From d444bbbd4b117c936d2466191c5a82a21ca560e1 Mon Sep 17 00:00:00 2001
From: Sigbjorn Finne <sigbjorn.finne@gmail.com>
Date: Tue, 3 Mar 2009 07:14:11 -0800
Subject: [PATCH] added isUTF8Encoded predicate + utf8Encode to avoid repeated
 encodings

---
 Codec/Binary/UTF8/String.hs | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/Codec/Binary/UTF8/String.hs b/Codec/Binary/UTF8/String.hs
index 27c003f..6f79d71 100644
--- a/Codec/Binary/UTF8/String.hs
+++ b/Codec/Binary/UTF8/String.hs
@@ -24,13 +24,9 @@ import Data.Char        (chr,ord)
 
 default(Int)
 
--- | Encode a string using 'encode' and store the result in a 'String'.
 encodeString :: String -> String
 encodeString xs = map (toEnum . fromEnum) (encode xs)
 
--- | Decode a string using 'decode' using a 'String' as input.
--- | This is not safe but it is necessary if UTF-8 encoded text
--- | has been loaded into a 'String' prior to being decoded.
 decodeString :: String -> String
 decodeString xs = decode (map (toEnum . fromEnum) xs)
 
@@ -66,20 +62,13 @@ decode [    ] = ""
 decode (c:cs)
   | c < 0x80  = chr (fromEnum c) : decode cs
   | c < 0xc0  = replacement_character : decode cs
-  | c < 0xe0  = multi1
+  | c < 0xe0  = multi_byte 1 0x1f 0x80
   | c < 0xf0  = multi_byte 2 0xf  0x800
   | c < 0xf8  = multi_byte 3 0x7  0x10000
   | c < 0xfc  = multi_byte 4 0x3  0x200000
   | c < 0xfe  = multi_byte 5 0x1  0x4000000
   | otherwise = replacement_character : decode cs
   where
-    multi1 = case cs of
-      c1 : ds | c1 .&. 0xc0 == 0x80 ->
-        let d = ((fromEnum c .&. 0x1f) `shiftL` 6) .|.  fromEnum (c1 .&. 0x3f)
-        in if d >= 0x000080 then toEnum d : decode ds
-                            else replacement_character : decode ds
-      _ -> replacement_character : decode cs
-
     multi_byte :: Int -> Word8 -> Int -> [Char]
     multi_byte i mask overlong = aux i cs (fromEnum (c .&. mask))
       where