基于逻辑的spark df追加新列

需要基于其他列向下面的df添加新列。这是df模式

scala> a.printSchema()
root
 |-- ID: decimal(22,0) (nullable = true)
 |-- NAME: string (nullable = true)
 |-- AMOUNT: double (nullable = true)
 |-- CODE: integer (nullable = true)
 |-- NAME1: string (nullable = true)
 |-- code1: array (nullable = true)
 |    |-- element: integer (containsNull = true)
 |-- revised_code string (nullable = true)

现在我想根据下面的条件添加一个列say标志

 1=> if code == revised_code, than flag is P
 2 => if code != revised code than I  
 3=> if both code and revised_code is null than no flag.

这是我正在尝试的自定义项,但它给出了 I 对于案例1和案例3。

 def tagsUdf =
    udf((code: String, revised_code: String) =>
      if (code == null  && revised_code == null ) ""
      else if (code == revised_code) "P" else "I")


tagsUdf(col("CODE"), col("revised_code"))

有人能指出我犯了什么错吗

I/P DF
+-------------+-------+------------+
|NAME         |   CODE|revised_code|
+-------------+-------+------------+
|       amz   |   null|       null|
|   Watch     |   null|       5812|
|   Watch     |   null|       5812|
|   Watch     |   5812|       5812|
|       amz   |   null|       null|
|   amz       | 9999  |       4352|
+-------------+-------+-----------+
Schema:
root
 |-- MERCHANT_NAME: string (nullable = true)
 |-- CODE: integer (nullable = true)
 |-- revised_mcc: string (nullable = true)

O/P DF    
+-------------+-------+-----------------+
|NAME         |   CODE|revised_code|flag|
+-------------+-------+-----------------+
|   amz       |   null|       null| null|
|   Watch     |   null|       5812|  I  |
|   Watch     |   null|       5812|  I  |
|   Watch     |   5812|       5812|  P  |
|   amz       |   null|       null| null|
|amz          | 9999  |       4352|  I  |
+-------------+-------+-----------------+