prog8/parser/antlr/Prog8ANTLR.g4

/*
Prog8 combined lexer and parser grammar

NOTES:

- whitespace is ignored. (tabs/spaces)
- every position can be empty, be a comment, or contain ONE statement.

*/

// -> java classes Prog8ANTLRParser and Prog8ANTLRLexer,
// both NOT to be used from Kotlin code, but ONLY through Kotlin class Prog8Parser
grammar Prog8ANTLR;

@header {
package prog8.parser;
}

EOL :  ('\r'? '\n' | '\r' | '\n')+ ;
LINECOMMENT : EOL [ \t]* COMMENT -> channel(HIDDEN);
COMMENT :  ';' ~[\r\n]* -> channel(HIDDEN) ;
BLOCK_COMMENT : '/*' ( BLOCK_COMMENT | . )*? '*/'  -> skip ;

WS :  [ \t] -> skip ;
// WS2 : '\\' EOL -> skip;
VOID: 'void';
NAME :  [\p{Letter}][\p{Letter}\p{Mark}\p{Digit}_]* ;           // match unicode properties
UNDERSCORENAME :  '_' NAME ;           // match unicode properties
DEC_INTEGER :  DEC_DIGIT (DEC_DIGIT | '_')* ;
HEX_INTEGER :  '$' HEX_DIGIT (HEX_DIGIT | '_')* ;
BIN_INTEGER :  '%' BIN_DIGIT (BIN_DIGIT | '_')* ;
ADDRESS_OF: '&' ;
INVALID_AND_COMPOSITE: '&&' ;

fragment HEX_DIGIT: ('a'..'f') | ('A'..'F') | ('0'..'9') ;
fragment BIN_DIGIT: ('0' | '1') ;
fragment DEC_DIGIT: ('0'..'9') ;

FLOAT_NUMBER :  FNUMBER (('E'|'e') ('+' | '-')? DEC_INTEGER)? ;	// sign comes later from unary expression
FNUMBER : FDOTNUMBER |  FNUMDOTNUMBER ;
FDOTNUMBER : '.' (DEC_DIGIT | '_')+ ;
FNUMDOTNUMBER : DEC_DIGIT (DEC_DIGIT | '_')* FDOTNUMBER? ;

STRING_ESCAPE_SEQ :  '\\' . | '\\x' . . | '\\u' . . . .;
STRING :
	'"' ( STRING_ESCAPE_SEQ | ~[\\\r\n\f"] )* '"'
	;
INLINEASMBLOCK :
	'{{' .+? '}}'
	;

SINGLECHAR :
	'\'' ( STRING_ESCAPE_SEQ | ~[\\\r\n\f'] ) '\''
	;

ZEROPAGE : '@zp' ;

ZEROPAGEREQUIRE : '@requirezp' ;

ZEROPAGENOT: '@nozp' ;

SHARED : '@shared' ;

SPLIT: '@split' ;

ARRAYSIG :
    '[]'
    ;


// A module (file) consists of zero or more directives or blocks, in any order.
// If there are more than one, then they must be separated by EOL (one or more newlines).
// However, trailing EOL is NOT required.
// Note: the parser may see *several* consecutive EOLs - this happens when EOL and comments are interleaved (see #47)
module: EOL* ((directive | block) (EOL+ (directive | block))*)? EOL* EOF;

block: identifier integerliteral? EOL? '{' EOL? (block_statement | EOL)* '}';

block_statement:
	directive
	| variabledeclaration
	| subroutinedeclaration
	| inlineasm
	| inlineir
	| labeldef
	;


statement :
	directive
	| variabledeclaration
	| assignment
	| augassignment
	| unconditionaljump
	| postincrdecr
	| functioncall_stmt
	| if_stmt
	| branch_stmt
	| subroutinedeclaration
	| inlineasm
	| inlineir
	| returnstmt
	| forloop
	| whileloop
	| untilloop
	| repeatloop
	| unrollloop
	| whenstmt
	| breakstmt
	| continuestmt
	| labeldef
	;


variabledeclaration :
	varinitializer
	| vardecl
	| constdecl
	| memoryvardecl
    ;


subroutinedeclaration :
	subroutine
	| asmsubroutine
	| romsubroutine
    ;


labeldef :  identifier ':'  ;

unconditionaljump :  'goto'  (integerliteral | scoped_identifier) ;

directive :
	directivename=('%output' | '%launcher' | '%zeropage' | '%zpreserved' | '%zpallowed' | '%address' | '%import' |
                       '%breakpoint' | '%asminclude' | '%asmbinary' | '%option' | '%encoding' )
        (directivearg? | directivearg (',' directivearg)*)
        ;

directivearg : stringliteral | identifier | integerliteral ;

vardecl: datatype (arrayindex | ARRAYSIG)? decloptions identifier (',' identifier)* ;

decloptions: (SHARED | ZEROPAGE | ZEROPAGEREQUIRE | ZEROPAGENOT | SPLIT)* ;

varinitializer : vardecl '=' expression ;

constdecl: 'const' varinitializer ;

memoryvardecl: ADDRESS_OF varinitializer;

datatype:  'ubyte' | 'byte' | 'uword' | 'word' | 'float' | 'str' | 'bool' ;

arrayindex:  '[' expression ']' ;

assignment :  (assign_target '=' expression) | (assign_target '=' assignment) | (multi_assign_target '=' expression);

augassignment :
	assign_target operator=('+=' | '-=' | '/=' | '*=' | '&=' | '|=' | '^=' | '%=' | '<<=' | '>>=' ) expression
	;

