Add graph traversal endpoints and sort metrics by channel name

search_app.py

@@ -201,6 +201,15 @@ def elastic_metrics_payload(
                         "top_hits": {
                             "size": 1,
                             "_source": {"includes": ["channel_name"]},
+                            "sort": [
+                                {
+                                    "channel_name.keyword": {
+                                        "order": "asc",
+                                        "missing": "_last",
+                                        "unmapped_type": "keyword",
+                                    }
+                                }
+                            ],
                         }
                     }
                 },
@@ -568,58 +577,14 @@ def build_query_payload(
     return body
 
 
-def create_app(config: AppConfig = CONFIG) -> Flask:
-    app = Flask(__name__, static_folder=str(Path(__file__).parent / "static"))
-    client = _ensure_client(config)
-    index = config.elastic.index
-    qdrant_url = config.qdrant_url
-    qdrant_collection = config.qdrant_collection
-    qdrant_vector_name = config.qdrant_vector_name
-    qdrant_vector_size = config.qdrant_vector_size
-    qdrant_embed_model = config.qdrant_embed_model
-
-    @app.route("/")
-    def index_page():
-        return send_from_directory(app.static_folder, "index.html")
-
-    @app.route("/graph")
-    def graph_page():
-        return send_from_directory(app.static_folder, "graph.html")
-
-    @app.route("/vector-search")
-    def vector_search_page():
-        return send_from_directory(app.static_folder, "vector.html")
-
-    @app.route("/static/<path:filename>")
-    def static_files(filename: str):
-        return send_from_directory(app.static_folder, filename)
-
-    def normalize_reference_list(values: Any) -> List[str]:
-        if values is None:
-            return []
-        if isinstance(values, (list, tuple, set)):
-            iterable = values
-        else:
-            iterable = [values]
-        normalized: List[str] = []
-        for item in iterable:
-            candidate: Optional[str]
-            if isinstance(item, dict):
-                candidate = item.get("video_id") or item.get("id")  # type: ignore[assignment]
-            else:
-                candidate = item  # type: ignore[assignment]
-            if candidate is None:
-                continue
-            text = str(candidate).strip()
-            if not text:
-                continue
-            if text.lower() in {"none", "null"}:
-                continue
-            normalized.append(text)
-        return normalized
-
 def build_graph_payload(
-    root_id: str, depth: int, max_nodes: int, *, include_external: bool = True
+    client: "Elasticsearch",
+    index: str,
+    root_id: str,
+    depth: int,
+    max_nodes: int,
+    *,
+    include_external: bool = True,
 ) -> Dict[str, Any]:
     root_id = root_id.strip()
     if not root_id:
@@ -637,11 +602,7 @@ def build_graph_payload(
             LOGGER.debug("Graph: failed to load %s: %s", video_id, exc)
             doc_cache[video_id] = None
         doc = doc_cache[video_id]
-            if (
+        if doc is not None and not include_external and doc.get("external_reference"):
-                doc is not None
-                and not include_external
-                and doc.get("external_reference")
-            ):
             doc_cache[video_id] = None
             return None
         return doc_cache[video_id]
@@ -760,7 +721,10 @@ def build_graph_payload(
         },
     }
 
+
 def build_full_graph_payload(
+    client: "Elasticsearch",
+    index: str,
     max_nodes: Optional[int],
     *,
     highlight_id: Optional[str] = None,
@@ -811,7 +775,7 @@ def build_full_graph_payload(
                 if (not existing.get("title") or existing["title"] == node_id) and doc.get("title"):
                     existing["title"] = doc["title"]
                 if not existing.get("channel_id") and doc.get("channel_id"):
-                        existing["channel_id"] = doc["channel_id"]
+                    existing["channel_id"] = doc.get("channel_id")
                 if (
                     existing.get("channel_name") in {"Unknown", node_id, None}
                     and (doc.get("channel_name") or doc.get("channel_id"))
@@ -852,9 +816,7 @@ def build_full_graph_payload(
     scroll_id: Optional[str] = None
     try:
         body = {"query": query, "_source": source_fields, "sort": ["_doc"]}
-            response = client.search(
+        response = client.search(index=index, body=body, size=batch_size, scroll="1m")
-                index=index, body=body, size=batch_size, scroll="1m"
-            )
         scroll_id = response.get("_scroll_id")
         stop_fetch = False
         while not stop_fetch:
@@ -919,12 +881,6 @@ def build_full_graph_payload(
         if link.get("source") in nodes and link.get("target") in nodes
     ]
 
