module languages/java/syntax/Lexical

imports basic/Whitespace
imports basic/NatCon

exports 

  sorts Identifier Literal NullLiteral StringLiteral
        CharacterLiteral BooleanLiteral FloatingPointLiteral IntegerLiteral
        OctalIntegerLiteral HexIntegerLiteral DecimalIntegerLiteral
        StringCharacter EscapeSequence UnicodeEscape SingleCharacter
	DecimalLongLiteral HexLongLiteral OctalLongLiteral LongLiteral
	DoubleLiteral

  context-free syntax
    "@"NatCon 			-> Identifier {avoid}

  lexical syntax
    "\\" [u]+ [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] -> UnicodeEscape

    "0" 			-> DecimalIntegerLiteral
    [1-9] [0-9]* 		-> DecimalIntegerLiteral
    [0] [xX] [0-9a-fA-F]+	-> HexIntegerLiteral
    [0] [0-7]+	 		-> OctalIntegerLiteral

    "0" [lL] 			-> DecimalLongLiteral
    [1-9] [0-9]* [lL] 		-> DecimalLongLiteral
    [0] [xX] [0-9a-fA-F]+ [lL] 	-> HexLongLiteral
    [0] [0-7]+ [lL] 		-> OctalLongLiteral

    [0-9]+ "." [0-9]* ( [eE] [\+\-]? [0-9]+ )? [fF] -> FloatingPointLiteral
    "." [0-9]+ ( [eE] [\+\-]? [0-9]+ )? [fF] -> FloatingPointLiteral
    [0-9]+ [eE] [\+\-]? [0-9]+ [fF] -> FloatingPointLiteral
    [0-9]+ ( [eE] [\+\-]? [0-9]+ )? [fF] -> FloatingPointLiteral

    [0-9]+ "." [0-9]* ( [eE] [\+\-]? [0-9]+ )? [dD]? -> DoubleLiteral
    "." [0-9]+ ( [eE] [\+\-]? [0-9]+ )? [dD]? -> DoubleLiteral
    [0-9]+ [eE] [\+\-]? [0-9]+ [dD]? -> DoubleLiteral
    [0-9]+ ( [eE] [\+\-]? [0-9]+ )? [dD] -> DoubleLiteral

    "true" -> BooleanLiteral
    "false" -> BooleanLiteral
    "null" -> NullLiteral
    UnicodeEscape -> SingleCharacter
    ~[\'\\] -> SingleCharacter
    "'" SingleCharacter "'" -> CharacterLiteral
    "\\" [btnfr\"\'\\] -> EscapeSequence
    "\\" [0-7] -> EscapeSequence
    "\\" [0-7] [0-7] -> EscapeSequence
    "\\" [0-3] [0-7] [0-7] -> EscapeSequence
    "'" EscapeSequence "'" -> CharacterLiteral
    UnicodeEscape -> StringCharacter
    ~[\"\\] -> StringCharacter
    EscapeSequence -> StringCharacter
    [A-Za-z\_\$] [A-Za-z0-9\_\$]* -> Identifier

    "" -> Identifier
    "" -> Identifier
    "" -> Identifier

    "void" -> Identifier {reject}
    "class" -> Identifier {reject}
    "extends" -> Identifier {reject}
    "implements" -> Identifier {reject}
    "static" -> Identifier {reject}
    "this" -> Identifier {reject}
    "super" -> Identifier {reject}
    "new" -> Identifier {reject}
    "instanceof" -> Identifier {reject}
    "interface" -> Identifier {reject}
    "true" -> Identifier {reject}
    "false" -> Identifier {reject}
    "null" -> Identifier {reject}
    "throws" -> Identifier {reject}
    "public" -> Identifier {reject}
    "protected" -> Identifier {reject}
    "private" -> Identifier {reject}
    "abstract" -> Identifier {reject}
    "final" -> Identifier {reject}
    "native" -> Identifier {reject}
    "synchronized" -> Identifier {reject}
    "transient" -> Identifier {reject}
    "volatile" -> Identifier {reject}
    "package" -> Identifier {reject}
    "import" -> Identifier {reject}
    "if" -> Identifier {reject}
    "else" -> Identifier {reject}
    "switch" -> Identifier {reject}
    "case" -> Identifier {reject}
    "default" -> Identifier {reject}
    "while" -> Identifier {reject}
    "do" -> Identifier {reject}
    "for" -> Identifier {reject}
    "break" -> Identifier {reject}
    "continue" -> Identifier {reject}
    "return" -> Identifier {reject}
    "throw" -> Identifier {reject}
    "try" -> Identifier {reject}
    "catch" -> Identifier {reject}
    "finally" -> Identifier {reject}


    "boolean" -> Identifier {reject}
    "byte" -> Identifier {reject}
    "short" -> Identifier {reject}
    "int" -> Identifier {reject}
    "long" -> Identifier {reject}
    "char" -> Identifier {reject}
    "float" -> Identifier {reject}
    "double" -> Identifier {reject}

    "\"" StringCharacter* "\"" -> StringLiteral {cons("StringCharacter-s")}

  lexical restrictions
    "void" "class" "extends" "implements" "static" "this" "super" "new" "instanceof" "interface" "true" "false" "null" "throws" "public" "protected" "private" "abstract" "final" "native" "synchronized" "transient" "volatile" "package" "import" "if" "else" "switch" "case" "default" "while" "do" "for" "break" "continue" "return" "throw" "try" "catch" "finally" "boolean" "byte" "short" "int" "long" "char" "float" "double" "" "" "" -/- [a-zA-Z0-9\_]
    Identifier -/- [a-zA-Z0-9\_\$]
    DecimalIntegerLiteral -/- [a-zA-Z0-9\_\.]
    HexIntegerLiteral -/- [a-zA-Z0-9\_\.]
    OctalIntegerLiteral -/- [a-zA-Z0-9\_\.]    
    DecimalLongLiteral -/- [a-zA-Z0-9\_\.]
    HexLongLiteral -/- [a-zA-Z0-9\_\.]
    OctalLongLiteral -/- [a-zA-Z0-9\_\.]
    FloatingPointLiteral -/- [a-zA-Z0-9\_\.]
    DoubleLiteral -/- [a-zA-Z0-9\_\.]

  context-free syntax
    DecimalIntegerLiteral 	-> IntegerLiteral {prefer,cons("DecimalIntegerLiteral")}
    HexIntegerLiteral 		-> IntegerLiteral {prefer,cons("HexIntegerLiteral")}
    OctalIntegerLiteral 	-> IntegerLiteral {prefer,cons("OctalIntegerLiteral")}
    IntegerLiteral 		-> Literal {prefer,cons("IntegerLiteral")}

    DecimalLongLiteral 	-> LongLiteral {prefer,cons("DecimalLongLiteral")}
    HexLongLiteral 	-> LongLiteral {prefer,cons("HexLongLiteral")}
    OctalLongLiteral 	-> LongLiteral {prefer,cons("OctalLongLiteral")}
    LongLiteral 	-> Literal {prefer,cons("LongLiteral")}

    FloatingPointLiteral 	-> Literal {prefer,cons("FloatingPointLiteral")}
    DoubleLiteral		-> Literal {prefer, cons("DoubleLiteral")}
    BooleanLiteral 		-> Literal {prefer,cons("BooleanLiteral")}
    CharacterLiteral 		-> Literal {prefer,cons("CharacterLiteral")}
    StringLiteral 		-> Literal {prefer,cons("StringLiteral")}
    NullLiteral 		-> Literal {prefer,cons("NullLiteral")}