class AtomicModel:
    Layout = "layout"
    MFD = "mfd"
    MFR = "mfr"
    OCR = "ocr"
    WirelessTable = "wireless_table"
    WiredTable = "wired_table"
    TableCls = "table_cls"
    ImgOrientationCls = "img_ori_cls"

doclayout_yolo_weights = os.path.join(auto_download_and_get_model_root_path(ModelPath.doclayout_yolo), ModelPath.doclayout_yolo)

pip install "mineru[vllm]"：安裝 mineru 主包及 vllm 推理後端相關的基礎依賴。
pip install "mineru-vl-utils[vllm]"：安裝 mineru 的視覺相關核心工具與vllm適配的組件，且確保其支持 vllm 推理。
pip install torch==2.9.0+cu121 torchvision==0.24.0+cu121 torchaudio==2.8.0+cu121 --index-url https://download.pytorch.org/whl/cu121
pip install loguru pypdfium2 doclayout_yolo：安裝輕量輔助工具，支持日誌、PDF 處理和文檔佈局分析。
mamba install -c conda-forge tqdm vllm ultralytics：安裝進度條工具、vllm 推理引擎和圖像處理模型庫。
還可參考miner-u項目中的pyproject.toml文件。

# 1. 導入 modelscope 的核心下載函數
from modelscope import snapshot_download
import os
# --- 配置區 ---
# 指定要從 ModelScope Hub 下載的模型 ID
# ModelScope 會自動從 'https://modelscope.cn/models' 下載
model_id = 'OpenDataLab/MinerU2.5-2509-1.2B'
# 指定你希望將模型文件保存到的本地目錄
# 注意：在 modelscope 中，這個參數叫做 cache_dir
local_dir_path = './MinerU2.5'
# 指定要下載的模型版本，例如 'master' (主分支) 或一個具體的 commit ID
# 這是一個好習慣，可以保證你下載版本的確定性
revision = 'master'
# --- 執行區 ---
print(f"準備從 ModelScope 下載模型: {model_id} (版本: {revision})")
print(f"將保存到本地目錄: {local_dir_path}")
try:
    # 2. 開始執行下載
    # 函數會返回實際存放模型文件的完整路徑
    downloaded_path = snapshot_download(
        model_id=model_id,
        cache_dir=local_dir_path,
        revision=revision,
        # allow_pattern="*.safetensors",  # 可選：只下載 safetensors 格式的權重文件
        # ignore_file_pattern=[r"\.md$", r"\.py$"], # 可選：忽略所有 Markdown 和 Python 文件
    )
    print(f"\n✅ 模型已成功下載到: {downloaded_path}")
    print("這個返回的路徑是包含模型文件的最終目錄，你可以直接使用它。")
except Exception as e:
    print(f"\n❌ 下載過程中出現錯誤: {e}")
    print("\n排查建議:")
    print("1. 檢查你的網絡連接是否可以訪問 modelscope.cn。")
    print("2. 確認模型 ID 'Qwen/Qwen3-8B' 是否正確。")
    print("3. 如果是私有模型，請確保已在終端運行 'modelscope login' 並輸入了你的 Token。")

