AakashPradeep edited a comment on pull request #1580: URL: https://github.com/apache/incubator-hudi/pull/1580#issuecomment-623205984
Now it checks for the existing table name with delete and upsert opertions when Append is the SaveMode. exceptions --- scala> df.write.format("hudi"). | options(getQuickstartWriteConfigs). | option(PRECOMBINE_FIELD_OPT_KEY, "ts"). | option(RECORDKEY_FIELD_OPT_KEY, "uuid"). | option(PARTITIONPATH_FIELD_OPT_KEY, "partitionpath"). | option(TABLE_NAME, "foo_table"). | mode(Append). | save(basePath) org.apache.hudi.exception.HoodieException: hoodie table with name hudi_trips_cow already exist at file:/tmp/hudi_trips_cow at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:89) at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:108) at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45) at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70) at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68) at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676) at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73) at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676) at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229) ... 68 elided scala> df.write.format("hudi"). | options(getQuickstartWriteConfigs). | option(OPERATION_OPT_KEY,"delete"). | option(PRECOMBINE_FIELD_OPT_KEY, "ts"). | option(RECORDKEY_FIELD_OPT_KEY, "uuid"). | option(PARTITIONPATH_FIELD_OPT_KEY, "partitionpath"). | option(TABLE_NAME, tableName). | mode(Append). | save(basePath) scala> df.write.format("hudi"). | options(getQuickstartWriteConfigs). | option(OPERATION_OPT_KEY,"delete"). | option(PRECOMBINE_FIELD_OPT_KEY, "ts"). | option(RECORDKEY_FIELD_OPT_KEY, "uuid"). | option(PARTITIONPATH_FIELD_OPT_KEY, "partitionpath"). | option(TABLE_NAME, "foo_table"). | mode(Append). | save(basePath) org.apache.hudi.exception.HoodieException: hoodie table with name hudi_trips_cow already exist at file:/tmp/hudi_trips_cow at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:89) at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:108) at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45) at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70) at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68) at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676) at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73) at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676) at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229) ... 69 elided and work for valid table name ------------- scala> df.write.format("hudi"). | options(getQuickstartWriteConfigs). | option(PRECOMBINE_FIELD_OPT_KEY, "ts"). | option(RECORDKEY_FIELD_OPT_KEY, "uuid"). | option(PARTITIONPATH_FIELD_OPT_KEY, "partitionpath"). | option(TABLE_NAME, tableName). | mode(Append). | save(basePath) scala> ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org