perf: shallow listing, os.scandir stats, server-side search for large buckets

app/encrypted_storage.py

@@ -192,7 +192,10 @@ class EncryptedObjectStorage:
 
     def list_objects_shallow(self, bucket_name: str, **kwargs):
         return self.storage.list_objects_shallow(bucket_name, **kwargs)
-    
+
+    def search_objects(self, bucket_name: str, query: str, **kwargs):
+        return self.storage.search_objects(bucket_name, query, **kwargs)
+
     def list_objects_all(self, bucket_name: str):
         return self.storage.list_objects_all(bucket_name)
     

app/storage.py

@@ -692,6 +692,83 @@ class ObjectStorage:
             next_continuation_token=next_token,
         )
 
+    def search_objects(
+        self,
+        bucket_name: str,
+        query: str,
+        *,
+        prefix: str = "",
+        limit: int = 500,
+    ) -> Dict[str, Any]:
+        bucket_path = self._bucket_path(bucket_name)
+        if not bucket_path.is_dir():
+            raise BucketNotFoundError("Bucket does not exist")
+
+        if prefix:
+            search_root = bucket_path / prefix.replace("/", os.sep)
+            if not search_root.is_dir():
+                return {"results": [], "truncated": False}
+            resolved = search_root.resolve()
+            if not str(resolved).startswith(str(bucket_path.resolve())):
+                return {"results": [], "truncated": False}
+        else:
+            search_root = bucket_path
+
+        query_lower = query.lower()
+        results: list[Dict[str, Any]] = []
+        internal = self.INTERNAL_FOLDERS
+        bucket_str = str(bucket_path)
+        bucket_len = len(bucket_str) + 1
+        meta_root = self._bucket_meta_root(bucket_name)
+        scan_limit = limit * 4
+
+        matched = 0
+        scanned = 0
+        search_str = str(search_root)
+        stack = [search_str]
+        while stack:
+            current = stack.pop()
+            try:
+                with os.scandir(current) as it:
+                    for entry in it:
+                        if current == bucket_str and entry.name in internal:
+                            continue
+                        if entry.is_dir(follow_symlinks=False):
+                            stack.append(entry.path)
+                        elif entry.is_file(follow_symlinks=False):
+                            scanned += 1
+                            key = entry.path[bucket_len:].replace(os.sep, "/")
+                            if query_lower in key.lower():
+                                st = entry.stat(follow_symlinks=False)
+                                meta_path = meta_root / (key + ".meta.json")
+                                last_modified = ""
+                                try:
+                                    if meta_path.exists():
+                                        md = json.loads(meta_path.read_text(encoding="utf-8"))
+                                        last_modified = md.get("last_modified", "")
+                                except (OSError, json.JSONDecodeError):
+                                    pass
+                                if not last_modified:
+                                    last_modified = datetime.fromtimestamp(
+                                        st.st_mtime, tz=timezone.utc
+                                    ).strftime("%Y-%m-%dT%H:%M:%S.000Z")
+                                results.append({
+                                    "key": key,
+                                    "size": st.st_size,
+                                    "last_modified": last_modified,
+                                })
+                                matched += 1
+                            if matched >= scan_limit:
+                                break
+            except PermissionError:
+                continue
+            if matched >= scan_limit:
+                break
+
+        results.sort(key=lambda r: r["key"])
+        truncated = len(results) > limit
+        return {"results": results[:limit], "truncated": truncated}
+
     def put_object(
         self,
         bucket_name: str,

app/ui.py

@@ -641,6 +641,33 @@ def stream_bucket_objects(bucket_name: str):
     )
 
 
+@ui_bp.get("/buckets/<bucket_name>/objects/search")
+@limiter.limit("30 per minute")
+def search_bucket_objects(bucket_name: str):
+    principal = _current_principal()
+    try:
+        _authorize_ui(principal, bucket_name, "list")
+    except IamError as exc:
+        return jsonify({"error": str(exc)}), 403
+
+    query = request.args.get("q", "").strip()
+    if not query:
+        return jsonify({"results": [], "truncated": False})
+
+    try:
+        limit = max(1, min(int(request.args.get("limit", 500)), 1000))
+    except (ValueError, TypeError):
+        limit = 500
+
+    prefix = request.args.get("prefix", "").strip()
+
+    storage = _storage()
+    try:
+        return jsonify(storage.search_objects(bucket_name, query, prefix=prefix, limit=limit))
+    except StorageError as exc:
+        return jsonify({"error": str(exc)}), 404
+
+
 @ui_bp.post("/buckets/<bucket_name>/upload")
 @limiter.limit("30 per minute")
 def upload_object(bucket_name: str):