From: Mart Lubbers <mart@martlubbers.net>
Date: Fri, 12 Feb 2016 17:13:29 +0000 (+0100)
Subject: working lexer and printer
X-Git-Url: https://git.martlubbers.net/?a=commitdiff_plain;h=98144e50ff2ca8e8d89dd1a39d4f2a41c2c6dab6;p=cc1516.git

working lexer and printer
---

diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..56d9b95
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,7 @@
+CPM:=cpm
+
+all:
+	$(CPM) make
+
+clean:
+	$(RM) -rv Clean\ System\ Files sapl lex
diff --git a/example.spl b/example.spl
new file mode 100644
index 0000000..f7ce562
--- /dev/null
+++ b/example.spl
@@ -0,0 +1,11 @@
+/*
+	Three ways to implement the f acto rial function in SPL.
+	First the recursive version .
+*/
+facR(n) :: Int -> Int {
+	if (n < 2) {
+		return 1;
+	} else {
+		return n * facR(n-1);
+	}
+}
diff --git a/lex.dcl b/lex.dcl
index 46a3ab8..d6c421c 100644
--- a/lex.dcl
+++ b/lex.dcl
@@ -9,18 +9,29 @@ import Data.Either
 	| CharToken Char    // Character literal
 	//Keyword tokens
 	| VarToken          // var keyword
-	| VoidToken         // void keyword
 	| ReturnToken       // return keyword
 	| IfToken           // if keyword
 	| ElseToken         // else keyword
 	| WhileToken        // while keyword
 	| TrueToken         // True keyword
 	| FalseToken        // False keyword
+	| VoidToken         // Void keyword
+	| IntTypeToken      // Int keyword
+	| CharTypeToken     // Char keyword
+	| BoolTypeToken     // Bool keyword
+	//Two character tokens
+	| DoubleColonToken  // ::
+	| LesserEqToken     // <=
+	| GreaterEqToken    // >=
+	| EqualsToken       // ==
+	| AmpersandsToken   // &&
+	| PipesToken        // ||
+    | ArrowToken        // ->
 	//One character tokens
 	| BraceOpenToken    // (
 	| BraceCloseToken   // )
 	| CBraceOpenToken   // {
-	| CBraceCloseToken  // {
+	| CBraceCloseToken  // }
 	| SquareOpenToken   // [
 	| SquareCloseToken  // ]
 	| CommaToken        // ,
@@ -36,16 +47,11 @@ import Data.Either
 	| LesserToken       // <
 	| BiggerToken       // >
 	| ExclamationToken  // !
-	//Two character tokens
-	| DoubleColonToken  // ::
-	| LesserEqToken     // <=
-	| GreaterEqToken    // >=
-	| EqualsToken       // ==
-	| AmpersandsToken   // &&
-	| PipesToken        // ||
-    | ArrowToken        // ->
+	//Special tokens
 	| EndOfFileToken    // EOF
 
 :: LexerOutput :== Either String [Token]
 
+instance toString LexerOutput
+
 lexer :: [Char] -> LexerOutput
diff --git a/lex.icl b/lex.icl
index a1912bf..aa50e72 100644
--- a/lex.icl
+++ b/lex.icl
@@ -1,38 +1,29 @@
 implementation module lex
 
+from Text import class Text, instance Text String
+import Control.Monad
 import Data.Either
+import Data.Functor
 import Data.List
 import StdString
-import System.CommandLine
-import StdFile
-import StdMisc
 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 StdFile
+import System.CommandLine
 import qualified Text
 
 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) = fclose (out <<< "\n" <<< toString (lexer toparse)) w
 = w
-	where
-		readEntireFile :: *File -> *([Char], *File)
-		readEntireFile f
-		# (b, c, f) = freadc f
-		| not b = ([], f)
-		# (cs, f) = readEntireFile f
-		= ([c:cs], f)
+
+readEntireFile :: *File -> *([Char], *File)
+readEntireFile f
+# (b, c, f) = freadc f
+| not b = ([], f)
+# (cs, f) = readEntireFile f
+= ([c:cs], f)
 
 lexer :: [Char] -> LexerOutput
 lexer [] = Right []
@@ -40,60 +31,17 @@ lexer x = case lex x of
 	(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)
-
+untilNext :: [Char] -> [Char]
+untilNext [] = []
+untilNext ['*':'/':rest] = rest
+untilNext [x:rest] = untilNext rest
 
