import json
import re
from typing import Dict, List
from langchain_text_splitters import CharacterTextSplitter, MarkdownHeaderTextSplitter,MarkdownTextSplitter,TokenTextSplitter,RecursiveCharacterTextSplitter
from modelsAPI.model_api import OpenaiAPI
from markdown_process.save_markdown import Save_Markdown_to_Milvus
from markdown_process.convert_header import convert_numbered_headings, custom_convert_numbered_headings,parse_markdown,header_postprocess,postprocess_chunks
from markdown_it import MarkdownIt
from markdown_it.tree import SyntaxTreeNode
def reset_chunk(chunks):
    id_list = []
    for res in chunks:
        if res['Header_1'] == res['text']:
            id = res['id']
            id_list.append(id)
    # print(id_list)
    for iditem in id_list:
        result = [item for item in chunks if item['id'] == iditem][0]
        result_ = [item for item in chunks if item['id'] == iditem + 1][0]
        result_['Header_2'] = result_['Header_1']
        result_['Header_1'] = result['Header_1']
        result_['text'] = result['text'] + '\n' + result_['text']
    result_devide = [record for record in chunks if not record['Header_1'] == record['text']]
    for index, item in enumerate(result_devide):
        item['id'] = index + 1
    return result_devide
def remove_markdown_images(text):
    """
    移除Markdown格式的图像链接

    参数:
        text: 包含Markdown图像链接的原始字符串

    返回:
        移除图像链接后的文本
    """
    # 匹配 ![](path) 或 [](path) 格式
    pattern = r'!?\[\]\(/root/output/[^/]+/images/[a-f0-9]+\.(?:jpg|png|gif|bmp)\)'
    return re.sub(pattern, '', text)
def remove_markdown_images(text):
    """
    移除Markdown格式的图像链接

    参数:
        text: 包含Markdown图像链接的原始字符串

    返回:
        移除图像链接后的文本
    """
    # 匹配 ![](path) 或 [](path) 格式
    pattern = r'http://\d{0,9}\.\d{0,9}\.\d{0,9}\.\d{0,9}:\d+/[^\s\'"<>]+'
    return re.sub(pattern, '', text)

def extract_urls(text):
    # 定义匹配 URL 的正则表达式模式
    pattern = r'http://\d{0,9}\.\d{0,9}\.\d{0,9}\.\d{0,9}:\d{0,9}/output/images/[a-f0-9]+\.(?:jpg|jpeg|png|gif)'

    # 查找所有匹配的 URL
    urls = re.findall(pattern, text)

    # # 可选：过滤只保留特定扩展名的文件（如.jpg, .png等）
    # image_urls = [url for url in urls if url.lower().endswith(('.jpg', '.jpeg', '.png', '.gif'))]

    return urls

def extract_and_convert_image_paths(text):
    """
    从字符串中提取图像路径并转换为新格式

    参数:
        text: 包含图像路径的原始字符串

    返回:
        包含原始路径和转换后路径的字典列表
    """
    # 正则表达式匹配图像路径
    pattern = r'(/root/output/[^/]+/images/[a-f0-9]+\.(?:jpg|png|gif|bmp))'
    matches = re.findall(pattern, text)

    converted_paths = []

    for original_path in matches:
        # 分解原始路径
        path_parts = original_path.split('/')

        # 提取关键部分
        # 格式: /root/output/<文件夹>/images/<图片名>
        folder_name = path_parts[3]  # 获取"生成式人工智能传播风险：理论内涵、形成机理与治理策略_景奎"这部分
        image_name = path_parts[-1]  # 获取图片文件名

        # 构建新路径
        new_path = f"mineru/{folder_name}/images/{image_name}"

        converted_paths.append({
            'original_path': original_path,
            'converted_path': new_path
        })

    return converted_paths

class MarkdownAwareTextSplitter(RecursiveCharacterTextSplitter):
    def __init__(self, **kwargs):
        # 优先用Markdown的分隔符
        separators = [
            # 保持表格完整 (匹配Markdown表格)
            r'\n\s*\|',  # 表格行
            r'\n#+\s+',  # 标题
            r'\n\*\*\s+', # 分隔线
            r'\n\n',     # 双换行
            r'\n',       # 单换行
            r'\.\s+',    # 句号+空格
            r'\s+',      # 任意空白
        ]
        super().__init__(separators=separators, **kwargs)

    def split_text(self, text: str) -> List[str]:
        # 预处理：保护表格结构
        protected_tables = []
        def _protect_tables(match):
            protected_tables.append(match.group(0))
            return f"__TABLE_{len(protected_tables)-1}__"

