Add commit scheduler and usage stats tracking to

app.py

@@ -1,6 +1,47 @@
-from huggingface_hub import HfApi
-import gradio as gr
+import json
+import os
 import re
+from datetime import datetime
+from pathlib import Path
+
+import gradio as gr
+from dotenv import load_dotenv
+from huggingface_hub import CommitScheduler, HfApi
+from huggingface_hub.utils import HfHubHTTPError
+
+load_dotenv()
+
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+JSON_DATASET_DIR = Path("dataset")
+JSON_DATASET_DIR.mkdir(parents=True, exist_ok=True)
+JSON_DATASET_PATH = JSON_DATASET_DIR / "dataset.jsonl"
+
+scheduler = CommitScheduler(
+    repo_id="librarian-bots/collection_cloner-usage-stats",
+    repo_type="dataset",
+    folder_path=JSON_DATASET_DIR,
+    path_in_repo=str(JSON_DATASET_PATH),
+    token=HF_TOKEN,
+)
+
+
+def save_json(source_slug: str, destination_slug: str) -> None:
+    with scheduler.lock:
+        with JSON_DATASET_PATH.open("a") as f:
+            if source_slug.startswith("hf_"):  # catch people accidentally adding tokens
+                return None
+            if destination_slug.startswith("hf_"):
+                return None
+            json.dump(
+                {
+                    "source_collection": source_slug,
+                    "destination_collection": destination_slug,
+                    "datetime": datetime.now().isoformat(),
+                },
+                f,
+            )
+            f.write("\n")
 
 
 def extract_slug(url):
@@ -33,9 +74,16 @@ def clone_collection(
         token=token,
     )
     for item in collection.items:
-        api.add_collection_item(
-            new_collection.slug, item.item_id, item_type=item.item_type
-        )
+        try:
+            api.add_collection_item(
+                new_collection.slug, item.item_id, item_type=item.item_type
+            )
+        except HfHubHTTPError as e:
+            gr.Info(
+                f"Failed to add item {item.item_id} to collection {new_collection.slug} because it already exists in this collection."
+            )
+    if not private:
+        save_json(collection.slug, new_collection.slug)
     return f"[Collection]({collection.url}) has been cloned into [{new_collection.slug}]({new_collection.url})"
 
 
@@ -48,8 +96,12 @@ with gr.Blocks(css="style.css") as demo:
     gr.HTML(title)
     gr.HTML(
         """<p style='text-align: center;'>
-This space allows you to clone a <a href="https://huggingface.co/docs/hub/collections">Collection</a> from the Hugging Face Hub into your own namespace.
-You can then edit the collection to your liking!</p>"""
+This space allows you to clone a <a href="https://huggingface.co/docs/hub/collections">Collection</a> from the Hugging Face Hub into your own namespace.<p>
+<p style='text-align: center;'> You can edit this cloned Collection to your liking!</p>"""
+    )
+    gr.Markdown(
+        """
+                **Note**: To track interest in this feature this Space keeps a record of clones which are cloned into public collection. Clones into private Collections are not tracked."""
     )
     gr.Markdown("## Authentication")
     gr.Markdown(