implementation module lex
-import Data.Either
-import Data.List
+import Control.Monad
+import Data.Either, Data.Maybe, Data.Map, Data.Func
import StdString
-import System.CommandLine
-import StdFile
-import StdMisc
+import StdTuple
import StdBool
-from StdFunc import id, const
-import Data.Maybe
-import Control.Applicative
-import Control.Monad
-import Control.Monad.State
-import Data.Functor
-from Data.Func import $
-from Text import class Text, instance Text String
-import qualified Text
+import StdList
+import StdChar
+
+SingleCharTokens :: Map Char Token
+SingleCharTokens = fromList [
+ ('(', BraceOpenToken), (')', BraceCloseToken), ('{', CBraceOpenToken),
+ ('}', CBraceCloseToken), ('[', SquareOpenToken), (']', SquareCloseToken),
+ (',', CommaToken), (':', ColonToken), (';', SColonToken),
+ ('.', DotToken), ('+', PlusToken), ('*', StarToken), ('/', SlashToken),
+ ('%', PercentToken), ('=', AssignmentToken), ('<', LesserToken),
+ ('>', BiggerToken), ('!', ExclamationToken)]
-Start :: *World -> *World
-Start w
-# (args, w) = getCommandLine w // We lezen nu nog standaard van stdin
-# (out, w) = stdio w
-# (toparse, out) = readEntireFile out
-# out = out <<< print (lexer toparse)
-# (b, w) = fclose out w
-| not b = setReturnCode 1 w
-= w
- where
- readEntireFile :: *File -> *([Char], *File)
- readEntireFile f
- # (b, c, f) = freadc f
- | not b = ([], f)
- # (cs, f) = readEntireFile f
- = ([c:cs], f)
+EscapeMap :: Map Char Char
+EscapeMap = fromList [('a', toChar 7), ('b', '\b'), ('f', '\f'), ('n', '\n'),
+ ('r', '\r'), ('t', '\t'), ('v', '\v')]
lexer :: [Char] -> LexerOutput
lexer [] = Right []
(Right t, rest) = lexer rest >>= \ts.Right [t:ts]
(Left e, _) = Left e
-print :: LexerOutput -> String
-print (Left l) = "Error: " +++ l
-print (Right x) = 'Text'.concat (print` 0 x)
- where
- print` :: Int [Token] -> [String]
- print` _ [] = []
- print` i [(IdentToken l):rest] = [toString l:print` i rest]
- print` i [(NumberToken j):rest] = [toString j:print` i rest]
- print` i [(CharToken c):rest] = ["'":toString c:"'":print` i rest]
- print` i [VarToken:rest] = ["var ":print` i rest]
- print` i [VoidToken:rest] = ["Void":print` i rest]
- print` i [ReturnToken:rest] = ["return":print` i rest]
- print` i [IfToken:rest] = ["if":print` i rest]
- print` i [ElseToken:rest] = ["else":print` i rest]
- print` i [WhileToken:rest] = ["while":print` i rest]
- print` i [TrueToken:rest] = ["True":print` i rest]
- print` i [FalseToken:rest] = ["False":print` i rest]
- print` i [BraceOpenToken:rest] = ["(":print` i rest]
- print` i [BraceCloseToken:rest] = [")":print` i rest]
- print` i [CBraceOpenToken:rest] = ["{\n":tab (i+1):print` (i+1) rest]
- print` i [CBraceCloseToken:rest] = ["}\n":tab i:print` i rest]
- print` i [SquareOpenToken:rest] = ["[":print` i rest]
- print` i [SquareCloseToken:rest] = ["]":print` i rest]