        # 用临时标记替换表格
        table_pattern = r'(\n\|.+\|.+\n(\|.+\|.+\n)+)'
        text_with_protected_tables = re.sub(
            table_pattern,
            _protect_tables,
            text,
            flags=re.MULTILINE
        )

        # 常规切分
        chunks = super().split_text(text_with_protected_tables)

        # 恢复表格
        final_chunks = []
        for chunk in chunks:
            for i, table in enumerate(protected_tables):
                chunk = chunk.replace(f"__TABLE_{i}__", table)
            final_chunks.append(chunk)

        return final_chunks

def split_regular(resource,mdDocs,logger,database_name,collection_name,chunk_type,chunk_size,chunk_overlap=50,max_level=3):

    if chunk_type =="03":
        text_splitter =TokenTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
        texts = text_splitter.split_text(mdDocs)
        milvus = Save_Markdown_to_Milvus(database_name=database_name,collection_name=collection_name)
        for text in texts:
            convert_path_list=extract_and_convert_image_paths(text)
            text = remove_markdown_images(text)
            if convert_path_list:
                img_path = ",".join(convert_path_list)
            vector = OpenaiAPI.get_embeddings(text)
            data = [[text],[vector],[resource],[img_path]]
            milvus.save_hybrid_md(data=data)
            results.append({"id":j+i+1,"text":text,"resource":resource,"img_path":img_path})
        milvus.close()
    else:
         #自定义分解
        md_header_json = parse_markdown(mdDocs,max_level=max_level)
        # print(md_header_json)
        #合并处理
        md_header_list = header_postprocess(md_header_json)
        logger.info("markdown splitting...")

        milvus = Save_Markdown_to_Milvus(database_name=database_name,collection_name=collection_name)
        results = []
        for i ,md in enumerate(md_header_list):
            if md["text"]:
                header_1 = md["Header_1"]
                header_2 = md["Header_2"]
                header_3 = md["Header_3"]
                text = md["text"]

                # print("Header_1:",header_1)
                # print("Header_2:",header_2)
                # print("Header_3:",header_3)
                # print("text:",text_)
                # print("======================================")
                if chunk_type =="01":
                    text_splitter = RecursiveCharacterTextSplitter(
                    chunk_size=chunk_size,
                    chunk_overlap=chunk_overlap,
                    length_function=len,
                    separators=["  ","\n\n"]
                )
                    texts = text_splitter.split_text(text)
                    for j,txt in enumerate(texts):
                        img_list = extract_urls(txt)
                        txt = remove_markdown_images(txt)
                        if img_list:
                            img_path = ",".join(img_list)
                        # convert_path_list=extract_and_convert_image_paths(text)
                        # text = remove_markdown_images(text)
                        # if convert_path_list:
                        #     img_path = ",".join(convert_path_list)
                # print(j)
                # print(texts)
            #     print("======================================")
                        vector = OpenaiAPI.get_embeddings(txt)
                        data = [[header_1],[header_2],[header_3],[txt],[vector],[resource],[img_path]]
                        # milvus.save_md(data=data)
                        milvus.save_hybrid_md(data=data)
                        results.append({"id":j+i+1,"Header_1":header_1,"Header_2":header_2,"Header_3":header_3,"text":txt,"resource":resource,"img_path":img_path})

                else:
                    img_list = extract_urls(txt)
                    txt = remove_markdown_images(txt)
                    if img_list:
                        img_path = ",".join(img_list)
                    # convert_path_list=extract_and_convert_image_paths(text)
                    # text = remove_markdown_images(text)
                    # if convert_path_list:
                    #     img_path = ",".join(convert_path_list)
                    vector = OpenaiAPI.get_embeddings(text)
                    data = [[header_1],[header_2],[header_3],[text],[vector],[resource],[img_path]]
                    milvus.save_hybrid_md(data=data)
                    results.append({"id":i+1,"Header_1":header_1,"Header_2":header_2,"Header_3":header_3,"text":txt,"resource":resource,"img_path":img_path})
        milvus.close()

    return results

def split_text(resource, mdDocs, logger, chunk_type, chunk_size, chunk_overlap=50,max_level=3):
    """
    拆分文本的函数

