"""Row-based splitting for spreadsheet documents."""

from __future__ import annotations

from rag_cut.models import Block, BlockType, SplitConfig
from rag_cut.parsers.pdf.tables import (
    build_table_embedding_text,
    detect_spreadsheet_layout,
    extract_table_keywords,
    rows_to_markdown,
)


def _chunk_meta(table_block: Block, chunk_rows: list[list[str]], md: str, row_range: list[int]) -> dict:
    """Build per-chunk metadata without leaking the full source table."""
    header_rows = table_block.meta.get("header_rows") or 1
    keywords = extract_table_keywords(
        table_block.meta.get("table_title") or "",
        md,
        table_block.meta.get("table_description") or "",
    )
    embedding_text = build_table_embedding_text(
        table_title=table_block.meta.get("table_title") or "",
        markdown=md,
        description=table_block.meta.get("table_description") or "",
        keywords=keywords,
    )
    return {
        "sheet": table_block.meta.get("sheet"),
        "table_title": table_block.meta.get("table_title"),
        "table_description": table_block.meta.get("table_description"),
        "header_rows": header_rows,
        "header_row_start": table_block.meta.get("header_row_start"),
        "header_row_end": table_block.meta.get("header_row_end"),
        "data_start_row": table_block.meta.get("data_start_row"),
        "preamble_rows": table_block.meta.get("preamble_rows", 0),
        "row_count": len(chunk_rows),
        "col_count": max((len(r) for r in chunk_rows), default=0),
        "chunk_rows": chunk_rows,
        "row_range": row_range,
        "keywords": keywords,
        "embedding_text": embedding_text,
    }


def split_by_row(blocks: list[Block], config: SplitConfig) -> list[list[Block]]:
    table_block = next((b for b in blocks if b.type == BlockType.TABLE and b.meta.get("rows")), None)
    if not table_block:
        return [blocks] if blocks else []

    rows: list[list[str]] = table_block.meta["rows"]
    layout = {
        "header_row_start": table_block.meta.get("header_row_start"),
        "header_row_end": table_block.meta.get("header_row_end"),
        "data_start_row": table_block.meta.get("data_start_row"),
        "header_rows": table_block.meta.get("header_rows"),
    }
    if not layout["header_row_start"]:
        layout = detect_spreadsheet_layout(rows)

    h_start = max(1, config.header_row_start) - 1
    h_end = max(h_start + 1, config.header_row_end)
    header = rows[h_start:h_end]
    header_rows = layout.get("header_rows") or len(header)
    data_start = max(config.start_row - 1, h_end)
    data_rows = rows[data_start:]
    rows_per = max(1, config.rows_per_chunk)

    groups: list[list[Block]] = []
    for i in range(0, len(data_rows), rows_per):
        slice_rows = data_rows[i : i + rows_per]
        chunk_rows = header + slice_rows
        md = rows_to_markdown(chunk_rows, header_rows=header_rows)
        row_range = [
            data_start + i + 1,
            data_start + i + len(slice_rows),
        ]
        groups.append(
            [
                Block(
                    type=BlockType.TABLE,
                    markdown=md,
                    meta=_chunk_meta(table_block, chunk_rows, md, row_range),
                )
            ]
        )
    return groups