Skip to content

Add spark's legacy mode write tests to spark3.0 and 3.1 versions. #3767

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

Merged
RussellSpitzer merged 2 commits into from
Dec 18, 2021
Merged

Add spark's legacy mode write tests to spark3.0 and 3.1 versions. #3767

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c3b4f08
Add spark's legacy mode write tests to spark3.0 and 3.1 versions
SinghAsDev Dec 17, 2021
dfed4cd
Fix tests
SinghAsDev Dec 18, 2021
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
132 changes: 132 additions & 0 deletions spark/v3.0/spark/src/test/java/org/apache/iceberg/spark/actions/TestCreateActions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,6 +136,7 @@ public void before() {

spark.conf().set("hive.exec.dynamic.partition", "true");
spark.conf().set("hive.exec.dynamic.partition.mode", "nonstrict");
spark.conf().set("spark.sql.parquet.writeLegacyFormat", false);
spark.sql(String.format("DROP TABLE IF EXISTS %s", baseTableName));

List<SimpleRecord> expected = Lists.newArrayList(
Expand Down Expand Up @@ -570,6 +571,137 @@ public void schemaEvolutionTestWithSparkSQL() throws Exception {
assertEquals("Output must match", expectedAfterAddColumn, afterMigarteAfterAddResults);
}

@Test
public void testHiveStyleThreeLevelList() throws Exception {
threeLevelList(true);
}

@Test
public void testThreeLevelList() throws Exception {
threeLevelList(false);
}

@Test
public void testHiveStyleThreeLevelListWithNestedStruct() throws Exception {
threeLevelListWithNestedStruct(true);
}

@Test
public void testThreeLevelListWithNestedStruct() throws Exception {
threeLevelListWithNestedStruct(false);
}

@Test
public void testHiveStyleThreeLevelLists() throws Exception {
threeLevelLists(true);
}

@Test
public void testThreeLevelLists() throws Exception {
threeLevelLists(false);
}

@Test
public void testHiveStyleStructOfThreeLevelLists() throws Exception {
structOfThreeLevelLists(true);
}

@Test
public void testStructOfThreeLevelLists() throws Exception {
structOfThreeLevelLists(false);
}

public void threeLevelList(boolean useLegacyMode) throws Exception {
spark.conf().set("spark.sql.parquet.writeLegacyFormat", useLegacyMode);

String tableName = sourceName(String.format("threeLevelList_%s", useLegacyMode));
File location = temp.newFolder();
sql("CREATE TABLE %s (col1 ARRAY<STRUCT<col2: INT>>)" +
" STORED AS parquet" +
" LOCATION '%s'", tableName, location);

int testValue = 12345;
sql("INSERT INTO %s VALUES (ARRAY(STRUCT(%s)))", tableName, testValue);
List<Object[]> expected = sql(String.format("SELECT * FROM %s", tableName));

// migrate table
SparkActions.get().migrateTable(tableName).execute();

// check migrated table is returning expected result
List<Object[]> results = sql("SELECT * FROM %s", tableName);
Assert.assertTrue(results.size() > 0);
assertEquals("Output must match", expected, results);
}

private void threeLevelListWithNestedStruct(boolean useLegacyMode) throws Exception {
spark.conf().set("spark.sql.parquet.writeLegacyFormat", useLegacyMode);

String tableName = sourceName(String.format("threeLevelListWithNestedStruct_%s", useLegacyMode));
File location = temp.newFolder();
sql("CREATE TABLE %s (col1 ARRAY<STRUCT<col2: STRUCT<col3: INT>>>)" +
" STORED AS parquet" +
" LOCATION '%s'", tableName, location);

int testValue = 12345;
sql("INSERT INTO %s VALUES (ARRAY(STRUCT(STRUCT(%s))))", tableName, testValue);
List<Object[]> expected = sql(String.format("SELECT * FROM %s", tableName));

// migrate table
SparkActions.get().migrateTable(tableName).execute();

// check migrated table is returning expected result
List<Object[]> results = sql("SELECT * FROM %s", tableName);
Assert.assertTrue(results.size() > 0);
assertEquals("Output must match", expected, results);
}

private void threeLevelLists(boolean useLegacyMode) throws Exception {
spark.conf().set("spark.sql.parquet.writeLegacyFormat", useLegacyMode);

