From 2789bbeb14c4cae244d3b0281a63c883648b1d86 Mon Sep 17 00:00:00 2001
From: Dylan De Faoite <dylanseandefaoite@gmail.com>
Date: Sat, 31 Jan 2026 15:46:53 +0000
Subject: [PATCH] feat: add summary endpoint

---
 server/app.py      | 16 +++++++++++++++-
 server/stat_gen.py | 18 ++++++++++++++++--
 2 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/server/app.py b/server/app.py
index b579bb7..580396a 100644
--- a/server/app.py
+++ b/server/app.py
@@ -10,7 +10,9 @@ app = Flask(__name__)
 CORS(app, resources={r"/*": {"origins": "http://localhost:5173"}})
 
 # Global State
-stat_obj = None
+posts_df = pd.read_json('posts.jsonl', lines=True)
+comments_df = pd.read_json('comments.jsonl', lines=True)
+stat_obj = StatGen(posts_df, comments_df)
 
 @app.route('/upload', methods=['POST'])
 def upload_data():
@@ -89,6 +91,18 @@ def search_dataset():
     query = data["query"]
     return jsonify(stat_obj.filter_events(query).to_dict(orient='records')), 200
 
+@app.route('/stats/summary', methods=["GET"])
+def get_summary():
+    if stat_obj is None:
+        return jsonify({"error": "No data uploaded"}), 400
+    
+    try:
+        return jsonify(stat_obj.get_summary()), 200
+    except ValueError as e:
+        return jsonify({"error": f"Malformed or missing data: {str(e)}"}), 400
+    except Exception as e:
+        return jsonify({"error": f"An unexpected error occurred: {str(e)}"}), 500
+
 @app.route('/reset', methods=["GET"])
 def reset_dataset():
     if stat_obj is None:
diff --git a/server/stat_gen.py b/server/stat_gen.py
index 2280174..738c5d3 100644
--- a/server/stat_gen.py
+++ b/server/stat_gen.py
@@ -88,7 +88,7 @@ class StatGen:
             self.df
             .groupby('date')
             .size()
-            .reset_index(name='posts_count')
+            .reset_index(name='event_count')
         )
     
     def filter_events(self, search_query: str) -> pd.DataFrame:
@@ -96,4 +96,18 @@ class StatGen:
         return self.df
     
     def reset_dataset(self) -> None:
-        self.df = self.original_df.copy(deep=True)
\ No newline at end of file
+        self.df = self.original_df.copy(deep=True)
+
+    def get_summary(self) -> dict:
+        return {
+            "total_events": int(len(self.df)),
+            "total_posts": int((self.df["type"] == "post").sum()),
+            "total_comments": int((self.df["type"] == "comment").sum()),
+            "unique_users": int(self.df["author"].nunique()),
+            "time_range": {
+                "start": int(self.df["dt"].min().timestamp()),
+                "end": int(self.df["dt"].max().timestamp())
+            }
+        }
+
+