diff options
author | Reynold Xin <rxin@databricks.com> | 2015-03-02 22:14:08 -0800 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2015-03-02 22:14:08 -0800 |
commit | 54d19689ff8d786acde5b8ada6741854ffadadea (patch) | |
tree | b0a2a68c3e8ea6a7f0209fa6a12d02d1c38b3c71 /sql | |
parent | 12599942e69e4d73040f3a8611661a0862514ffc (diff) | |
download | spark-54d19689ff8d786acde5b8ada6741854ffadadea.tar.gz spark-54d19689ff8d786acde5b8ada6741854ffadadea.tar.bz2 spark-54d19689ff8d786acde5b8ada6741854ffadadea.zip |
[SPARK-5310][SQL] Fixes to Docs and Datasources API
- Various Fixes to docs
- Make data source traits actually interfaces
Based on #4862 but with fixed conflicts.
Author: Reynold Xin <rxin@databricks.com>
Author: Michael Armbrust <michael@databricks.com>
Closes #4868 from marmbrus/pr/4862 and squashes the following commits:
fe091ea [Michael Armbrust] Merge remote-tracking branch 'origin/master' into pr/4862
0208497 [Reynold Xin] Test fixes.
34e0a28 [Reynold Xin] [SPARK-5310][SQL] Various fixes to Spark SQL docs.
Diffstat (limited to 'sql')
21 files changed, 98 insertions, 124 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala index f3aac0826a..46f50708a9 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala @@ -64,7 +64,7 @@ private[sql] object DataFrame { * val people = sqlContext.parquetFile("...") * * // Create a DataFrame from data sources - * val df = + * val df = sqlContext.load("...", "json") * }}} * * Once created, it can be manipulated using the various domain-specific-language (DSL) functions @@ -80,9 +80,10 @@ private[sql] object DataFrame { * {{{ * // The following creates a new column that increases everybody's age by 10. * people("age") + 10 // in Scala + * people.col("age").plus(10); // in Java * }}} * - * A more concrete example: + * A more concrete example in Scala: * {{{ * // To create DataFrame using SQLContext * val people = sqlContext.parquetFile("...") @@ -94,6 +95,18 @@ private[sql] object DataFrame { * .agg(avg(people("salary")), max(people("age"))) * }}} * + * and in Java: + * {{{ + * // To create DataFrame using SQLContext + * DataFrame people = sqlContext.parquetFile("..."); + * DataFrame department = sqlContext.parquetFile("..."); + * + * people.filter("age".gt(30)) + * .join(department, people.col("deptId").equalTo(department("id"))) + * .groupBy(department.col("name"), "gender") + * .agg(avg(people.col("salary")), max(people.col("age"))); + * }}} + * * @groupname basic Basic DataFrame functions * @groupname dfops Language Integrated Queries * @groupname rdd RDD Operations @@ -102,7 +115,7 @@ private[sql] object DataFrame { */ // TODO: Improve documentation. @Experimental -class DataFrame protected[sql]( +class DataFrame private[sql]( @transient val sqlContext: SQLContext, @DeveloperApi @transient val queryExecution: SQLContext#QueryExecution) extends RDDApi[Row] with Serializable { @@ -295,12 +308,14 @@ class DataFrame protected[sql]( * 1984 04 0.450090 0.483521 * }}} * @param numRows Number of rows to show - * @group basic + * + * @group action */ def show(numRows: Int): Unit = println(showString(numRows)) /** * Displays the top 20 rows of [[DataFrame]] in a tabular form. + * @group action */ def show(): Unit = show(20) @@ -738,16 +753,19 @@ class DataFrame protected[sql]( /** * Returns the first `n` rows. + * @group action */ def head(n: Int): Array[Row] = limit(n).collect() /** * Returns the first row. + * @group action */ def head(): Row = head(1).head /** * Returns the first row. Alias for head(). + * @group action */ override def first(): Row = head() @@ -834,6 +852,11 @@ class DataFrame protected[sql]( /** * @group basic */ + override def cache(): this.type = persist() + + /** + * @group basic + */ override def persist(newLevel: StorageLevel): this.type = { sqlContext.cacheManager.cacheQuery(this, None, newLevel) this @@ -847,6 +870,11 @@ class DataFrame protected[sql]( this } + /** + * @group basic + */ + override def unpersist(): this.type = unpersist(blocking = false) + ///////////////////////////////////////////////////////////////////////////// // I/O ///////////////////////////////////////////////////////////////////////////// diff --git a/sql/core/src/main/scala/org/apache/spark/sql/RDDApi.scala b/sql/core/src/main/scala/org/apache/spark/sql/RDDApi.scala index df866fd1ad..ba4373f012 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/RDDApi.