Skip to content
Original file line number Diff line number Diff line change
Expand Up @@ -1213,21 +1213,6 @@ class DDLParserSuite extends AnalysisTest {
"The feature is not supported: DESC TABLE COLUMN for a specific partition."))
}

test("SPARK-17328 Fix NPE with EXPLAIN DESCRIBE TABLE") {
comparePlans(parsePlan("describe t"),
DescribeRelation(
UnresolvedTableOrView(Seq("t"), "DESCRIBE TABLE", true), Map.empty, isExtended = false))
comparePlans(parsePlan("describe table t"),
DescribeRelation(
UnresolvedTableOrView(Seq("t"), "DESCRIBE TABLE", true), Map.empty, isExtended = false))
comparePlans(parsePlan("describe table extended t"),
DescribeRelation(
UnresolvedTableOrView(Seq("t"), "DESCRIBE TABLE", true), Map.empty, isExtended = true))
comparePlans(parsePlan("describe table formatted t"),
DescribeRelation(
UnresolvedTableOrView(Seq("t"), "DESCRIBE TABLE", true), Map.empty, isExtended = true))
}

test("insert table: basic append") {
Seq(
"INSERT INTO TABLE testcat.ns1.ns2.tbl SELECT * FROM source",
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ import org.apache.spark.sql.internal.{SQLConf, StaticSQLConf}
import org.apache.spark.sql.internal.SQLConf.{PARTITION_OVERWRITE_MODE, PartitionOverwriteMode, V2_SESSION_CATALOG_IMPLEMENTATION}
import org.apache.spark.sql.internal.connector.SimpleTableProvider
import org.apache.spark.sql.sources.SimpleScanSource
import org.apache.spark.sql.types.{BooleanType, LongType, MetadataBuilder, StringType, StructField, StructType}
import org.apache.spark.sql.types.{LongType, MetadataBuilder, StringType, StructField, StructType}
import org.apache.spark.sql.util.CaseInsensitiveStringMap
import org.apache.spark.unsafe.types.UTF8String
import org.apache.spark.util.Utils
Expand Down Expand Up @@ -89,71 +89,6 @@ class DataSourceV2SQLSuite
checkAnswer(spark.internalCreateDataFrame(rdd, table.schema), Seq.empty)
}

test("DescribeTable using v2 catalog") {
spark.sql("CREATE TABLE testcat.table_name (id bigint, data string)" +
" USING foo" +
" PARTITIONED BY (id)")
val descriptionDf = spark.sql("DESCRIBE TABLE testcat.table_name")
assert(descriptionDf.schema.map(field => (field.name, field.dataType)) ===
Seq(
("col_name", StringType),
("data_type", StringType),
("comment", StringType)))
val description = descriptionDf.collect()
assert(description === Seq(
Row("id", "bigint", ""),
Row("data", "string", ""),
Row("", "", ""),
Row("# Partitioning", "", ""),
Row("Part 0", "id", "")))

val e = intercept[AnalysisException] {
sql("DESCRIBE TABLE testcat.table_name PARTITION (id = 1)")
}
assert(e.message.contains("DESCRIBE does not support partition for v2 tables"))
}

test("DescribeTable with v2 catalog when table does not exist.") {
intercept[AnalysisException] {
spark.sql("DESCRIBE TABLE testcat.table_name")
}
}