- print` i [CommaToken:rest] = [", ":print` i rest]
- print` i [ColonToken:rest] = [":":print` i rest]
- print` i [SColonToken:CBraceCloseToken:rest] =
- [";\n":tab (i-1):"}\n":print` (i-1) rest]
- print` i [SColonToken:rest] = [";\n":tab i:print` i rest]
- print` i [DotToken:rest] = [".":print` i rest]
- print` i [PlusToken:rest] = [" + ":print` i rest]
- print` i [DashToken:rest] = [" - ":print` i rest]
- print` i [StarToken:rest] = [" * ":print` i rest]
- print` i [SlashToken:rest] = [" / ":print` i rest]
- print` i [PercentToken:rest] = [" % ":print` i rest]
- print` i [AssignmentToken:rest] = [" = ":print` i rest]
- print` i [LesserToken:rest] = [" < ":print` i rest]
- print` i [BiggerToken:rest] = [" > ":print` i rest]
- print` i [ExclamationToken:rest] = ["!":print` i rest]
- print` i [DoubleColonToken:rest] = [" :: ":print` i rest]
- print` i [LesserEqToken:rest] = [" <= ":print` i rest]
- print` i [GreaterEqToken:rest] = [" >= ":print` i rest]
- print` i [EqualsToken:rest] = [" == ":print` i rest]
- print` i [AmpersandsToken:rest] = [" && ":print` i rest]
- print` i [PipesToken:rest] = [" || ":print` i rest]
- print` i [ArrowToken:rest] = [" -> ":print` i rest]
- print` i [EndOfFileToken:rest] = ["\n":print` i rest]
-
-tab :: Int -> String
-tab 0 = ""
-tab i = "\t" +++ tab (i-1)
-
-
lex :: [Char] -> (Either String Token, [Char])
lex [] = (Right EndOfFileToken, [])
-lex ['v':'a':'r':rest] = (Right VarToken, rest)
-lex ['V':'o':'i':'d':rest] = (Right VoidToken, rest)
-lex ['r':'e':'t':'u':'r':'n':rest] = (Right ReturnToken, rest)
-lex ['i':'f':rest] = (Right IfToken, rest)
-lex ['e':'l':'s':'e':rest] = (Right ElseToken, rest)
-lex ['w':'h':'i':'l':'e':rest] = (Right WhileToken, rest)
-lex ['T':'r':'u':'e':rest] = (Right TrueToken, rest)
-lex ['F':'a':'l':'s':'e':rest] = (Right FalseToken, rest)
-lex ['\'':'\\':x:'\'':rest] = case x of
- 'a' = (Right (CharToken (toChar 7)), rest) //Alarm
- 'b' = (Right (CharToken '\b'), rest) //Backspace
- 'f' = (Right (CharToken '\f'), rest) //Formfeed
- 'n' = (Right (CharToken '\n'), rest) //Newline
- 'r' = (Right (CharToken '\r'), rest) //Carriage Return
- 't' = (Right (CharToken '\t'), rest) //Horizontal tab
- 'v' = (Right (CharToken '\v'), rest) //Vertical tab
- _ = (Left ("Unknown escape: \\" +++ toString x), rest)
-lex ['\'':x:'\'':rest] = (Right (CharToken x), rest)
-lex [':':':':rest] = (Right DoubleColonToken, rest)
-lex ['<':'=':rest] = (Right LesserEqToken, rest)
-lex ['>':'=':rest] = (Right GreaterEqToken, rest)
-lex ['=':'=':rest] = (Right EqualsToken, rest)
-lex ['&':'&':rest] = (Right AmpersandsToken, rest)
-lex ['|':'|':rest] = (Right PipesToken, rest)
-lex ['-':'>':rest] = (Right ArrowToken, rest)
-lex ['(':rest] = (Right BraceOpenToken, rest)
-lex [')':rest] = (Right BraceCloseToken, rest)
-lex ['{':rest] = (Right CBraceOpenToken, rest)