-        links = [
-            link
-            for link in links
-            if link.get("source") in nodes and link.get("target") in nodes
-        ]
-
     return {
         "root": highlight_id or "",
         "depth": 0,
@@ -938,6 +894,58 @@ def build_full_graph_payload(
         },
     }
 
+
+def create_app(config: AppConfig = CONFIG) -> Flask:
+    app = Flask(__name__, static_folder=str(Path(__file__).parent / "static"))
+    client = _ensure_client(config)
+    index = config.elastic.index
+    qdrant_url = config.qdrant_url
+    qdrant_collection = config.qdrant_collection
+    qdrant_vector_name = config.qdrant_vector_name
+    qdrant_vector_size = config.qdrant_vector_size
+    qdrant_embed_model = config.qdrant_embed_model
+
+    @app.route("/")
+    def index_page():
+        return send_from_directory(app.static_folder, "index.html")
+
+    @app.route("/graph")
+    def graph_page():
+        return send_from_directory(app.static_folder, "graph.html")
+
+    @app.route("/vector-search")
+    def vector_search_page():
+        return send_from_directory(app.static_folder, "vector.html")
+
+    @app.route("/static/<path:filename>")
+    def static_files(filename: str):
+        return send_from_directory(app.static_folder, filename)
+
+    def normalize_reference_list(values: Any) -> List[str]:
+        if values is None:
+            return []
+        if isinstance(values, (list, tuple, set)):
+            iterable = values
+        else:
+            iterable = [values]
+        normalized: List[str] = []
+        for item in iterable:
+            candidate: Optional[str]
+            if isinstance(item, dict):
+                candidate = item.get("video_id") or item.get("id")  # type: ignore[assignment]
+            else:
+                candidate = item  # type: ignore[assignment]
+            if candidate is None:
+                continue
+            text = str(candidate).strip()
+            if not text:
+                continue
+            if text.lower() in {"none", "null"}:
+                continue
+            normalized.append(text)
+        return normalized
+
+
     @app.route("/api/channels")
     def channels():
         include_external = request.args.get("external", default="0", type=str)
@@ -952,6 +960,15 @@ def build_full_graph_payload(
                             "top_hits": {
                                 "size": 1,
                                 "_source": {"includes": ["channel_name"]},
+                                "sort": [
+                                    {
+                                        "channel_name.keyword": {
+                                            "order": "asc",
+                                            "missing": "_last",
+                                            "unmapped_type": "keyword",
+                                        }
+                                    }
+                                ],
                             }
                         }
                     },
@@ -1050,13 +1067,20 @@ def build_full_graph_payload(
 
         if full_graph:
             payload = build_full_graph_payload(
+                client,
+                index,
                 None,
                 highlight_id=video_id or None,
                 include_external=include_external,
             )
         else:
             payload = build_graph_payload(
-                video_id, depth, max_nodes, include_external=include_external
+                client,
+                index,
+                video_id,
+                depth,
+                max_nodes,
+                include_external=include_external,
             )
             if not payload["nodes"]:
                 return (
@@ -1367,6 +1391,15 @@ def build_full_graph_payload(
                                     "top_hits": {
                                         "size": 1,
                                         "_source": {"includes": ["channel_name"]},
+                                        "sort": [
+                                            {
+                                                "channel_name.keyword": {
+                                                    "order": "asc",
+                                                    "missing": "_last",
+                                                    "unmapped_type": "keyword",
+                                                }
+                                            }
+                                        ],
                                     }
                                 }
                             },