feat: add extraction_service (PDF/Docx/Txt) and update .gitignore to exclude venv

extraction_service/services/pdf_processor.py

@@ -0,0 +1,192 @@
+"""
+PDF处理主服务
+
+实现顺序降级策略：
+1. 检测语言
+2. 中文PDF → PyMuPDF（快速）
+3. 英文PDF → Nougat → 失败降级PyMuPDF
+"""
+
+from typing import Dict, Any, Optional
+from loguru import logger
+
+from .language_detector import detect_language
+from .nougat_extractor import extract_pdf_nougat, check_nougat_available
+from .pdf_extractor import extract_pdf_pymupdf
+
+
+def extract_pdf(
+    file_path: str,
+    force_method: Optional[str] = None
+) -> Dict[str, Any]:
+    """
+    PDF提取主函数（顺序降级策略）
+    
+    处理流程：
+    1. 检测语言
+    2. 中文 → 直接PyMuPDF
+    3. 英文 → 尝试Nougat → 失败降级PyMuPDF
+    
+    Args:
+        file_path: PDF文件路径
+        force_method: 强制使用的方法 ('nougat' | 'pymupdf')
+    
+    Returns:
+        {
+            "success": True,
+            "method": "nougat" | "pymupdf",
+            "reason": "chinese_pdf" | "english_pdf" | "nougat_failed" | "nougat_low_quality",
+            "text": "提取的文本",
+            "metadata": {...}
+        }
+    """
+    try:
+        logger.info(f"开始处理PDF: {file_path}")
+        
+        # Step 1: 语言检测
+        logger.info("[Step 1] 检测PDF语言...")
+        language = detect_language(file_path)
+        logger.info(f"检测结果: {language}")
+        
+        # 如果强制指定方法
+        if force_method:
+            logger.info(f"强制使用方法: {force_method}")
+            
+            if force_method == 'nougat':
+                return extract_pdf_nougat(file_path)
+            elif force_method == 'pymupdf':
+                result = extract_pdf_pymupdf(file_path)
+                result['reason'] = 'force_pymupdf'
+                return result
+        
+        # Step 2: 中文PDF → 直接PyMuPDF
+        if language == 'chinese':
+            logger.info("[Step 2] 中文PDF，使用PyMuPDF快速处理")
+            
+            result = extract_pdf_pymupdf(file_path)
+            
+            if result['success']:
+                result['reason'] = 'chinese_pdf'
+                result['detected_language'] = language
+                logger.info("✅ PyMuPDF处理成功（中文PDF）")
+                return result
+            else:
+                logger.error("❌ PyMuPDF处理失败")
+                return result
+        
+        # Step 3: 英文PDF → 尝试Nougat
+        logger.info("[Step 3] 英文PDF，尝试Nougat高质量解析")
+        
+        # 检查Nougat是否可用
+        if not check_nougat_available():
+            logger.warning("⚠️ Nougat不可用，降级到PyMuPDF")
+            
+            result = extract_pdf_pymupdf(file_path)
+            if result['success']:
+                result['reason'] = 'nougat_unavailable'
+                result['detected_language'] = language
+            return result
+        
+        # 尝试Nougat
+        try:
+            nougat_result = extract_pdf_nougat(file_path)
+            
+            if not nougat_result['success']:
+                logger.warning("⚠️ Nougat提取失败，降级到PyMuPDF")
+                raise Exception(nougat_result.get('error', 'Nougat failed'))
+            
+            # 质量检查
+            quality_score = nougat_result['metadata'].get('quality_score', 0)
+            
+            logger.info(f"Nougat质量评分: {quality_score:.2f}")
+            
+            # 质量阈值：0.7
+            if quality_score >= 0.7:
+                logger.info("✅ Nougat处理成功（质量合格）")
+                nougat_result['reason'] = 'english_pdf_high_quality'
+                nougat_result['detected_language'] = language
+                return nougat_result
+            else:
+                logger.warning(f"⚠️ Nougat质量不足: {quality_score:.2f}，降级到PyMuPDF")
+                raise Exception(f"Quality too low: {quality_score}")
+        
+        except Exception as e:
+            logger.warning(f"Nougat处理失败: {str(e)}，降级到PyMuPDF")
+        
+        # Step 4: 降级到PyMuPDF
+        logger.info("[Step 4] 降级使用PyMuPDF")
+        
+        result = extract_pdf_pymupdf(file_path)
+        
+        if result['success']:
+            result['reason'] = 'nougat_failed_or_low_quality'
+            result['detected_language'] = language
+            result['fallback'] = True
+            logger.info("✅ PyMuPDF处理成功（降级方案）")
+        else:
+            logger.error("❌ PyMuPDF处理也失败了")
+        
+        return result
+    
+    except Exception as e:
+        logger.error(f"PDF处理完全失败: {str(e)}")
+        return {
+            "success": False,
+            "error": str(e),
+            "method": "unknown"
+        }
+
+
+def get_pdf_processing_strategy(file_path: str) -> Dict[str, Any]:
+    """
+    获取PDF处理策略（不实际提取）
+    
+    用于预览将使用哪种方法
+    
+    Args:
+        file_path: PDF文件路径
+    
+    Returns:
+        {
+            "detected_language": "chinese" | "english",
+            "recommended_method": "nougat" | "pymupdf",
+            "reason": "...",
+            "nougat_available": True | False
+        }
+    """
+    try:
+        # 检测语言
+        language = detect_language(file_path)
+        
+        # 检查Nougat可用性
+        nougat_available = check_nougat_available()
+        
+        # 决定策略
+        if language == 'chinese':
+            recommended_method = 'pymupdf'
+            reason = '中文PDF，推荐使用PyMuPDF快速处理'
+        elif nougat_available:
+            recommended_method = 'nougat'
+            reason = '英文PDF，推荐使用Nougat高质量解析'
+        else:
+            recommended_method = 'pymupdf'
+            reason = 'Nougat不可用，使用PyMuPDF'
+        
+        return {
+            "detected_language": language,
+            "recommended_method": recommended_method,
+            "reason": reason,
+            "nougat_available": nougat_available
+        }
+    
+    except Exception as e:
+        logger.error(f"获取处理策略失败: {str(e)}")
+        return {
+            "error": str(e)
+        }
+
+
+
+
+
+