"""Run chunking on all sample files in data/."""

from __future__ import annotations

import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "backend"))

from rag_cut.models import SplitConfig, SplitMode
from rag_cut.pipeline import chunk_document

DATA = Path(__file__).resolve().parent.parent / "data"
OUT = Path(__file__).resolve().parent.parent / "storage"


def main() -> None:
    for path in sorted(DATA.iterdir()):
        if not path.is_file():
            continue
        ext = path.suffix.lower()
        if ext == ".xlsx":
            config = SplitConfig(mode=SplitMode.BY_ROW, rows_per_chunk=5)
        else:
            config = SplitConfig(mode=SplitMode.DEFAULT)

        print(f"\n{'=' * 60}\n{path.name} ({ext})")
        result = chunk_document(path, config=config)
        print(f"blocks={result.block_count} chunks={result.chunk_count} mode={result.split_mode.value}")

        out_file = OUT / f"{path.stem}_chunks.json"
        out_file.write_text(result.model_dump_json(indent=2), encoding="utf-8")
        print(f"saved -> {out_file.name}")

        if result.chunks:
            c0 = result.chunks[0]
            print(f"chunk[0] types={c0.block_types} chars={c0.char_count}")
            print(c0.content[:300].replace("\n", " ") + "...")


if __name__ == "__main__":
    main()