Examples with Table org.apache.iceberg.Table used on opensource projects

Example 71 with Table

use of org.apache.iceberg.Table in project hive by apache.

the class TestInputFormatReaderDeletes method rowSet.

@Override
public StructLikeSet rowSet(String name, Table table, String... columns) {
    InputFormatConfig.ConfigBuilder builder = new InputFormatConfig.ConfigBuilder(conf).readFrom(table.location());
    Schema projected = table.schema().select(columns);
    StructLikeSet set = StructLikeSet.create(projected.asStruct());
    set.addAll(TestIcebergInputFormats.TESTED_INPUT_FORMATS.stream().filter(recordFactory -> recordFactory.name().equals(inputFormat)).map(recordFactory -> recordFactory.create(builder.project(projected).conf()).getRecords()).flatMap(List::stream).map(record -> new InternalRecordWrapper(projected.asStruct()).wrap(record)).collect(Collectors.toList()));
    return set;
}

Example 72 with Table

use of org.apache.iceberg.Table in project hive by apache.

the class TestHiveIcebergPartitions method testHourTransform.

@Test
public void testHourTransform() throws IOException {
    Schema schema = new Schema(optional(1, "id", Types.LongType.get()), optional(2, "part_field", Types.TimestampType.withoutZone()));
    PartitionSpec spec = PartitionSpec.builderFor(schema).hour("part_field").build();
    List<Record> records = TestHelper.RecordsBuilder.newInstance(schema).add(1L, LocalDateTime.of(2019, 2, 22, 9, 44, 54)).add(2L, LocalDateTime.of(2019, 2, 22, 10, 44, 54)).add(3L, LocalDateTime.of(2019, 2, 23, 9, 44, 54)).build();
    Table table = testTables.createTable(shell, "part_test", schema, spec, fileFormat, records);
    HiveIcebergTestUtils.validateData(table, records, 0);
    HiveIcebergTestUtils.validateDataWithSQL(shell, "part_test", records, "id");
}

Example 73 with Table

use of org.apache.iceberg.Table in project hive by apache.

the class TestHiveIcebergPartitions method testDayTransform.

@Test
public void testDayTransform() throws IOException {
    Schema schema = new Schema(optional(1, "id", Types.LongType.get()), optional(2, "part_field", Types.TimestampType.withoutZone()));
    PartitionSpec spec = PartitionSpec.builderFor(schema).day("part_field").build();
    List<Record> records = TestHelper.RecordsBuilder.newInstance(schema).add(1L, LocalDateTime.of(2019, 2, 22, 9, 44, 54)).add(2L, LocalDateTime.of(2019, 2, 22, 10, 44, 54)).add(3L, LocalDateTime.of(2019, 2, 23, 9, 44, 54)).build();
    Table table = testTables.createTable(shell, "part_test", schema, spec, fileFormat, records);
    HiveIcebergTestUtils.validateData(table, records, 0);
    HiveIcebergTestUtils.validateDataWithSQL(shell, "part_test", records, "id");
}

Example 74 with Table

use of org.apache.iceberg.Table in project hive by apache.

the class TestHiveIcebergPartitions method testPartitionPruning.

@Test
public void testPartitionPruning() throws IOException {
    Schema salesSchema = new Schema(required(1, "ss_item_sk", Types.IntegerType.get()), required(2, "ss_sold_date_sk", Types.IntegerType.get()));
    PartitionSpec salesSpec = PartitionSpec.builderFor(salesSchema).identity("ss_sold_date_sk").build();
    Schema dimSchema = new Schema(required(1, "d_date_sk", Types.IntegerType.get()), required(2, "d_moy", Types.IntegerType.get()));
    List<Record> salesRecords = TestHelper.RecordsBuilder.newInstance(salesSchema).add(51, 5).add(61, 6).add(71, 7).add(81, 8).add(91, 9).build();
    List<Record> dimRecords = TestHelper.RecordsBuilder.newInstance(salesSchema).add(1, 10).add(2, 20).add(3, 30).add(4, 40).add(5, 50).build();
    Table salesTable = testTables.createTable(shell, "x1_store_sales", salesSchema, salesSpec, fileFormat, null);
    PartitionKey partitionKey = new PartitionKey(salesSpec, salesSchema);
    for (Record r : salesRecords) {
        partitionKey.partition(r);
        testTables.appendIcebergTable(shell.getHiveConf(), salesTable, fileFormat, partitionKey, ImmutableList.of(r));
    }
    testTables.createTable(shell, "x1_date_dim", dimSchema, fileFormat, dimRecords);
    String query = "select s.ss_item_sk from x1_store_sales s, x1_date_dim d " + "where s.ss_sold_date_sk=d.d_date_sk*2 and d.d_moy=30";
    // Check the query results
    List<Object[]> rows = shell.executeStatement(query);
    Assert.assertEquals(1, rows.size());
    Assert.assertArrayEquals(new Object[] { 61 }, rows.get(0));
    // Check if Dynamic Partitioning is used
    Assert.assertTrue(shell.executeStatement("explain " + query).stream().filter(a -> ((String) a[0]).contains("Dynamic Partitioning Event Operator")).findAny().isPresent());
}

Example 75 with Table

use of org.apache.iceberg.Table in project hive by apache.

the class TestHiveIcebergPartitions method testBucketTransform.

@Test
public void testBucketTransform() throws IOException {
    Schema schema = new Schema(optional(1, "id", Types.LongType.get()), optional(2, "part_field", Types.StringType.get()));
    PartitionSpec spec = PartitionSpec.builderFor(schema).bucket("part_field", 2).build();
    List<Record> records = TestHelper.RecordsBuilder.newInstance(schema).add(1L, "Part1").add(2L, "Part2").add(3L, "Art3").build();
    Table table = testTables.createTable(shell, "part_test", schema, spec, fileFormat, records);
    HiveIcebergTestUtils.validateData(table, records, 0);
    HiveIcebergTestUtils.validateDataWithSQL(shell, "part_test", records, "id");
}