Text.Pandoc.Parsing

A utility library with parsers used in pandoc readers.

Documentation

take1WhileP :: Monad m => (Char -> Bool) -> ParserT Text st m Text

Parse characters while a predicate is true.

takeP :: Monad m => Int -> ParserT Text st m Text

countChar :: (Stream s m Char, Monad m) => Int -> ParsecT s st m Char -> ParsecT s st m Text

Like count, but packs its result

textStr :: Stream s m Char => Text -> ParsecT s u m Text

Like string, but uses Text.

anyLine :: Monad m => ParserT Text st m Text

Parse any line of text

anyLineNewline :: Monad m => ParserT Text st m Text

Parse any line, include the final newline in the output

indentWith :: Stream s m Char => HasReaderOptions st => Int -> ParserT s st m Text

Parse indent by specified number of spaces (or equiv. tabs)

manyChar :: Stream s m t => ParserT s st m Char -> ParserT s st m Text

Like many, but packs its result.

many1Char :: Stream s m t => ParserT s st m Char -> ParserT s st m Text

Like many1, but packs its result.

manyTillChar :: Stream s m t => ParserT s st m Char -> ParserT s st m a -> ParserT s st m Text

Like manyTill, but packs its result.

many1TillChar :: (Show end, Stream s m t) => ParserT s st m Char -> ParserT s st m end -> ParserT s st m Text

Like many1Till, but packs its result

many1Till :: (Show end, Stream s m t) => ParserT s st m a -> ParserT s st m end -> ParserT s st m [a]

Like manyTill, but reads at least one item.

manyUntil :: ParserT s u m a -> ParserT s u m b -> ParserT s u m ([a], b)

Like manyTill, but also returns the result of end parser.

manyUntilChar :: ParserT s u m Char -> ParserT s u m b -> ParserT s u m (Text, b)

Like manyUntil, but also packs its result.

sepBy1' :: ParsecT s u m a -> ParsecT s u m sep -> ParsecT s u m [a]

Like sepBy1 from Parsec, but does not fail if it sep succeeds and p fails.

notFollowedBy' :: (Show b, Stream s m a) => ParserT s st m b -> ParserT s st m ()

A more general form of notFollowedBy. This one allows any type of parser to be specified, and succeeds only if that parser fails. It does not consume any input.

oneOfStrings :: Stream s m Char => [Text] -> ParserT s st m Text

Parses one of a list of strings. If the list contains two strings one of which is a prefix of the other, the longer string will be matched if possible.

oneOfStringsCI :: Stream s m Char => [Text] -> ParserT s st m Text

Parses one of a list of strings (tried in order), case insensitive.

spaceChar :: Stream s m Char => ParserT s st m Char

Parses a space or tab.

nonspaceChar :: Stream s m Char => ParserT s st m Char

Parses a nonspace, nonnewline character.

skipSpaces :: Stream s m Char => ParserT s st m ()

Skips zero or more spaces or tabs.

blankline :: Stream s m Char => ParserT s st m Char

Skips zero or more spaces or tabs, then reads a newline.

blanklines :: Stream s m Char => ParserT s st m Text

Parses one or more blank lines and returns a string of newlines.

gobbleSpaces :: (HasReaderOptions st, Monad m) => Int -> ParserT Text st m ()

Gobble n spaces; if tabs are encountered, expand them and gobble some or all of their spaces, leaving the rest.

gobbleAtMostSpaces :: (HasReaderOptions st, Monad m) => Int -> ParserT Text st m Int

Gobble up to n spaces; if tabs are encountered, expand them and gobble some or all of their spaces, leaving the rest.

enclosed

Arguments

:: (Show end, Stream s m Char)

=> ParserT s st m t

start parser

-> ParserT s st m end

end parser

-> ParserT s st m a

content parser (to be used repeatedly)

-> ParserT s st m [a]

Parses material enclosed between start and end parsers.

stringAnyCase :: Stream s m Char => Text -> ParserT s st m Text

Parse string, case insensitive.

parseFromString :: (Stream s m Char, IsString s) => ParserT s st m r -> Text -> ParserT s st m r

Parse contents of str using parser and return result.

parseFromString' :: (Stream s m Char, IsString s, HasLastStrPosition u) => ParserT s u m a -> Text -> ParserT s u m a

Like parseFromString but specialized for ParserState. This resets stateLastStrPos, which is almost always what we want.

