3950

Build # 3950

Build Type

push

jenkins

Committed by GitHub

Commit Message

<a href="https://github.com/apache/carbondata/commit/<a class=hub.com/apache/carbondata/commit/81da3d28d2dd25ecb1290c9d7065780826e140a5">81da3d28d<a href="https://github.com/apache/carbondata/commit/81da3d28d2dd25ecb1290c9d7065780826e140a5">">Merge </a><a class="double-link" href="https://github.com/apache/carbondata/commit/<a class="double-link" href="https://github.com/apache/carbondata/commit/27adf1434aea71a316f052f78745d24d6fbdd6d2">27adf1434</a>">27adf1434</a><a href="https://github.com/apache/carbondata/commit/81da3d28d2dd25ecb1290c9d7065780826e140a5"> into 188e7e4d4">188e7e4d4</a>

Run Details

64941 of 83520 relevant lines covered (77.76%)

1.02 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

97.5

/integration/spark2/src/main/scala/org/apache/spark/sql/CarbonCountStar.scala

/*
 * 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

import scala.collection.JavaConverters._

import org.apache.hadoop.fs.Path
import org.apache.hadoop.mapred.JobConf
import org.apache.hadoop.mapreduce.Job
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.{InternalRow, TableIdentifier}
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.execution.LeafExecNode
import org.apache.spark.sql.optimizer.CarbonFilters
import org.apache.spark.sql.types.StringType
import org.apache.spark.unsafe.types.UTF8String

import org.apache.carbondata.core.datastore.impl.FileFactory
import org.apache.carbondata.core.metadata.AbsoluteTableIdentifier
import org.apache.carbondata.core.metadata.schema.table.CarbonTable
import org.apache.carbondata.core.mutate.CarbonUpdateUtil
import org.apache.carbondata.core.util.ThreadLocalSessionInfo
import org.apache.carbondata.hadoop.api.{CarbonInputFormat, CarbonTableInputFormat}
import org.apache.carbondata.hadoop.util.CarbonInputFormatUtil

case class CarbonCountStar(
    attributesRaw: Seq[Attribute],
    carbonTable: CarbonTable,
    sparkSession: SparkSession,
    outUnsafeRows: Boolean = true) extends LeafExecNode {

  override def doExecute(): RDD[InternalRow] = {
    ThreadLocalSessionInfo
      .setConfigurationToCurrentThread(sparkSession.sessionState.newHadoopConf())
    val absoluteTableIdentifier = carbonTable.getAbsoluteTableIdentifier
    val (job, tableInputFormat) = createCarbonInputFormat(absoluteTableIdentifier)
    CarbonInputFormat.setQuerySegment(job.getConfiguration, carbonTable)

    // get row count
    val rowCount = CarbonUpdateUtil.getRowCount(
      tableInputFormat.getBlockRowCount(
        job,
        carbonTable,
        CarbonFilters.getPartitions(
          Seq.empty,
          sparkSession,
          TableIdentifier(
            carbonTable.getTableName,
            Some(carbonTable.getDatabaseName))).map(_.asJava).orNull, false),
      carbonTable)
    val valueRaw =
      attributesRaw.head.dataType match {
        case StringType => Seq(UTF8String.fromString(Long.box(rowCount).toString)).toArray
          .asInstanceOf[Array[Any]]
        case _ => Seq(Long.box(rowCount)).toArray.asInstanceOf[Array[Any]]
      }
    val value = new GenericInternalRow(valueRaw)
    val unsafeProjection = UnsafeProjection.create(output.map(_.dataType).toArray)
    val row = if (outUnsafeRows) unsafeProjection(value) else value
    sparkContext.parallelize(Seq(row))
  }

  override def output: Seq[Attribute] = {
    attributesRaw
  }

  private def createCarbonInputFormat(absoluteTableIdentifier: AbsoluteTableIdentifier
  ): (Job, CarbonTableInputFormat[Array[Object]]) = {
    val carbonInputFormat = new CarbonTableInputFormat[Array[Object]]()
    val jobConf: JobConf = new JobConf(FileFactory.getConfiguration)
    SparkHadoopUtil.get.addCredentials(jobConf)
    CarbonInputFormat.setTableInfo(jobConf, carbonTable.getTableInfo)
    val job = new Job(jobConf)
    FileInputFormat.addInputPath(job, new Path(absoluteTableIdentifier.getTablePath))
    CarbonInputFormat
      .setTransactionalTable(job.getConfiguration,
        carbonTable.getTableInfo.isTransactionalTable)
    CarbonInputFormatUtil.setDataMapJobIfConfigured(job.getConfiguration)
    (job, carbonInputFormat)
  }
}

