Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[SPARK-22972] Couldn't find corresponding Hive SerDe for data source provider org.apache.spark.sql.hive.orc #20165

Closed
wants to merge 6 commits into from
Closed

[SPARK-22972] Couldn't find corresponding Hive SerDe for data source provider org.apache.spark.sql.hive.orc #20165

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
fa902d6
[SPARK-22972] Couldn't find corresponding Hive SerDe for data source …
xubo245 Jan 5, 2018
cf7cbce
keep the original one and update code style
xubo245 Jan 5, 2018
b64ce53
fix scala style: Whitespace at end of line
xubo245 Jan 5, 2018
1cfa72f
add withTable and tableSchema
xubo245 Jan 8, 2018
cc4dd13
add a line
xubo245 Jan 8, 2018
3eafdfb
update style
xubo245 Jan 8, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/internal/HiveSerDe.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,7 @@ object HiveSerDe {
val key = source.toLowerCase(Locale.ROOT) match {
case s if s.startsWith("org.apache.spark.sql.parquet") => "parquet"
case s if s.startsWith("org.apache.spark.sql.orc") => "orc"
case s if s.startsWith("org.apache.spark.sql.hive.orc") => "orc"
case s if s.equals("orcfile") => "orc"
case s if s.equals("parquetfile") => "parquet"
case s if s.equals("avrofile") => "avro"
Expand Down
29 changes: 29 additions & 0 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/HiveOrcSourceSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,10 @@ package org.apache.spark.sql.hive.orc
import java.io.File

import org.apache.spark.sql.Row
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.execution.datasources.orc.OrcSuite
import org.apache.spark.sql.hive.test.TestHiveSingleton
import org.apache.spark.sql.internal.HiveSerDe
import org.apache.spark.util.Utils

class HiveOrcSourceSuite extends OrcSuite with TestHiveSingleton {
Expand Down Expand Up @@ -62,6 +64,33 @@ class HiveOrcSourceSuite extends OrcSuite with TestHiveSingleton {
""".stripMargin)
}

test("SPARK-22972: hive orc source") {
val tableName = "normal_orc_as_source_hive"
withTable(tableName) {
sql(
s"""
|CREATE TABLE $tableName
|USING org.apache.spark.sql.hive.orc
|OPTIONS (
| PATH '${new File(orcTableAsDir.getAbsolutePath).toURI}'
|)
""".stripMargin)

val tableMetadata = spark.sessionState.catalog.getTableMetadata(
TableIdentifier(tableName))
assert(tableMetadata.storage.inputFormat ==
Option("org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"))
assert(tableMetadata.storage.outputFormat ==
Option("org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"))
assert(tableMetadata.storage.serde ==
Option("org.apache.hadoop.hive.ql.io.orc.OrcSerde"))
assert(HiveSerDe.sourceToSerDe("org.apache.spark.sql.hive.orc")
.equals(HiveSerDe.sourceToSerDe("orc")))
assert(HiveSerDe.sourceToSerDe("org.apache.spark.sql.orc")
.equals(HiveSerDe.sourceToSerDe("orc")))
}
}

test("SPARK-19459/SPARK-18220: read char/varchar column written by Hive") {
val location = Utils.createTempDir()
val uri = location.toURI
Expand Down