More documentation for encodings
darcs-hash:20080115224955-a4fee-339ceea9439723fa09096abab221f2ad735c8905
This commit is contained in:
parent
38afec5701
commit
e849ef1404
@ -2,7 +2,7 @@
|
||||
-- | ASCII (American Standard Code for Information Interchange) is the
|
||||
-- \"normal\" computer encoding using the byte values 0-127 to represent
|
||||
-- characters. Refer to <http://en.wikipedia.org/wiki/ASCII> for
|
||||
-- more informations.
|
||||
-- more information.
|
||||
module Data.Encoding.ASCII
|
||||
(ASCII(..)) where
|
||||
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | This module implements Windows Codepage number 1250 which encodes languages that use latin script.
|
||||
See <http://en.wikipedia.org/wiki/CP1250> for more information.
|
||||
-}
|
||||
module Data.Encoding.CP1250
|
||||
(CP1250(..)) where
|
||||
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | This module implements Windows Codepage number 1251 which encodes languages that use the cyrillic alphabet.
|
||||
See <http://en.wikipedia.org/wiki/CP1251> for more information.
|
||||
-}
|
||||
module Data.Encoding.CP1251
|
||||
(CP1251(..)) where
|
||||
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | This module implements Windows Codepage number 1252 which is a superset of ISO 8859-1.
|
||||
See <http://en.wikipedia.org/wiki/CP1252> for more information.
|
||||
-}
|
||||
module Data.Encoding.CP1252
|
||||
(CP1252(..)) where
|
||||
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | This module implements Windows Codepage number 1253 which encodes modern greek.
|
||||
See <http://en.wikipedia.org/wiki/CP1253> for more information.
|
||||
-}
|
||||
module Data.Encoding.CP1253
|
||||
(CP1253(..)) where
|
||||
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | This module implements Windows Codepage number 1254 which encodes the turkish language.
|
||||
See <http://en.wikipedia.org/wiki/CP1254> for more information.
|
||||
-}
|
||||
module Data.Encoding.CP1254
|
||||
(CP1254(..)) where
|
||||
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | This module implements Windows Codepage number 1255 which encodes the hebrew language.
|
||||
See <http://en.wikipedia.org/wiki/CP1255> for more information.
|
||||
-}
|
||||
module Data.Encoding.CP1255
|
||||
(CP1255(..)) where
|
||||
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | This module implements Windows Codepage number 1256 which encodes languages which use the arabic script.
|
||||
See <http://en.wikipedia.org/wiki/CP1256> for more information.
|
||||
-}
|
||||
module Data.Encoding.CP1256
|
||||
(CP1256(..)) where
|
||||
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | This module implements Windows Codepage number 1257 which encodes the estonian, latvian and lithuanian language.
|
||||
See <http://en.wikipedia.org/wiki/CP1257> for more information.
|
||||
-}
|
||||
module Data.Encoding.CP1257
|
||||
(CP1257(..)) where
|
||||
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | This module implements Windows Codepage number 1258 which encodes the vietnamese language.
|
||||
See <http://en.wikipedia.org/wiki/CP1258> for more information.
|
||||
-}
|
||||
module Data.Encoding.CP1258
|
||||
(CP1258(..)) where
|
||||
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{-# LANGUAGE CPP,TemplateHaskell,DeriveDataTypeable #-}
|
||||
{- | Implements ISO\/IEC 8859-1 alias latin-1 encoding. See
|
||||
<http://en.wikipedia.org/wiki/ISO/IEC_8859-1> for further informations.
|
||||
<http://en.wikipedia.org/wiki/ISO/IEC_8859-1> for further information.
|
||||
-}
|
||||
module Data.Encoding.ISO88591
|
||||
(ISO88591(..)
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE DeriveDataTypeable #-}
|
||||
{- | This module implements KOI8-R encoding which covers the russian and bulgarian alphabet.
|
||||
See <http://en.wikipedia.org/wiki/KOI8-R> for more information.
|
||||
-}
|
||||
module Data.Encoding.KOI8R
|
||||
(KOI8R(..)) where
|
||||
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
{-# LANGUAGE DeriveDataTypeable #-}
|
||||
{- | This module implements UTF-16 encoding and decoding as in RFC 2781
|
||||
{- | This module implements UTF-16 encoding and decoding as in RFC 2781.
|
||||
See <http://en.wikipedia.org/wiki/UTF-16> for more information.
|
||||
-}
|
||||
module Data.Encoding.UTF16
|
||||
(UTF16(..)
|
||||
@ -18,9 +19,9 @@ import Data.Dynamic (toDyn)
|
||||
import Data.Typeable
|
||||
|
||||
data UTF16
|
||||
= UTF16
|
||||
| UTF16BE
|
||||
| UTF16LE
|
||||
= UTF16 -- ^ Decodes big and little endian, encodes big endian.
|
||||
| UTF16BE -- ^ Big endian decoding and encoding, fails if the string isn\'t actually big endian.
|
||||
| UTF16LE -- ^ Little endian decoding and encoding.
|
||||
deriving (Eq,Show,Typeable)
|
||||
|
||||
utf16enc :: Bool -> (EncodeState,String) -> Maybe (Word8,(EncodeState,String))
|
||||
|
||||
@ -1,4 +1,7 @@
|
||||
{-# LANGUAGE DeriveDataTypeable #-}
|
||||
{- | This module implements UTF-32 encoding and decoding.
|
||||
See <http://en.wikipedia.org/wiki/UTF-32> for more information.
|
||||
-}
|
||||
module Data.Encoding.UTF32
|
||||
(UTF32(..))
|
||||
where
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
{-# LANGUAGE DeriveDataTypeable #-}
|
||||
{- | This module implements UTF-8 encoding and decoding as in RFC 3629.
|
||||
See <http://en.wikipedia.org/wiki/UTF-8> for more information.
|
||||
-}
|
||||
module Data.Encoding.UTF8
|
||||
(UTF8(..)) where
|
||||
@ -14,8 +15,8 @@ import Control.Exception
|
||||
import Data.Typeable
|
||||
|
||||
data UTF8
|
||||
= UTF8
|
||||
| UTF8Strict
|
||||
= UTF8 -- ^ Very forgiving decoding mechanism, accepts everything that it can make any sense of.
|
||||
| UTF8Strict -- ^ More strict decoding, doesn\'t accept sequences that have a too long representation and checks bits that aren\'t used in the decoding.
|
||||
deriving (Eq,Show,Typeable)
|
||||
|
||||
encodeUTF8 :: Char -> (Word8,EncodeState)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user