lineClump :: Monad m => ParserT Text st m Text

Parse raw line block up to and including blank lines.

charsInBalanced :: Stream s m Char => Char -> Char -> ParserT s st m Char -> ParserT s st m Text

Parse a string of characters between an open character and a close character, including text between balanced pairs of open and close, which must be different. For example, charsInBalanced '(' ')' anyChar will parse "(hello (there))" and return "hello (there)".

romanNumeral

Arguments

:: Stream s m Char

=> Bool

Uppercase if true

-> ParserT s st m Int

Parses a roman numeral (uppercase or lowercase), returns number.

emailAddress :: Stream s m Char => ParserT s st m (Text, Text)

Parses an email address; returns original and corresponding escaped mailto: URI.

uri :: Stream s m Char => ParserT s st m (Text, Text)

Parses a URI. Returns pair of original and URI-escaped version.

mathInline :: (HasReaderOptions st, Stream s m Char) => ParserT s st m Text

mathDisplay :: (HasReaderOptions st, Stream s m Char) => ParserT s st m Text

withHorizDisplacement

Arguments

:: Stream s m Char

=> ParserT s st m a

Parser to apply

-> ParserT s st m (a, Int)

(result, displacement)

Applies a parser, returns tuple of its results and its horizontal displacement (the difference between the source column at the end and the source column at the beginning). Vertical displacement (source row) is ignored.

withRaw :: Monad m => ParsecT Text st m a -> ParsecT Text st m (a, Text)

Applies a parser and returns the raw string that was parsed, along with the value produced by the parser.

escaped

Arguments

:: Stream s m Char

=> ParserT s st m Char

Parser for character to escape

-> ParserT s st m Char

Parses backslash, then applies character parser.

characterReference :: Stream s m Char => ParserT s st m Char

Parse character entity.

upperRoman :: Stream s m Char => ParserT s st m (ListNumberStyle, Int)

Parses an uppercase roman numeral and returns (UpperRoman, number).

lowerRoman :: Stream s m Char => ParserT s st m (ListNumberStyle, Int)

Parses a lowercase roman numeral and returns (LowerRoman, number).

decimal :: Stream s m Char => ParserT s st m (ListNumberStyle, Int)

Parses a decimal numeral and returns (Decimal, number).

lowerAlpha :: Stream s m Char => ParserT s st m (ListNumberStyle, Int)

Parses a lowercase letter and returns (LowerAlpha, number).

upperAlpha :: Stream s m Char => ParserT s st m (ListNumberStyle, Int)

Parses an uppercase letter and returns (UpperAlpha, number).

anyOrderedListMarker :: Stream s m Char => ParserT s ParserState m ListAttributes

Parses an ordered list marker and returns list attributes.

orderedListMarker :: Stream s m Char => ListNumberStyle -> ListNumberDelim -> ParserT s ParserState m Int

Parses an ordered list marker with a given style and delimiter, returns number.

charRef :: Stream s m Char => ParserT s st m Inline

Parses a character reference and returns a Str element.

lineBlockLines :: Monad m => ParserT Text st m [Text]

Parses an RST-style line block and returns a list of strings.

tableWith :: (Stream s m Char, HasReaderOptions st, Monad mf) => ParserT s st m (mf [Blocks], [Alignment], [Int]) -> ([Int] -> ParserT s st m (mf [Blocks])) -> ParserT s st m sep -> ParserT s st m end -> ParserT s st m (mf Blocks)

Parse a table using headerParser, rowParser, lineParser, and footerParser.

widthsFromIndices :: Int -> [Int] -> [Double]

gridTableWith

Arguments

:: (Stream s m Char, HasReaderOptions st, HasLastStrPosition st, Monad mf, IsString s)

=> ParserT s st m (mf Blocks)

Block list parser

-> Bool

Headerless table

-> ParserT s st m (mf Blocks)

gridTableWith'

Arguments

:: (Stream s m Char, HasReaderOptions st, HasLastStrPosition st, Monad mf, IsString s)

=> ParserT s st m (mf Blocks)

Block list parser

-> Bool

Headerless table

-> ParserT s st m (TableComponents mf)

readWith :: Parser Text st a -> st -> Text -> Either PandocError a

Parse a string with a given parser and state

readWithM

Arguments

:: (Stream s m Char, ToText s)

=> ParserT s st m a

parser

-> st

initial state

-> s

input

-> m (Either PandocError a)

