Paths fixed... need to double check the path exclusion format to feed api

AirlockTools.py

@@ -18,6 +18,7 @@ import gc
 import json
 import os
 import pandas as pd
+import re
 import urllib3
 import utils.allowlist
 import utils.getdeviceevents
@@ -26,13 +27,14 @@ import utils.pathfunctions
 import utils.policyfunctions
 import utils.pretty as ct
 
+
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 dotenv.load_dotenv()
 
 #Constants
 url = os.getenv('url')
-badpublisherlist = ["Brave Software, Inc.",	"Zoom Video Communications, Inc.", "GlavSoft LLC"]
+bad_publisher_list = ["Brave","Zoom", "GlavSoft", "VNC"]
 pups = ["logmein", "invalid"]
 badpathparts = ["users", "wwwroot", "windows\\temp", "windows\\task", "windows\\system32", "startup", "windows\\fonts", "Recycle.Bin", "AppData", "programdata"]
 path_exclusion_constant = 3
@@ -277,7 +279,7 @@ def menu_prepare_to_enforce():
 				categorized = utils.hashfunctions.categorizeHashes(
 					pd.read_parquet(f"parquet\\combined_hashlist_{first_policy}_{second_policy}.parquet"),
 					threat_tolerance_constant,
-					badpublisherlist,
+					bad_publisher_list,
 					pups
 				)
 
@@ -325,86 +327,15 @@ def menu_prepare_to_enforce():
 				del condensed_combo
 				gc.collect()
 
-			if not os.path.exists(f"needs_approved\\hashes_rep_unknown_{first_policy}_{second_policy}.csv"):
+		
-				
+			
-				condensed_combo = pd.read_parquet(f"parquet\\condensed_executions_{first_policy}_{second_policy}.parquet")
-				needsapproval= pd.read_parquet(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet")
-				
-				#Pull hash info for the entries in the needs approval table
-				needsapproval = pd.merge(condensed_combo, needsapproval, on='sha256', how='inner')
-				
-				#Deduplicate lists in the columns
-				for col in needsapproval.columns:
-					if needsapproval[col].apply(lambda x: isinstance(x, list)).all():
-						needsapproval[col] = needsapproval[col].apply(deduplicate_list)
-
-				#Rename Publisher, Keep and reorder columns we want
-				needsapproval = needsapproval.rename(columns={'publisher_x': 'publisher'})
-				needsapproval = needsapproval[['sha256', 'publisher', 'description', 'filename', 'hostname', 'username', 'productname', 'productversion','reputation_lastseen', 'reputation_scannermatch', 'reputation_scannercount','reputation_status', 'reputation_threatlevel', 'reputation_threatname','reputation_timestamp', 'pprocess', 'gprocess', 'commandline']]
-				
-				needsapproval['filename_key'] = needsapproval['filename'].apply(lambda x: x[0] if isinstance(x, list) and x else '')
-				needsapproval = needsapproval.sort_values(by='filename_key').drop(columns=['filename_key'])
-
-				needsapproval.to_parquet(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet",index=False)
-
-				del needsapproval
-				del condensed_combo
-				gc.collect()
-
-			if not os.path.exists(f"needs_approved\\hashes_rep_good_{first_policy}_{second_policy}.csv"):
-				
-				condensed_combo = pd.read_parquet(f"parquet\\condensed_executions_{first_policy}_{second_policy}.parquet")
-				needsapproval= pd.read_parquet(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet")
-				
-				#Pull hash info for the entries in the needs approval table
-				needsapproval = pd.merge(condensed_combo, needsapproval, on='sha256', how='inner')
-				
-				#Deduplicate lists in the columns
-				for col in needsapproval.columns:
-					if needsapproval[col].apply(lambda x: isinstance(x, list)).all():
-						needsapproval[col] = needsapproval[col].apply(deduplicate_list)
-
-				#Rename Publisher, Keep and reorder columns we want
-				needsapproval = needsapproval.rename(columns={'publisher_x': 'publisher'})
-				needsapproval = needsapproval[['sha256', 'publisher', 'description', 'filename', 'hostname', 'username', 'productname', 'productversion','reputation_lastseen', 'reputation_scannermatch', 'reputation_scannercount','reputation_status', 'reputation_threatlevel', 'reputation_threatname','reputation_timestamp', 'pprocess', 'gprocess', 'commandline']]
-				
-				needsapproval['filename_key'] = needsapproval['filename'].apply(lambda x: x[0] if isinstance(x, list) and x else '')
-				needsapproval = needsapproval.sort_values(by='filename_key').drop(columns=['filename_key'])
-
-				needsapproval.to_parquet(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet", index=False)
-
-				del needsapproval
-				del condensed_combo
-				gc.collect()
-				
-			if not os.path.exists(f"needs_approved\\hashes_rep_bad_{first_policy}_{second_policy}.html"):
-				
-				condensed_combo = pd.read_parquet(f"parquet\\condensed_executions_{first_policy}_{second_policy}.parquet")
-				needsapproval= pd.read_parquet(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet")
-				
-				#Pull hash info for the entries in the needs approval table
-				needsapproval = pd.merge(condensed_combo, needsapproval, on='sha256', how='inner')
-				
-				#Deduplicate lists in the columns
-				for col in needsapproval.columns:
-					if needsapproval[col].apply(lambda x: isinstance(x, list)).all():
-						needsapproval[col] = needsapproval[col].apply(deduplicate_list)
-
-				#Rename Publisher, Keep and reorder columns we want
-				needsapproval = needsapproval.rename(columns={'publisher_x': 'publisher'})
-				needsapproval = needsapproval[['sha256', 'publisher', 'description', 'filename', 'hostname', 'username', 'productname', 'productversion','reputation_lastseen', 'reputation_scannermatch', 'reputation_scannercount','reputation_status', 'reputation_threatlevel', 'reputation_threatname','reputation_timestamp', 'pprocess', 'gprocess', 'commandline']]
-				
-				needsapproval['filename_key'] = needsapproval['filename'].apply(lambda x: x[0] if isinstance(x, list) and x else '')
-				needsapproval = needsapproval.sort_values(by='filename_key').drop(columns=['filename_key'])
-				
-				needsapproval.to_parquet(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet", index=False)
-				
-				del needsapproval
-				del condensed_combo
-				gc.collect()
 				