 lex :: [Char] -> (Either String Token, [Char])
 lex [] = (Right EndOfFileToken, [])
+//Comments
+lex ['/':'/':rest] = lex (tl (dropWhile ((<>) '\n') rest))
+lex ['/':'*':rest] = lex (untilNext rest)
+//Keyword tokens
 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)
@@ -102,16 +50,10 @@ 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 ['I':'n':'t':rest] = (Right IntTypeToken, rest)
+lex ['C':'h':'a':'r':rest] = (Right CharTypeToken, rest)
+lex ['B':'o':'o':'l':rest] = (Right BoolTypeToken, rest)
+//Two character tokens
 lex [':':':':rest] = (Right DoubleColonToken, rest)
 lex ['<':'=':rest] = (Right LesserEqToken, rest)
 lex ['>':'=':rest] = (Right GreaterEqToken, rest)
@@ -119,6 +61,7 @@ lex ['=':'=':rest] = (Right EqualsToken, rest)
 lex ['&':'&':rest] = (Right AmpersandsToken, rest)
 lex ['|':'|':rest] = (Right PipesToken, rest)
 lex ['-':'>':rest] = (Right ArrowToken, rest)
+//One character tokens
 lex ['(':rest] = (Right BraceOpenToken, rest)
 lex [')':rest] = (Right BraceCloseToken, rest)
 lex ['{':rest] = (Right CBraceOpenToken, rest)
@@ -138,12 +81,76 @@ lex ['=':rest] = (Right AssignmentToken, rest)
 lex ['<':rest] = (Right LesserToken, rest)
 lex ['>':rest] = (Right BiggerToken, rest)
 lex ['!':rest] = (Right ExclamationToken, rest)
+//Value tokens
+lex ['\'':x:'\'':rest] = (Right (CharToken x), 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), [])
 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)
+| isDigit x = let (is, rest) = span isDigit xs in
+	(Right (NumberToken [x:is]), rest)
+| isAlpha x = let (is, rest) = span (\c.isAlphanum c || c == '_') xs in
+	(Right (IdentToken [x:is]), rest)
 | otherwise = (Left ("Unexpected character: " +++ toString x), [])
+
+instance toString LexerOutput where
+	toString (Left l) = "Error: " +++ l
+	toString (Right x) = 'Text'.concat (print 0 x)
+
+tab :: Int -> [String]
+tab i = replicate i "\t"
+
+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 [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 [VoidToken:rest] = ["Void":print i rest]
+print i [IntTypeToken:rest] = ["Int":print i rest]
+print i [CharTypeToken:rest] = ["Char":print i rest]
+print i [BoolTypeToken:rest] = ["Bool":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 [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] = case rest of
+	[CBraceCloseToken:_] = 	["}\n":tab (i-2)] ++ print (i-1) rest
+	_ = ["}\n":tab (i-1)] ++ print (i-1) 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:rest] = case rest of
+	[CBraceCloseToken:_] = [";\n":tab (i-1)] ++ print i 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 [EndOfFileToken:rest] = ["\n":print i rest]
diff --git a/lex.prj b/lex.prj
index 35240fc..199a01e 100644
--- a/lex.prj
+++ b/lex.prj
@@ -349,34 +349,6 @@ OtherModules
 			ReadableABC:	False
 			ReuseUniqueNodes:	True
 			Fusion:	False
-	Module
-		Name:	Control.Monad.State
-		Dir:	{Application}/lib/iTasks-SDK/Dependencies/Platform/OS-Independent
-		Compiler
-			NeverMemoryProfile:	False
-			NeverTimeProfile:	False
-			StrictnessAnalysis:	True
-			ListTypes:	StrictExportTypes
-			ListAttributes:	True
-			Warnings:	True
-			Verbose:	True
-			ReadableABC:	False
-			ReuseUniqueNodes:	True
-			Fusion:	False
-	Module
-		Name:	Control.Monad.Trans
-		Dir:	{Application}/lib/iTasks-SDK/Dependencies/Platform/OS-Independent
-		Compiler
-			NeverMemoryProfile:	False
-			NeverTimeProfile:	False
-			StrictnessAnalysis:	True
-			ListTypes:	StrictExportTypes
-			ListAttributes:	True
-			Warnings:	True
-			Verbose:	True
-			ReadableABC:	False
-			ReuseUniqueNodes:	True
-			Fusion:	False
 	Module
 		Name:	Data.Either
 		Dir:	{Application}/lib/iTasks-SDK/Dependencies/Platform/OS-Independent
@@ -419,20 +391,6 @@ OtherModules
 			ReadableABC:	False
 			ReuseUniqueNodes:	True
 			Fusion:	False
-	Module
-		Name:	Data.Functor.Identity
-		Dir:	{Application}/lib/iTasks-SDK/Dependencies/Platform/OS-Independent
-		Compiler
-			NeverMemoryProfile:	False
-			NeverTimeProfile:	False
-			StrictnessAnalysis:	True
-			ListTypes:	StrictExportTypes
-			ListAttributes:	True
-			Warnings:	True
-			Verbose:	True
-			ReadableABC:	False
-			ReuseUniqueNodes:	True
-			Fusion:	False
 	Module
 		Name:	Data.List
 		Dir:	{Application}/lib/iTasks-SDK/Dependencies/Platform/OS-Independent