INNER CODE UNIT · Python

dead_count

nubenetes/awesome-kubernetes · src/main.py:291

    dead_count = initial_count - len(all_raw_assets)
    if dead_count > 0:
        log_event(f"[*] Health Filter: Removed {dead_count} definitively dead (404) links.")

    unique_assets_map = {}
    for asset in all_raw_assets:
        clean_url = asset["url"].split('#')[0].rstrip('/').lower()
        if clean_url not in unique_assets_map:
            unique_assets_map[clean_url] = asset
        else:
            if len(asset.get("context", "")) > len(unique_assets_map[clean_url].get("context", "")):
                unique_assets_map[clean_url] = asset

    all_raw_assets = list(unique_assets_map.values())
    log_event(f"[*] Total after initial deduplication: {len(all_raw_assets)} unique links.")

    # 5. Evaluation and Registration
    from src.gemini_utils import is_fuzzy_duplicate

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…