javacc MIPS syntactic analyzer

Makefile

all:
	javacc *.jj
	javac *.java
clean:
	rm -f *.java *.class

syntactic.jj

// ---------------------------------------------------------
// MIPS syntactic analyser
// ---------------------------------------------------------

options {
      STATIC = false; 
}
PARSER_BEGIN(Somador)
      class Somador {
           static public void main( String[] args )
           throws ParseException, TokenMgrError {
                /* Estas classes serao geradas pelo JavaCC */
                Somador parser = new Somador( System.in ) ;
                parser.Start();
            }
      }
PARSER_END(Somador)

// ---------------------------------------------------------
// Lexico
// ---------------------------------------------------------


SKIP  : { " " | "\t" | "\r" | "\n" | "\r\n" }
SKIP  : {< "#" (~["\n"])* > }

TOKEN : { < T_MOVE : "move "                     >}
TOKEN : { < T_ADD : "add "                       >}
TOKEN : { < T_ADDU : "addu "                     >}
TOKEN : { < T_SUBU : "subu "                     >}
TOKEN : { < T_LOAD_IMMEDIATE : "li "             >}
TOKEN : { < T_LOAD_ADDRESS : "la "               >}
TOKEN : { < T_LOAD_WORD : "lw "                  >}
TOKEN : { < T_STORE_WORD : "sw "                 >}
TOKEN : { < T_JUMP : "j "                        >}
TOKEN : { < T_MULT : "mult "                     >}
TOKEN : { < T_MFLO : "mflo "                     >}
TOKEN : { < T_MFHI : "mfhi "                     >}
TOKEN : { < T_DIV : "div "                     >}
TOKEN : { < T_SYSCALL : "syscall"                >}
TOKEN : { < LETTER  : ["a"-"z", "A"-"Z"]           >}                              
TOKEN : { < DIGIT   : ["0"-"9"]                    >}                                
TOKEN : { < LABEL   : <LETTER>(<LETTER>|<DIGIT>)*  >}      
TOKEN : { < INT_NUM : (["+", "-"])* (["0"-"9"])+   >}          
TOKEN : { < ASPAS   : "\"" > }
TOKEN : { < STR     : "\""(~["\"","\n","\r"])* "\"">}

TOKEN : { < T_DATA_DIRECTIVE :".data"           >}
TOKEN : { < T_SPACE_DIRECTIVE :".space"         >}
TOKEN : { < T_BYTE_DIRECTIVE :".byte"           >}
TOKEN : { < T_HALF_DIRECTIVE :".half"           >}
TOKEN : { < T_WORD_DIRECTIVE :".word"           >}
TOKEN : { < T_ASCIIZ_DIRECTIVE :".asciiz"       >}
TOKEN : { < T_TEXT_DIRECTIVE :".text"           >}
TOKEN : { < T_GLOBL_DIRECTIVE :".globl"         >}
TOKEN : { < T_REG : "$zero" | "$at" | "$v0" | "$v1" | "$a0" | "$a1" | "$a2" | "$a3" | "$t0" | "$t1" | "$t2" | "$t3" | "$t4" | "$t5" | "$t6" | "$t7" | "$s0" | "$s1" | "$s2" | "$s3" | "$s4" | "$s5" | "$s6" | "$s7" | "$t8" | "$t9" | "$k0" | "$k1" | "$gp" | "$sp" | "$fp" | "$ra">}
TOKEN : { < T_COLON :  ":"                      >}
TOKEN : { < T_COMMA :  ","                      >}
TOKEN : { < T_LB :"("                           >}
TOKEN : { < T_RB :  ")"                         >}


// EOF : Retornado pelo implicitamente

// ---------------------------------------------------------
// Sintatico
// ---------------------------------------------------------
void Start() : {
}

{ 
  (Expressao() <EOF> )* <EOF> 
}

void Expressao():{
}

{
  
  <T_DATA_DIRECTIVE>
  (<LABEL><T_COLON> (<T_SPACE_DIRECTIVE><INT_NUM> | <T_ASCIIZ_DIRECTIVE><STR>))*
  <T_TEXT_DIRECTIVE>
  (<LABEL><T_COLON>
    (
       (<T_MOVE>           <T_REG><T_COMMA><T_REG>)
      |(<T_ADD>            <T_REG><T_COMMA><T_REG><T_COMMA><T_REG>)
      |(<T_ADDU>           <T_REG><T_COMMA><T_REG>)
      |(<T_DIV>            <T_REG><T_COMMA><T_REG>)
      |(<T_SUBU>           <T_REG><T_COMMA><T_REG>)
      |(<T_LOAD_IMMEDIATE> <T_REG><T_COMMA>(<INT_NUM>| <DIGIT>))
      |(<T_LOAD_ADDRESS>   <T_REG><T_COMMA><LABEL>)
      |(<T_LOAD_WORD>      <T_REG><T_COMMA>(<INT_NUM>| <DIGIT>)<T_LB><T_REG><T_RB>)
      |(<T_STORE_WORD>     <T_REG><T_COMMA>(<INT_NUM>| <DIGIT>)<T_LB><T_REG><T_RB>)
      |(<T_JUMP>           <T_REG><T_COMMA><T_REG>)
      |(<T_MULT>           <T_REG><T_COMMA><T_REG>)
      |(<T_MFLO>           <T_REG>)
      |(<T_MFHI>           <T_REG>)
      |(<T_SYSCALL>)
    )*
  )*
}