I'm an amateur with ANTLR and I'm creating an interpreter for a simple processor and I have run into a small issue with the VALUE token throwing errors. I'm a student, so I'm not asking you to do my homework for me...I've pretty much completed it (including all class files for the interpreter) but this one issue is defeating me even though it's likely simple and staring me right in the face.
ANTLR works keeps giving me this console error message;
"error(208): newExpr.g:193:1: The following token definitions can never be matched because prior tokens match the same input: VALUE"
Clearly there is something wrong with the regular expressions for VALUE but I can't see what it is, either there or anywhere else in the grammar. If you could point out what I'm missing it would be much appreciated...as googling hasn't really helped me find the error in my own grammar.
grammar newExpr;
options
{
language=Java;
}
@header
{
import java.util.*;
}
@members
{
ArrayList myInitialise = new ArrayList();
ArrayList InstructionList = new ArrayList();
}
/*--------------------------------------------------------------------------------------------------------------------------------*
* PARSER RULES *
*--------------------------------------------------------------------------------------------------------------------------------*//
/*
* prog is where the interpretation beings and consists of one or more (+) 'stat' rules
*/
prog : stat+;
/*
* stat rules are the general parse rules of entire operations on the processor.
* They consist of smaller data operations rules (dataop) or memory operations (memop).
*/
stat : BASIC r1=REG c1=COMMA r2=REG c2=COMMA dataop NEWLINE
{
int reg1 = Integer.parseInt($r1.text.substring(1)); // these lines convert the token input stream and converts to an actual integer
int reg2 = Integer.parseInt($r2.text.substring(1));
int IMDT = $dataop.value; // take the immediate integer
// LOAD operation
if($BASIC.text.equals("LD"))
InstructionList.add(new ld(reg1, reg2, IMDT));
// STORE operation
else if($BASIC.text.equals("ST"))
InstructionList.add(new st(reg1, reg2, IMDT));
// SUBTRACTION operation
else if($BASIC.text.equals("SUB"))
InstructionList.add(new sub(reg1, reg2, IMDT));
// ADDITION operation
else if($BASIC.text.equals("ADD"))
InstructionList.add(new add(reg1, reg2, IMDT));
// MULTIPLICATION operation
else if($BASIC.text.equals("MUL"))
InstructionList.add(new mul(reg1, reg2, IMDT));
// DIVISION operation
else if($BASIC.text.equals("DIV"))
InstructionList.add(new div(reg1, reg2, IMDT));
}
|
i1 = INDEX '=' memop NEWLINE
{
myInitialise.add(new memInit(Integer.parseInt($i1.text), $dataop.value));
}
|
JUMP REG COMMA dataop NEWLINE
{
int R = Integer.parseInt($REG.text.substring(1));
int val = $dataop.value;
// BRANCH EQUAL operation
if($JUMP.text.equals("BEZ"))
InstructionList.add(new branchEqualZero(R,value));
// BRANCH NOT EQUAL operation
else if($JUMP.text.equals("BNEZ"))
InstructionList.add(new branchNotEqualZero(R,value));
}
|
JUMP REG NEWLINE
{
int R = Integer.parseInt($REG.text.substring(1));
InstructionList.add(new jump(R));
}
|
HALT
{
InstructionList.add(new halt());
}
;
dataop returns [int value]
: INDEX
{
$value = Integer.parseInt($INDEX.text);
}
|
VALUE
{
$value = Integer.parseInt($VALUE.text.substring(1))*-1;
};
memop returns [int value]
: INDEX
{
$value = Integer.parseInt($INDEX.text);
}
|
VALUE
{
$value = Integer.parseInt($VALUE.text.substring(1))*-1;
}
|
MEMVAL
{
if($MEMVAL.text.startsWith("-"))
{
$value = Integer.parseInt($MEMVAL.text.substring(1))*-1;
}
else
$value = Integer.parseInt($MEMVAL.text);
};
/*--------------------------------------------------------------------------------------------------------------------------------*
* LEXER RULES *
*--------------------------------------------------------------------------------------------------------------------------------*/
/*
* RegExps for BASIC instructions (load, store, add, subtract, multiply, divide
*/
BASIC : ('L' 'D') | ('S' 'T') | ('A' 'D' 'D') | ('S' 'U' 'B') | ('M' 'U' 'L') | ('D' 'I' 'V');
/*
* The comma is simply for syntactic purposes, to separate data and register references
*/
COMMA : ',';
/*
* Regular Expressions for the processor registers R0-R31
*/
REG : ('R') (('0'..'9') | ('0'..'2') ('0'..'9') | ('3') ('0'..'1') );
/*
* 'Index' is the set of regular expressions matching memory locations
*/
INDEX : ('0'..'9')
|
('0'..'9') ('0'..'9')
|
('0'..'9') ('0'..'9') ('0'..'9')
|
('0'..'9') ('0'..'9') ('0'..'9') ('0'..'9')
|
('0'..'5') ('0'..'9') ('0'..'9') ('0'..'9') ('0'..'9')
|
('6') ('0'..'4') ('0'..'9') ('0'..'9') ('0'..'9')
|
('6') ('5') ('0'..'4') ('0'..'9') ('0'..'9')
|
('6') ('5') ('5') ('0'..'2') ('0'..'9')
|
('6') ('5') ('5') ('3') ('0'..'5');
/*
* Reg Exps for memory initialisation instructions
*/
MEMVAL : ('0'..'9')+ | '-' ('0'..'9')+;
/*
* Simple integers for data values
*/
VALUE : '-' (('0'..'9') **PROBLEM IS HERE**
|
('0'..'9') ('0'..'9')
|
('0'..'9') ('0'..'9') ('0'..'9')
|
('0'..'9') ('0'..'9') ('0'..'9') ('0'..'9')
|
('0'..'5') ('0'..'9') ('0'..'9') ('0'..'9') ('0'..'9')
|
('6') ('0'..'4') ('0'..'9') ('0'..'9') ('0'..'9')
|
('6') ('5') ('0'..'4') ('0'..'9') ('0'..'9')
|
('6') ('5') ('5') ('0'..'2') ('0'..'9')
|
('6') ('5') ('5') ('3') ('0'..'6'));
/*
* Regular Expressions for return/newline characters
*/
NEWLINE : '\r'? '\n' ;
/*
* This simply makes the interpreter tolerant to whitespace
*/
WHITESPACE : (' ' | '\t' | '\u000C')+ {skip();};
/*
* RegExp for Branch on Equal to Zero/Branch on Not Equal to Zero instructions
*/
BRANCH : ('B' 'E' 'Z') | ('B' 'N' 'E' 'Z');
/*
* RegExp for jump instruction
*/
JUMP : ('J' 'R');
/*
* The HALT instruction ends the program and executes all instructions
* in the Instruction List on the data/values that have been entered
*/
HALT : ('H' 'A' 'L' 'T');
