# Copyright (c) 2025 Patrick Motsch
# All rights reserved.

"""
Document Index helper for Context operations.
Handles parsing and formatting of document indexes.
"""

import logging
from typing import Dict, Any
from datetime import datetime, UTC

logger = logging.getLogger(__name__)

class DocumentIndexHelper:
    """Helper for document index operations"""
    
    def __init__(self, methodInstance):
        """
        Initialize document index helper.
        
        Args:
            methodInstance: Instance of MethodContext (for access to services)
        """
        self.method = methodInstance
        self.services = methodInstance.services
    
    def parseDocumentIndex(self, documentsIndex: str, workflow: Any) -> Dict[str, Any]:
        """Parse the document index string into structured data."""
        try:
            indexData = {
                "workflowId": getattr(workflow, 'id', 'unknown'),
                "generatedAt": datetime.now(UTC).isoformat(),
                "totalDocuments": 0,
                "rounds": [],
                "documentReferences": []
            }
            
            # Extract document references from the index string
            lines = documentsIndex.split('\n')
            currentRound = None
            currentDocList = None
            
            for line in lines:
                line = line.strip()
                if not line:
                    continue
                
                # Check for round headers
                if "Current round documents:" in line:
                    currentRound = "current"
                    continue
                elif "Past rounds documents:" in line:
                    currentRound = "past"
                    continue
                
                # Check for document list references (docList:...)
                if line.startswith("- docList:"):
                    docListRef = line.replace("- docList:", "").strip()
                    currentDocList = {
                        "reference": docListRef,
                        "round": currentRound,
                        "documents": []
                    }
                    indexData["rounds"].append(currentDocList)
                    continue
                
                # Check for individual document references (docItem:...)
                if line.startswith("  - docItem:") or line.startswith("- docItem:"):
                    docItemRef = line.replace("  - docItem:", "").replace("- docItem:", "").strip()
                    indexData["documentReferences"].append({
                        "reference": docItemRef,
                        "round": currentRound,
                        "docList": currentDocList["reference"] if currentDocList else None
                    })
                    indexData["totalDocuments"] += 1
                    if currentDocList:
                        currentDocList["documents"].append(docItemRef)
            
            return indexData
            
        except Exception as e:
            logger.error(f"Error parsing document index: {str(e)}")
            return {
                "workflowId": getattr(workflow, 'id', 'unknown'),
                "error": f"Failed to parse document index: {str(e)}",
                "rawIndex": documentsIndex
            }