    Args:
        resource: 资源标识
        mdDocs: Markdown文档内容
        logger: 日志记录器
        chunk_type: 拆分类型("01"或"03")
            "01": 智能分割(基于递归字符分割)
            "03": 按字符分割(基于token分割)
        chunk_size: 块长度
        chunk_overlap: 块重叠大小(默认为50)

    Returns:
        list: 拆分后的文本块列表，每个元素是包含文本和元数据的字典
    """
    #print(2222222222222222222222222222222222)
    if chunk_type == "03":
        logger.info(f"chunk size: {chunk_size},chunk_overlap: {chunk_overlap},chunk_type: {chunk_type}")
        return _split_by_token(resource, mdDocs, logger, chunk_size, chunk_overlap)
    else:
        return _split_custom(resource, mdDocs, logger, chunk_type, chunk_size, chunk_overlap,max_level)

def split_page_chunk(resource,content_chunk_list,chunk_size,chunk_overlap,logger,max_level,chunk_type):
    def process_content_list(parsed_data: List[Dict],max_level) -> List[Dict]:
        """
        处理 parsed_data：
        1. 将 text_level=1/2 的标题添加到后续无 text_level 的文本前
        2. 合并 type=image 的项到前一个 chunk
        """
        processed_data = []
        current_titles = {level: "" for level in range(1, max_level + 1)}  # 各级标题缓存

        if isinstance(max_level, str):
            try:
                max_level = int(max_level)
            except ValueError:
                max_level = 3  # 默认值

        for item in parsed_data:
            if not isinstance(item, dict):
                continue

            raw_text_level = item.get("text_level")
            text_level = None
            if raw_text_level is not None:
                if isinstance(raw_text_level, str):
                    try:
                        text_level = int(raw_text_level.strip()) if raw_text_level.strip() else None
                    except ValueError:
                        text_level = None
                elif isinstance(raw_text_level, int):
                    text_level = raw_text_level

            item_type = item.get("type", "text")
            text = item.get("text", "")
            page_idx = item.get("page_idx", -1)
            id = item.get("id")

            if text_level is not None and 1 <= text_level <= max_level:
                # 更新当前层级及更低层级的标题（例如：遇到2级标题会清除3级的缓存）
                for level in range(text_level, max_level + 1):
                    current_titles[level] = text + "\n" if level == text_level else ""
                continue  # 标题本身不单独生成 chunk

            # 合并图片逻辑
            if item_type == "image":
                image_path = item.get("image_path","")
                image_caption = item.get("image_caption","")
                if image_path:
                    text = f"![{image_caption}]({image_path})"
                if processed_data:
                    processed_data[-1]["text"] += f"![{image_caption}]({image_path})"
                continue
            elif item_type =="table":
                table_caption = "".join(item.get("table_caption", ""))
                table_body = item.get("table_body", "")
                text = table_caption + "\n" + table_body
            # 普通文本：添加当前所有层级的标题（从高到低）
            combined_title = "".join(
                current_titles[level]
                for level in range(1, max_level + 1)
                if current_titles[level]
            )
            full_text = combined_title + text

            # 添加到结果（仅当有内容时）
            if full_text.strip():
                processed_data.append({
                    "id":id,
                    "text": full_text,
                    "page_idx": page_idx+1,
                    "type": item_type,
                    "image_path":image_path if item_type == "image" else ""
                })

        return processed_data
    results = []
    processed_data = process_content_list(content_chunk_list,max_level=max_level)
    for i,data in enumerate(processed_data):
        if chunk_type == "01" or "02":
            chunks = _split_recursively(data["text"], chunk_size, chunk_overlap)
        else:
            chunks = _split_by_token(resource=resource,md_text=data.get["text"],logger=logger,chunk_size=chunk_size,chunk_overlap=chunk_overlap)
        for j, chunk in enumerate(chunks):
            result = _process_chunk(chunk, resource, {}, str(data.get("id")) +f"-{j}", logger,page_idx=data.get("page_idx"))
            results.append(result)
    print(111111111111111111)
    return results

def _split_by_token(resource, md_text,logger, chunk_size, chunk_overlap):
    """
    使用markdown解析器保持结构完整的切分方法，支持chunk重叠

    参数:
        resource: 关联的资源标识
        md_text: 要切分的Markdown文本
        chunk_size: 每个chunk的目标大小
        chunk_overlap: chunk之间的重叠大小

