python_ai/checkTitleName.py

import time

from docx import Document
from pprint import pprint
from qwen_agent.agents import Assistant
import re
import json_repair
import math
from docx.opc.pkgreader import _SerializedRelationships, _SerializedRelationship
from docx.opc.oxml import parse_xml


# from myLogger import outLog

def load_from_xml_v2(baseURI, rels_item_xml):
    """
    Return |_SerializedRelationships| instance loaded with the
    relationships contained in *rels_item_xml*. Returns an empty
    collection if *rels_item_xml* is |None|.
    """
    srels = _SerializedRelationships()
    if rels_item_xml is not None:
        rels_elm = parse_xml(rels_item_xml)
        for rel_elm in rels_elm.Relationship_lst:
            if rel_elm.target_ref in ('../NULL', 'NULL'):
                continue
            srels._srels.append(_SerializedRelationship(baseURI, rel_elm))
    return srels


_SerializedRelationships.load_from_xml = load_from_xml_v2
import logging

# outLog.logger = logging.getLogger("checkTitleName")
userLog = None
llm_cfg = {
    # 'model': 'qwen1.5-72b-chat',
    'model': "qwen2-72b-instruct",
    'model_server': 'DashScope',  # base_url, also known as api_base
    'api_key': 'sk-ea89cf04431645b185990b8af8c9bb13',
}
bot = Assistant(llm=llm_cfg,
                name='Assistant',
                )


# 记录程序开始的时间戳
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


# 获取文档中 详细设计方案 章节的所有内容
def getDocxToTitleName(docxPath):
    loopCount = 0
    while True:
        loopCount += 1
        if (loopCount >= 60):
            raise Exception("文档读取超时，或文档存在问题无法读取")
            break
        try:
            document = Document(docxPath)
            break
        except Exception as e:
            time.sleep(1)
            pass
    # 逐段读取docx文档的内容
    levelList = []
    words = []
    addStart = False
    levelText = ""
    count = 0
    total = len(document.paragraphs)
    yield f"文档结构检查----文档内容解析中{str(count)}/{str(total)}"
    for paragraph in document.paragraphs:
        count += 1
        yield f"文档结构检查----文档内容解析中{str(count)}/{str(total)}"
        # 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
            level = isTitle(paragraph)
            if level == "0":
                words.append(text)
    yield words


def checkTitleName(filename, user_id, outLog):
    global userLog
    userLog = outLog.get_queue(user_id, "checkTitleName")
    yield '文档结构检查----启动中'
    userLog.info("文档结构检查---任务开始")
    with open("ce模板.txt", "r", encoding='utf-8') as f:
        gettext = f.readlines()
    count = 0
    reserr = []
    try:
        for i in getDocxToTitleName(filename):
            word = i
            if (isinstance(word, str)):
                yield word
                continue
    except Exception as e:
        userLog.warning(e)
        yield "文档结构检查----文件无法正常打开。可以尝试用WORD或WPS打开文件，进行修复并另存，用另存的文件再做一次尝试。"
        userLog.warning("checkTitleName----文档无法打开，请检查文档内容")
        outLog.mark_done(user_id, "checkTitleName")
        return
    for text in gettext:
        count += 1
        prompt = f'''
        \n 这些是文章的标题，请问【{text}】在标题中是否可以配对的，若有请指出是哪个标题，若没有请回到不存在
        '''
        xushang = "回答格式{‘name’:‘名称’,'answer'：‘回答’，“标题”：“标题”}请严格按照格式回答问题，不要做过多我解释"
        yield f"文档结构检查----结构分析中{count}/{len(gettext)}"
        strword = "\n".join(word) + prompt + xushang
        messages = [{'role': 'user', 'content': [{'text': strword}]}]
        runList = []
        for rsp in bot.run(messages):
            runList.append(rsp)
            # print(rsp)
        data = runList[len(runList) - 1][0]["content"]
        parsed_data = json_repair.loads(data.replace('`', ''))
        if (parsed_data["answer"] == "不存在"):
            reserr.append(text)
            userLog.info("文档结构检查----文档结构存在异常：" + text.replace('\n', ''))
    resInfo = "文档结构存在异常：<br>"
    if (len(reserr) > 0):
        for i in reserr:
            resInfo += "**" + i.replace('\n', '') + "**<br>"

        yield resInfo
    else:
        yield "**文档结构未发现异常**"
        userLog.info("文档结构检查----文档结构未发现异常")
    outLog.mark_done(user_id, "checkTitleName")