如果要在python/pyspark中获取数组，则跳过数字跟在字符串后面的拆分

def get_array(string):
    result = []
    strings = string.split()
    i = 0
    while i < len(strings):
        if strings[i][0].isdigit():
            i += 2
        else:
            result.append(strings[i])
            i += 1
    return result

# 示例用法
string = "1 apple 2 banana 3 orange"
array = get_array(string)
print(array)  # 输出: ['apple', 'banana', 'orange']

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

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

# 示例数据
data = [("1 apple",), ("2 banana",), ("3 orange",)]
df = spark.createDataFrame(data, ["string"])

# 拆分字符串并获取数组
array_df = df.withColumn("array", split(col("string"), " ")) \
             .selectExpr("filter(array, x -> !substring(x, 0, 1) rlike '\\d+') as array")

# 显示结果
array_df.show(truncate=False)