hunk ./Makefile 5
-	ghc -threaded --make -package nuance-recognizer -package nlsml -package realspeak -package alsa -package gf -o $@ $< /usr/local/ScanSoft/RealSpeak_4.0/api/lib/lhstts.so
+	ghc -threaded --make -package utf8-string -package nuance-recognizer -package nlsml -package realspeak -package alsa -package gf -o $@ $< /usr/local/ScanSoft/RealSpeak_4.0/api/lib/lhstts.so
hunk ./UTF8.hs 1
-----------------------------------------------------------------------
--- |
--- Module      : UTF8
--- Maintainer  : AR
--- Stability   : (stable)
--- Portability : (portable)
---
--- > CVS $Date: 2005/04/21 16:23:42 $ 
--- > CVS $Author: bringert $
--- > CVS $Revision: 1.5 $
---
--- From the Char module supplied with HBC.
--- code by Thomas Hallgren (Jul 10 1999)
------------------------------------------------------------------------------
-
-module UTF8 (decodeUTF8, encodeUTF8) where
-
--- | Take a Unicode string and encode it as a string
--- with the UTF8 method.
-decodeUTF8 :: String -> String
-decodeUTF8 "" = ""
-decodeUTF8 (c:cs) | c < '\x80' = c : decodeUTF8 cs
-decodeUTF8 (c:c':cs) | '\xc0' <= c  && c  <= '\xdf' && 
-		      '\x80' <= c' && c' <= '\xbf' =
-	toEnum ((fromEnum c `mod` 0x20) * 0x40 + fromEnum c' `mod` 0x40) : decodeUTF8 cs
-decodeUTF8 (c:c':c'':cs) | '\xe0' <= c   && c   <= '\xef' && 
-		          '\x80' <= c'  && c'  <= '\xbf' &&
-		          '\x80' <= c'' && c'' <= '\xbf' =
-	toEnum ((fromEnum c `mod` 0x10 * 0x1000) + (fromEnum c' `mod` 0x40) * 0x40 + fromEnum c'' `mod` 0x40) : decodeUTF8 cs
-decodeUTF8 s = s ---- AR workaround 22/6/2006
-----decodeUTF8 _ = error "UniChar.decodeUTF8: bad data"
-
-encodeUTF8 :: String -> String
-encodeUTF8 "" = ""
-encodeUTF8 (c:cs) =
-	if c > '\x0000' && c < '\x0080' then
-	    c : encodeUTF8 cs
-	else if c < toEnum 0x0800 then
-	    let i = fromEnum c
-	    in  toEnum (0xc0 + i `div` 0x40) : 
-	        toEnum (0x80 + i `mod` 0x40) : 
-		encodeUTF8 cs
-	else
-	    let i = fromEnum c
-	    in  toEnum (0xe0 + i `div` 0x1000) : 
-	        toEnum (0x80 + (i `mod` 0x1000) `div` 0x40) : 
-		toEnum (0x80 + i `mod` 0x40) : 
-		encodeUTF8 cs
rmfile ./UTF8.hs
hunk ./translator.hs 1
-import UTF8
-
hunk ./translator.hs 10
+import Codec.Binary.UTF8.String as UTF8
+
hunk ./translator.hs 83
-        printResults rs = sequence [printf "%3d %s\n" c (encodeUTF8 r) | (c,r) <- rs]
+        printResults rs = sequence [printf "%3d %s\n" c (UTF8.encodeString r) | (c,r) <- rs]