import sys
from pathlib import Path

# Ensure project root is on sys.path so package imports work when running this script directly
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
from markdownconverter.core.core import convert_pdf_to_markdown

pdf = Path(
    r"c:\src\____GitProjects\SXXXXXXX_MarkdownConverter\doc\ICD_DECD_FTH - GRIFO-F_TH, Data Exchange Control Document for, rev -A, Draft 2.pdf"
)
md_out = pdf.with_suffix(".md")
img_folder = pdf.parent / f"{pdf.stem}_images"

print("Input PDF:", pdf)
print("Output MD:", md_out)
print("Image folder:", img_folder)

try:
    # For testing, limit to first 5 pages to speed up debugging
    result = convert_pdf_to_markdown(
        str(pdf),
        str(md_out),
        extract_images=True,
        image_folder=str(img_folder),
        page_limit=5,
    )
    print("\nConversion completed. Markdown saved to:", result)
    # Print preview
    with open(result, "r", encoding="utf-8") as f:
        lines = f.readlines()
    preview = "".join(lines[:200])
    print("\n--- Markdown preview (first 200 lines) ---\n")
    print(preview)
    # Count images
    if img_folder.exists():
        imgs = list(img_folder.glob("*"))
        print(f"\nImages extracted: {len(imgs)}")
    else:
        print("\nImages extracted: 0")
except Exception as e:
    import traceback

    print("Conversion failed:", e)
    traceback.print_exc()