Function _looks_like_data_row

scripts/extract_pdf_assets.py:80–86

Heuristic: a data row from a tabular layout, not part of a caption.

(text: str)

def _looks_like_data_row(text: str) -> bool:
    """Heuristic: a data row from a tabular layout, not part of a caption."""
    tokens = text.split()
    if len(tokens) < 3:
        return False
    numeric_tokens = sum(1 for tok in tokens if _NUMERIC_TOKEN_RE.match(tok))
    return numeric_tokens >= max(2, len(tokens) // 2)


def _looks_like_text_table_row(text: str) -> bool: