"""
OCR服务模块
---------
提供OCR识别服务，协调OCR流程。
"""

from typing import Dict, List, Optional, Tuple, Union, Any
import os

from ..config.settings import ConfigManager
from ..core.utils.log_utils import get_logger
from ..core.ocr.table_ocr import OCRProcessor

logger = get_logger(__name__)

class OCRService:
    """
    OCR识别服务：协调OCR流程
    """
    
    def __init__(self, config: Optional[ConfigManager] = None):
        """
        初始化OCR服务
        
        Args:
            config: 配置管理器，如果为None则创建新的
        """
        logger.info("初始化OCRService")
        self.config = config or ConfigManager()
        
        # 创建OCR处理器
        self.ocr_processor = OCRProcessor(self.config)
        
        logger.info("OCRService初始化完成")
    
    def get_unprocessed_images(self) -> List[str]:
        """
        获取待处理的图片列表
        
        Returns:
            待处理图片路径列表
        """
        return self.ocr_processor.get_unprocessed_images()
    
    def process_image(self, image_path: str) -> Optional[str]:
        """
        处理单个图片文件
        
        Args:
            image_path: 图片文件路径
            
        Returns:
            生成的Excel文件路径，如果处理失败则返回None
        """
        try:
            # 检查文件是否存在
            if not os.path.exists(image_path):
                logger.error(f"文件不存在: {image_path}")
                return None
                
            # 检查文件类型
            if not self._is_valid_image(image_path):
                logger.error(f"不支持的文件类型: {image_path}")
                return None
                
            # 检查是否已处理
            excel_file = self._get_excel_path(image_path)
            if os.path.exists(excel_file):
                logger.info(f"文件已处理过，跳过OCR识别: {image_path}")
                return excel_file
                
            # 执行OCR识别
            result = self.ocr_processor.process_image(image_path)
            if not result:
                logger.error(f"OCR识别失败: {image_path}")
                return None
                
            # 生成Excel文件
            excel_file = self._generate_excel(result, image_path)
            if not excel_file:
                logger.error(f"生成Excel文件失败: {image_path}")
                return None
                
            logger.info(f"处理完成: {image_path} -> {excel_file}")
            return excel_file
            
        except Exception as e:
            logger.error(f"处理图片时发生错误: {e}", exc_info=True)
            return None
    
    def process_images_batch(self, batch_size: int = None, max_workers: int = None) -> Tuple[int, int]:
        """
        批量处理图片
        
        Args:
            batch_size: 批处理大小
            max_workers: 最大线程数
            
        Returns:
            (总处理数, 成功处理数)元组
        """
        logger.info(f"OCRService开始批量处理图片, batch_size={batch_size}, max_workers={max_workers}")
        return self.ocr_processor.process_images_batch(batch_size, max_workers)
    
    # 添加batch_process作为process_images_batch的别名，确保兼容性
    def batch_process(self, batch_size: int = None, max_workers: int = None) -> Tuple[int, int]:
        """
        批量处理图片（别名方法，与process_images_batch功能相同）
        
        Args:
            batch_size: 批处理大小
            max_workers: 最大线程数
            
        Returns:
            (总处理数, 成功处理数)元组
        """
        logger.info(f"OCRService.batch_process被调用，转发到process_images_batch")
        return self.process_images_batch(batch_size, max_workers)
    
    def validate_image(self, image_path: str) -> bool:
        """
        验证图片是否有效
        
        Args:
            image_path: 图片路径
            
        Returns:
            图片是否有效
        """
        return self.ocr_processor.validate_image(image_path)
    
    def _is_valid_image(self, image_path: str) -> bool:
        """
        检查文件是否为有效的图片格式
        
        Args:
            image_path: 图片文件路径
            
        Returns:
            是否为有效图片格式
        """
        return self.validate_image(image_path)
    
    def _get_excel_path(self, image_path: str) -> str:
        """
        根据图片路径生成对应的Excel文件路径
        
        Args:
            image_path: 图片文件路径
            
        Returns:
            Excel文件路径
        """
        # 获取文件名（不含扩展名）
        base_name = os.path.splitext(os.path.basename(image_path))[0]
        # 生成Excel文件路径
        output_dir = self.config.get('Paths', 'output_folder', fallback='data/output')
        excel_path = os.path.join(output_dir, f"{base_name}.xlsx")
        return excel_path
    
    def _generate_excel(self, ocr_result: dict, image_path: str) -> Optional[str]:
        """
        根据OCR结果生成Excel文件
        
        Args:
            ocr_result: OCR识别结果
            image_path: 原始图片路径
            
        Returns:
            生成的Excel文件路径，失败返回None
        """
        try:
            excel_path = self._get_excel_path(image_path)
            
            # 确保输出目录存在
            os.makedirs(os.path.dirname(excel_path), exist_ok=True)
            
            # 调用OCR处理器的Excel生成功能
            if hasattr(self.ocr_processor, 'generate_excel'):
                success = self.ocr_processor.generate_excel(ocr_result, excel_path)
                if success:
                    return excel_path
            else:
                # 如果OCR处理器没有generate_excel方法，直接返回路径
                # 假设OCR处理器已经生成了Excel文件
                if os.path.exists(excel_path):
                    return excel_path
            
            return None
            
        except Exception as e:
            logger.error(f"生成Excel文件时发生错误: {e}", exc_info=True)
            return None