You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@carbondata.apache.org by qi...@apache.org on 2018/04/26 11:37:30 UTC

carbondata git commit: [HOTFIX] Remove carbon-spark2 dependency in carbon-bloom

Repository: carbondata
Updated Branches:
  refs/heads/master 21c5fb1db -> 0668e7d71


[HOTFIX] Remove carbon-spark2 dependency in carbon-bloom

This closes #2229


Project: http://git-wip-us.apache.org/repos/asf/carbondata/repo
Commit: http://git-wip-us.apache.org/repos/asf/carbondata/commit/0668e7d7
Tree: http://git-wip-us.apache.org/repos/asf/carbondata/tree/0668e7d7
Diff: http://git-wip-us.apache.org/repos/asf/carbondata/diff/0668e7d7

Branch: refs/heads/master
Commit: 0668e7d714bafc9939dd74a961e13b10bdab5494
Parents: 21c5fb1
Author: Jacky Li <ja...@qq.com>
Authored: Thu Apr 26 14:31:09 2018 +0800
Committer: QiangCai <qi...@qq.com>
Committed: Thu Apr 26 19:36:25 2018 +0800

----------------------------------------------------------------------
 datamap/bloom/pom.xml                           |   2 +-
 .../bloom/BloomCoarseGrainDataMapSuite.scala    | 127 -------------------
 integration/spark2/pom.xml                      |   6 +
 .../bloom/BloomCoarseGrainDataMapSuite.scala    | 126 ++++++++++++++++++
 4 files changed, 133 insertions(+), 128 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/carbondata/blob/0668e7d7/datamap/bloom/pom.xml
----------------------------------------------------------------------
diff --git a/datamap/bloom/pom.xml b/datamap/bloom/pom.xml
index 472df36..4ef8c0a 100644
--- a/datamap/bloom/pom.xml
+++ b/datamap/bloom/pom.xml
@@ -20,7 +20,7 @@
   <dependencies>
     <dependency>
       <groupId>org.apache.carbondata</groupId>
-      <artifactId>carbondata-spark2</artifactId>
+      <artifactId>carbondata-core</artifactId>
       <version>${project.version}</version>
     </dependency>
     <dependency>

