将文本文件加载到Spark上下文时跳过缺少字段的行

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

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

# 定义数据的schema
schema = StructType([
    StructField("field1", StringType(), True),
    StructField("field2", StringType(), True),
    StructField("field3", StringType(), True)
])

# 读取文本文件并应用schema
df = spark.read.csv("path/to/text/file.txt", schema=schema, sep="\t", header=False, mode="DROPMALFORMED")

# 打印DataFrame的内容
df.show()