Removes the ParsecT layer from the monad transformer stack

testStringWith :: Show a => ParserT Text ParserState Identity a -> Text -> IO ()

Parse a string with parser (for testing).

guardEnabled :: (Stream s m a, HasReaderOptions st) => Extension -> ParserT s st m ()

Succeed only if the extension is enabled.

guardDisabled :: (Stream s m a, HasReaderOptions st) => Extension -> ParserT s st m ()

Succeed only if the extension is disabled.

updateLastStrPos :: (Stream s m a, HasLastStrPosition st) => ParserT s st m ()

Update the position on which the last string ended.

notAfterString :: (Stream s m a, HasLastStrPosition st) => ParserT s st m Bool

Whether we are right after the end of a string.

logMessage :: (Stream s m a, HasLogMessages st) => LogMessage -> ParserT s st m ()

Add a log message.

reportLogMessages :: (PandocMonad m, HasLogMessages st) => ParserT s st m ()

Report all the accumulated log messages, according to verbosity level.

data ParserState

Parsing options.

Constructors

ParserState

Fields

• stateOptions :: ReaderOptions

  User options

• stateParserContext :: ParserContext

  Inside list?

• stateQuoteContext :: QuoteContext

  Inside quoted environment?

• stateAllowLinks :: Bool

  Allow parsing of links

• stateAllowLineBreaks :: Bool

  Allow parsing of line breaks

• stateMaxNestingLevel :: Int

  Max # of nested Strong/Emph

• stateLastStrPos :: Maybe SourcePos

  Position after last str parsed

• stateKeys :: KeyTable

  List of reference keys

• stateHeaderKeys :: KeyTable

  List of implicit header ref keys

• stateSubstitutions :: SubstTable

  List of substitution references

• stateNotes :: NoteTable

  List of notes (raw bodies)

• stateNotes' :: NoteTable'

  List of notes (parsed bodies)

• stateNoteRefs :: Set Text

  List of note references used

• stateInNote :: Bool

  True if parsing note contents

• stateNoteNumber :: Int

  Last note number for citations

• stateMeta :: Meta

  Document metadata

• stateMeta' :: F Meta

  Document metadata

• stateCitations :: Map Text Text

  RST-style citations

• stateHeaderTable :: [HeaderType]

  Ordered list of header types used

• stateIdentifiers :: Set Text

  Header identifiers used

• stateNextExample :: Int

  Number of next example

• stateExamples :: Map Text Int

  Map from example labels to numbers

• stateMacros :: Map Text Macro

  Table of macros defined so far

• stateRstDefaultRole :: Text

  Current rST default interpreted text role

• stateRstHighlight :: Maybe Text

  Current rST literal block language

• stateRstCustomRoles :: Map Text (Text, Maybe Text, Attr)

  Current rST custom text roles Triple represents: 1) Base role, 2) Optional format (only for :raw: roles), 3) Additional classes (rest of Attr is unused)).

• stateCaption :: Maybe Inlines

  Caption in current environment

• stateInHtmlBlock :: Maybe Text

  Tag type of HTML block being parsed

• stateFencedDivLevel :: Int

  Depth of fenced div

• stateContainers :: [Text]

  parent include files

• stateLogMessages :: [LogMessage]

  log messages

• stateMarkdownAttribute :: Bool

  True if in markdown=1 context

Instances

Default ParserState

Defined in Text.Pandoc.Parsing

Methods

def :: ParserState

HasMeta ParserState

Defined in Text.Pandoc.Parsing

Methods

setMeta :: ToMetaValue b => Text -> b -> ParserState -> ParserState

deleteMeta :: Text -> ParserState -> ParserState

HasIncludeFiles ParserState

Defined in Text.Pandoc.Parsing

Methods

getIncludeFiles :: ParserState -> [Text]

addIncludeFile :: Text -> ParserState -> ParserState

dropLatestIncludeFile :: ParserState -> ParserState

HasLogMessages ParserState

Defined in Text.Pandoc.Parsing

Methods

addLogMessage :: LogMessage -> ParserState -> ParserState

getLogMessages :: ParserState -> [LogMessage]