# Copyright (c) Opendatalab. All rights reserved.
import copy
import json
import os
from pathlib import Path
# 【核心修改】在所有其他導入之前，設定自訂的緩存路徑
# 這行程式碼必須放在腳本的最頂部
# 同時設定 MINERU_MODEL_SOURCE，確保它使用 modelscope 的緩存機制
os.environ['MINERU_MODEL_SOURCE'] = "modelscope"#從魔塔社區下載模型
os.environ['MODELSCOPE_CACHE'] = "/home/agent/models/MinerU2.5"#下載的模型存到這個路徑
from loguru import logger
from mineru.cli.common import convert_pdf_bytes_to_bytes_by_pypdfium2, prepare_env, read_fn
from mineru.data.data_reader_writer import FileBasedDataWriter
from mineru.utils.draw_bbox import draw_layout_bbox, draw_span_bbox
from mineru.utils.enum_class import MakeMode
from mineru.backend.vlm.vlm_analyze import doc_analyze as vlm_doc_analyze
from mineru.backend.pipeline.pipeline_analyze import doc_analyze as pipeline_doc_analyze
from mineru.backend.pipeline.pipeline_middle_json_mkcontent import union_make as pipeline_union_make
from mineru.backend.pipeline.model_json_to_middle_json import result_to_middle_json as pipeline_result_to_middle_json
from mineru.backend.vlm.vlm_middle_json_mkcontent import union_make as vlm_union_make
from mineru.utils.guess_suffix_or_lang import guess_suffix_by_path
def do_parse(
    output_dir,  # Output directory for storing parsing results
    pdf_file_names: list[str],  # List of PDF file names to be parsed
    pdf_bytes_list: list[bytes],  # List of PDF bytes to be parsed
    p_lang_list: list[str],  # List of languages for each PDF, default is 'ch' (Chinese)
    backend="pipeline",  # The backend for parsing PDF, default is 'pipeline'
    parse_method="auto",  # The method for parsing PDF, default is 'auto'
    formula_enable=True,  # Enable formula parsing
    table_enable=True,  # Enable table parsing
    server_url=None,  # Server URL for vlm-http-client backend
    f_draw_layout_bbox=True,  # Whether to draw layout bounding boxes
    f_draw_span_bbox=True,  # Whether to draw span bounding boxes
    f_dump_md=True,  # Whether to dump markdown files
    f_dump_middle_json=True,  # Whether to dump middle JSON files
    f_dump_model_output=True,  # Whether to dump model output files
    f_dump_orig_pdf=True,  # Whether to dump original PDF files
    f_dump_content_list=True,  # Whether to dump content list files
    f_make_md_mode=MakeMode.MM_MD,  # The mode for making markdown content, default is MM_MD
    start_page_id=0,  # Start page ID for parsing, default is 0
    end_page_id=None,  # End page ID for parsing, default is None (parse all pages until the end of the document)
):
    if backend == "pipeline":
        for idx, pdf_bytes in enumerate(pdf_bytes_list):
            new_pdf_bytes = convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id, end_page_id)
            pdf_bytes_list[idx] = new_pdf_bytes
        infer_results, all_image_lists, all_pdf_docs, lang_list, ocr_enabled_list = pipeline_doc_analyze(pdf_bytes_list, p_lang_list, parse_method=parse_method, formula_enable=formula_enable,table_enable=table_enable)
        for idx, model_list in enumerate(infer_results):
            model_json = copy.deepcopy(model_list)
            pdf_file_name = pdf_file_names[idx]
            local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
            image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
            images_list = all_image_lists[idx]
            pdf_doc = all_pdf_docs[idx]
            _lang = lang_list[idx]
            _ocr_enable = ocr_enabled_list[idx]
            middle_json = pipeline_result_to_middle_json(model_list, images_list, pdf_doc, image_writer, _lang, _ocr_enable, formula_enable)
            pdf_info = middle_json["pdf_info"]
            pdf_bytes = pdf_bytes_list[idx]
            _process_output(
                pdf_info, pdf_bytes, pdf_file_name, local_md_dir, local_image_dir,
                md_writer, f_draw_layout_bbox, f_draw_span_bbox, f_dump_orig_pdf,
                f_dump_md, f_dump_content_list, f_dump_middle_json, f_dump_model_output,
                f_make_md_mode, middle_json, model_json, is_pipeline=True
            )
    else:
        if backend.startswith("vlm-"):
            backend = backend[4:]
        f_draw_span_bbox = False
        parse_method = "vlm"
        for idx, pdf_bytes in enumerate(pdf_bytes_list):
            pdf_file_name = pdf_file_names[idx]
            pdf_bytes = convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id, end_page_id)
            local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
            image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
            middle_json, infer_result = vlm_doc_analyze(pdf_bytes, image_writer=image_writer, backend=backend, server_url=server_url)
            pdf_info = middle_json["pdf_info"]
            _process_output(
                pdf_info, pdf_bytes, pdf_file_name, local_md_dir, local_image_dir,
                md_writer, f_draw_layout_bbox, f_draw_span_bbox, f_dump_orig_pdf,
                f_dump_md, f_dump_content_list, f_dump_middle_json, f_dump_model_output,
                f_make_md_mode, middle_json, infer_result, is_pipeline=False
