| /* |
| * 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.io.IOException; |
| import java.util.List; |
| import org.apache.iceberg.exceptions.RuntimeIOException; |
| import org.apache.iceberg.expressions.Expression; |
| import org.apache.iceberg.expressions.Expressions; |
| import org.apache.iceberg.expressions.ResidualEvaluator; |
| import org.apache.iceberg.io.CloseableIterable; |
| import org.apache.iceberg.relocated.com.google.common.collect.Iterables; |
| import org.apache.iceberg.relocated.com.google.common.collect.Sets; |
| import org.apache.iceberg.types.Type; |
| import org.apache.iceberg.types.TypeUtil; |
| import org.apache.iceberg.util.ParallelIterable; |
| import org.apache.iceberg.util.ThreadPools; |
| |
| /** |
| * A {@link Table} implementation that exposes a table's manifest entries as rows, for both delete and data files. |
| * <p> |
| * WARNING: this table exposes internal details, like files that have been deleted. For a table of the live data files, |
| * use {@link DataFilesTable}. |
| */ |
| public class AllEntriesTable extends BaseMetadataTable { |
| private final TableOperations ops; |
| private final Table table; |
| private final String name; |
| |
| AllEntriesTable(TableOperations ops, Table table) { |
| this(ops, table, table.name() + ".all_entries"); |
| } |
| |
| AllEntriesTable(TableOperations ops, Table table, String name) { |
| this.ops = ops; |
| this.table = table; |
| this.name = name; |
| } |
| |
| @Override |
| Table table() { |
| return table; |
| } |
| |
| @Override |
| public String name() { |
| return name; |
| } |
| |
| @Override |
| public TableScan newScan() { |
| return new Scan(ops, table, schema()); |
| } |
| |
| @Override |
| public Schema schema() { |
| Schema schema = ManifestEntry.getSchema(table.spec().partitionType()); |
| if (table.spec().fields().size() < 1) { |
| // avoid returning an empty struct, which is not always supported. instead, drop the partition field (id 102) |
| return TypeUtil.selectNot(schema, Sets.newHashSet(102)); |
| } else { |
| return schema; |
| } |
| } |
| |
| @Override |
| String metadataLocation() { |
| return ops.current().metadataFileLocation(); |
| } |
| |
| @Override |
| MetadataTableType metadataTableType() { |
| return MetadataTableType.ALL_ENTRIES; |
| } |
| |
| private static class Scan extends BaseAllMetadataTableScan { |
| |
| Scan(TableOperations ops, Table table, Schema schema) { |
| super(ops, table, schema); |
| } |
| |
| private Scan(TableOperations ops, Table table, Schema schema, TableScanContext context) { |
| super(ops, table, schema, context); |
| } |
| |
| @Override |
| protected TableScan newRefinedScan(TableOperations ops, Table table, Schema schema, |
| TableScanContext context) { |
| return new Scan(ops, table, schema, context); |
| } |
| |
| @Override |
| protected long targetSplitSize(TableOperations ops) { |
| return ops.current().propertyAsLong( |
| TableProperties.METADATA_SPLIT_SIZE, TableProperties.METADATA_SPLIT_SIZE_DEFAULT); |
| } |
| |
| @Override |
| protected CloseableIterable<FileScanTask> planFiles( |
| TableOperations ops, Snapshot snapshot, Expression rowFilter, |
| boolean ignoreResiduals, boolean caseSensitive, boolean colStats) { |
| CloseableIterable<ManifestFile> manifests = allManifestFiles(ops.current().snapshots()); |
| Type fileProjection = schema().findType("data_file"); |
| Schema fileSchema = fileProjection != null ? new Schema(fileProjection.asStructType().fields()) : new Schema(); |
| String schemaString = SchemaParser.toJson(schema()); |
| String specString = PartitionSpecParser.toJson(PartitionSpec.unpartitioned()); |
| Expression filter = ignoreResiduals ? Expressions.alwaysTrue() : rowFilter; |
| ResidualEvaluator residuals = ResidualEvaluator.unpartitioned(filter); |
| |
| return CloseableIterable.transform(manifests, manifest -> new ManifestEntriesTable.ManifestReadTask( |
| ops.io(), manifest, fileSchema, schemaString, specString, residuals, ops.current().specsById())); |
| } |
| } |
| |
| private static CloseableIterable<ManifestFile> allManifestFiles(List<Snapshot> snapshots) { |
| try (CloseableIterable<ManifestFile> iterable = new ParallelIterable<>( |
| Iterables.transform(snapshots, snapshot -> (Iterable<ManifestFile>) () -> snapshot.allManifests().iterator()), |
| ThreadPools.getWorkerPool())) { |
| return CloseableIterable.withNoopClose(Sets.newHashSet(iterable)); |
| } catch (IOException e) { |
| throw new RuntimeIOException(e, "Failed to close parallel iterable"); |
| } |
| } |
| } |