Corrected Hash Functions to properly categorize Low threat unsigned hashes & added regular expessions to the path function eligibility logic

utils/hashfunctions.py

@@ -69,11 +69,12 @@ def augmentAggregatedHashes(url, agg_df: pd.DataFrame) -> pd.DataFrame:
     return aug_df
  
 def categorizeHashes(aug_df: pd.DataFrame, threat_tolerance: int, untrusted_publishers: list):
-   if untrusted_publishers is None:
-       untrusted_publishers = []
+    if untrusted_publishers is None:
+        untrusted_publishers = []
 
-   df = aug_df.copy()
-   def reputationtool(row, threat_tolerance):
+    df = aug_df.copy()
+
+    def reputationtool(row, threat_tolerance):
         if row["reputation_scannermatch"] == "N/A":
             return True
         try:
@@ -83,11 +84,15 @@ def categorizeHashes(aug_df: pd.DataFrame, threat_tolerance: int, untrusted_publ
             pass
         return False
 
-   mask_needsreview = (df["publisher_y"] == "Not Signed") & df.apply(lambda row: reputationtool(row, threat_tolerance), axis=1)
-   mask_approved = (df["publisher_y"] != "Not Signed") & (~df["publisher_y"].isin(untrusted_publishers))
+    mask_needsreview = (df["publisher_y"] == "Not Signed") & df.apply(lambda row: reputationtool(row, threat_tolerance), axis=1)
 
-   needsreview_df = df[mask_needsreview]
-   approved_df = df[mask_approved]
-   remaining_df = df[~(mask_needsreview | mask_approved)]
+    mask_approved = (
+        ((df["publisher_y"] != "Not Signed") & (~df["publisher_y"].isin(untrusted_publishers))) |
+        ((df["publisher_y"] == "Not Signed") & (~df.apply(lambda row: reputationtool(row, threat_tolerance), axis=1)))
+    )
 
-   return needsreview_df, approved_df, remaining_df
+    needsreview_df = df[mask_needsreview]
+    approved_df = df[mask_approved]
+    remaining_df = df[~(mask_needsreview | mask_approved)]
+
+    return needsreview_df, approved_df, remaining_df