test("DescribeTable extended using v2 catalog") {
spark.sql("CREATE TABLE testcat.table_name (id bigint, data string)" +
" USING foo" +
" PARTITIONED BY (id)" +
" TBLPROPERTIES ('bar'='baz', 'password' = 'password')" +
" COMMENT 'this is a test table'" +
" LOCATION 'file:/tmp/testcat/table_name'")
val descriptionDf = spark.sql("DESCRIBE TABLE EXTENDED testcat.table_name")
assert(descriptionDf.schema.map(field => (field.name, field.dataType))
=== Seq(
("col_name", StringType),
("data_type", StringType),
("comment", StringType)))
assert(descriptionDf.collect()
.map(_.toSeq)
.map(_.toArray.map(_.toString.trim)) === Array(
Array("id", "bigint", ""),
Array("data", "string", ""),
Array("", "", ""),
Array("# Partitioning", "", ""),
Array("Part 0", "id", ""),
Array("", "", ""),
Array("# Metadata Columns", "", ""),
Array("index", "int", "Metadata column used to conflict with a data column"),
Array("_partition", "string", "Partition key used to store the row"),
Array("", "", ""),
Array("# Detailed Table Information", "", ""),
Array("Name", "testcat.table_name", ""),
Array("Comment", "this is a test table", ""),
Array("Location", "file:/tmp/testcat/table_name", ""),
Array("Provider", "foo", ""),
Array(TableCatalog.PROP_OWNER.capitalize, defaultUser, ""),
Array("Table Properties", "[bar=baz,password=*********(redacted)]", "")))
}

test("Describe column for v2 catalog") {
val t = "testcat.tbl"
withTable(t) {
Expand Down Expand Up @@ -2410,49 +2345,6 @@ class DataSourceV2SQLSuite
}
}

test("SPARK-34561: drop/add columns to a dataset of `DESCRIBE TABLE`") {
val tbl = s"${catalogAndNamespace}tbl"
withTable(tbl) {
sql(s"CREATE TABLE $tbl (c0 INT) USING $v2Format")
val description = sql(s"DESCRIBE TABLE $tbl")
val noCommentDataset = description.drop("comment")
val expectedSchema = new StructType()
.add(
name = "col_name",
dataType = StringType,
nullable = false,
metadata = new MetadataBuilder().putString("comment", "name of the column").build())
.add(
name = "data_type",
dataType = StringType,
nullable = false,
metadata = new MetadataBuilder().putString("comment", "data type of the column").build())
assert(noCommentDataset.schema === expectedSchema)
val isNullDataset = noCommentDataset
.withColumn("is_null", noCommentDataset("col_name").isNull)
assert(isNullDataset.schema === expectedSchema.add("is_null", BooleanType, false))
}
}

test("SPARK-34576: drop/add columns to a dataset of `DESCRIBE COLUMN`") {
val tbl = s"${catalogAndNamespace}tbl"
withTable(tbl) {
sql(s"CREATE TABLE $tbl (c0 INT) USING $v2Format")
val description = sql(s"DESCRIBE TABLE $tbl c0")
val noCommentDataset = description.drop("info_value")
val expectedSchema = new StructType()
.add(
name = "info_name",
dataType = StringType,
nullable = false,
metadata = new MetadataBuilder().putString("comment", "name of the column info").build())
assert(noCommentDataset.schema === expectedSchema)
val isNullDataset = noCommentDataset
.withColumn("is_null", noCommentDataset("info_name").isNull)
assert(isNullDataset.schema === expectedSchema.add("is_null", BooleanType, false))
}
}

test("SPARK-34923: do not propagate metadata columns through Project") {
val t1 = s"${catalogAndNamespace}table"
withTable(t1) {
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
/*
* 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.spark.sql.execution.command

import org.apache.spark.sql.catalyst.analysis.{AnalysisTest, UnresolvedTableOrView}
import org.apache.spark.sql.catalyst.parser.CatalystSqlParser.parsePlan
import org.apache.spark.sql.catalyst.plans.logical.DescribeRelation