HasLastStrPosition ParserState

Defined in Text.Pandoc.Parsing

Methods

setLastStrPos :: Maybe SourcePos -> ParserState -> ParserState

getLastStrPos :: ParserState -> Maybe SourcePos

HasMacros ParserState

Defined in Text.Pandoc.Parsing

Methods

extractMacros :: ParserState -> Map Text Macro

updateMacros :: (Map Text Macro -> Map Text Macro) -> ParserState -> ParserState

HasIdentifierList ParserState

Defined in Text.Pandoc.Parsing

Methods

extractIdentifierList :: ParserState -> Set Text

updateIdentifierList :: (Set Text -> Set Text) -> ParserState -> ParserState

HasReaderOptions ParserState

Defined in Text.Pandoc.Parsing

Methods

extractReaderOptions :: ParserState -> ReaderOptions

getOption :: forall s (m :: Type -> Type) t b. Stream s m t => (ReaderOptions -> b) -> ParserT s ParserState m b

Monad m => HasQuoteContext ParserState m

Defined in Text.Pandoc.Parsing

Methods

getQuoteContext :: Stream s m t => ParsecT s ParserState m QuoteContext

withQuoteContext :: QuoteContext -> ParsecT s ParserState m a -> ParsecT s ParserState m a

class HasReaderOptions st where

Minimal complete definition

extractReaderOptions

Methods

extractReaderOptions :: st -> ReaderOptions

getOption :: Stream s m t => (ReaderOptions -> b) -> ParserT s st m b

Instances

HasReaderOptions ParserState

Defined in Text.Pandoc.Parsing

Methods

extractReaderOptions :: ParserState -> ReaderOptions

getOption :: forall s (m :: Type -> Type) t b. Stream s m t => (ReaderOptions -> b) -> ParserT s ParserState m b

class HasIdentifierList st where

Methods

extractIdentifierList :: st -> Set Text

updateIdentifierList :: (Set Text -> Set Text) -> st -> st

Instances

HasIdentifierList ParserState

Defined in Text.Pandoc.Parsing

Methods

extractIdentifierList :: ParserState -> Set Text

updateIdentifierList :: (Set Text -> Set Text) -> ParserState -> ParserState

class HasMacros st where

Methods

extractMacros :: st -> Map Text Macro

updateMacros :: (Map Text Macro -> Map Text Macro) -> st -> st

Instances

HasMacros ParserState

Defined in Text.Pandoc.Parsing

Methods

extractMacros :: ParserState -> Map Text Macro

updateMacros :: (Map Text Macro -> Map Text Macro) -> ParserState -> ParserState

class HasLogMessages st where

Methods

addLogMessage :: LogMessage -> st -> st

getLogMessages :: st -> [LogMessage]

Instances

HasLogMessages ParserState

Defined in Text.Pandoc.Parsing

Methods

addLogMessage :: LogMessage -> ParserState -> ParserState

getLogMessages :: ParserState -> [LogMessage]

class HasLastStrPosition st where

Methods

setLastStrPos :: Maybe SourcePos -> st -> st

getLastStrPos :: st -> Maybe SourcePos

Instances

HasLastStrPosition ParserState

Defined in Text.Pandoc.Parsing

Methods

setLastStrPos :: Maybe SourcePos -> ParserState -> ParserState

getLastStrPos :: ParserState -> Maybe SourcePos

class HasIncludeFiles st where

Methods

getIncludeFiles :: st -> [Text]

addIncludeFile :: Text -> st -> st

dropLatestIncludeFile :: st -> st

Instances

HasIncludeFiles ParserState

Defined in Text.Pandoc.Parsing

Methods

getIncludeFiles :: ParserState -> [Text]

addIncludeFile :: Text -> ParserState -> ParserState

dropLatestIncludeFile :: ParserState -> ParserState

defaultParserState :: ParserState

data HeaderType

Constructors

SingleHeader Char

Single line of characters underneath

DoubleHeader Char

Lines of characters above and below

Instances

Eq HeaderType

Defined in Text.Pandoc.Parsing

Methods

(==) :: HeaderType -> HeaderType -> Bool

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

Show HeaderType

Defined in Text.Pandoc.Parsing

Methods

showsPrec :: Int -> HeaderType -> ShowS

show :: HeaderType -> String

showList :: [HeaderType] -> ShowS

data ParserContext

Constructors

ListItemState

Used when running parser on list item contents

NullState

Default state

Instances

Eq ParserContext

Defined in Text.Pandoc.Parsing

Methods

(==) :: ParserContext -> ParserContext -> Bool

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

Show ParserContext

Defined in Text.Pandoc.Parsing

Methods

showsPrec :: Int -> ParserContext -> ShowS

show :: ParserContext -> String

showList :: [ParserContext] -> ShowS

data QuoteContext

Constructors

InSingleQuote

Used when parsing inside single quotes

InDoubleQuote

Used when parsing inside double quotes

NoQuote

Used when not parsing inside quotes

Instances

Eq QuoteContext

Defined in Text.Pandoc.Parsing

Methods

(==) :: QuoteContext -> QuoteContext -> Bool

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

Show QuoteContext

Defined in Text.Pandoc.Parsing

Methods

showsPrec :: Int -> QuoteContext -> ShowS

show :: QuoteContext -> String

showList :: [QuoteContext] -> ShowS

class HasQuoteContext st m where

Methods

getQuoteContext :: Stream s m t => ParsecT s st m QuoteContext

withQuoteContext :: QuoteContext -> ParsecT s st m a -> ParsecT s st m a

Instances

Monad m => HasQuoteContext ParserState m

Defined in Text.Pandoc.Parsing

Methods

getQuoteContext :: Stream s m t => ParsecT s ParserState m QuoteContext

withQuoteContext :: QuoteContext -> ParsecT s ParserState m a -> ParsecT s ParserState m a

type NoteTable = [(Text, Text)]

type NoteTable' = Map Text (SourcePos, F Blocks)

type KeyTable = Map Key (Target, Attr)

type SubstTable = Map Key Inlines

newtype Key

Constructors

Key Text

Instances

Eq Key

Defined in Text.Pandoc.Parsing

Methods

(==) :: Key -> Key -> Bool

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

Ord Key

Defined in Text.Pandoc.Parsing

Methods

compare :: Key -> Key -> Ordering

(<) :: Key -> Key -> Bool

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

(>) :: Key -> Key -> Bool

(>=) :: Key -> Key -> Bool

max :: Key -> Key -> Key

min :: Key -> Key -> Key

Read Key

Defined in Text.Pandoc.Parsing

Methods

readsPrec :: Int -> ReadS Key

readList :: ReadS [Key]

readPrec :: ReadPrec Key

readListPrec :: ReadPrec [Key]

Show Key

Defined in Text.Pandoc.Parsing

Methods

showsPrec :: Int -> Key -> ShowS

show :: Key -> String

showList :: [Key] -> ShowS

toKey :: Text -> Key

registerHeader :: (Stream s m a, HasReaderOptions st, HasLogMessages st, HasIdentifierList st) => Attr -> Inlines -> ParserT s st m Attr

smartPunctuation :: (HasReaderOptions st, HasLastStrPosition st, HasQuoteContext st m, Stream s m Char) => ParserT s st m Inlines -> ParserT s st m Inlines

singleQuoteStart :: (HasLastStrPosition st, HasQuoteContext st m, Stream s m Char) => ParserT s st m ()

singleQuoteEnd :: Stream s m Char => ParserT s st m ()

doubleQuoteStart :: (HasQuoteContext st m, Stream s m Char) => ParserT s st m ()

doubleQuoteEnd :: Stream s m Char => ParserT s st m ()

ellipses :: Stream s m Char => ParserT s st m Inlines

apostrophe :: Stream s m Char => ParserT s st m Inlines

dash :: (HasReaderOptions st, Stream s m Char) => ParserT s st m Inlines

nested :: Stream s m a => ParserT s ParserState m a -> ParserT s ParserState m a

citeKey :: (Stream s m Char, HasLastStrPosition st) => ParserT s st m (Bool, Text)

type Parser t s = Parsec t s

type ParserT = ParsecT

type F = Future ParserState

newtype Future s a

Reader monad wrapping the parser state. This is used to possibly delay evaluation until all relevant information has been parsed and made available in the parser state.

