You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
118 lines
4.0 KiB
118 lines
4.0 KiB
import re
|
|
import time
|
|
from docx import Document
|
|
from pprint import pprint
|
|
# from paddlenlp import Taskflow
|
|
#
|
|
# similarity = Taskflow("text_similarity", truncation=True, max_length=102400)
|
|
|
|
|
|
def getOutlineLevel(inputXml):
|
|
"""
|
|
功能 从xml字段中提取出<w:outlineLvl w:val="number"/>中的数字number
|
|
参数 inputXml
|
|
返回 number
|
|
"""
|
|
start_index = inputXml.find('<w:outlineLvl')
|
|
end_index = inputXml.find('>', start_index)
|
|
number = inputXml[start_index:end_index + 1]
|
|
number = re.search("\d+", number).group()
|
|
return number
|
|
|
|
|
|
def isTitle(paragraph):
|
|
"""
|
|
功能 判断该段落是否设置了大纲等级
|
|
参数 paragraph:段落
|
|
返回 None:普通正文，没有大纲级别 0:一级标题 1:二级标题 2:三级标题
|
|
"""
|
|
# 如果是空行，直接返回None
|
|
if paragraph.text.strip() == '':
|
|
return None
|
|
|
|
# 如果该段落是直接在段落里设置大纲级别的，根据xml判断大纲级别
|
|
paragraphXml = paragraph._p.xml
|
|
if paragraphXml.find('<w:outlineLvl') >= 0:
|
|
return getOutlineLevel(paragraphXml)
|
|
# 如果该段落是通过样式设置大纲级别的，逐级检索样式及其父样式，判断大纲级别
|
|
targetStyle = paragraph.style
|
|
while targetStyle is not None:
|
|
# 如果在该级style中找到了大纲级别，返回
|
|
if targetStyle.element.xml.find('<w:outlineLvl') >= 0:
|
|
return getOutlineLevel(targetStyle.element.xml)
|
|
else:
|
|
targetStyle = targetStyle.base_style
|
|
# 如果在段落、样式里都没有找到大纲级别，返回None
|
|
return None
|
|
|
|
def getDocxToText12biaoti(name):
|
|
document = Document(name)
|
|
# 逐段读取docx文档的内容
|
|
levelList=[]
|
|
words=[]
|
|
levelText=""
|
|
i = 0
|
|
firstTitle = 0
|
|
secondTitle = 0
|
|
sanjiTitle = 0
|
|
for paragraph in document.paragraphs:
|
|
# 判断该段落的标题级别
|
|
# 这里用isTitle()临时代表，具体见下文介绍的方法
|
|
text = paragraph.text
|
|
|
|
if text.strip():#非空判断
|
|
# print("非空")
|
|
# words.append(text)
|
|
level = isTitle(paragraph)
|
|
if level=="0":
|
|
firstTitle+=1
|
|
secondTitle = 0
|
|
if(text.find("附件")>=0):
|
|
continue
|
|
words.append("{}:".format(firstTitle)+text)
|
|
elif level=="1":
|
|
secondTitle+=1
|
|
sanjiTitle=0
|
|
# words.append("\t"+"{}.{}".format(firstTitle,secondTitle)+text)
|
|
words.append("{}.{}".format(firstTitle,secondTitle)+text)
|
|
elif level=="2":
|
|
sanjiTitle += 1
|
|
# words.append("\t"+"{}.{}".format(firstTitle,secondTitle)+text)
|
|
words.append("{}.{}.{}".format(firstTitle, secondTitle,sanjiTitle) + text)
|
|
|
|
|
|
# 将所有段落文本拼接成一个字符串，并用换行符分隔
|
|
print(len(words))
|
|
if len(words)==0:
|
|
raise Exception("I know python!")
|
|
text = '\n'.join(words)
|
|
with open("ce1.txt", 'w',encoding="utf-8") as txt_file:
|
|
txt_file.write(text)
|
|
return words
|
|
mobanList=[]
|
|
dangqianList=[]
|
|
errorList =[]
|
|
# 将文本写入txt文件
|
|
# with open("ce模板.txt", 'r',encoding="utf-8") as txt_file:
|
|
# for i in txt_file:
|
|
# i=re.sub(r'[\t\n]', '', i)
|
|
# mobanList.append(i)
|
|
# pprint(mobanList)
|
|
# dangqianList=getDocxToText12biaoti("1.docx")
|
|
# if len(dangqianList)!=len(mobanList):
|
|
# print("标题数量与模板不一致")
|
|
# for num in range(len(mobanList)):
|
|
# moban = mobanList[num]
|
|
# dangqian= dangqianList[num]
|
|
# fenshu=similarity([[dangqian,moban]])
|
|
# pprint(fenshu)
|
|
# if (fenshu[0]["similarity"]<0.85):
|
|
# errorList.append(dangqianList)
|
|
# getDocxToText12biaoti("1.docx")
|
|
# pprint(errorList)
|
|
|
|
prompt = '''{}这是文档大纲，根据大纲分析文档中是否有{}这块内容的描述,若不存在请回答不存在
|
|
'''
|
|
dagang ="1"
|
|
biaozhun="2"
|
|
print(prompt.format(dagang, biaozhun))
|