Copyright (c) Daan Leijen 1999-2001 (c) Paolo Martini 2007 BSD-style (see the LICENSE file) derek.a.elkins@gmail.com provisional portable Safe Haskell2010

Text.Parsec.Prim

Description

The primitive parser combinators.

Synopsis

# Documentation

unexpected :: Stream s m t => String -> ParsecT s u m a Source #

The parser unexpected msg always fails with an unexpected error message msg without consuming any input.

The parsers fail, (<?>) and unexpected are the three parsers used to generate error messages. Of these, only (<?>) is commonly used. For an example of the use of unexpected, see the definition of notFollowedBy.

data ParsecT s u m a Source #

ParserT monad transformer and Parser type

ParsecT s u m a is a parser with stream type s, user state type u, underlying monad m and return type a. Parsec is strict in the user state. If this is undesirable, simply use a data type like data Box a = Box a and the state type Box YourStateType to add a level of indirection.

Instances
 MonadState s m => MonadState s (ParsecT s' u m) Source # Instance detailsMethodsget :: ParsecT s' u m s #put :: s -> ParsecT s' u m () #state :: (s -> (a, s)) -> ParsecT s' u m a # MonadReader r m => MonadReader r (ParsecT s u m) Source # Instance detailsMethodsask :: ParsecT s u m r #local :: (r -> r) -> ParsecT s u m a -> ParsecT s u m a #reader :: (r -> a) -> ParsecT s u m a # MonadError e m => MonadError e (ParsecT s u m) Source # Instance detailsMethodsthrowError :: e -> ParsecT s u m a #catchError :: ParsecT s u m a -> (e -> ParsecT s u m a) -> ParsecT s u m a # MonadTrans (ParsecT s u) Source # Instance detailsMethodslift :: Monad m => m a -> ParsecT s u m a # Monad (ParsecT s u m) Source # Instance detailsMethods(>>=) :: ParsecT s u m a -> (a -> ParsecT s u m b) -> ParsecT s u m b #(>>) :: ParsecT s u m a -> ParsecT s u m b -> ParsecT s u m b #return :: a -> ParsecT s u m a #fail :: String -> ParsecT s u m a # Functor (ParsecT s u m) Source # Instance detailsMethodsfmap :: (a -> b) -> ParsecT s u m a -> ParsecT s u m b #(<$) :: a -> ParsecT s u m b -> ParsecT s u m a # MonadFail (ParsecT s u m) Source # Since: 3.1.12.0 Instance detailsMethodsfail :: String -> ParsecT s u m a # Applicative (ParsecT s u m) Source # Instance detailsMethodspure :: a -> ParsecT s u m a #(<*>) :: ParsecT s u m (a -> b) -> ParsecT s u m a -> ParsecT s u m b #liftA2 :: (a -> b -> c) -> ParsecT s u m a -> ParsecT s u m b -> ParsecT s u m c #(*>) :: ParsecT s u m a -> ParsecT s u m b -> ParsecT s u m b #(<*) :: ParsecT s u m a -> ParsecT s u m b -> ParsecT s u m a # MonadIO m => MonadIO (ParsecT s u m) Source # Instance detailsMethodsliftIO :: IO a -> ParsecT s u m a # Alternative (ParsecT s u m) Source # Instance detailsMethodsempty :: ParsecT s u m a #(<|>) :: ParsecT s u m a -> ParsecT s u m a -> ParsecT s u m a #some :: ParsecT s u m a -> ParsecT s u m [a] #many :: ParsecT s u m a -> ParsecT s u m [a] # MonadPlus (ParsecT s u m) Source # Instance detailsMethodsmzero :: ParsecT s u m a #mplus :: ParsecT s u m a -> ParsecT s u m a -> ParsecT s u m a # MonadCont m => MonadCont (ParsecT s u m) Source # Instance detailsMethodscallCC :: ((a -> ParsecT s u m b) -> ParsecT s u m a) -> ParsecT s u m a # Semigroup a => Semigroup (ParsecT s u m a) Source # The Semigroup instance for ParsecT is used to append the result of several parsers, for example:(many$ char a) <> (many $char b) The above will parse a string like "aabbb" and return a successful parse result "aabbb". Compare against the below which will produce a result of "bbb" for the same input:(many$ char a) >> (many $char b) (many$ char a) *> (many $char b) Since: 3.1.12 Instance detailsMethods(<>) :: ParsecT s u m a -> ParsecT s u m a -> ParsecT s u m a #sconcat :: NonEmpty (ParsecT s u m a) -> ParsecT s u m a #stimes :: Integral b => b -> ParsecT s u m a -> ParsecT s u m a # (Monoid a, Semigroup (ParsecT s u m a)) => Monoid (ParsecT s u m a) Source # The Monoid instance for ParsecT is used for the same purposes as the Semigroup instance.Since: 3.1.12 Instance detailsMethodsmempty :: ParsecT s u m a #mappend :: ParsecT s u m a -> ParsecT s u m a -> ParsecT s u m a #mconcat :: [ParsecT s u m a] -> ParsecT s u m a # runParsecT :: Monad m => ParsecT s u m a -> State s u -> m (Consumed (m (Reply s u a))) Source # Low-level unpacking of the ParsecT type. To run your parser, please look to runPT, runP, runParserT, runParser and other such functions. mkPT :: Monad m => (State s u -> m (Consumed (m (Reply s u a)))) -> ParsecT s u m a Source # Low-level creation of the ParsecT type. You really shouldn't have to do this. type Parsec s u = ParsecT s u Identity Source # data Consumed a Source # Constructors  Consumed a Empty !a Instances  Source # Instance detailsMethodsfmap :: (a -> b) -> Consumed a -> Consumed b #(<$) :: a -> Consumed b -> Consumed a #

