lyxy-document/readers/pdf/docling.py

"""使用 docling 库解析 PDF 文件（不启用 OCR）"""

from typing import Optional, Tuple


def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
    """使用 docling 库解析 PDF 文件（不启用 OCR）"""
    try:
        from docling.datamodel.base_models import InputFormat
        from docling.datamodel.pipeline_options import PdfPipelineOptions
        from docling.document_converter import DocumentConverter, PdfFormatOption
    except ImportError:
        return None, "docling 库未安装"

    try:
        converter = DocumentConverter(
            format_options={
                InputFormat.PDF: PdfFormatOption(
                    pipeline_options=PdfPipelineOptions(do_ocr=False)
                )
            }
        )
        result = converter.convert(file_path)
        markdown_content = result.document.export_to_markdown()
        if not markdown_content.strip():
            return None, "文档为空"
        return markdown_content, None
    except Exception as e:
        return None, f"docling 解析失败: {str(e)}"