1	/*
2	* Licensed to the Apache Software Foundation (ASF) under one or more
3	* contributor license agreements. See the NOTICE file distributed with
4	* this work for additional information regarding copyright ownership.
5	* The ASF licenses this file to You under the Apache License, Version 2.0
6	* (the "License"); you may not use this file except in compliance with
7	* the License. You may obtain a copy of the License at
8	*
9	* http://www.apache.org/licenses/LICENSE-2.0
10	*
11	* Unless required by applicable law or agreed to in writing, software
12	* distributed under the License is distributed on an "AS IS" BASIS,
13	* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14	* See the License for the specific language governing permissions and
15	* limitations under the License.
16	*/
17
18	package org.apache.spark.sql
19
20	import scala.collection.JavaConverters._
21
22	import org.apache.hadoop.fs.Path
23	import org.apache.hadoop.mapred.JobConf
24	import org.apache.hadoop.mapreduce.Job
25	import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
26	import org.apache.spark.deploy.SparkHadoopUtil
27	import org.apache.spark.rdd.RDD
28	import org.apache.spark.sql.catalyst.{InternalRow, TableIdentifier}
29	import org.apache.spark.sql.catalyst.expressions._
30	import org.apache.spark.sql.execution.LeafExecNode
31	import org.apache.spark.sql.optimizer.CarbonFilters
32	import org.apache.spark.sql.types.StringType
33	import org.apache.spark.unsafe.types.UTF8String
34
35	import org.apache.carbondata.core.datastore.impl.FileFactory
36	import org.apache.carbondata.core.metadata.AbsoluteTableIdentifier
37	import org.apache.carbondata.core.metadata.schema.table.CarbonTable
38	import org.apache.carbondata.core.mutate.CarbonUpdateUtil
39	import org.apache.carbondata.core.util.ThreadLocalSessionInfo
40	import org.apache.carbondata.hadoop.api.{CarbonInputFormat, CarbonTableInputFormat}
41	import org.apache.carbondata.hadoop.util.CarbonInputFormatUtil
42
43	case class CarbonCountStar(	2✔
44	attributesRaw: Seq[Attribute],	2✔
45	carbonTable: CarbonTable,	2✔
46	sparkSession: SparkSession,	2✔
47	outUnsafeRows: Boolean = true) extends LeafExecNode {	2✔
48
49	override def doExecute(): RDD[InternalRow] = {
50	ThreadLocalSessionInfo
51	.setConfigurationToCurrentThread(sparkSession.sessionState.newHadoopConf())	2✔
52	val absoluteTableIdentifier = carbonTable.getAbsoluteTableIdentifier	2✔
53	val (job, tableInputFormat) = createCarbonInputFormat(absoluteTableIdentifier)	2✔
54	CarbonInputFormat.setQuerySegment(job.getConfiguration, carbonTable)	2✔
55
56	// get row count
57	val rowCount = CarbonUpdateUtil.getRowCount(	2✔
58	tableInputFormat.getBlockRowCount(	2✔
59	job,	2✔
60	carbonTable,	2✔
61	CarbonFilters.getPartitions(	2✔
62	Seq.empty,	2✔
63	sparkSession,	2✔
64	TableIdentifier(	2✔
65	carbonTable.getTableName,	2✔
66	Some(carbonTable.getDatabaseName))).map(_.asJava).orNull, false),	2✔
67	carbonTable)	2✔
68	val valueRaw =	2✔
69	attributesRaw.head.dataType match {	2✔
70	case StringType => Seq(UTF8String.fromString(Long.box(rowCount).toString)).toArray	2✔
71	.asInstanceOf[Array[Any]]	×
72	case _ => Seq(Long.box(rowCount)).toArray.asInstanceOf[Array[Any]]	2✔
73	}
74	val value = new GenericInternalRow(valueRaw)	2✔
75	val unsafeProjection = UnsafeProjection.create(output.map(_.dataType).toArray)	2✔
76	val row = if (outUnsafeRows) unsafeProjection(value) else value	2✔
77	sparkContext.parallelize(Seq(row))	2✔
78	}
79
80	override def output: Seq[Attribute] = {
81	attributesRaw	2✔
82	}
83
84	private def createCarbonInputFormat(absoluteTableIdentifier: AbsoluteTableIdentifier
85	): (Job, CarbonTableInputFormat[Array[Object]]) = {
86	val carbonInputFormat = new CarbonTableInputFormat[Array[Object]]()	2✔
87	val jobConf: JobConf = new JobConf(FileFactory.getConfiguration)	2✔
88	SparkHadoopUtil.get.addCredentials(jobConf)	2✔
89	CarbonInputFormat.setTableInfo(jobConf, carbonTable.getTableInfo)	2✔
90	val job = new Job(jobConf)	2✔
91	FileInputFormat.addInputPath(job, new Path(absoluteTableIdentifier.getTablePath))	2✔
92	CarbonInputFormat
93	.setTransactionalTable(job.getConfiguration,	2✔
94	carbonTable.getTableInfo.isTransactionalTable)	2✔
95	CarbonInputFormatUtil.setDataMapJobIfConfigured(job.getConfiguration)	2✔
96	(job, carbonInputFormat)	2✔
97	}
98	}

apache / carbondata / 3950

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous