mansipp commented on PR #9347:
URL: https://github.com/apache/hudi/pull/9347#issuecomment-1664649658
Manually tested s3a path using EMR cluster.
```scala
spark-shell \
--conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" \
--conf
"spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog"
\
--conf
"spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension" \
--conf "spark.sql.hive.convertMetastoreParquet=false" \
--jars
/usr/lib/hudi/hudi-aws-bundle-0.13.1-amzn-1-SNAPSHOT.jar,/usr/lib/hudi/hudi-spark3-bundle_2.12-0.13.1-amzn-1-SNAPSHOT.jar
```
```scala
import org.apache.spark.sql.SaveMode
import org.apache.spark.sql.functions._
import org.apache.hudi.DataSourceWriteOptions
import org.apache.hudi.DataSourceReadOptions
import org.apache.hudi.config.HoodieWriteConfig
import org.apache.hudi.hive.MultiPartKeysValueExtractor
import org.apache.hudi.hive.HiveSyncConfig
import org.apache.hudi.sync.common.HoodieSyncConfig
// Create a DataFrame
var tableName = "mansi_s3a_hudi_test"
var tablePath = "s3a://<myBucket>/tables/" + tableName
val inputDF = Seq(
("100", "2015-01-01", "2015-01-01T13:51:39.340396Z"),
("101", "2015-01-01", "2015-01-01T12:14:58.597216Z"),
("102", "2015-01-01", "2015-01-01T13:51:40.417052Z"),
("103", "2015-01-01", "2015-01-01T13:51:40.519832Z"),
("104", "2015-01-02", "2015-01-01T12:15:00.512679Z"),
("105", "2015-01-02", "2015-01-01T13:51:42.248818Z")
).toDF("id", "creation_date", "last_update_time")
//Specify common DataSourceWriteOptions in the single hudiOptions variable
val hudiOptions = Map[String,String](
HoodieWriteConfig.TABLE_NAME -> tableName,
DataSourceWriteOptions.TABLE_TYPE_OPT_KEY -> "COPY_ON_WRITE",
DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY -> "id",
DataSourceWriteOptions.PARTITIONPATH_FIELD_OPT_KEY -> "creation_date",
DataSourceWriteOptions.PRECOMBINE_FIELD_OPT_KEY -> "last_update_time",
DataSourceWriteOptions.HIVE_SYNC_ENABLED_OPT_KEY -> "true",
DataSourceWriteOptions.HIVE_TABLE_OPT_KEY -> tableName,
DataSourceWriteOptions.HIVE_PARTITION_FIELDS_OPT_KEY -> "creation_date",
DataSourceWriteOptions.HIVE_PARTITION_EXTRACTOR_CLASS_OPT_KEY ->
classOf[MultiPartKeysValueExtractor].getName
)
// Write the DataFrame as a Hudi dataset
(inputDF.write
.format("org.apache.hudi")
.option(DataSourceWriteOptions.OPERATION_OPT_KEY,
DataSourceWriteOptions.INSERT_OPERATION_OPT_VAL)
.options(hudiOptions)
.mode(SaveMode.Overwrite)
.save(tablePath))
```
--
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]
