使用Spark从HDFS到Oracle BLOB的CSV文件

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.functions._

val spark = SparkSession.builder()
  .appName("HDFS to Oracle BLOB")
  .config("spark.master", "local")
  .getOrCreate()

val csvFile = "hdfs://path/to/csv/file.csv"
val df = spark.read.format("csv")
  .option("header", "true")
  .option("inferSchema", "true")
  .load(csvFile)

val oracleUrl = "jdbc:oracle:thin:@//hostname:port/service"
val tableName = "your_table_name"
val blobColumnName = "your_blob_column_name"

df.write.format("jdbc")
  .option("url", oracleUrl)
  .option("dbtable", tableName)
  .option("user", "your_username")
  .option("password", "your_password")
  .option("driver", "oracle.jdbc.driver.OracleDriver")
  .option("batchsize", "1000")
  .option("truncate", "true")
  .option("fetchsize", "1000")
  .option("createTableColumnTypes", s"$blobColumnName BLOB")
  .mode("append")
  .save()