spark sql 2.3 源码解读 - Optimizer (4)

得到 Resolved Logical Plan 后，将进入优化阶段。后续执行逻辑如下：

// 如果缓存中有查询结果，则直接替换为缓存的结果，逻辑不复杂，这里不再展开讲了。
lazy val withCachedData: LogicalPlan = {
  assertAnalyzed()
  assertSupported()
  sparkSession.sharedState.cacheManager.useCachedData(analyzed)
}
// 对Logical Plan 优化
lazy val optimizedPlan: LogicalPlan = {
  sparkSession.sessionState.optimizer.execute(withCachedData)
}

下面看一下Optimizer：

/**
 * Abstract class all optimizers should inherit of, contains the standard batches (extending
 * Optimizers can override this.
 */
abstract class Optimizer(sessionCatalog: SessionCatalog)
  extends RuleExecutor[LogicalPlan] {
  

看到Optimizer也是继承自RuleExecutor，我们就开心了，和Analyzer一个套路，也是遍历tree，并对每个节点应用rule。下面直接看rules就好了：

def batches: Seq[Batch] = {
  val operatorOptimizationRuleSet =
    Seq(
      // Operator push down
      PushProjectionThroughUnion,
      ReorderJoin,
      EliminateOuterJoin,
      PushPredicateThroughJoin,
      PushDownPredicate,
      LimitPushDown,
      ColumnPruning,
      InferFiltersFromConstraints,
      // Operator combine
      CollapseRepartition,
      CollapseProject,
      CollapseWindow,
      CombineFilters,
      CombineLimits,
      CombineUnions,
      // Constant folding and strength reduction
      NullPropagation,
      ConstantPropagation,
      FoldablePropagation,
      OptimizeIn,
      ConstantFolding,
      ReorderAssociativeOperator,
      LikeSimplification,
      BooleanSimplification,
      SimplifyConditionals,
      RemoveDispensableExpressions,
      SimplifyBinaryComparison,
      PruneFilters,
      EliminateSorts,
      SimplifyCasts,
      SimplifyCaseConversionExpressions,
      RewriteCorrelatedScalarSubquery,
      EliminateSerialization,
      RemoveRedundantAliases,
      RemoveRedundantProject,
      SimplifyCreateStructOps,
      SimplifyCreateArrayOps,
      SimplifyCreateMapOps,
      CombineConcats) +