    返回:
        包含text和resource字段的字典列表
    """
    logger.info("开始按字符分片")
    if chunk_overlap >= chunk_size:
        raise ValueError("chunk_overlap必须小于chunk_size")

    md = MarkdownIt()
    tokens = md.parse(md_text)
    root = SyntaxTreeNode(tokens)
    if chunk_size >= 8192:
        raise ValueError("chunk_size不能大于4096")
    chunks = []
    current_chunk = ""
    overlap_buffer = ""

    def get_node_text(node):
        """递归获取节点的完整文本内容"""
        if node.type == "text":
            return node.content
        elif node.type == "inline" and node.children:
            return "".join(get_node_text(child) for child in node.children)
        elif node.children:
            # 对于块级元素，添加适当的换行
            contents = []
            for child in node.children:
                content = get_node_text(child)
                if content:
                    contents.append(content)
            return "\n".join(contents)
        return ""

    def process_node(node):
        nonlocal current_chunk, overlap_buffer
        content = get_node_text(node)

        # 处理当前内容
        remaining_content = content
        while remaining_content:
            # 计算还能添加到当前chunk的内容量
            remaining_space = chunk_size - len(current_chunk)

            if remaining_space <= 0:
                # 当前chunk已满，保存并准备重叠部分
                chunks.append(current_chunk)
                overlap_buffer = current_chunk[-chunk_overlap:] if chunk_overlap > 0 else ""
                current_chunk = overlap_buffer + remaining_content[:remaining_space]
                remaining_content = remaining_content[remaining_space:]
            else:
                # 添加到当前chunk
                add_content = remaining_content[:remaining_space]
                current_chunk += add_content
                remaining_content = remaining_content[remaining_space:]

    # 处理所有节点
    for child in root.children:
        process_node(child)

    # 添加最后一个chunk
    if current_chunk:
        chunks.append(current_chunk)

    # 过滤空chunk并添加resource信息
    return [{"text": text.strip(), "resource": resource}
            for text in chunks if text.strip()]

# def _split_by_token(resource, text, logger, chunk_size, chunk_overlap):
#     """按token分割文本"""
#     logger.info("开始按字符分割")
#     text_splitter = TokenTextSplitter(chunk_size=1024, chunk_overlap=100)
#     texts = text_splitter.split_text(text)
#     return [{"text": text, "resource": resource} for text in texts]


def _split_custom(resource, mdDocs, logger, chunk_type, chunk_size, chunk_overlap,max_level):
    """自定义分割处理"""
    logger.info("开始按自定义分割")
    results = []
    # if chunk_type=="02":
    if chunk_type=="02" or chunk_type=="01":
        # md_text = custom_convert_numbered_headings(mdDocs, max_level)
        # md_text = '\n'.join(md_text)
        chunks = _split_markdown(mdDocs,max_level)
        # chunks = _split_markdown(md_text,max_level)
        for idx, doc in enumerate(chunks, start=1):
            # 确保所有Header字段都存在
            headers = {f"Header_{i}": doc.metadata.get(f"Header_{i}", "")
                    for i in range(1, max_level + 1)}
            # if headers.get("Header_1") =="目  录" or headers.get("Header_1") =="目录" or headers.get("Header_1") =="目 录":
            #         continue
            result = _process_chunk(doc.page_content, resource, headers, idx, logger)
            results.append(result)
    results = reset_chunk(results)

    return results


def _split_markdown(text,max_level,chunk_size=2048,chunk_overlap=50):
    """
    根据 max_level 动态生成 headers_to_split_on 配置
    规则：
    - max_level=1 → 只按 # 分割
    - max_level=2 → 按 # 和 ## 分割
    - 以此类推
    """
    # 动态生成 headers_to_split_on 配置
    headers_to_split_on = [
        (f"{'#' * i}", f"Header_{i}") for i in range(1, max_level + 1)
    ]

