| Copyright | (c) Dong Han 2017-2019 |
|---|---|
| License | BSD |
| Maintainer | winterland1989@gmail.com |
| Stability | experimental |
| Portability | non-portable |
| Safe Haskell | None |
| Language | Haskell2010 |
Z.Data.Parser.Base
Description
Synopsis
- data Result e r
- type ParseError = [Text]
- type ParseStep e r = Bytes -> Result e r
- newtype Parser a = Parser {
- runParser :: forall r. (ParseError -> ParseStep ParseError r) -> (State# ParserState -> a -> ParseStep ParseError r) -> State# ParserState -> ParseStep ParseError r
- (<?>) :: Text -> Parser a -> Parser a
- parse :: Parser a -> Bytes -> (Bytes, Either ParseError a)
- parse' :: Parser a -> Bytes -> Either ParseError a
- parseChunk :: Parser a -> Bytes -> Result ParseError a
- type ParseChunks m err x = m Bytes -> Bytes -> m (Bytes, Either err x)
- parseChunks :: Monad m => (Bytes -> Result e a) -> ParseChunks m e a
- finishParsing :: Result ParseError a -> (Bytes, Either ParseError a)
- runAndKeepTrack :: Parser a -> Parser (Result ParseError a, [Bytes])
- match :: Parser a -> Parser (Bytes, a)
- ensureN :: Int -> Text -> Parser ()
- endOfInput :: Parser ()
- currentChunk :: Parser Bytes
- atEnd :: Parser Bool
- decodePrim :: forall a. Unaligned a => Parser a
- newtype BE a = BE {
- getBE :: a
- newtype LE a = LE {
- getLE :: a
- decodePrimLE :: forall a. Unaligned (LE a) => Parser a
- decodePrimBE :: forall a. Unaligned (BE a) => Parser a
- scan :: s -> (s -> Word8 -> Maybe s) -> Parser (Bytes, s)
- scanChunks :: forall s. s -> (s -> Bytes -> Either s (Bytes, Bytes, s)) -> Parser (Bytes, s)
- peekMaybe :: Parser (Maybe Word8)
- peek :: Parser Word8
- satisfy :: (Word8 -> Bool) -> Parser Word8
- satisfyWith :: (Word8 -> a) -> (a -> Bool) -> Parser a
- anyWord8 :: Parser Word8
- word8 :: Word8 -> Parser ()
- char8 :: Char -> Parser ()
- anyChar8 :: Parser Char
- anyCharUTF8 :: Parser Char
- charUTF8 :: Char -> Parser ()
- char7 :: Char -> Parser ()
- anyChar7 :: Parser Char
- skipWord8 :: Parser ()
- endOfLine :: Parser ()
- skip :: Int -> Parser ()
- skipWhile :: (Word8 -> Bool) -> Parser ()
- skipSpaces :: Parser ()
- take :: Int -> Parser Bytes
- takeN :: (Word8 -> Bool) -> Int -> Parser Bytes
- takeTill :: (Word8 -> Bool) -> Parser Bytes
- takeWhile :: (Word8 -> Bool) -> Parser Bytes
- takeWhile1 :: (Word8 -> Bool) -> Parser Bytes
- takeRemaining :: Parser Bytes
- bytes :: Bytes -> Parser ()
- bytesCI :: Bytes -> Parser ()
- text :: Text -> Parser ()
- fail' :: Text -> Parser a
- failWithInput :: (Bytes -> Text) -> Parser a
- unsafeLiftIO :: IO a -> Parser a
- decodeWord :: Parser Word
- decodeWord64 :: Parser Word64
- decodeWord32 :: Parser Word32
- decodeWord16 :: Parser Word16
- decodeWord8 :: Parser Word8
- decodeInt :: Parser Int
- decodeInt64 :: Parser Int64
- decodeInt32 :: Parser Int32
- decodeInt16 :: Parser Int16
- decodeInt8 :: Parser Int8
- decodeDouble :: Parser Double
- decodeFloat :: Parser Float
- decodeWordLE :: Parser Word
- decodeWord64LE :: Parser Word64
- decodeWord32LE :: Parser Word32
- decodeWord16LE :: Parser Word16
- decodeIntLE :: Parser Int
- decodeInt64LE :: Parser Int64
- decodeInt32LE :: Parser Int32
- decodeInt16LE :: Parser Int16
- decodeDoubleLE :: Parser Double
- decodeFloatLE :: Parser Float
- decodeWordBE :: Parser Word
- decodeWord64BE :: Parser Word64
- decodeWord32BE :: Parser Word32
- decodeWord16BE :: Parser Word16
- decodeIntBE :: Parser Int
- decodeInt64BE :: Parser Int64
- decodeInt32BE :: Parser Int32
- decodeInt16BE :: Parser Int16
- decodeDoubleBE :: Parser Double
- decodeFloatBE :: Parser Float
Parser types
Simple parsing result, that represent respectively:
- Success: the remaining unparsed data and the parsed value
- Failure: the remaining unparsed data and the error message
- Partial: that need for more input data, supply empty bytes to indicate
endOfInput
type ParseError = [Text] Source #
Type alias for error message
Simple CPSed parser
A parser takes a failure continuation, and a success one, while the success continuation is
usually composed by Monad instance, the failure one is more like a reader part, which can
be modified via <?>. If you build parsers from ground, a pattern like this can be used:
xxParser = do
ensureN errMsg ... -- make sure we have some bytes
Parser $ kf k s inp -> -- fail continuation, success continuation, state token and input
...
