aokolnychyi commented on code in PR #6365: URL: https://github.com/apache/iceberg/pull/6365#discussion_r1083068421
########## core/src/main/java/org/apache/iceberg/PositionDeletesTable.java: ########## @@ -0,0 +1,221 @@ +/* + * 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 com.github.benmanes.caffeine.cache.Caffeine; +import com.github.benmanes.caffeine.cache.LoadingCache; +import java.util.List; +import java.util.Map; +import java.util.function.Function; +import java.util.stream.Collectors; +import org.apache.iceberg.expressions.Expressions; +import org.apache.iceberg.expressions.ManifestEvaluator; +import org.apache.iceberg.expressions.ResidualEvaluator; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.types.TypeUtil; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.util.ParallelIterable; +import org.apache.iceberg.util.TableScanUtil; + +/** + * A {@link Table} implementation whose {@link Scan} provides {@link PositionDeletesScanTask}, for + * reading of position delete files. + */ +public class PositionDeletesTable extends BaseMetadataTable { + + private final Schema schema; + + PositionDeletesTable(Table table) { + super(table, table.name() + ".position_deletes"); + this.schema = calculateSchema(); + } + + PositionDeletesTable(Table table, String name) { + super(table, name); + this.schema = calculateSchema(); + } + + @Override + MetadataTableType metadataTableType() { + return MetadataTableType.POSITION_DELETES; + } + + @Override + public TableScan newScan() { + throw new UnsupportedOperationException( + "Cannot create TableScan from table of type POSITION_DELETES"); + } + + @Override + public BatchScan newBatchScan() { + return new PositionDeletesBatchScan(table(), schema()); + } + + @Override + public Schema schema() { + return schema; + } + + private Schema calculateSchema() { + Types.StructType partitionType = Partitioning.partitionType(table()); + Schema result = + new Schema( + MetadataColumns.DELETE_FILE_PATH, + MetadataColumns.DELETE_FILE_POS, + Types.NestedField.optional( + MetadataColumns.DELETE_FILE_ROW_FIELD_ID, + "row", + table().schema().asStruct(), + MetadataColumns.DELETE_FILE_ROW_DOC), + Types.NestedField.required( + MetadataColumns.PARTITION_COLUMN_ID, + "partition", + partitionType, + "Partition that position delete row belongs to"), + Types.NestedField.required( + MetadataColumns.SPEC_ID_COLUMN_ID, + "spec_id", + Types.IntegerType.get(), + MetadataColumns.SPEC_ID_COLUMN_DOC), + Types.NestedField.required( + MetadataColumns.FILE_PATH_COLUMN_ID, + "delete_file_path", + Types.StringType.get(), + MetadataColumns.FILE_PATH_COLUMN_DOC)); + + if (partitionType.fields().size() > 0) { + return result; + } else { + // avoid returning an empty struct, which is not always supported. + // instead, drop the partition field + return TypeUtil.selectNot(result, Sets.newHashSet(MetadataColumns.PARTITION_COLUMN_ID)); + } + } + + public static class PositionDeletesBatchScan + extends SnapshotScan<BatchScan, ScanTask, ScanTaskGroup<ScanTask>> implements BatchScan { + + protected PositionDeletesBatchScan(Table table, Schema schema) { + super(table, schema, new TableScanContext()); + } + + protected PositionDeletesBatchScan(Table table, Schema schema, TableScanContext context) { + super(table, schema, context); + } + + @Override + protected PositionDeletesBatchScan newRefinedScan( + Table newTable, Schema newSchema, TableScanContext newContext) { + return new PositionDeletesBatchScan(newTable, newSchema, newContext); + } + + @Override + public CloseableIterable<ScanTaskGroup<ScanTask>> planTasks() { + return TableScanUtil.planTaskGroups( + planFiles(), targetSplitSize(), splitLookback(), splitOpenFileCost()); + } + + @Override + protected List<String> scanColumns() { + return context().returnColumnStats() ? DELETE_SCAN_WITH_STATS_COLUMNS : DELETE_SCAN_COLUMNS; + } + + @Override + protected CloseableIterable<ScanTask> doPlanFiles() { + String schemaString = SchemaParser.toJson(tableSchema()); + + // prepare transformed partition specs and caches + Map<Integer, PartitionSpec> transformedSpecs = + table().specs().values().stream() + .map(spec -> transformSpec(tableSchema(), spec)) + .collect(Collectors.toMap(PartitionSpec::specId, spec -> spec)); + + LoadingCache<Integer, ResidualEvaluator> residualCache = + partitionCacheOf( + transformedSpecs, + spec -> + ResidualEvaluator.of( + spec, + shouldIgnoreResiduals() ? Expressions.alwaysTrue() : filter(), + isCaseSensitive())); + + LoadingCache<Integer, String> specStringCache = + partitionCacheOf(transformedSpecs, PartitionSpecParser::toJson); + + LoadingCache<Integer, ManifestEvaluator> evalCache = + partitionCacheOf( + transformedSpecs, + spec -> ManifestEvaluator.forRowFilter(filter(), spec, isCaseSensitive())); + + // iterate through delete manifests + CloseableIterable<ManifestFile> deleteManifests = + CloseableIterable.withNoopClose(snapshot().deleteManifests(table().io())); + CloseableIterable<ManifestFile> filteredManifests = + CloseableIterable.filter( Review Comment: Do we need to use a version of filter that updates `scanMetrics()`? -- 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: issues-unsubscr...@iceberg.apache.org 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
