Struct datafusion::physical_plan::parquet::ParquetExec

pub struct ParquetExec { /* fields omitted */ }

Execution plan for scanning one or more Parquet partitions

Implementations

impl ParquetExec

pub fn try_from_path(
    path: &str,
    projection: Option<Vec<usize>>,
    predicate: Option<Expr>,
    batch_size: usize,
    max_concurrency: usize,
    limit: Option<usize>
) -> Result<Self>

Create a new Parquet reader execution plan based on the specified Parquet filename or directory containing Parquet files

pub fn try_from_files(
    filenames: &[&str],
    projection: Option<Vec<usize>>,
    predicate: Option<Expr>,
    batch_size: usize,
    max_concurrency: usize,
    limit: Option<usize>
) -> Result<Self>

Create a new Parquet reader execution plan based on the specified list of Parquet files

pub fn new(
    partitions: Vec<ParquetPartition>,
    schema: Schema,
    projection: Option<Vec<usize>>,
    predicate_builder: Option<RowGroupPredicateBuilder>,
    batch_size: usize,
    limit: Option<usize>
) -> Self

Create a new Parquet reader execution plan with provided partitions and schema

pub fn partitions(&self) -> &[ParquetPartition]

Parquet partitions to read

pub fn projection(&self) -> &[usize]

Projection for which columns to load

pub fn batch_size(&self) -> usize

Batch size

pub fn statistics(&self) -> &Statistics

Statistics for the data set (sum of statistics for all partitions)

Trait Implementations

impl Clone for ParquetExec

fn clone(&self) -> ParquetExec

Returns a copy of the value.

pub 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 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_partitioning(&self) -> Partitioning

Get the output partitioning of this plan

fn with_new_children(
    &self,
    children: Vec<Arc<dyn ExecutionPlan>>
) -> Result<Arc<dyn ExecutionPlan>>

Returns a new plan where all children were replaced by new plans. The size of children must be equal to the size of ExecutionPlan::children().

fn execute<'life0, 'async_trait>(
    &'life0 self,
    partition: usize
) -> Pin<Box<dyn Future<Output = Result<SendableRecordBatchStream>> + Send + 'async_trait>> where
    'life0: 'async_trait,
    Self: 'async_trait, 

creates an iterator

fn required_child_distribution(&self) -> Distribution

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

fn metrics(&self) -> HashMap<String, SQLMetric>

Return a snapshot of the metrics collected during execution