diff options
author | Jacky Li <jacky.likun@huawei.com> | 2015-05-08 15:25:54 -0700 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2015-05-08 15:25:54 -0700 |
commit | 6dad76e5eba3c2925bfc9d142f31f7c2dc649886 (patch) | |
tree | 264c07242b5a7b555a7f58b14c2361f2df49db1d /sql/hive | |
parent | 90527f560462cc2d693176bd961b02767e460e06 (diff) | |
download | spark-6dad76e5eba3c2925bfc9d142f31f7c2dc649886.tar.gz spark-6dad76e5eba3c2925bfc9d142f31f7c2dc649886.tar.bz2 spark-6dad76e5eba3c2925bfc9d142f31f7c2dc649886.zip |
[SPARK-4699] [SQL] Make caseSensitive configurable in spark sql analyzer
based on #3558
Author: Jacky Li <jacky.likun@huawei.com>
Author: wangfei <wangfei1@huawei.com>
Author: scwf <wangfei1@huawei.com>
Closes #5806 from scwf/case and squashes the following commits:
cd51712 [wangfei] fix compile
d4b724f [wangfei] address michael's comment
af512c7 [wangfei] fix conflicts
4ef1be7 [wangfei] fix conflicts
269cf21 [scwf] fix conflicts
b73df6c [scwf] style issue
9e11752 [scwf] improve SimpleCatalystConf
b35529e [scwf] minor style
a3f7659 [scwf] remove unsed imports
2a56515 [scwf] fix conflicts
6db4bf5 [scwf] also fix for HiveContext
7fc4a98 [scwf] fix test case
d5a9933 [wangfei] fix style
eee75ba [wangfei] fix EmptyConf
6ef31cf [wangfei] revert pom changes
5d7c456 [wangfei] set CASE_SENSITIVE false in TestHive
966e719 [wangfei] set CASE_SENSITIVE false in hivecontext
fd30e25 [wangfei] added override
69b3b70 [wangfei] fix AnalysisSuite
5472b08 [wangfei] fix compile issue
56034ca [wangfei] fix conflicts and improve for catalystconf
664d1e9 [Jacky Li] Merge branch 'master' of https://github.com/apache/spark into case
12eca9a [Jacky Li] solve conflict with master
39e369c [Jacky Li] fix confilct after DataFrame PR
dee56e9 [Jacky Li] fix test case failure
05b09a3 [Jacky Li] fix conflict base on the latest master branch
73c16b1 [Jacky Li] fix bug in sql/hive
9bf4cc7 [Jacky Li] fix bug in catalyst
005c56d [Jacky Li] make SQLContext caseSensitivity configurable
6332e0f [Jacky Li] fix bug
fcbf0d9 [Jacky Li] fix scalastyle check
e7bca31 [Jacky Li] make caseSensitive configuration in Analyzer and Catalog
91b1b96 [Jacky Li] make caseSensitive configurable in Analyzer
f57f15c [Jacky Li] add testcase
578d167 [Jacky Li] make caseSensitive configurable
Diffstat (limited to 'sql/hive')
6 files changed, 28 insertions, 28 deletions
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala index 538c6c7f0a..3bab648e31 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala @@ -46,6 +46,7 @@ import org.apache.spark.sql.execution.{ExecutedCommand, ExtractPythonUdfs, Query import org.apache.spark.sql.hive.client._ import org.apache.spark.sql.hive.execution.{DescribeHiveTableCommand, HiveNativeCommand} import org.apache.spark.sql.sources.{DDLParser, DataSourceStrategy} +import org.apache.spark.sql.catalyst.CatalystConf import org.apache.spark.sql.types._ import org.apache.spark.util.Utils @@ -329,7 +330,7 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) { /* An analyzer that uses the Hive metastore. */ @transient override protected[sql] lazy val analyzer = - new Analyzer(catalog, functionRegistry, caseSensitive = false) { + new Analyzer(catalog, functionRegistry, conf) { override val extendedResolutionRules = catalog.ParquetConversions :: catalog.CreateTables :: @@ -350,6 +351,8 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) { protected[hive] class SQLSession extends super.SQLSession { protected[sql] override lazy val conf: SQLConf = new SQLConf { override def dialect: String = getConf(SQLConf.DIALECT, "hiveql") + override def caseSensitiveAnalysis: Boolean = + getConf(SQLConf.CASE_SENSITIVE, "false").toBoolean } /** 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 8fcdf3d0ab..f5398605bc 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 @@ -17,26 +17,18 @@ package org.apache.spark.sql.hive -import java.io.IOException -import java.util.{List => JList} - import com.google.common.base.Objects import com.google.common.cache.{CacheBuilder, CacheLoader, LoadingCache} import org.apache.hadoop.fs.Path -import org.apache.hadoop.hive.metastore.api.{FieldSchema, Partition => TPartition, Table => TTable} -import org.apache.hadoop.hive.metastore.