From 207c4b67da84e351095411b3dcd7cadccaf03173 Mon Sep 17 00:00:00 2001
From: Dylan De Faoite <dylanseandefaoite@gmail.com>
Date: Tue, 3 Mar 2026 17:28:46 +0000
Subject: [PATCH] feat(frontend): add dataset name requirements to the upload
 page

---
 frontend/src/pages/Upload.tsx | 28 +++++++++++++++++++++++++---
 server/app.py                 | 20 ++++++++++----------
 2 files changed, 35 insertions(+), 13 deletions(-)

diff --git a/frontend/src/pages/Upload.tsx b/frontend/src/pages/Upload.tsx
index 74a9b18..712d853 100644
--- a/frontend/src/pages/Upload.tsx
+++ b/frontend/src/pages/Upload.tsx
@@ -7,6 +7,7 @@ const styles = StatsStyling;
 const API_BASE_URL = "http://localhost:5000";
 
 const UploadPage = () => {
+  const [datasetName, setDatasetName] = useState("");
   const [postFile, setPostFile] = useState<File | null>(null);
   const [topicBucketFile, setTopicBucketFile] = useState<File | null>(null);
   const [returnMessage, setReturnMessage] = useState("");
@@ -15,6 +16,14 @@ const UploadPage = () => {
   const navigate = useNavigate();
 
   const uploadFiles = async () => {
+    const normalizedDatasetName = datasetName.trim();
+
+    if (!normalizedDatasetName) {
+      setHasError(true);
+      setReturnMessage("Please add a dataset name before continuing.");
+      return;
+    }
+
     if (!postFile || !topicBucketFile) {
       setHasError(true);
       setReturnMessage("Please upload both files before continuing.");
@@ -22,6 +31,7 @@ const UploadPage = () => {
     }
 
     const formData = new FormData();
+    formData.append("name", normalizedDatasetName);
     formData.append("posts", postFile);
     formData.append("topics", topicBucketFile);
 
@@ -63,7 +73,7 @@ const UploadPage = () => {
           <div>
             <h1 style={{ margin: 0, color: "#111827", fontSize: 28 }}>Upload Dataset</h1>
             <p style={{ margin: "8px 0 0", color: "#6b7280", fontSize: 14 }}>
-              Add your posts and topic map files to generate fresh analytics.
+              Name your dataset, then upload posts and topic map files to generate analytics.
             </p>
           </div>
           <button
@@ -83,11 +93,23 @@ const UploadPage = () => {
             gridTemplateColumns: "repeat(auto-fit, minmax(280px, 1fr))",
           }}
         >
+          <div style={{ ...styles.card, gridColumn: "auto" }}>
+            <h2 style={{ ...styles.sectionTitle, color: "#111827" }}>Dataset Name</h2>
+            <p style={styles.sectionSubtitle}>Use a clear label so you can identify this upload later.</p>
+            <input
+              style={{ ...styles.input, width: "100%", maxWidth: "100%", boxSizing: "border-box" }}
+              type="text"
+              placeholder="Example: Cork Discussions - Jan 2026"
+              value={datasetName}
+              onChange={(event) => setDatasetName(event.target.value)}
+            />
+          </div>
+
           <div style={{ ...styles.card, gridColumn: "auto" }}>
             <h2 style={{ ...styles.sectionTitle, color: "#111827" }}>Posts File (.jsonl)</h2>
             <p style={styles.sectionSubtitle}>Upload the raw post records export.</p>
             <input
-              style={{ ...styles.input, width: "80%", maxWidth: "100%" }}
+              style={{ ...styles.input, width: "100%", maxWidth: "100%", boxSizing: "border-box" }}
               type="file"
               accept=".jsonl"
               onChange={(event) => setPostFile(event.target.files?.[0] ?? null)}
@@ -101,7 +123,7 @@ const UploadPage = () => {
             <h2 style={{ ...styles.sectionTitle, color: "#111827" }}>Topics File (.json)</h2>
             <p style={styles.sectionSubtitle}>Upload your topic bucket mapping file.</p>
             <input
-              style={{ ...styles.input, width: "80%", maxWidth: "100%" }}
+              style={{ ...styles.input, width: "100%", maxWidth: "100%", boxSizing: "border-box" }}
               type="file"
               accept=".json"
               onChange={(event) => setTopicBucketFile(event.target.files?.[0] ?? null)}
diff --git a/server/app.py b/server/app.py
index c0d28ef..1332ad2 100644
--- a/server/app.py
+++ b/server/app.py
@@ -45,6 +45,7 @@ auth_manager = AuthManager(db, bcrypt)
 dataset_manager = DatasetManager(db)
 stat_gen = StatGen()
 
+
 @app.route("/register", methods=["POST"])
 def register_user():
     data = request.get_json()
@@ -113,12 +114,15 @@ def get_user_datasets():
 @app.route("/upload", methods=["POST"])
 @jwt_required()
 def upload_data():
-    if "posts" not in request.files or "topics" not in request.files or "name" not in request.form:
+    if "posts" not in request.files or "topics" not in request.files:
         return jsonify({"error": "Missing required files or form data"}), 400
 
     post_file = request.files["posts"]
     topic_file = request.files["topics"]
-    dataset_name = request.form["name"]
+    dataset_name = (request.form.get("name") or "").strip()
+
+    if not dataset_name:
+        return jsonify({"error": "Missing required dataset name"}), 400
 
     if post_file.filename == "" or topic_file.filename == "":
         return jsonify({"error": "Empty filename"}), 400
@@ -137,17 +141,13 @@ def upload_data():
         topics = json.load(topic_file)
         dataset_id = dataset_manager.save_dataset_info(current_user, dataset_name, topics)
 
-        process_dataset.delay(
-            dataset_id,
-            posts_df.to_dict(orient="records"),
-            topics
-        )
+        process_dataset.delay(dataset_id, posts_df.to_dict(orient="records"), topics)
 
         return jsonify(
             {
                 "message": "Dataset queued for processing",
                 "dataset_id": dataset_id,
-                "status": "processing"
+                "status": "processing",
             }
         ), 202
     except ValueError as e:
@@ -160,7 +160,7 @@ def upload_data():
 def get_dataset(dataset_id):
     try:
         user_id = int(get_jwt_identity())
-        
+
         if not dataset_manager.authorize_user_dataset(dataset_id, user_id):
             raise NotAuthorisedException("This user is not authorised to access this dataset")
 
@@ -181,7 +181,7 @@ def get_dataset(dataset_id):
 def get_dataset_status(dataset_id):
     try:
         user_id = int(get_jwt_identity())
-        
+
         if not dataset_manager.authorize_user_dataset(dataset_id, user_id):
             raise NotAuthorisedException("This user is not authorised to access this dataset")