lessonfile.py 文件源码

def rnc_markup_tokenizer(s):
    """
    [rn][mod1][num][\s-]
    """
    rn_re = re.compile(u"""(?P<p1>[b??#]?[ivIV]+)
                          (?P<p2>[^\d\s-]*)
                          (?P<p3>[^\s-]*)
                          (?P<sep>(\s*-\s*|\s*))""",
                       re.VERBOSE|re.UNICODE)
    i = 0
    retval = []
    while i < len(s):
        m = rn_re.match(s[i:])
        if not m:
            retval.append((u'ERR:%s' % s[i:], '', '', ''))
            break
        retval.append((m.group('p1'), m.group('p2'), m.group('p3'), m.group('sep')))
        i += m.end()
    return retval