gaborkaszab commented on code in PR #14508: URL: https://github.com/apache/iceberg/pull/14508#discussion_r2513269762
########## api/src/main/java/org/apache/iceberg/PartitionStatisticsScan.java: ########## @@ -0,0 +1,58 @@ +/* + * 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; + +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.io.CloseableIterable; + +public interface PartitionStatisticsScan { + + /** + * Create a new scan from this scan's configuration that will use the given snapshot by ID. + * + * @param snapshotId a snapshot ID + * @return a new scan based on this with the given snapshot ID + * @throws IllegalArgumentException if the snapshot cannot be found + */ + PartitionStatisticsScan useSnapshot(long snapshotId); + + /** + * Create a new scan from the results of this, where partitions are filtered by the {@link + * Expression}. + * + * @param filter a filter expression + * @return a new scan based on this with results filtered by the expression + */ + PartitionStatisticsScan filter(Expression filter); + + /** + * Create a new scan from this with the schema as its projection. Review Comment: Thank for pointing this out! My initial plan was to always query the 'traditional' partition stats and allow projection for the column-based once when we introduce them later. But it makes sense to project also the existing ones, and then the current design with PartitionStatistics isn't suitable for that. Let me wrap my head around this and come back with a different design that can tackle this too. ########## core/src/main/java/org/apache/iceberg/PartitionStatsHandler.java: ########## @@ -287,7 +289,11 @@ public static CloseableIterable<PartitionStats> readPartitionStatsFile( CloseableIterable<StructLike> records = InternalData.read(fileFormat, inputFile).project(schema).build(); - return CloseableIterable.transform(records, PartitionStatsHandler::recordToPartitionStats); + return CloseableIterable.transform( + records, + rec -> { + return (PartitionStats) recordToPartitionStats(rec); + }); Review Comment: We don't. Removed ########## core/src/main/java/org/apache/iceberg/BasePartitionStatisticsScan.java: ########## @@ -0,0 +1,89 @@ +/* + * 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; + +import java.util.List; +import java.util.Optional; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.types.Types; + +public class BasePartitionStatisticsScan implements PartitionStatisticsScan { + + private final Table table; + private Long snapshotId; + + public BasePartitionStatisticsScan(Table table) { + this.table = table; + } + + @Override + public PartitionStatisticsScan useSnapshot(long newSnapshotId) { + Preconditions.checkArgument( + table.snapshot(newSnapshotId) != null, "Cannot find snapshot with ID %s", newSnapshotId); + + this.snapshotId = newSnapshotId; + return this; + } + + @Override + public PartitionStatisticsScan filter(Expression newFilter) { + throw new UnsupportedOperationException("Filtering is not supported"); + } + + @Override + public PartitionStatisticsScan project(Schema newSchema) { + throw new UnsupportedOperationException("Projection is not supported"); + } + + @Override + public CloseableIterable<PartitionStatistics> scan() { Review Comment: I haven't introduced dedicated tests for this because now the capabilities is the same as we had before this patch, and TestPartitionStatsHandler covers it. Let's finalize the API part and I'll add a separate test suite too if you think it makes sense at this point. ########## core/src/main/java/org/apache/iceberg/PartitionStatsHandler.java: ########## @@ -225,7 +223,7 @@ public static PartitionStatisticsFile computeAndWriteStatsFile(Table table, long } try { - stats = computeAndMergeStatsIncremental(table, snapshot, partitionType, statisticsFile); + stats = computeAndMergeStatsIncremental(table, snapshot, statisticsFile.snapshotId()); Review Comment: The new Scan API encapsulates constructing a partitionType so no need to give it to the function as param. As a result later on we need the partitionType for sorting and writing, so we do calculate it. It seems cheap to produce so I don't see any issues with this. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
