shardulm94 commented on a change in pull request #1566: URL: https://github.com/apache/iceberg/pull/1566#discussion_r505886885
########## File path: parquet/src/test/java/org/apache/iceberg/parquet/TestParquetColumnIndex.java ########## @@ -0,0 +1,105 @@ +/* + * 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.parquet; + +import java.io.File; +import java.io.IOException; +import java.util.ArrayList; +import java.util.List; +import java.util.function.Function; +import org.apache.avro.generic.GenericData; +import org.apache.iceberg.Schema; +import org.apache.iceberg.avro.AvroSchemaUtil; +import org.apache.iceberg.data.parquet.GenericParquetReaders; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.Expressions; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.parquet.Parquet.ReadBuilder; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.PrimitiveType; +import org.junit.Assert; +import org.junit.Rule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; + +import static org.apache.iceberg.Files.localInput; +import static org.apache.iceberg.TableProperties.PARQUET_PAGE_SIZE_BYTES; +import static org.apache.iceberg.parquet.ParquetWritingTestUtils.writeRecords; +import static org.apache.parquet.schema.PrimitiveType.PrimitiveTypeName.INT32; +import static org.apache.parquet.schema.Type.Repetition.REQUIRED; + +public class TestParquetColumnIndex { + + private MessageType parquetSchema = new MessageType("schema", + new PrimitiveType(REQUIRED, INT32, "intCol")); + private Schema schema = ParquetSchemaUtil.convert(parquetSchema); + + @Rule + public TemporaryFolder temp = new TemporaryFolder(); + + @Test + public void testColumnIndexFilter() throws IOException { + File parquetFile = generateFileWithMultiplePages(ParquetAvroWriter::buildWriter); + int totalCount = getPageRecordCount(parquetFile, null); + int filterCount = getPageRecordCount(parquetFile, + Expressions.and(Expressions.notNull("intCol"), Expressions.equal("intCol", 1))); + Assert.assertTrue(filterCount < totalCount); Review comment: Shouldn't this end up reading one and only one page? Can make the assertion more strict? Based on my comment in https://github.com/apache/iceberg/pull/1566#discussion_r505847585 I doubt if the reduced row count is a result of page skipping or just row group skipping. ---------------------------------------------------------------- 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]
