tools/libreoffice_tools.py

import os
import subprocess
import platform
from smolagents import tool

def get_libreoffice_path():
    """
    Get the correct LibreOffice path based on the operating system.
    
    Returns:
        str: Path to LibreOffice executable or None if not found
    """
    system = platform.system()
    
    if system == "Darwin":  # macOS
        # Common LibreOffice installation paths on macOS
        possible_paths = [
            "/Applications/LibreOffice.app/Contents/MacOS/soffice",
            "/Applications/LibreOffice Developer Edition.app/Contents/MacOS/soffice",
            "/opt/homebrew/bin/soffice",  # Homebrew installation
            "/usr/local/bin/soffice"
        ]
        
        for path in possible_paths:
            if os.path.exists(path):
                return path
    
    elif system == "Linux":
        # Common LibreOffice paths on Linux
        possible_paths = [
            "/usr/bin/libreoffice",
            "/usr/bin/soffice",
            "/snap/bin/libreoffice",
            "/usr/local/bin/libreoffice"
        ]
        
        for path in possible_paths:
            if os.path.exists(path):
                return path
    
    elif system == "Windows":
        # Common LibreOffice paths on Windows
        possible_paths = [
            r"C:\Program Files\LibreOffice\program\soffice.exe",
            r"C:\Program Files (x86)\LibreOffice\program\soffice.exe"
        ]
        
        for path in possible_paths:
            if os.path.exists(path):
                return path
    
    # Try to find it in PATH as fallback
    try:
        result = subprocess.run(['which', 'soffice'], capture_output=True, text=True)
        if result.returncode == 0:
            return result.stdout.strip()
    except:
        pass
    
    try:
        result = subprocess.run(['which', 'libreoffice'], capture_output=True, text=True)
        if result.returncode == 0:
            return result.stdout.strip()
    except:
        pass
    
    return None

@tool
def convert_to_pdf_with_libreoffice(input_file: str, output_dir: str = None) -> str:
    """
    Convert a document to PDF using LibreOffice.
    
    Args:
        input_file: Path to the input document
        output_dir: Directory to save the PDF (optional, defaults to same directory as input)
    
    Returns:
        str: Path to the generated PDF file or error message
    """
    libreoffice_path = get_libreoffice_path()
    
    if not libreoffice_path:
        return "LibreOffice not found. Please install LibreOffice from https://www.libreoffice.org/"
    
    if not os.path.exists(input_file):
        return f"Input file not found: {input_file}"
    
    if output_dir is None:
        output_dir = os.path.dirname(input_file)
    
    if not os.path.exists(output_dir):
        os.makedirs(output_dir, exist_ok=True)
    
    try:
        # Use LibreOffice headless mode to convert to PDF
        cmd = [
            libreoffice_path,
            '--headless',
            '--convert-to', 'pdf',
            '--outdir', output_dir,
            input_file
        ]
        
        result = subprocess.run(cmd, capture_output=True, text=True, timeout=60)
        
        if result.returncode == 0:
            # Generate expected output filename
            base_name = os.path.splitext(os.path.basename(input_file))[0]
            pdf_path = os.path.join(output_dir, f"{base_name}.pdf")
            
            if os.path.exists(pdf_path):
                return pdf_path
            else:
                return f"PDF conversion completed but file not found at expected location: {pdf_path}"
        else:
            return f"LibreOffice conversion failed: {result.stderr}"
            
    except subprocess.TimeoutExpired:
        return "LibreOffice conversion timed out after 60 seconds"
    except Exception as e:
        return f"Error during LibreOffice conversion: {str(e)}"

@tool
def check_libreoffice_availability() -> bool:
    """
    Check if LibreOffice is available on the system.
    
    Returns:
        bool: True if LibreOffice is available, False otherwise
    """
    libreoffice_path = get_libreoffice_path()
    return libreoffice_path is not None

@tool
def get_libreoffice_info() -> str:
    """
    Get detailed information about LibreOffice installation for troubleshooting.
    
    Returns:
        str: Detailed information about LibreOffice availability and installation
    """
    libreoffice_path = get_libreoffice_path()
    
    if not libreoffice_path:
        system = platform.system()
        install_info = {
            "Darwin": "Install with: brew install libreoffice OR download from https://www.libreoffice.org/",
            "Linux": "Install with: sudo apt install libreoffice OR sudo yum install libreoffice",
            "Windows": "Download from https://www.libreoffice.org/"
        }
        
        return f"LibreOffice not found on {system}. {install_info.get(system, 'Install from https://www.libreoffice.org/')}"
    
    try:
        # Get version info
        result = subprocess.run([libreoffice_path, '--version'], capture_output=True, text=True, timeout=10)
        version_info = result.stdout.strip() if result.returncode == 0 else "Version unknown"
        
        return f"LibreOffice found at: {libreoffice_path}\nVersion: {version_info}"
    except:
        return f"LibreOffice found at: {libreoffice_path}\nVersion: Unable to determine"

if __name__ == "__main__":
    # Test the LibreOffice detection
    print(check_libreoffice_availability())