[jira] [Updated] (SPARK-18659) Incorrect behaviors in overwrite table for datasource tables
[
https://issues.apache.org/jira/browse/SPARK-18659?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Reynold Xin updated SPARK-18659:
Issue Type: Sub-task (was: Bug)
Parent: SPARK-17861
> Incorrect behaviors in overwrite table for datasource tables
>
>
> Key: SPARK-18659
> URL: https://issues.apache.org/jira/browse/SPARK-18659
> Project: Spark
> Issue Type: Sub-task
> Components: SQL
>Affects Versions: 2.1.0
>Reporter: Eric Liang
>Priority: Blocker
>
> The first three test cases fail due to a crash in hive client when dropping
> partitions that don't contain files. The last one deletes too many files due
> to a partition case resolution failure.
> {code}
> test("foo") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test select id, id, 'x' from
> range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("bar") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test partition (a, b) select id, id,
> 'x' from range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("baz") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test partition (A, B) select id, id,
> 'x' from range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("qux") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test partition (a=1, b) select id,
> 'x' from range(1)")
> assert(spark.sql("select * from test").count() == 10)
> }
> }
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Updated] (SPARK-18659) Incorrect behaviors in overwrite table for datasource tables
[
https://issues.apache.org/jira/browse/SPARK-18659?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Eric Liang updated SPARK-18659:
---
Description:
The first three test cases fail due to a crash in hive client when dropping
partitions that don't contain files. The last one deletes too many files due to
a partition case resolution failure.
{code}
test("foo") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test select id, id, 'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("bar") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (a, b) select id, id,
'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("baz") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (A, B) select id, id,
'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("qux") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (a=1, b) select id, 'x'
from range(1)")
assert(spark.sql("select * from test").count() == 10)
}
}
{code}
was:
The following test cases fail due to a crash in hive client when dropping
partitions that don't contain files. The last one deletes too many files due to
a partition case resolution failure.
{code}
test("foo") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test select id, id, 'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("bar") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (a, b) select id, id,
'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("baz") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (A, B) select id, id,
'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("qux") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (a=1, b) select id, 'x'
from range(1)")
assert(spark.sql("select * from test").count() == 10)
}
}
{code}
> Incorrect behaviors in overwrite table for datasource tables
>
>
> Key: SPARK-18659
> URL: https://issues.apache.org/jira/browse/SPARK-18659
> Project: Spark
> Issue Type: Bug
> Components: SQL
>Affects Versions: 2.1.0
>Reporter: Eric Liang
>Priority: Blocker
>
> The first three test cases fail due to a crash in hive client when dropping
> partitions that don't contain files. The last one deletes too many files due
> to a partition case resolution failure.
> {code}
> test("foo") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test select id, id, 'x' from
> range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("bar") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test partition (a, b) select id, id,
> 'x' from range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("baz") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
>
[jira] [Updated] (SPARK-18659) Incorrect behaviors in overwrite table for datasource tables
[
https://issues.apache.org/jira/browse/SPARK-18659?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Eric Liang updated SPARK-18659:
---
Description:
The following test cases fail due to a crash in hive client when dropping
partitions that don't contain files. The last one deletes too many files due to
a partition case resolution failure.
{code}
test("foo") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test select id, id, 'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("bar") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (a, b) select id, id,
'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("baz") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (A, B) select id, id,
'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("qux") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (a=1, b) select id, 'x'
from range(1)")
assert(spark.sql("select * from test").count() == 10)
}
}
{code}
was:
The following test cases fail due to a crash in hive client when dropping
partitions that don't contain files. The last one crashes due to a partition
case resolution failure.
{code}
test("foo") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test select id, id, 'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("bar") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (a, b) select id, id,
'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("baz") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (A, B) select id, id,
'x' from range(1)")
assert(spark.sql("select * from test").count() == 1)
}
}
test("qux") {
withTable("test") {
spark.range(10)
.selectExpr("id", "id as A", "'x' as B")
.write.partitionBy("A", "B").mode("overwrite")
.saveAsTable("test")
spark.sql("insert overwrite table test partition (a=1, b) select id, 'x'
from range(1)")
assert(spark.sql("select * from test").count() == 10)
}
}
{code}
> Incorrect behaviors in overwrite table for datasource tables
>
>
> Key: SPARK-18659
> URL: https://issues.apache.org/jira/browse/SPARK-18659
> Project: Spark
> Issue Type: Bug
> Components: SQL
>Affects Versions: 2.1.0
>Reporter: Eric Liang
>Priority: Blocker
>
> The following test cases fail due to a crash in hive client when dropping
> partitions that don't contain files. The last one deletes too many files due
> to a partition case resolution failure.
> {code}
> test("foo") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test select id, id, 'x' from
> range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("bar") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test partition (a, b) select id, id,
> 'x' from range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("baz") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.par
[jira] [Updated] (SPARK-18659) Incorrect behaviors in overwrite table for datasource tables
[
https://issues.apache.org/jira/browse/SPARK-18659?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Eric Liang updated SPARK-18659:
---
Summary: Incorrect behaviors in overwrite table for datasource tables
(was: Crash in overwrite table partitions due to hive metastore integration)
> Incorrect behaviors in overwrite table for datasource tables
>
>
> Key: SPARK-18659
> URL: https://issues.apache.org/jira/browse/SPARK-18659
> Project: Spark
> Issue Type: Bug
> Components: SQL
>Affects Versions: 2.1.0
>Reporter: Eric Liang
>Priority: Blocker
>
> The following test cases fail due to a crash in hive client when dropping
> partitions that don't contain files. The last one crashes due to a partition
> case resolution failure.
> {code}
> test("foo") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test select id, id, 'x' from
> range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("bar") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test partition (a, b) select id, id,
> 'x' from range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("baz") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test partition (A, B) select id, id,
> 'x' from range(1)")
> assert(spark.sql("select * from test").count() == 1)
> }
> }
> test("qux") {
> withTable("test") {
> spark.range(10)
> .selectExpr("id", "id as A", "'x' as B")
> .write.partitionBy("A", "B").mode("overwrite")
> .saveAsTable("test")
> spark.sql("insert overwrite table test partition (a=1, b) select id,
> 'x' from range(1)")
> assert(spark.sql("select * from test").count() == 10)
> }
> }
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
