Lexer

Documentation

data Token

Constructors

ITas

ITcase

ITclass

ITdata

ITdefault

ITderiving

ITdo

ITelse

IThiding

ITforeign

ITif

ITimport

ITin

ITinfix

ITinfixl

ITinfixr

ITinstance

ITlet

ITmodule

ITnewtype

ITof

ITqualified

ITthen

ITtype

ITwhere

ITforall IsUnicodeSyntax

ITexport

ITlabel

ITdynamic

ITsafe

ITinterruptible

ITunsafe

ITstdcallconv

ITccallconv

ITcapiconv

ITprimcallconv

ITjavascriptcallconv

ITmdo

ITfamily

ITrole

ITgroup

ITby

ITusing

ITpattern

ITstatic

ITstock

ITanyclass

ITvia

ITunit

ITsignature

ITdependency

ITrequires

ITinline_prag SourceText InlineSpec RuleMatchInfo

ITspec_prag SourceText

ITspec_inline_prag SourceText Bool

ITsource_prag SourceText

ITrules_prag SourceText

ITwarning_prag SourceText

ITdeprecated_prag SourceText

ITline_prag SourceText

ITcolumn_prag SourceText

ITscc_prag SourceText

ITgenerated_prag SourceText

ITcore_prag SourceText

ITunpack_prag SourceText

ITnounpack_prag SourceText

ITann_prag SourceText

ITcomplete_prag SourceText

ITclose_prag

IToptions_prag String

ITinclude_prag String

ITlanguage_prag

ITminimal_prag SourceText

IToverlappable_prag SourceText

IToverlapping_prag SourceText

IToverlaps_prag SourceText

ITincoherent_prag SourceText

ITctype SourceText

ITcomment_line_prag

ITdotdot

ITcolon

ITdcolon IsUnicodeSyntax

ITequal

ITlam

ITlcase

ITvbar

ITlarrow IsUnicodeSyntax

ITrarrow IsUnicodeSyntax

ITat

ITtilde

ITdarrow IsUnicodeSyntax

ITminus

ITbang

ITstar IsUnicodeSyntax

ITdot

ITbiglam

ITocurly

ITccurly

ITvocurly

ITvccurly

ITobrack

ITopabrack

ITcpabrack

ITcbrack

IToparen

ITcparen

IToubxparen

ITcubxparen

ITsemi

ITcomma

ITunderscore

ITbackquote

ITsimpleQuote

ITvarid FastString

ITconid FastString

ITvarsym FastString

ITconsym FastString

ITqvarid (FastString, FastString)

ITqconid (FastString, FastString)

ITqvarsym (FastString, FastString)

ITqconsym (FastString, FastString)

ITdupipvarid FastString

ITlabelvarid FastString

ITchar SourceText Char

ITstring SourceText FastString

ITinteger IntegralLit

ITrational FractionalLit

ITprimchar SourceText Char

ITprimstring SourceText ByteString

ITprimint SourceText Integer

ITprimword SourceText Integer

ITprimfloat FractionalLit

ITprimdouble FractionalLit

ITopenExpQuote HasE IsUnicodeSyntax

ITopenPatQuote

ITopenDecQuote

ITopenTypQuote

ITcloseQuote IsUnicodeSyntax

ITopenTExpQuote HasE

ITcloseTExpQuote

ITidEscape FastString

ITparenEscape

ITidTyEscape FastString

ITparenTyEscape

ITtyQuote

ITquasiQuote (FastString, FastString, RealSrcSpan)

ITqQuasiQuote (FastString, FastString, FastString, RealSrcSpan)

ITproc

ITrec

IToparenbar IsUnicodeSyntax

(|

ITcparenbar IsUnicodeSyntax

|)

ITlarrowtail IsUnicodeSyntax

-<

ITrarrowtail IsUnicodeSyntax

>-

ITLarrowtail IsUnicodeSyntax

-<<

ITRarrowtail IsUnicodeSyntax

>>-

ITtypeApp

Type application '@' (lexed differently than as-pattern '@', due to checking for preceding whitespace)