data Reply s u a Source #

Constructors

 Ok a !(State s u) ParseError Error ParseError
Instances
 Functor (Reply s u) Source # Instance detailsMethodsfmap :: (a -> b) -> Reply s u a -> Reply s u b #(<\$) :: a -> Reply s u b -> Reply s u a #

data State s u Source #

Constructors

 State FieldsstateInput :: s statePos :: !SourcePos stateUser :: !u

parsecMap :: (a -> b) -> ParsecT s u m a -> ParsecT s u m b Source #

parserReturn :: a -> ParsecT s u m a Source #

parserBind :: ParsecT s u m a -> (a -> ParsecT s u m b) -> ParsecT s u m b Source #

parserZero :: ParsecT s u m a Source #

parserZero always fails without consuming any input. parserZero is defined equal to the mzero member of the MonadPlus class and to the empty member of the Alternative class.

parserPlus :: ParsecT s u m a -> ParsecT s u m a -> ParsecT s u m a Source #

(<?>) :: ParsecT s u m a -> String -> ParsecT s u m a infix 0 Source #

The parser p <?> msg behaves as parser p, but whenever the parser p fails without consuming any input, it replaces expect error messages with the expect error message msg.

This is normally used at the end of a set alternatives where we want to return an error message in terms of a higher level construct rather than returning all possible characters. For example, if the expr parser from the try example would fail, the error message is: '...: expecting expression'. Without the (<?>) combinator, the message would be like '...: expecting "let" or letter', which is less friendly.

(<|>) :: ParsecT s u m a -> ParsecT s u m a -> ParsecT s u m a infixr 1 Source #

This combinator implements choice. The parser p <|> q first applies p. If it succeeds, the value of p is returned. If p fails without consuming any input, parser q is tried. This combinator is defined equal to the mplus member of the MonadPlus class and the (<|>) member of Alternative.

The parser is called predictive since q is only tried when parser p didn't consume any input (i.e.. the look ahead is 1). This non-backtracking behaviour allows for both an efficient implementation of the parser combinators and the generation of good error messages.

label :: ParsecT s u m a -> String -> ParsecT s u m a Source #

A synonym for <?>, but as a function instead of an operator.

labels :: ParsecT s u m a -> [String] -> ParsecT s u m a Source #

lookAhead :: Stream s m t => ParsecT s u m a -> ParsecT s u m a Source #

lookAhead p parses p without consuming any input.

