-
Notifications
You must be signed in to change notification settings - Fork 28.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[SPARK-24196][SQL] Implement Spark's own GetSchemasOperation
## What changes were proposed in this pull request? This PR fix SQL Client tools can't show DBs by implementing Spark's own `GetSchemasOperation`. ## How was this patch tested? unit tests and manual tests ![image](https://user-images.githubusercontent.com/5399861/47782885-3dd5d400-dd3c-11e8-8586-59a8c15c7020.png) ![image](https://user-images.githubusercontent.com/5399861/47782899-4928ff80-dd3c-11e8-9d2d-ba9580ba4301.png) Closes #22903 from wangyum/SPARK-24196. Authored-by: Yuming Wang <yumwang@ebay.com> Signed-off-by: gatorsmile <gatorsmile@gmail.com>
- Loading branch information
1 parent
6f35ede
commit 29a7d2d
Showing
5 changed files
with
201 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
66 changes: 66 additions & 0 deletions
66
...rver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkGetSchemasOperation.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,66 @@ | ||
/* | ||
* Licensed to the Apache Software Foundation (ASF) under one or more | ||
* contributor license agreements. See the NOTICE file distributed with | ||
* this work for additional information regarding copyright ownership. | ||
* The ASF licenses this file to You under the Apache License, Version 2.0 | ||
* (the "License"); you may not use this file except in compliance with | ||
* the License. You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.sql.hive.thriftserver | ||
|
||
import org.apache.hadoop.hive.ql.security.authorization.plugin.HiveOperationType | ||
import org.apache.hive.service.cli._ | ||
import org.apache.hive.service.cli.operation.GetSchemasOperation | ||
import org.apache.hive.service.cli.operation.MetadataOperation.DEFAULT_HIVE_CATALOG | ||
import org.apache.hive.service.cli.session.HiveSession | ||
|
||
import org.apache.spark.sql.SQLContext | ||
|
||
/** | ||
* Spark's own GetSchemasOperation | ||
* | ||
* @param sqlContext SQLContext to use | ||
* @param parentSession a HiveSession from SessionManager | ||
* @param catalogName catalog name. null if not applicable. | ||
* @param schemaName database name, null or a concrete database name | ||
*/ | ||
private[hive] class SparkGetSchemasOperation( | ||
sqlContext: SQLContext, | ||
parentSession: HiveSession, | ||
catalogName: String, | ||
schemaName: String) | ||
extends GetSchemasOperation(parentSession, catalogName, schemaName) { | ||
|
||
override def runInternal(): Unit = { | ||
setState(OperationState.RUNNING) | ||
// Always use the latest class loader provided by executionHive's state. | ||
val executionHiveClassLoader = sqlContext.sharedState.jarClassLoader | ||
Thread.currentThread().setContextClassLoader(executionHiveClassLoader) | ||
|
||
if (isAuthV2Enabled) { | ||
val cmdStr = s"catalog : $catalogName, schemaPattern : $schemaName" | ||
authorizeMetaGets(HiveOperationType.GET_TABLES, null, cmdStr) | ||
} | ||
|
||
try { | ||
val schemaPattern = convertSchemaPattern(schemaName) | ||
sqlContext.sessionState.catalog.listDatabases(schemaPattern).foreach { dbName => | ||
rowSet.addRow(Array[AnyRef](dbName, DEFAULT_HIVE_CATALOG)) | ||
} | ||
setState(OperationState.FINISHED) | ||
} catch { | ||
case e: HiveSQLException => | ||
setState(OperationState.ERROR) | ||
throw e | ||
} | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
103 changes: 103 additions & 0 deletions
103
...r/src/test/scala/org/apache/spark/sql/hive/thriftserver/SparkMetadataOperationSuite.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,103 @@ | ||
/* | ||
* Licensed to the Apache Software Foundation (ASF) under one or more | ||
* contributor license agreements. See the NOTICE file distributed with | ||
* this work for additional information regarding copyright ownership. | ||
* The ASF licenses this file to You under the Apache License, Version 2.0 | ||
* (the "License"); you may not use this file except in compliance with | ||
* the License. You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.sql.hive.thriftserver | ||
|
||
import java.util.Properties | ||
|
||
import org.apache.hive.jdbc.{HiveConnection, HiveQueryResultSet, Utils => JdbcUtils} | ||
import org.apache.hive.service.auth.PlainSaslHelper | ||
import org.apache.hive.service.cli.thrift._ | ||
import org.apache.thrift.protocol.TBinaryProtocol | ||
import org.apache.thrift.transport.TSocket | ||
|
||
class SparkMetadataOperationSuite extends HiveThriftJdbcTest { | ||
|
||
override def mode: ServerMode.Value = ServerMode.binary | ||
|
||
test("Spark's own GetSchemasOperation(SparkGetSchemasOperation)") { | ||
def testGetSchemasOperation( | ||
catalog: String, | ||
schemaPattern: String)(f: HiveQueryResultSet => Unit): Unit = { | ||
val rawTransport = new TSocket("localhost", serverPort) | ||
val connection = new HiveConnection(s"jdbc:hive2://localhost:$serverPort", new Properties) | ||
val user = System.getProperty("user.name") | ||
val transport = PlainSaslHelper.getPlainTransport(user, "anonymous", rawTransport) | ||
val client = new TCLIService.Client(new TBinaryProtocol(transport)) | ||
transport.open() | ||
var rs: HiveQueryResultSet = null | ||
try { | ||
val openResp = client.OpenSession(new TOpenSessionReq) | ||
val sessHandle = openResp.getSessionHandle | ||
val schemaReq = new TGetSchemasReq(sessHandle) | ||
|
||
if (catalog != null) { | ||
schemaReq.setCatalogName(catalog) | ||
} | ||
|
||
if (schemaPattern == null) { | ||
schemaReq.setSchemaName("%") | ||
} else { | ||
schemaReq.setSchemaName(schemaPattern) | ||
} | ||
|
||
val schemaResp = client.GetSchemas(schemaReq) | ||
JdbcUtils.verifySuccess(schemaResp.getStatus) | ||
|
||
rs = new HiveQueryResultSet.Builder(connection) | ||
.setClient(client) | ||
.setSessionHandle(sessHandle) | ||
.setStmtHandle(schemaResp.getOperationHandle) | ||
.build() | ||
f(rs) | ||
} finally { | ||
rs.close() | ||
connection.close() | ||
transport.close() | ||
rawTransport.close() | ||
} | ||
} | ||
|
||
def checkResult(dbNames: Seq[String], rs: HiveQueryResultSet): Unit = { | ||
if (dbNames.nonEmpty) { | ||
for (i <- dbNames.indices) { | ||
assert(rs.next()) | ||
assert(rs.getString("TABLE_SCHEM") === dbNames(i)) | ||
} | ||
} else { | ||
assert(!rs.next()) | ||
} | ||
} | ||
|
||
withDatabase("db1", "db2") { statement => | ||
Seq("CREATE DATABASE db1", "CREATE DATABASE db2").foreach(statement.execute) | ||
|
||
testGetSchemasOperation(null, "%") { rs => | ||
checkResult(Seq("db1", "db2"), rs) | ||
} | ||
testGetSchemasOperation(null, "db1") { rs => | ||
checkResult(Seq("db1"), rs) | ||
} | ||
testGetSchemasOperation(null, "db_not_exist") { rs => | ||
checkResult(Seq.empty, rs) | ||
} | ||
testGetSchemasOperation(null, "db*") { rs => | ||
checkResult(Seq("db1", "db2"), rs) | ||
} | ||
} | ||
} | ||
} |