对于spark版本>=2.4.0，这可以使用内置函数完成 array_repeat , transform 以及 substring .

import org.apache.spark.sql.functions.{array_repeat, transform, substring}

//Repeat the array `n` times
val repeated_df = df.withColumn("tmp",array_repeat($"text",length($"text")-3+1))
//Get the slices with transform higher order function
val res = repeated_df.withColumn("str_slices",
                                 expr("transform(tmp,(x,i) -> substring(x from i+1 for 3))")
                                )
//res.show()
+---+-----+---------------------+---------------+
|id |text |tmp                  |str_slices     |
+---+-----+---------------------+---------------+
|0  |hello|[hello, hello, hello]|[hel, ell, llo]|
|1  |hola |[hola, hola]         |[hol, ola]     |
+---+-----+---------------------+---------------+