import ply.lex as lex
keywords = (
    'int','String'
    )
tokens = (
    'NAME','NUMBER','INT','STRING','STRING_LIT','COMMENT','NEWLINE'
    )

literals = ['=','+','-','*','/', '(',')','{','}','[',']',';','%']

# Tokens

t_ignore     = " \t"
t_STRING     = r'"[a-zA-Z0-9_]*"'
t_COMMENT    = r'//'
def t_NAME(t):
    r'[a-zA-Z_][a-zA-Z0-9_]*'
    if t.value in keywords:
        t.type = t.value.upper()
    return t
def t_NUMBER(t):
    r'\d+'
    try:
        t.value = int(t.value)
    except ValueError:
        print ("Integer value too large", t.value)
        t.value = 0
    return t

def t_NEWLINE(t):
    r'\n+'
    t.lexer.lineno += t.value.count("\n")
    t.value='\n'
    return t
def t_NEWLINEr(t):
    r'\r+'
    t.lexer.lineno += t.value.count("\r")
    t.type="NEWLINE"
    t.value='\r'
    return t
def t_error(t):
    print( "Illegal character '%s'" % t.value[0])

    
# Build the lexer
lex.lex()
#lex.input("int skai;\nint lol=skai\ngetKey();")
lex.input(open(input("FILE >> ")).read())
out=""
data=""
lastToken=""
nextSlot=500  #500 bytes after program (change if needed)
names = {}
def getToken():
    global lastToken, lex
    lastToken=lex.token()
    return lastToken
inComment=False
jmploc=[]
while(lastToken!=None):
    token=getToken()
    if(token==None):
        break;
    if(token.value=='\n' or token.value=='\r'):
        inComment=False
        continue;
    if(token.value=="//"):
        inComment=True
    if(inComment):
        continue;
    if(token.type=='INT'):
        names[getToken().value]=nextSlot
        nextSlot+=1
        name=lastToken.value
        t=getToken()
        if(t.value!=';'):
            t=getToken()
            if(t.type=="NUMBER"):
                out+=chr(6)+chr(0)+chr(t.value)
            elif(t.type=="NAME" and t.value in names):
                out+=chr(14)+chr(names[t.value]&255)+chr(names[t.value]>>8)                        # LD SI, input
                out+=chr(15)+chr(names[name]&255)+chr(names[name]>>8)                              # LD DI, output
                out+=chr(0x2B)+chr(0x2A)                                                           # LOD / STO
            getToken()
            if(lastToken==None or lastToken.value!=';'):
                print("missing semicolon maybe? line: "+str(lastToken.lineno))
    elif(token.value=="getKey"):
        if(getToken().value=='('):
            if(getToken()!=None and lastToken.value==')'):
                print("getKey returns to nothing!  line: "+str(lastToken.lineno))
            elif(lastToken!=None):
                out+=chr(0xF0)                                                                     # KBD AL
                out+=chr(0x70)+chr(names[lastToken.value]&255)+chr(names[lastToken.value]>>8)      # LD [output], AL
                getToken()
            else:
                print("error: EOF while parsing.")
                break;
        else:
            print("getKey is no literal! Missing parenthesis? line: "+str(lastToken.lineno))
        getToken()
        if(lastToken==None or lastToken.value!=';'):
            print("missing semicolon maybe? line: "+str(lastToken.lineno))
    elif(token.value=="outS"):
        if(getToken().value=='('):
            if(getToken()!=None and lastToken.value==')'):
                print("outS has no input!  line: "+str(lastToken.lineno))
            elif(lastToken!=None):
                out+=chr(0x90)+chr(names[lastToken.value]&255)+chr(names[lastToken.value]>>8)      # LD AL, [input]
                out+=chr(0x80)                                                                     # WRT AL
                getToken()
            else:
                print("error: EOF while parsing.")
                break;
        else:
            print("outS is no literal! Missing parenthesis? line: "+str(lastToken.lineno))
        getToken()
        if(lastToken==None or lastToken.value!=';'):
            print("missing semicolon maybe? line: "+str(lastToken.lineno))
    elif(token.value=='%'):
        token=getToken()
        if(token.value.upper()=="MEMSTART"):
            token=getToken()
            if(token.type!="NUMBER"):
                print("Invalid value for definition 'MEMSTART' at line "+str(token.lineno))
                continue;
            nextSlot=token.value
        else:
            print("invalid '%' 'definition'. line: "+str(token.lineno))
    elif(token.value=="while"):
        if(getToken().value=='('):
            if(getToken()!=None and lastToken.value==')'):
                print("while statement has no condition!  line: "+str(lastToken.lineno))
            elif(lastToken!=None):
                name=lastToken.value
                getToken()
                if(getToken().value=='{'):
                    tmp=chr(0x90)+chr(names[name]&255)+chr(names[name]>>8)       # LD AL, [input]
                    tmp+=chr(0xD0)+chr(len(out)-1&255)+chr(len(out)-2>>8)        # JPZ start_of_while_loop
                    out+=chr(0x90)+chr(names[name]&255)+chr(names[name]>>8)      # LD AL, [input]
                    out+=chr(0x4A)+chr(0)+chr(1)                                 # CP  AL, 1
                    out+=chr(0xD0)+chr(len(out)-1&255)+chr(len(out)-2>>8)        # JP  end_of_while_loop
                    jmploc.append([tmp,len(out)-2])
                elif(lastToken.value==';'):
                    out+=chr(0xC3)+chr(len(out)-1&255)+chr(len(out)-2>>8)        # JMP $
            else:
                print("error: EOF while parsing.")
                break;
        else:
            print("while is no literal! Missing parenthesis? line: "+str(lastToken.lineno))
    elif(token.value=='}'):
        t=jmploc.pop()
        out+=t[0]
        out = out[:t[1]] + chr(len(out)>>8) + out[t[1]+1:]
        out = out[:t[1]+1] + chr(len(out)&255) + out[t[1]+2:]
    else:
        print("strange token '"+token.value+"' , line "+str(token.lineno))