You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by db...@apache.org on 2019/03/20 00:22:28 UTC
[spark] branch master updated: [SPARK-27197][SQL][TEST] Add
ReadNestedSchemaTest for file-based data sources
This is an automated email from the ASF dual-hosted git repository.
dbtsai pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 4d52477 [SPARK-27197][SQL][TEST] Add ReadNestedSchemaTest for file-based data sources
4d52477 is described below
commit 4d5247778aa706e6fe5eb79a339dc7fe9ddded96
Author: Dongjoon Hyun <dh...@apple.com>
AuthorDate: Wed Mar 20 00:22:05 2019 +0000
[SPARK-27197][SQL][TEST] Add ReadNestedSchemaTest for file-based data sources
## What changes were proposed in this pull request?
The reader schema is said to be evolved (or projected) when it changed after the data is written by writers. Apache Spark file-based data sources have a test coverage for that; e.g. [ReadSchemaSuite.scala](https://github.com/apache/spark/blob/master/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/ReadSchemaSuite.scala). This PR aims to add a test coverage for nested columns by adding and hiding nested columns.
## How was this patch tested?
Pass the Jenkins with newly added tests.
Closes #24139 from dongjoon-hyun/SPARK-27197.
Authored-by: Dongjoon Hyun <dh...@apple.com>
Signed-off-by: DB Tsai <d_...@apple.com>
---
.../datasources/AvroReadSchemaSuite.scala | 2 +
.../datasources/ReadNestedSchemaTest.scala | 158 +++++++++++++++++++++
.../execution/datasources/ReadSchemaSuite.scala | 12 ++
3 files changed, 172 insertions(+)
diff --git a/external/avro/src/test/scala/org/apache/spark/sql/execution/datasources/AvroReadSchemaSuite.scala b/external/avro/src/test/scala/org/apache/spark/sql/execution/datasources/AvroReadSchemaSuite.scala
index a480bb9..aa58cbd 100644
--- a/external/avro/src/test/scala/org/apache/spark/sql/execution/datasources/AvroReadSchemaSuite.scala
+++ b/external/avro/src/test/scala/org/apache/spark/sql/execution/datasources/AvroReadSchemaSuite.scala
@@ -21,6 +21,8 @@ class AvroReadSchemaSuite
extends ReadSchemaSuite
with AddColumnIntoTheMiddleTest
with HideColumnInTheMiddleTest
+ with AddNestedColumnTest
+ with HideNestedColumnTest
with ChangePositionTest {
override val format: String = "avro"
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/ReadNestedSchemaTest.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/ReadNestedSchemaTest.scala
new file mode 100644
index 0000000..2b0fdfe
--- /dev/null
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/ReadNestedSchemaTest.scala
@@ -0,0 +1,158 @@
+/*
+ * 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.datasources
+
+import java.io.File
+
+import org.apache.spark.sql.{DataFrame, Row}
+
+
+/**
+ * Add a nested column.
+ */
+trait AddNestedColumnTest extends ReadSchemaTest {
+
+ private def testAdd(df1: DataFrame, df2: DataFrame, expectedRows: Seq[Row]): Unit = {
+ withTempPath { dir =>
+ val path = dir.getCanonicalPath
+
+ val dir1 = s"$path${File.separator}part=one"
+ val dir2 = s"$path${File.separator}part=two"
+
+ df1.write.format(format).options(options).save(dir1)
+ df2.write.format(format).options(options).save(dir2)
+
+ val df = spark.read
+ .schema(df2.schema)
+ .format(format)
+ .options(options)
+ .load(path)
+
+ checkAnswer(df, expectedRows)
+ }
+ }
+
+ test("add a nested column at the end of the leaf struct column") {
+ testAdd(
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4, 'c7', 5)) c2"),
+ Seq(
+ Row(1, Row(2, Row(3, 4, null)), "one"),
+ Row(1, Row(2, Row(3, 4, 5)), "two")))
+ }
+
+ test("add a nested column in the middle of the leaf struct column") {
+ testAdd(
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c7', 5, 'c6', 4)) c2"),
+ Seq(
+ Row(1, Row(2, Row(3, null, 4)), "one"),
+ Row(1, Row(2, Row(3, 5, 4)), "two")))
+ }
+
+ test("add a nested column at the end of the middle struct column") {
+ testAdd(
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4), 'c7', 5) c2"),
+ Seq(
+ Row(1, Row(2, Row(3, 4), null), "one"),
+ Row(1, Row(2, Row(3, 4), 5), "two")))
+ }
+
+ test("add a nested column in the middle of the middle struct column") {
+ testAdd(
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c7', 5, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ Seq(
+ Row(1, Row(2, null, Row(3, 4)), "one"),
+ Row(1, Row(2, 5, Row(3, 4)), "two")))
+ }
+}
+
+/**
+ * Hide a nested column.
