Python - 提取句子 - 关闭1

Question

我想提取段落的句子并逐行打印出来。它做得很完美，除非一个句号跟随一个换行符。例如：用户完成一个句子，然后按Enter键。所以在这段时间之后没有空间

代码认为这句话是前一句的一部分，因为没有空格。打印出来时，它们会粘在一起。换句话说，如果在句点之后没有空格时提取句子，我怎么能改变代码呢？例如： This.should.be.considered.five.sentences 因为有五个句点，但代码只将其视为一个句子。

这是代码：

import re

abbreviations = {'dr.': 'doctor', 'mr.': 'mister', 'bro': 'brother', 'mrs.': 'mistress', 'ms.': 'miss', 'jr.': 'junior', 'sr.': 'senior',
                 'i.e.': 'for example', 'e.g.': 'for example', 'vs.': 'versus'}
terminators = ['.', '!', '?']
wrappers = ['"', "'", ')', ']', '}']


def find_sentences(paragraph):
   end = True
   sentences = []
   while end > -1:
       end = find_sentence_end(paragraph)
       if end > -1:
           sentences.append(paragraph[end:].strip())
           paragraph = paragraph[:end]
   sentences.append(paragraph)
   sentences.reverse()
   return sentences

def find_sentence_end(paragraph):
    [possible_endings, contraction_locations] = [[], []]
    contractions = abbreviations.keys()
    sentence_terminators = terminators + [terminator + wrapper for wrapper in wrappers for terminator in terminators]
    for sentence_terminator in sentence_terminators:
        t_indices = list(find_all(paragraph, sentence_terminator))
        possible_endings.extend(([] if not len(t_indices) else [[i, len(sentence_terminator)] for i in t_indices]))
    for contraction in contractions:
        c_indices = list(find_all(paragraph, contraction))
        contraction_locations.extend(([] if not len(c_indices) else [i + len(contraction) for i in c_indices]))
    possible_endings = [pe for pe in possible_endings if pe[0] + pe[1] not in contraction_locations]
    if len(paragraph) in [pe[0] + pe[1] for pe in possible_endings]:
        max_end_start = max([pe[0] for pe in possible_endings])
        possible_endings = [pe for pe in possible_endings if pe[0] != max_end_start]
    possible_endings = [pe[0] + pe[1] for pe in possible_endings if sum(pe) > len(paragraph) or (sum(pe) < len(paragraph) and paragraph[sum(pe)] == ' ')]
    end = (-1 if not len(possible_endings) else max(possible_endings))
    return end

def find_all(a_str, sub):
    start = 0
    while True:
        start = a_str.find(sub, start)
        if start == -1:
            return
        yield start
        start += len(sub)