String tableName = sourceName(String.format("threeLevelLists_%s", useLegacyMode));
File location = temp.newFolder();
sql("CREATE TABLE %s (col1 ARRAY<STRUCT<col2: INT>>, col3 ARRAY<STRUCT<col4: INT>>)" +
" STORED AS parquet" +
" LOCATION '%s'", tableName, location);

int testValue1 = 12345;
int testValue2 = 987654;
sql("INSERT INTO %s VALUES (ARRAY(STRUCT(%s)), ARRAY(STRUCT(%s)))",
tableName, testValue1, testValue2);
List<Object[]> expected = sql(String.format("SELECT * FROM %s", tableName));

// migrate table
SparkActions.get().migrateTable(tableName).execute();

// check migrated table is returning expected result
List<Object[]> results = sql("SELECT * FROM %s", tableName);
Assert.assertTrue(results.size() > 0);
assertEquals("Output must match", expected, results);
}

private void structOfThreeLevelLists(boolean useLegacyMode) throws Exception {
spark.conf().set("spark.sql.parquet.writeLegacyFormat", useLegacyMode);

String tableName = sourceName(String.format("structOfThreeLevelLists_%s", useLegacyMode));
File location = temp.newFolder();
sql("CREATE TABLE %s (col1 STRUCT<col2: ARRAY<STRUCT<col3: INT>>>)" +
" STORED AS parquet" +
" LOCATION '%s'", tableName, location);

int testValue1 = 12345;
sql("INSERT INTO %s VALUES (STRUCT(STRUCT(ARRAY(STRUCT(%s)))))",
tableName, testValue1);
List<Object[]> expected = sql(String.format("SELECT * FROM %s", tableName));

// migrate table
SparkActions.get().migrateTable(tableName).execute();

// check migrated table is returning expected result
List<Object[]> results = sql("SELECT * FROM %s", tableName);
Assert.assertTrue(results.size() > 0);
assertEquals("Output must match", expected, results);
}


private SparkTable loadTable(String name) throws NoSuchTableException, ParseException {
return (SparkTable) catalog.loadTable(Spark3Util.catalogAndIdentifier(spark, name).identifier());
Expand Down
132 changes: 132 additions & 0 deletions spark/v3.1/spark/src/test/java/org/apache/iceberg/spark/actions/TestCreateActions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,6 +136,7 @@ public void before() {

spark.conf().set("hive.exec.dynamic.partition", "true");
spark.conf().set("hive.exec.dynamic.partition.mode", "nonstrict");
spark.conf().set("spark.sql.parquet.writeLegacyFormat", false);
spark.sql(String.format("DROP TABLE IF EXISTS %s", baseTableName));

List<SimpleRecord> expected = Lists.newArrayList(
Expand Down Expand Up @@ -570,6 +571,137 @@ public void schemaEvolutionTestWithSparkSQL() throws Exception {
assertEquals("Output must match", expectedAfterAddColumn, afterMigarteAfterAddResults);
}

@Test
public void testHiveStyleThreeLevelList() throws Exception {
threeLevelList(true);
}

@Test
public void testThreeLevelList() throws Exception {
threeLevelList(false);
}

@Test
public void testHiveStyleThreeLevelListWithNestedStruct() throws Exception {
threeLevelListWithNestedStruct(true);
}

@Test
public void testThreeLevelListWithNestedStruct() throws Exception {
threeLevelListWithNestedStruct(false);
}

@Test
public void testHiveStyleThreeLevelLists() throws Exception {
threeLevelLists(true);
}

@Test
public void testThreeLevelLists() throws Exception {
threeLevelLists(false);
}

@Test
public void testHiveStyleStructOfThreeLevelLists() throws Exception {
structOfThreeLevelLists(true);
}

@Test
public void testStructOfThreeLevelLists() throws Exception {
structOfThreeLevelLists(false);
}

public void threeLevelList(boolean useLegacyMode) throws Exception {
spark.conf().set("spark.sql.parquet.writeLegacyFormat", useLegacyMode);