... kf errMsg (if input not OK)
... k s ... (if we get something useful for next parser)
Constructors
| Parser | |
Fields
| |
Running a parser
parse :: Parser a -> Bytes -> (Bytes, Either ParseError a) Source #
Parse the complete input, without resupplying, return the rest bytes
parse' :: Parser a -> Bytes -> Either ParseError a Source #
Parse the complete input, without resupplying
parseChunk :: Parser a -> Bytes -> Result ParseError a Source #
Parse an input chunk
type ParseChunks m err x = m Bytes -> Bytes -> m (Bytes, Either err x) Source #
Type alias for a streaming parser, draw chunk from Monad m with a initial chunk,
return result in Either err x.
parseChunks :: Monad m => (Bytes -> Result e a) -> ParseChunks m e a Source #
Run a chunk parser with an initial input string, and a monadic action that can supply more input if needed.
finishParsing :: Result ParseError a -> (Bytes, Either ParseError a) Source #
Finish parsing and fetch result, feed empty bytes if it's Partial result.
runAndKeepTrack :: Parser a -> Parser (Result ParseError a, [Bytes]) Source #
match :: Parser a -> Parser (Bytes, a) Source #
Return both the result of a parse and the portion of the input that was consumed while it was being parsed.
Basic parsers
ensureN :: Int -> Text -> Parser () Source #
Ensure that there are at least n bytes available. If not, the
computation will escape with Partial.
Since this parser is used in many other parsers, an extra error param is provide to attach custom error info.
endOfInput :: Parser () Source #
Test whether all input has been consumed, i.e. there are no remaining
undecoded bytes. Fail if not atEnd.
currentChunk :: Parser Bytes Source #
Get current input chunk, draw new chunk if neccessary. null means EOF.
Note this is different from takeRemaining, currentChunk only return what's
left in current input chunk.
Test whether all input has been consumed, i.e. there are no remaining undecoded bytes.
Primitive decoders
decodePrim :: forall a. Unaligned a => Parser a Source #
Decode a primitive type in host byte order.
big endianess wrapper
Instances
little endianess wrapper
Instances
decodePrimLE :: forall a. Unaligned (LE a) => Parser a Source #
Decode a primitive type in little endian.
decodePrimBE :: forall a. Unaligned (BE a) => Parser a Source #
Decode a primitive type in big endian.
More parsers
scan :: s -> (s -> Word8 -> Maybe s) -> Parser (Bytes, s) Source #
A stateful scanner. The predicate consumes and transforms a
state argument, and each transformed state is passed to successive
invocations of the predicate on each byte of the input until one
returns Nothing or the input ends.
This parser does not fail. It will return an empty string if the
predicate returns Nothing on the first byte of input.
scanChunks :: forall s. s -> (s -> Bytes -> Either s (Bytes, Bytes, s)) -> Parser (Bytes, s) Source #
peekMaybe :: Parser (Maybe Word8) Source #
Match any byte, to perform lookahead. Returns Nothing if end of
input has been reached. Does not consume any input.
