Question

我正在制作一个不和谐的机器人，每隔几秒就会将随机生成的句子喷射到聊天中。我试图使用nltk模块使句子更加连贯，但我抓住了一个错误并且无法弄明白。

import asyncio
import random
import discord.ext.commands
import markovify
import nltk
import re

class POSifiedText(markovify.Text):
    def word_split(self, sentence):
        words = re.split(self.word_split_pattern, sentence)
        words = ["::".join(tag) for tag in nltk.pos_tag(words) ]
        return words

    def word_join(self, words):
        sentence = " ".join(word.split("::")[0] for word in words)
        return sentence

with open("/root/sample.txt") as f:
    text = f.read()

text_model = POSifiedText(text, state_size=1)

client = discord.Client()
async def background_loop():
    await client.wait_until_ready()
    while not client.is_closed:
        channel = client.get_channel('channelid')
        messages = [(text_model.make_sentence(tries=8, max_overlap_total=10,default_max_overlap_ratio=0.5))]
        await client.send_message(channel, random.choice(messages))
        await asyncio.sleep(10)

client.loop.create_task(background_loop())
client.run("token")

来自输出日志的错误：

Traceback (most recent call last):
  File "/root/untitled/Loop.py", line 21, in <module>
    text_model = POSifiedText(text, state_size=1)
  File "/usr/local/lib/python3.5/dist-packages/markovify/text.py", line 24, in __init__
    runs = list(self.generate_corpus(input_text))
  File "/root/untitled/Loop.py", line 11, in word_split
    words = [": :".join(tag) for tag in nltk.pos_tag(words) ]
  File "/usr/local/lib/python3.5/dist-packages/nltk/tag/__init__.py", line 129, in pos_tag
    return _pos_tag(tokens, tagset, tagger)    
  File "/usr/local/lib/python3.5/dist-packages/nltk/tag/__init__.py", line 97, in _pos_tag
    tagged_tokens = tagger.tag(tokens)
  File "/usr/local/lib/python3.5/dist-packages/nltk/tag/perceptron.py", line 152, in tag
    context = self.START + [self.normalize(w) for w in tokens] + self.END
  File "/usr/local/lib/python3.5/dist-packages/nltk/tag/perceptron.py", line 152, in <listcomp>
    context = self.START + [self.normalize(w) for w in tokens] + self.END
  File "/usr/local/lib/python3.5/dist-packages/nltk/tag/perceptron.py", line 227, in normalize
    elif word[0].isdigit():
IndexError: string index out of range

Answer 1

word[0].isdigit():抛出错误的事实意味着word是一个空字符串。最可能的原因是你的正则表达式分裂有时会产生空字符串。

解决方案是在

之后

words = re.split(self.word_split_pattern, sentence)

放行

words = [w for w in words if len(w) > 0]

在python中编写discord bot，遇到错误“字符串索引超出范围”

1 个答案: