Text.Megaparsec

This module includes everything you need to get started writing a parser. If you are new to Megaparsec and don't know where to begin, take a look at the tutorials https://markkarpov.com/learn-haskell.html#megaparsec-tutorials.

By default this module is set up to parse character data. If you'd like to parse the result of your own tokenizer you should start with the following imports:

import Text.Megaparsec.Prim
import Text.Megaparsec.Combinator

Then you can implement your own version of satisfy on top of the token primitive, etc.

The typical import section looks like this:

import Text.Megaparsec
import Text.Megaparsec.String
-- import Text.Megaparsec.ByteString
-- import Text.Megaparsec.ByteString.Lazy
-- import Text.Megaparsec.Text
-- import Text.Megaparsec.Text.Lazy

As you can see the second import depends on the data type you want to use as input stream. It just defines the useful type-synonym Parser.

Megaparsec 5 uses some type-level machinery to provide flexibility without compromising on type safety. Thus type signatures are sometimes necessary to avoid ambiguous types. If you're seeing a error message that reads like “Ambiguous type variable e0 arising from … prevents the constraint (ErrorComponent e0) from being resolved”, you need to give an explicit signature to your parser to resolve the ambiguity. It's a good idea to provide type signatures for all top-level definitions.

Megaparsec is capable of a lot. Apart from this standard functionality you can parse permutation phrases with Text.Megaparsec.Perm, expressions with Text.Megaparsec.Expr, and even entire languages with Text.Megaparsec.Lexer. These modules should be imported explicitly along with the two modules mentioned above.

Running parser

type Parsec e s = ParsecT e s Identity

Parsec is a non-transformer variant of the more general ParsecT monad transformer.

data ParsecT e s m a

ParsecT e s m a is a parser with custom data component of error e, stream type s, underlying monad m and return type a.

Instances

(ErrorComponent e, Stream s) => MonadParsec e s (ParsecT e s m)

Methods

failure :: Set (ErrorItem (Token s)) -> Set (ErrorItem (Token s)) -> Set e -> ParsecT e s m a

label :: String -> ParsecT e s m a -> ParsecT e s m a

hidden :: ParsecT e s m a -> ParsecT e s m a

try :: ParsecT e s m a -> ParsecT e s m a

lookAhead :: ParsecT e s m a -> ParsecT e s m a

notFollowedBy :: ParsecT e s m a -> ParsecT e s m ()

withRecovery :: (ParseError (Token s) e -> ParsecT e s m a) -> ParsecT e s m a -> ParsecT e s m a

observing :: ParsecT e s m a -> ParsecT e s m (Either (ParseError (Token s) e) a)

eof :: ParsecT e s m ()

token :: (Token s -> Either (Set (ErrorItem (Token s)), Set (ErrorItem (Token s)), Set e) a) -> Maybe (Token s) -> ParsecT e s m a

tokens :: (Token s -> Token s -> Bool) -> [Token s] -> ParsecT e s m [Token s]

getParserState :: ParsecT e s m (State s)

updateParserState :: (State s -> State s) -> ParsecT e s m ()

(ErrorComponent e, Stream s, MonadError e' m) => MonadError e' (ParsecT e s m)

Methods

throwError :: e' -> ParsecT e s m a

catchError :: ParsecT e s m a -> (e' -> ParsecT e s m a) -> ParsecT e s m a

(ErrorComponent e, Stream s, MonadReader r m) => MonadReader r (ParsecT e s m)

Methods

ask :: ParsecT e s m r

local :: (r -> r) -> ParsecT e s m a -> ParsecT e s m a

reader :: (r -> a) -> ParsecT e s m a

(ErrorComponent e, Stream s, MonadState st m) => MonadState st (ParsecT e s m)

Methods

get :: ParsecT e s m st

put :: st -> ParsecT e s m ()

state :: (st -> (a, st)) -> ParsecT e s m a

MonadTrans (ParsecT e s)

Methods

lift :: Monad m => m a -> ParsecT e s m a

(ErrorComponent e, Stream s) => Monad (ParsecT e s m)

Methods

(>>=) :: ParsecT e s m a -> (a -> ParsecT e s m b) -> ParsecT e s m b

(>>) :: ParsecT e s m a -> ParsecT e s m b -> ParsecT e s m b

return :: a -> ParsecT e s m a

fail :: String -> ParsecT e s m a

Functor (ParsecT e s m)

Methods

fmap :: (a -> b) -> ParsecT e s m a -> ParsecT e s m b

(<$) :: a -> ParsecT e s m b -> ParsecT e s m a

(ErrorComponent e, Stream s) => MonadFail (ParsecT e s m)

Methods

fail :: String -> ParsecT e s m a

(ErrorComponent e, Stream s) => Applicative (ParsecT e s m)

Methods

pure :: a -> ParsecT e s m a

(<*>) :: ParsecT e s m (a -> b) -> ParsecT e s m a -> ParsecT e s m b

(*>) :: ParsecT e s m a -> ParsecT e s m b -> ParsecT e s m b

(<*) :: ParsecT e s m a -> ParsecT e s m b -> ParsecT e s m a

(ErrorComponent e, Stream s, MonadIO m) => MonadIO (ParsecT e s m)

Methods

liftIO :: IO a -> ParsecT e s m a

(ErrorComponent e, Stream s) => Alternative (ParsecT e s m)

Methods

empty :: ParsecT e s m a

(<|>) :: ParsecT e s m a -> ParsecT e s m a -> ParsecT e s m a

some :: ParsecT e s m a -> ParsecT e s m [a]

many :: ParsecT e s m a -> ParsecT e s m [a]

(ErrorComponent e, Stream s) => MonadPlus (ParsecT e s m)

Methods

mzero :: ParsecT e s m a

mplus :: ParsecT e s m a -> ParsecT e s m a -> ParsecT e s m a

(ErrorComponent e, Stream s, MonadCont m) => MonadCont (ParsecT e s m)

Methods

callCC :: ((a -> ParsecT e s m b) -> ParsecT e s m a) -> ParsecT e s m a

(ErrorComponent e, Stream s, Semigroup a) => Semigroup (ParsecT e s m a)

Methods

(<>) :: ParsecT e s m a -> ParsecT e s m a -> ParsecT e s m a

sconcat :: NonEmpty (ParsecT e s m a) -> ParsecT e s m a

stimes :: Integral b => b -> ParsecT e s m a -> ParsecT e s m a

(ErrorComponent e, Stream s, Monoid a) => Monoid (ParsecT e s m a)

Methods

mempty :: ParsecT e s m a

mappend :: ParsecT e s m a -> ParsecT e s m a -> ParsecT e s m a

mconcat :: [ParsecT e s m a] -> ParsecT e s m a

parse

Arguments

:: Parsec e s a

Parser to run

-> String

Name of source file

-> s

Input for parser

-> Either (ParseError (Token s) e) a

parse p file input runs parser p over Identity (see runParserT if you're using the ParsecT monad transformer; parse itself is just a synonym for runParser). It returns either a ParseError (Left) or a value of type a (Right). parseErrorPretty can be used to turn ParseError into the string representation of the error message. See Text.Megaparsec.Error if you need to do more advanced error analysis.

