Copyright | (c) Daan Leijen 1999-2001 (c) Paolo Martini 2007 |
---|---|
License | BSD-style (see the LICENSE file) |
Maintainer | derek.a.elkins@gmail.com |
Stability | provisional |
Portability | portable |
Safe Haskell | Safe |
Language | Haskell2010 |
Text.Parsec.Prim
Description
The primitive parser combinators.
Synopsis
- unknownError :: State s u -> ParseError
- sysUnExpectError :: String -> SourcePos -> Reply s u a
- unexpected :: Stream s m t => String -> ParsecT s u m a
- data ParsecT s u m a
- runParsecT :: Monad m => ParsecT s u m a -> State s u -> m ( Consumed (m ( Reply s u a)))
- mkPT :: Monad m => ( State s u -> m ( Consumed (m ( Reply s u a)))) -> ParsecT s u m a
- type Parsec s u = ParsecT s u Identity
- data Consumed a
-
data
Reply
s u a
- = Ok a !( State s u) ParseError
- | Error ParseError
-
data
State
s u =
State
{
- stateInput :: s
- statePos :: ! SourcePos
- stateUser :: !u
- parsecMap :: (a -> b) -> ParsecT s u m a -> ParsecT s u m b
- parserReturn :: a -> ParsecT s u m a
- parserBind :: ParsecT s u m a -> (a -> ParsecT s u m b) -> ParsecT s u m b
- mergeErrorReply :: ParseError -> Reply s u a -> Reply s u a
- parserFail :: String -> ParsecT s u m a
- parserZero :: ParsecT s u m a
- parserPlus :: ParsecT s u m a -> ParsecT s u m a -> ParsecT s u m a
- (<?>) :: ParsecT s u m a -> String -> ParsecT s u m a
- (<|>) :: ParsecT s u m a -> ParsecT s u m a -> ParsecT s u m a
- label :: ParsecT s u m a -> String -> ParsecT s u m a
- labels :: ParsecT s u m a -> [ String ] -> ParsecT s u m a
- lookAhead :: Stream s m t => ParsecT s u m a -> ParsecT s u m a
- class Monad m => Stream s m t | s -> t where
- tokens :: ( Stream s m t, Eq t) => ([t] -> String ) -> ( SourcePos -> [t] -> SourcePos ) -> [t] -> ParsecT s u m [t]
- try :: ParsecT s u m a -> ParsecT s u m a
- token :: Stream s Identity t => (t -> String ) -> (t -> SourcePos ) -> (t -> Maybe a) -> Parsec s u a
- tokenPrim :: Stream s m t => (t -> String ) -> ( SourcePos -> t -> s -> SourcePos ) -> (t -> Maybe a) -> ParsecT s u m a
- 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
- many :: ParsecT s u m a -> ParsecT s u m [a]
- skipMany :: ParsecT s u m a -> ParsecT s u m ()
- manyAccum :: (a -> [a] -> [a]) -> ParsecT s u m a -> ParsecT s u m [a]
- runPT :: Stream s m t => ParsecT s u m a -> u -> SourceName -> s -> m ( Either ParseError a)
- runP :: Stream s Identity t => Parsec s u a -> u -> SourceName -> s -> Either ParseError a
- runParserT :: Stream s m t => ParsecT s u m a -> u -> SourceName -> s -> m ( Either ParseError a)
- runParser :: Stream s Identity t => Parsec s u a -> u -> SourceName -> s -> Either ParseError a
- parse :: Stream s Identity t => Parsec s () a -> SourceName -> s -> Either ParseError a
- parseTest :: ( Stream s Identity t, Show a) => Parsec s () a -> s -> IO ()
- getPosition :: Monad m => ParsecT s u m SourcePos
- getInput :: Monad m => ParsecT s u m s
- setPosition :: Monad m => SourcePos -> ParsecT s u m ()
- setInput :: Monad m => s -> ParsecT s u m ()
- getParserState :: Monad m => ParsecT s u m ( State s u)
- setParserState :: Monad m => State s u -> ParsecT s u m ( State s u)
- updateParserState :: ( State s u -> State s u) -> ParsecT s u m ( State s u)
- getState :: Monad m => ParsecT s u m u
- putState :: Monad m => u -> ParsecT s u m ()
- modifyState :: Monad m => (u -> u) -> ParsecT s u m ()
- setState :: Monad m => u -> ParsecT s u m ()
- updateState :: Monad m => (u -> u) -> ParsecT s u m ()
Documentation
unknownError :: State s u -> ParseError Source #
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
.
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 # | |
MonadReader r m => MonadReader r ( ParsecT s u m) Source # | |
MonadError e m => MonadError e ( ParsecT s u m) Source # | |
Defined in Text.Parsec.Prim Methods throwError :: e -> ParsecT s u m a Source # catchError :: ParsecT s u m a -> (e -> ParsecT s u m a) -> ParsecT s u m a Source # |
|
MonadTrans ( ParsecT s u) Source # | |
Monad ( ParsecT s u m) Source # | |
Functor ( ParsecT s u m) Source # | |
MonadFail ( ParsecT s u m) Source # |
Since: 3.1.12.0 |
Applicative ( ParsecT s u m) Source # | |
Defined in Text.Parsec.Prim Methods pure :: a -> ParsecT s u m a Source # (<*>) :: ParsecT s u m (a -> b) -> ParsecT s u m a -> ParsecT s u m b Source # liftA2 :: (a -> b -> c) -> ParsecT s u m a -> ParsecT s u m b -> ParsecT s u m c Source # (*>) :: ParsecT s u m a -> ParsecT s u m b -> ParsecT s u m b Source # (<*) :: ParsecT s u m a -> ParsecT s u m b -> ParsecT s u m a Source # |
|
MonadIO m => MonadIO ( ParsecT s u m) Source # | |
Alternative ( ParsecT s u m) Source # | |
MonadPlus ( ParsecT s u m) Source # | |
MonadCont m => MonadCont ( ParsecT s u m) Source # | |
Semigroup a => Semigroup ( ParsecT s u m a) Source # |
The
(many $ char
The above will parse a string like
(many $ char Since: 3.1.12 |
( Monoid a, Semigroup ( ParsecT s u m a)) => Monoid ( ParsecT s u m a) Source # |
The
Since: 3.1.12 |
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.
Constructors
Ok a !( State s u) ParseError | |
Error ParseError |
Constructors
State | |
Fields
|
parserReturn :: a -> ParsecT s u m a Source #
mergeErrorReply :: ParseError -> Reply s u a -> Reply s u a Source #
parserFail :: String -> ParsecT s u m a 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.
(<?>) :: 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.
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 states
. This is trivial unless you are using the monad in a non-trivial way.
Instances
Monad m => Stream ByteString m Char Source # | |
Defined in Text.Parsec.Prim Methods uncons :: ByteString -> m ( Maybe ( Char , ByteString )) Source # |
|
Monad m => Stream ByteString m Char Source # | |
Defined in Text.Parsec.Prim Methods uncons :: ByteString -> m ( Maybe ( Char , ByteString )) Source # |
|
Monad m => Stream Text m Char Source # | |
Monad m => Stream Text m Char Source # | |
Monad m => Stream [tok] m tok Source # | |
Defined in Text.Parsec.Prim |
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
. The
source position of the
Just
x
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
. The
token can be shown using
Just
x
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
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
.
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.
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.