Finished refactoring options 9 and 10

scripts/lantern.py

@@ -561,9 +561,12 @@ Maintenance:
                         
                         participant_url = generate_local_participant_dir(participant.URL)
 
-                        print_colors('[+] Reading webrring participant\'s verified and unverified, and removing unverified and blacklisted rows')
+                        print_colors('[+] Reading webrring participant\'s verified and unverified')
-                        participant_verified_df = lantern.clean_csv(pd.read_csv(f'{participant_url}verified.csv'), local_blacklist)
+                        participant_verified_df, participant_unverified_df = get_participant_local_verified_and_unverified(participant_url)
-                        participant_unverified_df = lantern.clean_csv(pd.read_csv(f'{participant_url}unverified.csv'), local_blacklist)
+
+                        print_colors('[+] Removing unvalidated and blacklisted rows')
+                        participant_verified_df = lantern.clean_csv(participant_verified_df, local_blacklist)
+                        participant_unverified_df = lantern.clean_csv(participant_unverified_df, local_blacklist)
 
                         print_colors('[+] Marking sensitive rows')
                         participant_verified_df = lantern.mark_sensitive(participant_verified_df, local_sensitive)
@@ -585,7 +588,6 @@ Maintenance:
 
                 except Exception as err:
                     print_colors("[-] Option 4 failed suddently, please try again", is_error=True)
-                    raise err
 
                 break
 
@@ -1006,10 +1008,13 @@ Maintenance:
                 
                 try:
                     
+                    print_colors('[+] Reading local verified and unverified')
                     verified_df, unverified_df = get_local_verified_and_unverified()
 
+                    print_colors('[+] Removing cross dataframe replications')
                     verified_df, unverified_df = remove_cross_dataframe_replications(verified_df, unverified_df)
 
+                    print_colors('[+] Saving local verified and unverified')
                     save_local_verified_and_unverified(verified_df, unverified_df)
 
                 except Exception as err:
@@ -1020,80 +1025,30 @@ Maintenance:
             case 10:
                 print_colors("[+] 10) perform sanity checks on all csv files (to mark them as sensitive / or remove the ones that are blacklisted)")
 
-
+                try:
-
                     print_colors('[+] Reading local blacklist and sensitive words')
                     local_blacklist, local_sensitive = get_local_blacklist_and_sensitive()
 
+                    for participant in os.listdir(conf.PARTICIPANT_DIR):
+                        participant_local_dir = conf.PARTICIPANT_DIR + participant + '/'
 
+                        print_colors('[+] Reading webrring participant\'s verified and unverified')
+                        participant_verified_df, participant_unverified_df = get_participant_local_verified_and_unverified(participant_local_dir)
 
-                participantspath = rootpath+'www/participants/'
+                        print_colors('[+] Removing unverified and blacklisted rows')
-                for participant in os.listdir(participantspath):
+                        participant_verified_df = lantern.clean_csv(participant_verified_df, local_blacklist)
-                    print_colors(f"Participant: {participant}")
+                        participant_unverified_df = lantern.clean_csv(participant_unverified_df, local_blacklist)
-                    #read=input("Continue?")
-                    participantdir= participantspath+participant
-                    ################ BEGIN SANITY CHECKS FOR EACH PARTICIPANTS ##############
-                    # iterate through the participant's verified.csv and unverified.csv files
-                    for w in ['verified.csv','unverified.csv']:
-                        csvfilepath=participantdir+'/'+w
-                        print_colors(f"{csvfilepath}")
-                        csvdf = pd.read_csv(csvfilepath, on_bad_lines='skip')
-                        rows2delete= [] # it is an empty list at first
-                        for i,j in csvdf.iterrows():
-                            row=csvdf.loc[i,:].values.tolist()
-                            #print_colors(f"{row}")
                         
+                        print_colors('[+] Marking sensitive rows')
+                        participant_verified_df = lantern.mark_sensitive(participant_verified_df, local_sensitive)
+                        participant_unverified_df = lantern.mark_sensitive(participant_unverified_df, local_sensitive)
 
+                        print_colors('[+] Saving local participant verified and unverified')
+                        save_local_participant_verified_and_unverified(participant_verified_df, participant_unverified_df, participant_local_dir)
                 
