rangareddy commented on issue #12068:
URL: https://github.com/apache/hudi/issues/12068#issuecomment-2404182429
I have tested the following sample code and worked without any issues.
**Cluster Details:**
* Spark 3.5
* Hudi 1.0.0-beta2
```sh
spark-shell \
--jars
packaging/hudi-spark-bundle/target/hudi-spark3.5-bundle_2.12-1.0.0-beta2.jar \
--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.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar' \
--conf spark.ui.port=14040
```
```scala
import scala.collection.JavaConversions._
import org.apache.spark.sql.SaveMode._
import org.apache.hudi.DataSourceReadOptions._
import org.apache.hudi.DataSourceWriteOptions
import org.apache.hudi.DataSourceWriteOptions._
import org.apache.hudi.common.table.HoodieTableConfig._
import org.apache.hudi.config.HoodieWriteConfig
import org.apache.hudi.config.HoodieWriteConfig._
import org.apache.hudi.keygen.constant.KeyGeneratorOptions._
import org.apache.hudi.common.model.HoodieRecord
import org.apache.hudi.common.table.HoodieTableConfig
import org.apache.hudi.config.HoodieIndexConfig
import org.apache.hudi.common.config.HoodieStorageConfig
import org.apache.hudi.common.config.HoodieMetadataConfig
import org.apache.hudi.execution.bulkinsert.BulkInsertSortMode
import spark.implicits._
val columns = Seq("ts","uuid","rider","driver","fare","city")
val data =
Seq((1695159649087L,"334e26e9-8355-45cc-97c6-c31daf0df330","rider-A","driver-K",19.10,"san_francisco"),
(1695091554788L,"e96c4396-3fad-413a-a942-4cb36106d721","rider-C","driver-M",27.70
,"san_francisco"),
(1695046462179L,"9909a8b1-2d15-4d3d-8ec9-efc48c536a00","rider-D","driver-L",33.90
,"san_francisco"),
(1695516137016L,"e3cf430c-889d-4015-bc98-59bdce1e530c","rider-F","driver-P",34.15,"sao_paulo"
),
(1695115999911L,"c8abbe79-8d89-47ea-b4ce-4d224bae5bfa","rider-J","driver-T",17.85,"chennai"));
var inserts = spark.createDataFrame(data).toDF(columns:_*)
val tableName = "trips_table"
val basePath = "file:///tmp/trips_table"
val bulkWriteOptions: Map[String, String] = Map(
DataSourceWriteOptions.OPERATION.key() ->
DataSourceWriteOptions.BULK_INSERT_OPERATION_OPT_VAL,
DataSourceWriteOptions.TABLE_TYPE.key() ->
DataSourceWriteOptions.COW_TABLE_TYPE_OPT_VAL,
HoodieStorageConfig.PARQUET_COMPRESSION_CODEC_NAME.key() -> "snappy",
HoodieStorageConfig.PARQUET_MAX_FILE_SIZE.key() -> "2147483648",
"hoodie.parquet.small.file.limit" -> "1073741824",
HoodieTableConfig.POPULATE_META_FIELDS.key() -> "false",
HoodieWriteConfig.BULK_INSERT_SORT_MODE.key() ->
BulkInsertSortMode.GLOBAL_SORT.name(),
HoodieMetadataConfig.ENABLE_METADATA_INDEX_COLUMN_STATS.key() -> "true",
HoodieIndexConfig.INDEX_TYPE.key() -> "RECORD_INDEX",
DataSourceWriteOptions.META_SYNC_ENABLED.key() -> "false",
"hoodie.metadata.record.index.enable" -> "true",
"hoodie.metadata.enable" -> "true",
"hoodie.datasource.write.hive_style_partitioning" -> "true",
"hoodie.clustering.inline" -> "true",
"hoodie.clustering.plan.strategy.target.file.max.bytes" -> "2147483648",
"hoodie.clustering.plan.strategy.small.file.limit" -> "1073741824",
"hoodie.datasource.write.partitionpath.field" -> "city",
"hoodie.datasource.write.recordkey.field" -> "uuid",
"hoodie.datasource.write.precombine.field" -> "ts",
"hoodie.table.name" -> tableName
)
inserts.write.format("hudi").
options(bulkWriteOptions).
mode(Overwrite).
save(basePath)
val tripsDF = spark.read.format("hudi").load(basePath)
tripsDF.show(false)
```
--
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]
