create_table.scala

import org.apache.spark.sql.SaveMode._

val basePath = "/tmp/hudi/stocks"
val stocksDF1 = spark.read.json("docker/demo/data/batch_1.json")
val stocksDF2 = spark.read.option("multiline", "true").json("docker/demo/data/batch_2.json").limit(1)

stocksDF1.write.format("hudi").
  option("hoodie.datasource.write.recordkey.field", "symbol").
  option("hoodie.datasource.write.partitionpath.field", "date").
  option("hoodie.datasource.write.precombine.field", "ts").
  option("hoodie.table.name", "stocks").
  mode(Overwrite).
  save(basePath)

stocksDF2.write.format("hudi").
  option("hoodie.datasource.write.recordkey.field", "symbol").
  option("hoodie.datasource.write.partitionpath.field", "date").
  option("hoodie.datasource.write.precombine.field", "ts").
  mode(Append).
  save(basePath)