import inspect
import os
import sys
from bs4 import BeautifulSoup
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + "/../")
from format_convert.convert_tree import _Document, _Page, _Sentence
import logging
import traceback
from format_convert import get_memory_info
from format_convert.convert_need_interface import from_office_interface
from format_convert.convert_xlsx import xlsx2text, XlsxConvert
from format_convert.utils import judge_error_code, get_logger, log


@get_memory_info.memory_decorator
def xls2text(path, unique_type_dir):
    log("into xls2text")
    try:
        # 调用libreoffice格式转换
        file_path = from_office_interface(path, unique_type_dir, 'xlsx')
        if judge_error_code(file_path):
            return file_path

        text = xlsx2text(file_path, unique_type_dir)
        if judge_error_code(text):
            return text

        return text
    except Exception as e:
        log("xls2text error!")
        traceback.print_exc()
        return [-1]


class XlsConvert:
    def __init__(self, path, unique_type_dir):
        self._doc = _Document(path)
        self.path = path
        self.unique_type_dir = unique_type_dir

    def convert(self):
        # 先判断特殊xls文件，可能是html文本
        is_html_xls = False
        try:
            with open(self.path, 'r', encoding='utf-8') as f:
                html_str = f.read()
            soup = BeautifulSoup(html_str, 'lxml')
            text = soup.text
            is_html_xls = True
        except:
            pass

        if is_html_xls:
            self._page = _Page(None, 0)
            _sen = _Sentence(text, (0, 0, 0, 0))
            self._page.add_child(_sen)
            self._doc.add_child(self._page)
        else:
            # 调用office格式转换
            # file_path = from_office_interface(self.path, self.unique_type_dir, 'xlsx')
            # if judge_error_code(file_path):
            #     self._doc.error_code = file_path
            #     return
            _xlsx = XlsxConvert(self.path, self.unique_type_dir, is_xls=True)
            _xlsx.convert()
            self._doc = _xlsx._doc

    def get_html(self):
        try:
            self.convert()
        except:
            traceback.print_exc()
            self._doc.error_code = [-1]
        # print("xls ", self._doc)
        if self._doc.error_code is not None:
            return self._doc.error_code
        # print(self._doc.children)
        return self._doc.get_html()


if __name__ == '__main__':
    c = XlsConvert("C:/Users/Administrator/Downloads/1683641686556.xls", "C:/Users/Administrator/Downloads/1")
    print(c.get_html())