Match any byte, to perform lookahead. Does not consume any input, but will fail if end of input has been reached.
satisfy :: (Word8 -> Bool) -> Parser Word8 Source #
The parser satisfy p succeeds for any byte for which the
predicate p returns True. Returns the byte that is actually
parsed.
digit = satisfy isDigit
where isDigit w = w >= 48 && w <= 57satisfyWith :: (Word8 -> a) -> (a -> Bool) -> Parser a Source #
The parser satisfyWith f p transforms a byte, and succeeds if
the predicate p returns True on the transformed value. The
parser returns the transformed byte that was parsed.
anyCharUTF8 :: Parser Char Source #
Decode next few bytes as an UTF8 char.
Don't use this method as UTF8 decoder, it's slower than validate.
endOfLine :: Parser () Source #
Match either a single newline byte '\n', or a carriage
return followed by a newline byte "\r\n".
skipWhile :: (Word8 -> Bool) -> Parser () Source #
Skip past input for as long as the predicate returns True.
skipSpaces :: Parser () Source #
Skip over white space using isSpace.
takeN :: (Word8 -> Bool) -> Int -> Parser Bytes Source #
Similar to take, but requires the predicate to succeed on next N bytes
of input, and take N bytes(no matter if N+1 byte satisfy predicate or not).
takeTill :: (Word8 -> Bool) -> Parser Bytes Source #
Consume input as long as the predicate returns False or reach the end of input,
and return the consumed input.
takeWhile :: (Word8 -> Bool) -> Parser Bytes Source #
Consume input as long as the predicate returns True or reach the end of input,
and return the consumed input.
Error reporting
failWithInput :: (Bytes -> Text) -> Parser a Source #
Similar to fail`, but can produce error message with current input chunk.
unsafeLiftIO :: IO a -> Parser a Source #
Specialized primitive parser
decodeWord :: Parser Word Source #
Decode Word in host endian order.
decodeWord64 :: Parser Word64 Source #
Decode Word64 in host endian order.
decodeWord32 :: Parser Word32 Source #
Decode Word32 in host endian order.
decodeWord16 :: Parser Word16 Source #
Decode Word16 in host endian order.
decodeWord8 :: Parser Word8 Source #
Decode Word8 in host endian order.
decodeInt64 :: Parser Int64 Source #
Decode Int64 in host endian order.
decodeInt32 :: Parser Int32 Source #
Decode Int32 in host endian order.
decodeInt16 :: Parser Int16 Source #
Decode Int16 in host endian order.
decodeInt8 :: Parser Int8 Source #
Decode Int8 in host endian order.
decodeDouble :: Parser Double Source #
Decode Double in host endian order.
decodeFloat :: Parser Float Source #
Decode Float in host endian order.
decodeWordLE :: Parser Word Source #
Decode Word in little endian order.
decodeWord64LE :: Parser Word64 Source #
Decode Word64 in little endian order.
decodeWord32LE :: Parser Word32 Source #
Decode Word32 in little endian order.
decodeWord16LE :: Parser Word16 Source #
Decode Word16 in little endian order.
decodeIntLE :: Parser Int Source #
Decode Int in little endian order.
decodeInt64LE :: Parser Int64 Source #
Decode Int64 in little endian order.
decodeInt32LE :: Parser Int32 Source #
Decode Int32 in little endian order.
decodeInt16LE :: Parser Int16 Source #
Decode Int16 in little endian order.
decodeDoubleLE :: Parser Double Source #
Decode Double in little endian order.
decodeFloatLE :: Parser Float Source #
Decode Float in little endian order.
decodeWordBE :: Parser Word Source #
Decode Word in big endian order.
decodeWord64BE :: Parser Word64 Source #
Decode Word64 in big endian order.
decodeWord32BE :: Parser Word32 Source #
Decode Word32 in big endian order.
decodeWord16BE :: Parser Word16 Source #
Decode Word16 in big endian order.
decodeIntBE :: Parser Int Source #
Decode Int in big endian order.
decodeInt64BE :: Parser Int64 Source #
Decode Int64 in big endian order.
decodeInt32BE :: Parser Int32 Source #
Decode Int32 in big endian order.
decodeInt16BE :: Parser Int16 Source #
Decode Int16 in big endian order.
decodeDoubleBE :: Parser Double Source #
Decode Double in big endian order.
decodeFloatBE :: Parser Float Source #
Decode Float in big endian order.