class DescribeTableParserSuite extends AnalysisTest {
test("SPARK-17328: Fix NPE with EXPLAIN DESCRIBE TABLE") {
comparePlans(parsePlan("describe t"),
DescribeRelation(
UnresolvedTableOrView(Seq("t"), "DESCRIBE TABLE", true), Map.empty, isExtended = false))
comparePlans(parsePlan("describe table t"),
DescribeRelation(
UnresolvedTableOrView(Seq("t"), "DESCRIBE TABLE", true), Map.empty, isExtended = false))
comparePlans(parsePlan("describe table extended t"),
DescribeRelation(
UnresolvedTableOrView(Seq("t"), "DESCRIBE TABLE", true), Map.empty, isExtended = true))
comparePlans(parsePlan("describe table formatted t"),
DescribeRelation(
UnresolvedTableOrView(Seq("t"), "DESCRIBE TABLE", true), Map.empty, isExtended = true))
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,87 @@
/*
* 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.spark.sql.execution.command

import org.apache.spark.sql.{AnalysisException, QueryTest}
import org.apache.spark.sql.types.{BooleanType, MetadataBuilder, StringType, StructType}

/**
* This base suite contains unified tests for the `DESCRIBE TABLE` command that check V1 and V2
* table catalogs. The tests that cannot run for all supported catalogs are located in more
* specific test suites:
*
* - V2 table catalog tests: `org.apache.spark.sql.execution.command.v2.DescribeTableSuite`
* - V1 table catalog tests:
* `org.apache.spark.sql.execution.command.v1.DescribeTableSuiteBase`
* - V1 In-Memory catalog: `org.apache.spark.sql.execution.command.v1.DescribeTableSuite`
* - V1 Hive External catalog:
* `org.apache.spark.sql.hive.execution.command.DescribeTableSuite`
*/
trait DescribeTableSuiteBase extends QueryTest with DDLCommandTestUtils {
override val command = "DESCRIBE TABLE"

test("DESCRIBE TABLE in a catalog when table does not exist") {
withNamespaceAndTable("ns", "table") { tbl =>
val e = intercept[AnalysisException] {
sql(s"DESCRIBE TABLE ${tbl}_non_existence")
}
assert(e.getMessage.contains(s"Table or view not found: ${tbl}_non_existence"))
}
}

test("SPARK-34561: drop/add columns to a dataset of `DESCRIBE TABLE`") {
withNamespaceAndTable("ns", "table") { tbl =>
sql(s"CREATE TABLE $tbl (c0 INT) $defaultUsing")
val description = sql(s"DESCRIBE TABLE $tbl")
val noCommentDataset = description.drop("comment")
val expectedSchema = new StructType()
.add(
name = "col_name",
dataType = StringType,
nullable = false,
metadata = new MetadataBuilder().putString("comment", "name of the column").build())
.add(
name = "data_type",
dataType = StringType,
nullable = false,
metadata = new MetadataBuilder().putString("comment", "data type of the column").build())
assert(noCommentDataset.schema === expectedSchema)
val isNullDataset = noCommentDataset
.withColumn("is_null", noCommentDataset("col_name").isNull)
assert(isNullDataset.schema === expectedSchema.add("is_null", BooleanType, false))
}
}

test("SPARK-34576: drop/add columns to a dataset of `DESCRIBE COLUMN`") {
withNamespaceAndTable("ns", "table") { tbl =>
sql(s"CREATE TABLE $tbl (c0 INT) $defaultUsing")
val description = sql(s"DESCRIBE TABLE $tbl c0")
val noCommentDataset = description.drop("info_value")
val expectedSchema = new StructType()
.add(
name = "info_name",
dataType = StringType,
nullable = false,
metadata = new MetadataBuilder().putString("comment", "name of the column info").build())
assert(noCommentDataset.schema === expectedSchema)
val isNullDataset = noCommentDataset
.withColumn("is_null", noCommentDataset("info_name").isNull)
assert(isNullDataset.schema === expectedSchema.add("is_null", BooleanType, false))
}
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,106 @@
/*
* 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.spark.sql.execution.command.v1

import org.apache.spark.sql.{AnalysisException, QueryTest, Row}
import org.apache.spark.sql.execution.command
import org.apache.spark.sql.types.StringType