{TableType, Warehouse} +import org.apache.hadoop.hive.metastore.api.FieldSchema +import org.apache.hadoop.hive.metastore.Warehouse import org.apache.hadoop.hive.ql.metadata._ -import org.apache.hadoop.hive.ql.plan.CreateTableDesc -import org.apache.hadoop.hive.serde.serdeConstants -import org.apache.hadoop.hive.serde2.`lazy`.LazySimpleSerDe -import org.apache.hadoop.hive.serde2.{Deserializer, SerDeException} -import org.apache.hadoop.util.ReflectionUtils +import org.apache.hadoop.hive.serde2.Deserializer import org.apache.spark.Logging -import org.apache.spark.sql.hive.client.IsolatedClientLoader import org.apache.spark.sql.{SaveMode, AnalysisException, SQLContext} -import org.apache.spark.sql.catalyst.analysis.{MultiInstanceRelation, NoSuchTableException, Catalog, OverrideCatalog} +import org.apache.spark.sql.catalyst.analysis.{MultiInstanceRelation, Catalog, OverrideCatalog} import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.catalyst.planning.PhysicalOperation import org.apache.spark.sql.catalyst.plans.logical @@ -44,7 +36,7 @@ import org.apache.spark.sql.catalyst.plans.logical._ import org.apache.spark.sql.catalyst.rules._ import org.apache.spark.sql.hive.client._ import org.apache.spark.sql.parquet.{ParquetRelation2, Partition => ParquetPartition, PartitionSpec} -import org.apache.spark.sql.sources.{CreateTableUsingAsSelect, DDLParser, LogicalRelation, ResolvedDataSource} +import org.apache.spark.sql.sources.{CreateTableUsingAsSelect, LogicalRelation, ResolvedDataSource} import org.apache.spark.sql.types._ import org.apache.spark.util.Utils @@ -54,7 +46,7 @@ import scala.collection.JavaConversions._ private[hive] class HiveMetastoreCatalog(val client: ClientInterface, hive: HiveContext) extends Catalog with Logging { - import org.apache.spark.sql.hive.HiveMetastoreTypes._ + val conf = hive.conf /** Usages should lock on `this`. */ protected[hive] lazy val hiveWarehouse = new Warehouse(hive.hiveconf) @@ -148,7 +140,7 @@ private[hive] class HiveMetastoreCatalog(val client: ClientInterface, hive: Hive val tableProperties = new scala.collection.mutable.HashMap[String, String] tableProperties.put("spark.sql.sources.provider", provider) if (userSpecifiedSchema.isDefined) { - val threshold = hive.conf.schemaStringLengthThreshold + val threshold = conf.schemaStringLengthThreshold val schemaJsonString = userSpecifiedSchema.get.json // Split the JSON string. val parts = schemaJsonString.grouped(threshold).toSeq @@ -355,7 +347,7 @@ private[hive] class HiveMetastoreCatalog(val client: ClientInterface, hive: Hive // Inserting into partitioned table is not supported in Parquet data source (yet). if !relation.hiveQlTable.isPartitioned && hive.convertMetastoreParquet && - hive.conf.parquetUseDataSourceApi && + conf.parquetUseDataSourceApi && relation.tableDesc.getSerdeClassName.toLowerCase.contains("parquet") => val parquetRelation = convertToParquetRelation(relation) val attributedRewrites = relation.output.zip(parquetRelation.output) @@ -366,7 +358,7 @@ private[hive] class HiveMetastoreCatalog(val client: ClientInterface, hive: Hive // Inserting into partitioned table is not supported in Parquet data source (yet). if !relation.hiveQlTable.isPartitioned && hive.convertMetastoreParquet && - hive.conf.parquetUseDataSourceApi && + conf.parquetUseDataSourceApi && relation.tableDesc.getSerdeClassName.toLowerCase.contains("parquet") => val parquetRelation = convertToParquetRelation(relation) val attributedRewrites = relation.output.zip(parquetRelation.output) @@ -375,7 +367,7 @@ private[hive] class HiveMetastoreCatalog(val client: ClientInterface, hive: Hive // Read path case p @ PhysicalOperation(_, _, relation: MetastoreRelation) if hive.convertMetastoreParquet && - hive.conf.parquetUseDataSourceApi && + conf.parquetUseDataSourceApi && relation.tableDesc.getSerdeClassName.toLowerCase.contains("parquet") => val parquetRelation = convertToParquetRelation(relation) val attributedRewrites = relation.output.zip(parquetRelation.output) @@ -435,7 +427,7 @@ private[hive] class HiveMetastoreCatalog(val client: ClientInterface, hive: Hive val mode = if (allowExisting) SaveMode.Ignore else SaveMode.ErrorIfExists