目录
1.传统的文本分割方法短板
传统的文本分割方法在处理长句子时可能会产生意外的结果,因为它在分割句子时并没有考虑语义,只是基于标点符号和字符数量进行的。
2.传统的文本分割方法举例
from langchain.text_splitter import CharacterTextSplitter
import re
from typing import List
from configs.model_config import SENTENCE_SIZE
class ChineseTextSplitter(CharacterTextSplitter):
def __init__(self, pdf: bool = False, sentence_size: int = SENTENCE_SIZE, **kwargs):
super().__init__(**kwargs)
self.pdf = pdf
self.sentence_size = sentence_size
def split_text1(self, text: str) -> List[str]:
if self.pdf:
text = re.sub(r"\n{3,}", "\n", text)
text = re.sub('\s', ' ', text)
text = text.replace("\n\n", "")
sent_sep_pattern = re.compile('([﹒﹔﹖﹗.。!?]["’”」』]{0,2}|(?=["‘“「『]{1,2}|$))') # del :;
sent_list = []
for ele in sent_sep_pattern.split(text):
if sent_sep_pattern.match(ele) and sent_list:
sent_list[-1] += ele
elif ele:
sent_list.append(ele)
return sent_list
def split_text(self, text