spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From wzhfy <...@git.apache.org>
Subject [GitHub] spark pull request #18309: [SPARK-21079] [SQL] Calculate total size of a par...
Date Thu, 15 Jun 2017 18:19:33 GMT
Github user wzhfy commented on a diff in the pull request:

    https://github.com/apache/spark/pull/18309#discussion_r122275444
  
    --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala ---
    @@ -128,6 +128,40 @@ class StatisticsSuite extends StatisticsCollectionTestBase with TestHiveSingleto
           TableIdentifier("tempTable"), ignoreIfNotExists = true, purge = false)
       }
     
    +  test("SPARK-21079 - analyze table with location different than that of individual partitions")
{
    +    def queryTotalSize(tableName: String): BigInt =
    +      spark.table(tableName).queryExecution.analyzed.stats(conf).sizeInBytes
    +
    +    sql(
    +      """
    +        |CREATE TABLE analyzeTable_part (key STRING, value STRING) PARTITIONED BY (ds
STRING)
    +      """.stripMargin).collect()
    +    sql(
    +      """
    +        |INSERT INTO TABLE analyzeTable_part PARTITION (ds='2010-01-01')
    +        |SELECT * FROM src
    +      """.stripMargin).collect()
    +    sql(
    +      """
    +        |INSERT INTO TABLE analyzeTable_part PARTITION (ds='2010-01-02')
    +        |SELECT * FROM src
    +      """.stripMargin).collect()
    +    sql(
    +      """
    +        |INSERT INTO TABLE analyzeTable_part PARTITION (ds='2010-01-03')
    +        |SELECT * FROM src
    +      """.stripMargin).collect()
    +
    +    // Modify table location to not match location of individual partitions
    +    sql("ALTER TABLE analyzeTable_part SET LOCATION 'file:/do/not/use'").collect()
    --- End diff --
    
    BTW, we need to move `withTempDirs` from `FileStreamSourceSuite` to `SQLTestUtils`.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message