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

numbers = integer `sepBy` char ','

parseMaybe :: (ErrorComponent e, Stream s) => Parsec e s a -> s -> Maybe a

parseMaybe p input runs the parser p on input and returns the result inside Just on success and Nothing on failure. This function also parses eof, so if the parser doesn't consume all of its input, it will fail.

The function is supposed to be useful for lightweight parsing, where error messages (and thus file name) are not important and entire input should be parsed. For example it can be used when parsing of a single number according to specification of its format is desired.

parseTest

Arguments

:: (ShowErrorComponent e, Ord (Token s), ShowToken (Token s), Show a)

=> Parsec e s a

Parser to run

-> s

Input for parser

-> IO ()

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

runParser

Arguments

:: Parsec e s a

Parser to run

-> String

Name of source file

-> s

Input for parser

-> Either (ParseError (Token s) e) a

runParser p file input runs parser p on the input stream of tokens input, obtained from source file. The file 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 file = runParser p file <$> readFile file

runParser'

Arguments

:: Parsec e s a

Parser to run

-> State s

Initial state

-> (State s, Either (ParseError (Token s) e) a)

The function is similar to runParser with the difference that it accepts and returns parser state. This allows to specify arbitrary textual position at the beginning of parsing, for example. This is the most general way to run a parser over the Identity monad.

Since: 4.2.0

runParserT

Arguments

:: Monad m

=> ParsecT e s m a

Parser to run

-> String

Name of source file

-> s

Input for parser

-> m (Either (ParseError (Token s) e) a)

runParserT p file input runs parser p on the input list of tokens input, obtained from source file. The file is only used in error messages and may be the empty string. Returns a computation in the underlying monad m that returns either a ParseError (Left) or a value of type a (Right).

runParserT'

Arguments

:: Monad m

=> ParsecT e s m a

Parser to run

-> State s

Initial state

-> m (State s, Either (ParseError (Token s) e) a)

This function is similar to runParserT, but like runParser' it accepts and returns parser state. This is thus the most general way to run a parser.

Since: 4.2.0

Combinators

(<|>) :: Alternative f => forall a. f a -> f a -> f a

An associative binary operation

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.

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.

many :: Alternative f => forall a. f a -> f [a]

Zero or more.

many p applies the parser p zero or more times and returns a list of the returned values of p. Note that if the p parser fails consuming input, then the entire many p parser fails with the error message p produced instead of just stopping iterating. In these cases wrapping p with try may be desirable.

identifier = (:) <$> letter <*> many (alphaNumChar <|> char '_')

some :: Alternative f => forall a. f a -> f [a]

One or more.

some p applies the parser p one or more times and returns a list of the returned values of p. The note about behavior of the combinator in the case when p fails consuming input (see many) applies to some as well.

word = some letter

optional :: Alternative f => f a -> f (Maybe a)

One or none.

optional p tries to apply the parser p. It will parse p or nothing. It only fails if p fails after consuming input. On success result of p is returned inside of Just, on failure Nothing is returned.

unexpected :: MonadParsec e s m => ErrorItem (Token s) -> m a

The parser unexpected item fails with an error message telling about unexpected item item without consuming any input.

match :: MonadParsec e s m => m a -> m ([Token s], a)

Return both the result of a parse and the list of tokens that were consumed during parsing. This relies on the change of the stateTokensProcessed value to evaluate how many tokens were consumed.

Since: 5.3.0

region

Arguments

:: MonadParsec e s m

=> (ParseError (Token s) e -> ParseError (Token s) e)

How to process ParseErrors

-> m a

The “region” that processing applies to

-> m a

Specify how to process ParseErrors that happen inside of this wrapper. As a side effect of the current implementation changing errorPos with this combinator will also change the final statePos in the parser state.

Since: 5.3.0

failure :: MonadParsec e s m => Set (ErrorItem (Token s)) -> Set (ErrorItem (Token s)) -> Set e -> m a

The most general way to stop parsing and report a ParseError.

unexpected is defined in terms of this function:

unexpected item = failure (Set.singleton item) Set.empty Set.empty

Since: 4.2.0

(<?>) :: MonadParsec e s m => m a -> String -> m a infix 0

A synonym for label in the form of an operator.

label :: MonadParsec e s m => String -> m a -> m a

The parser label name p behaves as parser p, but whenever the parser p fails without consuming any input, it replaces names of “expected” tokens with the name name.

hidden :: MonadParsec e s m => m a -> m a

hidden p behaves just like parser p, but it doesn't show any “expected” tokens in error message when p fails.

try :: MonadParsec e s m => m a -> m a

The parser try p behaves like parser p, except that it backtracks the parser state when p fails (either consuming input or not).

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.

For example, here is a parser that is supposed to parse the word “let” or the word “lexical”:

>>> parseTest (string "let" <|> string "lexical") "lexical"
1:1:
unexpected "lex"
expecting "let"

What happens here? The first parser consumes “le” and fails (because it doesn't see a “t”). The second parser, however, isn't tried, since the first parser has already consumed some input! try fixes this behavior and allows backtracking to work:

>>> parseTest (try (string "let") <|> string "lexical") "lexical"
"lexical"

try also improves error messages in case of overlapping alternatives, because Megaparsec's hint system can be used:

>>> parseTest (try (string "let") <|> string "lexical") "le"
1:1:
unexpected "le"
expecting "let" or "lexical"

Please note that as of Megaparsec 4.4.0, string backtracks automatically (see tokens), so it does not need try. However, the examples above demonstrate the idea behind try so well that it was decided to keep them. You still need to use try when your alternatives are complex, composite parsers.

lookAhead :: MonadParsec e s m => m a -> m a

If p in lookAhead p succeeds (either consuming input or not) the whole parser behaves like p succeeded without consuming anything (parser state is not updated as well). If p fails, lookAhead has no effect, i.e. it will fail consuming input if p fails consuming input. Combine with try if this is undesirable.

notFollowedBy :: MonadParsec e s m => m a -> m ()

notFollowedBy p only succeeds when the parser p fails. This parser never consumes any input and never modifies parser state. It can be used to implement the “longest match” rule.

withRecovery :: MonadParsec e s m => (ParseError (Token s) e -> m a) -> m a -> m a

withRecovery r p allows continue parsing even if parser p fails. In this case r is called with the actual ParseError as its argument. Typical usage is to return a value signifying failure to parse this particular object and to consume some part of the input up to the point where the next object starts.

