gateway/modules/workflow/documentManager.py

"""
Document Manager Module for handling document operations and content extraction.
"""

import logging
from typing import Dict, Any, List, Optional
from datetime import datetime
from modules.interfaces.serviceChatModel import ChatDocument, ChatContent
from modules.workflow.documentProcessor import getDocumentContents

logger = logging.getLogger(__name__)

class DocumentManager:
    """Manager for document operations and content extraction."""
    
    _instance = None
    
    @classmethod
    def getInstance(cls):
        """Return a singleton instance of the document manager."""
        if cls._instance is None:
            cls._instance = cls()
        return cls._instance
    
    def __init__(self):
        """Initialize the document manager."""
        if DocumentManager._instance is not None:
            raise RuntimeError("Singleton instance already exists - use getInstance()")
        
        self.service = None
    
    def initialize(self, service=None):
        """Initialize or update the manager with service references."""
        if service:
            # Validate required interfaces
            required_interfaces = ['base', 'msft', 'google']
            missing_interfaces = []
            for interface in required_interfaces:
                if not hasattr(service, interface):
                    missing_interfaces.append(interface)
            
            if missing_interfaces:
                logger.warning(f"Service container missing required interfaces: {', '.join(missing_interfaces)}")
                return False
        
        self.service = service
        return True
    
    async def extractContent(self, fileId: int) -> Optional[ChatDocument]:
        """
        Extract content from a file.
        
        Args:
            fileId: ID of the file to process
            
        Returns:
            ChatDocument object with extracted content or None if processing failed
        """
        try:
            # Get file metadata and content from service
            fileMetadata = await self.service.base.getFileMetadata(fileId)
            fileContent = await self.service.base.getFileContent(fileId)
            
            if not fileMetadata or not fileContent:
                logger.error(f"Could not retrieve file data for fileId {fileId}")
                return None
            
            # Extract content using documentProcessor
            contents = getDocumentContents(fileMetadata, fileContent)
            
            # Create ChatDocument
            return ChatDocument(
                id=str(fileId),  # Using fileId as document id
                fileId=fileId,
                filename=fileMetadata.get("name", "unknown"),
                fileSize=fileMetadata.get("size", 0),
                mimeType=fileMetadata.get("mimeType", "application/octet-stream"),
                contents=contents
            )
            
        except Exception as e:
            logger.error(f"Error extracting content from file {fileId}: {str(e)}", exc_info=True)
            return None
    
    async def processFileIds(self, fileIds: List[int]) -> List[ChatDocument]:
        """
        Process multiple files and extract their contents.
        
        Args:
            fileIds: List of file IDs to process
            
        Returns:
            List of ChatDocument objects
        """
        documents = []
        for fileId in fileIds:
            try:
                document = await self.extractContent(fileId)
                if document:
                    documents.append(document)
            except Exception as e:
                logger.error(f"Error processing file {fileId}: {str(e)}")
                continue
        return documents
    
    async def getFileContent(self, fileId: int) -> Optional[bytes]:
        """
        Get raw file content.
        
        Args:
            fileId: ID of the file
            
        Returns:
            File content as bytes or None if not found
        """
        try:
            return await self.service.base.getFileContent(fileId)
        except Exception as e:
            logger.error(f"Error getting file content for {fileId}: {str(e)}")
            return None
    
    async def getFileMetadata(self, fileId: int) -> Optional[Dict[str, Any]]:
        """
        Get file metadata.
        
        Args:
            fileId: ID of the file
            
        Returns:
            File metadata dictionary or None if not found
        """
        try:
            return await self.service.base.getFileMetadata(fileId)
        except Exception as e:
            logger.error(f"Error getting file metadata for {fileId}: {str(e)}")
            return None
    
    async def saveFile(self, filename: str, content: bytes, mimeType: str) -> Optional[int]:
        """
        Save a new file.
        
        Args:
            filename: Name of the file
            content: File content as bytes
            mimeType: MIME type of the file
            
        Returns:
            File ID if successful, None otherwise
        """
        try:
            return await self.service.base.saveFile(filename, content, mimeType)
        except Exception as e:
            logger.error(f"Error saving file {filename}: {str(e)}")
            return None
    
    async def deleteFile(self, fileId: int) -> bool:
        """
        Delete a file.
        
        Args:
            fileId: ID of the file to delete
            
        Returns:
            True if successful, False otherwise
        """
        try:
            return await self.service.base.deleteFile(fileId)
        except Exception as e:
            logger.error(f"Error deleting file {fileId}: {str(e)}")
            return False

# Singleton factory for the document manager
def getDocumentManager():
    return DocumentManager.getInstance()