ggs production data

src/compare.py

@@ -1,5 +1,8 @@
 import csv
 from Levenshtein import distance
+import pandas as pd
+import uuid
+
 
 # TODO Filter für Spalten, ggfs. Klasse benötigt
 
@@ -42,21 +45,87 @@ def find_similar_pairs(pair, other_data):
     return similar_pairs
 
 
+def create_uuid():
+    return str(uuid.uuid4())
+
+
+def add_hl_tag(row):
+    return 'HL0707104-' + row['klasse']
+
+
+def create_import_list(path, path_new, old_pairs, new_pairs, common_pairs):
+    df = pd.read_csv(path, sep=';', encoding='utf-8')
+    df = df[~df[['name', 'vorname']].apply(tuple, axis=1).isin(old_pairs)]
+    df = df.drop('username', axis=1, errors='ignore')
+    df = df.drop('klasse', axis=1, errors='ignore')
+    # print(len(df))
+    # print(df)
+    new_data = pd.read_csv(path_new, sep=';', encoding='utf-8')
+
+    # Bei Schüler: alte Klassen gelöscht, mit neuen Klassen aus new-data auffüllen
+
+    matches = new_data[~new_data[['name', 'vorname']].apply(tuple, axis=1).isin(new_pairs)]
+    matches.loc[:, 'klasse'] = matches.apply(add_hl_tag, axis=1)
+    # print(len(matches))
+    # print(matches)
+    df = pd.merge(df, matches, how='outer', left_on=['name', 'vorname'], right_on=['name', 'vorname'])
+    df = df[['name', 'vorname', 'klasse', 'schuelerid', 'mailUserQuota', 'oxUserQuota', 'oxContext']]
+    # print(df)
+    print(len(df))
+
+
+    new_data = new_data[~new_data[['name', 'vorname']].apply(tuple, axis=1).isin(common_pairs)]
+    # new_data = new_data.drop('Unnamed: 2', axis=1, errors='ignore')
+    new_uuids = []
+    for row in range(len(new_data)):
+        new_uuids.append(create_uuid())
+    # Klasse?? Unterschied zwischen Lehrer und Schüler
+    #new_data['klasse'] = None
+    new_data.loc[:, 'klasse'] = new_data.apply(add_hl_tag, axis=1)
+    new_data.insert(loc=2, column='schuelerid', value=new_uuids)
+    mailUserQuota = 1024
+    oxUserQuota = 5120
+    oxContext = 16
+    new_data['mailUserQuota'] = mailUserQuota
+    new_data['oxUserQuota'] = oxUserQuota
+    new_data['oxContext'] = oxContext
+    # print(new_data)
+    print(len(new_data))
+
+    # vor dem merge daten ergänzen
+    # import_df = pd.merge(df, new_data, how='outer', left_on=['name', 'vorname', 'mailUserQuota', 'oxUserQuota', 'oxContext'], right_on=['name', 'vorname', 'mailUserQuota', 'oxUserQuota', 'oxContext'])
+    import_df = pd.merge(df, new_data, how='outer', left_on=['name', 'vorname', 'klasse', 'schuelerid', 'mailUserQuota', 'oxUserQuota', 'oxContext'], right_on=['name', 'vorname', 'klasse', 'schuelerid', 'mailUserQuota', 'oxUserQuota', 'oxContext'])
+    # pd.set_option('display.max_rows', None)
+    # pd.set_option('display.max_columns', None)
+    # print(import_df)
+    # print(len(import_df))
+    # pd.reset_option('display.max_rows')
+    # pd.reset_option('display.max_columns')
+    out_path = '../GGS/outputSchueler.csv'
+    import_df.to_csv(out_path, index=False)
+    print(len(import_df))
+    print('Schüler Import Liste erzeugt')
+    print('Testuser manuell nachtragen!!')
+
+
 def main():
     file1_path = '../GGS/ggsSnew.csv'  # Pfad zur ersten CSV-Datei
     file2_path = '../GGS/ggsSold2.cvs'  # Pfad zur zweiten CSV-Datei
+    file3_path = '../GGS/downloadS.csv'
 
-    common_pairs, unique_pairs1, unique_pairs2, data1, data2 = compare_csv(file1_path, file2_path)
+    common_pairs, new_pairs, old_pairs, data1, data2 = compare_csv(file1_path, file2_path)
 
     print(f"Anzahl der übereinstimmenden Paare: {len(common_pairs)}")
-    print(f"Anzahl der neuen Einträge: {len(unique_pairs1)}")
-    print(f"Anzahl der veralteten Einträge: {len(unique_pairs2)}")
+    print(f"Anzahl der neuen Einträge: {len(new_pairs)}")
+    print(f"Anzahl der veralteten Einträge: {len(old_pairs)}")
 
-    for pair in data1:
-        similar_pairs_list2 = find_similar_pairs(pair, set(data2) - {pair})
+    # for pair in data1:
+    #     similar_pairs_list2 = find_similar_pairs(pair, set(data2) - {pair})
+    #
+    #     if similar_pairs_list2:
+    #         print(f"Ähnliche Paare zu {pair} in Liste 2: {similar_pairs_list2}")
 
-        if similar_pairs_list2:
-            print(f"Ähnliche Paare zu {pair} in Liste 2: {similar_pairs_list2}")
+    create_import_list(file3_path, file1_path, old_pairs, new_pairs, common_pairs)
 
 
 if __name__ == "__main__":