过滤PySpark中的任何非字母数字

from pyspark.sql import SparkSession
from pyspark.sql.functions import regexp_replace

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

# 创建示例数据
data = [("Hello, World! 123",), ("Spark#PySpark",)]
df = spark.createDataFrame(data, ["text"])

# 使用regexp_replace函数过滤非字母数字
df_filtered = df.withColumn("filtered_text", regexp_replace(df.text, "[^a-zA-Z0-9]", ""))

# 显示过滤后的结果
df_filtered.show(truncate=False)

+-------------------+--------------+
|text               |filtered_text |
+-------------------+--------------+
|Hello, World! 123  |HelloWorld123 |
|Spark#PySpark      |SparkPySpark  |
+-------------------+--------------+