-                            ################################ SANITY CHECKS ####################################
+                except Exception as err:
-							### SANITY CHECK 0: make sure that ✔️ and x are replaced with YES/NO, as it changed since v1.0.1 ###
+                    print_colors("[-] Option 10 failed suddently, please try again", is_error=True)
-                            if  csvdf.at[i, 'Status'] == "✔️" or csvdf.at[i, 'Status'] == "YES" :
-                                csvdf.at[i, 'Status'] = "YES" 
-                                csvdf.to_csv(csvfilepath, index=False)
-                            else:
-                                csvdf.at[i, 'Status'] = "NO" 
-                                csvdf.to_csv(csvfilepath, index=False)
 
-                            if  csvdf.at[i, 'Sensitive'] == "✔️" or csvdf.at[i, 'Sensitive'] == "YES" :
-                                csvdf.at[i, 'Sensitive'] = "YES" 
-                                csvdf.to_csv(csvfilepath, index=False)
-                            else:
-                                csvdf.at[i, 'Sensitive'] = "NO" 
-                                csvdf.to_csv(csvfilepath, index=False)
-							
-                            ### SANITY CHECK 1: Mark all the rows that have incorrect formatting for deletion###
-                            if IsURLValid(csvdf.at[i, 'Instance']) is False or IsCategoryValid(csvdf.at[i, 'Category']) is False or IsNameValid(csvdf.at[i, 'Name']) is False or IsURLValid(csvdf.at[i, 'URL']) is False or IsStatusValid(csvdf.at[i, 'Sensitive']) is False or  IsDescriptionValid(csvdf.at[i, 'Description']) is False or  IsStatusValid(csvdf.at[i, 'Status']) is False or  IsScoreValid(csvdf.at[i, 'Score']) is False:
-                                if i not in rows2delete:
-                                    print_colors(f"Marking row {i} for deletion, as it has invalid inputs")
-                                    #print_colors(f"{row}")
-                                    print(IsURLValid(csvdf.at[i, 'Instance']), IsCategoryValid(csvdf.at[i, 'Category']), IsNameValid(csvdf.at[i, 'Name']), IsURLValid(csvdf.at[i, 'URL']), IsStatusValid(csvdf.at[i, 'Sensitive']), IsDescriptionValid(csvdf.at[i, 'Description']), IsStatusValid(csvdf.at[i, 'Status']),  IsScoreValid(csvdf.at[i, 'Score']))
-                                    rows2delete.append(i)
-                                    read=input("Continue?")
-
-                            ### SANITY CHECK 2: Mark all rows that are not allowed (blacklist) for deletion ###
-                            for k,l in bldf.iterrows():
-                                blword=bldf.at[k, 'blacklisted-words']
-                                if any(blword in str(x) for x in row) == True:
-                                    if i not in rows2delete:
-                                        print_colors(f"Marking row {i} for deletion, as it matches with the blacklisted word {blword}")
-                                        rows2delete.append(i)
-                                        #read=input("Continue?")
-                            ### SANITY CHECK 3: Mark all rows that match sensitive words to be sensitive = YES
-                            for k,l in sedf.iterrows():
-                                seword=sedf.at[k, 'sensitive-words']
-                                if any(seword in str(x) for x in row) == True:
-                                    print_colors(f"Marking row {i} as sensitive, as it matches with the sensitive word {seword}")
-                                    csvdf.at[i, 'Sensitive']="YES"
-                                    csvdf.to_csv(csvfilepath, index=False)
-                                    #read=input("Continue?")
-
-
-                        for i in rows2delete:
-                            row=csvdf.loc[i,:].values.tolist()
-                            print_colors(f'[+] REMOVING ROW : {i} {row}')
-                            csvdf.drop(i, inplace= True)
-                            csvdf.to_csv(csvfilepath, index=False)
-                            #read=input("Continue?")
                 break
             
             case 11:

scripts/utils.py

@@ -60,7 +60,7 @@ def IsXFTPServerValid(url: str) -> bool:
     Returns True if URL is a valid SimpleX XFTP Server URL
     False otherwise
     """
-    return conf.RecognizeSimplexType(url) == 'xftp'
+    return RecognizeSimplexType(url) == 'xftp'
 