            )
def _process_output(
        pdf_info,
        pdf_bytes,
        pdf_file_name,
        local_md_dir,
        local_image_dir,
        md_writer,
        f_draw_layout_bbox,
        f_draw_span_bbox,
        f_dump_orig_pdf,
        f_dump_md,
        f_dump_content_list,
        f_dump_middle_json,
        f_dump_model_output,
        f_make_md_mode,
        middle_json,
        model_output=None,
        is_pipeline=True
):
    """處理輸出文件"""
    if f_draw_layout_bbox:
        draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_layout.pdf")
    if f_draw_span_bbox:
        draw_span_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_span.pdf")
    if f_dump_orig_pdf:
        md_writer.write(
            f"{pdf_file_name}_origin.pdf",
            pdf_bytes,
        )
    image_dir = str(os.path.basename(local_image_dir))
    if f_dump_md:
        make_func = pipeline_union_make if is_pipeline else vlm_union_make
        md_content_str = make_func(pdf_info, f_make_md_mode, image_dir)
        md_writer.write_string(
            f"{pdf_file_name}.md",
            md_content_str,
        )
    if f_dump_content_list:
        make_func = pipeline_union_make if is_pipeline else vlm_union_make
        content_list = make_func(pdf_info, MakeMode.CONTENT_LIST, image_dir)
        md_writer.write_string(
            f"{pdf_file_name}_content_list.json",
            json.dumps(content_list, ensure_ascii=False, indent=4),
        )
    if f_dump_middle_json:
        md_writer.write_string(
            f"{pdf_file_name}_middle.json",
            json.dumps(middle_json, ensure_ascii=False, indent=4),
        )
    if f_dump_model_output:
        md_writer.write_string(
            f"{pdf_file_name}_model.json",
            json.dumps(model_output, ensure_ascii=False, indent=4),
        )
    logger.info(f"local output dir is {local_md_dir}")
def parse_doc(
        path_list: list[Path],
        output_dir,
        lang="ch",
        backend="pipeline",
        method="auto",
        server_url=None,
        start_page_id=0,
        end_page_id=None
):
    """
        Parameter description:
        path_list: List of document paths to be parsed, can be PDF or image files.
        output_dir: Output directory for storing parsing results.
        lang: Language option, default is 'ch', optional values include['ch', 'ch_server', 'ch_lite', 'en', 'korean', 'japan', 'chinese_cht', 'ta', 'te', 'ka']。
            Input the languages in the pdf (if known) to improve OCR accuracy.  Optional.
            Adapted only for the case where the backend is set to "pipeline"
        backend: the backend for parsing pdf:
            pipeline: More general.
            vlm-transformers: More general.
            vlm-vllm-engine: Faster(engine).
            vlm-http-client: Faster(client).
            without method specified, pipeline will be used by default.
        method: the method for parsing pdf:
            auto: Automatically determine the method based on the file type.
            txt: Use text extraction method.
            ocr: Use OCR method for image-based PDFs.
            Without method specified, 'auto' will be used by default.
            Adapted only for the case where the backend is set to "pipeline".
        server_url: When the backend is `http-client`, you need to specify the server_url, for example:`http://127.0.0.1:30000`
        start_page_id: Start page ID for parsing, default is 0
        end_page_id: End page ID for parsing, default is None (parse all pages until the end of the document)
    """
    try:
        file_name_list = []
        pdf_bytes_list = []
        lang_list = []
        for path in path_list:
            file_name = str(Path(path).stem)
            pdf_bytes = read_fn(path)
            file_name_list.append(file_name)
            pdf_bytes_list.append(pdf_bytes)
            lang_list.append(lang)
        do_parse(
            output_dir=output_dir,
            pdf_file_names=file_name_list,
            pdf_bytes_list=pdf_bytes_list,
            p_lang_list=lang_list,
            backend=backend,
            parse_method=method,
            server_url=server_url,
            start_page_id=start_page_id,
            end_page_id=end_page_id
        )
    except Exception as e:
        logger.exception(e)
if __name__ == '__main__':
    # args
    __dir__ = os.path.dirname(os.path.abspath(__file__))
    pdf_files_dir = os.path.join(__dir__, "pdfs")
    output_dir = os.path.join(__dir__, "output")
    pdf_suffixes = ["pdf"]
    image_suffixes = ["png", "jpeg", "jp2", "webp", "gif", "bmp", "jpg"]
    doc_path_list = []
    for doc_path in Path(pdf_files_dir).glob('*'):
        if guess_suffix_by_path(doc_path) in pdf_suffixes + image_suffixes:
            doc_path_list.append(doc_path)
    # 【關鍵修改 1】: 確保使用 modelscope 來尋找本地緩存的模型
    # 即使您已下載，這一步有助於函式庫正確定位
    # os.environ['MINERU_MODEL_SOURCE'] = "modelscope"
    print(f" 即將使用 'vlm-vllm-engine' 後端處理 {len(doc_path_list)} 個文件...")
    parse_doc(doc_path_list, output_dir, backend="vlm-vllm-engine")  # faster(engine).