 			if os.path.exists(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet") & os.path.exists(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet") & os.path.exists(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet"):
-			
+				
+				utils.hashfunctions.combineHashAndHist(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet", first_policy, second_policy)			
+				utils.hashfunctions.combineHashAndHist(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet", first_policy, second_policy)
+				utils.hashfunctions.combineHashAndHist(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet", first_policy, second_policy)
+
 				unknown = pd.read_parquet(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet")
 				good = pd.read_parquet(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet")
 				bad = pd.read_parquet(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet")
@@ -423,15 +354,14 @@ def menu_prepare_to_enforce():
 				unknown = unknown[~unknown["filename"].str.contains(pattern, na=False)]
 				good = good[~good["filename"].str.contains(pattern, na=False)]
 
-
 				unknown.to_csv(f"needs_approved\\hashes_rep_unknown_{first_policy}_{second_policy}.csv",index=False)
 				good.to_csv(f"needs_approved\\hashes_rep_good_{first_policy}_{second_policy}.csv",index=False)
+				bad.to_csv(f"needs_approved\\hashes_rep_bad_{first_policy}_{second_policy}.csv",index=False)
 
 				ct.style_dataframe_dark(unknown, f"needs_approved\\hashes_rep_unknown_{first_policy}_{second_policy}.html")
 				ct.style_dataframe_dark(good, f"needs_approved\\hashes_rep_good_{first_policy}_{second_policy}.html")
 				ct.style_dataframe_dark(bad, f"needs_approved\\hashes_rep_bad_{first_policy}_{second_policy}.html")
 
-
 		elif choice == "3":
 			
 			if os.path.exists(f"approved\\hashes_rep_unknown_{first_policy}_{second_policy}.csv") and os.path.exists(f"approved\\hashes_rep_good_{first_policy}_{second_policy}.csv"):
@@ -454,54 +384,67 @@ def menu_prepare_to_enforce():
 				if not os.path.exists(f"parquet\\path_needs_approved_{first_policy}_{second_policy}.parquet"):
 					all_approved_hashes = pd.read_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet")
 					print(ct.colorText(f"Beginning calculating longest common filepaths for path exceptions","green"))
-					grouped_df_view, df_with_groups_appended = utils.pathfunctions.export_groups_for_review(all_approved_hashes,"filename","longestcfp",min_files_for_path,path_exclusion_constant)
+					
-				
+					haslcp = utils.pathfunctions.split_filepaths_grouped(all_approved_hashes)
-					df_with_groups_appended.to_parquet(f"parquet\\approved_hashes_with_paths_{first_policy}_{second_policy}.parquet", index=False)
+					haslcp.drop_duplicates()
-		
+
 					forbidden = utils.pathfunctions.regulator(badpathparts, True)
-					forbidden_lcfp = grouped_df_view["longestcfp"].str.contains(forbidden, na=False)
+					forbidden_lcfp = haslcp["longestcfp"].str.contains(forbidden, na=False)
-
-					# Make a real DataFrame copy before modifying
-					grouped_df_view = grouped_df_view[~forbidden_lcfp].copy()
 