Constructors

Future

Fields

• runDelayed :: Reader s a

Instances

Monad (Future s)

Defined in Text.Pandoc.Parsing

Methods

(>>=) :: Future s a -> (a -> Future s b) -> Future s b

(>>) :: Future s a -> Future s b -> Future s b

return :: a -> Future s a

Functor (Future s)

Defined in Text.Pandoc.Parsing

Methods

fmap :: (a -> b) -> Future s a -> Future s b

(<$) :: a -> Future s b -> Future s a

Applicative (Future s)

Defined in Text.Pandoc.Parsing

Methods

pure :: a -> Future s a

(<*>) :: Future s (a -> b) -> Future s a -> Future s b

liftA2 :: (a -> b -> c) -> Future s a -> Future s b -> Future s c

(*>) :: Future s a -> Future s b -> Future s b

(<*) :: Future s a -> Future s b -> Future s a

Semigroup a => Semigroup (Future s a)

Defined in Text.Pandoc.Parsing

Methods

(<>) :: Future s a -> Future s a -> Future s a

sconcat :: NonEmpty (Future s a) -> Future s a

stimes :: Integral b => b -> Future s a -> Future s a

(Semigroup a, Monoid a) => Monoid (Future s a)

Defined in Text.Pandoc.Parsing

Methods

mempty :: Future s a

mappend :: Future s a -> Future s a -> Future s a

mconcat :: [Future s a] -> Future s a

runF :: Future s a -> s -> a

askF :: Future s s

asksF :: (s -> a) -> Future s a

returnF :: Monad m => a -> m (Future s a)

trimInlinesF :: Future s Inlines -> Future s Inlines

token :: Stream s m t => (t -> Text) -> (t -> SourcePos) -> (t -> Maybe a) -> ParsecT s st m a

(<+?>) :: Monoid a => ParserT s st m a -> ParserT s st m a -> ParserT s st m a infixr 5

extractIdClass :: Attr -> Attr

insertIncludedFile :: (PandocMonad m, HasIncludeFiles st) => ParserT [a] st m Blocks -> (Text -> [a]) -> [FilePath] -> FilePath -> ParserT [a] st m Blocks

Parse content of include file as blocks. Circular includes result in an PandocParseError.

insertIncludedFileF :: (PandocMonad m, HasIncludeFiles st) => ParserT Text st m (Future st Blocks) -> [FilePath] -> FilePath -> ParserT Text st m (Future st Blocks)

Parse content of include file as future blocks. Circular includes result in an PandocParseError.

Re-exports from Text.Parsec

class Monad m => Stream s (m :: Type -> Type) t | s -> t

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

Instances

Monad m => Stream Text m Char

Defined in Text.Parsec.Prim

Methods

uncons :: Text -> m (Maybe (Char, Text))

Monad m => Stream Text m Char

Defined in Text.Parsec.Prim

Methods

uncons :: Text -> m (Maybe (Char, Text))

Monad m => Stream ByteString m Char

Defined in Text.Parsec.Prim

Methods

uncons :: ByteString -> m (Maybe (Char, ByteString))

Monad m => Stream ByteString m Char

Defined in Text.Parsec.Prim

Methods

uncons :: ByteString -> m (Maybe (Char, ByteString))

Monad m => Stream [tok] m tok

Defined in Text.Parsec.Prim

Methods

uncons :: [tok] -> m (Maybe (tok, [tok]))

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

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)
       }

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

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).

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

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

tokenPrim

Arguments

:: forall s (m :: Type -> Type) t a u. 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

anyToken :: forall s (m :: Type -> Type) t u. (Stream s m t, Show t) => ParsecT s u m t

The parser anyToken accepts any kind of token. It is for example used to implement eof. Returns the accepted token.

getInput :: forall (m :: Type -> Type) s u. Monad m => ParsecT s u m s

Returns the current input

setInput :: forall (m :: Type -> Type) s u. Monad m => s -> ParsecT s u m ()

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

unexpected :: forall s (m :: Type -> Type) t u a. Stream s m t => String -> ParsecT s u m a

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.

char :: forall s (m :: Type -> Type) u. Stream s m Char => Char -> ParsecT s u m Char

char c parses a single character c. Returns the parsed character (i.e. c).

 semiColon  = char ';'

letter :: forall s (m :: Type -> Type) u. Stream s m Char => ParsecT s u m Char

Parses an alphabetic Unicode characters (lower-case, upper-case and title-case letters, plus letters of caseless scripts and modifiers letters according to isAlpha). Returns the parsed character.

digit :: forall s (m :: Type -> Type) u. Stream s m Char => ParsecT s u m Char

Parses an ASCII digit. Returns the parsed character.

alphaNum :: forall s (m :: Type -> Type) u. Stream s m Char => ParsecT s u m Char

Parses a alphabetic or numeric Unicode characters according to isAlphaNum. Returns the parsed character.