    """如果您由於網絡問題無法下載模型，可以設置環境變量MINERU_MODEL_SOURCE為modelscope使用免代理倉庫下載模型"""
    # os.environ['MINERU_MODEL_SOURCE'] = "modelscope"
    """Use pipeline mode if your environment does not support VLM"""
    # parse_doc(doc_path_list, output_dir, backend="pipeline")
    """To enable VLM mode, change the backend to 'vlm-xxx'"""
    # parse_doc(doc_path_list, output_dir, backend="vlm-transformers")  # more general.
    # parse_doc(doc_path_list, output_dir, backend="vlm-vllm-engine")  # faster(engine).
    # parse_doc(doc_path_list, output_dir, backend="vlm-http-client", server_url="http://127.0.0.1:30000")  # faster(client).

# Copyright (c) Opendatalab. All rights reserved.
import copy
import json
import os
from pathlib import Path
# 強制使用 CPU，禁用 CUDA
# 【核心修改1：自定義模型保存路徑】
# 修改為你需要的模型緩存目錄（確保路徑存在且有讀寫權限）
os.environ['MINERU_MODEL_SOURCE'] = "modelscope"  # 從 ModelScope 下載模型
os.environ['MODELSCOPE_CACHE'] = "/home/agent/ltcode/mineru/model/MinerU_Pipeline"  # 自定義模型保存路徑
from loguru import logger
from mineru.cli.common import convert_pdf_bytes_to_bytes_by_pypdfium2, prepare_env, read_fn
from mineru.data.data_reader_writer import FileBasedDataWriter
from mineru.utils.draw_bbox import draw_layout_bbox, draw_span_bbox
from mineru.utils.enum_class import MakeMode
from mineru.backend.vlm.vlm_analyze import doc_analyze as vlm_doc_analyze
from mineru.backend.pipeline.pipeline_analyze import doc_analyze as pipeline_doc_analyze
from mineru.backend.pipeline.pipeline_middle_json_mkcontent import union_make as pipeline_union_make
from mineru.backend.pipeline.model_json_to_middle_json import result_to_middle_json as pipeline_result_to_middle_json
from mineru.backend.vlm.vlm_middle_json_mkcontent import union_make as vlm_union_make
from mineru.utils.guess_suffix_or_lang import guess_suffix_by_path
def do_parse(
    output_dir,  # 結果輸出目錄
    pdf_file_names: list[str],  # PDF文件名列表
    pdf_bytes_list: list[bytes],  # PDF字節流列表
    p_lang_list: list[str],  # 每種PDF的語言，默認中文"ch"
    backend="pipeline",  # 解析後端，默認"pipeline"
    parse_method="auto",  # 解析方式，默認"auto"（此處會強制設為"ocr"）
    formula_enable=True,  # 【核心配置1：啓用公式解析】
    table_enable=True,  # 【核心配置2：啓用表格解析】
    server_url=None,  # vlm-http-client後端的服務地址（Pipeline後端無用）
    f_draw_layout_bbox=True,  # 【核心配置3：啓用佈局邊界框繪製】
    f_draw_span_bbox=True,  # 【核心配置4：啓用元素邊界框繪製】
    f_dump_md=True,  # 【核心配置5：啓用Markdown輸出】
    f_dump_middle_json=True,  # 【核心配置6：啓用中間JSON輸出】
    f_dump_model_output=True,  # 【核心配置7：啓用模型原始輸出】
    f_dump_orig_pdf=True,  # 【核心配置8：啓用原始PDF保存】
    f_dump_content_list=True,  # 【核心配置9：啓用內容列表輸出】
    f_make_md_mode=MakeMode.MM_MD,  # Markdown生成模式，默認標準MM_MD
    start_page_id=0,  # 起始解析頁碼（0開始）
    end_page_id=None,  # 結束解析頁碼（None表示到最後一頁）
):
    if backend == "pipeline":
        # 【關鍵：強制使用OCR解析】覆蓋傳入的parse_method，確保所有PDF用OCR分析
        parse_method = "ocr"
        # 截取指定頁碼範圍的PDF
        for idx, pdf_bytes in enumerate(pdf_bytes_list):
            new_pdf_bytes = convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id, end_page_id)
            pdf_bytes_list[idx] = new_pdf_bytes
        # 【Pipeline全功能調用】啓用公式、表格解析，使用OCR方式
        infer_results, all_image_lists, all_pdf_docs, lang_list, ocr_enabled_list = pipeline_doc_analyze(
            pdf_bytes_list,
            p_lang_list,
            parse_method=parse_method,  # 已強制為"ocr"
            formula_enable=formula_enable,  # 啓用公式解析
            table_enable=table_enable  # 啓用表格解析
        )
        # 逐個處理PDF的解析結果
        for idx, model_list in enumerate(infer_results):
            model_json = copy.deepcopy(model_list)
            pdf_file_name = pdf_file_names[idx]