+ */
+trait HideNestedColumnTest extends ReadSchemaTest {
+
+ private def testHide(df1: DataFrame, df2: DataFrame, df3: DataFrame, expectedRows: Seq[Row]) = {
+ withTempPath { dir =>
+ val path = dir.getCanonicalPath
+
+ val dir1 = s"$path${File.separator}part=one"
+ val dir2 = s"$path${File.separator}part=two"
+ val dir3 = s"$path${File.separator}part=three"
+
+ df1.write.format(format).options(options).save(dir1)
+ df2.write.format(format).options(options).save(dir2)
+ df3.write.format(format).options(options).save(dir3)
+
+ val df = spark.read
+ .schema(df1.schema)
+ .format(format)
+ .options(options)
+ .load(path)
+
+ checkAnswer(df, expectedRows)
+ }
+ }
+
+ test("hide a nested column at the end of the leaf struct column") {
+ testHide(
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ sql("SELECT 5 c1, named_struct('c3', 6, 'c4', named_struct('c5', 7, 'c6', 8, 'c7', 9)) c2"),
+ sql("SELECT 0 c1, named_struct('c3', 1, 'c4', named_struct('c5', 2, 'c6', 3, 'c8', 4)) c2"),
+ Seq(
+ Row(1, Row(2, Row(3, 4)), "one"),
+ Row(5, Row(6, Row(7, 8)), "two"),
+ Row(0, Row(1, Row(2, 3)), "three")))
+ }
+
+ test("hide a nested column in the middle of the leaf struct column") {
+ testHide(
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ sql("SELECT 5 c1, named_struct('c3', 6, 'c4', named_struct('c5', 7, 'c7', 8, 'c6', 9)) c2"),
+ sql("SELECT 0 c1, named_struct('c3', 1, 'c4', named_struct('c7', 2, 'c5', 3, 'c6', 4)) c2"),
+ Seq(
+ Row(1, Row(2, Row(3, 4)), "one"),
+ Row(5, Row(6, Row(7, 9)), "two"),
+ Row(0, Row(1, Row(3, 4)), "three")))
+ }
+
+ test("hide a nested column at the end of the middle struct column") {
+ testHide(
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ sql("SELECT 5 c1, named_struct('c3', 6, 'c4', named_struct('c5', 7, 'c6', 8), 'c7', 9) c2"),
+ sql("SELECT 0 c1, named_struct('c3', 1, 'c4', named_struct('c5', 2, 'c6', 3), 'c8', 4) c2"),
+ Seq(
+ Row(1, Row(2, Row(3, 4)), "one"),
+ Row(5, Row(6, Row(7, 8)), "two"),
+ Row(0, Row(1, Row(2, 3)), "three")))
+ }
+
+ test("hide a nested column in the middle of the middle struct column") {
+ testHide(
+ sql("SELECT 1 c1, named_struct('c3', 2, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ sql("SELECT 5 c1, named_struct('c3', 6, 'c7', 7, 'c4', named_struct('c5', 8, 'c6', 9)) c2"),
+ sql("SELECT 0 c1, named_struct('c7', 1, 'c3', 2, 'c4', named_struct('c5', 3, 'c6', 4)) c2"),
+ Seq(
+ Row(1, Row(2, Row(3, 4)), "one"),
+ Row(5, Row(6, Row(8, 9)), "two"),
+ Row(0, Row(2, Row(3, 4)), "three")))
+ }
+}
+
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/ReadSchemaSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/ReadSchemaSuite.scala
index 802fda8..8c95349 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/ReadSchemaSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/ReadSchemaSuite.scala
@@ -76,6 +76,8 @@ class JsonReadSchemaSuite
extends ReadSchemaSuite
with AddColumnIntoTheMiddleTest
with HideColumnInTheMiddleTest
+ with AddNestedColumnTest
+ with HideNestedColumnTest
with ChangePositionTest
with IntegralTypeTest
with ToDoubleTypeTest
@@ -89,6 +91,8 @@ class OrcReadSchemaSuite
extends ReadSchemaSuite
with AddColumnIntoTheMiddleTest
with HideColumnInTheMiddleTest
+ with AddNestedColumnTest
+ with HideNestedColumnTest
with ChangePositionTest {
override val format: String = "orc"
@@ -109,6 +113,8 @@ class VectorizedOrcReadSchemaSuite
extends ReadSchemaSuite
with AddColumnIntoTheMiddleTest
with HideColumnInTheMiddleTest
+ with AddNestedColumnTest
+ with HideNestedColumnTest
with ChangePositionTest
with BooleanTypeTest
with IntegralTypeTest
@@ -132,6 +138,8 @@ class ParquetReadSchemaSuite
extends ReadSchemaSuite
with AddColumnIntoTheMiddleTest
with HideColumnInTheMiddleTest
+ with AddNestedColumnTest
+ with HideNestedColumnTest
with ChangePositionTest {
override val format: String = "parquet"
@@ -152,6 +160,8 @@ class VectorizedParquetReadSchemaSuite
extends ReadSchemaSuite
with AddColumnIntoTheMiddleTest
with HideColumnInTheMiddleTest
+ with AddNestedColumnTest
+ with HideNestedColumnTest
with ChangePositionTest {
override val format: String = "parquet"
@@ -172,6 +182,8 @@ class MergedParquetReadSchemaSuite
extends ReadSchemaSuite
with AddColumnIntoTheMiddleTest
with HideColumnInTheMiddleTest
+ with AddNestedColumnTest
+ with HideNestedColumnTest
with ChangePositionTest {
override val format: String = "parquet"
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org