Added Publisher Push

utils/hashfunctions.py

@@ -367,6 +367,9 @@ def generatePreflights(first_policy, second_policy):
     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)
 
+    publishers = tryToReadCSV(f"approved\\publishers_{first_policy}_{second_policy}.csv")
+    publishers.to_parquet(f"parquet\\publishers_{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)
@@ -375,9 +378,25 @@ def generatePreflights(first_policy, second_policy):
     
     ct.style_dataframe_dark(allowbyhash, 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")
-   
+    ct.style_dataframe_dark(publishers, f"preflight\\publishers_{first_policy}_{second_policy}.html")
+
     del allowbyhash
     del pathexclusions
     gc.collect()
 
+def generatePublist(first_policy,second_policy,bad_publisher_list):
+    
+    try:
+         publist = pd.read_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet", columns=['publisher'])
+    except Exception as e:
+        print(f"Error reading parquet file: {e}")
+        publist = pd.DataFrame()  
+
+    #Drop all not signed, only keep unique values
+    publist = publist[publist['publisher'] != "Not Signed"].drop_duplicates(subset='publisher')
+    #Remove Bad publisher if somehow they made it this far
+    pattern = pathf.regulator(bad_publisher_list)
+    publist = publist[~publist["publisher"].str.contains(pattern, na=False)]
+
+    publist.to_csv(f"needs_approved\\publishers_{first_policy}_{second_policy}.csv", index=False)