From 256611bef5372295004d3aa10e94c841ac57c1e0 Mon Sep 17 00:00:00 2001
From: Aayush Goel <81844215+Aayush-Goel-04@users.noreply.github.com>
Date: Thu, 27 Apr 2023 06:00:38 +0530
Subject: [PATCH] Create detect_duplicate_features.py

Fixes #1451
Python script to detect feature overlap between new and existing CAPA rules. Checks if the a feature in new rules exists in an existing rule
---
 scripts/detect_duplicate_features.py | 67 ++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)
 create mode 100644 scripts/detect_duplicate_features.py

diff --git a/scripts/detect_duplicate_features.py b/scripts/detect_duplicate_features.py
new file mode 100644
index 00000000..7da0655e
--- /dev/null
+++ b/scripts/detect_duplicate_features.py
@@ -0,0 +1,67 @@
+import os
+import yaml
+
+def findall_features(features):
+    feature_list = []
+    for feature in features:
+        if 'and' in feature:
+            and_list = findall_features(feature['and'])
+            for x in and_list:
+                feature_list.append(x)
+        elif 'or' in feature:
+            or_list = findall_features(feature['or'])
+            for y in or_list:
+                feature_list.append(y)
+        else:
+            feature_list.append(feature)
+    return feature_list
+
+def find_overlapping_rules(new_rule_path, rules_path):
+    if not new_rule_path.endswith('.yml'):
+        return 'ERROR ! New rule path file name incorrect'
+    
+    count = 0
+
+    with open(new_rule_path, 'r') as f:
+        new_rule = yaml.safe_load(f)
+    if 'rule' not in new_rule:
+        return "ERROR ! given new rule path isn't a rule"
+    
+    new_rule_features = findall_features(new_rule['rule']['features'])
+
+    overlapping_rules = []
+    
+    for dirpath, dirnames, filenames in os.walk(rules_path):
+        for filename in filenames:
+            if filename.endswith('.yml'):
+                rule_path = os.path.join(dirpath, filename)
+                with open(rule_path, 'r') as f:
+                    rule = yaml.safe_load(f)
+                    if 'rule' not in rule:
+                        continue
+                    rule_features = findall_features(rule['rule']['features'])
+                    count+=1
+                if any([feature in rule_features for feature in new_rule_features]):
+                    overlapping_rules.append(rule_path)
+    result = {'overlapping_rules': overlapping_rules,
+              'count': count}
+    
+    return result
+
+# usage
+base_dir = ''
+new_rule_path = base_dir + 'rules\\anti-analysis\\reference-analysis-tools-strings.yml'
+rules_path = base_dir + 'rules'
+
+try:
+    result = find_overlapping_rules(new_rule_path, rules_path)
+    print('New rule path : %s' % new_rule_path)
+    print('Number of rules checked : %s ' % result['count'])
+    print('Paths to overlapping rules : ', result['overlapping_rules'])
+    print('Number of rules containing same features : %s' % len(result['overlapping_rules']))
+except Exception as e:
+    print(e)
+    try:
+        print(result,'')
+    except:
+        pass