from flask_app.general.format_change import pdf2docx
from flask_app.general.通义千问long import upload_file
from flask_app.货物标.截取pdf货物标版 import truncate_pdf_main
from flask_app.货物标.技术参数要求提取 import get_technical_requirements


def extract_matching_keys(data_dict, good_list):
    """
    递归遍历data_dict，查找good_list中存在的键，并将匹配的键及其值添加到结果字典中。

    参数:
    - data_dict (dict): 要遍历的嵌套字典。
    - good_list (list): 包含要查找的键的列表。

    返回:
    - dict: 包含所有匹配键及其值的字典。
    """
    result = {}

    def recurse(current_dict):
        if isinstance(current_dict, dict):
            for key, value in current_dict.items():
                if key in good_list:
                    result[key] = value
                # 递归遍历子字典
                recurse(value)
        elif isinstance(current_dict, list):
            for item in current_dict:
                recurse(item)
        # 如果current_dict不是dict或list，则无需进一步处理

    recurse(data_dict)
    return result

def get_technical_requirements_main(file_path,output_folder):
    truncate_file=truncate_pdf_main(file_path,output_folder,5)[0]
    truncate_file_docx=pdf2docx(truncate_file)
    file_id=upload_file(truncate_file_docx)
    final_res=get_technical_requirements(file_id)
    # 安全地提取 "技术要求" 内部的字典内容
    if isinstance(final_res, dict) and '技术要求' in final_res and isinstance(final_res['技术要求'], dict):
        technical_requirements = final_res['技术要求']
        good_list = technical_requirements.pop('货物列表', [])  # 如果 '货物列表' 不存在，返回 []
        return extract_matching_keys(technical_requirements,good_list)
    else:
        return final_res
if __name__ == "__main__":
    file_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\45f650ce-e519-457b-9ad6-5840e2ede539\\ztbfile.pdf"
    output_folder = "C:\\Users\\Administrator\\Desktop\\fsdownload\\45f650ce-e519-457b-9ad6-5840e2ede539\\tmp"
    res=get_technical_requirements_main(file_path,output_folder)
    print(res)