assign_target:
	scoped_identifier               #IdentifierTarget
	| arrayindexed                  #ArrayindexedTarget
	| directmemory                  #MemoryTarget
	;

multi_assign_target:
    assign_target (',' assign_target)+ ;

postincrdecr :  assign_target  operator = ('++' | '--') ;

expression :
	'(' expression ')'
	| functioncall
	| <assoc=right> prefix = ('+'|'-'|'~') expression
	| left = expression EOL? bop = ('*' | '/' | '%' ) EOL? right = expression
	| left = expression EOL? bop = ('+' | '-' ) EOL? right = expression
	| left = expression EOL? bop = ('<<' | '>>' ) EOL? right = expression
	| left = expression EOL? bop = '&' EOL? right = expression
	| left = expression EOL? bop = '^' EOL? right = expression
	| left = expression EOL? bop = '|' EOL? right = expression
	| left = expression EOL? bop = ('<' | '>' | '<=' | '>=') EOL? right = expression
	| left = expression EOL? bop = ('==' | '!=') EOL? right = expression
	| rangefrom = expression rto = ('to'|'downto') rangeto = expression ('step' rangestep = expression)?	// can't create separate rule due to mutual left-recursion
	| left = expression EOL? bop = 'in' EOL? right = expression
	| left = expression EOL? bop = ('not in ' | 'not in\t' | 'not in\n' | 'not in\r') EOL? right = expression
	| prefix = 'not' expression
	| left = expression EOL? bop = 'and' EOL? right = expression
	| left = expression EOL? bop = 'or' EOL? right = expression
	| left = expression EOL? bop = 'xor' EOL? right = expression
	| literalvalue
	| scoped_identifier
	| arrayindexed
	| directmemory
	| addressof
	| expression typecast
	;

arrayindexed:
    scoped_identifier arrayindex
    ;


typecast : 'as' datatype;

directmemory : '@' '(' expression ')';

addressof : <assoc=right> ADDRESS_OF (scoped_identifier | arrayindexed) ;


functioncall : scoped_identifier '(' expression_list? ')'  ;

functioncall_stmt : VOID? scoped_identifier '(' expression_list? ')'  ;

expression_list :
	expression (',' EOL? expression)*           // you can split the expression list over several lines
	;

returnstmt : 'return' expression? ;

breakstmt : 'break';

continuestmt: 'continue';

identifier :  NAME | UNDERSCORENAME | VOID;

scoped_identifier :  identifier ('.' identifier)* ;

integerliteral :  intpart=(DEC_INTEGER | HEX_INTEGER | BIN_INTEGER) ;

booleanliteral :  'true' | 'false' ;

arrayliteral :  '[' EOL? expression (',' EOL? expression)* EOL? ']' ;       // you can split the values over several lines

stringliteral : (encoding=NAME ':')? STRING ;

charliteral : (encoding=NAME ':')? SINGLECHAR ;

floatliteral :  FLOAT_NUMBER ;


literalvalue :
	integerliteral
	| booleanliteral
	| arrayliteral
	| stringliteral
	| charliteral
	| floatliteral
	;

inlineasm :  '%asm' EOL? INLINEASMBLOCK;

inlineir: '%ir' EOL? INLINEASMBLOCK;

inline: 'inline';

subroutine :
	'sub' identifier '(' sub_params? ')' sub_return_part? EOL? (statement_block EOL?)
	;

sub_return_part : '->' datatype  ;

statement_block :
	'{' EOL?
		(statement | EOL) *
	'}'
	;


sub_params :  vardecl (',' EOL? vardecl)* ;

asmsubroutine :
    inline? 'asmsub' asmsub_decl EOL? (statement_block EOL?)
    ;

romsubroutine :
    'romsub' integerliteral '=' asmsub_decl
    ;

asmsub_decl : identifier '(' asmsub_params? ')' asmsub_clobbers? asmsub_returns? ;

asmsub_params :  asmsub_param (',' EOL? asmsub_param)* ;

asmsub_param :  vardecl '@' register=NAME ;      // A,X,Y,AX,AY,XY,Pc,Pz,Pn,Pv allowed.

asmsub_clobbers : 'clobbers' '(' clobber? ')' ;

clobber :  NAME (',' NAME)* ;       // A,X,Y allowed

asmsub_returns :  '->' asmsub_return (',' EOL? asmsub_return)* ;

asmsub_return :  datatype '@' register=NAME ;     // A,X,Y,AX,AY,XY,Pc,Pz,Pn,Pv allowed


if_stmt :  'if' expression EOL? (statement | statement_block) EOL? else_part?  ; // statement is constrained later

else_part :  'else' EOL? (statement | statement_block) ;   // statement is constrained later


branch_stmt : branchcondition EOL? (statement | statement_block) EOL? else_part? ;

branchcondition: 'if_cs' | 'if_cc' | 'if_eq' | 'if_z' | 'if_ne' | 'if_nz' | 'if_pl' | 'if_pos' | 'if_mi' | 'if_neg' | 'if_vs' | 'if_vc' ;


forloop :  'for' scoped_identifier 'in' expression EOL? (statement | statement_block) ;

whileloop:  'while' expression EOL? (statement | statement_block) ;

untilloop:  'do' (statement | statement_block) EOL? 'until' expression ;

repeatloop:  'repeat' expression? EOL? (statement | statement_block) ;

unrollloop:  'unroll' expression EOL? (statement | statement_block) ;      // note: expression must evaluate to a constant

whenstmt: 'when' expression EOL? '{' EOL? (when_choice | EOL) * '}' EOL? ;

when_choice:  (expression_list | 'else' ) '->' (statement | statement_block ) ;