http://git-wip-us.apache.org/repos/asf/carbondata/blob/0668e7d7/datamap/bloom/src/test/scala/org/apache/carbondata/datamap/bloom/BloomCoarseGrainDataMapSuite.scala
----------------------------------------------------------------------
diff --git a/datamap/bloom/src/test/scala/org/apache/carbondata/datamap/bloom/BloomCoarseGrainDataMapSuite.scala b/datamap/bloom/src/test/scala/org/apache/carbondata/datamap/bloom/BloomCoarseGrainDataMapSuite.scala
deleted file mode 100644
index 21283fe..0000000
--- a/datamap/bloom/src/test/scala/org/apache/carbondata/datamap/bloom/BloomCoarseGrainDataMapSuite.scala
+++ /dev/null
@@ -1,127 +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.carbondata.datamap.bloom
-
-import java.io.{File, PrintWriter}
-import java.util.UUID
-
-import scala.util.Random
-
-import org.apache.spark.sql.Row
-import org.apache.spark.sql.test.util.QueryTest
-import org.scalatest.BeforeAndAfterAll
-
-class BloomCoarseGrainDataMapSuite extends QueryTest with BeforeAndAfterAll {
-  val inputFile = s"$resourcesPath/bloom_datamap_input.csv"
-  val normalTable = "carbon_normal"
-  val bloomDMSampleTable = "carbon_bloom"
-  val dataMapName = "bloom_dm"
-  val lineNum = 500000
-
-  override protected def beforeAll(): Unit = {
-    createFile(inputFile, line = lineNum, start = 0)
-    sql(s"DROP TABLE IF EXISTS $normalTable")
-    sql(s"DROP TABLE IF EXISTS $bloomDMSampleTable")
-  }
-
-  test("test bloom datamap") {
-    sql(
-      s"""
-         | CREATE TABLE $normalTable(id INT, name STRING, city STRING, age INT,
-         | s1 STRING, s2 STRING, s3 STRING, s4 STRING, s5 STRING, s6 STRING, s7 STRING, s8 STRING)
-         | STORED BY 'carbondata' TBLPROPERTIES('table_blocksize'='128')
-         |  """.stripMargin)
-    sql(
-      s"""
-         | CREATE TABLE $bloomDMSampleTable(id INT, name STRING, city STRING, age INT,
-         | s1 STRING, s2 STRING, s3 STRING, s4 STRING, s5 STRING, s6 STRING, s7 STRING, s8 STRING)
-         | STORED BY 'carbondata' TBLPROPERTIES('table_blocksize'='128')
-         |  """.stripMargin)
-    sql(
-      s"""
-         | CREATE DATAMAP $dataMapName ON TABLE $bloomDMSampleTable
-         | USING '${classOf[BloomCoarseGrainDataMapFactory].getName}'
-         | DMProperties('BLOOM_COLUMNS'='city,id', 'BLOOM_SIZE'='640000')
-      """.stripMargin)
-
-    sql(
-      s"""
-         | LOAD DATA LOCAL INPATH '$inputFile' INTO TABLE $normalTable
-         | OPTIONS('header'='false')
-       """.stripMargin)
-    sql(
-      s"""
-         | LOAD DATA LOCAL INPATH '$inputFile' INTO TABLE $bloomDMSampleTable
-         | OPTIONS('header'='false')
-       """.stripMargin)
-
-    sql(s"show datamap on table $bloomDMSampleTable").show(false)
-    sql(s"select * from $bloomDMSampleTable where city = 'city_5'").show(false)
-    sql(s"select * from $bloomDMSampleTable limit 5").show(false)
-
-    checkExistence(sql(s"show datamap on table $bloomDMSampleTable"), true, dataMapName)
-//    checkAnswer(sql(s"show datamap on table $bloomDMSampleTable"),
-//      Row(dataMapName, classOf[BloomCoarseGrainDataMapFactory].getName, "(NA)"))
-    checkAnswer(sql(s"select * from $bloomDMSampleTable where id = 1"),
-      sql(s"select * from $normalTable where id = 1"))
-    checkAnswer(sql(s"select * from $bloomDMSampleTable where id = 999"),
-      sql(s"select * from $normalTable where id = 999"))
-    checkAnswer(sql(s"select * from $bloomDMSampleTable where city = 'city_1'"),
-      sql(s"select * from $normalTable where city = 'city_1'"))
-    checkAnswer(sql(s"select * from $bloomDMSampleTable where city = 'city_999'"),
-      sql(s"select * from $normalTable where city = 'city_999'"))
-    checkAnswer(sql(s"select count(distinct id), count(distinct name), count(distinct city)," +
-                    s" count(distinct s1), count(distinct s2) from $bloomDMSampleTable"),
-      sql(s"select count(distinct id), count(distinct name), count(distinct city)," +
-          s" count(distinct s1), count(distinct s2) from $normalTable"))
-    checkAnswer(sql(s"select min(id), max(id), min(name), max(name), min(city), max(city)" +
-                    s" from $bloomDMSampleTable"),
-      sql(s"select min(id), max(id), min(name), max(name), min(city), max(city)" +
-          s" from $normalTable"))
-  }
-
-  // todo: will add more tests on bloom datamap, such as exception, delete datamap, show profiler
-
-  override protected def afterAll(): Unit = {
-    deleteFile(inputFile)
-    sql(s"DROP TABLE IF EXISTS $normalTable")
-    sql(s"DROP TABLE IF EXISTS $bloomDMSampleTable")
-  }
-
-  private def createFile(fileName: String, line: Int = 10000, start: Int = 0) = {
-    if (!new File(fileName).exists()) {
-      val write = new PrintWriter(new File(fileName))
-      for (i <- start until (start + line)) {
-        write.println(
-          s"$i,n$i,city_$i,${ Random.nextInt(80) }," +
-          s"${ UUID.randomUUID().toString },${ UUID.randomUUID().toString }," +
-          s"${ UUID.randomUUID().toString },${ UUID.randomUUID().toString }," +
-          s"${ UUID.randomUUID().toString },${ UUID.randomUUID().toString }," +
-          s"${ UUID.randomUUID().toString },${ UUID.randomUUID().toString }")
-      }
-      write.close()
-    }
-  }
-
-  private def deleteFile(fileName: String): Unit = {
-    val file = new File(fileName)
-    if (file.exists()) {
-      file.delete()
-    }
-  }
-}