/**
* This base suite contains unified tests for the `DESCRIBE TABLE` command that checks V1
* table catalogs. The tests that cannot run for all V1 catalogs are located in more
* specific test suites:
*
* - V1 In-Memory catalog: `org.apache.spark.sql.execution.command.v1.DescribeTableSuite`
* - V1 Hive External catalog:
* `org.apache.spark.sql.hive.execution.command.DescribeTableSuite`
*/
trait DescribeTableSuiteBase extends command.DescribeTableSuiteBase
with command.TestsV1AndV2Commands {

test("DESCRIBE TABLE with non-'partitioned-by' clause") {
withNamespaceAndTable("ns", "table") { tbl =>
spark.sql(s"CREATE TABLE $tbl (id bigint, data string) $defaultUsing")
val descriptionDf = spark.sql(s"DESCRIBE TABLE $tbl")
assert(descriptionDf.schema.map(field => (field.name, field.dataType)) ===
Seq(
("col_name", StringType),
("data_type", StringType),
("comment", StringType)))
QueryTest.checkAnswer(
descriptionDf,
Seq(
Row("data", "string", null),
Row("id", "bigint", null)))
}
}

test("Describing a partition is not supported") {
withNamespaceAndTable("ns", "table") { tbl =>
spark.sql(s"CREATE TABLE $tbl (id bigint, data string) $defaultUsing " +
"PARTITIONED BY (id)")
val e = intercept[AnalysisException] {
sql(s"DESCRIBE TABLE $tbl PARTITION (id = 1)")
}
assert(e.message === "Partition not found in table 'table' database 'ns':\nid -> 1")
}
}
}

/**
* The class contains tests for the `DESCRIBE TABLE` command to check V1 In-Memory
* table catalog.
*/
class DescribeTableSuite extends DescribeTableSuiteBase with CommandSuiteBase {
override def commandVersion: String = super[DescribeTableSuiteBase].commandVersion

test("DESCRIBE TABLE EXTENDED of a partitioned table") {
withNamespaceAndTable("ns", "table") { tbl =>
spark.sql(s"CREATE TABLE $tbl (id bigint, data string) $defaultUsing" +
" PARTITIONED BY (id)" +
" TBLPROPERTIES ('bar'='baz')" +
" COMMENT 'this is a test table'" +
" LOCATION 'file:/tmp/testcat/table_name'")
val descriptionDf = spark.sql(s"DESCRIBE TABLE EXTENDED $tbl")
assert(descriptionDf.schema.map(field => (field.name, field.dataType)) === Seq(
("col_name", StringType),
("data_type", StringType),
("comment", StringType)))
QueryTest.checkAnswer(
descriptionDf.filter("col_name != 'Created Time'"),
Seq(
Row("data", "string", null),
Row("id", "bigint", null),
Row("# Partition Information", "", ""),
Row("# col_name", "data_type", "comment"),
Row("id", "bigint", null),
Row("", "", ""),
Row("# Detailed Table Information", "", ""),
Row("Database", "ns", ""),
Row("Table", "table", ""),
Row("Last Access", "UNKNOWN", ""),
Row("Created By", "Spark 3.4.0-SNAPSHOT", ""),
Copy link
Contributor

Choose a reason for hiding this comment

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

we should filter out this row as well, otherwise we need to keep updating this test when making a new release. cc @MaxGekk

Copy link
Member Author

Choose a reason for hiding this comment

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

Will do in another PR for DESCRIBE TABLE tests.

Copy link
Contributor

Choose a reason for hiding this comment

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

Next time, let's address comments immediately. We missed fixing it in the next PR...

Row("Type", "EXTERNAL", ""),
Row("Provider", "parquet", ""),
Row("Comment", "this is a test table", ""),
Row("Table Properties", "[bar=baz]", ""),
Row("Location", "file:/tmp/testcat/table_name", ""),
Row("Partition Provider", "Catalog", "")))
}
}
}
Loading