    # 初始化分割器
    splitter = MarkdownHeaderTextSplitter(
        headers_to_split_on=headers_to_split_on,
        strip_headers=False  # 废弃标题文本
    )
    chunks = splitter.split_text(text)
    char_splitter = CharacterTextSplitter(
        chunk_size=chunk_size,
        chunk_overlap=chunk_overlap,
        length_function=len,
        separator=""  # 优先按段落分割
    )
    # 检查并处理过大的分块

    final_chunks = []
    header_chunks = []
    for chunk in chunks:
        # content = chunk.page_content  # 只获取文本内容，忽略metadata
        if len(chunk.page_content) <=8000:
            final_chunks.append(chunk)
            header_chunks.append(chunk.metadata) #dict
        else:
            # 直接分割文本内容
            split_texts = char_splitter.split_documents([chunk])
            final_chunks.extend(split_texts)

    return final_chunks

    # 执行分割
    # return splitter.split_text(text)

def _split_recursively(text, chunk_size, chunk_overlap):
    """递归字符分割"""
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1024,
        chunk_overlap=100,
        length_function=len,
        # separators=["\n\n\n","(?<!#)\n\n","  "],
        separators=[""],
        keep_separator=True,
        is_separator_regex=True
    )
    semantic_chunks = text_splitter.split_text(text)

    # 2. 再用 CharacterTextSplitter 按字符数精确分割
    char_splitter = CharacterTextSplitter(
        chunk_size=1024,#2048
        chunk_overlap=50,
        length_function=len,
        separator=""  # 按纯字符切分
    )

    final_chunks = []
    for chunk in semantic_chunks:
        final_chunks.extend(char_splitter.split_text(chunk))

    return final_chunks
    # return text_splitter.split_text(text)


def _split_with_images(resource, text, logger, chunk_size, chunk_overlap):
    """处理没有章节信息的文本分割"""
    results = []
    chunks = _split_recursively(text, chunk_size, chunk_overlap)

    for i, chunk in enumerate(chunks):
        img_list = extract_urls(chunk)
        logger.info(f"img_list: {img_list}")
        # clean_text = remove_markdown_images(chunk)
        img_path = ",".join(img_list) if img_list else ""

        results.append({
            "id": i+1,
            "text": text,#clean_text,
            "resource": resource,
            "img_path": img_path
        })
    logger.info(f"results: {results}")
    return results


def _process_chunk(text, resource, headers, chunk_id, logger,page_idx=None,origin_text=None):
    """处理单个文本块，提取图片和清理文本"""
    img_list = extract_urls(text)
    # logger.info(f"img_list: {img_list}")
    # clean_text = remove_markdown_images(text)
    img_path = ",".join(img_list) if img_list else ""
    if img_path:
        logger.info(f"Get Image Path: {img_path}")

    return {
        "id": chunk_id,
        "Header_1": headers.get("Header_1", ""),
        "Header_2": headers.get("Header_2", ""),
        "Header_3": headers.get("Header_3", ""),
        "text":text.replace("# ",""),
        "resource": resource,
        "img_path": img_path,
        "page":page_idx,
        "origin_text":text
    }

def save_md(results, collection_name,database_name):
    """
    保存Markdown到Milvus数据库的函数
    :param results: 拆分后的文本块列表
    :param database_name: 数据库名称
    :param collection_name: 集合名称
    :return: 保存后的结果列表
    """
    texts = [item.get("text") for item in results]
    # vectors = OpenaiAPI.get_embeddings(texts)
    vectors = OpenaiAPI.batch_embeddings(texts)

    milvus = Save_Markdown_to_Milvus(database_name=database_name, collection_name=collection_name)
    all_data = []
    for idx, item in enumerate(results):
        text = item.get("text")
        resource = item.get("resource")
        img_path = item.get("img_path", "null")
        vector = vectors[idx].get("embedding")  # 获取对应的嵌入向量

        data_item = {
            "text": text,
            "vector": vector,
            "resource": resource,
            "img_path": img_path,
            "page_idx": item.get("page_idx"),
            "origin_id": str(item.get("id")),
            "origin_text":item.get("origin_text")
        }

        # 添加标题信息（如果有）
        if "Header_1" in item:
            data_item.update({
                "Header_1": item.get("Header_1"),
                "Header_2": item.get("Header_2"),
                "Header_3": item.get("Header_3")
            })
        all_data.append(data_item)

        # milvus.save_hybrid_md(data=[data_item])
    milvus.save_hybrid_md(data=all_data)

    milvus.close()
    return results
    # milvus = Save_Markdown_to_Milvus(database_name=database_name, collection_name=collection_name)

    # for item in results:
    #     text = item.get("text")
    #     resource = item.get("resource")
    #     img_path = item.get("img_path", "null")
    #     vector = OpenaiAPI.get_embeddings(text)

