Repository: spark Updated Branches: refs/heads/master c5abb3c2d -> 049f243c5
[SPARK-23490][SQL] Check storage.locationUri with existing table in CreateTable ## What changes were proposed in this pull request? For CreateTable with Append mode, we should check if `storage.locationUri` is the same with existing table in `PreprocessTableCreation` In the current code, there is only a simple exception if the `storage.locationUri` is different with existing table: `org.apache.spark.sql.AnalysisException: Table or view not found:` which can be improved. ## How was this patch tested? Unit test Author: Wang Gengliang <gengliang.w...@databricks.com> Closes #20660 from gengliangwang/locationUri. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/049f243c Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/049f243c Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/049f243c Branch: refs/heads/master Commit: 049f243c59737699fee54fdc9d65cbd7c788032a Parents: c5abb3c Author: Wang Gengliang <gengliang.w...@databricks.com> Authored: Thu Feb 22 21:49:25 2018 -0800 Committer: gatorsmile <gatorsm...@gmail.com> Committed: Thu Feb 22 21:49:25 2018 -0800 ---------------------------------------------------------------------- .../spark/sql/execution/datasources/rules.scala | 8 ++++++ .../spark/sql/execution/command/DDLSuite.scala | 29 ++++++++++++++++++++ 2 files changed, 37 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/049f243c/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala index 5cc21ee..0dea767 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala @@ -118,6 +118,14 @@ case class PreprocessTableCreation(sparkSession: SparkSession) extends Rule[Logi s"`${existingProvider.getSimpleName}`. It doesn't match the specified format " + s"`${specifiedProvider.getSimpleName}`.") } + tableDesc.storage.locationUri match { + case Some(location) if location.getPath != existingTable.location.getPath => + throw new AnalysisException( + s"The location of the existing table ${tableIdentWithDB.quotedString} is " + + s"`${existingTable.location}`. It doesn't match the specified location " + + s"`${tableDesc.location}`.") + case _ => + } if (query.schema.length != existingTable.schema.length) { throw new AnalysisException( http://git-wip-us.apache.org/repos/asf/spark/blob/049f243c/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala index f76bfd2..b800e6f 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala @@ -536,6 +536,35 @@ abstract class DDLSuite extends QueryTest with SQLTestUtils { } } + test("create table - append to a non-partitioned table created with different paths") { + import testImplicits._ + withTempDir { dir1 => + withTempDir { dir2 => + withTable("path_test") { + Seq(1L -> "a").toDF("v1", "v2") + .write + .mode(SaveMode.Append) + .format("json") + .option("path", dir1.getCanonicalPath) + .saveAsTable("path_test") + + val ex = intercept[AnalysisException] { + Seq((3L, "c")).toDF("v1", "v2") + .write + .mode(SaveMode.Append) + .format("json") + .option("path", dir2.getCanonicalPath) + .saveAsTable("path_test") + }.getMessage + assert(ex.contains("The location of the existing table `default`.`path_test`")) + + checkAnswer( + spark.table("path_test"), Row(1L, "a") :: Nil) + } + } + } + } + test("Refresh table after changing the data source table partitioning") { import testImplicits._ --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org