import uuid
import docx
from docx import Document
from docx.text.paragraph import Paragraph


# document = Document('深圳证券交易所股票上市规则.docx').add_


def catalogue_get(doc):
    # global heading, parent_id
    docx = Document(doc)
    lastest_heading = 0
    record = ['1']  # 记录目录结构
    point = '.'
    dataContent = ''  # 内容数据
    data = []
    header = 0
    for paragraph in docx.paragraphs:
        # print(paragraph.text)
        info = {}
        data.append(info)
        header += 1
        if paragraph.style.name[:7] == 'Heading':
            if header == 1:
                lines = f'<div><center><h1>{paragraph.text}</h1></center></div> '
                dataContent += lines
                # print(lines)
            this_heading = int(paragraph.style.name[-1])
            if this_heading < 4:
                result = ''.join(record) + point
                if this_heading == 1 and lastest_heading == 0:
                    heading = ''.join(record) + '.'
                    # print(f'heading:{heading}')
                else:
                    if this_heading > lastest_heading:
                        record.append('1')
                        parent_id = '.'.join(record[:-1]) + '.'

                        # info['parent_id'] = parent_id
                        # info.update({'id': heading, 'text': paragraph.text,'parent_id':parent_id})
                        # print(f'record:{record}', f'parent_id:{parent_id}')
                    elif this_heading == lastest_heading:
                        record[-1] = str(int(record[-1]) + 1)
                        parent_id = '.'.join(record[:-1]) + '.'
                        # info['parent_id'] = parent_id
                        # info.update({'id': heading, 'text': paragraph.text, 'parent_id': parent_id})
                        # print(record, f'parent_id:{parent_id}')

                        # print(f'record[-1]:{record}')

                    else:
                        record[this_heading - 1] = str(int(record[this_heading - 1]) + 1)
                        record[this_heading:] = []
                        parent_id = 0
                        # info['parent_id'] = 0
                        # info.update({'id': heading, 'text': paragraph.text, 'parent_id': 0})
                        # print(record, 'parent_id:0')

                heading = '.'.join(record) + point  # 显示一段目录
                lastest_heading = this_heading
                # print(heading, paragraph.text, paragraph.style.name, sep='   ')
                # info['id'] = heading
                # info['text'] = paragraph.text
                headingList = heading.split('.')
                # headingStr = ''
                parent_id = '.'.join(headingList[:-2]) + '.'
                # print(f'parent_id:{parent_id}')
                # print(f'headingList:{headingList}')
                # connection = str(uuid.uuid3(uuid.NAMESPACE_DNS, paragraph.text)).replace('-', '')
                # , 'connection': connection
                infos = {'id': heading, 'text': paragraph.text, 'parent_id': parent_id}
                data.append(infos)
                size = int(str(paragraph.style.name).replace('Heading ', ''))+2
                lines = f"<h{size} id='{heading}'>{paragraph.text}</h{size}>"
                dataContent += lines
                # print(lines)
                # print(heading, paragraph.text,parent_id,sep='   ')
        else:
            if header == 1:
                lines = f'<div><center><h1>{paragraph.text}</h1></center></div> '
                dataContent += lines
                # print(lines)
            else:
                lines = f'<p>{paragraph.text}</p>'
                dataContent += lines
                # print(lines)
    data = [i for i in data if i]
    return dataContent

    #         return data
    # print(data)
    # data = [i for i in data if i]
    # data[0]['parent_id'] = 0
    # return data


# path = 'D://Users/Desktop/new/深圳证券交易所创业板股票上市规则（2020年修订）.docx'
path = '深圳证券交易所股票上市规则.docx'
# data = catalogue_get(path)

data = catalogue_get(path)
print(data)