Pyspark :如何根据另一列中的匹配值从数组中的第一个匹配值开始挑选值，直到最后一个值

from pyspark.sql import SparkSession
from pyspark.sql.functions import array_position, slice, col

# 初始化SparkSession
spark = SparkSession.builder.appName("example").getOrCreate()

# 创建示例数据
data = [
    (1, ["apple", "banana", "cherry"], "banana"),
    (2, ["dog", "cat", "elephant"], "cat"),
    (3, ["red", "green", "blue"], "yellow")
]

# 创建DataFrame
df = spark.createDataFrame(data, ["id", "array_col", "match_value"])

# 找到匹配值在数组中的位置
df = df.withColumn("match_index", array_position(col("array_col"), col("match_value")))

# 提取从第一个匹配值开始到数组末尾的部分
df = df.withColumn("result", slice(col("array_col"), col("match_index"), len(col("array_col")) - col("match_index") + 1))

# 显示结果
df.select("id", "array_col", "match_value", "result").show(truncate=False)

+---+------------------+-----------+------------------+
|id |array_col         |match_value|result            |
+---+------------------+-----------+------------------+
|1  |[apple, banana, cherry]|banana     |[banana, cherry]  |
|2  |[dog, cat, elephant]|cat        |[cat, elephant]   |
|3  |[red, green, blue]  |yellow     |[]                |
+---+------------------+-----------+------------------+