如何在不循环每个条件的情况下在Spark中级联未知数量的条件

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

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

# 假设这是你的原始DataFrame
data = [("Alice", 1), ("Bob", 2), ("Cathy", 3)]
columns = ["Name", "Value"]
df = spark.createDataFrame(data, columns)

# 这是你动态获取的条件列表
conditions = ["Value > 1", "Value < 3"]

# 使用expr函数构建SQL表达式
sql_expression = " AND ".join(conditions)

# 应用条件过滤DataFrame
filtered_df = df.filter(expr(sql_expression))

# 显示结果
filtered_df.show()

import re

# 简单的正则表达式来检查条件格式
condition_pattern = re.compile(r"^[a-zA-Z_][a-zA-Z0-9_]*\s*[=<>!]{1,2}\s*[a-zA-Z0-9_, ]+$")

for condition in conditions:
    if not condition_pattern.match(condition):
        raise ValueError(f"Invalid condition: {condition}")