PySpark如果不存在，则在嵌套字段中添加新对象

from pyspark.sql import SparkSession
from pyspark.sql.types import StructType, StructField, StringType, IntegerType

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

# 定义嵌套字段的结构
schema = StructType([
    StructField("name", StringType(), True),
    StructField("age", IntegerType(), True),
    StructField("address", StructType([
        StructField("street", StringType(), True),
        StructField("city", StringType(), True),
        StructField("state", StringType(), True)
    ]), True)
])

# 创建一个空的DataFrame
df = spark.createDataFrame([], schema)

# 添加新对象到嵌套字段中
new_object = {
    "name": "John",
    "age": 30,
    "address": {
        "street": "123 Main St",
        "city": "New York",
        "state": "NY"
    }
}
df = df.append(new_object, ignore_index=True)

# 显示DataFrame内容
df.show()