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/RDDApi.scala @@ -29,13 +29,13 @@ import org.apache.spark.storage.StorageLevel */ private[sql] trait RDDApi[T] { - def cache(): this.type = persist() + def cache(): this.type def persist(): this.type def persist(newLevel: StorageLevel): this.type - def unpersist(): this.type = unpersist(blocking = false) + def unpersist(): this.type def unpersist(blocking: Boolean): this.type diff --git a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JDBCRelation.scala b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JDBCRelation.scala index beb76f2c55..1778d39c42 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JDBCRelation.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/JDBCRelation.scala @@ -119,7 +119,8 @@ private[sql] case class JDBCRelation( url: String, table: String, parts: Array[Partition])(@transient val sqlContext: SQLContext) - extends PrunedFilteredScan { + extends BaseRelation + with PrunedFilteredScan { override val schema = JDBCRDD.resolveTable(url, table) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/json/JSONRelation.scala b/sql/core/src/main/scala/org/apache/spark/sql/json/JSONRelation.scala index f9d0ba2241..b645199ded 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/json/JSONRelation.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/json/JSONRelation.scala @@ -90,7 +90,10 @@ private[sql] case class JSONRelation( samplingRatio: Double, userSpecifiedSchema: Option[StructType])( @transient val sqlContext: SQLContext) - extends TableScan with InsertableRelation { + extends BaseRelation + with TableScan + with InsertableRelation { + // TODO: Support partitioned JSON relation. private def baseRDD = sqlContext.sparkContext.textFile(path) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala index 8d95858493..234e6bb844 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala @@ -159,7 +159,8 @@ private[sql] case class ParquetRelation2( maybeSchema: Option[StructType] = None, maybePartitionSpec: Option[PartitionSpec] = None)( @transient val sqlContext: SQLContext) - extends CatalystScan + extends BaseRelation + with CatalystScan with InsertableRelation with SparkHadoopMapReduceUtil with Logging { diff --git a/sql/core/src/main/scala/org/apache/spark/sql/sources/interfaces.scala b/sql/core/src/main/scala/org/apache/spark/sql/sources/interfaces.scala index 0c4b706eee..a046a48c17 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/sources/interfaces.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/sources/interfaces.scala @@ -14,6 +14,7 @@ * See the License for the specific language governing permissions and * limitations under the License. */ + package org.apache.spark.sql.sources import org.apache.spark.annotation.{Experimental, DeveloperApi} @@ -90,12 +91,6 @@ trait CreatableRelationProvider { * existing data is expected to be overwritten by the contents of the DataFrame. * ErrorIfExists mode means that when saving a DataFrame to a data source, * if data already exists, an exception is expected to be thrown. - * - * @param sqlContext - * @param mode - * @param parameters - * @param data - * @return */ def createRelation( sqlContext: SQLContext, @@ -138,7 +133,7 @@ abstract class BaseRelation { * A BaseRelation that can produce all of its tuples as an RDD of Row objects. */ @DeveloperApi -trait TableScan extends BaseRelation { +trait TableScan { def buildScan(): RDD[Row] } @@ -148,7 +143,7 @@ trait TableScan extends BaseRelation { * containing all of its tuples as Row objects. */ @DeveloperApi -trait PrunedScan extends BaseRelation { +trait PrunedScan { def buildScan(requiredColumns: Array[String]): RDD[Row] } @@ -162,25 +157,11 @@ trait PrunedScan extends BaseRelation { * as filtering partitions based on a bloom filter. */ @DeveloperApi -trait PrunedFilteredScan extends BaseRelation { +trait PrunedFilteredScan { def buildScan(requiredColumns: Array[String], filters: Array[Filter]): RDD[Row] } /** - * ::Experimental:: - * An