Function _grow_table_region

scripts/extract_pdf_assets.py:839–915

Walk away from the caption in ``direction`` ('up' or 'down') and collect logical rows that look like part of a tabular layout. Returns the list of accepted row bboxes (caption excluded) and the number of rows confirmed as table body rows. The caller decides which direction wins.

(
    page,
    caption_anchor: dict,
    rows: list[dict],
    paragraph_blocks: list[tuple[float, float, float, float, str]],
    *,
    direction: str,
    upper_bound: float,
    lower_bound: float,
)

def _grow_table_region(
    page,
    caption_anchor: dict,
    rows: list[dict],
    paragraph_blocks: list[tuple[float, float, float, float, str]],
    *,
    direction: str,
    upper_bound: float,
    lower_bound: float,
) -> tuple[list[tuple[float, float, float, float]], int]:
    """Walk away from the caption in ``direction`` ('up' or 'down') and collect
    logical rows that look like part of a tabular layout.

    Returns the list of accepted row bboxes (caption excluded) and the number
    of rows confirmed as table body rows.  The caller decides which direction
    wins.
    """
    caption_y0 = caption_anchor["bbox"][1]
    caption_y1 = caption_anchor["bbox"][3]

    accepted: list[tuple[float, float, float, float]] = []
    data_row_count = 0
    consecutive_non_data = 0
    seen_data = False
    last_accepted_edge = caption_y1 if direction == "down" else caption_y0

    if direction == "down":
        candidates = [r for r in rows if r["bbox"][1] > caption_y1 + 0.5]
        candidates.sort(key=lambda r: r["bbox"][1])
        boundary_check = lambda ly0, ly1: ly1 >= lower_bound
    else:
        candidates = [r for r in rows if r["bbox"][3] < caption_y0 - 0.5]
        candidates.sort(key=lambda r: r["bbox"][3], reverse=True)
        boundary_check = lambda ly0, ly1: ly0 <= upper_bound

    for row in candidates:
        restricted_row = _restrict_row_to_caption_column(row, caption_anchor["bbox"], page.rect)
        if restricted_row is None:
            continue
        row = restricted_row
        rx0, ry0, rx1, ry1 = row["bbox"]
        if boundary_check(ry0, ry1):
            break
        text = row["text"]
        is_table_row = _row_is_table_like(row)
        in_paragraph_block = _line_is_inside_any_block(row["bbox"], paragraph_blocks)
        row_gap = ry0 - last_accepted_edge if direction == "down" else last_accepted_edge - ry1
        row_height = max(ry1 - ry0, 1.0)
        if seen_data and row_gap > max(12.0, row_height * 1.8) and not is_table_row:
            break
        if (
            seen_data
            and len(row.get("members", []) or []) <= 1
            and in_paragraph_block
            and not _looks_like_data_row(text)
        ):
            break
        # If this row sits entirely inside a real prose paragraph and does not