 # stub function
 def IsSMPServerValid(url: str) -> bool:
@@ -68,7 +68,7 @@ def IsSMPServerValid(url: str) -> bool:
     Returns True if URL is a valid SimpleX SMP Server URL
     False otherwise
     """
-    return conf.RecognizeSimplexType(url) == 'smp'
+    return RecognizeSimplexType(url) == 'smp'
 
 def IsClearnetLinkValid(url: str) -> bool:
     """
@@ -242,7 +242,7 @@ def IsNameValid(name: str) -> bool:
     Check the parameter name only contains [a-zA-Z0-9] and is 64 chars long.
     """
     try:
-        return bool(VALID_NAME_PATTERN.fullmatch(name.strip()))
+        return bool(conf.VALID_NAME_PATTERN.fullmatch(name.strip()))
     except Exception:
         return False
 
@@ -278,10 +278,10 @@ def is_row_valid(row):
     """
     try:
         return (
-            IsUrlValid(row['Instance']) and 
+            IsURLValid(row['Instance']) and 
             IsCategoryValid(row['Category']) and 
             IsNameValid(row['Name']) and 
-            IsUrlValid(row['URL']) and 
+            IsURLValid(row['URL']) and 
             IsStatusValid(row['Sensitive']) and  
             IsDescriptionValid(row['Description']) and 
             IsStatusValid(row['Status']) and 
@@ -339,6 +339,17 @@ def remove_duplications(df):
     return df
 
 def remove_cross_dataframe_replications(main_df, sub_df):
+    """
+    remove replications from sub_df that exist in main_df
+
+    Parameters:
+        main_df (Dataframe): the dataframe to keep replications
+        sub_df (Dataframe): the dataframe to remove replications
+
+    Returns:
+        Dataframe: the main_df with removed duplications
+        Dataframe: the sub_df with removed duplications and removed replications
+    """
     try:
 
         main_df = remove_duplications(main_df)
@@ -350,7 +361,6 @@ def remove_cross_dataframe_replications(main_df, sub_df):
 
     except Exception as err:
         print_colors('[-] Removing cross dataframe duplications failed',is_error=True)
-        raise err #REMOVE!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
 
 
     return main_df, sub_df
@@ -365,7 +375,7 @@ def save_local_verified_and_unverified(verified_df, unverified_df):
         unverified_df (Dataframe): local unverified rows dataframe
 
     Returns:
-        Dataframe: the combined dataframe will be returned
+        bool: True if successful, False if not
     """
     try:
         current_instance = get_current_instance() + '/'
@@ -382,6 +392,32 @@ def save_local_verified_and_unverified(verified_df, unverified_df):
         print_colors('[-] Saving verified and unverified failed',is_error=True)
         return False
 
+def save_local_participant_verified_and_unverified(verified_df, unverified_df, participant):
+    """
+    saves the local verified and unverified of a participant
+
+    Parameters:
+        verified_df (Dataframe): local verified rows dataframe
+        unverified_df (Dataframe): local unverified rows dataframe
+        participant (str): participant's onion local path
+
+    Returns:
+        bool: True if successful, False if not
+    """
+    try:
+
+        verified_df.to_csv(f'{participant}verified.csv', index=False)
+
+        unverified_df.to_csv(f'{participant}unverified.csv', index=False)
+
+        print_colors('[+] Verified and unverified saved successfully')
+
+        return True 
+    
+    except Exception as err:
+        print_colors('[-] Saving verified and unverified failed',is_error=True)
+        return False
+
 ###################### Getters/Generators ######################
 def generate_participant_url(participant):
     """
@@ -414,33 +450,29 @@ def get_participant_local_verified_and_unverified(participant):
     reads the local verified csv and the local unverified csv of a participant
 
     Parameters:
-        participant (str): participant's onion address/instance
+        participant (str): participant's local files path
 
     Returns:
         verified_df(Dataframe): verified.csv as dataframe
         unverified_df(Dataframe): unverified.csv as dataframe
     """
     
-    try:
-        current_instance = get_current_instance() + '/'
     try:
         verified_df = pd.read_csv(f'{participant}verified.csv')
     
     except FileNotFoundError:
         print_colors("[-] File not found: verified.csv", is_error=True)
+        return pd.Dataframe(), pd.Dataframe()
 
     try:
         unverified_df = pd.read_csv(f'{participant}unverified.csv')
 
     except FileNotFoundError:
         print_colors("[-] Participant File not found: unverified.csv", is_error=True)
+        return pd.Dataframe(), pd.Dataframe()
 
     return verified_df, unverified_df
 
-    except Exception as err:
-        print_colors('[-] Failed reading the verified and unverified files',is_error=True)
-
-    return pd.DataFrame(), pd.DataFrame()
 
 def get_official_participants():
     """