grammar.py 文件源码

def read_grammar(input, nonterm_parser, probabilistic=False, encoding=None):
    """
    Return a pair consisting of a starting category and a list of
    ``Productions``.

    :param input: a grammar, either in the form of a string or else
        as a list of strings.
    :param nonterm_parser: a function for parsing nonterminals.
        It should take a ``(string, position)`` as argument and
        return a ``(nonterminal, position)`` as result.
    :param probabilistic: are the grammar rules probabilistic?
    :type probabilistic: bool
    :param encoding: the encoding of the grammar, if it is a binary string
    :type encoding: str
    """
    if encoding is not None:
        input = input.decode(encoding)
    if isinstance(input, string_types):
        lines = input.split('\n')
    else:
        lines = input

    start = None
    productions = []
    continue_line = ''
    for linenum, line in enumerate(lines):
        line = continue_line + line.strip()
        if line.startswith('#') or line=='': continue
        if line.endswith('\\'):
            continue_line = line[:-1].rstrip()+' '
            continue
        continue_line = ''
        try:
            if line[0] == '%':
                directive, args = line[1:].split(None, 1)
                if directive == 'start':
                    start, pos = nonterm_parser(args, 0)
                    if pos != len(args):
                        raise ValueError('Bad argument to start directive')
                else:
                    raise ValueError('Bad directive')
            else:
                # expand out the disjunctions on the RHS
                productions += _read_production(line, nonterm_parser, probabilistic)
        except ValueError as e:
            raise ValueError('Unable to parse line %s: %s\n%s' %
                             (linenum+1, line, e))

    if not productions:
        raise ValueError('No productions found!')
    if not start:
        start = productions[0].lhs()
    return (start, productions)