String tableName = sourceName(String.format("threeLevelList_%s", useLegacyMode));
File location = temp.newFolder();
sql("CREATE TABLE %s (col1 ARRAY<STRUCT<col2: INT>>)" +
" STORED AS parquet" +
" LOCATION '%s'", tableName, location);

int testValue = 12345;
sql("INSERT INTO %s VALUES (ARRAY(STRUCT(%s)))", tableName, testValue);
List<Object[]> expected = sql(String.format("SELECT * FROM %s", tableName));

// migrate table
SparkActions.get().migrateTable(tableName).execute();

// check migrated table is returning expected result
List<Object[]> results = sql("SELECT * FROM %s", tableName);
Assert.assertTrue(results.size() > 0);
assertEquals("Output must match", expected, results);
}

private void threeLevelListWithNestedStruct(boolean useLegacyMode) throws Exception {
spark.conf().set("spark.sql.parquet.writeLegacyFormat", useLegacyMode);

String tableName = sourceName(String.format("threeLevelListWithNestedStruct_%s", useLegacyMode));
File location = temp.newFolder();
sql("CREATE TABLE %s (col1 ARRAY<STRUCT<col2: STRUCT<col3: INT>>>)" +
" STORED AS parquet" +
" LOCATION '%s'", tableName, location);

int testValue = 12345;
sql("INSERT INTO %s VALUES (ARRAY(STRUCT(STRUCT(%s))))", tableName, testValue);
List<Object[]> expected = sql(String.format("SELECT * FROM %s", tableName));

// migrate table
SparkActions.get().migrateTable(tableName).execute();

// check migrated table is returning expected result
List<Object[]> results = sql("SELECT * FROM %s", tableName);
Assert.assertTrue(results.size() > 0);
assertEquals("Output must match", expected, results);
}

private void threeLevelLists(boolean useLegacyMode) throws Exception {
spark.conf().set("spark.sql.parquet.writeLegacyFormat", useLegacyMode);

String tableName = sourceName(String.format("threeLevelLists_%s", useLegacyMode));
File location = temp.newFolder();
sql("CREATE TABLE %s (col1 ARRAY<STRUCT<col2: INT>>, col3 ARRAY<STRUCT<col4: INT>>)" +
" STORED AS parquet" +
" LOCATION '%s'", tableName, location);

int testValue1 = 12345;
int testValue2 = 987654;
sql("INSERT INTO %s VALUES (ARRAY(STRUCT(%s)), ARRAY(STRUCT(%s)))",
tableName, testValue1, testValue2);
List<Object[]> expected = sql(String.format("SELECT * FROM %s", tableName));

// migrate table
SparkActions.get().migrateTable(tableName).execute();

// check migrated table is returning expected result
List<Object[]> results = sql("SELECT * FROM %s", tableName);
Assert.assertTrue(results.size() > 0);
assertEquals("Output must match", expected, results);
}

private void structOfThreeLevelLists(boolean useLegacyMode) throws Exception {
spark.conf().set("spark.sql.parquet.writeLegacyFormat", useLegacyMode);

String tableName = sourceName(String.format("structOfThreeLevelLists_%s", useLegacyMode));
File location = temp.newFolder();
sql("CREATE TABLE %s (col1 STRUCT<col2: ARRAY<STRUCT<col3: INT>>>)" +
" STORED AS parquet" +
" LOCATION '%s'", tableName, location);

int testValue1 = 12345;
sql("INSERT INTO %s VALUES (STRUCT(STRUCT(ARRAY(STRUCT(%s)))))",
tableName, testValue1);
List<Object[]> expected = sql(String.format("SELECT * FROM %s", tableName));

// migrate table
SparkActions.get().migrateTable(tableName).execute();

// check migrated table is returning expected result
List<Object[]> results = sql("SELECT * FROM %s", tableName);
Assert.assertTrue(results.size() > 0);
assertEquals("Output must match", expected, results);
}


private SparkTable loadTable(String name) throws NoSuchTableException, ParseException {
return (SparkTable) catalog.loadTable(Spark3Util.catalogAndIdentifier(spark, name).identifier());
Expand Down