nsivabalan commented on issue #5869: URL: https://github.com/apache/hudi/issues/5869#issuecomment-1527002010
Not reproducible w/ https://github.com/apache/hudi/pull/8490 ``` import org.apache.spark.sql.SaveMode._ import org.apache.hudi.DataSourceReadOptions._ import org.apache.hudi.DataSourceWriteOptions._ import org.apache.spark.sql.{DataFrame, Row, SparkSession} import scala.collection.mutable val tableName = "hudi5869" val spark = SparkSession.builder.enableHiveSupport.getOrCreate val basePath = "/tmp/hudi5869/" import spark.implicits._ // spark-shell val hudiOptions = mutable.Map( "hoodie.table.name" -> tableName, "hoodie.datasource.write.table.type" -> "MERGE_ON_READ", "hoodie.datasource.write.operation" -> "upsert", "hoodie.datasource.write.recordkey.field" -> "id", "hoodie.datasource.write.precombine.field" -> "last_update_time", "hoodie.datasource.write.partitionpath.field" -> "creation_date", "hoodie.index.type" -> "GLOBAL_BLOOM", "hoodie.bloom.index.update.partition.path" -> "true", "hoodie.compact.inline" -> "true", "hoodie.datasource.write.keygenerator.class" -> "org.apache.hudi.keygen.ComplexKeyGenerator" ) val df = Seq( ("100", "2015-01-01", "1","a"), ("101", "2015-01-01", "1","a") ).toDF("id", "creation_date", "last_update_time", "new_col") df.write.format("hudi"). options(hudiOptions). mode(Append). save(basePath) spark.read.format("hudi").load(basePath).show(false) val df1 = Seq( ("100", "2015-01-02", "2","b"), ("101", "2015-01-01", "2","b") ).toDF("id", "creation_date", "last_update_time", "new_col") df1.write.format("hudi"). options(hudiOptions). mode(Append). save(basePath) spark.read.format("hudi").load(basePath).show(false) ``` Output: ``` scala> spark.read.format("hudi").load(basePath).show(false) +-------------------+---------------------+------------------+----------------------+---------------------------------------------------------------------------+---+-------------+----------------+-------+ |_hoodie_commit_time|_hoodie_commit_seqno |_hoodie_record_key|_hoodie_partition_path|_hoodie_file_name |id |creation_date|last_update_time|new_col| +-------------------+---------------------+------------------+----------------------+---------------------------------------------------------------------------+---+-------------+----------------+-------+ |20230427220827516 |20230427220827516_0_1|id:101 |2015-01-01 |f183954a-9d23-4192-a1ed-8efc25e4e77f-0 |101|2015-01-01 |2 |b | |20230427220827516 |20230427220827516_1_0|id:100 |2015-01-02 |b395a368-8e9a-46c8-8660-c78cfd53d06f-0_1-275-1770_20230427220827516.parquet|100|2015-01-02 |2 |b | +-------------------+---------------------+------------------+----------------------+---------------------------------------------------------------------------+---+-------------+----------------+-------+ ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org