Struct FileReader 

pub struct FileReader { /* private fields */ }

A current-format Lance file reader backed by fully decoded metadata.

Implementations

impl FileReader

pub fn with_scheduler(&self, scheduler: Arc<dyn EncodingsIo>) -> Self

pub fn with_io_stats(&self, stats: Arc<dyn IoStatsRecorder>) -> Self

Returns a clone of this reader whose I/O is additionally recorded into stats, on top of the scheduler’s global accounting.

All cached metadata is shared with self, so no file is re-opened and only a few Arc clones are performed. If the underlying I/O service does not support per-scope statistics (e.g. an in-memory scheduler), the returned reader is an ordinary, uninstrumented clone.

pub fn with_coalesce_gap(&self, gap: u64) -> Self

Returns a clone of this reader whose I/O merges requested byte ranges that are at most gap bytes apart into one request, instead of those within the object store’s block size.

Each range is cut back out of the merged request and decoded as before, so reads return the same data at every gap; a wider gap reads the bytes between the ranges too, in fewer requests. All cached metadata is shared with self. If the underlying I/O service does not coalesce requests (e.g. an in-memory scheduler), the returned reader is an ordinary clone.

pub fn num_rows(&self) -> u64

pub fn column_num_rows(&self, column_index: usize) -> Result<u64>

The number of rows stored in a single physical column.

For ordinary (rectangular) files every column has the same length, equal to num_rows. Files written with FileWriter::write_column may have columns of differing lengths; this returns the length of one such column, derived by summing its pages’ row counts. Errors if column_index is out of bounds.

pub fn metadata(&self) -> &Arc<CachedFileMetadata>

pub fn file_statistics(&self) -> FileStatistics

pub async fn read_global_buffer(&self, index: u32) -> Result<Bytes>

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

impl FileReader

pub async fn try_open( scheduler: FileScheduler, base_projection: Option<ReaderProjection>, decoder_plugins: Arc<DecoderPlugins>, cache: &LanceCache, options: FileReaderOptions, ) -> Result<Self>

pub async fn try_open_with_file_metadata( scheduler: Arc<dyn EncodingsIo>, path: Path, base_projection: Option<ReaderProjection>, decoder_plugins: Arc<DecoderPlugins>, metadata: Arc<CachedFileMetadata>, cache: &LanceCache, options: FileReaderOptions, ) -> Result<Self>

pub async fn read_all_metadata( scheduler: &FileScheduler, ) -> Result<CachedFileMetadata>

pub async fn read_metadata_index( scheduler: &FileScheduler, ) -> Result<FileMetadataIndex>

pub async fn read_metadata_index_with_schema( scheduler: &FileScheduler, file_schema: Arc<Schema>, num_rows: u64, ) -> Result<FileMetadataIndex>

pub fn version(&self) -> ConcreteFileVersion

pub async fn read_tasks( &self, params: ReadBatchParams, batch_size: u32, projection: Option<ReaderProjection>, filter: FilterExpression, ) -> Result<Pin<Box<dyn Stream<Item = ReadBatchTask> + Send>>>

pub async fn read_stream_projected( &self, params: ReadBatchParams, batch_size: u32, batch_readahead: u32, projection: ReaderProjection, filter: FilterExpression, ) -> Result<Pin<Box<dyn RecordBatchStream>>>

pub fn read_stream_projected_blocking( &self, params: ReadBatchParams, batch_size: u32, projection: Option<ReaderProjection>, filter: FilterExpression, ) -> Result<Box<dyn RecordBatchReader + Send + 'static>>

pub async fn read_stream( &self, params: ReadBatchParams, batch_size: u32, batch_readahead: u32, filter: FilterExpression, ) -> Result<Pin<Box<dyn RecordBatchStream>>>

Trait Implementations

impl Clone for FileReader

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FileReader

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

Formats the value using the given formatter.