从Spark作业读取Impala表和列名

import org.apache.spark.sql.SparkSession

val spark = SparkSession.builder()
  .appName("Read from Impala")
  .config("spark.sql.catalogImplementation", "hive")
  .config("spark.sql.warehouse.dir", "hdfs://<your_hdfs_path>")
  .config("spark.sql.hive.metastore.version", "3.1.2")
  .config("spark.sql.hive.metastore.jars", "<path_to_hive_jars>")
  .getOrCreate()

val df = spark.read
  .format("jdbc")
  .option("url", "jdbc:impala://<impala_host>:<impala_port>/<database>")
  .option("dbtable", "<table_name>")
  .option("user", "<username>")
  .option("password", "<password>")
  .load()

df.show()  // 显示DataFrame的内容
df.printSchema()  // 打印DataFrame的模式（列名和数据类型）

val columnNames = df.columns