-
Notifications
You must be signed in to change notification settings - Fork 703
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[CARBONDATA-863] Support creation and deletion of dictionary files th…
…rough RDD during alter add and drop This closes #733
- Loading branch information
Showing
5 changed files
with
286 additions
and
74 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
110 changes: 110 additions & 0 deletions
110
.../spark-common/src/main/scala/org/apache/carbondata/spark/rdd/AlterTableAddColumnRDD.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 +1,110 @@ | ||
| /* | ||
| * 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.carbondata.spark.rdd | ||
|
|
||
| import org.apache.spark.{Partition, SparkContext, TaskContext} | ||
| import org.apache.spark.rdd.RDD | ||
| import org.apache.spark.sql.execution.command.AlterTableAddColumnsModel | ||
|
|
||
| import org.apache.carbondata.common.logging.LogServiceFactory | ||
| import org.apache.carbondata.core.constants.CarbonCommonConstants | ||
| import org.apache.carbondata.core.metadata.CarbonTableIdentifier | ||
| import org.apache.carbondata.core.metadata.encoder.Encoding | ||
| import org.apache.carbondata.core.metadata.schema.table.column.ColumnSchema | ||
| import org.apache.carbondata.core.util.path.CarbonStorePath | ||
| import org.apache.carbondata.spark.util.GlobalDictionaryUtil | ||
|
|
||
| /** | ||
| * This is a partitioner class for dividing the newly added columns into partitions | ||
| * | ||
| * @param rddId | ||
| * @param idx | ||
| * @param schema | ||
| */ | ||
| class AddColumnPartition(rddId: Int, idx: Int, schema: ColumnSchema) extends Partition { | ||
| override def index: Int = idx | ||
|
|
||
| override def hashCode(): Int = 41 * (41 + rddId) + idx | ||
|
|
||
| val columnSchema = schema | ||
| } | ||
|
|
||
| /** | ||
| * This class is aimed at generating dictionary file for the newly added columns | ||
| */ | ||
| class AlterTableAddColumnRDD[K, V](sc: SparkContext, | ||
| @transient newColumns: Seq[ColumnSchema], | ||
| alterTableModel: AlterTableAddColumnsModel, | ||
| carbonTableIdentifier: CarbonTableIdentifier, | ||
| carbonStorePath: String) extends RDD[(Int, String)](sc, Nil) { | ||
|
|
||
| override def getPartitions: Array[Partition] = { | ||
| newColumns.zipWithIndex.map { column => | ||
| new DropColumnPartition(id, column._2, column._1) | ||
| }.toArray | ||
| } | ||
|
|
||
| override def compute(split: Partition, | ||
| context: TaskContext): Iterator[(Int, String)] = { | ||
| val LOGGER = LogServiceFactory.getLogService(this.getClass.getName) | ||
| val status = CarbonCommonConstants.STORE_LOADSTATUS_SUCCESS | ||
| val iter = new Iterator[(Int, String)] { | ||
| try { | ||
| val columnSchema = split.asInstanceOf[DropColumnPartition].columnSchema | ||
| // create dictionary file if it is a dictionary column | ||
| if (columnSchema.hasEncoding(Encoding.DICTIONARY) && | ||
| !columnSchema.hasEncoding(Encoding.DIRECT_DICTIONARY)) { | ||
| val carbonTablePath = CarbonStorePath | ||
| .getCarbonTablePath(carbonStorePath, carbonTableIdentifier) | ||
| var rawData: String = null | ||
| if (null != columnSchema.getDefaultValue) { | ||
| rawData = new String(columnSchema.getDefaultValue, | ||
| CarbonCommonConstants.DEFAULT_CHARSET_CLASS) | ||
| } | ||
| GlobalDictionaryUtil | ||
| .loadDefaultDictionaryValueForNewColumn(carbonTablePath, | ||
| columnSchema, | ||
| carbonTableIdentifier, | ||