If p fails and consumes some input, so does lookAhead. Combine with try if this is undesirable.

class Monad m => Stream s m t | s -> t where Source #

An instance of Stream has stream type s, underlying monad m and token type t determined by the stream

Some rough guidelines for a "correct" instance of Stream:

• unfoldM uncons gives the [t] corresponding to the stream
• A Stream instance is responsible for maintaining the "position within the stream" in the stream state s. This is trivial unless you are using the monad in a non-trivial way.

Minimal complete definition

uncons

Methods

uncons :: s -> m (Maybe (t, s)) Source #

Instances
 Source # Instance detailsMethodsuncons :: ByteString -> m (Maybe (Char, ByteString)) Source # Source # Instance detailsMethodsuncons :: ByteString -> m (Maybe (Char, ByteString)) Source # Monad m => Stream Text m Char Source # Instance detailsMethodsuncons :: Text -> m (Maybe (Char, Text)) Source # Monad m => Stream Text m Char Source # Instance detailsMethodsuncons :: Text -> m (Maybe (Char, Text)) Source # Monad m => Stream [tok] m tok Source # Instance detailsMethodsuncons :: [tok] -> m (Maybe (tok, [tok])) Source #

tokens :: (Stream s m t, Eq t) => ([t] -> String) -> (SourcePos -> [t] -> SourcePos) -> [t] -> ParsecT s u m [t] Source #

try :: ParsecT s u m a -> ParsecT s u m a Source #

The parser try p behaves like parser p, except that it pretends that it hasn't consumed any input when an error occurs.

This combinator is used whenever arbitrary look ahead is needed. Since it pretends that it hasn't consumed any input when p fails, the (<|>) combinator will try its second alternative even when the first parser failed while consuming input.

The try combinator can for example be used to distinguish identifiers and reserved words. Both reserved words and identifiers are a sequence of letters. Whenever we expect a certain reserved word where we can also expect an identifier we have to use the try combinator. Suppose we write:

 expr        = letExpr <|> identifier <?> "expression"

letExpr     = do{ string "let"; ... }
identifier  = many1 letter

If the user writes "lexical", the parser fails with: unexpected 'x', expecting 't' in "let". Indeed, since the (<|>) combinator only tries alternatives when the first alternative hasn't consumed input, the identifier parser is never tried (because the prefix "le" of the string "let" parser is already consumed). The right behaviour can be obtained by adding the try combinator:

 expr        = letExpr <|> identifier <?> "expression"

letExpr     = do{ try (string "let"); ... }
identifier  = many1 letter

Arguments

 :: Stream s Identity t => (t -> String) Token pretty-printing function. -> (t -> SourcePos) Computes the position of a token. -> (t -> Maybe a) Matching function for the token to parse. -> Parsec s u a

The parser token showTok posFromTok testTok accepts a token t with result x when the function testTok t returns Just x. The source position of the t should be returned by posFromTok t and the token can be shown using showTok t.

This combinator is expressed in terms of tokenPrim. It is used to accept user defined token streams. For example, suppose that we have a stream of basic tokens tupled with source positions. We can then define a parser that accepts single tokens as:

 mytoken x
= token showTok posFromTok testTok
where
showTok (pos,t)     = show t
posFromTok (pos,t)  = pos
testTok (pos,t)     = if x == t then Just t else Nothing

Arguments

 :: Stream s m t => (t -> String) Token pretty-printing function. -> (SourcePos -> t -> s -> SourcePos) Next position calculating function. -> (t -> Maybe a) Matching function for the token to parse. -> ParsecT s u m a

The parser tokenPrim showTok nextPos testTok accepts a token t with result x when the function testTok t returns Just x. The token can be shown using showTok t. The position of the next token should be returned when nextPos is called with the current source position pos, the current token t and the rest of the tokens toks, nextPos pos t toks.

