Skip to content

[SPARK-26176][SQL] Verify column names for CTAS with STORED AS #24075

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
sujith71955 wants to merge 4 commits into from
Closed

[SPARK-26176][SQL] Verify column names for CTAS with STORED AS #24075

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6d162fc
[SPARK-21912][SQL] Invalid column names validation is been added when…
sujith71955 Mar 12, 2019
b199894
[SPARK-21912][SQL] Verify column names for CTAS with `STORED AS
sujith71955 Mar 15, 2019
02f2c19
[SPARK-21912][SQL] Verify column names for CTAS with `STORED AS
sujith71955 Mar 18, 2019
8da74a9
[SPARK-21912][SQL] Verify column names for CTAS with `STORED AS
sujith71955 Mar 19, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/command/ddl.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -886,7 +886,8 @@ object DDLUtils {
if (serde == HiveSerDe.sourceToSerDe("orc").get.serde) {
OrcFileFormat.checkFieldNames(colNames)
} else if (serde == HiveSerDe.sourceToSerDe("parquet").get.serde ||
serde == Some("parquet.hive.serde.ParquetHiveSerDe")) {
serde == Some("parquet.hive.serde.ParquetHiveSerDe") ||
serde == Some("org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe")) {
ParquetSchemaConverter.checkFieldNames(colNames)
}
case "parquet" => ParquetSchemaConverter.checkFieldNames(colNames)
Expand Down
2 changes: 0 additions & 2 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,12 +133,10 @@ case class DataSourceAnalysis(conf: SQLConf) extends Rule[LogicalPlan] with Cast

override def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators {
case CreateTable(tableDesc, mode, None) if DDLUtils.isDatasourceTable(tableDesc) =>
DDLUtils.checkDataColNames(tableDesc)
CreateDataSourceTableCommand(tableDesc, ignoreIfExists = mode == SaveMode.Ignore)

case CreateTable(tableDesc, mode, Some(query))
if query.resolved && DDLUtils.isDatasourceTable(tableDesc) =>
DDLUtils.checkDataColNames(tableDesc.copy(schema = query.schema))
CreateDataSourceTableAsSelectCommand(tableDesc, mode, query, query.output.map(_.name))

case InsertIntoTable(l @ LogicalRelation(_: InsertableRelation, _, _, _),
Expand Down
3 changes: 3 additions & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,6 +206,8 @@ case class PreprocessTableCreation(sparkSession: SparkSession) extends Rule[Logi
val analyzedQuery = query.get
val normalizedTable = normalizeCatalogTable(analyzedQuery.schema, tableDesc)

DDLUtils.checkDataColNames(tableDesc.copy(schema = analyzedQuery.schema))

This comment was marked as resolved.

Sign in to view


val output = analyzedQuery.output
val partitionAttrs = normalizedTable.partitionColumnNames.map { partCol =>
output.find(_.name == partCol).get
Expand All @@ -219,6 +221,7 @@ case class PreprocessTableCreation(sparkSession: SparkSession) extends Rule[Logi

c.copy(tableDesc = normalizedTable, query = Some(reorderedQuery))
} else {
DDLUtils.checkDataColNames(tableDesc)
val normalizedTable = normalizeCatalogTable(tableDesc.schema, tableDesc)

val partitionSchema = normalizedTable.partitionColumnNames.map { partCol =>
Expand Down
5 changes: 2 additions & 3 deletions sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,11 +151,9 @@ object HiveAnalysis extends Rule[LogicalPlan] {
ifPartitionNotExists, query.output.map(_.name))

case CreateTable(tableDesc, mode, None) if DDLUtils.isHiveTable(tableDesc) =>
DDLUtils.checkDataColNames(tableDesc)
CreateTableCommand(tableDesc, ignoreIfExists = mode == SaveMode.Ignore)

case CreateTable(tableDesc, mode, Some(query)) if DDLUtils.isHiveTable(tableDesc) =>
DDLUtils.checkDataColNames(tableDesc)
CreateHiveTableAsSelectCommand(tableDesc, query, query.output.map(_.name), mode)

case InsertIntoDir(isLocal, storage, provider, child, overwrite)
Expand Down Expand Up @@ -210,7 +208,8 @@ case class RelationConversions(
case CreateTable(tableDesc, mode, Some(query))
if DDLUtils.isHiveTable(tableDesc) && tableDesc.partitionColumnNames.isEmpty &&
isConvertible(tableDesc) && SQLConf.get.getConf(HiveUtils.CONVERT_METASTORE_CTAS) =>
DDLUtils.checkDataColNames(tableDesc)
// validation is required to be done here before relation conversion.
DDLUtils.checkDataColNames(tableDesc.copy(schema = query.schema))
Copy link
Copy Markdown
Contributor

@cloud-fan cloud-fan Mar 18, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we need to call it here?

OptimizedCreateHiveTableAsSelectCommand(
tableDesc, query, query.output.map(_.name), mode)
}
Expand Down
5 changes: 5 additions & 0 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2163,6 +2163,11 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
}.getMessage
assert(m.contains(s"contains invalid character(s)"))

val m1 = intercept[AnalysisException] {
sql(s"CREATE TABLE t21912 STORED AS $source AS SELECT 1 `col$name`")
}.getMessage
assert(m1.contains(s"contains invalid character(s)"))

val m2 = intercept[AnalysisException] {
sql(s"CREATE TABLE t21912 USING $source AS SELECT 1 `col$name`")
}.getMessage
Expand Down