使用PLY 构建一个汇编器(1)

ORG_DATA  0000           ;The start address of data
BUF   DW  00FF, 5500
NEXT  DW  0CFF, 5D00
ORG_CODE  0000		       ;The start address of code
start:  addi  $t0, $Zero,      ;A label for the first statement,$t0=0
 	lw    $v0, BUF($t0)      ;$v0=00FF  (BUF[0])
 	addi  $t0, $t0, 2
 	lw	  $v1, BUF($t0)	 ;$v1=5500  (BUF[2])
 	add   $v0, $v0, $v1	;$v0=$v0+$v1=55FF
 	addi  $t0, $t0, 2
 	sw    $v0, BUF($t0)    	;BUF[4]=55FF
 	j	  start
end  start

tokens =  [
	'IDENTIFIER', 'NUMBER','REG',
	'ORG_DATA', 'ORG_CODE', 'DW', 'END',
	'ADD', 'ADDU', 'SUB', 'SUBU', 'AND', 'OR', 'XOR', 'NOR', 'SLT', 'SLTU',
	'SLL', 'SRL', 'SRA',
	'SLLV', 'SRLV', 'SRAV',
	'JR',
	'ADDI','ADDIU','ANDI','ORI', 'XORI',
	'LUI',
	'LW', 'SW',
	'BEQ', 'BNE', 'SLTI', 'SLTIU',
	'J', 'JAL']
 
literals = [ ':',',','(',')' ]
 
def t_NUMBER(t):
	r'[0-9][a-fA-F0-9]*'
	try:
		t.value = int(t.value,16);
	except ValueError:
		print "Number %s is bad!" % t.value
		t.value = 
	return t		
 
def t_COMMENT(t):
	r';.*'
	pass
 
reserved  = {
	"add"		:"ADD",
	"addu"		:"ADDU",
	"sub"		:"SUB",
	"subu"		:"SUBU",
	"and"		:"AND",
	"or"		:"OR",
	"xor"		:"XOR",
	"nor"		:"NOR",
	"slt"		:"SLT",
	"sltu"		:"SLTU",
	"sll"		:"SLL",
	"srl"		:"SRL",
	"sra"		:"SRA",
	"sllv"		:"SLLV",
	"srlv"		:"SRLV",
	"srav"		:"SRAV",
	"jr"		:"JR",
	"addi"		:"ADDI",
	"addiu"		:"ADDIU",
	"ori"		:"ORI",
	"xori"		:"XORI",
	"lui"		:"LUI",
	"lw"		:"LW",
	"sw"		:"SW",
	"beq"		:"BEQ",
	"bne"		:"BNE",
	"slti"		:"SLTI",
	"sltiu"		:"SLTIU",
	"j"			:"J",
	"jal"		:"JAL",
	"ORG_DATA" 	:"ORG_DATA",
	"ORG_CODE" 	:"ORG_CODE",
	"DW" 		:"DW",
	"end"		:"END",
}
 
def t_IDENTIFIER(t):
	r'\b[a-zA-Z_][a-zA-Z_0-9]*'
	t.type = reserved.get(t.value,'IDENTIFIER')    # Check for reserved words
	return t	
 
def t_REG(t):
	r'\$[a-zA-Z_0-9]*'
	return t
 
def t_newline(t):
	r'\n+'
	t.lexer.lineno += len(t.value)
 
t_ignore  = ' \t\v'
 
def t_error(t):
    print "Illegal character '%s' on line %d " % (t.value[],t.lexer.lineno)
    t.lexer.skip(1)
 
# Compute column.
#     input is the input text string
#     token is a token instance
def find_column(input,token):
    i = token.lexpos
    while i > :
        if input[i] == '\n': break
        i -= 1
    column = (token.lexpos - i)+1
    return column