检查以下代码。

scala> val df = Seq("A","AA","BB","AAAA","ABA","AAAAA","BAB").toDF("Class")
df: org.apache.spark.sql.DataFrame = [Class: string]

scala> df.filter(!col("Class").rlike("[^A]+")).show
+-----+
|Class|
+-----+
|    A|
|   AA|
| AAAA|
|AAAAA|
+-----+

尝试使用rlike函数

val data1 =
      """
        |Class
        |A
        |AA
        |BB
        |AAAA
        |ABA
        |AAAAA
      """.stripMargin
    val stringDS1 = data1.split(System.lineSeparator())
      .map(_.split("\\|").map(_.replaceAll("""^[ \t]+|[ \t]+$""", "")).mkString(","))
      .toSeq.toDS()
    val df1 = spark.read
      .option("sep", ",")
      .option("inferSchema", "true")
      .option("header", "true")
      .option("nullValue", "null")
      .csv(stringDS1)
    df1.show(false)
    df1.printSchema()

    /**
      * +-----+
      * |Class|
      * +-----+
      * |A    |
      * |AA   |
      * |BB   |
      * |AAAA |
      * |ABA  |
      * |AAAAA|
      * +-----+
      *
      * root
      * |-- Class: string (nullable = true)
      */

    df1.filter(col("Class").rlike("""^A+$"""))
      .show(false)

    /**
      * +-----+
      * |Class|
      * +-----+
      * |A    |
      * |AA   |
      * |AAAA |
      * |AAAAA|
      * +-----+
      */