过滤嵌套的JSON结构并获取字段名作为Pyspark中的值

from pyspark.sql import SparkSession
from pyspark.sql.functions import col

spark = SparkSession.builder.appName("Nested JSON Filter").getOrCreate()

data = spark.read.json("data.json")

def filter_nested_json(column, parent_name=""):
    result = []
    for field in column.schema.fields:
        name = parent_name + "." + field.name if parent_name else field.name
        if isinstance(field.dataType, ArrayType):
            result.append(name)
        elif isinstance(field.dataType, StructType):
            result.extend(filter_nested_json(col(name), name))
        else:
            result.append(name)
    return result

filtered_columns = filter_nested_json(data)