Note that numeric digits outside the ASCII range (such as arabic-indic digits like e.g. "٤" or U+0664), as well as numeric characters which aren't digits, are parsed by this function but not by digit.

skipMany :: forall s u (m :: Type -> Type) a. ParsecT s u m a -> ParsecT s u m ()

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

 spaces  = skipMany space

skipMany1 :: forall s (m :: Type -> Type) t u a. Stream s m t => ParsecT s u m a -> ParsecT s u m ()

skipMany1 p applies the parser p one or more times, skipping its result.

spaces :: forall s (m :: Type -> Type) u. Stream s m Char => ParsecT s u m ()

Skips zero or more white space characters. See also skipMany.

space :: forall s (m :: Type -> Type) u. Stream s m Char => ParsecT s u m Char

Parses a white space character (any character which satisfies isSpace) Returns the parsed character.

anyChar :: forall s (m :: Type -> Type) u. Stream s m Char => ParsecT s u m Char

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

satisfy :: forall s (m :: Type -> Type) u. Stream s m Char => (Char -> Bool) -> ParsecT s u 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.

newline :: forall s (m :: Type -> Type) u. Stream s m Char => ParsecT s u m Char

Parses a newline character ('\n'). Returns a newline character.

string :: forall s (m :: Type -> Type) u. Stream s m Char => String -> ParsecT s u m String

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

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

count :: forall s (m :: Type -> Type) t u a. Stream s m t => Int -> ParsecT s u m a -> ParsecT s u 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 returned by p.

eof :: forall s (m :: Type -> Type) t u. (Stream s m t, Show t) => ParsecT s u m ()

This parser only succeeds at the end of the input. This is not a primitive parser but it is defined using notFollowedBy.

 eof  = notFollowedBy anyToken <?> "end of input"

noneOf :: forall s (m :: Type -> Type) u. Stream s m Char => [Char] -> ParsecT s u 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.

 consonant = noneOf "aeiou"

oneOf :: forall s (m :: Type -> Type) u. Stream s m Char => [Char] -> ParsecT s u m Char

oneOf cs succeeds if the current character is in the supplied list of characters cs. Returns the parsed character. See also satisfy.

  vowel  = oneOf "aeiou"

lookAhead :: forall s (m :: Type -> Type) t u a. Stream s m t => ParsecT s u m a -> ParsecT s u m a

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.

notFollowedBy :: forall s (m :: Type -> Type) t a u. (Stream s m t, Show a) => ParsecT s u m a -> ParsecT s u m ()

notFollowedBy p only succeeds when parser p fails. This parser does not consume any input. This parser can be used to implement the 'longest match' rule. For example, when recognizing keywords (for example let), we want to make sure that a keyword is not followed by a legal identifier character, in which case the keyword is actually an identifier (for example lets). We can program this behaviour as follows:

 keywordLet  = try (do{ string "let"
                      ; notFollowedBy alphaNum
                      })

NOTE: Currently, notFollowedBy exhibits surprising behaviour when applied to a parser p that doesn't consume any input; specifically

• notFollowedBy . notFollowedBy is not equivalent to lookAhead, and
• notFollowedBy eof never fails.

See haskell/parsec#8 for more details.

many :: forall s u (m :: Type -> Type) a. ParsecT s u m a -> ParsecT s u m [a]

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)
                 }

many1 :: forall s (m :: Type -> Type) t u a. Stream s m t => ParsecT s u m a -> ParsecT s u m [a]

many1 p applies the parser p one or more times. Returns a list of the returned values of p.

 word  = many1 letter

manyTill :: forall s (m :: Type -> Type) t u a end. Stream s m t => ParsecT s u m a -> ParsecT s u m end -> ParsecT s u 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   = do{ string "<!--"
                     ; manyTill anyChar (try (string "-->"))
                     }

Note the overlapping parsers anyChar and string "-->", and therefore the use of the try combinator.

(<|>) :: forall s u (m :: Type -> Type) a. ParsecT s u m a -> ParsecT s u m a -> ParsecT s u m a infixr 1

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.

