fsa.py 文件源码

def u_to_utf8(dfa, base=0):
    c = itertools.count(base)
    transitions = dfa.transitions

    for src, trans in iteritems(transitions):
        trans = transitions[src]
        for label, dest in list(iteritems(trans)):
            if label is EPSILON:
                continue
            elif label is ANY:
                raise Exception
            else:
                assert isinstance(label, text_type)
                label8 = label.encode("utf8")
                for i, byte in enumerate(label8):
                    if i < len(label8) - 1:
                        st = next(c)
                        dfa.add_transition(src, byte, st)
                        src = st
                    else:
                        dfa.add_transition(src, byte, dest)
                del trans[label]