Function _normalize_person_name

agents/coldstart-agent/main.py:667–671

(value: str)

    splitter = re.sub(r"\s+(?:and|&)\s+", ",", normalized_line, flags=re.IGNORECASE)
    candidates = [segment.strip() for segment in re.split(r"[;,]", splitter) if segment.strip()]
    def _normalize_person_name(value: str) -> str:
        cleaned = _collapse_whitespace(value)
        cleaned = re.sub(r"^(?:dr|prof|professor)\.?\s+", "", cleaned, flags=re.IGNORECASE)
        cleaned = re.sub(r"[^\w\u4e00-\u9fff]+", " ", cleaned, flags=re.UNICODE)
        return _collapse_whitespace(cleaned).casefold()

    normalized_scholar_name = _normalize_person_name(scholar_name)