GHC.Utils.Encoding.UTF8

Simple, non-streaming UTF-8 codecs.

This is one of several UTF-8 implementations provided by GHC; see Note [GHC's many UTF-8 implementations] in GHC.Encoding.UTF8 for an overview.

Decoding single characters

utf8DecodeCharAddr# :: Addr# -> Int# -> (# Char#, Int# #)

Decode a single character at the given Addr#.

utf8DecodeCharPtr :: Ptr Word8 -> (Char, Int)

Decode a single codepoint starting at the given Ptr.

utf8DecodeCharByteArray# :: ByteArray# -> Int# -> (# Char#, Int# #)

Decode a single codepoint starting at the given byte offset into a ByteArray#.

utf8PrevChar :: Ptr Word8 -> IO (Ptr Word8)

Find the start of the codepoint preceding the codepoint at the given Ptr. This is undefined if there is no previous valid codepoint.

utf8CharStart :: Ptr Word8 -> IO (Ptr Word8)

Find the start of the codepoint at the given Ptr. This is undefined if there is no previous valid codepoint.

utf8UnconsByteString :: ByteString -> Maybe (Char, ByteString)

Decoding strings

utf8DecodeByteString :: ByteString -> [Char]

Decode a ByteString containing a UTF-8 string.

utf8DecodeShortByteString :: ShortByteString -> [Char]

utf8DecodeForeignPtr :: ForeignPtr Word8 -> Int -> Int -> [Char]

utf8DecodeByteArray# :: ByteArray# -> [Char]

Counting characters

utf8CountCharsShortByteString :: ShortByteString -> Int

utf8CountCharsByteArray# :: ByteArray# -> Int

Comparison

utf8CompareByteArray# :: ByteArray# -> ByteArray# -> Ordering

utf8CompareShortByteString :: ShortByteString -> ShortByteString -> Ordering

Encoding strings

utf8EncodeByteArray# :: String -> ByteArray#

utf8EncodePtr :: Ptr Word8 -> String -> IO ()

utf8EncodeByteString :: String -> ByteString

Encode a String into a ByteString.

utf8EncodeShortByteString :: String -> ShortByteString

utf8EncodedLength :: String -> Int