+					
 					print(ct.colorText("Removing forbidden filepaths for path exceptions", "green"))
 
-					for col in grouped_df_view.columns:
+					# Make a real DataFrame copy before modifying
-							if grouped_df_view[col].apply(lambda x: isinstance(x, list)).all():
+					lcp_not_forbidden = haslcp[~forbidden_lcfp].copy()
-								grouped_df_view[col] = grouped_df_view[col].apply(deduplicate_list)
 
 
-					grouped_df_view.to_parquet(f"parquet\\path_needs_approved_{first_policy}_{second_policy}.parquet", index=False)
+					#For the review, drop down to only the columns we care, and then group by the commmon file path, consolidating and dropping dupes
-					grouped_df_view.to_csv(f"needs_approved\\path_needs_approved_{first_policy}_{second_policy}.csv", index=False)
+					lcp_not_forbidden_review = lcp_not_forbidden[['longestcfp', 'middle', 'filename_only', 'sha256']]				
-					ct.style_dataframe_dark(grouped_df_view, f"needs_approved\\path_needs_approved_{first_policy}_{second_policy}.html")
+
+					# Count unique sha256 per longestcfp
+					unique_sha_counts = lcp_not_forbidden_review.groupby('longestcfp')['sha256'].nunique().reset_index()
+					unique_sha_counts.columns = ['longestcfp', 'unique_sha256_count']
+
+					# Merge the count back into the original DataFrame
+					lcp_not_forbidden_review = lcp_not_forbidden_review.merge(unique_sha_counts, on='longestcfp', how='left')
+					lcp_not_forbidden_review = lcp_not_forbidden_review[lcp_not_forbidden_review['unique_sha256_count'] >= min_files_for_path]
+			
+
+
+	
 					
-					del grouped_df_view
+					lcp_not_forbidden_review.to_parquet(f"parquet\\path_needs_approved_{first_policy}_{second_policy}.parquet",index=False)
-					del df_with_groups_appended
+					lcp_not_forbidden_review.to_csv(f"needs_approved\\path_needs_approved_{first_policy}_{second_policy}.csv",index=False)
-					gc.collect()
+								
-
+				
 			else:
 				print(ct.colorText(f"Please manually approve hashes prior to this step","red"))
-
+					
-
 		elif choice == "4":
 			
-			if os.path.exists(f"parquet\\approved_hashes_with_paths_{first_policy}_{second_policy}.parquet") and os.path.exists(f"approved\\path_needs_approved_{first_policy}_{second_policy}.csv"):
+			if  os.path.exists(f"approved\\path_needs_approved_{first_policy}_{second_policy}.csv"):
 				if not os.path.exists(f"parquet\\final_hash_approvals_{first_policy}_{second_policy}.parquet") and not os.path.exists(f"parquet\\final_path_exclusions_{first_policy}_{second_policy}.parquet"):
-					df1 = pd.read_parquet(f"parquet\\approved_hashes_with_paths_{first_policy}_{second_policy}.parquet")
+					allhashes = pd.read_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet")
-					allowbyhash = utils.pathfunctions.mask_from_csv(df1, f"approved\\path_needs_approved_{first_policy}_{second_policy}.csv","longestcfp")
 					
 					pathexclusions = tryToReadCSV(f"approved\\path_needs_approved_{first_policy}_{second_policy}.csv")
-					
 					pathexclusions.to_parquet(f"parquet\\final_path_exclusions_{first_policy}_{second_policy}.parquet", index=False)
 		
+					allowbyhash = allhashes[~allhashes['sha256'].isin(pathexclusions['sha256'])]
+
 					allowbyhash.to_parquet(f"parquet\\final_hash_approvals_{first_policy}_{second_policy}.parquet", index=False)
-				
+
 					easyview = allowbyhash.groupby('sha256').agg(list).reset_index()
+					# Deduplicate all list columns in easyview
+					for col in easyview.columns:
+						if col != 'sha256':  # Skip the grouping column
+							easyview[col] = easyview[col].apply(lambda x: list(set(x)))
+
+					easyview = easyview.sort_values(by=["reputation_status", "filename"])
 			
 					ct.style_dataframe_dark(easyview, f"preflight\\final_hash_approvals_{first_policy}_{second_policy}.html")
 					ct.style_dataframe_dark(pathexclusions, f"preflight\\final_path_exclusions_{first_policy}_{second_policy}.html")
 