http://git-wip-us.apache.org/repos/asf/carbondata/blob/0668e7d7/integration/spark2/pom.xml
----------------------------------------------------------------------
diff --git a/integration/spark2/pom.xml b/integration/spark2/pom.xml
index 2372539..1afb08f 100644
--- a/integration/spark2/pom.xml
+++ b/integration/spark2/pom.xml
@@ -55,6 +55,12 @@
       <version>${project.version}</version>
     </dependency>
     <dependency>
+      <groupId>org.apache.carbondata</groupId>
+      <artifactId>carbondata-bloom</artifactId>
+      <version>${project.version}</version>
+      <scope>test</scope>
+    </dependency>
+    <dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>
     </dependency>

http://git-wip-us.apache.org/repos/asf/carbondata/blob/0668e7d7/integration/spark2/src/test/scala/org/apache/carbondata/datamap/bloom/BloomCoarseGrainDataMapSuite.scala
----------------------------------------------------------------------
diff --git a/integration/spark2/src/test/scala/org/apache/carbondata/datamap/bloom/BloomCoarseGrainDataMapSuite.scala b/integration/spark2/src/test/scala/org/apache/carbondata/datamap/bloom/BloomCoarseGrainDataMapSuite.scala
new file mode 100644
index 0000000..33de06f
--- /dev/null
+++ b/integration/spark2/src/test/scala/org/apache/carbondata/datamap/bloom/BloomCoarseGrainDataMapSuite.scala
@@ -0,0 +1,126 @@
+/*
+ * 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.datamap.bloom
+
+import java.io.{File, PrintWriter}
+import java.util.UUID
+
+import scala.util.Random
+
+import org.apache.spark.sql.test.util.QueryTest
+import org.scalatest.BeforeAndAfterAll
+
+class BloomCoarseGrainDataMapSuite extends QueryTest with BeforeAndAfterAll {
+  val inputFile = s"$resourcesPath/bloom_datamap_input.csv"
+  val normalTable = "carbon_normal"
+  val bloomDMSampleTable = "carbon_bloom"
+  val dataMapName = "bloom_dm"
+  val lineNum = 500000
+
+  override protected def beforeAll(): Unit = {
+    createFile(inputFile, line = lineNum, start = 0)
+    sql(s"DROP TABLE IF EXISTS $normalTable")
+    sql(s"DROP TABLE IF EXISTS $bloomDMSampleTable")
+  }
+
+  test("test bloom datamap") {
+    sql(
+      s"""
+         | CREATE TABLE $normalTable(id INT, name STRING, city STRING, age INT,
+         | s1 STRING, s2 STRING, s3 STRING, s4 STRING, s5 STRING, s6 STRING, s7 STRING, s8 STRING)
+         | STORED BY 'carbondata' TBLPROPERTIES('table_blocksize'='128')
+         |  """.stripMargin)
+    sql(
+      s"""
+         | CREATE TABLE $bloomDMSampleTable(id INT, name STRING, city STRING, age INT,
+         | s1 STRING, s2 STRING, s3 STRING, s4 STRING, s5 STRING, s6 STRING, s7 STRING, s8 STRING)
+         | STORED BY 'carbondata' TBLPROPERTIES('table_blocksize'='128')
+         |  """.stripMargin)
+    sql(
+      s"""
+         | CREATE DATAMAP $dataMapName ON TABLE $bloomDMSampleTable
+         | USING '${classOf[BloomCoarseGrainDataMapFactory].getName}'
+         | DMProperties('BLOOM_COLUMNS'='city,id', 'BLOOM_SIZE'='640000')
+      """.stripMargin)
+
+    sql(
+      s"""
