ocr_platform/ocr_tools/universal_doc_parser/__init__.py

"""
Universal Document Parser

统一文档处理流水线，支持多种模型（MinerU、PaddleX、DotsOCR等）进行文档解析。
提供完整的处理流程：PDF分类、页面方向识别、Layout检测、OCR识别、表格VLM识别等。
"""

from .core.pipeline_manager_v2 import EnhancedDocPipeline
from .core.pipeline_manager_v2_streaming import StreamingDocPipeline
from .core.config_manager import ConfigManager
from .core.model_factory import ModelFactory

# 从 ocr_utils 导入工具函数
try:
    from ocr_utils import OutputFormatterV2, save_mineru_format
except ImportError:
    # 降级：从 utils 导入（向后兼容）
    from .utils import OutputFormatterV2, save_mineru_format

__all__ = [
    'EnhancedDocPipeline',
    'StreamingDocPipeline',
    'ConfigManager',
    'ModelFactory',
    'OutputFormatterV2',
    'save_mineru_format',
]

__version__ = "2.0.0"