Github user mallman commented on a diff in the pull request:

    https://github.com/apache/spark/pull/16071#discussion_r90303311
  
    --- Diff: 
sql/hive/src/test/scala/org/apache/spark/sql/hive/PartitionProviderCompatibilitySuite.scala
 ---
    @@ -205,6 +205,58 @@ class PartitionProviderCompatibilitySuite
             }
           }
         }
    +
    +    test(s"SPARK-18635 special chars in partition values - partition 
management $enabled") {
    +      withTable("test") {
    +        spark.range(10)
    +          .selectExpr("id", "id as A", "'%' as B")
    +          .write.partitionBy("A", "B").mode("overwrite")
    +          .saveAsTable("test")
    +        assert(spark.sql("select * from test").count() == 10)
    +        assert(spark.sql("select * from test where B = '%'").count() == 10)
    +        assert(spark.sql("select * from test where B = '$'").count() == 0)
    +        spark.range(10)
    +          .selectExpr("id", "id as A", "'=' as B")
    +          .write.mode("append").insertInto("test")
    +        spark.sql("insert into test partition (A, B) select id, id, '%=' 
from range(10)")
    +        assert(spark.sql("select * from test").count() == 30)
    +        assert(spark.sql("select * from test where B = '%'").count() == 10)
    +        assert(spark.sql("select * from test where B = '='").count() == 10)
    +        assert(spark.sql("select * from test where B = '%='").count() == 
10)
    +
    +        // show partitions sanity check
    +        val parts = spark.sql("show partitions 
test").collect().map(_.get(0)).toSeq
    +        assert(parts.length == 30)
    +        assert(parts.contains("A=0/B=%25"))
    +        assert(parts.contains("A=0/B=%3D"))
    +        assert(parts.contains("A=0/B=%25%3D"))
    +
    +        // custom locations sanity check
    +        withTempDir { dir =>
    +          spark.sql(s"""
    +            |alter table test partition (A=0, B='%')
    +            |set location '${dir.getAbsolutePath}'""".stripMargin)
    +          assert(spark.sql("select * from test").count() == 29)  // 
missing 1
    --- End diff --
    
    Ah. I see. So Hive/Spark doesn't move partition data when the partition 
location is changed. Might be clearer to call that out in your comment rather 
than just "missing 1".


---
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 [email protected] or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to