+         | LOAD DATA LOCAL INPATH '$inputFile' INTO TABLE $normalTable
+         | OPTIONS('header'='false')
+       """.stripMargin)
+    sql(
+      s"""
+         | LOAD DATA LOCAL INPATH '$inputFile' INTO TABLE $bloomDMSampleTable
+         | OPTIONS('header'='false')
+       """.stripMargin)
+
+    sql(s"show datamap on table $bloomDMSampleTable").show(false)
+    sql(s"select * from $bloomDMSampleTable where city = 'city_5'").show(false)
+    sql(s"select * from $bloomDMSampleTable limit 5").show(false)
+
+    checkExistence(sql(s"show datamap on table $bloomDMSampleTable"), true, dataMapName)
+//    checkAnswer(sql(s"show datamap on table $bloomDMSampleTable"),
+//      Row(dataMapName, classOf[BloomCoarseGrainDataMapFactory].getName, "(NA)"))
+    checkAnswer(sql(s"select * from $bloomDMSampleTable where id = 1"),
+      sql(s"select * from $normalTable where id = 1"))
+    checkAnswer(sql(s"select * from $bloomDMSampleTable where id = 999"),
+      sql(s"select * from $normalTable where id = 999"))
+    checkAnswer(sql(s"select * from $bloomDMSampleTable where city = 'city_1'"),
+      sql(s"select * from $normalTable where city = 'city_1'"))
+    checkAnswer(sql(s"select * from $bloomDMSampleTable where city = 'city_999'"),
+      sql(s"select * from $normalTable where city = 'city_999'"))
+    checkAnswer(sql(s"select count(distinct id), count(distinct name), count(distinct city)," +
+                    s" count(distinct s1), count(distinct s2) from $bloomDMSampleTable"),
+      sql(s"select count(distinct id), count(distinct name), count(distinct city)," +
+          s" count(distinct s1), count(distinct s2) from $normalTable"))
+    checkAnswer(sql(s"select min(id), max(id), min(name), max(name), min(city), max(city)" +
+                    s" from $bloomDMSampleTable"),
+      sql(s"select min(id), max(id), min(name), max(name), min(city), max(city)" +
+          s" from $normalTable"))
+  }
+
+  // todo: will add more tests on bloom datamap, such as exception, delete datamap, show profiler
+
+  override protected def afterAll(): Unit = {
+    deleteFile(inputFile)
+    sql(s"DROP TABLE IF EXISTS $normalTable")
+    sql(s"DROP TABLE IF EXISTS $bloomDMSampleTable")
+  }
+
+  private def createFile(fileName: String, line: Int = 10000, start: Int = 0) = {
+    if (!new File(fileName).exists()) {
+      val write = new PrintWriter(new File(fileName))
+      for (i <- start until (start + line)) {
+        write.println(
+          s"$i,n$i,city_$i,${ Random.nextInt(80) }," +
+          s"${ UUID.randomUUID().toString },${ UUID.randomUUID().toString }," +
+          s"${ UUID.randomUUID().toString },${ UUID.randomUUID().toString }," +
+          s"${ UUID.randomUUID().toString },${ UUID.randomUUID().toString }," +
+          s"${ UUID.randomUUID().toString },${ UUID.randomUUID().toString }")
+      }
+      write.close()
+    }
+  }
+
+  private def deleteFile(fileName: String): Unit = {
+    val file = new File(fileName)
+    if (file.exists()) {
+      file.delete()
+    }
+  }
+}