|
| 1 | +/* |
| 2 | + * Licensed to the Apache Software Foundation (ASF) under one |
| 3 | + * or more contributor license agreements. See the NOTICE file |
| 4 | + * distributed with this work for additional information |
| 5 | + * regarding copyright ownership. The ASF licenses this file |
| 6 | + * to you under the Apache License, Version 2.0 (the |
| 7 | + * "License"); you may not use this file except in compliance |
| 8 | + * with the License. You may obtain a copy of the License at |
| 9 | + * |
| 10 | + * http://www.apache.org/licenses/LICENSE-2.0 |
| 11 | + * |
| 12 | + * Unless required by applicable law or agreed to in writing, software |
| 13 | + * distributed under the License is distributed on an "AS IS" BASIS, |
| 14 | + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 15 | + * See the License for the specific language governing permissions and |
| 16 | + * limitations under the License. |
| 17 | + */ |
| 18 | + |
| 19 | +package org.apache.flink.table.planner.plan.optimize; |
| 20 | + |
| 21 | +import org.apache.flink.table.catalog.Column; |
| 22 | +import org.apache.flink.table.connector.source.abilities.SupportsReadingMetadata; |
| 23 | +import org.apache.flink.table.planner.connectors.DynamicSourceUtils; |
| 24 | +import org.apache.flink.table.planner.plan.nodes.physical.stream.StreamPhysicalCalcBase; |
| 25 | +import org.apache.flink.table.planner.plan.nodes.physical.stream.StreamPhysicalChangelogNormalize; |
| 26 | +import org.apache.flink.table.planner.plan.nodes.physical.stream.StreamPhysicalExchange; |
| 27 | +import org.apache.flink.table.planner.plan.nodes.physical.stream.StreamPhysicalTableSourceScan; |
| 28 | +import org.apache.flink.table.planner.plan.nodes.physical.stream.StreamPhysicalWatermarkAssigner; |
| 29 | +import org.apache.flink.table.planner.plan.optimize.program.FlinkChangelogModeInferenceProgram; |
| 30 | +import org.apache.flink.table.planner.plan.schema.TableSourceTable; |
| 31 | +import org.apache.flink.table.planner.plan.trait.UpdateKindTrait$; |
| 32 | +import org.apache.flink.table.planner.plan.trait.UpdateKindTraitDef$; |
| 33 | +import org.apache.flink.table.planner.plan.utils.FlinkRelUtil; |
| 34 | + |
| 35 | +import org.apache.calcite.rel.RelNode; |
| 36 | +import org.apache.calcite.rel.SingleRel; |
| 37 | +import org.apache.calcite.rex.RexNode; |
| 38 | +import org.apache.calcite.util.ImmutableBitSet; |
| 39 | + |
| 40 | +import java.util.Collection; |
| 41 | +import java.util.List; |
| 42 | +import java.util.Map; |
| 43 | +import java.util.Objects; |
| 44 | +import java.util.Optional; |
| 45 | +import java.util.Set; |
| 46 | +import java.util.stream.Collectors; |
| 47 | + |
| 48 | +/** |
| 49 | + * Checks if it is safe to remove ChangelogNormalize as part of {@link |
| 50 | + * FlinkChangelogModeInferenceProgram}. It checks: |
| 51 | + * |
| 52 | + * <ul> |
| 53 | + * <li>if there is no filter pushed into the changelog normalize |
| 54 | + * <li>if we don't need to produce UPDATE_BEFORE |
| 55 | + * <li>we don't access any metadata columns |
| 56 | + * </ul> |
| 57 | + */ |
| 58 | +public class ChangelogNormalizeRequirementResolver { |
| 59 | + |
| 60 | + /** Checks if it is safe to remove ChangelogNormalize. */ |
| 61 | + public static boolean isRequired(StreamPhysicalChangelogNormalize normalize) { |
| 62 | + if (normalize.filterCondition() != null) { |
| 63 | + return true; |
| 64 | + } |
| 65 | + if (!Objects.equals( |
| 66 | + normalize.getTraitSet().getTrait(UpdateKindTraitDef$.MODULE$.INSTANCE()), |
| 67 | + UpdateKindTrait$.MODULE$.ONLY_UPDATE_AFTER())) { |
| 68 | + return true; |
| 69 | + } |
| 70 | + |
| 71 | + // check if metadata columns are accessed |
| 72 | + final RelNode input = normalize.getInput(); |
| 73 | + |
| 74 | + return visit(input, bitSetForAllOutputColumns(input)); |
| 75 | + } |
| 76 | + |
| 77 | + private static ImmutableBitSet bitSetForAllOutputColumns(RelNode input) { |
| 78 | + return ImmutableBitSet.builder().set(0, input.getRowType().getFieldCount()).build(); |
| 79 | + } |
| 80 | + |
| 81 | + private static boolean visit(final RelNode rel, final ImmutableBitSet requiredColumns) { |
| 82 | + if (rel instanceof StreamPhysicalCalcBase) { |
| 83 | + return visitCalc((StreamPhysicalCalcBase) rel, requiredColumns); |
| 84 | + } else if (rel instanceof StreamPhysicalTableSourceScan) { |
