Function _caption_match_is_inline_reference

scripts/extract_pdf_assets.py:371–380

Reject prose references such as "Table 8 summarizes ...".

(line_text: str, match: re.Match[str])

def _caption_match_is_inline_reference(line_text: str, match: re.Match[str]) -> bool:
    """Reject prose references such as "Table 8 summarizes ..."."""
    tail = line_text[match.end():]
    if not tail or not tail[0].isspace():
        return False
    rest = tail.strip()
    if not rest:
        return False
    first_word = re.match(r"[A-Za-z]+", rest)
    return bool(first_word and first_word.group(0)[0].islower())


def _collect_xref_rects(page) -> list[tuple[float, float, float, float]]: