From c298a22257a433a090b18b4042954dd35b36e848 Mon Sep 17 00:00:00 2001
From: Ayden Jahola <jaholaayden@gmail.com>
Date: Sun, 8 Sep 2024 18:57:37 +0100
Subject: [PATCH] add scripts

---
 scripts/removeDuplicate.js | 45 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)
 create mode 100644 scripts/removeDuplicate.js

diff --git a/scripts/removeDuplicate.js b/scripts/removeDuplicate.js
new file mode 100644
index 0000000..91c2e17
--- /dev/null
+++ b/scripts/removeDuplicate.js
@@ -0,0 +1,45 @@
+const mongoose = require("mongoose");
+
+require("dotenv").config();
+
+const TriviaQuestion = require("../models/TriviaQuestion");
+
+// Connect to MongoDB
+mongoose
+  .connect(process.env.MONGODB_URI)
+  .then(() => console.log("✅ Connected to MongoDB"))
+  .catch((err) => console.error("❌ Failed to connect to MongoDB", err));
+
+async function removeDuplicates() {
+  try {
+    // Aggregate duplicates
+    const duplicates = await TriviaQuestion.aggregate([
+      {
+        $group: {
+          _id: "$question", // Group by the question text
+          count: { $sum: 1 },
+          ids: { $push: "$_id" }, // Collect ids of the duplicate entries
+        },
+      },
+      {
+        $match: { count: { $gt: 1 } }, // Match groups with more than one document
+      },
+    ]);
+
+    // Remove duplicates
+    for (const doc of duplicates) {
+      const idsToRemove = doc.ids.slice(1); // Keep the first entry and remove the rest
+      await TriviaQuestion.deleteMany({ _id: { $in: idsToRemove } });
+      console.log(`Removed duplicates: ${idsToRemove}`);
+    }
+
+    console.log("Duplicates removed");
+  } catch (err) {
+    console.error("Error removing duplicates:", err);
+  } finally {
+    // Close the connection
+    mongoose.connection.close();
+  }
+}
+
+removeDuplicates();