같은 사건, 일곱 번 — 신원 대 같음

def dedupe_stories(rows: list[dict]) -> list[dict]:
    """Collapse the same story delivered by several sources.

    Measured: 8% of a day's rows were duplicates -- one story arrived
    seven times under seven different wrapper URLs, so canonical-URL
    identity (correct at ingest) cannot see it.

    RENDER-time only: every row stays in the store, and the copy that
    survives is the most useful one, holding the position of the FIRST
    copy so the shelf's ordering is untouched.
    """
    best: dict[str, dict] = {}
    order: list[str] = []
    for row in rows:
        key = title_key(str(row.get("title") or ""))   # punctuation-blind
        if not key:
            key = f"__id{row.get('id')}"               # never merge on empty
        if key not in best:
            best[key] = row
            order.append(key)                          # position of copy #1
        elif _story_rank(row) > _story_rank(best[key]):
            best[key] = row                            # ...but the best copy
    return [best[key] for key in order]


def _story_rank(row: dict) -> tuple:
    """Which copy is most useful to a reader, in priority order."""
    return (
        bool(row.get("cleaned_at")),        # already pre-processed
        bool(row.get("image_url")),         # has a picture
        not is_shell(row.get("url", "")),   # points at the publisher
        bool(row.get("summary")),           # has a dek
    )