Note that if r fails, original error message is reported as if without withRecovery. In no way recovering parser r can influence error messages.

Since: 4.4.0

observing :: MonadParsec e s m => m a -> m (Either (ParseError (Token s) e) a)

observing p allows to “observe” failure of the p parser, should it happen, without actually ending parsing, but instead getting the ParseError in Left. On success parsed value is returned in Right as usual. Note that this primitive just allows you to observe parse errors as they happen, it does not backtrack or change how the p parser works in any way.

Since: 5.1.0

eof :: MonadParsec e s m => m ()

This parser only succeeds at the end of the input.

token :: MonadParsec e s m => (Token s -> Either (Set (ErrorItem (Token s)), Set (ErrorItem (Token s)), Set e) a) -> Maybe (Token s) -> m a

The parser token test mrep accepts a token t with result x when the function test t returns Right x. mrep may provide representation of the token to report in error messages when input stream in empty.

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

satisfy f = token testChar Nothing
  where
    testChar x =
      if f x
        then Right x
        else Left (Set.singleton (Tokens (x:|[])), Set.empty, Set.empty)

tokens :: MonadParsec e s m => (Token s -> Token s -> Bool) -> [Token s] -> m [Token s]

The parser tokens test parses a list of tokens and returns it. Supplied predicate test is used to check equality of given and parsed tokens.

This can be used for example to write string:

string = tokens (==)

Note that beginning from Megaparsec 4.4.0, this is an auto-backtracking primitive, which means that if it fails, it never consumes any input. This is done to make its consumption model match how error messages for this primitive are reported (which becomes an important thing as user gets more control with primitives like withRecovery):

>>> parseTest (string "abc") "abd"
1:1:
unexpected "abd"
expecting "abc"

This means, in particular, that it's no longer necessary to use try with tokens-based parsers, such as string and string'. This feature does not affect performance in any way.

between :: Applicative m => m open -> m close -> m a -> m a

between open close p parses open, followed by p and close. Returns the value returned by p.

braces = between (symbol "{") (symbol "}")

choice :: (Foldable f, Alternative m) => f (m a) -> m a

choice ps tries to apply the parsers in the list ps in order, until one of them succeeds. Returns the value of the succeeding parser.

count :: Applicative m => Int -> m a -> m [a]

count n p parses n occurrences of p. If n is smaller or equal to zero, the parser equals to return []. Returns a list of n values.

count' :: Alternative m => Int -> Int -> m a -> m [a]

count' m n p parses from m to n occurrences of p. If n is not positive or m > n, the parser equals to return []. Returns a list of parsed values.

Please note that m may be negative, in this case effect is the same as if it were equal to zero.

eitherP :: Alternative m => m a -> m b -> m (Either a b)

Combine two alternatives.

Since: 4.4.0

endBy :: Alternative m => m a -> m sep -> m [a]

endBy p sep parses zero or more occurrences of p, separated and ended by sep. Returns a list of values returned by p.

cStatements = cStatement `endBy` semicolon

endBy1 :: Alternative m => m a -> m sep -> m [a]

endBy1 p sep parses one or more occurrences of p, separated and ended by sep. Returns a list of values returned by p.

manyTill :: Alternative m => m a -> m end -> m [a]

manyTill p end applies parser p zero or more times until parser end succeeds. Returns the list of values returned by p. This parser can be used to scan comments:

simpleComment = string "<!--" >> manyTill anyChar (string "-->")

someTill :: Alternative m => m a -> m end -> m [a]

someTill p end works similarly to manyTill p end, but p should succeed at least once.

option :: Alternative m => a -> m a -> m a

option x p tries to apply the parser p. If p fails without consuming input, it returns the value x, otherwise the value returned by p.

priority = option 0 (digitToInt <$> digitChar)

sepBy :: Alternative m => m a -> m sep -> m [a]

sepBy p sep parses zero or more occurrences of p, separated by sep. Returns a list of values returned by p.

commaSep p = p `sepBy` comma

sepBy1 :: Alternative m => m a -> m sep -> m [a]

sepBy1 p sep parses one or more occurrences of p, separated by sep. Returns a list of values returned by p.

sepEndBy :: Alternative m => m a -> m sep -> m [a]

sepEndBy p sep parses zero or more occurrences of p, separated and optionally ended by sep. Returns a list of values returned by p.

sepEndBy1 :: Alternative m => m a -> m sep -> m [a]

sepEndBy1 p sep parses one or more occurrences of p, separated and optionally ended by sep. Returns a list of values returned by p.

skipMany :: Alternative m => m a -> m ()

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

space = skipMany spaceChar

skipSome :: Alternative m => m a -> m ()

skipSome p applies the parser p one or more times, skipping its result.

Character parsing

newline :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a newline character.

crlf :: (MonadParsec e s m, Token s ~ Char) => m String

Parse a carriage return character followed by a newline character. Return the sequence of characters parsed.

eol :: (MonadParsec e s m, Token s ~ Char) => m String

Parse a CRLF (see crlf) or LF (see newline) end of line. Return the sequence of characters parsed.

eol = (pure <$> newline) <|> crlf <?> "end of line"

tab :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a tab character.

space :: (MonadParsec e s m, Token s ~ Char) => m ()

Skip zero or more white space characters.

See also: skipMany and spaceChar.

controlChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a control character (a non-printing character of the Latin-1 subset of Unicode).

spaceChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a Unicode space character, and the control characters: tab, newline, carriage return, form feed, and vertical tab.

upperChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse an upper-case or title-case alphabetic Unicode character. Title case is used by a small number of letter ligatures like the single-character form of Lj.

lowerChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a lower-case alphabetic Unicode character.

letterChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse an alphabetic Unicode character: lower-case, upper-case, or title-case letter, or a letter of case-less scripts/modifier letter.

alphaNumChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse an alphabetic or numeric digit Unicode characters.

Note that the numeric digits outside the ASCII range are parsed by this parser but not by digitChar. Such digits may be part of identifiers but are not used by the printer and reader to represent numbers.

printChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a printable Unicode character: letter, number, mark, punctuation, symbol or space.

digitChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse an ASCII digit, i.e between “0” and “9”.

octDigitChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse an octal digit, i.e. between “0” and “7”.

hexDigitChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a hexadecimal digit, i.e. between “0” and “9”, or “a” and “f”, or “A” and “F”.

markChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a Unicode mark character (accents and the like), which combines with preceding characters.

numberChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a Unicode numeric character, including digits from various scripts, Roman numerals, etc.

punctuationChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a Unicode punctuation character, including various kinds of connectors, brackets and quotes.

symbolChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a Unicode symbol characters, including mathematical and currency symbols.

separatorChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a Unicode space and separator characters.

asciiChar :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a character from the first 128 characters of the Unicode character set, corresponding to the ASCII character set.

latin1Char :: (MonadParsec e s m, Token s ~ Char) => m Char

Parse a character from the first 256 characters of the Unicode character set, corresponding to the ISO 8859-1 (Latin-1) character set.

charCategory :: (MonadParsec e s m, Token s ~ Char) => GeneralCategory -> m Char

charCategory cat parses character in Unicode General Category cat, see GeneralCategory.

char :: (MonadParsec e s m, Token s ~ Char) => Char -> m Char

char c parses a single character c.

semicolon = char ';'

char' :: (MonadParsec e s m, Token s ~ Char) => Char -> m Char

The same as char but case-insensitive. This parser returns the actually parsed character preserving its case.

>>> parseTest (char' 'e') "E"
'E'
>>> parseTest (char' 'e') "G"
1:1:
unexpected 'G'
expecting 'E' or 'e'

anyChar :: (MonadParsec e s m, Token s ~ Char) => m Char

This parser succeeds for any character. Returns the parsed character.

oneOf :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char

oneOf cs succeeds if the current character is in the supplied collection of characters cs. Returns the parsed character. Note that this parser cannot automatically generate the “expected” component of error message, so usually you should label it manually with label or (<?>).

See also: satisfy.

digit = oneOf ['0'..'9'] <?> "digit"

oneOf' :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char

The same as oneOf, but case-insensitive. Returns the parsed character preserving its case.

vowel = oneOf' "aeiou" <?> "vowel"

noneOf :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char

As the dual of oneOf, noneOf cs succeeds if the current character not in the supplied list of characters cs. Returns the parsed character.

noneOf' :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char

The same as noneOf, but case-insensitive.

consonant = noneOf' "aeiou" <?> "consonant"

satisfy :: (MonadParsec e s m, Token s ~ Char) => (Char -> Bool) -> m Char

The parser satisfy f succeeds for any character for which the supplied function f returns True. Returns the character that is actually parsed.

digitChar = satisfy isDigit <?> "digit"
oneOf cs  = satisfy (`elem` cs)

string :: (MonadParsec e s m, Token s ~ Char) => String -> m String

string s parses a sequence of characters given by s. Returns the parsed string (i.e. s).

divOrMod = string "div" <|> string "mod"

string' :: (MonadParsec e s m, Token s ~ Char) => String -> m String

The same as string, but case-insensitive. On success returns string cased as actually parsed input.

>>> parseTest (string' "foobar") "foObAr"
"foObAr"

Textual source position

data Pos

Positive integer that is used to represent line number, column number, and similar things like indentation level. Semigroup instance can be used to safely and purely add Poses together.

Since: 5.0.0

Instances

Eq Pos

Methods

(==) :: Pos -> Pos -> Bool

(/=) :: Pos -> Pos -> Bool

Data Pos

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> Pos -> c Pos

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c Pos

toConstr :: Pos -> Constr

dataTypeOf :: Pos -> DataType

dataCast1 :: Typeable (* -> *) t => (forall d. Data d => c (t d)) -> Maybe (c Pos)

dataCast2 :: Typeable (* -> * -> *) t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Pos)

gmapT :: (forall b. Data b => b -> b) -> Pos -> Pos

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Pos -> r

gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Pos -> r

gmapQ :: (forall d. Data d => d -> u) -> Pos -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> Pos -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> Pos -> m Pos

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> Pos -> m Pos

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> Pos -> m Pos

Ord Pos

Methods

compare :: Pos -> Pos -> Ordering

(<) :: Pos -> Pos -> Bool

(<=) :: Pos -> Pos -> Bool

(>) :: Pos -> Pos -> Bool

(>=) :: Pos -> Pos -> Bool

max :: Pos -> Pos -> Pos

min :: Pos -> Pos -> Pos

Read Pos

Methods

readsPrec :: Int -> ReadS Pos

readList :: ReadS [Pos]

readPrec :: ReadPrec Pos

readListPrec :: ReadPrec [Pos]

Show Pos

Methods

showsPrec :: Int -> Pos -> ShowS

show :: Pos -> String

showList :: [Pos] -> ShowS

Semigroup Pos

Methods

(<>) :: Pos -> Pos -> Pos

sconcat :: NonEmpty Pos -> Pos

stimes :: Integral b => b -> Pos -> Pos

Arbitrary Pos

Methods

arbitrary :: Gen Pos

shrink :: Pos -> [Pos]

NFData Pos

Methods

rnf :: Pos -> ()

mkPos :: (Integral a, MonadThrow m) => a -> m Pos

Construction of Pos from an instance of Integral. The function throws InvalidPosException when given non-positive argument. Note that the function is polymorphic with respect to MonadThrow m, so you can get result inside of Maybe, for example.

Since: 5.0.0

unPos :: Pos -> Word

Extract Word from Pos.

Since: 5.0.0

unsafePos :: Word -> Pos

Dangerous construction of Pos. Use when you know for sure that argument is positive.

Since: 5.0.0

data InvalidPosException

The exception is thrown by mkPos when its argument is not a positive number.

Since: 5.0.0

Constructors

InvalidPosException

Instances

Eq InvalidPosException

Methods

(==) :: InvalidPosException -> InvalidPosException -> Bool

(/=) :: InvalidPosException -> InvalidPosException -> Bool

Data InvalidPosException

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> InvalidPosException -> c InvalidPosException

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c InvalidPosException

toConstr :: InvalidPosException -> Constr

dataTypeOf :: InvalidPosException -> DataType

dataCast1 :: Typeable (* -> *) t => (forall d. Data d => c (t d)) -> Maybe (c InvalidPosException)

dataCast2 :: Typeable (* -> * -> *) t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c InvalidPosException)

gmapT :: (forall b. Data b => b -> b) -> InvalidPosException -> InvalidPosException

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> InvalidPosException -> r

gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> InvalidPosException -> r

gmapQ :: (forall d. Data d => d -> u) -> InvalidPosException -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> InvalidPosException -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> InvalidPosException -> m InvalidPosException

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> InvalidPosException -> m InvalidPosException

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> InvalidPosException -> m InvalidPosException

Show InvalidPosException

Methods

showsPrec :: Int -> InvalidPosException -> ShowS

show :: InvalidPosException -> String

showList :: [InvalidPosException] -> ShowS

Generic InvalidPosException

Associated Types

type Rep InvalidPosException :: * -> *

Methods

from :: InvalidPosException -> Rep InvalidPosException x

to :: Rep InvalidPosException x -> InvalidPosException

Exception InvalidPosException

Methods

toException :: InvalidPosException -> SomeException

fromException :: SomeException -> Maybe InvalidPosException

displayException :: InvalidPosException -> String

NFData InvalidPosException

Methods

rnf :: InvalidPosException -> ()

type Rep InvalidPosException

type Rep InvalidPosException = D1 (MetaData "InvalidPosException" "Text.Megaparsec.Pos" "megaparsec-5.3.1-4PNWjfGTZk1HgUWwVLM9zx" False) (C1 (MetaCons "InvalidPosException" PrefixI False) U1)

data SourcePos

The data type SourcePos represents source positions. It contains the name of the source file, a line number, and a column number. Source line and column positions change intensively during parsing, so we need to make them strict to avoid memory leaks.

Constructors

SourcePos

Fields

• sourceName :: FilePath

  Name of source file

• sourceLine :: !Pos

  Line number

• sourceColumn :: !Pos

  Column number

Instances

Eq SourcePos

Methods

(==) :: SourcePos -> SourcePos -> Bool

(/=) :: SourcePos -> SourcePos -> Bool

Data SourcePos

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> SourcePos -> c SourcePos

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c SourcePos

toConstr :: SourcePos -> Constr

dataTypeOf :: SourcePos -> DataType

dataCast1 :: Typeable (* -> *) t => (forall d. Data d => c (t d)) -> Maybe (c SourcePos)

dataCast2 :: Typeable (* -> * -> *) t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c SourcePos)

gmapT :: (forall b. Data b => b -> b) -> SourcePos -> SourcePos

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> SourcePos -> r

gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> SourcePos -> r

gmapQ :: (forall d. Data d => d -> u) -> SourcePos -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> SourcePos -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> SourcePos -> m SourcePos

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> SourcePos -> m SourcePos

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> SourcePos -> m SourcePos

Ord SourcePos

Methods

compare :: SourcePos -> SourcePos -> Ordering

(<) :: SourcePos -> SourcePos -> Bool

(<=) :: SourcePos -> SourcePos -> Bool

(>) :: SourcePos -> SourcePos -> Bool

(>=) :: SourcePos -> SourcePos -> Bool

max :: SourcePos -> SourcePos -> SourcePos

min :: SourcePos -> SourcePos -> SourcePos

Read SourcePos

Methods

readsPrec :: Int -> ReadS SourcePos

readList :: ReadS [SourcePos]

readPrec :: ReadPrec SourcePos

readListPrec :: ReadPrec [SourcePos]

Show SourcePos

Methods

showsPrec :: Int -> SourcePos -> ShowS

show :: SourcePos -> String

showList :: [SourcePos] -> ShowS

Generic SourcePos

Associated Types

type Rep SourcePos :: * -> *

Methods

from :: SourcePos -> Rep SourcePos x

to :: Rep SourcePos x -> SourcePos

Arbitrary SourcePos

Methods

arbitrary :: Gen SourcePos

shrink :: SourcePos -> [SourcePos]

NFData SourcePos

Methods

rnf :: SourcePos -> ()

type Rep SourcePos

type Rep SourcePos = D1 (MetaData "SourcePos" "Text.Megaparsec.Pos" "megaparsec-5.3.1-4PNWjfGTZk1HgUWwVLM9zx" False) (C1 (MetaCons "SourcePos" PrefixI True) ((:*:) (S1 (MetaSel (Just Symbol "sourceName") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 FilePath)) ((:*:) (S1 (MetaSel (Just Symbol "sourceLine") NoSourceUnpackedness SourceStrict DecidedUnpack) (Rec0 Pos)) (S1 (MetaSel (Just Symbol "sourceColumn") NoSourceUnpackedness SourceStrict DecidedUnpack) (Rec0 Pos)))))

initialPos :: String -> SourcePos

Construct initial position (line 1, column 1) given name of source file.

sourcePosPretty :: SourcePos -> String

Pretty-print a SourcePos.

Since: 5.0.0

Error messages

data ErrorItem t

Data type that is used to represent “unexpected/expected” items in ParseError. The data type is parametrized over the token type t.

Since: 5.0.0

Constructors

Tokens (NonEmpty t)

Non-empty stream of tokens

Label (NonEmpty Char)

Label (cannot be empty)

EndOfInput

End of input

Instances

Eq t => Eq (ErrorItem t)

Methods

(==) :: ErrorItem t -> ErrorItem t -> Bool

(/=) :: ErrorItem t -> ErrorItem t -> Bool

Data t => Data (ErrorItem t)

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> ErrorItem t -> c (ErrorItem t)

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c (ErrorItem t)

toConstr :: ErrorItem t -> Constr

dataTypeOf :: ErrorItem t -> DataType

dataCast1 :: Typeable (* -> *) t => (forall d. Data d => c (t d)) -> Maybe (c (ErrorItem t))

dataCast2 :: Typeable (* -> * -> *) t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c (ErrorItem t))

gmapT :: (forall b. Data b => b -> b) -> ErrorItem t -> ErrorItem t

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> ErrorItem t -> r

gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> ErrorItem t -> r

gmapQ :: (forall d. Data d => d -> u) -> ErrorItem t -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> ErrorItem t -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> ErrorItem t -> m (ErrorItem t)

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> ErrorItem t -> m (ErrorItem t)

