"""Automatic split policy selection based on parsed document shape."""

from __future__ import annotations

from pathlib import Path

from rag_cut.models import Block, BlockType, SplitConfig, SplitMode
from rag_cut.parsers.pdf.tables import detect_spreadsheet_layout, is_qa_style_table

SPREADSHEET_EXTS = {".xlsx", ".xls", ".csv"}
PRESENTATION_EXTS = {".ppt", ".pptx", ".ppsx"}
TEXT_EXTS = {".md", ".txt", ".html", ".htm", ".json", ".xml", ".log"}
IMAGE_EXTS = {".jpg", ".jpeg", ".png", ".bmp", ".gif"}


def _table_rows(blocks: list[Block]) -> int:
    if len(blocks) != 1 or blocks[0].type != BlockType.TABLE:
        return 0
    rows = blocks[0].meta.get("rows") or []
    return len(rows)


def _rows_per_chunk(data_row_count: int) -> int:
    if data_row_count <= 20:
        return max(1, data_row_count)
    if data_row_count <= 80:
        return 10
    if data_row_count <= 300:
        return 20
    return 40


def choose_split_config(path: Path, blocks: list[Block]) -> SplitConfig:
    """Choose conservative defaults that preserve document structure first."""
    ext = path.suffix.lower()
    row_count = _table_rows(blocks)

    if ext in SPREADSHEET_EXTS or row_count:
        rows = blocks[0].meta.get("rows") or [] if blocks else []
        layout = detect_spreadsheet_layout(rows) if rows else {
            "header_row_start": 1,
            "header_row_end": 1,
            "data_start_row": 2,
        }
        data_row_count = max(0, row_count - layout["data_start_row"] + 1)
        rows_per = 1 if is_qa_style_table(rows, layout) else _rows_per_chunk(data_row_count)
        return SplitConfig(
            mode=SplitMode.BY_ROW,
            max_chunk_size=2400,
            overlap=0,
            header_row_start=layout["header_row_start"],
            header_row_end=layout["header_row_end"],
            start_row=layout["data_start_row"],
            rows_per_chunk=rows_per,
        )

    if ext == ".pdf" or ext in PRESENTATION_EXTS:
        return SplitConfig(mode=SplitMode.DEFAULT, max_chunk_size=2600, overlap=120)

    if ext in IMAGE_EXTS:
        return SplitConfig(mode=SplitMode.DEFAULT, max_chunk_size=2200, overlap=0)

    if ext in TEXT_EXTS:
        return SplitConfig(mode=SplitMode.DEFAULT, max_chunk_size=1800, overlap=120)

    return SplitConfig(mode=SplitMode.DEFAULT, max_chunk_size=2200, overlap=120)


def split_config_summary(config: SplitConfig) -> dict[str, int | str | None]:
    return {
        "mode": config.mode.value,
        "delimiter": config.delimiter,
        "parent_delimiter": config.parent_delimiter,
        "child_delimiter": config.child_delimiter,
        "max_chunk_size": config.max_chunk_size,
        "child_max_size": config.child_max_size,
        "overlap": config.overlap,
        "header_row_start": config.header_row_start,
        "header_row_end": config.header_row_end,
        "start_row": config.start_row,
        "rows_per_chunk": config.rows_per_chunk,
    }