rangareddy commented on issue #2509:
URL: https://github.com/apache/hudi/issues/2509#issuecomment-3737107671
```sh
spark-shell \
--jars /usr/lib/hudi/hudi-spark-bundle.jar \
--conf spark.serializer=org.apache.spark.serializer.KryoSerializer
```
```scala
import org.apache.spark.sql.types._
var seq = Seq((1, "2020-01-01 11:22:30", 2, 2))
var df = seq.toDF("pk", "time_string" , "partition", "sort_key")
df= df.withColumn("ts", col("time_string").cast(TimestampType))
val tableName = "test_ts_table"
val outputPath = f"s3://one-house-db-uat/data/$tableName"
var hudiOptions = Map[String,String](
"hoodie.table.name" -> tableName,
"hoodie.consistency.check.enabled" -> "true",
"hoodie.datasource.write.storage.type" -> "COPY_ON_WRITE",
"hoodie.datasource.write.recordkey.field" -> "pk",
"hoodie.datasource.write.partitionpath.field" -> "partition",
"hoodie.datasource.write.precombine.field" -> "sort_key",
"hoodie.datasource.hive_sync.enable" -> "true",
"hoodie.datasource.hive_sync.mode" -> "hms",
"hoodie.datasource.hive_sync.jdbcurl" -> "thrift://localhost:9083",
"hoodie.datasource.hive_sync.database" -> "default",
"hoodie.datasource.hive_sync.table" -> tableName,
"hoodie.datasource.hive_sync.partition_fields" -> "partition",
"hoodie.datasource.write.hive_style_partitioning" -> "true",
"hoodie.datasource.hive_sync.partition_extractor_class" ->
"org.apache.hudi.hive.MultiPartKeysValueExtractor",
"hoodie.datasource.hive_sync.support_timestamp" -> "false"
)
df.write.format("hudi").options(hudiOptions).mode("overwrite").save(outputPath)
spark.sql(f"select pk, time_string, sort_key, ts, partition from
$tableName").show()
+---+-------------------+--------+-------------------+---------+
| pk| time_string|sort_key| ts|partition|
+---+-------------------+--------+-------------------+---------+
| 1|2020-01-01 11:22:30| 2|2020-01-01 11:22:30| 2|
+---+-------------------+--------+-------------------+---------+
spark.sql(f"describe $tableName").show()
+--------------------+---------+-------+
| col_name|data_type|comment|
+--------------------+---------+-------+
| _hoodie_commit_time| string| NULL|
|_hoodie_commit_seqno| string| NULL|
| _hoodie_record_key| string| NULL|
|_hoodie_partition...| string| NULL|
| _hoodie_file_name| string| NULL|
| pk| int| NULL|
| time_string| string| NULL|
| sort_key| int| NULL|
| ts|timestamp| NULL|
| partition| int| NULL|
|# Partition Infor...| | |
| # col_name|data_type|comment|
| partition| int| NULL|
+--------------------+---------+-------+
```
```scala
val tableName = "test_ts_table2"
val outputPath = f"s3://one-house-db-uat/data/$tableName"
var hudiOptions = Map[String,String](
"hoodie.table.name" -> tableName,
"hoodie.consistency.check.enabled" -> "true",
"hoodie.datasource.write.storage.type" -> "COPY_ON_WRITE",
"hoodie.datasource.write.recordkey.field" -> "pk",
"hoodie.datasource.write.partitionpath.field" -> "partition",
"hoodie.datasource.write.precombine.field" -> "sort_key",
"hoodie.datasource.hive_sync.enable" -> "true",
"hoodie.datasource.hive_sync.mode" -> "hms",
"hoodie.datasource.hive_sync.jdbcurl" -> "thrift://localhost:9083",
"hoodie.datasource.hive_sync.database" -> "default",
"hoodie.datasource.hive_sync.table" -> tableName,
"hoodie.datasource.hive_sync.partition_fields" -> "partition",
"hoodie.datasource.write.hive_style_partitioning" -> "true",
"hoodie.datasource.hive_sync.partition_extractor_class" ->
"org.apache.hudi.hive.MultiPartKeysValueExtractor",
"hoodie.datasource.hive_sync.support_timestamp" -> "true"
)
df.write.format("hudi").options(hudiOptions).mode("overwrite").save(outputPath)
spark.sql(f"select pk, time_string, sort_key, ts, partition from
$tableName").show()
+---+-------------------+--------+-------------------+---------+
| pk| time_string|sort_key| ts|partition|
+---+-------------------+--------+-------------------+---------+
| 1|2020-01-01 11:22:30| 2|2020-01-01 11:22:30| 2|
+---+-------------------+--------+-------------------+---------+
spark.sql(f"describe $tableName").show()
+--------------------+---------+-------+
| col_name|data_type|comment|
+--------------------+---------+-------+
| _hoodie_commit_time| string| NULL|
|_hoodie_commit_seqno| string| NULL|
| _hoodie_record_key| string| NULL|
|_hoodie_partition...| string| NULL|
| _hoodie_file_name| string| NULL|
| pk| int| NULL|
| time_string| string| NULL|
| sort_key| int| NULL|
| ts|timestamp| NULL|
| partition| int| NULL|
|# Partition Infor...| | |
| # col_name|data_type|comment|
| partition| int| NULL|
+--------------------+---------+-------+
```
--
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]