interface for experimenting with a more direct connection to the query planner. Compared to - * [[PrunedFilteredScan]], this operator receives the raw expressions from the - * [[org.apache.spark.sql.catalyst.plans.logical.LogicalPlan]]. Unlike the other APIs this - * interface is not designed to be binary compatible across releases and thus should only be used - * for experimentation. - */ -@Experimental -trait CatalystScan extends BaseRelation { - def buildScan(requiredColumns: Seq[Attribute], filters: Seq[Expression]): RDD[Row] -} - -@DeveloperApi -/** * ::DeveloperApi:: * A BaseRelation that can be used to insert data into it through the insert method. * If overwrite in insert method is true, the old data in the relation should be overwritten with @@ -196,6 +177,20 @@ trait CatalystScan extends BaseRelation { * If a data source needs to check the actual nullability of a field, it needs to do it in the * insert method. */ -trait InsertableRelation extends BaseRelation { +@DeveloperApi +trait InsertableRelation { def insert(data: DataFrame, overwrite: Boolean): Unit } + +/** + * ::Experimental:: + * An interface for experimenting with a more direct connection to the query planner. Compared to + * [[PrunedFilteredScan]], this operator receives the raw expressions from the + * [[org.apache.spark.sql.catalyst.plans.logical.LogicalPlan]]. Unlike the other APIs this + * interface is NOT designed to be binary compatible across releases and thus should only be used + * for experimentation. + */ +@Experimental +trait CatalystScan { + def buildScan(requiredColumns: Seq[Attribute], filters: Seq[Expression]): RDD[Row] +} diff --git a/sql/core/src/test/scala/org/apache/spark/sql/sources/DDLTestSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/sources/DDLTestSuite.scala index 0ec756bfeb..54af50c6e1 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/sources/DDLTestSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/sources/DDLTestSuite.scala @@ -29,7 +29,7 @@ class DDLScanSource extends RelationProvider { } case class SimpleDDLScan(from: Int, to: Int)(@transient val sqlContext: SQLContext) - extends TableScan { + extends BaseRelation with TableScan { override def schema = StructType(Seq( diff --git a/sql/core/src/test/scala/org/apache/spark/sql/sources/FilteredScanSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/sources/FilteredScanSuite.scala index 41cd35683c..ffeccf0b69 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/sources/FilteredScanSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/sources/FilteredScanSuite.scala @@ -32,7 +32,8 @@ class FilteredScanSource extends RelationProvider { } case class SimpleFilteredScan(from: Int, to: Int)(@transient val sqlContext: SQLContext) - extends PrunedFilteredScan { + extends BaseRelation + with PrunedFilteredScan { override def schema = StructType( diff --git a/sql/core/src/test/scala/org/apache/spark/sql/sources/PrunedScanSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/sources/PrunedScanSuite.scala index a33cf1172c..08fb5380dc 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/sources/PrunedScanSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/sources/PrunedScanSuite.scala @@ -31,7 +31,8 @@ class PrunedScanSource extends RelationProvider { } case class SimplePrunedScan(from: Int, to: Int)(@transient val sqlContext: SQLContext) - extends PrunedScan { + extends BaseRelation + with PrunedScan { override def schema = StructType( diff --git a/sql/core/src/test/scala/org/apache/spark/sql/sources/TableScanSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/sources/TableScanSuite.scala index 0a4d4b6342..7928600ac2 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/sources/TableScanSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/sources/TableScanSuite.scala @@ -33,7 +33,7 @@ class SimpleScanSource extends RelationProvider { } case class SimpleScan(from: Int, to: Int)(@transient val sqlContext: SQLContext) - extends TableScan { + extends BaseRelation with TableScan { override def schema = StructType(StructField("i", IntegerType, nullable = false) :: Nil) @@ -51,10 +51,11 @@ class AllDataTypesScanSource extends SchemaRelationProvider { } case class AllDataTypesScan( - from: Int, - to: Int, - userSpecifiedSchema: StructType)(@transient val sqlContext: SQLContext) - extends TableScan { + from: Int, + to: Int, + userSpecifiedSchema: StructType)(@transient val sqlContext: SQLContext) + extends BaseRelation + with TableScan { override def schema = userSpecifiedSchema diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala index 86fc6548f9..fe86bd206a 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala @@ -777,7 +777,8 @@ private[hive] case class MetastoreRelation val columnOrdinals = AttributeMap(attributes.zipWithIndex) } -object HiveMetastoreTypes { + +private[hive] object HiveMetastoreTypes { protected val ddlParser = new DDLParser(HiveQl.parseSql(_)) def toDataType(metastoreType: String): DataType = synchronized { diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala index a547babceb..a0c91cbc4e 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/CreateTableAsSelect.scala @@ -28,7 +28,6 @@ import org.apache.spark.sql.hive.HiveContext import org.apache.spark.sql.hive.MetastoreRelation /** - * :: Experimental :: * Create table and insert the query result into it. * @param database the database name of the new relation * @param tableName the table name of the new relation @@ -38,7 +37,7 @@ import org.apache.spark.sql.hive.MetastoreRelation * @param desc the CreateTableDesc, which may contains serde, storage handler etc. */ -@Experimental +private[hive] case class CreateTableAsSelect( database: String, tableName: String, diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/DescribeHiveTableCommand.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/DescribeHiveTableCommand.scala index 07b5a84fb6..d0510aa342 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/DescribeHiveTableCommand.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/DescribeHiveTableCommand.scala @@ -29,11 +29,9 @@ import org.apache.spark.sql.hive.HiveShim import org.apache.spark.sql.SQLContext /** - * :: DeveloperApi :: - * * Implementation for "describe [extended] table". */ -@DeveloperApi +private[hive] case class DescribeHiveTableCommand( table: MetastoreRelation, override val output: Seq[Attribute], diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveNativeCommand.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveNativeCommand.scala index 781a2e9164..9636da2060 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveNativeCommand.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveNativeCommand.scala @@ -17,17 +17,13 @@ package org.apache.spark.sql.hive.execution
-import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.sql.catalyst.expressions.{AttributeReference, Row}
import org.apache.spark.sql.execution.RunnableCommand
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.types.StringType
-/**
- * :: DeveloperApi ::
- */
-@DeveloperApi
+private[hive]
case class HiveNativeCommand(sql: String) extends RunnableCommand {
override def output =
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala index b56175fe76..5b3cf2861e 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala @@ -26,21 +26,19 @@ import org.apache.hadoop.hive.serde2.objectinspector._ import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.ObjectInspectorCopyOption import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils -import org.apache.spark.annotation.DeveloperApi import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.execution._ import org.apache.spark.sql.hive._ import org.apache.spark.sql.types.{BooleanType, DataType} /** - * :: DeveloperApi :: * The Hive table scan operator. Column and partition pruning are both handled. * * @param requestedAttributes Attributes to be fetched from the Hive table. * @param relation The Hive table be be scanned. * @param partitionPruningPred An optional partition pruning predicate for partitioned table. */ -@DeveloperApi +private[hive] case class HiveTableScan( requestedAttributes: Seq[Attribute], relation: MetastoreRelation, diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala index 91af35f096..ba5c8e028a 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala @@ -32,7 +32,6 @@ import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.Object import org.apache.hadoop.hive.serde2.objectinspector._ import org.apache.hadoop.mapred.