adds upload-duplicate_strategy config in interface and backend

scipaperloader/blueprints/upload.py

@@ -22,6 +22,7 @@ from flask import (
 from ..db import db
 from ..models import PaperMetadata, ActivityLog
 from ..celery import celery  # Import the celery instance directly
+from ..defaults import DUPLICATE_STRATEGIES
 
 bp = Blueprint("upload", __name__)
 
@@ -55,10 +56,10 @@ def upload():
         
         return jsonify({"task_id": task.id})
 
-    return render_template("upload.html.jinja")
+    return render_template("upload.html.jinja", duplicate_strategies=DUPLICATE_STRATEGIES)
 
 @celery.task(bind=True)
-def process_csv(self, file_content, delimiter, duplicate_strategy):
+def process_csv(self, file_content, delimiter, duplicate_strategy="skip"):
     """Process CSV file and import paper metadata."""
 
     # With the ContextTask in place, we're already inside an app context

scipaperloader/defaults.py

@@ -1 +1,22 @@
 DEBUG = False  # make sure DEBUG is off unless enabled explicitly otherwise
+
+# Define duplicate handling strategies with descriptions for the UI
+DUPLICATE_STRATEGIES = {
+    "skip": {
+        "name": "Skip duplicates",
+        "description": "Skip papers that already exist in the database",
+        "is_default": True
+    },
+    "update": {
+        "name": "Update duplicates",
+        "description": "Update existing papers with new metadata",
+        "is_default": False
+    },
+    # Add new strategies here, they will automatically appear in the UI
+    # Example:
+    # "merge": {
+    #     "name": "Merge duplicates",
+    #     "description": "Merge new data with existing data, keeping both values",
+    #     "is_default": False
+    # }
+}

scipaperloader/templates/upload.html.jinja

@@ -58,6 +58,16 @@
       <option value="|">Pipe (|)</option>
     </select>
   </div>
+  <div class="form-group mt-3">
+    <label for="duplicate_strategy">Duplicate Handling Strategy</label>
+    <select name="duplicate_strategy" id="duplicate_strategy" class="form-control">
+      {% for strategy_id, strategy in duplicate_strategies.items() %}
+      <option value="{{ strategy_id }}" {% if strategy.is_default %}selected{% endif %}>
+        {{ strategy.name }} - {{ strategy.description }}
+      </option>
+      {% endfor %}
+    </select>
+  </div>
   <button type="submit" class="btn btn-primary mt-3">Upload</button>
 </form>