kuczoram commented on a change in pull request #2407:
URL: https://github.com/apache/hive/pull/2407#discussion_r656843384
##########
File path:
iceberg/iceberg-handler/src/test/java/org/apache/iceberg/mr/hive/TestHiveIcebergStorageHandlerWithEngine.java
##########
@@ -1273,6 +1274,510 @@ public void testScanTableCaseInsensitive() throws
IOException {
Assert.assertArrayEquals(new Object[] {1L, "Bob", "Green"}, rows.get(1));
}
+ @Test
+ public void testAddColumnToIcebergTable() throws IOException {
+ // Create an Iceberg table with the columns customer_id, first_name and
last_name with some initial data.
+ Table icebergTable = testTables.createTable(shell, "customers",
HiveIcebergStorageHandlerTestUtils.CUSTOMER_SCHEMA,
+ fileFormat, HiveIcebergStorageHandlerTestUtils.CUSTOMER_RECORDS);
+
+ // Add a new column (age long) to the Iceberg table.
+ icebergTable.updateSchema().addColumn("age",
Types.LongType.get()).commit();
+
+ Schema customerSchemaWithAge = new Schema(optional(1, "customer_id",
Types.LongType.get()),
+ optional(2, "first_name", Types.StringType.get(), "This is first
name"),
+ optional(3, "last_name", Types.StringType.get(), "This is last name"),
+ optional(4, "age", Types.LongType.get()));
+
+ Schema customerSchemaWithAgeOnly =
+ new Schema(optional(1, "customer_id", Types.LongType.get()),
optional(4, "age", Types.LongType.get()));
+
+ // Also add a new entry to the table where the age column is set.
+ icebergTable = testTables.loadTable(TableIdentifier.of("default",
"customers"));
+ List<Record> newCustomerWithAge =
TestHelper.RecordsBuilder.newInstance(customerSchemaWithAge)
+ .add(3L, "James", "Red", 34L).add(4L, "Lily", "Blue", null).build();
+ testTables.appendIcebergTable(shell.getHiveConf(), icebergTable,
fileFormat, null, newCustomerWithAge);
+
+ // Do a 'select *' from Hive and check if the age column appears in the
result.
+ // It should be null for the old data and should be filled for the data
added after the column addition.
+ TestHelper.RecordsBuilder customersWithAgeBuilder =
TestHelper.RecordsBuilder.newInstance(customerSchemaWithAge)
+ .add(0L, "Alice", "Brown", null).add(1L, "Bob", "Green", null).add(2L,
"Trudy", "Pink", null)
+ .add(3L, "James", "Red", 34L).add(4L, "Lily", "Blue", null);
+ List<Record> customersWithAge = customersWithAgeBuilder.build();
+
+ List<Object[]> rows = shell.executeStatement("SELECT * FROM
default.customers");
+ HiveIcebergTestUtils.validateData(customersWithAge,
HiveIcebergTestUtils.valueForRow(customerSchemaWithAge, rows),
+ 0);
+
+ // Do a 'select customer_id, age' from Hive to check if the new column can
be queried from Hive.
+ // The customer_id is needed because of the result sorting.
+ TestHelper.RecordsBuilder customerWithAgeOnlyBuilder =
TestHelper.RecordsBuilder
+ .newInstance(customerSchemaWithAgeOnly).add(0L, null).add(1L,
null).add(2L, null).add(3L, 34L).add(4L, null);
+ List<Record> customersWithAgeOnly = customerWithAgeOnlyBuilder.build();
+
+ rows = shell.executeStatement("SELECT customer_id, age FROM
default.customers");
+ HiveIcebergTestUtils.validateData(customersWithAgeOnly,
+ HiveIcebergTestUtils.valueForRow(customerSchemaWithAgeOnly, rows), 0);
+
+ // Insert some data with age column from Hive. Insert an entry with null
age and an entry with filled age.
+ shell.executeStatement(
+ "INSERT INTO default.customers values (5L, 'Lily', 'Magenta', NULL),
(6L, 'Roni', 'Purple', 23L)");
+
+ customersWithAgeBuilder.add(5L, "Lily", "Magenta", null).add(6L, "Roni",
"Purple", 23L);
+ customersWithAge = customersWithAgeBuilder.build();
+ rows = shell.executeStatement("SELECT * FROM default.customers");
+ HiveIcebergTestUtils.validateData(customersWithAge,
HiveIcebergTestUtils.valueForRow(customerSchemaWithAge, rows),
+ 0);
+
+ customerWithAgeOnlyBuilder.add(5L, null).add(6L, 23L);
+ customersWithAgeOnly = customerWithAgeOnlyBuilder.build();
+ rows = shell.executeStatement("SELECT customer_id, age FROM
default.customers");
+ HiveIcebergTestUtils.validateData(customersWithAgeOnly,
+ HiveIcebergTestUtils.valueForRow(customerSchemaWithAgeOnly, rows), 0);
+ }
+
+ @Test
+ public void testAddRequiredColumnToIcebergTable() throws IOException {
+ // Create an Iceberg table with the columns customer_id, first_name and
last_name with some initial data.
+ Table icebergTable = testTables.createTable(shell, "customers",
HiveIcebergStorageHandlerTestUtils.CUSTOMER_SCHEMA,
+ fileFormat, null);
+
+ // Add a new required column (age long) to the Iceberg table.
+
icebergTable.updateSchema().allowIncompatibleChanges().addRequiredColumn("age",
Types.LongType.get()).commit();
+
+ Schema customerSchemaWithAge = new Schema(optional(1, "customer_id",
Types.LongType.get()),
+ optional(2, "first_name", Types.StringType.get(), "This is first
name"),
+ optional(3, "last_name", Types.StringType.get(), "This is last name"),
+ required(4, "age", Types.LongType.get()));
+
+ // Insert some data with age column from Hive.
+ shell.executeStatement(
+ "INSERT INTO default.customers values (0L, 'Lily', 'Magenta', 28L),
(1L, 'Roni', 'Purple', 33L)");
+
+ // Do a 'select *' from Hive and check if the age column appears in the
result.
+ List<Record> customersWithAge =
TestHelper.RecordsBuilder.newInstance(customerSchemaWithAge)
+ .add(0L, "Lily", "Magenta", 28L).add(1L, "Roni", "Purple",
33L).build();
+ List<Object[]> rows = shell.executeStatement("SELECT * FROM
default.customers");
+ HiveIcebergTestUtils.validateData(customersWithAge,
HiveIcebergTestUtils.valueForRow(customerSchemaWithAge, rows),
+ 0);
+
+ // Should add test step to insert NULL value into the new required column.
But at the moment it
+ // works inconsistently for different file types, so leave it for later
when this behaviour is cleaned up.
+ }
+
+ @Test
+ public void testAddColumnIntoStructToIcebergTable() throws IOException {
+ Schema schema = new Schema(required(1, "id", Types.LongType.get()),
required(2, "person", Types.StructType
+ .of(required(3, "first_name", Types.StringType.get()), required(4,
"last_name", Types.StringType.get()))));
+ List<Record> people = TestHelper.generateRandomRecords(schema, 3, 0L);
+
+ // Create an Iceberg table with the columns customer_id, first_name and
last_name with some initial data.
Review comment:
Oh, thanks, fixed it.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