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> ErrorItem t -> m (ErrorItem t)

Ord t => Ord (ErrorItem t)

Methods

compare :: ErrorItem t -> ErrorItem t -> Ordering

(<) :: ErrorItem t -> ErrorItem t -> Bool

(<=) :: ErrorItem t -> ErrorItem t -> Bool

(>) :: ErrorItem t -> ErrorItem t -> Bool

(>=) :: ErrorItem t -> ErrorItem t -> Bool

max :: ErrorItem t -> ErrorItem t -> ErrorItem t

min :: ErrorItem t -> ErrorItem t -> ErrorItem t

Read t => Read (ErrorItem t)

Methods

readsPrec :: Int -> ReadS (ErrorItem t)

readList :: ReadS [ErrorItem t]

readPrec :: ReadPrec (ErrorItem t)

readListPrec :: ReadPrec [ErrorItem t]

Show t => Show (ErrorItem t)

Methods

showsPrec :: Int -> ErrorItem t -> ShowS

show :: ErrorItem t -> String

showList :: [ErrorItem t] -> ShowS

Generic (ErrorItem t)

Associated Types

type Rep (ErrorItem t) :: * -> *

Methods

from :: ErrorItem t -> Rep (ErrorItem t) x

to :: Rep (ErrorItem t) x -> ErrorItem t

Arbitrary t => Arbitrary (ErrorItem t)

Methods

arbitrary :: Gen (ErrorItem t)

shrink :: ErrorItem t -> [ErrorItem t]

NFData t => NFData (ErrorItem t)

Methods

rnf :: ErrorItem t -> ()

(Ord t, ShowToken t) => ShowErrorComponent (ErrorItem t)

Methods

showErrorComponent :: ErrorItem t -> String

type Rep (ErrorItem t)

type Rep (ErrorItem t) = D1 (MetaData "ErrorItem" "Text.Megaparsec.Error" "megaparsec-5.3.1-4PNWjfGTZk1HgUWwVLM9zx" False) ((:+:) (C1 (MetaCons "Tokens" PrefixI False) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 (NonEmpty t)))) ((:+:) (C1 (MetaCons "Label" PrefixI False) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 (NonEmpty Char)))) (C1 (MetaCons "EndOfInput" PrefixI False) U1)))

class Ord e => ErrorComponent e where

The type class defines how to represent information about various exceptional situations. Data types that are used as custom data component in ParseError must be instances of this type class.

Since: 5.0.0

Minimal complete definition

representFail, representIndentation

Methods

representFail :: String -> e

Represent the message passed to fail in parser monad.

Since: 5.0.0

representIndentation :: Ordering -> Pos -> Pos -> e

Represent information about incorrect indentation.

Since: 5.0.0

Instances

ErrorComponent ()

Methods

representFail :: String -> ()

representIndentation :: Ordering -> Pos -> Pos -> ()

ErrorComponent Dec

Methods

representFail :: String -> Dec

representIndentation :: Ordering -> Pos -> Pos -> Dec

data Dec

“Default error component”. This is our instance of ErrorComponent provided out-of-box.

Since: 5.0.0

Constructors

DecFail String

fail has been used in parser monad

DecIndentation Ordering Pos Pos

Incorrect indentation error: desired ordering between reference level and actual level, reference indentation level, actual indentation level

Instances

Eq Dec

Methods

(==) :: Dec -> Dec -> Bool

(/=) :: Dec -> Dec -> Bool

Data Dec

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> Dec -> c Dec

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c Dec

toConstr :: Dec -> Constr

dataTypeOf :: Dec -> DataType

dataCast1 :: Typeable (* -> *) t => (forall d. Data d => c (t d)) -> Maybe (c Dec)

dataCast2 :: Typeable (* -> * -> *) t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Dec)

gmapT :: (forall b. Data b => b -> b) -> Dec -> Dec

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Dec -> r

gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Dec -> r

gmapQ :: (forall d. Data d => d -> u) -> Dec -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> Dec -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> Dec -> m Dec

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> Dec -> m Dec

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> Dec -> m Dec

Ord Dec

Methods

compare :: Dec -> Dec -> Ordering

(<) :: Dec -> Dec -> Bool

(<=) :: Dec -> Dec -> Bool

(>) :: Dec -> Dec -> Bool

(>=) :: Dec -> Dec -> Bool

max :: Dec -> Dec -> Dec

min :: Dec -> Dec -> Dec

Read Dec

Methods

readsPrec :: Int -> ReadS Dec

readList :: ReadS [Dec]

readPrec :: ReadPrec Dec

readListPrec :: ReadPrec [Dec]

Show Dec

Methods

showsPrec :: Int -> Dec -> ShowS

show :: Dec -> String

showList :: [Dec] -> ShowS

Arbitrary Dec

Methods

arbitrary :: Gen Dec

shrink :: Dec -> [Dec]

NFData Dec

Methods

rnf :: Dec -> ()

ShowErrorComponent Dec

Methods

showErrorComponent :: Dec -> String

ErrorComponent Dec

Methods

representFail :: String -> Dec

representIndentation :: Ordering -> Pos -> Pos -> Dec

data ParseError t e

ParseError represents… parse errors. It provides the stack of source positions, a set of expected and unexpected tokens as well as a set of custom associated data. The data type is parametrized over the token type t and the custom data e.

Note that the stack of source positions contains current position as its head, and the rest of positions allows to track full sequence of include files with topmost source file at the end of the list.

Semigroup (and Monoid) instance of the data type allows to merge parse errors from different branches of parsing. When merging two ParseErrors, the longest match is preferred; if positions are the same, custom data sets and collections of message items are combined.

