utils/pathfunctions.py

@@ -69,6 +69,7 @@ def split_filepaths_grouped(df, col="filename", group_parts=4, min_parts=4):
             row["longestcfp"] = prefix_str
             row["middle"] = middle
             row["filename_only"] = filename
+            row["file_extension"] = os.path.splitext(filename)[1]
             new_rows.append(row)
 
     return pd.DataFrame(new_rows).drop(columns=["group_key"])
@@ -175,7 +176,7 @@ def generatePathReview(first_policy, second_policy, badpathparts, min_files_for_
         lcp_not_forbidden = haslcp[~forbidden_lcfp].copy()
 
         #For the review, drop down to only the columns we care, and then group by the commmon file path, consolidating and dropping dupes
-        lcp_not_forbidden_review = lcp_not_forbidden[['longestcfp', 'middle', 'filename_only', 'sha256']]				
+        lcp_not_forbidden_review = lcp_not_forbidden[['longestcfp', 'middle', 'filename_only', 'file_extension', 'sha256']]				
 
         # Count unique sha256 per longestcfp
         unique_sha_counts = lcp_not_forbidden_review.groupby('longestcfp')['sha256'].nunique().reset_index()

utils/policyfunctions.py

@@ -95,19 +95,23 @@ def sendToPolicy(url, first_policy, second_policy, destination_name, destination
     ct.areYouSure()
     confirmation = input(ct.colorText("Type 'I AGREE' to continue: ","white"))
 
+
     if confirmation.strip().upper() == "I AGREE":
         print(ct.colorText("Proceeding with the code...", "yellow"))
         print(ct.colorText(f"Adding path exclusions to {destination_name}", "yellow"))
-        pathexcludelist = pathexclusions['longestcfp'].unique().tolist()
+
+        # Get unique combinations of longestcfp and file_extension
+        unique_combinations = pathexclusions[["longestcfp", "file_extension"]].drop_duplicates()
 
         # Regex to match a Windows drive letter at the start (e.g., C:\)
         drive_letter_pattern = re.compile(r'^[a-zA-Z]:\\')
 
-        # Processed list
+        # Build processed paths like \\path\\**.exe or C:\path\**.jar
         processed_paths = [
-            (path if drive_letter_pattern.match(path) else f"\\\\{path}") + "**"
-            for path in pathexcludelist
-]
+            (path if drive_letter_pattern.match(path) else f"\\\\{path}") + f"\\**{ext}"
+            for path, ext in unique_combinations.itertuples(index=False, name=None)
+        ]
+
         addPath(url, destination_id,processed_paths)
         
         print(ct.colorText(f"Adding hashes to {allowlist_parent_name}", "yellow"))