"""Rebuild the bundled PDF table-of-contents index (references/pdf/_toc.json).

Self-contained: reads every PDF bundled under the skill's references/pdf/ and
writes the multi-level TOC next to them. Run after adding/updating manuals.

    /mnt/c/Users/NAURA/.local/bin/uv.exe run --no-project --with pymupdf \
        python .claude/skills/halcon/scripts/extract_toc.py
"""
import fitz, os, glob, json

# references/pdf/ relative to this script (scripts/ -> ../references/pdf)
HERE = os.path.dirname(os.path.abspath(__file__))
PDF_DIR = os.path.normpath(os.path.join(HERE, "..", "references", "pdf"))
OUT = os.path.join(PDF_DIR, "_toc.json")

out = {}
for p in sorted(glob.glob(os.path.join(PDF_DIR, "*.pdf"))):
    name = os.path.basename(p)
    try:
        doc = fitz.open(p)
        out[name] = {"pages": doc.page_count, "toc": doc.get_toc()}  # [level,title,page]
        doc.close()
    except Exception as e:
        out[name] = {"error": str(e)}

with open(OUT, "w", encoding="utf-8") as f:
    json.dump(out, f, ensure_ascii=False, indent=1)

for name, v in out.items():
    if "error" in v:
        print(f"{name}: ERROR {v['error']}")
    else:
        print(f"{name}: {v['pages']} pages, {len(v['toc'])} toc entries")
print("wrote", OUT)