diff options
author | Raúl Benencia <rul@kalgan.cc> | 2013-09-05 19:57:02 -0300 |
---|---|---|
committer | Raúl Benencia <rul@kalgan.cc> | 2013-09-05 19:57:02 -0300 |
commit | 3bd3fd2c6eae2f36f69f247403421e8cf8226394 (patch) | |
tree | 0d92cd91d69cf52b9168c403af317643e88c2587 /src/Codec | |
parent | 41b53ca04b6d52457f331930e8fea68416498882 (diff) |
Moved all code to src/
Diffstat (limited to 'src/Codec')
-rw-r--r-- | src/Codec/Text/Rfc1342.hs | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/src/Codec/Text/Rfc1342.hs b/src/Codec/Text/Rfc1342.hs new file mode 100644 index 0000000..f6d8fe2 --- /dev/null +++ b/src/Codec/Text/Rfc1342.hs @@ -0,0 +1,57 @@ +{- A simple RFC1342 decoder. + - + - Copyright 2013 Raúl Benencia <rul@kalgan.cc> + - + - Licensed under the GNU GPL version 3 or higher + - + -} +module Codec.Text.Rfc1342 (decodeField) where + +import qualified Codec.Binary.Base64 as B64 +import qualified Codec.Binary.QuotedPrintable as QP + +import Data.Char (toLower, isSpace, chr) +import Data.List(isPrefixOf) +import Data.Word (Word8) + +import Data.Encoding(decodeString) + +-- Encoding imports. If you want to support more encodings, just add'em here. +import Data.Encoding.UTF8 +import Data.Encoding.ISO88591 +import Data.Encoding.ISO88592 +import Data.Encoding.ISO88598 +import Data.Encoding.ISO88599 + +decodeField :: String -> String +decodeField ('=':'?':cs) = decodeWithCharset dec rest + where (encoding, rest) = span (\c -> c /= '?') cs + dec = case (map toLower encoding) of + "utf-8" -> decodeString UTF8 + "iso-8859-1" -> decodeString ISO88591 + "iso-8859-2" -> decodeString ISO88592 + "iso-8859-8" -> decodeString ISO88598 + "iso-8859-9" -> decodeString ISO88599 + _ -> id +decodeField [] = [] +decodeField (c:cs) = c:decodeField cs + +decodeWithCharset dec [] = [] +decodeWithCharset dec ('?':c:'?':cs) | toLower c == 'b' = dataDecodeWith B64.decode + | toLower c == 'q' = dataDecodeWith QP.decode + | otherwise = cs + where (encoded, rest') = span (\c -> c /= '?') cs + rest = if "?=" `isPrefixOf` rest' + then drop 2 rest' + else rest' + dataDecodeWith datadec = (_2spc . dec . unwrap . datadec $ encoded) ++ decodeField rest -- ++ (decodeField $ dropWhile isSpace rest) + +unwrap :: Maybe [Word8] -> String +unwrap Nothing = [] +unwrap (Just str) = bytesToString str + +bytesToString :: [Word8] -> String +bytesToString = map (chr . fromIntegral) + +-- Sometimes an underscore represents the SPACE character +_2spc = map (\x -> if x == '_' then ' ' else x)
\ No newline at end of file |