ITunknown String

Used when the lexer can't make sense of it

ITeof

end of file token

ITdocCommentNext String

something beginning -- |

ITdocCommentPrev String

something beginning -- ^

ITdocCommentNamed String

something beginning -- $

ITdocSection Int String

a section heading

ITdocOptions String

doc options (prune, ignore-exports, etc)

ITlineComment String

comment starting by "--"

ITblockComment String

comment in {- -}

Instances

Show Token

Defined in Lexer

Methods

showsPrec :: Int -> Token -> ShowS

show :: Token -> String

showList :: [Token] -> ShowS

Outputable Token

Defined in Lexer

Methods

ppr :: Token -> SDoc

pprPrec :: Rational -> Token -> SDoc

lexer :: Bool -> (Located Token -> P a) -> P a

pragState :: DynFlags -> StringBuffer -> RealSrcLoc -> PState

mkPState :: DynFlags -> StringBuffer -> RealSrcLoc -> PState

Creates a parse state from a DynFlags value

mkPStatePure :: ParserFlags -> StringBuffer -> RealSrcLoc -> PState

Creates a parse state from a ParserFlags value

data PState

Constructors

PState

Fields

• buffer :: StringBuffer
• options :: ParserFlags
• messages :: DynFlags -> Messages
• tab_first :: Maybe RealSrcSpan
• tab_count :: !Int
• last_tk :: Maybe Token
• last_loc :: RealSrcSpan
• last_len :: !Int
• loc :: RealSrcLoc
• context :: [LayoutContext]
• lex_state :: [Int]
• srcfiles :: [FastString]
• alr_pending_implicit_tokens :: [RealLocated Token]
• alr_next_token :: Maybe (RealLocated Token)
• alr_last_loc :: RealSrcSpan
• alr_context :: [ALRContext]
• alr_expecting_ocurly :: Maybe ALRLayout
• alr_justClosedExplicitLetBlock :: Bool
• annotations :: [(ApiAnnKey, [SrcSpan])]
• comment_q :: [Located AnnotationComment]
• annotations_comments :: [(SrcSpan, [Located AnnotationComment])]

newtype P a

Constructors

P

Fields

• unP :: PState -> ParseResult a

Instances

Monad P

Defined in Lexer

Methods

(>>=) :: P a -> (a -> P b) -> P b

(>>) :: P a -> P b -> P b

return :: a -> P a

Functor P

Defined in Lexer

Methods

fmap :: (a -> b) -> P a -> P b

(<$) :: a -> P b -> P a

MonadFail P

Defined in Lexer

Methods

fail :: String -> P a

Applicative P

Defined in Lexer

Methods

pure :: a -> P a

(<*>) :: P (a -> b) -> P a -> P b

liftA2 :: (a -> b -> c) -> P a -> P b -> P c

(*>) :: P a -> P b -> P b

(<*) :: P a -> P b -> P a

data ParseResult a

Constructors

POk PState a

PFailed (DynFlags -> Messages) SrcSpan MsgDoc

mkParserFlags :: DynFlags -> ParserFlags

Extracts the flag information needed for parsing

mkParserFlags'

Arguments

:: EnumSet WarningFlag

warnings flags enabled

-> EnumSet Extension

permitted language extensions enabled

-> UnitId

key of package currently being compiled

-> Bool

are safe imports on?

-> Bool

keeping Haddock comment tokens

-> Bool

keep regular comment tokens

-> Bool

If this is enabled, '{-}' and '{--}' update the internal position kept by the parser. Otherwise, those pragmas are lexed as ITline_prag and ITcolumn_prag tokens.

