pyc64list.py

# c64list clone in python 2.7
# heavily based on https://ruslanspivak.com/lsbasi-part6/

petscii = """ !"#$%&'()*+,-./0123456789:;<=>?@abcdefghijklmnopqrstuvwxyz[~]^_ ABCDEFGHIJKLMNOPQRSTUVWXYZ"""

keywords = (' ',  'end', 'for', 'next', 'input#', 'print')

tokens   = (0x20, 0x80,  0x81,  0x82,   0x83,     0x99)

ignore_whitespace = False

"""
I've decided to leave " out of tokens, since quoted strings
seem like a whole class unto themselves, needs additional
processing
"""


def parse_line(data):
    # empty line
    if not data:
        print "Empty line"
        return None
    return Lexer.get_next_token(data)


class Lexer(object):
    def __init__(self, text):
        # client string input, e.g. 'print "hello"'
        self.keywords = None
        self.text = text
        # self.pos is an index into self.text
        self.pos = 0
        self.current_char = self.text[self.pos]

        # current list of tokenized bytes:
        self.token_output = []

    def error(self):
        raise Exception('Invalid character')

    def advance(self):
        """Advance the 'pos' pointer and set the 'current_char' variable."""
        self.pos += 1
        if self.pos > len(self.text) - 1:
            self.current_char = None  # Indicates end of input
        else:
            self.current_char = self.text[self.pos]

    def skip_whitespace(self):
        if not ignore_whitespace:
            while self.current_char is not None and self.current_char.isspace():
                self.advance()

    def get_next_token(self):
        """Lexical analyzer (also known as scanner or tokenizer)
        This method is responsible for breaking a sentence
        apart into tokens, one token at a time.
        """
        while self.current_char is not None:

            if self.current_char.isspace():
                self.skip_whitespace()
                continue

            # search for defined keywords:
            kw = self.keywords
            if kw:
                # token found. add it to output list:
                self.token_output.append(tokens.index(keywords))
                # advance 'pos' by as many chars are in keyword:
                for i in len(kw):
                    self.advance()
                return self.keywords(tokens)
            else:
                return None


class Interpreter(object):
    def __init__(self, lexer):
        self.lexer = lexer
        # set current token to the first token taken from the input
        self.current_token = self.lexer.get_next_token()

    def error(self):
        raise Exception('Invalid syntax')

    def eat(self, token_type):
        # compare the current token type with the passed token
        # type and if they match then "eat" the current token
        # and assign the next token to the self.current_token,
        # otherwise raise an exception.
        if self.current_token.type == token_type:
            self.current_token = self.lexer.get_next_token()
        else:
            self.error()


def main():
    while True:
        try:
            # To run under Python3 replace 'raw_input' call
            # with 'input'
            text = raw_input('pyc64list> ')
        except EOFError:
            break
        if not text:
            continue
        lexer = Lexer(text)
        interpreter = Interpreter(lexer)
        result = interpreter.text
        print(result)


if __name__ == '__main__':
    main()