            # 準備輸出目錄（自動創建images和md子目錄）
            local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
            image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
            images_list = all_image_lists[idx]
            pdf_doc = all_pdf_docs[idx]
            _lang = lang_list[idx]
            _ocr_enable = ocr_enabled_list[idx]  # OCR已強制啓用，此處為True
            # 生成Pipeline格式的中間JSON（含OCR文本、公式/表格信息）
            middle_json = pipeline_result_to_middle_json(
                model_list, images_list, pdf_doc, image_writer, _lang, _ocr_enable, formula_enable
            )
            pdf_info = middle_json["pdf_info"]
            pdf_bytes = pdf_bytes_list[idx]
            # 輸出所有配置的結果文件
            _process_output(
                pdf_info, pdf_bytes, pdf_file_name, local_md_dir, local_image_dir,
                md_writer, f_draw_layout_bbox, f_draw_span_bbox, f_dump_orig_pdf,
                f_dump_md, f_dump_content_list, f_dump_middle_json, f_dump_model_output,
                f_make_md_mode, middle_json, model_json, is_pipeline=True
            )
    else:
        # VLM後端邏輯（本代碼已禁用，無需關注）
        if backend.startswith("vlm-"):
            backend = backend[4:]
        f_draw_span_bbox = False
        parse_method = "vlm"
        for idx, pdf_bytes in enumerate(pdf_bytes_list):
            pdf_file_name = pdf_file_names[idx]
            pdf_bytes = convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id, end_page_id)
            local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
            image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
            middle_json, infer_result = vlm_doc_analyze(pdf_bytes, image_writer=image_writer, backend=backend, server_url=server_url)
            pdf_info = middle_json["pdf_info"]
            _process_output(
                pdf_info, pdf_bytes, pdf_file_name, local_md_dir, local_image_dir,
                md_writer, f_draw_layout_bbox, f_draw_span_bbox, f_dump_orig_pdf,
                f_dump_md, f_dump_content_list, f_dump_middle_json, f_dump_model_output,
                f_make_md_mode, middle_json, infer_result, is_pipeline=False
            )
def _process_output(
        pdf_info,
        pdf_bytes,
        pdf_file_name,
        local_md_dir,
        local_image_dir,
        md_writer,
        f_draw_layout_bbox,
        f_draw_span_bbox,
        f_dump_orig_pdf,
        f_dump_md,
        f_dump_content_list,
        f_dump_middle_json,
        f_dump_model_output,
        f_make_md_mode,
        middle_json,
        model_output=None,
        is_pipeline=True
):
    """處理所有輸出文件（按配置生成對應結果）"""
    # 1. 生成帶佈局邊界框的PDF（標註標題、段落、表格位置）
    if f_draw_layout_bbox:
        draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_layout.pdf")
    # 2. 生成帶元素邊界框的PDF（標註文本塊、公式、表格的具體位置）
    if f_draw_span_bbox:
        draw_span_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_span.pdf")
    # 3. 保存原始PDF（便於對比解析前後內容）
    if f_dump_orig_pdf:
        md_writer.write(f"{pdf_file_name}_origin.pdf", pdf_bytes)
    image_dir = str(os.path.basename(local_image_dir))
    # 4. 生成Markdown文件（核心結果，可直接閲讀）
    if f_dump_md:
        make_func = pipeline_union_make if is_pipeline else vlm_union_make
        md_content_str = make_func(pdf_info, f_make_md_mode, image_dir)
        md_writer.write_string(f"{pdf_file_name}.md", md_content_str)
    # 5. 生成內容列表JSON（便於快速查看文檔結構）
    if f_dump_content_list:
        make_func = pipeline_union_make if is_pipeline else vlm_union_make
        content_list = make_func(pdf_info, MakeMode.CONTENT_LIST, image_dir)
        md_writer.write_string(
            f"{pdf_file_name}_content_list.json",
