Struct MergeScanExec

pub struct MergeScanExec {
    table: TableName,
    regions: Vec<RegionId>,
    plan: LogicalPlan,
    schema: SchemaRef,
    arrow_schema: SchemaRef,
    region_query_handler: RegionQueryHandlerRef,
    metric: ExecutionPlanMetricsSet,
    properties: PlanProperties,
    sub_stage_metrics: Arc<Mutex<Vec<RecordBatchMetrics>>>,
    query_ctx: QueryContextRef,
    target_partition: usize,
}

Fields

table: TableName

regions: Vec<RegionId>

plan: LogicalPlan

schema: SchemaRef

arrow_schema: SchemaRef

region_query_handler: RegionQueryHandlerRef

metric: ExecutionPlanMetricsSet

properties: PlanProperties

sub_stage_metrics: Arc<Mutex<Vec<RecordBatchMetrics>>>

Metrics from sub stages

query_ctx: QueryContextRef

target_partition: usize

Implementations

impl MergeScanExec

pub fn new( table: TableName, regions: Vec<RegionId>, plan: LogicalPlan, arrow_schema: &ArrowSchema, region_query_handler: RegionQueryHandlerRef, query_ctx: QueryContextRef, target_partition: usize, ) -> Result<Self>

pub fn to_stream( &self, context: Arc<TaskContext>, partition: usize, ) -> Result<SendableRecordBatchStream>

fn arrow_schema_to_schema(arrow_schema: ArrowSchemaRef) -> Result<SchemaRef>

pub fn sub_stage_metrics(&self) -> Vec<RecordBatchMetrics>

pub fn partition_count(&self) -> usize

pub fn region_count(&self) -> usize

Trait Implementations

impl Debug for MergeScanExec

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl DisplayAs for MergeScanExec

fn fmt_as(&self, _t: DisplayFormatType, f: &mut Formatter<'_>) -> Result

Format according to DisplayFormatType, used when verbose representation looks different from the default one

impl ExecutionPlan for MergeScanExec

fn as_any(&self) -> &dyn Any

Returns the execution plan as Any so that it can be downcast to a specific implementation.

fn schema(&self) -> ArrowSchemaRef

Get the schema for this execution plan

fn properties(&self) -> &PlanProperties

Return properties of the output of the ExecutionPlan, such as output ordering(s), partitioning information etc.

fn children(&self) -> Vec<&Arc<dyn ExecutionPlan>>

Get a list of children ExecutionPlans that act as inputs to this plan. The returned list will be empty for leaf nodes such as scans, will contain a single value for unary nodes, or two values for binary nodes (such as joins).

fn with_new_children( self: Arc<Self>, _children: Vec<Arc<dyn ExecutionPlan>>, ) -> Result<Arc<dyn ExecutionPlan>>

Returns a new ExecutionPlan where all existing children were replaced by the children, in order

fn execute( &self, partition: usize, context: Arc<TaskContext>, ) -> Result<DfSendableRecordBatchStream>

Begin execution of partition, returning a Stream of [RecordBatch]es.

fn metrics(&self) -> Option<MetricsSet>

Return a snapshot of the set of [Metric]s for this [ExecutionPlan]. If no Metrics are available, return None.

fn name(&self) -> &'static str

where Self: Sized,

Short name for the ExecutionPlan, such as ‘ParquetExec’.

fn static_name() -> &'static str

where Self: Sized,

Short name for the ExecutionPlan, such as ‘ParquetExec’. Like name but can be called without an instance.

fn required_input_distribution(&self) -> Vec<Distribution>

Specifies the data distribution requirements for all the children for this ExecutionPlan, By default it’s [[Distribution::UnspecifiedDistribution]] for each child,

fn required_input_ordering(&self) -> Vec<Option<Vec<PhysicalSortRequirement>>>

Specifies the ordering required for all of the children of this ExecutionPlan.

fn maintains_input_order(&self) -> Vec<bool>

Returns false if this ExecutionPlan’s implementation may reorder rows within or between partitions.

fn benefits_from_input_partitioning(&self) -> Vec<bool>

Specifies whether the ExecutionPlan benefits from increased parallelization at its input for each child.

fn repartitioned( &self, _target_partitions: usize, _config: &ConfigOptions, ) -> Result<Option<Arc<dyn ExecutionPlan>>, DataFusionError>

If supported, attempt to increase the partitioning of this ExecutionPlan to produce target_partitions partitions.

fn statistics(&self) -> Result<Statistics, DataFusionError>

Returns statistics for this ExecutionPlan node. If statistics are not available, should return [Statistics::new_unknown] (the default), not an error.