from pathlib import Path
import subprocess
import tempfile
import os
from typing import Dict, List, Optional

class DocumentProcessor:
    def __init__(self):
        self.supported_extensions = {
            'doc': 'libreoffice',
            'docx': 'libreoffice',
            'odt': 'libreoffice',
            'rtf': 'libreoffice',
            'txt': 'libreoffice',
            'html': 'libreoffice',
            'htm': 'libreoffice',
            'xls': 'libreoffice',
            'xlsx': 'libreoffice',
            'ppt': 'libreoffice',
            'pptx': 'libreoffice',
            'pdf': 'pdf'
        }

    def convert_to_pdf(self, input_file: Path) -> bytes:
        """
        Convert a document to PDF format
        """
        if not input_file.exists():
            raise FileNotFoundError(f"Input file not found: {input_file}")

        input_extension = input_file.suffix.lower()[1:]  # Remove the dot
        if input_extension not in self.supported_extensions:
            raise ValueError(f"Unsupported file extension: {input_extension}")

        if input_extension == 'pdf':
            # If it's already a PDF, just read and return it
            with open(input_file, 'rb') as f:
                return f.read()

        # Use LibreOffice for conversion
        with tempfile.TemporaryDirectory() as temp_dir:
            output_file = Path(temp_dir) / f"{input_file.stem}.pdf"
            
            # Convert using LibreOffice
            cmd = [
                'libreoffice',
                '--headless',
                '--convert-to', 'pdf',
                '--outdir', str(temp_dir),
                str(input_file)
            ]
            
            try:
                subprocess.run(cmd, check=True, capture_output=True)
            except subprocess.CalledProcessError as e:
                raise RuntimeError(f"Conversion failed: {e.stderr.decode()}")

            if not output_file.exists():
                raise RuntimeError("Conversion failed: Output file not created")

            # Read and return the PDF content
            with open(output_file, 'rb') as f:
                return f.read()

    def batch_convert_directory(self, directory: str) -> List[Dict]:
        """
        Convert all documents in a directory to PDF format
        """
        directory_path = Path(directory)
        if not directory_path.exists():
            raise FileNotFoundError(f"Directory not found: {directory}")

        results = []
        for file_path in directory_path.glob('*'):
            if file_path.is_file() and file_path.suffix.lower()[1:] in self.supported_extensions:
                try:
                    pdf_content = self.convert_to_pdf(file_path)
                    output_file = file_path.with_suffix('.pdf')
                    with open(output_file, 'wb') as f:
                        f.write(pdf_content)
                    
                    results.append({
                        "source_file": str(file_path),
                        "output_file": str(output_file),
                        "status": "success"
                    })
                except Exception as e:
                    results.append({
                        "source_file": str(file_path),
                        "status": "error",
                        "error": str(e)
                    })

        return results