Constructors

ParseError

Fields

• errorPos :: NonEmpty SourcePos

  Stack of source positions

• errorUnexpected :: Set (ErrorItem t)

  Unexpected items

• errorExpected :: Set (ErrorItem t)

  Expected items

• errorCustom :: Set e

  Associated data, if any

Instances

(Eq e, Eq t) => Eq (ParseError t e)

Methods

(==) :: ParseError t e -> ParseError t e -> Bool

(/=) :: ParseError t e -> ParseError t e -> Bool

(Ord e, Ord t, Data e, Data t) => Data (ParseError t e)

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> ParseError t e -> c (ParseError t e)

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c (ParseError t e)

toConstr :: ParseError t e -> Constr

dataTypeOf :: ParseError t e -> DataType

dataCast1 :: Typeable (* -> *) t => (forall d. Data d => c (t d)) -> Maybe (c (ParseError t e))

dataCast2 :: Typeable (* -> * -> *) t => (forall d a. (Data d, Data a) => c (t d a)) -> Maybe (c (ParseError t e))

gmapT :: (forall b. Data b => b -> b) -> ParseError t e -> ParseError t e

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> ParseError t e -> r

gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> ParseError t e -> r

gmapQ :: (forall d. Data d => d -> u) -> ParseError t e -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> ParseError t e -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> ParseError t e -> m (ParseError t e)

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> ParseError t e -> m (ParseError t e)

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> ParseError t e -> m (ParseError t e)

(Ord e, Ord t, Read e, Read t) => Read (ParseError t e)

Methods

readsPrec :: Int -> ReadS (ParseError t e)

readList :: ReadS [ParseError t e]

readPrec :: ReadPrec (ParseError t e)

readListPrec :: ReadPrec [ParseError t e]

(Show e, Show t) => Show (ParseError t e)

Methods

showsPrec :: Int -> ParseError t e -> ShowS

show :: ParseError t e -> String

showList :: [ParseError t e] -> ShowS

Generic (ParseError t e)

Associated Types

type Rep (ParseError t e) :: * -> *

Methods

from :: ParseError t e -> Rep (ParseError t e) x

to :: Rep (ParseError t e) x -> ParseError t e

(Ord t, Ord e) => Semigroup (ParseError t e)

Methods

(<>) :: ParseError t e -> ParseError t e -> ParseError t e

sconcat :: NonEmpty (ParseError t e) -> ParseError t e

stimes :: Integral b => b -> ParseError t e -> ParseError t e

(Ord t, Ord e) => Monoid (ParseError t e)

Methods

mempty :: ParseError t e

mappend :: ParseError t e -> ParseError t e -> ParseError t e

mconcat :: [ParseError t e] -> ParseError t e

(Arbitrary t, Ord t, Arbitrary e, Ord e) => Arbitrary (ParseError t e)

Methods

arbitrary :: Gen (ParseError t e)

shrink :: ParseError t e -> [ParseError t e]

(Show t, Typeable * t, Ord t, ShowToken t, Show e, Typeable * e, ShowErrorComponent e) => Exception (ParseError t e)

Methods

toException :: ParseError t e -> SomeException

fromException :: SomeException -> Maybe (ParseError t e)

displayException :: ParseError t e -> String

(NFData t, NFData e) => NFData (ParseError t e)

Methods

rnf :: ParseError t e -> ()

type Rep (ParseError t e)

type Rep (ParseError t e) = D1 (MetaData "ParseError" "Text.Megaparsec.Error" "megaparsec-5.3.1-4PNWjfGTZk1HgUWwVLM9zx" False) (C1 (MetaCons "ParseError" PrefixI True) ((:*:) ((:*:) (S1 (MetaSel (Just Symbol "errorPos") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 (NonEmpty SourcePos))) (S1 (MetaSel (Just Symbol "errorUnexpected") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 (Set (ErrorItem t))))) ((:*:) (S1 (MetaSel (Just Symbol "errorExpected") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 (Set (ErrorItem t)))) (S1 (MetaSel (Just Symbol "errorCustom") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 (Set e))))))

class ShowToken a where

Type class ShowToken includes methods that allow to pretty-print single token as well as stream of tokens. This is used for rendering of error messages.

Minimal complete definition

showTokens

Methods

showTokens :: NonEmpty a -> String

Pretty-print non-empty stream of tokens. This function is also used to print single tokens (represented as singleton lists).

Since: 5.0.0

Instances

ShowToken Char

Methods

showTokens :: NonEmpty Char -> String

class Ord a => ShowErrorComponent a where

The type class defines how to print custom data component of ParseError.

Since: 5.0.0

Minimal complete definition

showErrorComponent

Methods

showErrorComponent :: a -> String

Pretty-print custom data component of ParseError.

Instances

ShowErrorComponent Dec

Methods

showErrorComponent :: Dec -> String

(Ord t, ShowToken t) => ShowErrorComponent (ErrorItem t)

Methods

showErrorComponent :: ErrorItem t -> String

parseErrorPretty

Arguments

:: (Ord t, ShowToken t, ShowErrorComponent e)

=> ParseError t e

Parse error to render

-> String

Result of rendering

Pretty-print a ParseError. The rendered String always ends with a newline.

The function is defined as:

parseErrorPretty e =
  sourcePosStackPretty (errorPos e) ++ ":\n" ++ parseErrorTextPretty e

Since: 5.0.0

Debugging

dbg

Arguments

:: (Stream s, ShowToken (Token s), ShowErrorComponent e, Show a)

=> String

Debugging label

-> ParsecT e s m a

Parser to debug

-> ParsecT e s m a

Parser that prints debugging messages

dbg label p parser works exactly like p, but when it's evaluated it also prints information useful for debugging. The label is only used to refer to this parser in the debugging output. This combinator uses the trace function from Debug.Trace under the hood.

Typical usage is to wrap every sub-parser in misbehaving parser with dbg assigning meaningful labels. Then give it a shot and go through the print-out. As of current version, this combinator prints all available information except for hints, which are probably only interesting to the maintainer of Megaparsec itself and may be quite verbose to output in general. Let me know if you would like to be able to see hints in the debugging output.

The output itself is pretty self-explanatory, although the following abbreviations should be clarified (they are derived from the low-level source code):

• COK—“consumed OK”. The parser consumed input and succeeded.
• CERR—“consumed error”. The parser consumed input and failed.
• EOK—“empty OK”. The parser succeeded without consuming input.
• EERR—“empty error”. The parser failed without consuming input.

Finally, it's not possible to lift this function into some monad transformers without introducing surprising behavior (e.g. unexpected state backtracking) or adding otherwise redundant constraints (e.g. Show instance for state), so this helper is only available for ParsecT monad, not MonadParsec in general.

Since: 5.1.0

Low-level operations

class Ord (Token s) => Stream s where

An instance of Stream s has stream type s. Token type is determined by the stream and can be found via Token type function.

Minimal complete definition

uncons, updatePos

Associated Types

type Token s :: *

Type of token in stream.

