# -*- coding: utf-8 -*-
# 
# @author: lyg, ym
# @date: 2025-5-8
# @version: 1
# @description: docx文档拆分器，根据段落拆分，将图片和表格转换为json数据。
import docx
import docx.table
import json
from dataclasses import dataclass
from PIL import Image
import io
import re

from knowledgebase.doc.image_to_text import ImageToText


@dataclass
class ParagraphInfo:
    """
    段落信息
    :param text: str - 段落文本
    :param level: int - 段落级别，1-9级标题，0表示正文
    :param title_no: str - 标题编号，如1.1、1.1.1等
    """
    text: str
    level: int
    title_no: str

    @property
    def full_text(self):
        """
        获取段落完整文本，包含标题编号
        :return: str - 段落完整文本
        """
        return f"{self.title_no} {self.text}"

    def __init__(self, text: str, level: int):
        """
        段落信息
        :param text: str - 段落文本
        :param level: int - 段落级别，1-9级标题，0表示正文
        """
        self.text = text
        self.level = level
        self.title_no = ''


class DocSplit:
    """
    docx文档拆分器，根据段落拆分，将图片和表格转换为json数据。
    1.封装段落信息
    2.将图片和表格转换为json
    3.将段落按照文档标题级别组合成树形结构

    """

    def __init__(self, doc_file):
        self.doc_file = doc_file
        self.image_to_text = ImageToText()
        self.paragraphs:list[ParagraphInfo] = []

    def table_to_json(self, table: docx.table.Table):
        """
           将表格转换为 JSON 格式

           :param table: docx.table.Table - 要转换的表格对象
           :return list - 表格数据，以 JSON 格式表示
        """
        table_data = []
        headers = []
        first_row = True
        row: docx.table._Row
        for row in table.rows:
            if first_row:
                for cell in row.cells:
                    headers.append(cell.text)
                first_row = False
                continue
            row_data = {}
            row_idx = 0
            for cell in row.cells:
                if cell.tables:
                    # 嵌套表格处理
                    if len(cell.tables) == 1:
                        text = self.table_to_json(cell.tables[0])
                    else:
                        text = []
                        for tbl in cell.tables:
                            tbl_json = self.table_to_json(tbl)
                            text.append(tbl_json)
                else:
                    # 单元格文本获取
                    text = cell.text
                row_data[headers[row_idx]] = text
                row_idx += 1

            table_data.append(row_data)
        return table_data

    def split(self):
        """
        将文档拆分成段落，并返回段落列表

        :return: list[ParagraphInfo] - 段落列表
        """
        document = docx.Document(self.doc_file)
        table_cnt = 0
        paragraph_cnt = 0

        for element in document.element.body:
            if element.tag.endswith('p'):  # 段落
                # 获取标题多级编号
                paragraph = document.paragraphs[paragraph_cnt]
                paragraph_text = paragraph.text
                if paragraph_text:
                    self.paragraphs.append(ParagraphInfo(paragraph_text, self.get_header_level(paragraph)))
                # 检查是否是图片，如果是图片则转换为文本
                img_data = self.get_image_blob(paragraph)
                if img_data:
                    text = self.gen_text_from_img(img_data)
                    self.paragraphs.append(ParagraphInfo(text, 0))
                paragraph_cnt += 1
            elif element.tag.endswith('tbl'):  # 表格
                table = document.tables[table_cnt]  # 获取当前表格对象
                table_cnt += 1
                table_data = self.table_to_json(table)
                self.paragraphs.append(ParagraphInfo(json.dumps(table_data, indent=4, ensure_ascii=False), 0))
            else:
                continue
        # 生成标题编号
        self.gen_title_no(self.paragraphs)

    @staticmethod
    def get_image_blob(paragraph):
        # 遍历段落中的所有Run对象（图片通常在单独的Run中）
        for run in paragraph.runs:
            xml = run._element.xml
            if xml.find('v:imagedata') != -1:
                # 使用正则表达式查找r:id属性
                match = re.search(r'r:id="([^"]+)"', xml)
                if match:
                    r_id = match.group(1)
                    if r_id:
                        # 获取图片信息
                        image_part = paragraph.part.rels[r_id].target_part
                        return DocSplit.image_convert(image_part.blob, "png")
            if xml.find('wp:inline') != -1 or xml.find('wp:anchor') != -1:
                # 使用正则表达式查找r:embed属性
                match = re.search(r'r:embed="([^"]+)"', xml)
                if match:
                    r_id = match.group(1)
                    if r_id:
                        # 获取图片信息
                        image_part = paragraph.part.rels[r_id].target_part
                        return DocSplit.image_convert(image_part.blob, "png")
        return None

    @staticmethod
    def gen_title_no(paragraphs: list[ParagraphInfo]):
        title_levels = [1, 1, 1, 1, 1, 1, 1, 1, 1]
        for i in range(len(paragraphs)):
            if paragraphs[i].level > 0:
                for j in range(paragraphs[i].level - 1):
                    title_levels[j] = 1
                paragraphs[i].title_no = '.'.join([str(x) for x in title_levels[0:paragraphs[i].level]])
                title_levels[paragraphs[i].level - 1] += 1
            else:
                title_levels = [1, 1, 1, 1, 1, 1, 1, 1, 1]

    @staticmethod
    def get_header_level(paragraph) -> int:
        if paragraph.style.base_style:
            style = paragraph.style.base_style
        else:
            style = paragraph.style
        if style and style.name.startswith('Heading'):
            # 获取标题级别
            level = int(style.name.split(' ')[1])
            return level
        else:
            return 0

    @staticmethod
    def image_convert(_in: bytes, _out_format: str) -> bytes:
        in_io = io.BytesIO()
        in_io.write(_in)
        img = Image.open(in_io, "r")
        out_io = io.BytesIO()
        img.save(out_io, "png")
        out_io.seek(0)
        return out_io.read()

    def gen_text_from_img(self, img_data:bytes):
        return self.image_to_text.gen_text_from_img(img_data)

if __name__ == '__main__':
    doc_file = r'D:\workspace\PythonProjects\KnowledgeBase\doc\ZL格式(公开).docx'
    doc_split = DocSplit(doc_file)
    doc_split.split()
    print("\n".join([x.full_text for x in doc_split.paragraphs]))