CreateTableUsingAsSelect( desc.name, - hive.conf.defaultDataSourceName, + conf.defaultDataSourceName, temporary = false, mode, options = Map.empty[String, String], @@ -464,7 +456,7 @@ private[hive] class HiveMetastoreCatalog(val client: ClientInterface, hive: Hive val mode = if (allowExisting) SaveMode.Ignore else SaveMode.ErrorIfExists CreateTableUsingAsSelect( tblName, - hive.conf.defaultDataSourceName, + conf.defaultDataSourceName, temporary = false, mode, options = Map.empty[String, String], diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala index 1f40a5340c..1598d4bd47 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala @@ -26,15 +26,16 @@ import org.apache.hadoop.hive.ql.io.avro.{AvroContainerInputFormat, AvroContaine import org.apache.hadoop.hive.ql.metadata.Table import org.apache.hadoop.hive.ql.parse.VariableSubstitution import org.apache.hadoop.hive.ql.processors._ -import org.apache.hadoop.hive.serde2.RegexSerDe import org.apache.hadoop.hive.serde2.`lazy`.LazySimpleSerDe import org.apache.hadoop.hive.serde2.avro.AvroSerDe -import org.apache.spark.sql.SQLConf + +import org.apache.spark.sql.catalyst.CatalystConf import org.apache.spark.sql.catalyst.analysis._ import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan import org.apache.spark.sql.execution.CacheTableCommand import org.apache.spark.sql.hive._ import org.apache.spark.sql.hive.execution.HiveNativeCommand +import org.apache.spark.sql.SQLConf import org.apache.spark.util.Utils import org.apache.spark.{SparkConf, SparkContext} @@ -103,10 +104,11 @@ class TestHiveContext(sc: SparkContext) extends HiveContext(sc) { /** Fewer partitions to speed up testing. */ protected[sql] override lazy val conf: SQLConf = new SQLConf { override def numShufflePartitions: Int = getConf(SQLConf.SHUFFLE_PARTITIONS, "5").toInt - // TODO as in unit test, conf.clear() probably be called, all of the value will be cleared. // The super.getConf(SQLConf.DIALECT) is "sql" by default, we need to set it as "hiveql" override def dialect: String = super.getConf(SQLConf.DIALECT, "hiveql") + override def caseSensitiveAnalysis: Boolean = + getConf(SQLConf.CASE_SENSITIVE, "false").toBoolean } } diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala index 7d728fe87b..2c9c08a9f3 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala @@ -29,7 +29,6 @@ import org.apache.hadoop.hive.conf.HiveConf.ConfVars import org.apache.spark.{SparkFiles, SparkException} import org.apache.spark.sql.{AnalysisException, DataFrame, Row} import org.apache.spark.sql.catalyst.plans.logical.Project -import org.apache.spark.sql.functions._ import org.apache.spark.sql.hive._ import org.apache.spark.sql.hive.test.TestHive import org.apache.spark.sql.hive.test.TestHive._ diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala index c605f10175..1353802604 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala @@ -493,6 +493,12 @@ class SQLQuerySuite extends QueryTest { } } + test("SPARK-4699 HiveContext should be case insensitive by default") { + checkAnswer( + sql("SELECT KEY FROM Src ORDER BY value"), + sql("SELECT key FROM src ORDER BY value").collect().toSeq) + } + test("SPARK-5284 Insert into Hive throws NPE when a inner complex type field has a null value") { val schema = StructType( StructField("s", diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala index d5dd0bf58e..bf1121ddf0 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala @@ -21,14 +21,12 @@ import java.io.File import org.scalatest.BeforeAndAfterAll -import org.apache.spark.sql.{QueryTest, SQLConf, SaveMode} +import org.apache.spark.sql.{QueryTest, SQLConf} import org.apache.spark.sql.catalyst.expressions.Row import org.apache.spark.sql.execution.{ExecutedCommand, PhysicalRDD} import org.apache.spark.sql.hive.execution.HiveTableScan -import org.apache.spark.sql.hive.test.TestHive import org.apache.spark.sql.hive.test.TestHive._ import org.apache.spark.sql.hive.test.TestHive.implicits._ -import org.apache.spark.sql.json.JSONRelation import org.apache.spark.sql.sources.{InsertIntoDataSource, LogicalRelation} import org.apache.spark.sql.parquet.{ParquetRelation2, ParquetTableScan} import org.apache.spark.sql.SaveMode |