From ab6ee644c7d246ac1bc152f9bae44771eef941db Mon Sep 17 00:00:00 2001
From: = <=>
Date: Fri, 22 Aug 2025 16:19:59 -0400
Subject: [PATCH] Think i fixed the signed package issue

---
 utils/hashfunctions.py | 22 +++++++++++++++++-----
 utils/pathfunctions.py |  2 +-
 2 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/utils/hashfunctions.py b/utils/hashfunctions.py
index 5ea3dfa..0bb484d 100644
--- a/utils/hashfunctions.py
+++ b/utils/hashfunctions.py
@@ -78,19 +78,31 @@ def categorizeHashes(aug_df: pd.DataFrame, threat_tolerance: int, untrusted_publ
     def reputationtool(row):
         val = row["reputation_scannermatch"]
         if pd.isna(val) or val == "N/A":
-            return True if row["publisher_y"] == "Not Signed" else False
+            return row["publisher_y"] == "Not Signed"
         try:
             return int(val) > threat_tolerance
         except (ValueError, TypeError):
-            return True if row["publisher_y"] == "Not Signed" else False
+            return row["publisher_y"] == "Not Signed"
 
     df["reputation_flag"] = df.apply(reputationtool, axis=1)
 
-    mask_needsreview = (df["publisher_y"] == "Not Signed") & df["reputation_flag"]
+    mask_needsreview = (
+        ((df["publisher_y"] == "Not Signed") & df["reputation_flag"]) |
+        (df["reputation_status"] == "UNKNOWN")
+    )
 
     mask_approved = (
-        ((df["publisher_y"] != "Not Signed") & ~df["publisher_y"].isin(untrusted_publishers)) |
-        ((df["publisher_y"] == "Not Signed") & ~df["reputation_flag"] & ~df["publisher_y"].isin(untrusted_publishers))
+        (
+            (df["publisher_y"] != "Not Signed") &
+            ~df["publisher_y"].isin(untrusted_publishers) &
+            ~df["reputation_status"].isna()
+        ) |
+        (
+            (df["publisher_y"] == "Not Signed") &
+            ~df["reputation_flag"] &
+            ~df["publisher_y"].isin(untrusted_publishers) &
+            ~df["reputation_status"].isna()
+        )
     )
 
     needsreview_df = df[mask_needsreview]
diff --git a/utils/pathfunctions.py b/utils/pathfunctions.py
index 128da2a..7c01eec 100644
--- a/utils/pathfunctions.py
+++ b/utils/pathfunctions.py
@@ -106,7 +106,7 @@ def filepathInitialGroup(df: pd.DataFrame):
     path_eligible = grouped_df[grouped_df["depth"] > 2].drop(columns=["depth"])
     path_ineligible = grouped_df[grouped_df["depth"] <= 2].drop(columns=["depth"])
 
-    # Step 10: Move entries from eligible to ineligible if grouped_directory contains 'C:\Users' or 'c$\Users'
+    # Step 10: Move entries from eligible to ineligible if grouped_directory contains excluded directories'
     mask = path_eligible["grouped_directory"].str.contains(r"(?i)(?:\\Users|\\c\$\\Users|inetpub\\wwwroot|windows\\temp)", na=False)
     move_to_ineligible = path_eligible[mask]
     path_eligible = path_eligible[~mask]