#!/bin/env python

# 2.3 imports
from optparse import OptionParser

# our imports
import lex


class NasmGrammar(lex.Grammar):

    GRAMMAR_LIST = [
        {'name': 'keyword',
         'expr': \
         r"""(?:section|global|extern)(?![a-zA-Z_])""",
         'action': lex.make_token},
        
        {'name': "nasm macros",
         'expr': r"%(?:define|undef|assign|strlen|macro|endmacro|if|elif|else|endif|ifdef|ifndef|include|push|pop|stacksize)(?![a-zA-Z_])",
         'action': lex.make_token
         },

        {'name': "instructions",
         'expr': \
         r"""(?:jeq|jne|ja|jmp|push|pushad|pushfd|call|ret|sub|add|pop|popa|popad|popfd|call|and|cwd|cdq|cmp|cmpxchg|cpuid|div|divpd|enter|leave|fadd|fld|fmul|fsqrt|fsub|hlt|imul|inc|int|int3|lea|mov|movd|mul|neg|not|nop|or|sal|sar|shl|shr|shld|shrd|syscall|sysenter|sysexit|test|xchg|xadd|xor)(?![a-zA-Z_])""",
         'action': lex.make_token},

        {'name': "registers",
         'expr': \
         r"""(?:eax|ax|ah|al|ebx|bx|bh|bl|ecx|cx|ch|cl|esi|edi|esp|ebp)""",
         'action': lex.make_token},

        {'name': "prefix",
         'expr': r"(?:dword|word|lock)",
         'action': lex.make_token
        },

        {'name': "label",
         'expr': r"[a-zA-Z_.][a-zA-Z0-9_.]*:",
         'action': lex.make_token},
        
        {'name': "identifier",
         'expr': r"[a-zA-Z_][a-zA-Z0-9_]*",
         'action': lex.make_token},
        
        {'name': "integer",
         'expr': r"(0|[1-9][0-9]*|0[0-7]+|0[xX][0-9a-fA-F]+)[lL]?",
         'action': lex.make_token},
        
        {'name': "float",
         'expr': \
         r"""[0-9]+\.[0-9]*|\.[0-9]+|([0-9]|
         [0-9]+\.[0-9]*|\.[0-9]+)[eE][\+-]?[0-9]+""",
         'action': lex.make_token},
        
        {'name': "string3",
         'expr': r'"""[.|\n]*?(?:"""|$)',
         'action': lex.make_token},
        
        {'name': "string1",
         'expr': r'"(?:\\.|[^\\"])*(?:"|$)',
         'action': lex.make_token},
        
        {'name': "string2",
         'expr': r"'(?:\\.|[^\\'])*(?:'|$)",
         'action': lex.make_token},
        
        {'name': "comment",
         'expr': r'[;].*(?:\n|$)',
         'action': lex.make_token},

        {'name': "default",
         'expr': r'\\.|.|\n',
         'action': lex.silent}
        ]

    def _default_rules(self):
        """subclasses can override this to define defaults for a grammar"""
        for rdir in NasmGrammar.GRAMMAR_LIST:
            self.add_rule(**rdir)
        
if __name__ == "__main__":
    usage = "%%prog <file> [<file> ...]\n\n" \
            "Lex one or more files according to the python grammar"
    parser = OptionParser(usage=usage)
    (options, args) = parser.parse_args()
    g = NasmGrammar()
    l = lex.Lexer(grammar=g)

    for path in args:
        f = open(path, 'r')
        data = f.read()
        f.close()

        print "Lexing %s:" % (path)
        l.lex(data)

        for x in l:
            if x is not None:
                print x