Struct datafusion::physical_plan::file_format::ParquetExec

pub struct ParquetExec { /* private fields */ }

Execution plan for scanning one or more Parquet partitions

Implementations

impl ParquetExec

pub fn new(
    base_config: FileScanConfig,
    predicate: Option<Expr>,
    metadata_size_hint: Option<usize>
) -> Self

Create a new Parquet reader execution plan provided file list and schema.

pub fn base_config(&self) -> &FileScanConfig

Ref to the base configs

pub fn pruning_predicate(&self) -> Option<&PruningPredicate>

Optional reference to this parquet scan’s pruning predicate

pub fn with_parquet_file_reader_factory(
    self,
    parquet_file_reader_factory: Arc<dyn ParquetFileReaderFactory>
) -> Self

Optional user defined parquet file reader factory.

ParquetFileReaderFactory complements TableProvider, It enables users to provide custom implementation for data access operations.

If custom ParquetFileReaderFactory is provided, then data access operations will be routed to this factory instead of ObjectStore.

Trait Implementations

impl Clone for ParquetExec

fn clone(&self) -> ParquetExec

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ParquetExec

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

Formats the value using the given formatter.

impl ExecutionPlan for ParquetExec

fn as_any(&self) -> &dyn Any

Return a reference to Any that can be used for downcasting

fn output_partitioning(&self) -> Partitioning

Get the output partitioning of this plan

fn schema(&self) -> SchemaRef

Get the schema for this execution plan

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

Get a list of child execution plans that provide the input for this plan. The returned list will be empty for leaf nodes, will contain a single value for unary nodes, or two values for binary nodes (such as joins).

fn output_ordering(&self) -> Option<&[PhysicalSortExpr]>

If the output of this operator is sorted, returns Some(keys) with the description of how it was sorted.

fn relies_on_input_order(&self) -> bool

Returns true if this operator relies on its inputs being produced in a certain order (for example that they are sorted a particular way) for correctness.

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

Returns a new plan where all children were replaced by new plans.

fn execute(
    &self,
    partition_index: usize,
    ctx: Arc<TaskContext>
) -> Result<SendableRecordBatchStream>

creates an iterator

fn fmt_as(&self, t: DisplayFormatType, f: &mut Formatter<'_>) -> Result

Format this ExecutionPlan to f in the specified type.

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

Return a snapshot of the set of Metrics for this ExecutionPlan.

fn statistics(&self) -> Statistics

Returns the global output statistics for this ExecutionPlan node.

fn required_child_distribution(&self) -> Distribution

Specifies the data distribution requirements of all the children for this operator

fn maintains_input_order(&self) -> bool

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

fn benefits_from_input_partitioning(&self) -> bool

Returns true if this operator would benefit from partitioning its input (and thus from more parallelism). For operators that do very little work the overhead of extra parallelism may outweigh any benefits