(<?>) :: forall s u (m :: Type -> Type) a. ParsecT s u m a -> String -> ParsecT s u m a infix 0

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.

choice :: forall s (m :: Type -> Type) t u a. Stream s m t => [ParsecT s u m a] -> ParsecT s u 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.

try :: forall s u (m :: Type -> Type) a. ParsecT s u m a -> ParsecT s u m a

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

sepBy :: forall s (m :: Type -> Type) t u a sep. Stream s m t => ParsecT s u m a -> ParsecT s u m sep -> ParsecT s u 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` (symbol ",")

sepBy1 :: forall s (m :: Type -> Type) t u a sep. Stream s m t => ParsecT s u m a -> ParsecT s u m sep -> ParsecT s u m [a]

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

sepEndBy :: forall s (m :: Type -> Type) t u a sep. Stream s m t => ParsecT s u m a -> ParsecT s u m sep -> ParsecT s u m [a]

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

 haskellStatements  = haskellStatement `sepEndBy` semi

sepEndBy1 :: forall s (m :: Type -> Type) t u a sep. Stream s m t => ParsecT s u m a -> ParsecT s u m sep -> ParsecT s u 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.

endBy :: forall s (m :: Type -> Type) t u a sep. Stream s m t => ParsecT s u m a -> ParsecT s u m sep -> ParsecT s u 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` semi

endBy1 :: forall s (m :: Type -> Type) t u a sep. Stream s m t => ParsecT s u m a -> ParsecT s u m sep -> ParsecT s u 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.

option :: forall s (m :: Type -> Type) t a u. Stream s m t => a -> ParsecT s u m a -> ParsecT s u m a

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

 priority  = option 0 (do{ d <- digit
                         ; return (digitToInt d)
                         })

optional :: forall s (m :: Type -> Type) t u a. Stream s m t => ParsecT s u m a -> ParsecT s u m ()

optional p tries to apply parser p. It will parse p or nothing. It only fails if p fails after consuming input. It discards the result of p.

optionMaybe :: forall s (m :: Type -> Type) t u a. Stream s m t => ParsecT s u m a -> ParsecT s u m (Maybe a)

optionMaybe p tries to apply parser p. If p fails without consuming input, it return Nothing, otherwise it returns Just the value returned by p.

getState :: forall (m :: Type -> Type) s u. Monad m => ParsecT s u m u

Returns the current user state.

setState :: forall (m :: Type -> Type) u s. Monad m => u -> ParsecT s u m ()

An alias for putState for backwards compatibility.

updateState :: forall (m :: Type -> Type) u s. Monad m => (u -> u) -> ParsecT s u m ()

An alias for modifyState for backwards compatibility.

data SourcePos

The abstract data type SourcePos represents source positions. It contains the name of the source (i.e. file name), a line number and a column number. SourcePos is an instance of the Show, Eq and Ord class.

Instances

Eq SourcePos

Defined in Text.Parsec.Pos

Methods

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

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

Data SourcePos

Defined in Text.Parsec.Pos

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 :: forall r r'. (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

Defined in Text.Parsec.Pos

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

Show SourcePos

Defined in Text.Parsec.Pos

Methods

showsPrec :: Int -> SourcePos -> ShowS

show :: SourcePos -> String

showList :: [SourcePos] -> ShowS

getPosition :: forall (m :: Type -> Type) s u. Monad m => ParsecT s u m SourcePos

Returns the current source position. See also SourcePos.

setPosition :: forall (m :: Type -> Type) s u. Monad m => SourcePos -> ParsecT s u m ()

setPosition pos sets the current source position to pos.

sourceColumn :: SourcePos -> Column

Extracts the column number from a source position.

sourceLine :: SourcePos -> Line

Extracts the line number from a source position.

setSourceColumn :: SourcePos -> Column -> SourcePos

Set the column number of a source position.

setSourceLine :: SourcePos -> Line -> SourcePos

Set the line number of a source position.

incSourceColumn :: SourcePos -> Column -> SourcePos

Increments the column number of a source position.

incSourceLine :: SourcePos -> Line -> SourcePos

Increments the line number of a source position.

newPos :: SourceName -> Line -> Column -> SourcePos

Create a new SourcePos with the given source name, line number and column number.

initialPos :: SourceName -> SourcePos

Create a new SourcePos with the given source name, and line number and column number set to 1, the upper left.

type Line = Int

type Column = Int

data ParseError

The abstract data type ParseError represents parse errors. It provides the source position (SourcePos) of the error and a list of error messages (Message). A ParseError can be returned by the function parse. ParseError is an instance of the Show and Eq classes.

Instances

Eq ParseError

Defined in Text.Parsec.Error

Methods

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

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

Show ParseError

Defined in Text.Parsec.Error

Methods

showsPrec :: Int -> ParseError -> ShowS

show :: ParseError -> String

showList :: [ParseError] -> ShowS