pengzhiwei2018 commented on a change in pull request #3393:
URL: https://github.com/apache/hudi/pull/3393#discussion_r684324260
##########
File path:
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/TestCreateTable.scala
##########
@@ -272,4 +277,154 @@ class TestCreateTable extends TestHoodieSqlBase {
)
}
}
+
+ test("Test Create Table From Exist Hoodie Table") {
+ withTempDir { tmp =>
+ // Write a table by spark dataframe.
+ Seq("2021-08-02", "2021/08/02").foreach { partitionValue =>
+ val tableName = generateTableName
+ val tablePath = s"${tmp.getCanonicalPath}/$tableName"
+ import spark.implicits._
+ val df = Seq((1, "a1", 10, 1000, partitionValue)).toDF("id", "name",
"value", "ts", "dt")
Review comment:
done!
##########
File path:
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/TestCreateTable.scala
##########
@@ -272,4 +277,154 @@ class TestCreateTable extends TestHoodieSqlBase {
)
}
}
+
+ test("Test Create Table From Exist Hoodie Table") {
+ withTempDir { tmp =>
+ // Write a table by spark dataframe.
+ Seq("2021-08-02", "2021/08/02").foreach { partitionValue =>
+ val tableName = generateTableName
+ val tablePath = s"${tmp.getCanonicalPath}/$tableName"
+ import spark.implicits._
+ val df = Seq((1, "a1", 10, 1000, partitionValue)).toDF("id", "name",
"value", "ts", "dt")
+ df.write.format("hudi")
+ .option(HoodieWriteConfig.TABLE_NAME.key, tableName)
+ .option(TABLE_TYPE.key, COW_TABLE_TYPE_OPT_VAL)
+ .option(RECORDKEY_FIELD.key, "id")
+ .option(PRECOMBINE_FIELD.key, "ts")
+ .option(PARTITIONPATH_FIELD.key, "dt")
+ .option(KEYGENERATOR_CLASS.key, classOf[SimpleKeyGenerator].getName)
+ .option(HoodieWriteConfig.INSERT_PARALLELISM.key, "1")
+ .option(HoodieWriteConfig.UPSERT_PARALLELISM.key, "1")
+ .mode(SaveMode.Overwrite)
+ .save(tablePath)
+
+ // Create a table over the exist old table.
+ spark.sql(
+ s"""
+ |create table $tableName using hudi
+ | options (
+ | primaryKey = 'id',
+ | preCombineField = 'ts'
+ |)
+ |partitioned by (dt)
+ |location '$tablePath'
+ |""".stripMargin)
+ checkAnswer(s"select id, name, value, ts, dt from $tableName")(
+ Seq(1, "a1", 10, 1000, partitionValue)
+ )
+ // Check the missing properties for spark sql
+ val metaClient = HoodieTableMetaClient.builder()
+ .setBasePath(tablePath)
+ .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))
+
+ // Test insert into
+ spark.sql(s"insert into $tableName values(2, 'a2', 10, 1000,
'$partitionValue')")
+ checkAnswer(s"select id, name, value, ts, dt from $tableName order by
id")(
+ Seq(1, "a1", 10, 1000, partitionValue),
Review comment:
done!
--
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]
