feat: 添加PaddleOCR_VL和PaddleOCR结果合并模块，支持数据加载和Markdown生成

merger/paddleocr_vl_merger.py

@@ -0,0 +1,76 @@
+"""
+PaddleOCR_VL 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
+except ImportError:
+    from text_matcher import TextMatcher
+    from bbox_extractor import BBoxExtractor
+    from data_processor import DataProcessor
+    from markdown_generator import MarkdownGenerator
+
+
+class PaddleOCRVLMerger:
+    """PaddleOCR_VL 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()
+    
+    def merge_table_with_bbox(self, paddleocr_vl_json_path: str, 
+                             paddle_json_path: str) -> List[Dict]:
+        """
+        合并 PaddleOCR_VL 和 PaddleOCR 的结果
+        
+        Args:
+            paddleocr_vl_json_path: PaddleOCR_VL 输出的 JSON 路径
+            paddle_json_path: PaddleOCR 输出的 JSON 路径
+        
+        Returns:
+            合并后的结果 (MinerU 格式)
+        """
+        # 加载数据
+        with open(paddleocr_vl_json_path, 'r', encoding='utf-8') as f:
+            paddleocr_vl_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)
+        
+        # 处理 PaddleOCR_VL 的数据
+        merged_data = self.data_processor.process_paddleocr_vl_data(
+            paddleocr_vl_data, paddle_text_boxes
+        )
+        
+        return merged_data
+    
+    def generate_enhanced_markdown(self, merged_data: List[Dict], 
+                                   output_path: str = None,
+                                   source_file: str = None) -> str:
+        """生成增强的 Markdown"""
+        return self.markdown_generator._generate_paddleocr_vl_markdown(
+            merged_data, output_path, source_file
+        )
+    
+    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"""
+        return self.bbox_extractor.extract_table_cells_with_bbox(merged_data)