Struct datafusion::datasource::physical_plan::CsvExec

pub struct CsvExec {
    pub file_compression_type: FileCompressionType,
    /* private fields */
}

Execution plan for scanning a CSV file

Fields

file_compression_type: FileCompressionType

Compression type of the file associated with CsvExec

Implementations

impl CsvExec

pub fn new( base_config: FileScanConfig, has_header: bool, delimiter: u8, quote: u8, escape: Option<u8>, file_compression_type: FileCompressionType ) -> Self

Create a new CSV reader execution plan provided base and specific configurations

pub fn base_config(&self) -> &FileScanConfig

Ref to the base configs

pub fn has_header(&self) -> bool

true if the first line of each file is a header

pub fn delimiter(&self) -> u8

A column delimiter

pub fn quote(&self) -> u8

The quote character

pub fn escape(&self) -> Option<u8>

The escape character

Trait Implementations

impl Clone for CsvExec

fn clone(&self) -> CsvExec

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for CsvExec

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

Formats the value using the given formatter.

impl DisplayAs for CsvExec

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 CsvExec

fn as_any(&self) -> &dyn Any

Return a reference to Any that can be used for downcasting

fn repartitioned( &self, target_partitions: usize, config: &ConfigOptions ) -> Result<Option<Arc<dyn ExecutionPlan>>>

Redistribute files across partitions according to their size See comments on FileGroupPartitioner for more detail.

Return None if can’t get repartitioned(empty/compressed file).

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

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

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>, _: 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<SendableRecordBatchStream>

Begin execution of partition, returning a Stream of RecordBatches.

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

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

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

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

fn schema(&self) -> Arc<Schema>

Get the schema for this execution plan

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.