optimize and clean up

app/app.py

@@ -302,27 +302,24 @@ def get_merged_df(table_name):
         for i, row in result.iterrows():
             if (pd.isna(row.get('norm_email')) or row.get('norm_email') == '') and pd.notna(row.get('E-Mail-Adresse')):
                 result.at[i, 'norm_email'] = f"{row.get('E-Mail-Adresse')}".strip()
-                
-        # only keep required columns
-        result = result[[
-            'norm_name', 'norm_date', 'norm_email', 'norm_amount','norm_currency', 'norm_zweck'
-        ]]
         
-        # rename columns to match CAMT format
+        # rename columns
         result = result.rename(columns={
             'norm_name': 'name',
             'norm_date': 'booking_date',
-            'norm_email': 'E-Mail',
+            'norm_email': 'email',
             'norm_amount': 'amount',
             'norm_currency': 'currency',
-            'norm_zweck': 'remittance'
+            'norm_zweck': 'reference'
         })
         
-        # copy booking_date to value_date
+        # add sign column based on amount
-        result['value_date'] = result['booking_date']
+        result['sign'] = result['amount'].apply(lambda x: 'CRDT' if x >= 0 else 'DBIT')
         
-
+        # sort columns
-        result['credit_debit'] = result['amount'].apply(lambda x: 'CRDT' if x >= 0 else 'DBIT')        
+        result = result[[
+            'booking_date', 'name', 'email', 'amount', 'currency', 'sign', 'reference'
+        ]]
         
     else:
         raise ValueError(f"Unknown table_name '{table_name}'")
@@ -486,11 +483,10 @@ def generate_mt940(df: pd.DataFrame,
     df : pd.DataFrame
       Columns required:
         - 'booking_date' (datetime or str YYYY-MM-DD)
-        - 'value_date'   (datetime or str YYYY-MM-DD)
         - 'amount'       (float)
         - 'currency'     (str, e.g. 'EUR')
-        - 'credit_debit' (str, 'CRDT' or 'DBIT')
+        - 'sign'         (str, 'CRDT' or 'DBIT')
-        - 'remittance'   (str, used inside your info_prefix section)
+        - 'reference'    (str, used inside your info_prefix section)
         - 'name'         (str, appended after “?32” in tag 86)
     account_iban : str
       Goes into tag 25 exactly as you want it (e.g. "11223344/55667788").
@@ -507,8 +503,8 @@ def generate_mt940(df: pd.DataFrame,
       The literal reference after that code (default "NONREF")
     info_prefix : str, optional
       If you set e.g. "169?00RAISENOW??20", your tag 86 lines become
-        169?00RAISENOW??20<remittance> ?32<name>
+        169?00RAISENOW??20<reference> ?32<name>
-      If you leave it `None`, we fall back to a simple `<name> <remittance>` join.
+      If you leave it `None`, we fall back to a simple `<name> <reference>` join.
 
     Returns
     -------
@@ -516,9 +512,8 @@ def generate_mt940(df: pd.DataFrame,
     """
     # normalize & sort
     df2 = df.copy()
-    df2['value_date']   = pd.to_datetime(df2['value_date'])
     df2['booking_date'] = pd.to_datetime(df2['booking_date'])
-    df2.sort_values('value_date', inplace=True)
+    df2.sort_values('booking_date', inplace=True)
 
     # constant currency
     currency = df2['currency'].iat[0]
@@ -533,7 +528,7 @@ def generate_mt940(df: pd.DataFrame,
         lines.append(f":28C:{statement_number}")
 
     # opening balance
-    first_dt = df2['value_date'].iat[0]
+    first_dt = df2['booking_date'].iat[0]
     ob_sign = 'C' if opening_balance >= 0 else 'D'
     ob_amt  = abs(opening_balance)
     ob_str  = f"{ob_amt:.2f}".replace('.', ',')
@@ -541,44 +536,43 @@ def generate_mt940(df: pd.DataFrame,
 
     # transactions
     for _, row in df2.iterrows():
-        vd = row['value_date']
         bd = row['booking_date']
-        sign = 'C' if row['credit_debit']=='CRDT' else 'D'
+        sign = 'C' if row['sign']=='CRDT' else 'D'
         amt = abs(row['amount'])
         amt_str = f"{amt:.2f}".replace('.', ',')
 
         # :61:YYMMDDMMDD[C|D]amount<txn_code><txn_ref>
         lines.append(
-            f":61:{vd.strftime('%y%m%d')}"
+            f":61:{bd.strftime('%y%m%d')}"
             f"{bd.strftime('%m%d')}"
             f"{sign}{amt_str}"
             f"{txn_code}{txn_ref}"
         )
 
         # :86: either structured or simple fallback
-        raw_rem  = row.get('remittance', '')
+        raw_rem  = row.get('reference', '')
         raw_name = row.get('name', '')
         rem  = '' if pd.isna(raw_rem) else str(raw_rem)
         name = '' if pd.isna(raw_name) else str(raw_name)
 
         if info_prefix:
-            # your “169?00RAISENOW??20<remittance> ?32<name>”
+            # your “169?00RAISENOW??20<reference> ?32<name>”
             lines.append(f":86:{info_prefix}{rem} ?32{name}")
         else:
-            # old-style "<name> <remittance>"
+            # old-style "<name> <reference>"
             info = " ".join(filter(None, [name, rem]))
             lines.append(f":86:{info}")
 
     # closing balance
     net_mv = sum(
-        row['amount'] if row['credit_debit']=='CRDT' else -row['amount']
+        row['amount'] if row['sign']=='CRDT' else -row['amount']
         for _, row in df2.iterrows()
     )
     closing = opening_balance + net_mv
     cb_sign = 'C' if closing >= 0 else 'D'
     cb_amt  = abs(closing)
     cb_str  = f"{cb_amt:.2f}".replace('.', ',')
-    last_dt = df2['value_date'].iat[-1]
+    last_dt = df2['booking_date'].iat[-1]
     lines.append(f":62F:{cb_sign}{last_dt.strftime('%y%m%d')}{currency}{cb_str}")
     
     file_str = "\r\n".join(lines)