JingsongLi commented on a change in pull request #1346: URL: https://github.com/apache/iceberg/pull/1346#discussion_r494735542
########## File path: flink/src/test/java/org/apache/iceberg/flink/source/TestFlinkScan.java ########## @@ -0,0 +1,385 @@ +/* + * 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.time.LocalDate; +import java.time.LocalDateTime; +import java.time.LocalTime; +import java.util.Arrays; +import java.util.Collections; +import java.util.Comparator; +import java.util.List; +import java.util.Locale; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.data.conversion.DataStructureConverter; +import org.apache.flink.table.data.conversion.DataStructureConverters; +import org.apache.flink.table.types.utils.TypeConversions; +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.FlinkSchemaUtil; +import org.apache.iceberg.flink.RowDataConverter; +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.apache.iceberg.util.DateTimeUtil; +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(); + + private HadoopCatalog catalog; + protected String warehouse; + + // parametrized variables + private final FileFormat fileFormat; + + @Parameterized.Parameters(name = "format={0}") + public static Object[] parameters() { + return new Object[] {"avro", "parquet", "orc"}; + } + + 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()); + // before variables + Configuration conf = new Configuration(); + warehouse = "file:" + warehouseFile; + catalog = new HadoopCatalog(conf, warehouse); + } + + private List<Row> execute(Table table) throws IOException { + return execute(table, ScanOptions.builder().build()); + } + + protected abstract List<Row> execute(Table table, List<String> projectFields) throws IOException; + + protected abstract List<Row> execute(Table table, ScanOptions options) throws IOException; + + protected abstract List<Row> execute(Table table, List<Expression> filters, String sqlFilter) throws IOException; + + /** + * The Flink SQL has no residuals, because there will be operator to filter all the data that should be filtered. + * But the FlinkInputFormat can't. + */ + protected abstract void assertResiduals(Schema schema, List<Row> results, List<Record> writeRecords, + List<Record> filteredRecords) throws IOException; + + /** + * Schema: [data, nested[f1, f2, f3], id] + * Projection: [nested.f2, data] + * The Flink SQL output: [f2, data] + * The FlinkInputFormat output: [nested[f2], data]. + */ + protected abstract void assertNestedProjection(Table table, List<Record> records) throws IOException; Review comment: I think we can move `testNestedProjection` to `TestFlinkInputFormat`, because only InputFormat supports nested push-down, SQL can not. ########## File path: flink/src/test/java/org/apache/iceberg/flink/source/TestFlinkScan.java ########## @@ -0,0 +1,385 @@ +/* + * 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.time.LocalDate; +import java.time.LocalDateTime; +import java.time.LocalTime; +import java.util.Arrays; +import java.util.Collections; +import java.util.Comparator; +import java.util.List; +import java.util.Locale; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.data.conversion.DataStructureConverter; +import org.apache.flink.table.data.conversion.DataStructureConverters; +import org.apache.flink.table.types.utils.TypeConversions; +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.FlinkSchemaUtil; +import org.apache.iceberg.flink.RowDataConverter; +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.apache.iceberg.util.DateTimeUtil; +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(); + + private HadoopCatalog catalog; + protected String warehouse; + + // parametrized variables + private final FileFormat fileFormat; + + @Parameterized.Parameters(name = "format={0}") + public static Object[] parameters() { + return new Object[] {"avro", "parquet", "orc"}; + } + + 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()); + // before variables + Configuration conf = new Configuration(); + warehouse = "file:" + warehouseFile; + catalog = new HadoopCatalog(conf, warehouse); + } + + private List<Row> execute(Table table) throws IOException { + return execute(table, ScanOptions.builder().build()); + } + + protected abstract List<Row> execute(Table table, List<String> projectFields) throws IOException; + + protected abstract List<Row> execute(Table table, ScanOptions options) throws IOException; + + protected abstract List<Row> execute(Table table, List<Expression> filters, String sqlFilter) throws IOException; + + /** + * The Flink SQL has no residuals, because there will be operator to filter all the data that should be filtered. + * But the FlinkInputFormat can't. + */ + protected abstract void assertResiduals(Schema schema, List<Row> results, List<Record> writeRecords, + List<Record> filteredRecords) throws IOException; Review comment: This is also because of the difference between InputFormat and SQL(It can actually filter out the data). I think I should put it into a subclass of SQL. ---------------------------------------------------------------- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