            json.dumps(content_list, ensure_ascii=False, indent=4),
        )
    # 6. 生成中間JSON（結構化數據，含所有元素的位置、內容，用於二次開發）
    if f_dump_middle_json:
        md_writer.write_string(
            f"{pdf_file_name}_middle.json",
            json.dumps(middle_json, ensure_ascii=False, indent=4),
        )
    # 7. 生成模型原始輸出JSON（調試用，查看模型檢測的原始結果）
    if f_dump_model_output:
        md_writer.write_string(
            f"{pdf_file_name}_model.json",
            json.dumps(model_output, ensure_ascii=False, indent=4),
        )
    logger.info(f"✅ 解析完成！結果保存目錄：{local_md_dir}")
def parse_doc(
        path_list: list[Path],
        output_dir,
        lang="ch",  # 【關鍵：指定OCR語言為中文，可改為"en"（英文）等】
        backend="pipeline",  # 固定為Pipeline後端
        method="auto",  # 會在do_parse中強制改為"ocr"，此處僅為兼容參數
        server_url=None,  # Pipeline後端無用
        start_page_id=0,  # 起始頁碼
        end_page_id=None  # 結束頁碼
):
    """入口函數：讀取文件列表，調用do_parse執行解析"""
    try:
        file_name_list = []
        pdf_bytes_list = []
        lang_list = []
        # 遍歷待解析文件，讀取字節流和文件名
        for path in path_list:
            if not path.exists():
                logger.warning(f"❌ 文件不存在：{path}，已跳過")
                continue
            file_name = str(Path(path).stem)  # 取文件名（不含後綴）
            pdf_bytes = read_fn(path)  # 讀取文件字節流
            file_name_list.append(file_name)
            pdf_bytes_list.append(pdf_bytes)
            lang_list.append(lang)  # 所有文件使用同一語言（可按需修改為不同語言）
        if not file_name_list:
            logger.error("❌ 無有效文件可解析，請檢查pdfs目錄下是否有PDF/圖像文件")
            return
        # 調用核心解析函數do_parse
        do_parse(
            output_dir=output_dir,
            pdf_file_names=file_name_list,
            pdf_bytes_list=pdf_bytes_list,
            p_lang_list=lang_list,
            backend=backend,
            parse_method=method,
            start_page_id=start_page_id,
            end_page_id=end_page_id
        )
    except Exception as e:
        logger.exception(f"❌ 解析過程出錯：{str(e)}")
if __name__ == '__main__':
    # 【核心配置2：指定文件目錄和輸出目錄】
    __dir__ = os.path.dirname(os.path.abspath(__file__))
    pdf_files_dir = os.path.join(__dir__, "pdfs")  # 待解析文件目錄（需手動創建，放入PDF/圖像）
    output_dir = os.path.join(__dir__, "pipeline_ocr_output")  # 結果輸出目錄（自動創建）
    # 【核心配置3：支持的文件類型（PDF+常見圖像格式）】
    pdf_suffixes = ["pdf"]
    image_suffixes = ["png", "jpeg", "jp2", "webp", "gif", "bmp", "jpg"]
    supported_suffixes = pdf_suffixes + image_suffixes
    # 讀取pdfs目錄下的所有支持類型文件
    doc_path_list = []
    if not os.path.exists(pdf_files_dir):
        os.makedirs(pdf_files_dir)
        logger.warning(f"⚠️  pdfs目錄不存在，已自動創建：{pdf_files_dir}，請放入待解析文件")
    else:
        for doc_path in Path(pdf_files_dir).glob('*'):
            suffix = guess_suffix_by_path(doc_path).lower()
            if suffix in supported_suffixes:
                doc_path_list.append(doc_path)
    # 打印解析前信息
    print(f"=====================================")
    print(f" 開始解析：")
    print(f" 待解析文件目錄：{pdf_files_dir}")
    print(f" 有效文件數量：{len(doc_path_list)}")
    print(f" 解析方式：Pipeline後端 + OCR全量分析")
    print(f"️  結果輸出目錄：{output_dir}")
    print(f"️  OCR識別語言：中文（ch）")
    print(f"=====================================")
    # 【核心調用：啓動Pipeline+OCR解析】
    if doc_path_list:
        parse_doc(
            path_list=doc_path_list,
            output_dir=output_dir,
            backend="pipeline",  # 固定使用Pipeline後端
            lang="ch",  # 可改為"en"（英文）、"japan"（日文）等
            start_page_id=0,  # 從第1頁開始解析（0對應第1頁）
            end_page_id=None  # 解析到最後一頁
        )
    else:
        print(f"❌ 無有效文件可解析，請在 {pdf_files_dir} 目錄放入PDF或圖像文件")