"""Build rich table blocks from PDF layout regions."""

from __future__ import annotations

from pathlib import Path

import fitz

from rag_cut.models import Block, BlockType
from rag_cut.parsers.pdf.layout import LayoutRegion, PageLayout
from rag_cut.parsers.pdf.ocr import describe_visual, ocr_pixmap
from rag_cut.parsers.pdf.tables import (
    detect_header_row_count,
    extract_table_keywords,
    header_signature,
    normalize_rows,
    rows_to_markdown,
    split_body_and_footnotes,
)


def _crop_region(page: fitz.Page, region: LayoutRegion, zoom: float = 2.0) -> fitz.Pixmap:
    clip = fitz.Rect(region.x0, region.y0, region.x1, region.y1)
    return page.get_pixmap(matrix=fitz.Matrix(zoom, zoom), clip=clip, alpha=False)


def _save_pixmap(pix: fitz.Pixmap, path: Path) -> None:
    if pix.n - pix.alpha > 3:
        pix = fitz.Pixmap(fitz.csRGB, pix)
    pix.save(str(path))


def build_table_block(
    page: fitz.Page,
    region: LayoutRegion,
    layout: PageLayout,
    assets_dir: Path,
    chapter_title: str | None,
) -> Block | None:
    """Extract a table block with rows, screenshot, OCR and structural metadata."""
    raw_rows = region.data.get("rows") or []
    normalized = normalize_rows(raw_rows)
    if not normalized:
        return None

    header_rows = detect_header_row_count(normalized)
    body_rows, footnote_rows, footnotes = split_body_and_footnotes(normalized, header_rows)
    data_rows = normalized[:header_rows] + body_rows
    if not data_rows:
        return None

    page_no = layout.page_index + 1
    table_index = int(region.data.get("table_index", 0)) + 1
    crop_id = f"page{page_no}_table{table_index}.png"
    crops_dir = assets_dir / "crops"
    crops_dir.mkdir(parents=True, exist_ok=True)
    crop_path = crops_dir / crop_id

    ocr_text = ""
    try:
        crop_pix = _crop_region(page, region)
        _save_pixmap(crop_pix, crop_path)
        ocr_text = ocr_pixmap(crop_pix)
    except Exception:
        crop_path_str = ""
    else:
        crop_path_str = str(crop_path)

    sig = header_signature(normalized, header_rows)
    md = rows_to_markdown(normalized, header_rows=header_rows, include_footnotes=footnotes)
    if not md:
        return None

    header_text = " ".join(" ".join(r for r in row if r) for row in normalized[:header_rows])
    keywords = extract_table_keywords(header_text, md, footnotes, ocr_text)

    meta: dict = {
        "page": page_no,
        "pages": [page_no],
        "bbox": [region.x0, region.y0, region.x1, region.y1],
        "bboxes": [{"page": page_no, "bbox": [region.x0, region.y0, region.x1, region.y1]}],
        "table_source": region.data.get("source", "pymupdf"),
        "crop_path": crop_path_str,
        "rows": normalized,
        "row_count": len(normalized),
        "col_count": max((len(r) for r in normalized), default=0),
        "header_rows": header_rows,
        "header_signature": [list(r) for r in sig],
        "footnotes": footnotes,
        "keywords": keywords,
        "cross_page": False,
    }
    if chapter_title:
        meta["chapter"] = chapter_title

    return Block(
        type=BlockType.TABLE,
        markdown=md,
        ocr_text=ocr_text,
        text=describe_visual(ocr_text, "表格", crop_id) if ocr_text else "",
        image_id=crop_id,
        image_path=crop_path_str or None,
        meta=meta,
    )