Function _cluster_lines_into_rows

scripts/extract_pdf_assets.py:693–742

Cluster sibling text lines that share roughly the same vertical band. PDFs created by LaTeX often emit one PyMuPDF "line" per cell, so a single visual row of a table is split into many independent line records. We merge lines whose ``y0`` falls within ``y_tolerance`` points of the row

(
    lines: list[dict], *, y_tolerance: float = 2.0
)

def _cluster_lines_into_rows(
    lines: list[dict], *, y_tolerance: float = 2.0
) -> list[dict]:
    """Cluster sibling text lines that share roughly the same vertical band.

    PDFs created by LaTeX often emit one PyMuPDF "line" per cell, so a single
    visual row of a table is split into many independent line records.  We
    merge lines whose ``y0`` falls within ``y_tolerance`` points of the row
    seed so that downstream heuristics can reason about a true logical row.

    Each output record::

        {
            "bbox": (x0, y0, x1, y1),  # union of all member bboxes
            "tokens": [str, ...],       # text content of each member, left-to-right
            "text": str,                # tokens joined by single spaces
            "members": [dict, ...],     # original line records inside the row
        }
    """
    rows: list[dict] = []
    sorted_lines = sorted(lines, key=lambda r: (r["bbox"][1], r["bbox"][0]))
    for line in sorted_lines:
        bx0, by0, bx1, by1 = line["bbox"]
        placed = False
        for row in rows:
            rx0, ry0, rx1, ry1 = row["bbox"]
            row_mid = (ry0 + ry1) / 2.0
            line_mid = (by0 + by1) / 2.0
            if abs(line_mid - row_mid) <= y_tolerance:
                row["bbox"] = (
                    min(rx0, bx0),
                    min(ry0, by0),
                    max(rx1, bx1),
                    max(ry1, by1),
                )
                row["members"].append(line)
                placed = True
                break
        if not placed:
            rows.append({
                "bbox": (bx0, by0, bx1, by1),
                "members": [line],
            })

    for row in rows:
        row["members"].sort(key=lambda m: m["bbox"][0])
        row["tokens"] = [m["text"] for m in row["members"]]
        row["text"] = " ".join(row["tokens"])
    rows.sort(key=lambda r: r["bbox"][1])
    return rows


def _row_is_table_like(row: dict) -> bool: