JingsongLi commented on a change in pull request #1346: URL: https://github.com/apache/iceberg/pull/1346#discussion_r472019911
########## File path: flink/src/test/java/org/apache/iceberg/flink/source/TestFlinkScan.java ########## @@ -0,0 +1,340 @@ +/* + * 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.iceberg.flink.source; + +import java.io.File; +import java.io.IOException; +import java.util.Arrays; +import java.util.Collections; +import java.util.Comparator; +import java.util.List; +import java.util.Locale; +import org.apache.flink.test.util.AbstractTestBase; +import org.apache.flink.types.Row; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.AppendFiles; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.TestHelpers; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.data.GenericAppenderHelper; +import org.apache.iceberg.data.RandomGenericData; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.Expressions; +import org.apache.iceberg.flink.CatalogLoader; +import org.apache.iceberg.hadoop.HadoopCatalog; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.types.Types; +import org.junit.Assert; +import org.junit.Before; +import org.junit.Test; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +import static org.apache.iceberg.types.Types.NestedField.required; + +@RunWith(Parameterized.class) +public abstract class TestFlinkScan extends AbstractTestBase { + + private static final Schema SCHEMA = new Schema( + required(1, "data", Types.StringType.get()), + required(2, "id", Types.LongType.get()), + required(3, "dt", Types.StringType.get())); + + private static final PartitionSpec SPEC = PartitionSpec.builderFor(SCHEMA) + .identity("dt") + .bucket("id", 1) + .build(); + + // before variables + private Configuration conf; + String warehouse; + private HadoopCatalog catalog; + + // parametrized variables + private final FileFormat fileFormat; + + @Parameterized.Parameters + public static Object[] parameters() { + // TODO add orc and parquet + return new Object[] {"avro"}; + } + + TestFlinkScan(String fileFormat) { + this.fileFormat = FileFormat.valueOf(fileFormat.toUpperCase(Locale.ENGLISH)); + } + + @Before + public void before() throws IOException { + File warehouseFile = TEMPORARY_FOLDER.newFolder(); + Assert.assertTrue(warehouseFile.delete()); + conf = new Configuration(); + warehouse = "file:" + warehouseFile; + catalog = new HadoopCatalog(conf, warehouse); + } + + private List<Row> execute(Table table) throws IOException { + return executeWithOptions(table, null, null, null, null, null, null, null, null); + } + + private List<Row> execute(Table table, List<String> projectFields) throws IOException { + return executeWithOptions(table, projectFields, null, null, null, null, null, null, null); + } + + protected abstract List<Row> executeWithOptions( + Table table, List<String> projectFields, CatalogLoader loader, Long snapshotId, + Long startSnapshotId, Long endSnapshotId, Long asOfTimestamp, List<Expression> filters, String sqlFilter) + throws IOException; + + protected abstract void assertResiduals(List<Row> results, List<Record> writeRecords, List<Record> filteredRecords) + throws IOException; + + @Test + public void testUnpartitionedTable() throws Exception { + Table table = catalog.createTable(TableIdentifier.of("default", "t"), SCHEMA); + List<Record> expectedRecords = RandomGenericData.generate(SCHEMA, 2, 0L); + new GenericAppenderHelper(table, fileFormat, TEMPORARY_FOLDER).appendToTable(expectedRecords); + assertRecords(execute(table), expectedRecords); + } + + @Test + public void testPartitionedTable() throws Exception { + Table table = catalog.createTable(TableIdentifier.of("default", "t"), SCHEMA, SPEC); + List<Record> expectedRecords = RandomGenericData.generate(SCHEMA, 1, 0L); + expectedRecords.get(0).set(2, "2020-03-20"); + new GenericAppenderHelper(table, fileFormat, TEMPORARY_FOLDER).appendToTable( + org.apache.iceberg.TestHelpers.Row.of("2020-03-20", 0), expectedRecords); + assertRecords(execute(table), expectedRecords); + } + + @Test + public void testProjection() throws Exception { Review comment: There is a `NestedFieldsProjectableTableSource` in Flink, but so far, no connector has implemented it. There may be unknown risks, and I tend not to implement it first. ---------------------------------------------------------------- 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]
