ragflow in the repository, with codex-created yandex disk plugin JUST IN CASE, also llamaindex enrichment with yandex disk predefined data

ext_stats.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+import argparse
+import json
+from collections import Counter
+from pathlib import Path
+
+
+def normalize_ext(path_str: str) -> str:
+    ext = Path(path_str).suffix.lower()
+    return ext if ext else "(no_ext)"
+
+
+def load_paths(json_path: Path) -> list[str]:
+    with json_path.open("r", encoding="utf-8") as f:
+        data = json.load(f)
+    if not isinstance(data, list):
+        raise ValueError("Expected JSON to be a list of file paths")
+    if not all(isinstance(item, str) for item in data):
+        raise ValueError("Expected JSON list to contain only strings")
+    return data
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(
+        description="Count file extensions from a JSON list of paths."
+    )
+    parser.add_argument(
+        "json_path",
+        nargs="?",
+        default="yadisk_files.json",
+        help="Path to JSON file (default: yadisk_files.json)",
+    )
+    args = parser.parse_args()
+
+    json_path = Path(args.json_path)
+    if not json_path.exists():
+        raise SystemExit(f"JSON file not found: {json_path}")
+
+    paths = load_paths(json_path)
+    counts = Counter(normalize_ext(p) for p in paths)
+
+    for ext, count in counts.most_common():
+        print(f"{ext}\t{count}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())