Trait DataSource 

pub trait DataSource:
    Send
    + Sync
    + Debug {
    // Required methods
    fn open(
        &self,
        partition: usize,
        context: Arc<TaskContext>,
    ) -> Result<SendableRecordBatchStream>;
    fn as_any(&self) -> &dyn Any;
    fn fmt_as(&self, t: DisplayFormatType, f: &mut Formatter<'_>) -> Result;
    fn output_partitioning(&self) -> Partitioning;
    fn eq_properties(&self) -> EquivalenceProperties;
    fn partition_statistics(
        &self,
        partition: Option<usize>,
    ) -> Result<Statistics>;
    fn with_fetch(&self, _limit: Option<usize>) -> Option<Arc<dyn DataSource>>;
    fn fetch(&self) -> Option<usize>;
    fn try_swapping_with_projection(
        &self,
        _projection: &[ProjectionExpr],
    ) -> Result<Option<Arc<dyn DataSource>>>;

    // Provided methods
    fn repartitioned(
        &self,
        _target_partitions: usize,
        _repartition_file_min_size: usize,
        _output_ordering: Option<LexOrdering>,
    ) -> Result<Option<Arc<dyn DataSource>>> { ... }
    fn scheduling_type(&self) -> SchedulingType { ... }
    fn statistics(&self) -> Result<Statistics> { ... }
    fn metrics(&self) -> ExecutionPlanMetricsSet { ... }
    fn try_pushdown_filters(
        &self,
        filters: Vec<Arc<dyn PhysicalExpr>>,
        _config: &ConfigOptions,
    ) -> Result<FilterPushdownPropagation<Arc<dyn DataSource>>> { ... }
}

A source of data, typically a list of files or memory

This trait provides common behaviors for abstract sources of data. It has two common implementations:

1. FileScanConfig: lists of files
2. MemorySourceConfig: in memory list of RecordBatch

File format specific behaviors are defined by FileSource

See Also

• FileSource for file format specific implementations (Parquet, Json, etc)
• DataSourceExec: The [ExecutionPlan] that reads from a DataSource

Notes

Requires Debug to assist debugging

The following diagram shows how DataSource, FileSource, and DataSourceExec are related

                      ┌─────────────────────┐                              -----► execute path
                      │                     │                              ┄┄┄┄┄► init path
                      │   DataSourceExec    │  
                      │                     │    
                      └───────▲─────────────┘
                              ┊  │
                              ┊  │
                      ┌──────────▼──────────┐                            ┌──────────-──────────┐
                      │                     │                            |                     |
                      │  DataSource(trait)  │                            | TableProvider(trait)|
                      │                     │                            |                     |
                      └───────▲─────────────┘                            └─────────────────────┘
                              ┊  │                                                  ┊
              ┌───────────────┿──┴────────────────┐                                 ┊
              |   ┌┄┄┄┄┄┄┄┄┄┄┄┘                   |                                 ┊
              |   ┊                               |                                 ┊
   ┌──────────▼──────────┐             ┌──────────▼──────────┐                      ┊
   │                     │             │                     │           ┌──────────▼──────────┐
   │   FileScanConfig    │             │ MemorySourceConfig  │           |                     |
   │                     │             │                     │           |  FileFormat(trait)  |
   └──────────────▲──────┘             └─────────────────────┘           |                     |
              │   ┊                                                      └─────────────────────┘
              │   ┊                                                                 ┊
              │   ┊                                                                 ┊
   ┌──────────▼──────────┐                                               ┌──────────▼──────────┐
   │                     │                                               │     ArrowSource     │
   │ FileSource(trait)   ◄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄│          ...        │
   │                     │                                               │    ParquetSource    │
   └─────────────────────┘                                               └─────────────────────┘
              │
              │
              │
              │
   ┌──────────▼──────────┐
   │     ArrowSource     │
   │          ...        │
   │    ParquetSource    │
   └─────────────────────┘
              |
FileOpener (called by FileStream)
              │
   ┌──────────▼──────────┐
   │                     │
   │     RecordBatch     │
   │                     │
   └─────────────────────┘

Required Methods

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

fn as_any(&self) -> &dyn Any

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

Format this source for display in explain plans

fn output_partitioning(&self) -> Partitioning

fn eq_properties(&self) -> EquivalenceProperties

fn partition_statistics(&self, partition: Option<usize>) -> Result<Statistics>

Returns statistics for a specific partition, or aggregate statistics across all partitions if partition is None.

fn with_fetch(&self, _limit: Option<usize>) -> Option<Arc<dyn DataSource>>

Return a copy of this DataSource with a new fetch limit

fn fetch(&self) -> Option<usize>

fn try_swapping_with_projection( &self, _projection: &[ProjectionExpr], ) -> Result<Option<Arc<dyn DataSource>>>

Provided Methods

fn repartitioned( &self, _target_partitions: usize, _repartition_file_min_size: usize, _output_ordering: Option<LexOrdering>, ) -> Result<Option<Arc<dyn DataSource>>>

Return a copy of this DataSource with a new partitioning scheme.

Returns Ok(None) (the default) if the partitioning cannot be changed. Refer to [ExecutionPlan::repartitioned] for details on when None should be returned.

Repartitioning should not change the output ordering, if this ordering exists. Refer to MemorySourceConfig::repartition_preserving_order and the FileSource’s FileGroupPartitioner::repartition_file_groups for examples.

fn scheduling_type(&self) -> SchedulingType

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

👎Deprecated since 51.0.0: Use partition_statistics instead

Returns aggregate statistics across all partitions.

Deprecated

Use Self::partition_statistics instead, which provides more fine-grained control over statistics retrieval (per-partition or aggregate).

fn metrics(&self) -> ExecutionPlanMetricsSet

fn try_pushdown_filters( &self, filters: Vec<Arc<dyn PhysicalExpr>>, _config: &ConfigOptions, ) -> Result<FilterPushdownPropagation<Arc<dyn DataSource>>>

Try to push down filters into this DataSource. See ExecutionPlan::handle_child_pushdown_result for more details.

Implementors

impl DataSource for FileScanConfig

impl DataSource for MemorySourceConfig