#!/usr/bin/env python3

import ply.lex as lex

# List of token names.   This is always required
tokens = (
   'OP',
   'JUMP',
   'COMMA',
   'COLON',
   'SYMBOL',
   'NUMBER',
   'HEXNUMBER',
   'DOT',
   'REG',
   'NL'
)

# Regular expression rules for simple tokens
t_COMMA   = r','
t_COLON   = r':'
t_DOT     = r'\.'

def t_OP(t):
    r"mov|and|dec|hlt|add|sub|inc"
    return t

def t_REG(t):
    r"\b(AD?M?|DM?|M|_)\b"
    return t

def t_JUMP(t):
    r"jmp|jlt|jgt|jle|jge|jeq|jne"
    return t

def t_NUMBER(t):
    r'\#\d+'
    t.value = int(t.value[1:])
    return t

def t_HEXNUMBER(t):
    r'\#0x[0-9a-fA-F]+'
    t.value = int(t.value[1:], 16)
    return t

def t_SYMBOL(t):
    r'[a-z][A-Za-z0-9_]+'
    return t

# Define a rule so we can track line numbers
def t_NL(t):
    r'\n+'
    t.lexer.lineno += len(t.value)
    return t

# A string containing ignored characters (spaces and tabs)
t_ignore  = ' \t'
#t_ignore_COMMENT = r';.*'

def t_COMMENT(t):
    r';.*'
    pass

# Error handling rule
def t_error(t):
    print("!!! Illegal character '%s'" % t.value[0])
    t.lexer.skip(1)

# EOF handling rule
def t_eof(t):
    if not t.lexer.newline_added:
        t.lexer.input("\n")
        t.lexer.newline_added = True
        return t.lexer.token()
    return None

# Build the lexer
lexer = lex.lex()
lexer.newline_added = False