[
https://issues.apache.org/jira/browse/HUDI-1842?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17392644#comment-17392644
]
ASF GitHub Bot commented on HUDI-1842:
--------------------------------------
pengzhiwei2018 commented on a change in pull request #3393:
URL: https://github.com/apache/hudi/pull/3393#discussion_r682236278
##########
File path:
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/TestCreateTable.scala
##########
@@ -272,4 +278,48 @@ class TestCreateTable extends TestHoodieSqlBase {
)
}
}
+
+ test("Test Create Table From Exist Hoodie Table") {
+ withTempDir{tmp =>
+ // Write a table by spark dataframe.
+ val tableName = generateTableName
+ import spark.implicits._
+ val df = Seq((1, "a1", 10, 1000, "2021-08-02")).toDF("id", "name",
"value", "ts", "dt")
+ df.write.format("hudi")
+ .option(HoodieWriteConfig.TABLE_NAME.key, tableName)
+ .option(TABLE_TYPE_OPT_KEY.key, COW_TABLE_TYPE_OPT_VAL)
+ .option(RECORDKEY_FIELD_OPT_KEY.key, "id")
+ .option(PRECOMBINE_FIELD_OPT_KEY.key, "ts")
+ .option(PARTITIONPATH_FIELD_OPT_KEY.key, "dt")
+ .option(KEYGENERATOR_CLASS_OPT_KEY.key,
classOf[ComplexKeyGenerator].getName)
+ .option(HoodieWriteConfig.INSERT_PARALLELISM.key, "1")
+ .option(HoodieWriteConfig.UPSERT_PARALLELISM.key, "1")
+ .mode(SaveMode.Overwrite)
+ .save(tmp.getCanonicalPath)
+
+ // Create a table over the exist old table.
+ spark.sql(
+ s"""
+ |create table $tableName using hudi
+ | options (
+ | primaryKey = 'id',
+ | preCombineField = 'ts'
+ |)
+ |partitioned by (dt)
+ |location '${tmp.getCanonicalPath}'
+ |""".stripMargin)
+ checkAnswer(s"select id, name, value, ts, dt from $tableName")(
+ Seq(1, "a1", 10, 1000, "2021-08-02")
+ )
+ // Check the missing properties for spark sql
+ val metaClient = HoodieTableMetaClient.builder()
+ .setBasePath(tmp.getCanonicalPath)
+ .setConf(spark.sessionState.newHadoopConf())
+ .build()
+ val properties = metaClient.getTableConfig.getProps.asScala.toMap
+
assertResult(true)(properties.contains(HoodieTableConfig.HOODIE_TABLE_CREATE_SCHEMA.key))
+
assertResult("dt")(properties(HoodieTableConfig.HOODIE_TABLE_PARTITION_FIELDS_PROP.key))
+
assertResult("ts")(properties(HoodieTableConfig.HOODIE_TABLE_PRECOMBINE_FIELD_PROP.key))
Review comment:
Yes, will add more test case for this.
--
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]
> [SQL] Spark Sql Support For The Exists Hoodie Table
> ---------------------------------------------------
>
> Key: HUDI-1842
> URL: https://issues.apache.org/jira/browse/HUDI-1842
> Project: Apache Hudi
> Issue Type: Sub-task
> Reporter: pengzhiwei
> Assignee: pengzhiwei
> Priority: Blocker
> Labels: pull-request-available, release-blocker
> Fix For: 0.9.0
>
>
> In order to support spark sql for hoodie, we persist some table properties to
> the hoodie.properties. e.g. primaryKey, preCombineField, partition columns.
> For the exists hoodie tables, these properties are missing. We need do some
> code in UpgradeDowngrade to support spark sql for the exists tables.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
