Hive优化器原理与源码解析系列--优化规则UnionPullUpConstantsRule(八)

SELECT key, value, ds FROM (
     SELECT key, value, ds FROM src_union_1
     UNION ALL
     SELECT key, value, ds FROM src_union_2
     UNION ALL
     SELECT key, value, ds FROM src_union_3
) subq where key = 86;

SELECT 86 as key, value, ds FROM (
        SELECT value, ds FROM src_union_1
        UNION ALL
        SELECT value, ds FROM src_union_2
        UNION ALL
        SELECT value, ds FROM src_union_3
) subq where key = 86;

final Union union = call.rel(0);
    final int count = union.getRowType().getFieldCount();
    if (count == 1) {//投影中只有一个字段无法再进行上拉，会导致select中字段为空列表
      return;
    }
    final RexBuilder rexBuilder = union.getCluster().getRexBuilder();
    final RelMetadataQuery mq = RelMetadataQuery.instance();
    final RelOptPredicateList predicates = mq.getPulledUpPredicates(union);
    if (predicates == null) {//从union操作符中拉取谓词
      return;
    }
    Map<RexNode, RexNode> conditionsExtracted = HiveReduceExpressionsRule.predicateConstants(//提取常量谓词
            RexNode.class, rexBuilder, predicates);
    Map<RexNode, RexNode> constants = new HashMap<>();
    for (int i = 0; i < count ; i++) {
      RexNode expr = rexBuilder.makeInputRef(union, i);
      if (conditionsExtracted.containsKey(expr)) {
        constants.put(expr, conditionsExtracted.get(expr));
      }
    }
    // None of the expressions are constant. Nothing to do.
    if (constants.isEmpty()) {//常量谓词为null，则不做任何优化
      return;
    }

// Create expressions for Project operators before and after the Union
    List<RelDataTypeField> fields = union.getRowType().getFieldList();
    List<RexNode> topChildExprs = new ArrayList<>(); //存放顶层Unoin的子所有的字段RexNode（常量 + 非常量）
    List<String> topChildExprsFields = new ArrayList<>();
    List<RexNode> refs = new ArrayList<>();
    ImmutableBitSet.Builder refsIndexBuilder = ImmutableBitSet.builder();

    for (int i = 0; i < count ; i++) {
      RexNode expr = rexBuilder.makeInputRef(union, i);
      RelDataTypeField field = fields.get(i);
      if (constants.containsKey(expr)) {
        topChildExprs.add(constants.get(expr));//如果是常量，则存放的字段对应的常量rexnode值
        topChildExprsFields.add(field.getName());
      } else {
        topChildExprs.add(expr);//不是常量谓词，则存放的是该字段RexNode
        topChildExprsFields.add(field.getName());
        refs.add(expr);//，仅存放的该字段RexNode不是常量谓词的字段
        refsIndexBuilder.set(i);
      }
    }
    ImmutableBitSet refsIndex = refsIndexBuilder.build();

    // Update top Project positions
    final Mappings.TargetMapping mapping =
            RelOptUtil.permutation(refs, union.getInput(0).getRowType()).inverse();
    topChildExprs = ImmutableList.copyOf(RexUtil.apply(mapping, topChildExprs));

// Update top Project positions         select中字段已经更新为常量
topChildExprs = ImmutableList.copyOf(RexUtil.apply(mapping, topChildExprs));//并生成一个新的排序列表

// Create new Project-Union-Project sequences
final RelBuilder relBuilder = call.builder();
    for (int i = 0; i < union.getInputs().size() ; i++) {
      RelNode input = union.getInput(i);
      List<Pair<RexNode, String>> newChildExprs = new ArrayList<>();
      for (int j = 0; j < refsIndex.cardinality(); j++ ) {
        int pos = refsIndex.nth(j);
        newChildExprs.add(
                Pair.<RexNode, String>of(rexBuilder.makeInputRef(input, pos),
                        input.getRowType().getFieldList().get(pos).getName()));
      }
      if (newChildExprs.isEmpty()) {
        // At least a single item in project is required.
        newChildExprs.add(Pair.<RexNode,String>of(
                topChildExprs.get(0), topChildExprsFields.get(0)));
      }
      
      // Add the input with project on top
      relBuilder.push(input);
      relBuilder.project(Pair.left(newChildExprs), Pair.right(newChildExprs));//子relNode创建新的字段引用，此时已经去掉了已经被上拉的常量字段
    }
    relBuilder.union(union.all, union.getInputs().size());
    // Create top Project fixing nullability of fields
    relBuilder.project(topChildExprs, topChildExprsFields);
    relBuilder.convert(union.getRowType(), false);
    call.transformTo(relBuilder.build());

SELECT 86 as key, value, ds FROM (
SELECT value, ds FROM src_union_1
UNION ALL
SELECT value, ds FROM src_union_2
UNION ALL
SELECT value, ds FROM src_union_3
) subq where key = 86;