Exclusion Divide added

AirlockTools.py

@@ -15,6 +15,7 @@
 import argparse
 import dotenv
 import os
+import re
 import pandas as pd
 import urllib3
 import utils.clientfunctions
@@ -133,7 +134,7 @@ def menu_main():
 		ct.displayIntro();
 		print(ct.colorText("1. Get All Events for Single Device", "yellow"))
 		print(ct.colorText("2. OTP", "yellow"))
-		print(ct.colorText("3. Placeholder for Another Tool", "yellow"))
+		print(ct.colorText("3. Divide by Exclusion", "yellow"))
 		print(ct.colorText("4. Prepare Policy For Enforcement", "yellow"))
 		print(ct.colorText("Q. Quit", "yellow"))
 
@@ -174,9 +175,11 @@ def menu_otp():
 def menu_feature2():
 	while True:
 		print("\n--- Submenu ---")
-		print("1. Pull last 24 horus execution for all ATPolicys")
+		print("1. Pull last 24 hours execution for all ATPolicys")
 		print("2. Generate Paths")
-		print("3  Merge")
+		print("3.  Merge")
+		print("4. Pull existing paths")
+		print("5. Divide By Excluded or not excluded by path")
 		print("Q. Exit")
 		choice = input("Enter your choice: ")
 
@@ -218,6 +221,115 @@ def menu_feature2():
 
 		elif choice == "3":
 			utils.pathfunctions.mergeTesting()
+
+		elif choice == "4":
+
+
+			# Get the AT policies dictionary
+			atpolicies = utils.policyfunctions.listATPolicies(url)
+
+			# List to hold each policy's path data
+			all_paths = []
+
+			# Loop through each policy name and group ID
+			for policy_name, group_id in atpolicies.items():
+				try:
+					# Get the list of paths using the group ID
+					paths = utils.pathfunctions.listPaths(url, group_id)
+
+					# Ensure each path is a string and append properly
+					for path in paths:
+						if isinstance(path, str):
+							all_paths.append({
+								'PolicyName': policy_name,
+								'GroupID': group_id,
+								'Path': path
+							})
+				except Exception as e:
+					print(f"Error retrieving paths for policy '{policy_name}': {e}")
+
+			# Convert to DataFrame
+			if all_paths:
+				paths_df = pd.DataFrame(all_paths)
+				print(paths_df.head())  # Optional: preview first few rows
+				print("✅ Paths DataFrame created.")
+			else:
+				paths_df = pd.DataFrame()
+				print("⚠️ No paths were retrieved.")
+
+			# Save to CSV
+			paths_df.to_csv("paths.csv", index=False)
+		elif choice == "5":
+
+			# Load and clean data
+			filenames_df = pd.read_csv('merged_output.csv')  # Contains 'PolicyName' and 'filename'
+			exclusions_df = pd.read_csv('paths.csv')  # Contains 'PolicyName' and 'Path'
+
+			# Clean and normalize columns
+			filenames_df['filename'] = filenames_df['filename'].fillna('').astype(str).str.strip()
+			filenames_df['PolicyName'] = filenames_df['PolicyName'].fillna('').astype(str).str.strip()
+			exclusions_df['Path'] = exclusions_df['Path'].fillna('').astype(str).str.strip()
+			exclusions_df['PolicyName'] = exclusions_df['PolicyName'].fillna('').astype(str).str.strip()
+
+			# Decode escaped backslashes in exclusion patterns
+			exclusions_df['Path'] = exclusions_df['Path'].apply(lambda p: p.encode('utf-8').decode('unicode_escape'))
+
+			# Build exclusion map: {PolicyName: [compiled regex patterns]}
+			exclusion_map = {}
+			for _, row in exclusions_df.iterrows():
+				policy = row['PolicyName']
+				raw_pattern = row['Path']
+				try:
+					regex = utils.pathfunctions.wildcardRegex(raw_pattern)
+					print(f"[EXCLUSION MAP] Policy: {policy}, Pattern: {raw_pattern} → Regex: {regex.pattern}")
+					exclusion_map.setdefault(policy, []).append(regex)
+				except Exception as e:
+					print(f"[ERROR] Failed to compile pattern for Policy: {policy}, Path: {raw_pattern}, Error: {e}")
+
+			# Function to check if a filename matches any exclusion pattern for its PolicyName
+			def is_excluded(row):
+				policy = row['PolicyName'].strip()
+				path = os.path.normpath(row['filename'].strip())
+				patterns = exclusion_map.get(policy, [])
+				for r in patterns:
+					if r.match(path):
+						print(f"[MATCH] {policy}: {path} matches {r.pattern}")
+						return True
+				print(f"[NO MATCH] {policy}: {path}")
+				return False
+
+			# Apply matching
+			excluded = filenames_df[filenames_df.apply(is_excluded, axis=1)]
+			not_excluded = filenames_df[~filenames_df.apply(is_excluded, axis=1)]
+
+			
+			# Desired column order
+			column_order = [
+				'PolicyName', 'filename', 'longestcfp',
+				'pprocess', 'gprocess',  'sha256', 'publisher', 'description', 'productname','commandline',  'middle', 'filename_only',
+				'file_extension', 'unique_sha256_count', 'hostname', 'username', 'productversion',
+				'reputation_lastseen', 'reputation_scannermatch', 'reputation_scannercount',
+				'reputation_status', 'reputation_threatlevel', 'reputation_threatname', 'reputation_timestamp'
+			]
+
+			# Reorder columns (ignore missing ones)
+			excluded = excluded[[col for col in column_order if col in excluded.columns]]
+			not_excluded = not_excluded[[col for col in column_order if col in not_excluded.columns]]
+
+
+			# Save results
+			excluded.to_csv('excluded_filenames.csv', index=False)
+			not_excluded.to_csv('non_excluded_filenames.csv', index=False)
+
+
+		elif choice == "6":
+					
+			pattern = utils.pathfunctions.wildcardRegex("C:\\Windows\\SystemTemp\\????????\\????????.dll")
+			test_path = "C:\\Windows\\SystemTemp\\fsq2xzua\\fsq2xzua.dll"
+
+			print("Match:", pattern.match(test_path) is not None)
+
+
 		elif choice == "Q":
 			break
 		else: