From 1d14560e29d43e8cb5c59ff83a4e67cd85359932 Mon Sep 17 00:00:00 2001
From: arvindrai <arvindrai@1337.berkeley.edu>
Date: Tue, 2 Dec 2025 04:56:35 +0000
Subject: [PATCH] Upload files to "old-scripts"

uploaded
---
 old-scripts/top_vulnerability_types.py | 49 ++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)
 create mode 100644 old-scripts/top_vulnerability_types.py

diff --git a/old-scripts/top_vulnerability_types.py b/old-scripts/top_vulnerability_types.py
new file mode 100644
index 0000000..1d9eaf8
--- /dev/null
+++ b/old-scripts/top_vulnerability_types.py
@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+import json
+from collections import Counter
+import matplotlib.pyplot as plt
+
+# Path to your JSON file
+path = "wordfence_vulnerabilities.json"
+
+# Load JSON data
+with open(path, "r", encoding="utf-8") as f:
+    data = json.load(f)
+
+vuln_types = []
+
+for entry in data:
+    title = entry.get("title")
+    if not isinstance(title, str):
+        continue
+
+    # Split on the first dash (" - ") and take the right-hand side
+    if " - " in title:
+        vuln = title.split(" - ", 1)[1].strip()
+        vuln_types.append(vuln)
+
+# Count occurrences
+counts = Counter(vuln_types)
+top25 = counts.most_common(25)
+total = sum(counts.values())
+
+if not vuln_types:
+    print("⚠️ No vulnerability types found — check dash formatting.")
+    exit()
+
+# Print table of top 25
+print("\nTop 25 Vulnerability Types:\n")
+for name, count in top25:
+    rel = (count / total) * 100
+    print(f"{name:60} {count:5d} ({rel:5.2f}%)")
+
+# Visualization
+labels, values = zip(*top25)
+plt.figure(figsize=(10, 6))
+plt.barh(labels[::-1], values[::-1], color="cornflowerblue")
+plt.title("Top 25 Most Common Vulnerability Types")
+plt.xlabel("Count")
+plt.ylabel("Vulnerability Type")
+plt.tight_layout()
+plt.show()
+