    #     if "Header_1" in item:  # 有标题的情况
    #         data = [{"text":text,
    #                  "vector":vector,
    #                  "resource":resource,
    #                  "img_path":img_path,
    #                  "Header_1":item.get("Header_1"),
    #                  "Header_2":item.get("Header_2"),
    #                  "Header_3":item.get("Header_3"),
    #                  "page_idx":item.get("page_idx"),
    #                  "origin_id":str(item.get("id"))}]

    #     else:  # 没有标题的情况
    #         data = [{"text":text,
    #                  "vector":vector,
    #                  "resource":resource,
    #                  "img_path":img_path,
    #                  "page_idx":item.get("page_idx"),
    #                  "origin_id":str(item.get("id"))
    #         }]

    #     milvus.save_hybrid_md(data=data)

    # milvus.close()
    # return results

def hierarchical_save(results,collection_name,database_name):
    texts = [item.get("text") for item in results]
    # vectors = OpenaiAPI.get_embeddings(texts)
    vectors = OpenaiAPI.batch_embeddings(texts)

    milvus = Save_Markdown_to_Milvus(database_name=database_name, collection_name=collection_name)
    all_data = []
    for idx, item in enumerate(results):
        text = item.get("text")
        resource = item.get("resource")
        img_path = item.get("img_path", "null")
        vector = vectors[idx].get("embedding")  # 获取对应的嵌入向量

        data_item = {
            "text": text,
            "vector": vector,
            "resource": resource,
            "img_path": img_path,
            "page_idx": item.get("page_idx"),
            "origin_id": str(item.get("id")),
            "origin_text": item.get("origin_text"),
        }

        # 添加标题信息（如果有）
        if "Header_1" in item:
            data_item.update({
                "Header_1": item.get("Header_1"),
                "Header_2": item.get("Header_2"),
                "Header_3": item.get("Header_3")
            })
        all_data.append(data_item)

        # milvus.save_hybrid_md(data=[data_item])
    milvus.hierarchical_insert(data=all_data,collection_name=collection_name,database_name=database_name)

    milvus.close()
    return results

def split_insert(resource, mdDocs, logger, database_name, collection_name, chunk_type, chunk_length, chunk_overlap=50,max_level=3):
    """
    原始函数的包装函数，保持接口不变
    """
    # 先拆分文本
    results = split_text(resource, mdDocs, logger, chunk_type, chunk_length, chunk_overlap,max_level)
    # 然后保存到数据库
    return save_md(results, database_name, collection_name)


def split_by_md_header(mdDocs,logger,database_name,collection_name):
    """
    Split with metadata like "Metadata (("Header_1", "xxx"), ("Header_2", "xxxx")) page_content="xxx..."
    :param mdDocs: markdown text
    :return:
    """
    mdDocs = convert_numbered_headings(mdDocs)
    headers_to_split_on = [("#", "Header_1"), ("##", "Header_2"), ("###", "Header_3")]
    md_header_splitter = MarkdownHeaderTextSplitter(headers_to_split_on=headers_to_split_on, return_each_line=True)
    md_header_splits = md_header_splitter.split_text(mdDocs)
    # md_text_splitter = MarkdownTextSplitter(chunk_size=512,)
    #存入向量数据库
    milvus = Save_Markdown_to_Milvus(database_name=database_name,collection_name=collection_name)
    final_splits = []
    for _, i in enumerate(md_header_splits):
        logger.info(f"Index: {_}, Metadata: {i.metadata} Content: {i.page_content}")

        if i.metadata:
            header_1 = i.metadata["Header_1"] if "Header_1" in i.metadata.keys() else None
            header_2 = i.metadata["Header_2"] if "Header_2" in i.metadata.keys() else None
            header_3 = i.metadata["Header_3"] if "Header_3" in i.metadata.keys() else None
            text = i.page_content
            # metadata = {"title": header_1, "sub_title": header_2, "sub_sub_title": header_3,"text":text}
            vector = OpenaiAPI.get_embeddings(text)
            if vector is None:
                logger.error("向量生成失败")
                raise ValueError("向量生成失败")

            data = [[header_1],[header_2],[header_3],[text],[vector]]
            logger.info(f"Index:{_},header_1:{header_1},header_2:{header_2},header_3:{header_3},text:{text}")
            # data={"text":text,"header_1":header_1,"header_2":header_2,"header_3":header_3,"vector":vector}
            result = milvus.save_md(data=data)
            # print(f"Index:{_},header_1:{header_1},header_2:{header_2},header_3:{header_3},text:{text}")
            # print("---------------------")
    return md_header_splits