ocr_verify/merger/dotsocr_merger.py

"""
DotsOCR 和 PaddleOCR 合并模块
"""
import json
from typing import List, Dict

try:
    from .text_matcher import TextMatcher
    from .bbox_extractor import BBoxExtractor
    from .data_processor import DataProcessor
    from .markdown_generator import MarkdownGenerator
    from .unified_output_converter import UnifiedOutputConverter
except ImportError:
    from text_matcher import TextMatcher
    from bbox_extractor import BBoxExtractor
    from data_processor import DataProcessor
    from markdown_generator import MarkdownGenerator
    from unified_output_converter import UnifiedOutputConverter


class DotsOCRMerger:
    """DotsOCR 和 PaddleOCR 结果合并器"""
    
    def __init__(self, look_ahead_window: int = 10, similarity_threshold: int = 90):
        """
        Args:
            look_ahead_window: 向前查找的窗口大小
            similarity_threshold: 文本相似度阈值
        """
        self.look_ahead_window = look_ahead_window
        self.similarity_threshold = similarity_threshold
        
        # 初始化子模块
        self.text_matcher = TextMatcher(similarity_threshold)
        self.bbox_extractor = BBoxExtractor()
        self.data_processor = DataProcessor(self.text_matcher, look_ahead_window)
        self.markdown_generator = MarkdownGenerator()
        self.output_converter = UnifiedOutputConverter()
    
    def merge_table_with_bbox(self, dotsocr_json_path: str, 
                             paddle_json_path: str,
                             data_format: str = 'mineru') -> List[Dict]:
        """
        合并 DotsOCR 和 PaddleOCR 的结果
        
        Args:
            dotsocr_json_path: DotsOCR 输出的 JSON 路径
            paddle_json_path: PaddleOCR 输出的 JSON 路径
            data_format: 输出格式（固定为 'mineru'）
        
        Returns:
            MinerU 格式的合并数据
        """
        # 加载数据
        with open(dotsocr_json_path, 'r', encoding='utf-8') as f:
            dotsocr_data = json.load(f)
        
        with open(paddle_json_path, 'r', encoding='utf-8') as f:
            paddle_data = json.load(f)
        
        # 🎯 提取 PaddleOCR 的文字框信息
        paddle_text_boxes = self.bbox_extractor.extract_paddle_text_boxes(paddle_data)
        
        # 🎯 使用专门的 DotsOCR 处理方法（自动转换为 MinerU 格式）
        merged_data = self.data_processor.process_dotsocr_data(
            dotsocr_data, paddle_text_boxes
        )
        
        return merged_data
    
    def generate_enhanced_markdown(self, merged_data: List[Dict], 
                                   output_path: str = None,
                                   source_file: str = None,
                                   data_format: str = 'mineru') -> str:
        """
        生成增强的 Markdown（MinerU 格式）
        
        Args:
            merged_data: 合并后的数据（MinerU 格式）
            output_path: 输出路径
            source_file: 源文件路径
            data_format: 数据格式（固定为 'mineru'）
        """
        # 🎯 强制使用 MinerU 格式生成 Markdown
        return self.markdown_generator.generate_enhanced_markdown(
            merged_data, output_path, source_file, data_format='mineru'
        )
    
    def extract_table_cells_with_bbox(self, merged_data: List[Dict]) -> List[Dict]:
        """提取所有表格单元格及其 bbox 信息"""
        # 🎯 直接复用 BBoxExtractor 的方法
        return self.bbox_extractor.extract_table_cells_with_bbox(merged_data)