String-Similiarity-Fix (#30364)

* fix script

* RN

* fix

* fixing

* RN

* fix to array

* testing

* Fix

* fix

* Fix

* test

* test

* RN

* fix

* fix

* fix unittest

* fix

* fix

* fix

* Bump pack from version CommonScripts to 1.12.39.

* Review Fixes

* ReleaseNotes fix

---------

Co-authored-by: Content Bot <[email protected]>

Packs/CommonScripts/ReleaseNotes/1_12_39.md

@@ -0,0 +1,5 @@
+
+#### Scripts
+
+##### StringSimilarity
+The script now supports comparing every string between two arrays of strings.

Packs/CommonScripts/Scripts/StringSimilarity/README.md

@@ -1,4 +1,4 @@
-This automation calculates the similarity ratio between text and a list of strings and outputs a decimal value between 0.0 and 1.0 (1.0 if the sequences are identical, and 0.0 if they don't have anything in common).
+This automation calculates the similarity ratio between every string in 2 different arrays and outputs a decimal value between 0.0 and 1.0 (1.0 if the sequences are identical, and 0.0 if they don't have anything in common).
 
 ## Script Data
 
@@ -14,16 +14,17 @@ This automation calculates the similarity ratio between text and a list of strin
 ---
 This script is used in the following playbooks and scripts.
 
-RDP Bitmap Cache - Detect and Hunt
+* RDP Bitmap Cache - Detect and Hunt
+* Compare Process Execution Arguments To LOLBAS Patterns
 
 ## Inputs
 
 ---
 
 | **Argument Name** | **Description** |
 | --- | --- |
-| string_A | First input string. |
-| string_B | Second input string. |
+| string_A | First array of strings to compare. |
+| string_B | Second array of strings to compare. |
 | similarity_threshold | The similarity threshold to show results for, a value between 0 < x >1. |
 
 ## Outputs

Packs/CommonScripts/Scripts/StringSimilarity/StringSimilarity.py

@@ -3,7 +3,7 @@
 import difflib
 
 
-def stringSimilarity(first_string: str, second_string: str, similarity_threshold: float):
+def stringSimilarity(first_array: str, second_array: str, similarity_threshold: float):
     """
     Calculate the similarity score between two strings using the SequenceMatcher.
 
@@ -26,26 +26,27 @@ def stringSimilarity(first_string: str, second_string: str, similarity_threshold
                     with a message indicating that no similarity score is calculated.
     """
 
-    similarity_ratio = difflib.SequenceMatcher(None, first_string, second_string).ratio()
-    if similarity_ratio >= float(similarity_threshold):
-        results = {
-            "StringA": first_string,
-            "StringB": second_string,
-            "SimilarityScore": similarity_ratio
-        }
-
-        return CommandResults("StringSimilarity", ["StringA", "StringB"], results)
-    return None
+    results = []
+    for string_a in first_array:
+        for string_b in second_array:
+            similarity_ratio = difflib.SequenceMatcher(None, string_a, string_b).ratio()
+            if similarity_ratio >= float(similarity_threshold):
+                results.append({
+                    "StringA": string_a,
+                    "StringB": string_b,
+                    "SimilarityScore": similarity_ratio
+                })
+    if not results:
+        return None
+    return CommandResults("StringSimilarity", ["StringA", "StringB"], results)
 
 
 def main():
     similarity_threshold = demisto.getArg('similarity_threshold')
-    first_string = demisto.getArg('string_A')
-    second_string = demisto.getArg('string_B')
-
+    first_array = argToList(demisto.getArg('string_A'))
+    second_array = argToList(demisto.getArg('string_B'))
     try:
-        results = stringSimilarity(first_string, second_string, similarity_threshold)
-
+        results = stringSimilarity(first_array, second_array, similarity_threshold)
         return_results(results)
     except Exception as e:
         return_error(f'Failed to check string similarity. Problem: {str(e)}')

Packs/CommonScripts/Scripts/StringSimilarity/StringSimilarity.yml

@@ -5,23 +5,25 @@ name: StringSimilarity
 script: ''
 type: python
 tags: []
-comment: This automation calculates the similarity ratio between text and a list of strings and outputs a decimal value between 0.0 and 1.0 (1.0 if the sequences are identical, and 0.0 if they don't have anything in common).
+comment: This automation calculates the similarity ratio between every string in 2 different arrays and outputs a decimal value between 0.0 and 1.0 (1.0 if the sequences are identical, and 0.0 if they don't have anything in common).
 enabled: true
 args:
 - name: string_A
   required: true
-  description: First input string.
+  description: First array of strings to compare.
+  isArray: true
 - name: string_B
   required: true
-  description: Second input string.
+  description: Second array of strings to compare.
+  isArray: true
 - name: similarity_threshold
   description: The similarity threshold to show results for, a value between 0 < x >1.
   defaultValue: "0.1"
 outputs:
 - contextPath: StringSimilarity.SimilarityScore
   description: Similarity score - a value between 1.0 if the sequences are identical, and 0.0 if they have nothing in common.
 scripttarget: 0
-dockerimage: demisto/python3:3.10.12.68714
+dockerimage: demisto/python3:3.10.13.78960
 subtype: python3
 runonce: false
 runas: DBotWeakRole

Packs/CommonScripts/Scripts/StringSimilarity/StringSimilarity_test.py

@@ -5,21 +5,21 @@
 
 
 @pytest.mark.parametrize("first_string, second_string, similarity_threshold, expected_result", [
-    ("hello", "hello", 0.9, {
+    (["hello"], ["hello"], 0.9, [{
         "StringA": "hello",
         "StringB": "hello",
         "SimilarityScore": 1.0,
-    }),
-    ("deeply", "deeply", 0.6, {
+    }]),
+    (["deeply"], ["deeply"], 0.6, [{
         "StringA": "deeply",
         "StringB": "deeply",
         "SimilarityScore": 1.0,
-    }),
-    ("testing", "test", 0.7, {
+    }]),
+    (["testing"], ["test"], 0.7, [{
         "StringA": "testing",
         "StringB": "test",
         "SimilarityScore": 0.7272727272727273,
-    }),
+    }]),
     ("a", "b", 0.1, {
      None})
 ])
@@ -62,7 +62,7 @@ def test_main_with_no_similarity_match(mocker):
     similarity_threshold = 0.1
     first_string = "hello"
     second_string = "world"
-    expected_results = {'StringA': 'hello', 'StringB': 'world', 'SimilarityScore': 0.2}
+    expected_results = [{'StringA': 'hello', 'StringB': 'world', 'SimilarityScore': 0.2}]
     # Mock demisto.getArg function to return the input arguments
     with patch.object(demisto, 'getArg') as mocked_getArg:
         mocked_getArg.side_effect = lambda arg_name: {

Packs/CommonScripts/pack_metadata.json

@@ -2,7 +2,7 @@
     "name": "Common Scripts",
     "description": "Frequently used scripts pack.",
     "support": "xsoar",
-    "currentVersion": "1.12.38",
+    "currentVersion": "1.12.39",
     "author": "Cortex XSOAR",
     "url": "https://www.paloaltonetworks.com/cortex",
     "email": "",