-lex ['}':rest] = (Right CBraceCloseToken, rest)
-lex ['[':rest] = (Right SquareOpenToken, rest)
-lex [']':rest] = (Right SquareCloseToken, rest)
-lex [',':rest] = (Right CommaToken, rest)
-lex [':':rest] = (Right ColonToken, rest)
-lex [';':rest] = (Right SColonToken, rest)
-lex ['.':rest] = (Right DotToken, rest)
-lex ['+':rest] = (Right PlusToken, rest)
-lex ['-':rest] = (Right DashToken, rest)
-lex ['*':rest] = (Right StarToken, rest)
-lex ['/':rest] = (Right SlashToken, rest)
-lex ['%':rest] = (Right PercentToken, rest)
-lex ['=':rest] = (Right AssignmentToken, rest)
-lex ['<':rest] = (Right LesserToken, rest)
-lex ['>':rest] = (Right BiggerToken, rest)
-lex ['!':rest] = (Right ExclamationToken, rest)
-lex [x:xs]
-| isSpace x = lex xs
-| isDigit x
- # (is, rest) = span isDigit xs
- = (Right (NumberToken [x:is]), rest)
-| isAlpha x
- # (is, rest) = span (\c.isAlphanum c || c == '_') xs
- = (Right (IdentToken [x:is]), rest)
-| otherwise = (Left ("Unexpected character: " +++ toString x), [])
+lex ['/':'/':xs] = lex $ dropWhile ((<>) '\n') xs
+lex ['/':'*':xs] =
+ lex $ tl $ map snd $ dropWhile ((<>) ('*', '/')) $ zip2 [zero:xs] xs
+lex ['v':'a':'r':xs] = (Right VarToken, xs)
+lex ['V':'o':'i':'d':xs] = (Right VoidToken, xs)
+lex ['r':'e':'t':'u':'r':'n':xs] = (Right ReturnToken, xs)
+lex ['i':'f':xs] = (Right IfToken, xs)
+lex ['e':'l':'s':'e':xs] = (Right ElseToken, xs)
+lex ['w':'h':'i':'l':'e':xs] = (Right WhileToken, xs)
+lex ['T':'r':'u':'e':xs] = (Right TrueToken, xs)
+lex ['F':'a':'l':'s':'e':xs] = (Right FalseToken, xs)
+lex ['I':'n':'t':xs] = (Right IntTypeToken, xs)
+lex ['C':'h':'a':'r':xs] = (Right CharTypeToken, xs)
+lex ['B':'o':'o':'l':xs] = (Right BoolTypeToken, xs)
+lex [':':':':xs] = (Right DoubleColonToken, xs)
+lex ['!':'=':xs] = (Right NotEqualToken, xs)
+lex ['<':'=':xs] = (Right LesserEqToken, xs)
+lex ['>':'=':xs] = (Right GreaterEqToken, xs)
+lex ['=':'=':xs] = (Right EqualsToken, xs)
+lex ['&':'&':xs] = (Right AmpersandsToken, xs)
+lex ['|':'|':xs] = (Right PipesToken, xs)
+lex ['-':'>':xs] = (Right ArrowToken, xs)
+lex ['\'':x:'\'':xs] = (Right (CharToken x), xs)
+lex ['\'':'\\':x:'\'':xs] = case get x EscapeMap of
+ Just t = (Right (CharToken t), xs)
+ _ = (Left ("Unknown escape: \\" +++ toString x), [])
+lex ['-':t=:[x:xs]]
+| isDigit x = let (i, r) = span isDigit t in (Right (NumberToken ['-':i]), r)
+| otherwise = (Right DashToken, xs)
+lex t=:[x:xs] = case get x SingleCharTokens of
+ (Just tok) = (Right tok, xs)
+ Nothing
+ | isSpace x = lex xs
+ | isDigit x = let (i, r) = span isDigit t in (Right (NumberToken i), r)
+ | isAlpha x = let (i, r) = span isIdent t in (Right (IdentToken i), r)
+ with isIdent c = isAlphanum c || c == '_'
+ | otherwise = (Left ("Unexpected character: " +++ toString x), [])
repositories / cc1516.git / blobdiff