Function extract_caption_lines

scripts/common.py:2129–2179

(pdf_text: str, kind: str)

def extract_caption_lines(pdf_text: str, kind: str) -> list[dict[str, str]]:
    grouped: dict[str, dict[str, str]] = {}
    scores: dict[str, int] = {}
    order: list[str] = []
    lines = [clean_pdf_line(line) for line in pdf_text.splitlines()]
    if kind == "figure":
        pattern = re.compile(
            r"^((?:"
            r"supplementary\s+fig(?:ure)?\.?\s*\d+[a-z]?"
            r"|extended\s+data\s+fig(?:ure)?\.?\s*\d+[a-z]?"
            r"|scheme\.?\s*\d+[a-z]?"
            r"|algorithm\.?\s*\d+[a-z]?"
            r"|fig(?:ure)?\.?\s*[AS]?\d+[a-z]?"
            r"|图\.?\s*[A-Z]?\d+[a-z]?"
            r"))(?!\.\d)(?:[:：.。,\s、|—–-]+|$)(.*)$",
            re.IGNORECASE,
        )
    else:
        pattern = re.compile(
            r"^((?:"
            r"supplementary\s+table\.?\s*\d+[a-z]?"
            r"|extended\s+data\s+table\.?\s*\d+[a-z]?"
            r"|table\.?\s*[AS]?\d+[a-z]?"
            r"|表\.?\s*[A-Z]?\d+[a-z]?"
            r"))(?!\.\d)(?:[:：.。,\s、|—–-]+|$)(.*)$",
            re.IGNORECASE,
        )
    for idx, line in enumerate(lines):
        if not line:
            continue
        match = pattern.match(line)
        if not match:
            continue
        label = normalize_caption_label(match.group(1))
        caption = normalize_whitespace(match.group(2))
        if not caption and idx + 1 < len(lines):
            caption = normalize_whitespace(lines[idx + 1])
        key = caption_label_key(label)
        if not key:
            continue
        candidate = {"id": label, "caption": caption}
        score = caption_preference_score(label, caption)
        if key not in grouped:
            grouped[key] = candidate
            scores[key] = score
            order.append(key)
            continue
        if score > scores[key]:
            grouped[key] = candidate
            scores[key] = score
    return [grouped[key] for key in order]


def infer_paper_type(title: str, abstract: str) -> tuple[str, str]: