tools/python/compress_pdf.py

#!/usr/bin/env python3
"""Compress PDF using Ghostscript."""
import argparse, json, sys, subprocess, shutil
from pathlib import Path

QUALITY_MAP = {
    'low': '/prepress',
    'medium': '/ebook',
    'high': '/screen',
}

def find_gs():
    """Find Ghostscript executable."""
    for name in ['gs', 'gswin64c', 'gswin32c']:
        path = shutil.which(name)
        if path:
            return path
    # Common paths
    import platform
    if platform.system() == 'Windows':
        import glob
        for pattern in ['C:/Program Files/gs/*/bin/gswin64c.exe', 'C:/Program Files (x86)/gs/*/bin/gswin32c.exe']:
            matches = glob.glob(pattern)
            if matches:
                return matches[0]
    return 'gs'

def compress(input_path, output_path, level='medium'):
    gs = find_gs()
    quality = QUALITY_MAP.get(level, '/ebook')
    
    if not output_path:
        output_path = str(Path(input_path).with_stem(Path(input_path).stem + '_compressed'))
    
    cmd = [
        gs, '-sDEVICE=pdfwrite', '-dCompatibilityLevel=1.4',
        f'-dPDFSETTINGS={quality}',
        '-dNOPAUSE', '-dQUIET', '-dBATCH',
        f'-sOutputFile={output_path}',
        input_path
    ]
    
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=300)
    if result.returncode != 0:
        raise RuntimeError(f"Ghostscript error: {result.stderr}")
    
    return output_path

def main():
    parser = argparse.ArgumentParser(description='Compress PDF')
    parser.add_argument('--input', required=True)
    parser.add_argument('--output', required=True)
    parser.add_argument('--level', default='medium', choices=['low', 'medium', 'high'])
    args = parser.parse_args()
    try:
        result = compress(args.input, args.output, args.level)
        original_size = Path(args.input).stat().st_size
        compressed_size = Path(result).stat().st_size
        reduction = (1 - compressed_size / original_size) * 100 if original_size > 0 else 0
        print(json.dumps({
            "success": True, "output": result,
            "message": f"PDF compressed by {reduction:.1f}% ({original_size} -> {compressed_size} bytes)"
        }))
    except Exception as e:
        print(json.dumps({"success": False, "output": "", "message": str(e)}))
        sys.exit(1)

if __name__ == '__main__':
    main()