Struct ScanBuilder

pub struct ScanBuilder<A> { /* private fields */ }

A struct for building a scan operation.

Implementations

impl<A: 'static + Send> ScanBuilder<A>

pub fn with_filter(self, filter: ExprRef) -> Self

pub fn with_some_filter(self, filter: Option<ExprRef>) -> Self

pub fn with_projection(self, projection: ExprRef) -> Self

pub fn with_row_range(self, row_range: Range<u64>) -> Self

pub fn with_some_row_range(self, row_range: Option<Range<u64>>) -> Self

pub fn with_selection(self, selection: Selection) -> Self

pub fn with_row_indices(self, row_indices: Buffer<u64>) -> Self

pub fn with_split_by(self, split_by: SplitBy) -> Self

pub fn with_concurrency(self, concurrency: usize) -> Self

The number of row splits to make progress on concurrently, must be greater than 0.

pub fn with_executor(self, executor: Arc<dyn TaskExecutor>) -> Self

pub fn with_metrics(self, metrics: VortexMetrics) -> Self

pub fn with_prune_file_on_open(self, stats_set: Arc<[StatsSet]>) -> Self

pub fn map<B: 'static>( self, map_fn: impl Fn(A) -> VortexResult<B> + 'static + Send + Sync, ) -> ScanBuilder<B>

Map each split of the scan. The function will be run on the spawned task.

pub fn dtype(&self) -> VortexResult<DType>

Returns the output DType of the scan.

pub fn build( self, ) -> VortexResult<Vec<impl Future<Output = VortexResult<Option<A>>>>>

Constructs a task per row split of the scan, returned as a vector of futures.

pub fn into_stream( self, ) -> VortexResult<impl Stream<Item = VortexResult<A>> + 'static>

Returns a stream over the scan objects.

impl ScanBuilder<ArrayRef>

pub fn new(layout_reader: Arc<dyn LayoutReader>) -> Self

pub fn map_to_record_batch(self, schema: SchemaRef) -> ScanBuilder<RecordBatch>

Map the scan into a stream of Arrow RecordBatch.

pub fn into_array_stream(self) -> VortexResult<impl ArrayStream + 'static>

Returns a stream over the scan with each CPU task polled on the current thread as per the behaviour of futures::stream::Buffered.

pub fn into_array_iter(self) -> VortexResult<impl ArrayIterator + 'static>

Returns a blocking iterator over the scan.

All work will be performed on the current thread, with tasks interleaved per the configured concurrency. Any configured executor will be ignored.