ad1happy2go commented on issue #9141:
URL: https://github.com/apache/hudi/issues/9141#issuecomment-1628840809
Tried this and it is working good. Can you try it?
```
import org.apache.hudi.QuickstartUtils
import org.apache.hudi.common.model.HoodieAvroPayload
import org.apache.hudi.common.model.WriteOperationType
import org.apache.hudi.config.HoodieWriteConfig
import org.apache.hudi.keygen.constant.KeyGeneratorOptions
import org.apache.spark.SparkConf
import org.apache.spark.api.java.JavaSparkContext
import org.apache.spark.api.java.function.Function
import org.apache.spark.sql.Dataset
import org.apache.spark.sql.Row
import org.apache.spark.sql.SparkSession
import java.util
import org.apache.hudi.config.HoodieWriteConfig.TBL_NAME
import org.apache.spark.sql.SaveMode.Append
import org.apache.spark.sql.SaveMode.Overwrite
import org.apache.hudi.DataSourceWriteOptions
val snapshotDf = spark.read.parquet("<Parquet Path>")
snapshotDf.registerTempTable("snapshot");
val snapshotDf2 = spark.sql("select * from snapshot where invoiceid is not
null and invoiceid !='' ")
val snapshotDf3 = snapshotDf2.withColumn("hash",
lit(col("invoiceid").hashCode() %10) )
snapshotDf3.write.format("hudi").options(QuickstartUtils.getQuickstartWriteConfigs())
.option(DataSourceWriteOptions.PRECOMBINE_FIELD_OPT_KEY, "orderdate")
.option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY, "invoiceid")
.option(DataSourceWriteOptions.PARTITIONPATH_FIELD_OPT_KEY, "hash")
.option(TBL_NAME.key(), "GE11")
.mode(Overwrite)
.save("file:///tmp/issue_9141");
```
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
