From 5c00a2f16acad7e206b2c46b0c04aa1d74e2d1c1 Mon Sep 17 00:00:00 2001
From: Marco Realacci <marco@marcorealacci.me>
Date: Sun, 6 Nov 2022 17:26:42 +0100
Subject: [PATCH] Introduced DiffyBOT! A tool that finds duplicate questions

---
 diffybot.py | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)
 create mode 100644 diffybot.py

diff --git a/diffybot.py b/diffybot.py
new file mode 100644
index 0000000..b8d25c6
--- /dev/null
+++ b/diffybot.py
@@ -0,0 +1,52 @@
+# A python helper script that finds duplicates
+
+import os
+
+path = input("Specify the path: ")
+
+quests = list(os.walk(path))[0][1]
+
+m = {}
+
+print("Loading questions...")
+
+for q in quests:
+    qq = open(path + "/" + q + "/quest.txt", "r").read()
+    if qq.startswith("img=") and "\n" in qq:
+        qq = qq[qq.index("\n"):]
+
+    cc = open(path + "/" + q + "/correct.txt", "r").read()
+    if cc.startswith("img=") and "\n" in cc:
+        cc = cc[cc.index("\n"):]
+    
+    qq = qq + cc
+
+    qq = qq.replace("\n", "")
+    qq = qq.replace("<pre>", "")
+    qq = qq.replace("<code>", "")
+    qq = qq.replace("</pre>", "")
+    qq = qq.replace("</code>", "")
+    qq = qq.replace("'", "")
+    qq = qq.replace("à", "a")
+    qq = qq.replace("è", "e")
+    qq = qq.replace("ì", "i")
+    qq = qq.replace("ò", "o")
+    qq = qq.replace("ù", "u")
+    qq = qq.replace(" ", "")
+    m[q] = qq
+
+print("Comparing questions...")
+
+rev_dict = {}
+
+for key, value in m.items():
+    rev_dict.setdefault(value, set()).add(key)
+
+
+result = [values for key, values in rev_dict.items()
+                              if len(values) > 1]
+
+if result:
+    print("Duplicate questions:", str(result))
+else:
+    print("There are no duplicates!")
\ No newline at end of file