-> ParserFlags

Given exactly the information needed, set up the ParserFlags

data ParserFlags

The subset of the DynFlags used by the parser. See mkParserFlags or mkParserFlags' for ways to construct this.

getRealSrcLoc :: P RealSrcLoc

getPState :: P PState

withThisPackage :: (UnitId -> a) -> P a

failLocMsgP :: RealSrcLoc -> RealSrcLoc -> String -> P a

failSpanMsgP :: SrcSpan -> SDoc -> P a

srcParseFail :: P a

getMessages :: PState -> DynFlags -> Messages

popContext :: P ()

pushModuleContext :: P ()

setLastToken :: RealSrcSpan -> Int -> P ()

setSrcLoc :: RealSrcLoc -> P ()

activeContext :: P Bool

nextIsEOF :: P Bool

getLexState :: P Int

popLexState :: P Int

pushLexState :: Int -> P ()

data ExtBits

Various boolean flags, mostly language extensions, that impact lexing and parsing. Note that a handful of these can change during lexing/parsing.

Constructors

FfiBit

InterruptibleFfiBit

CApiFfiBit

ArrowsBit

ThBit

ThQuotesBit

IpBit

OverloadedLabelsBit

ExplicitForallBit

BangPatBit

PatternSynonymsBit

HaddockBit

MagicHashBit

RecursiveDoBit

UnicodeSyntaxBit

UnboxedTuplesBit

UnboxedSumsBit

DatatypeContextsBit

MonadComprehensionsBit

TransformComprehensionsBit

QqBit

RawTokenStreamBit

AlternativeLayoutRuleBit

ALRTransitionalBit

RelaxedLayoutBit

NondecreasingIndentationBit

SafeHaskellBit

TraditionalRecordSyntaxBit

ExplicitNamespacesBit

LambdaCaseBit

BinaryLiteralsBit

NegativeLiteralsBit

HexFloatLiteralsBit

TypeApplicationsBit

StaticPointersBit

NumericUnderscoresBit

StarIsTypeBit

BlockArgumentsBit

NPlusKPatternsBit

DoAndIfThenElseBit

MultiWayIfBit

GadtSyntaxBit

InRulePragBit

InNestedCommentBit

UsePosPragsBit

If this is enabled, '{-}' and '{--}' update the internal position. Otherwise, those pragmas are lexed as tokens of their own.

Instances

Enum ExtBits

Defined in Lexer

Methods

succ :: ExtBits -> ExtBits

pred :: ExtBits -> ExtBits

toEnum :: Int -> ExtBits

fromEnum :: ExtBits -> Int

enumFrom :: ExtBits -> [ExtBits]

enumFromThen :: ExtBits -> ExtBits -> [ExtBits]

enumFromTo :: ExtBits -> ExtBits -> [ExtBits]

enumFromThenTo :: ExtBits -> ExtBits -> ExtBits -> [ExtBits]

getBit :: ExtBits -> P Bool

Check if a given flag is currently set in the bitmap.

addWarning :: WarningFlag -> SrcSpan -> SDoc -> P ()

lexTokenStream :: StringBuffer -> RealSrcLoc -> DynFlags -> ParseResult [Located Token]

addAnnotation :: SrcSpan -> AnnKeywordId -> SrcSpan -> P ()

type AddAnn = SrcSpan -> P ()

Encapsulated call to addAnnotation, requiring only the SrcSpan of the AST construct the annotation belongs to; together with the AnnKeywordId, this is the key of the annotation map.

This type is useful for places in the parser where it is not yet known what SrcSpan an annotation should be added to. The most common situation is when we are parsing a list: the annotations need to be associated with the AST element that *contains* the list, not the list itself. AddAnn lets us defer adding the annotations until we finish parsing the list and are now parsing the enclosing element; we then apply the AddAnn to associate the annotations. Another common situation is where a common fragment of the AST has been factored out but there is no separate AST node for this fragment (this occurs in class and data declarations). In this case, the annotation belongs to the parent data declaration.

The usual way an AddAnn is created is using the mj ("make jump") function, and then it can be discharged using the ams function.

addAnnsAt :: SrcSpan -> [AddAnn] -> P ()

Given a location and a list of AddAnn, apply them all to the location.

mkParensApiAnn :: SrcSpan -> [AddAnn]

Given a SrcSpan that surrounds a HsPar or HsParTy, generate AddAnn values for the opening and closing bordering on the start and end of the span

commentToAnnotation :: Located Token -> Located AnnotationComment