Since: 5.0.0

Methods

uncons :: s -> Maybe (Token s, s)

Get next token from the stream. If the stream is empty, return Nothing.

updatePos :: Proxy s -> Pos -> SourcePos -> Token s -> (SourcePos, SourcePos)

Update position in stream given tab width, current position, and current token. The result is a tuple where the first element will be used to report parse errors for current token, while the second element is the incremented position that will be stored in the parser's state. The stored (incremented) position is used whenever position can't be/shouldn't be updated by consuming a token. For example, when using failure, we don't grab a new token (we need to fail right were we are now), so error position will be taken from parser's state.

When you work with streams where elements do not contain information about their position in input, the result is usually consists of the third argument unchanged and incremented position calculated with respect to current token. This is how default instances of Stream work (they use defaultUpdatePos, which may be a good starting point for your own position-advancing function).

When you wish to deal with a stream of tokens where every token “knows” its start and end position in input (for example, you have produced the stream with Happy/Alex), then the best strategy is to use the start position as the actual element position and provide the end position of the token as the incremented one.

Since: 5.0.0

Instances

Stream String

Associated Types

type Token String :: *

Methods

uncons :: String -> Maybe (Token String, String)

updatePos :: Proxy * String -> Pos -> SourcePos -> Token String -> (SourcePos, SourcePos)

Stream ByteString

Associated Types

type Token ByteString :: *

Methods

uncons :: ByteString -> Maybe (Token ByteString, ByteString)

updatePos :: Proxy * ByteString -> Pos -> SourcePos -> Token ByteString -> (SourcePos, SourcePos)

Stream ByteString

Associated Types

type Token ByteString :: *

Methods

uncons :: ByteString -> Maybe (Token ByteString, ByteString)

updatePos :: Proxy * ByteString -> Pos -> SourcePos -> Token ByteString -> (SourcePos, SourcePos)

Stream Text

Associated Types

type Token Text :: *

Methods

uncons :: Text -> Maybe (Token Text, Text)

updatePos :: Proxy * Text -> Pos -> SourcePos -> Token Text -> (SourcePos, SourcePos)

Stream Text

Associated Types

type Token Text :: *

Methods

uncons :: Text -> Maybe (Token Text, Text)

updatePos :: Proxy * Text -> Pos -> SourcePos -> Token Text -> (SourcePos, SourcePos)

data State s

This is the Megaparsec's state, it's parametrized over stream type s.

Constructors

State

Fields

• stateInput :: s

  Current input (already processed input is removed from the stream)

• statePos :: NonEmpty SourcePos

  Current position (column + line number) with support for include files

• stateTokensProcessed :: !Word

  Number of processed tokens so far

  Since: 5.2.0

• stateTabWidth :: Pos

  Tab width to use

Instances

Eq s => Eq (State s)

Methods

(==) :: State s -> State s -> Bool

(/=) :: State s -> State s -> Bool

Data s => Data (State s)

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> State s -> c (State s)

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c (State s)

toConstr :: State s -> Constr

dataTypeOf :: State s -> DataType

dataCast1 :: Typeable (* -> *) t => (forall d. Data d => c (t d)) -> Maybe (c (State s))

dataCast2 :: Typeable (* -> * -> *) t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c (State s))

gmapT :: (forall b. Data b => b -> b) -> State s -> State s

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> State s -> r

gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> State s -> r

gmapQ :: (forall d. Data d => d -> u) -> State s -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> State s -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> State s -> m (State s)

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> State s -> m (State s)

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> State s -> m (State s)

Show s => Show (State s)

Methods

showsPrec :: Int -> State s -> ShowS

show :: State s -> String

showList :: [State s] -> ShowS

Generic (State s)

Associated Types

type Rep (State s) :: * -> *

Methods

from :: State s -> Rep (State s) x

to :: Rep (State s) x -> State s

Arbitrary a => Arbitrary (State a)

Methods

arbitrary :: Gen (State a)

shrink :: State a -> [State a]

NFData s => NFData (State s)

Methods

rnf :: State s -> ()

type Rep (State s)

type Rep (State s) = D1 (MetaData "State" "Text.Megaparsec.Prim" "megaparsec-5.3.1-4PNWjfGTZk1HgUWwVLM9zx" False) (C1 (MetaCons "State" PrefixI True) ((:*:) ((:*:) (S1 (MetaSel (Just Symbol "stateInput") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 s)) (S1 (MetaSel (Just Symbol "statePos") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 (NonEmpty SourcePos)))) ((:*:) (S1 (MetaSel (Just Symbol "stateTokensProcessed") SourceUnpack SourceStrict DecidedUnpack) (Rec0 Word)) (S1 (MetaSel (Just Symbol "stateTabWidth") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 Pos)))))

getInput :: MonadParsec e s m => m s

Return the current input.

setInput :: MonadParsec e s m => s -> m ()

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

getPosition :: MonadParsec e s m => m SourcePos

Return the current source position.

See also: setPosition, pushPosition, popPosition, and SourcePos.

getNextTokenPosition :: forall e s m. MonadParsec e s m => m (Maybe SourcePos)

Get the position where the next token in the stream begins. If the stream is empty, return Nothing.

Since: 5.3.0

setPosition :: MonadParsec e s m => SourcePos -> m ()

setPosition pos sets the current source position to pos.

See also: getPosition, pushPosition, popPosition, and SourcePos.

pushPosition :: MonadParsec e s m => SourcePos -> m ()

Push a position into stack of positions and continue parsing working with this position. Useful for working with include files and the like.

See also: getPosition, setPosition, popPosition, and SourcePos.

Since: 5.0.0

popPosition :: MonadParsec e s m => m ()

Pop a position from the stack of positions unless it only contains one element (in that case the stack of positions remains the same). This is how to return to previous source file after pushPosition.

See also: getPosition, setPosition, pushPosition, and SourcePos.

Since: 5.0.0

getTokensProcessed :: MonadParsec e s m => m Word

Get the number of tokens processed so far.

Since: 5.2.0

setTokensProcessed :: MonadParsec e s m => Word -> m ()

Set the number of tokens processed so far.

Since: 5.2.0

getTabWidth :: MonadParsec e s m => m Pos

Return the tab width. The default tab width is equal to defaultTabWidth. You can set a different tab width with the help of setTabWidth.

setTabWidth :: MonadParsec e s m => Pos -> m ()

Set tab width. If the argument of the function is not a positive number, defaultTabWidth will be used.

getParserState :: MonadParsec e s m => m (State s)

Return the full parser state as a State record.

setParserState :: MonadParsec e s m => State s -> m ()

setParserState st sets the parser state to st.

updateParserState :: MonadParsec e s m => (State s -> State s) -> m ()

updateParserState f applies the function f to the parser state.