| 85 | + return visitTableSourceScan((StreamPhysicalTableSourceScan) rel, requiredColumns); |
| 86 | + } else if (rel instanceof StreamPhysicalWatermarkAssigner |
| 87 | + || rel instanceof StreamPhysicalExchange) { |
| 88 | + // require all input columns |
| 89 | + final RelNode input = ((SingleRel) rel).getInput(); |
| 90 | + return visit(input, bitSetForAllOutputColumns(input)); |
| 91 | + } else { |
| 92 | + // these nodes should not be in an input of a changelog normalize |
| 93 | + // StreamPhysicalChangelogNormalize |
| 94 | + // StreamPhysicalDropUpdateBefore |
| 95 | + // StreamPhysicalUnion |
| 96 | + // StreamPhysicalSort |
| 97 | + // StreamPhysicalLimit |
| 98 | + // StreamPhysicalSortLimit |
| 99 | + // StreamPhysicalTemporalSort |
| 100 | + // StreamPhysicalWindowTableFunction |
| 101 | + // StreamPhysicalWindowRank |
| 102 | + // StreamPhysicalWindowDeduplicate |
| 103 | + // StreamPhysicalRank |
| 104 | + // StreamPhysicalOverAggregateBase |
| 105 | + // CommonPhysicalJoin |
| 106 | + // StreamPhysicalMatch |
| 107 | + // StreamPhysicalMiniBatchAssigner |
| 108 | + // StreamPhysicalExpand |
| 109 | + // StreamPhysicalWindowAggregateBase |
| 110 | + // StreamPhysicalGroupAggregateBase |
| 111 | + // StreamPhysicalSink |
| 112 | + // StreamPhysicalLegacySink |
| 113 | + // StreamPhysicalCorrelateBase |
| 114 | + // StreamPhysicalLookupJoin |
| 115 | + // StreamPhysicalValues |
| 116 | + // StreamPhysicalDataStreamScan |
| 117 | + // StreamPhysicalLegacyTableSourceScan |
| 118 | + throw new UnsupportedOperationException( |
| 119 | + String.format( |
| 120 | + "Unsupported to visit node %s. The node either should not be pushed" |
| 121 | + + " through the changelog normalize or is not supported yet.", |
| 122 | + rel.getClass().getSimpleName())); |
| 123 | + } |
| 124 | + } |
| 125 | + |
| 126 | + private static boolean visitTableSourceScan( |
| 127 | + StreamPhysicalTableSourceScan tableScan, ImmutableBitSet requiredColumns) { |
| 128 | + if (!(tableScan.tableSource() instanceof SupportsReadingMetadata)) { |
| 129 | + // source does not have metadata, no need to check |
| 130 | + return false; |
| 131 | + } |
| 132 | + final TableSourceTable sourceTable = tableScan.getTable().unwrap(TableSourceTable.class); |
| 133 | + assert sourceTable != null; |
| 134 | + // check if requiredColumns contain metadata column |
| 135 | + final List<Column.MetadataColumn> metadataColumns = |
| 136 | + DynamicSourceUtils.extractMetadataColumns( |
| 137 | + sourceTable.contextResolvedTable().getResolvedSchema()); |
| 138 | + final Set<String> metaColumnSet = |
| 139 | + metadataColumns.stream().map(Column::getName).collect(Collectors.toSet()); |
| 140 | + final List<String> columns = tableScan.getRowType().getFieldNames(); |
| 141 | + for (int index = 0; index < columns.size(); index++) { |
| 142 | + String column = columns.get(index); |
| 143 | + if (metaColumnSet.contains(column) && requiredColumns.get(index)) { |
| 144 | + // we require metadata column, therefore, we cannot remove the changelog normalize |
| 145 | + return true; |
| 146 | + } |
| 147 | + } |
| 148 | + |
| 149 | + return false; |
| 150 | + } |
| 151 | + |
| 152 | + private static boolean visitCalc(StreamPhysicalCalcBase calc, ImmutableBitSet requiredColumns) { |
| 153 | + // evaluate required columns from input |
| 154 | + final List<RexNode> projects = |
| 155 | + calc.getProgram().getProjectList().stream() |
| 156 | + .map(expr -> calc.getProgram().expandLocalRef(expr)) |
| 157 | + .collect(Collectors.toList()); |
| 158 | + final Map<Integer, List<Integer>> outFromSourcePos = |
| 159 | + FlinkRelUtil.extractSourceMapping(projects); |
| 160 | + final List<Integer> conv2Inputs = |
| 161 | + requiredColumns.toList().stream() |
| 162 | + .map( |
| 163 | + out -> |
| 164 | + Optional.ofNullable(outFromSourcePos.get(out)) |
| 165 | + .orElseThrow( |
| 166 | + () -> |
| 167 | + new IllegalStateException( |
| 168 | + String.format( |
| 169 | + "Invalid pos:%d over projection:%s", |
| 170 | + out, |
| 171 | + calc |
| 172 | + .getProgram())))) |
| 173 | + .flatMap(Collection::stream) |
| 174 | + .filter(index -> index != -1) |
| 175 | + .distinct() |
| 176 | + .collect(Collectors.toList()); |
| 177 | + return visit(calc.getInput(), ImmutableBitSet.of(conv2Inputs)); |
| 178 | + } |
| 179 | +} |
0 commit comments