-- Hoogle documentation, generated by Haddock
-- See Hoogle, http://www.haskell.org/hoogle/


-- | Unicode en-/decoding functions for utf8, iso-latin-* and other encodings
--   
--   Unicode encoding and decoding functions for utf8, iso-latin-* and
--   somes other encodings, used in the Haskell XML Toolbox. ISO Latin 1 -
--   16, utf8, utf16, ASCII are supported. Decoding is done with lasy
--   functions, errors may be detected or ignored.
@package hxt-unicode
@version 9.0.2

module Data.String.UTF8
encode :: [Char] -> [Word8]
decode :: [Word8] -> ([Char], [(Error, Int)])
decodeEmbedErrors :: [Word8] -> [Either (Error, Int) Char]
encodeOne :: Char -> [Word8]
decodeOne :: [Word8] -> (Either Error Char, Int, [Word8])
data Error
instance Show Error
instance Eq Error


-- | Interface for Data.Char.UTF8 funtions
module Data.String.UTF8Decoding

-- | calls <tt>Data.Char.UTF8.decode</tt> for parsing and decoding UTF-8
decodeUtf8 :: String -> (String, [String])
decodeUtf8EmbedErrors :: String -> [Either String Char]
decodeUtf8IgnoreErrors :: String -> String


-- | Constants for character encodings
module Data.String.EncodingNames
isoLatin1, unicodeString, utf16le, utf16be, utf16, utf8, ucs2, usAscii, iso8859_16, iso8859_15, iso8859_14, iso8859_13, iso8859_11, iso8859_10, iso8859_9, iso8859_8, iso8859_7, iso8859_6, iso8859_5, iso8859_4, iso8859_3, iso8859_2, iso8859_1 :: String

module Data.Char.IsoLatinTables
iso_8859_2 :: [(Char, Char)]
iso_8859_3 :: [(Char, Char)]
iso_8859_4 :: [(Char, Char)]
iso_8859_5 :: [(Char, Char)]
iso_8859_6 :: [(Char, Char)]
iso_8859_7 :: [(Char, Char)]
iso_8859_8 :: [(Char, Char)]
iso_8859_9 :: [(Char, Char)]
iso_8859_10 :: [(Char, Char)]
iso_8859_11 :: [(Char, Char)]
iso_8859_13 :: [(Char, Char)]
iso_8859_14 :: [(Char, Char)]
iso_8859_15 :: [(Char, Char)]
iso_8859_16 :: [(Char, Char)]


-- | Unicode and UTF-8 Conversion Functions
module Data.String.Unicode

-- | Unicode is represented as the Char type Precondition for this is the
--   support of Unicode character range in the compiler (e.g. ghc but not
--   hugs)
type Unicode = Char

-- | the type for Unicode strings
type UString = [Unicode]

-- | UTF-8 charachters are represented by the Char type
type UTF8Char = Char

-- | UTF-8 strings are implemented as Haskell strings
type UTF8String = String
type UStringWithErrors = [Either String Char]

-- | Decoding function with a pair containing the result string and a list
--   of decoding errors as result
type DecodingFct = String -> (UString, [String])

-- | Decoding function where decoding errors are interleaved with decoded
--   characters
type DecodingFctEmbedErrors = String -> UStringWithErrors

-- | UTF-8 to Unicode conversion with deletion of leading byte order mark,
--   as described in XML standard F.1
utf8ToUnicode :: DecodingFct
utf8ToUnicodeEmbedErrors :: DecodingFctEmbedErrors

-- | code conversion from latin1 to Unicode
latin1ToUnicode :: String -> UString

-- | UCS-2 to UTF-8 conversion with byte order mark analysis
ucs2ToUnicode :: String -> UString

-- | UCS-2 big endian to Unicode conversion
ucs2BigEndianToUnicode :: String -> UString

-- | UCS-2 little endian to Unicode conversion
ucs2LittleEndianToUnicode :: String -> UString

-- | UTF-16 big endian to UTF-8 conversion with removal of byte order mark
utf16beToUnicode :: String -> UString

-- | UTF-16 little endian to UTF-8 conversion with removal of byte order
--   mark
utf16leToUnicode :: String -> UString

-- | conversion from Unicode (Char) to a UTF8 encoded string.
unicodeCharToUtf8 :: Unicode -> UTF8String

-- | conversion from Unicode strings (UString) to UTF8 encoded strings.
unicodeToUtf8 :: UString -> UTF8String

-- | substitute all Unicode characters, that are not legal 1-byte UTF-8 XML
--   characters by a character reference.
--   
--   This function can be used to translate all text nodes and attribute
--   values into pure ascii.
--   
--   see also : <a>unicodeToLatin1</a>
unicodeToXmlEntity :: UString -> String

-- | substitute all Unicode characters, that are not legal latin1 UTF-8 XML
--   characters by a character reference.
--   
--   This function can be used to translate all text nodes and attribute
--   values into ISO latin1.
--   
--   see also : <a>unicodeToXmlEntity</a>
unicodeToLatin1 :: UString -> String

-- | removes all non ascii chars, may be used to transform a document into
--   a pure ascii representation by removing all non ascii chars from tag
--   and attibute names
--   
--   see also : <a>unicodeRemoveNoneLatin1</a>, <a>unicodeToXmlEntity</a>
unicodeRemoveNoneAscii :: UString -> String

-- | removes all non latin1 chars, may be used to transform a document into
--   a pure ascii representation by removing all non ascii chars from tag
--   and attibute names
--   
--   see also : <a>unicodeRemoveNoneAscii</a>, <a>unicodeToLatin1</a>
unicodeRemoveNoneLatin1 :: UString -> String

-- | convert an Unicode into a XML character reference.
--   
--   see also : <a>intToCharRefHex</a>
intToCharRef :: Int -> String

-- | convert an Unicode into a XML hexadecimal character reference.
--   
--   see also: <a>intToCharRef</a>
intToCharRefHex :: Int -> String
intToHexString :: Int -> String

-- | the lookup function for selecting the decoding function
getDecodingFct :: String -> Maybe DecodingFct

-- | the lookup function for selecting the decoding function
getDecodingFctEmbedErrors :: String -> Maybe DecodingFctEmbedErrors

-- | the lookup function for selecting the encoding function
getOutputEncodingFct :: String -> Maybe (String -> UString)

-- | White Space (XML Standard 2.3) and end of line handling (2.11)
--   
--   #x0D and #x0D#x0A are mapped to #x0A
normalizeNL :: String -> String
guessEncoding :: String -> String

-- | the lookup function for selecting the encoding function
getOutputEncodingFct' :: String -> Maybe (Char -> StringFct)

-- | conversion from Unicode (Char) to a UTF8 encoded string.
unicodeCharToUtf8' :: Char -> StringFct

-- | substitute all Unicode characters, that are not legal 1-byte UTF-8 XML
--   characters by a character reference.
unicodeCharToXmlEntity' :: Char -> StringFct

-- | substitute all Unicode characters, that are not legal latin1 UTF-8 XML
--   characters by a character reference.
unicodeCharToLatin1' :: Char -> StringFct