使用regex_extract遍历字符串列表Pyspark

from pyspark.sql import SparkSession
from pyspark.sql.functions import expr

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据
data = [("John", ["apple", "banana", "cherry"]),
        ("Alice", ["orange", "grape", "kiwi"]),
        ("Bob", ["melon", "strawberry", "pineapple"])]

df = spark.createDataFrame(data, ["name", "fruits"])

# 使用regex_extract遍历字符串列表
df = df.withColumn("fruit", expr("regex_extract(fruits, '(\\w+)', 1)"))

# 显示结果
df.show(truncate=False)

+-----+------------------+------+
|name |fruits            |fruit |
+-----+------------------+------+
|John |[apple, banana, cherry]|apple |
|Alice|[orange, grape, kiwi]  |orange|
|Bob  |[melon, strawberry, pineapple]|melon |
+-----+------------------+------+