-					del df1
+					
 					del allowbyhash
 					del pathexclusions
 					del easyview
@@ -542,7 +485,19 @@ def menu_prepare_to_enforce():
 					print(ct.colorText("Proceeding with the code...", "yellow"))
 					print(ct.colorText(f"Adding path exclusions to {destination_name}", "yellow"))
 					pathexcludelist = pathexclusions['longestcfp'].unique().tolist()
-					utils.policyfunctions.addPath(destination_id,pathexcludelist)
+
+				
+
+					# Regex to match a Windows drive letter at the start (e.g., C:\)
+					drive_letter_pattern = re.compile(r'^[a-zA-Z]:\\')
+
+					# Processed list
+					processed_paths = [
+						(path if drive_letter_pattern.match(path) else f"\\\\{path}") + "**"
+						for path in pathexcludelist
+]
+
+					utils.policyfunctions.addPath(destination_id,processed_paths)
 					
 					print(ct.colorText(f"Adding hashes to {allowlist_parent_name}", "yellow"))
 										
@@ -554,6 +509,8 @@ def menu_prepare_to_enforce():
 					utils.policyfunctions.addHash(allowlist_child_id, allowlist_childhashlist)			
 
 					ct.locked()
+					print(repr(processed_paths))
+					print(processed_paths)
 					exit()		
 					
 				else:

utils/hashfunctions.py

@@ -19,6 +19,7 @@ import os
 import json
 import utils.pathfunctions as pathf
 import utils.pretty as ct
+import gc
 
 
 def aggregateHashes(executions_json) -> pd.DataFrame:
@@ -103,7 +104,7 @@ def augmentAggregatedHashes(url, agg_df: pd.DataFrame) -> pd.DataFrame:
 
     return aug_df
 
-def categorizeHashes(df: pd.DataFrame, threat_tolerance: int, untrusted_publishers: list, pups: list):
+def categorizeHashes(df: pd.DataFrame, threat_tolerance: int, untrusted_publishers, pups: list):
     if untrusted_publishers is None: untrusted_publishers = []
     if pups is None: pups = []
 
@@ -126,14 +127,14 @@ def categorizeHashes(df: pd.DataFrame, threat_tolerance: int, untrusted_publishe
     mask_approved = (
         (
             (df["publisher"] != "Not Signed") &
-            ~df["publisher"].isin(untrusted_publishers) &
+            ~df["publisher"].str.contains(pathf.regulator(untrusted_publishers), case=False, na=False) &
             ~df["reputation_status"].isna() &
             ~df["description"].str.contains(pathf.regulator(pups), case=False, na=False)
         ) |
         (
             (df["publisher"] == "Not Signed") &
             ~df["reputation_flag"] &
-            ~df["publisher"].isin(untrusted_publishers) &
+            ~df["publisher"].str.contains(pathf.regulator(untrusted_publishers), case=False, na=False) &
             ~df["reputation_status"].isna() &
             ~df["description"].str.contains(pathf.regulator(pups), case=False, na=False)
         )
@@ -203,3 +204,21 @@ def destinationHashes(
     # Concatenate results
     df_hashdestination = pd.concat([df_paths, df_hashes], ignore_index=True)
     return df_hashdestination
+
+def combineHashAndHist(path, first_policy, second_policy):
+
+    condensed_combo = pd.read_parquet(f"parquet\\condensed_executions_{first_policy}_{second_policy}.parquet")
+    df = pd.read_parquet(path)
+			
+	#Pull hash info for the entries in the needs approval table
+    df = pd.merge(condensed_combo, df, on='sha256', how='inner')
+    
+    #Rename Publisher, Keep and reorder columns we want
+    df = df.rename(columns={'publisher_x': 'publisher'})
+    df = df[['sha256', 'publisher', 'description', 'filename', 'hostname', 'username', 'productname', 'productversion','reputation_lastseen', 'reputation_scannermatch', 'reputation_scannercount','reputation_status', 'reputation_threatlevel', 'reputation_threatname','reputation_timestamp', 'pprocess', 'gprocess', 'commandline']]
+    df = df.sort_values(by='filename')
+
+    df.to_parquet(path, index=False)
+    del df
+    del condensed_combo
+    gc.collect()

utils/pathfunctions.py

@@ -15,73 +15,60 @@
 
 import pandas as pd
 import os
-from itertools import chain
 import ast
 import re
 
