import docx2txt
import re


def insert_html_tag(paragraph: str, keyword_list: list) -> str:
    """
    插入html标签高亮敏感词
    :param paragraph: 待处理的段落
    :param keyword_list: 列表形式的敏感词
    :return: 标记后的段落
    """
    marked_paragraph = paragraph
    for keyword in keyword_list:
        marked_paragraph = marked_paragraph.replace(keyword,
                                                    '<span style="background-color:yellow">' + keyword + '</span>')
    return marked_paragraph


def docx_find(file_path: str, keyword_list: list) -> dict:
    """
    :param file_path: 文件路径
    :param keyword_list: 列表形式的敏感词
    :return: 返回一个字典，包含文件名和敏感词所在的段落 {'file_name': 'xxx.docx', 'find_list': ['段落1', '段落2', ...]}
    """
    # doc_file = Document(file_path)
    doc_text = docx2txt.process(file_path)  # 使用docx2txt模块读取docx文件
    find_dict = {'file_name': file_path, 'find_list': []}
    find_list = []
    paragraph_keyword = []

    for para in doc_text.split('\n'):
        para = re.sub(r'\s+', '', para)  # 删除段落中空格
        this_para_keyword = [keyword for keyword in keyword_list if keyword in para]  # 查找该段落中的敏感词

        if this_para_keyword:
            # 若该段落中有敏感词，则将该段落的所有keyword及该段落分别加入到paragraph_keyword和find_list中
            paragraph_keyword.append(this_para_keyword)
            find_list.append(para)

    print(len(find_list))
    find_dict['find_list'] = find_list
    find_dict['paragraph_keyword'] = paragraph_keyword
    return find_dict


# print(docx_find('浅水海底电缆打捞大作业.docx', ['机密', '铲出']))
def util_keyword_find(file_path: str, keyword_list: list) -> dict:
    """
    对指定单一文件进行敏感词查找
    :param file_path: 文件路径
    :param keyword_list: 列表形式的敏感词
    :return: 返回一个字典，包含文件名和敏感词所在的段落 {'file_name': 'xxx.docx', 'find_list': ['段落1', '段落2', ...]}
    """
    # check file type
    if file_path.endswith('.docx'):
        find_dict = docx_find(file_path, keyword_list)  # 调用docx_find函数
        for para, this_para_keyword in zip(find_dict['find_list'], find_dict['paragraph_keyword']):
            marked_para = insert_html_tag(para, keyword_list)
            find_dict['find_list'][find_dict['find_list'].index(para)] = marked_para
        # print(find_dict)
        return find_dict

    else:
        return {'file_name': file_path, 'find_list': []}


if __name__ == '__main__':
    print(util_keyword_find('浅水海底电缆打捞大作业.docx', ['打捞', '浅水']))