from typing import List, Dict
import pandas as pd
from datetime import datetime
from pathlib import Path
from jinja2 import Environment, FileSystemLoader
from weasyprint import HTML
import logging

logger = logging.getLogger(__name__)

class PullSheetService:
    def __init__(self):
        self.template_dir = Path("app/data/assets/templates")
        self.env = Environment(loader=FileSystemLoader(str(self.template_dir)))
        self.template = self.env.get_template("pull_sheet.html")
        self.output_dir = Path("app/data/cache/tcgplayer/pull_sheets")
        self.output_dir.mkdir(parents=True, exist_ok=True)
        
    def generate_pull_sheet_pdf(self, csv_path: str) -> str:
        """Generate a PDF pull sheet from a CSV file.
        
        Args:
            csv_path: Path to the CSV file containing pull sheet data
            
        Returns:
            Path to the generated PDF file
        """
        try:
            # Read and process CSV data
            items = self._read_and_process_csv(csv_path)
            
            # Prepare template data
            template_data = {
                'items': items,
                'generation_date': datetime.now().strftime("%Y-%m-%d %H:%M:%S")
            }
            
            # Render HTML
            html_content = self.template.render(**template_data)
            
            # Generate PDF
            pdf_path = self.output_dir / f"pull_sheet_{datetime.now().strftime('%Y%m%d_%H%M%S')}.pdf"
            HTML(string=html_content).write_pdf(str(pdf_path))
            
            return str(pdf_path)
            
        except Exception as e:
            logger.error(f"Error generating pull sheet PDF: {str(e)}")
            raise
            
    def _read_and_process_csv(self, csv_path: str) -> List[Dict]:
        """Read and process CSV data using pandas.
        
        Args:
            csv_path: Path to the CSV file
            
        Returns:
            List of processed items
        """
        # Read CSV into pandas DataFrame
        df = pd.read_csv(csv_path)
        
        # Filter out the "Orders Contained in Pull Sheet" row
        df = df[df['Product Line'] != 'Orders Contained in Pull Sheet:']
        
        # Convert Set Release Date to datetime
        df['Set Release Date'] = pd.to_datetime(df['Set Release Date'], format='%m/%d/%Y %H:%M:%S')
        
        # Sort by Set Release Date (descending) and then Product Name (ascending)
        df = df.sort_values(['Set Release Date', 'Product Name'], ascending=[False, True])
        
        # Convert to list of dictionaries
        items = []
        for _, row in df.iterrows():
            items.append({
                'product_name': row['Product Name'],
                'condition': row['Condition'],
                'quantity': str(int(row['Quantity'])),  # Convert to string for template
                'set': row['Set'],
                'rarity': row['Rarity']
            })
                
        return items