This is the most primitive combinator for accepting tokens. For example, the char parser could be implemented as:

 char c
= tokenPrim showChar nextPos testChar
where
showChar x        = "'" ++ x ++ "'"
testChar x        = if x == c then Just x else Nothing
nextPos pos x xs  = updatePosChar pos x

tokenPrimEx :: Stream s m t => (t -> String) -> (SourcePos -> t -> s -> SourcePos) -> Maybe (SourcePos -> t -> s -> u -> u) -> (t -> Maybe a) -> ParsecT s u m a Source #

many :: ParsecT s u m a -> ParsecT s u m [a] Source #

many p applies the parser p zero or more times. Returns a list of the returned values of p.

 identifier  = do{ c  <- letter
; cs <- many (alphaNum <|> char '_')
; return (c:cs)
}

skipMany :: ParsecT s u m a -> ParsecT s u m () Source #

skipMany p applies the parser p zero or more times, skipping its result.

 spaces  = skipMany space

manyAccum :: (a -> [a] -> [a]) -> ParsecT s u m a -> ParsecT s u m [a] Source #

runPT :: Stream s m t => ParsecT s u m a -> u -> SourceName -> s -> m (Either ParseError a) Source #

runP :: Stream s Identity t => Parsec s u a -> u -> SourceName -> s -> Either ParseError a Source #

runParserT :: Stream s m t => ParsecT s u m a -> u -> SourceName -> s -> m (Either ParseError a) Source #

The most general way to run a parser. runParserT p state filePath input runs parser p on the input list of tokens input, obtained from source filePath with the initial user state st. The filePath is only used in error messages and may be the empty string. Returns a computation in the underlying monad m that return either a ParseError (Left) or a value of type a (Right).

runParser :: Stream s Identity t => Parsec s u a -> u -> SourceName -> s -> Either ParseError a Source #

The most general way to run a parser over the Identity monad. runParser p state filePath input runs parser p on the input list of tokens input, obtained from source filePath with the initial user state st. The filePath is only used in error messages and may be the empty string. Returns either a ParseError (Left) or a value of type a (Right).

 parseFromFile p fname
= do{ input <- readFile fname
; return (runParser p () fname input)
}

parse :: Stream s Identity t => Parsec s () a -> SourceName -> s -> Either ParseError a Source #

parse p filePath input runs a parser p over Identity without user state. The filePath is only used in error messages and may be the empty string. Returns either a ParseError (Left) or a value of type a (Right).

 main    = case (parse numbers "" "11, 2, 43") of
Left err  -> print err
Right xs  -> print (sum xs)

numbers = commaSep integer

parseTest :: (Stream s Identity t, Show a) => Parsec s () a -> s -> IO () Source #

The expression parseTest p input applies a parser p against input input and prints the result to stdout. Used for testing parsers.

getPosition :: Monad m => ParsecT s u m SourcePos Source #

Returns the current source position. See also SourcePos.

getInput :: Monad m => ParsecT s u m s Source #

Returns the current input

setPosition :: Monad m => SourcePos -> ParsecT s u m () Source #

setPosition pos sets the current source position to pos.

setInput :: Monad m => s -> ParsecT s u m () Source #

setInput input continues parsing with input. The getInput and setInput functions can for example be used to deal with #include files.

getParserState :: Monad m => ParsecT s u m (State s u) Source #

Returns the full parser state as a State record.

setParserState :: Monad m => State s u -> ParsecT s u m (State s u) Source #

setParserState st set the full parser state to st.

updateParserState :: (State s u -> State s u) -> ParsecT s u m (State s u) Source #

updateParserState f applies function f to the parser state.

getState :: Monad m => ParsecT s u m u Source #

Returns the current user state.

putState :: Monad m => u -> ParsecT s u m () Source #

putState st set the user state to st.

modifyState :: Monad m => (u -> u) -> ParsecT s u m () Source #

modifyState f applies function f to the user state. Suppose that we want to count identifiers in a source, we could use the user state as:

 expr  = do{ x <- identifier
; modifyState (+1)
; return (Id x)
}

setState :: Monad m => u -> ParsecT s u m () Source #

An alias for putState for backwards compatibility.

updateState :: Monad m => (u -> u) -> ParsecT s u m () Source #

An alias for modifyState for backwards compatibility.