{FileOutputCommitter, FileOutputFormat, JobConf} -import org.apache.spark.annotation.DeveloperApi import org.apache.spark.rdd.RDD import org.apache.spark.sql.catalyst.expressions.Row import org.apache.spark.sql.execution.{UnaryNode, SparkPlan} @@ -41,10 +40,7 @@ import org.apache.spark.sql.hive.{ ShimFileSinkDesc => FileSinkDesc} import org.apache.spark.sql.hive.HiveShim._ import org.apache.spark.{SerializableWritable, SparkException, TaskContext} -/** - * :: DeveloperApi :: - */ -@DeveloperApi +private[hive] case class InsertIntoHiveTable( table: MetastoreRelation, partition: Map[String, Option[String]], diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformation.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformation.scala index c54fbb6e24..0c9aee3398 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformation.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformation.scala @@ -21,15 +21,12 @@ import java.io.{BufferedReader, InputStreamReader} import java.io.{DataInputStream, DataOutputStream, EOFException} import java.util.Properties +import scala.collection.JavaConversions._ + import org.apache.hadoop.hive.serde.serdeConstants import org.apache.hadoop.hive.serde2.AbstractSerDe -import org.apache.hadoop.hive.serde2.Serializer -import org.apache.hadoop.hive.serde2.Deserializer import org.apache.hadoop.hive.serde2.objectinspector._ -import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory.ObjectInspectorOptions -import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.ObjectInspectorCopyOption -import org.apache.spark.annotation.DeveloperApi import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.catalyst.plans.logical.ScriptInputOutputSchema import org.apache.spark.sql.execution._ @@ -38,19 +35,14 @@ import org.apache.spark.sql.hive.{HiveContext, HiveInspectors} import org.apache.spark.sql.hive.HiveShim._ import org.apache.spark.util.Utils - -/* Implicit conversions */ -import scala.collection.JavaConversions._ - /** - * :: DeveloperApi :: * Transforms the input by forking and running the specified script. * * @param input the set of expression that should be passed to the script. * @param script the command that should be executed. * @param output the attributes that are produced by the script. */ -@DeveloperApi +private[hive] case class ScriptTransformation( input: Seq[Expression], script: String, @@ -175,6 +167,7 @@ case class ScriptTransformation( /** * The wrapper class of Hive input and output schema properties */ +private[hive] case class HiveScriptIOSchema ( inputRowFormat: Seq[(String, String)], outputRowFormat: Seq[(String, String)], diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala index 36bd3f8fe2..63ad145a6a 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala @@ -17,7 +17,6 @@ package org.apache.spark.sql.hive.execution -import org.apache.spark.annotation.DeveloperApi import org.apache.spark.sql.AnalysisException import org.apache.spark.sql.catalyst.analysis.EliminateSubQueries import org.apache.spark.sql.catalyst.util._ @@ -30,14 +29,13 @@ import org.apache.spark.sql.hive.HiveContext import org.apache.spark.sql.types.StructType /** - * :: DeveloperApi :: * Analyzes the given table in the current database to generate statistics, which will be * used in query optimizations. * * Right now, it only supports Hive tables and it only updates the size of a Hive table * in the Hive metastore. */ -@DeveloperApi +private[hive] case class AnalyzeTable(tableName: String) extends RunnableCommand { override def run(sqlContext: SQLContext) = { @@ -47,10 +45,9 @@ case class AnalyzeTable(tableName: String) extends RunnableCommand { } /** - * :: DeveloperApi :: * Drops a table from the metastore and removes it if it is cached. */ -@DeveloperApi +private[hive] case class DropTable( tableName: String, ifExists: Boolean) extends RunnableCommand { @@ -75,10 +72,7 @@ case class DropTable( } } -/** - * :: DeveloperApi :: - */ -@DeveloperApi +private[hive] case class AddJar(path: String) extends RunnableCommand { override def run(sqlContext: SQLContext) = { @@ -89,10 +83,7 @@ case class AddJar(path: String) extends RunnableCommand { } } -/** - * :: DeveloperApi :: - */ -@DeveloperApi +private[hive] case class AddFile(path: String) extends RunnableCommand { override def run(sqlContext: SQLContext) = { @@ -103,10 +94,7 @@ case class AddFile(path: String) extends RunnableCommand { } } -/** - * :: DeveloperApi :: - */ -@DeveloperApi +private[hive] case class CreateMetastoreDataSource( tableName: String, userSpecifiedSchema: Option[StructType], @@ -146,10 +134,7 @@ case class CreateMetastoreDataSource( } } -/** - * :: DeveloperApi :: - */ -@DeveloperApi +private[hive] case class CreateMetastoreDataSourceAsSelect( tableName: String, provider: String, diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/package.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/package.scala deleted file mode 100644 index 4989c42e96..0000000000 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/package.scala +++ /dev/null @@ -1,25 +0,0 @@ -/* - * 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 - -/** - * Physical execution operators used for running queries against data stored in Hive. These - * are not intended for use by users, but are documents so that it is easier to understand - * the output of EXPLAIN queries. - */ -package object execution diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/parquet/HiveParquetSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveParquetSuite.scala index e89b4489f1..7ff5719adb 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/parquet/HiveParquetSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveParquetSuite.scala @@ -15,11 +15,12 @@ * limitations under the License. */ -package org.apache.spark.sql.parquet +package org.apache.spark.sql.hive -import org.apache.spark.sql.{SQLConf, QueryTest} import org.apache.spark.sql.catalyst.expressions.Row import org.apache.spark.sql.hive.test.TestHive +import org.apache.spark.sql.parquet.ParquetTest +import org.apache.spark.sql.{QueryTest, SQLConf} case class Cases(lower: String, UPPER: String) diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/parquet/parquetSuites.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala index 89b943f008..1904f5faef 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/parquet/parquetSuites.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala @@ -16,19 +16,20 @@ * limitations under the License. */ -package org.apache.spark.sql.parquet +package org.apache.spark.sql.hive import java.io.File import org.scalatest.BeforeAndAfterAll -import org.apache.spark.sql.{SQLConf, QueryTest} +import org.apache.spark.sql.{QueryTest, SQLConf, SaveMode} import org.apache.spark.sql.catalyst.expressions.Row import org.apache.spark.sql.execution.{ExecutedCommand, PhysicalRDD} -import org.apache.spark.sql.hive.execution.{InsertIntoHiveTable, HiveTableScan} +import org.apache.spark.sql.hive.execution.HiveTableScan import org.apache.spark.sql.hive.test.TestHive._ import org.apache.spark.sql.hive.test.TestHive.implicits._ import org.apache.spark.sql.sources.{InsertIntoDataSource, LogicalRelation} +import org.apache.spark.sql.parquet.{ParquetRelation2, ParquetTableScan} import org.apache.spark.sql.SaveMode import org.apache.spark.sql.types._ @@ -393,7 +394,7 @@ class ParquetDataSourceOffMetastoreSuite extends ParquetMetastoreSuiteBase { val df = sql("INSERT INTO TABLE test_insert_parquet SELECT a FROM jt") df.queryExecution.executedPlan match { - case insert: InsertIntoHiveTable => // OK + case insert: execution.InsertIntoHiveTable => // OK case o => fail(s"The SparkPlan should be ${classOf[InsertIntoHiveTable].getCanonicalName}. " + s"However, found ${o.toString}.") } @@ -422,7 +423,7 @@ class ParquetDataSourceOffMetastoreSuite extends ParquetMetastoreSuiteBase { val df = sql("INSERT INTO TABLE test_insert_parquet SELECT a FROM jt_array") df.queryExecution.executedPlan match { - case insert: InsertIntoHiveTable => // OK + case insert: execution.InsertIntoHiveTable => // OK case o => fail(s"The SparkPlan should be ${classOf[InsertIntoHiveTable].getCanonicalName}. " + s"However, found ${o.toString}.") } |