| carbonStorePath, | ||
| rawData) | ||
| } | ||
| } catch { | ||
| case ex: Exception => | ||
| throw ex | ||
| } | ||
|
|
||
| var finished = false | ||
|
|
||
| override def hasNext: Boolean = { | ||
|
|
||
| if (!finished) { | ||
| finished = true | ||
| finished | ||
| } else { | ||
| !finished | ||
| } | ||
| } | ||
|
|
||
| override def next(): (Int, String) = { | ||
| (split.index, status) | ||
| } | ||
| } | ||
| iter | ||
| } | ||
|
|
||
| } |
96 changes: 96 additions & 0 deletions
96
...spark-common/src/main/scala/org/apache/carbondata/spark/rdd/AlterTableDropColumnRDD.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 +1,96 @@ | ||
| /* | ||
| * 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.carbondata.spark.rdd | ||
|
|
||
| import org.apache.spark.{Partition, SparkContext, TaskContext} | ||
| import org.apache.spark.rdd.RDD | ||
|
|
||
| import org.apache.carbondata.common.logging.LogServiceFactory | ||
| import org.apache.carbondata.core.cache.dictionary.ManageDictionary | ||
| import org.apache.carbondata.core.constants.CarbonCommonConstants | ||
| import org.apache.carbondata.core.metadata.CarbonTableIdentifier | ||
| import org.apache.carbondata.core.metadata.encoder.Encoding | ||
| import org.apache.carbondata.core.metadata.schema.table.column.ColumnSchema | ||
|
|
||
| /** | ||
| * This is a partitioner class for dividing the newly added columns into partitions | ||
| * | ||
| * @param rddId | ||
| * @param idx | ||
| * @param schema | ||
| */ | ||
| class DropColumnPartition(rddId: Int, idx: Int, schema: ColumnSchema) extends Partition { | ||
| override def index: Int = idx | ||
|
|
||
| override def hashCode(): Int = 41 * (41 + rddId) + idx | ||
|
|
||
| val columnSchema = schema | ||
| } | ||
|
|
||
| /** | ||
| * This class is aimed at generating dictionary file for the newly added columns | ||
| */ | ||
| class AlterTableDropColumnRDD[K, V](sc: SparkContext, | ||
| @transient newColumns: Seq[ColumnSchema], | ||
| carbonTableIdentifier: CarbonTableIdentifier, | ||
| carbonStorePath: String) extends RDD[(Int, String)](sc, Nil) { | ||
|
|
||
| override def getPartitions: Array[Partition] = { | ||
| newColumns.zipWithIndex.map { column => | ||
| new DropColumnPartition(id, column._2, column._1) | ||
| }.toArray | ||
| } | ||
|
|
||
| override def compute(split: Partition, | ||
| context: TaskContext): Iterator[(Int, String)] = { | ||
| val LOGGER = LogServiceFactory.getLogService(this.getClass.getName) | ||
| val status = CarbonCommonConstants.STORE_LOADSTATUS_SUCCESS | ||
| val iter = new Iterator[(Int, String)] { | ||
| try { | ||
| val columnSchema = split.asInstanceOf[DropColumnPartition].columnSchema | ||
| if (columnSchema.hasEncoding(Encoding.DICTIONARY) && | ||
| !columnSchema.hasEncoding(Encoding.DIRECT_DICTIONARY)) { | ||
| ManageDictionary | ||
| .deleteDictionaryFileAndCache(columnSchema, carbonTableIdentifier, carbonStorePath) | ||
| } | ||
| } catch { | ||
| case ex: Exception => | ||
| LOGGER.error(ex, ex.getMessage) | ||
| throw ex | ||
| } | ||
|
|
||
| var finished = false | ||
|
|
||
| override def hasNext: Boolean = { | ||
|
|
||
| if (!finished) { | ||
| finished = true | ||
| finished | ||
| } else { | ||
| !finished | ||
| } | ||
| } | ||
|
|
||
| override def next(): (Int, String) = { | ||
| (split.index, status) | ||
| } | ||
| } | ||
| iter | ||
| } | ||
|
|
||
| } |
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
Oops, something went wrong.