diff options
author | jiangxingbo <jiangxb1987@gmail.com> | 2017-03-06 12:35:03 -0800 |
---|---|---|
committer | Xiao Li <gatorsmile@gmail.com> | 2017-03-06 12:35:03 -0800 |
commit | 9991c2dad6d09d77d5a61e4c4dcd1770e5d984d4 (patch) | |
tree | 364cd2f6f6ce57106fc3433057b5944cc559eaf5 | |
parent | 12bf832407eaaed90d7c599522457cb36b303b6c (diff) | |
download | spark-9991c2dad6d09d77d5a61e4c4dcd1770e5d984d4.tar.gz spark-9991c2dad6d09d77d5a61e4c4dcd1770e5d984d4.tar.bz2 spark-9991c2dad6d09d77d5a61e4c4dcd1770e5d984d4.zip |
[SPARK-19211][SQL] Explicitly prevent Insert into View or Create View As Insert
## What changes were proposed in this pull request?
Currently we don't explicitly forbid the following behaviors:
1. The statement CREATE VIEW AS INSERT INTO throws the following exception:
```
scala> spark.sql("CREATE VIEW testView AS INSERT INTO tab VALUES (1, \"a\")")
org.apache.spark.sql.AnalysisException: org.apache.hadoop.hive.ql.metadata.HiveException: org.apache.hadoop.hive.ql.metadata.HiveException: at least one column must be specified for the table;
scala> spark.sql("CREATE VIEW testView(a, b) AS INSERT INTO tab VALUES (1, \"a\")")
org.apache.spark.sql.AnalysisException: The number of columns produced by the SELECT clause (num: `0`) does not match the number of column names specified by CREATE VIEW (num: `2`).;
```
2. The statement INSERT INTO view VALUES throws the following exception from checkAnalysis:
```
scala> spark.sql("INSERT INTO testView VALUES (1, \"a\")")
org.apache.spark.sql.AnalysisException: Inserting into an RDD-based table is not allowed.;;
'InsertIntoTable View (`default`.`testView`, [a#16,b#17]), false, false
+- LocalRelation [col1#14, col2#15]
```
After this PR, the behavior changes to:
```
scala> spark.sql("CREATE VIEW testView AS INSERT INTO tab VALUES (1, \"a\")")
org.apache.spark.sql.catalyst.parser.ParseException: Operation not allowed: CREATE VIEW ... AS INSERT INTO;
scala> spark.sql("CREATE VIEW testView(a, b) AS INSERT INTO tab VALUES (1, \"a\")")
org.apache.spark.sql.catalyst.parser.ParseException: Operation not allowed: CREATE VIEW ... AS INSERT INTO;
scala> spark.sql("INSERT INTO testView VALUES (1, \"a\")")
org.apache.spark.sql.AnalysisException: `default`.`testView` is a view, inserting into a view is not allowed;
```
## How was this patch tested?
Add a new test case in `SparkSqlParserSuite`;
Update the corresponding test case in `SQLViewSuite`.
Author: jiangxingbo <jiangxb1987@gmail.com>
Closes #17125 from jiangxb1987/insert-with-view.
4 files changed, 26 insertions, 2 deletions
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala index 2f8489de6b..ffa5aed30e 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala @@ -606,7 +606,11 @@ class Analyzer( def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators { case i @ InsertIntoTable(u: UnresolvedRelation, parts, child, _, _) if child.resolved => - i.copy(table = EliminateSubqueryAliases(lookupTableFromCatalog(u))) + lookupTableFromCatalog(u).canonicalized match { + case v: View => + u.failAnalysis(s"Inserting into a view is not allowed. View: ${v.desc.identifier}.") + case other => i.copy(table = other) + } case u: UnresolvedRelation => resolveRelation(u) } diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala index c106163741..00d1d6d270 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala @@ -1331,6 +1331,15 @@ class SparkSqlAstBuilder(conf: SQLConf) extends AstBuilder { if (ctx.identifierList != null) { operationNotAllowed("CREATE VIEW ... PARTITIONED ON", ctx) } else { + // CREATE VIEW ... AS INSERT INTO is not allowed. + ctx.query.queryNoWith match { + case s: SingleInsertQueryContext if s.insertInto != null => + operationNotAllowed("CREATE VIEW ... AS INSERT INTO", ctx) + case _: MultiInsertQueryContext => + operationNotAllowed("CREATE VIEW ... AS FROM ... [INSERT INTO ...]+", ctx) + case _ => // OK + } + val userSpecifiedColumns = Option(ctx.identifierCommentList).toSeq.flatMap { icl => icl.identifierComment.asScala.map { ic => ic.identifier.getText -> Option(ic.STRING).map(string) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala index 2d95cb6d64..0e5a1dc6ab 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala @@ -172,7 +172,7 @@ abstract class SQLViewSuite extends QueryTest with SQLTestUtils { var e = intercept[AnalysisException] { sql(s"INSERT INTO TABLE $viewName SELECT 1") }.getMessage - assert(e.contains("Inserting into an RDD-based table is not allowed")) + assert(e.contains("Inserting into a view is not allowed. View: `default`.`testview`")) val dataFilePath = Thread.currentThread().getContextClassLoader.getResource("data/files/employee.dat") diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/SparkSqlParserSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/SparkSqlParserSuite.scala index bb6c486e88..d44a6e41cb 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/SparkSqlParserSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/SparkSqlParserSuite.scala @@ -210,6 +210,17 @@ class SparkSqlParserSuite extends PlanTest { "no viable alternative at input") } + test("create view as insert into table") { + // Single insert query + intercept("CREATE VIEW testView AS INSERT INTO jt VALUES(1, 1)", + "Operation not allowed: CREATE VIEW ... AS INSERT INTO") + + // Multi insert query + intercept("CREATE VIEW testView AS FROM jt INSERT INTO tbl1 SELECT * WHERE jt.id < 5 " + + "INSERT INTO tbl2 SELECT * WHERE jt.id > 4", + "Operation not allowed: CREATE VIEW ... AS FROM ... [INSERT INTO ...]+") + } + test("SPARK-17328 Fix NPE with EXPLAIN DESCRIBE TABLE") { assertEqual("describe table t", DescribeTableCommand( |