement i,StaticElement e,Ord i) => [(i,e)] -> String
+buildStaticMap lst = let  step :: Int -> [(i,e)] -> [(Int,(i,e))]
+                          step n chunk = let ss = findSplitSize (length chunk)
+                                             (h,d:t) = splitAt ss chunk
+                                         in if null chunk
+                                            then []
+                                            else (n,d):((step (n*2) h)++(step (n*2+1) t))
+                          checkHeap n [] = []
+                          checkHeap n ((c,x):xs) = if c == n
+                                                   then x:checkHeap (n+1) xs
+                                                   else error $ "Heap is not consistent: Should be "++show n++" but is "++show c
+                          uheap = sortBy (comparing fst) (step 1 slst)
+                          slst = sortBy (comparing fst) lst
+                          heap = checkHeap 1 $ sortBy (comparing fst) (step 1 slst)
+                          len = length heap
+                      in "StaticMap ("++buildStaticArray (1,len) (map fst heap)++") ("++buildStaticArray (1,len) (map snd heap)++")"
+
+maxSize :: Int -> Int
+maxSize d = (1 `shiftL` d) - 1
+
+treeDepth :: Int -> Int
+treeDepth sz = find' [0..]
+    where
+      find' (x:xs) = if 1 `shiftL` x > sz
+                     then x
+                     else find' xs
+
+findSplitSize :: Int -> Int
+findSplitSize len = let depth = treeDepth len
+                        free = (maxSize depth) - len
+                    in if free <= (1 `shiftL` (depth - 2))
+                       then maxSize (depth - 1)
+                       else len - (maxSize (depth - 2)) - 1