-def split_path(path):
+import os
-    parts = []
+import pandas as pd
-    while True:
-        head, tail = os.path.split(path)
-        if tail:
-            parts.insert(0, tail)
-            path = head
-        else:
-            if head:
-                parts.insert(0, head)
-            break
-    return parts
 
-def local_common_pass(paths, min_parts=3):
+import os
-    results = {}
+import pandas as pd
-    paths_sorted = sorted(paths)
-    for i, path in enumerate(paths_sorted):
-        candidates = []
 
-        if i > 0:
+def split_filepaths_grouped(df, col="filename", group_parts=3, min_parts=3):
-            try:
+    def clean_split(path):
-                candidates.append(os.path.commonpath([path, paths_sorted[i-1]]))
+        parts = os.path.normpath(path).split(os.sep)
-            except ValueError:
+        # Remove leading empty strings caused by UNC paths
-                # different drives, skip
+        parts = [p for p in parts if p]
-                pass
+        return parts
-        if i < len(paths_sorted) - 1:
-            try:
-                candidates.append(os.path.commonpath([path, paths_sorted[i+1]]))
-            except ValueError:
-                # different drives, skip
-                pass
 
-        best = path
+    df = df.copy()
-        best_len = 0
+    split_paths = df[col].apply(clean_split)
-        for c in candidates:
-            parts = split_path(c)
-            if len(parts) >= min_parts and len(parts) > best_len:
-                best = c
-                best_len = len(parts)
-        results[path] = best
-    return results
 
-def add_longest_common_two_local(df, col="filename_x", new_col="longestcfp", min_parts=3):
+    # Filter out paths with fewer than `min_parts` components
-    dirs_series = df[col].astype(str).apply(os.path.dirname)
+    df = df[split_paths.apply(lambda parts: len(parts) >= min_parts)].copy()
-    first_pass = local_common_pass(dirs_series.tolist(), min_parts)
+    split_paths = split_paths[df.index]  # Update split_paths to match filtered df
-    second_pass = local_common_pass(list(first_pass.values()), min_parts)
-    df[new_col] = dirs_series.map(lambda d: second_pass[first_pass[d]])
-    return df
 
-def export_groups_for_review(df, col, group_col, min_number_in_group, path_length_constant):
+    df["group_key"] = split_paths.apply(lambda parts: os.sep.join(parts[:group_parts]))
-    """
+    grouped = df.groupby("group_key")
-    Compute longest common paths, group filepaths, write CSV for review.
+    new_rows = []
-    """
-    df = df.drop_duplicates(subset=[col], keep='first')
-    df = add_longest_common_two_local(df, col=col, new_col=group_col)
-    grouped = df.groupby(group_col)[col].apply(list).reset_index()
-    grouped = grouped.sort_values(by=col)
-    print("Before filtering:", len(grouped))
-    grouped = grouped[grouped[col].apply(lambda x: len(x) >= min_number_in_group)]
-    filtered = grouped[grouped[group_col].apply(lambda x: len(os.path.normpath(x).split(os.sep)) >= path_length_constant)]
-    print("After filtering:", len(grouped))
 
-    return filtered, df
+    for _, group_df in grouped:
+        paths = group_df[col].tolist()
+        split_parts = [clean_split(p) for p in paths]
+
+        def longest_common_prefix(paths):
+            if not paths:
+                return []
+            prefix = paths[0]
+            for path in paths[1:]:
+                prefix = [a for a, b in zip(prefix, path) if a == b]
+                if not prefix:
+                    break
+            return prefix
+
+        common_prefix = longest_common_prefix(split_parts)
+        prefix_str = os.sep.join(common_prefix)
+
+        for i, parts in enumerate(split_parts):
+            filename = parts[-1]
+            middle = os.sep.join(parts[len(common_prefix):-1]) if len(parts) > len(common_prefix) + 1 else ""
+            row = group_df.iloc[i].copy()
+            row["longestcfp"] = prefix_str
+            row["middle"] = middle
+            row["filename_only"] = filename
+            new_rows.append(row)
+
+    return pd.DataFrame(new_rows).drop(columns=["group_key"])
 
 def mask_from_csv(df, csv_path, filepath_col):
     """