Struct FileReader

pub struct FileReader {
    pub object_reader: Arc<dyn Reader>,
    /* private fields */
}

Lance File Reader.

It reads arrow data from one data file.

Fields

object_reader: Arc<dyn Reader>

Implementations

impl FileReader

pub async fn try_new_with_fragment_id( object_store: &ObjectStore, path: &Path, schema: Schema, fragment_id: u32, field_id_offset: i32, max_field_id: i32, session: Option<&FileMetadataCache>, ) -> Result<Self>

Open file reader

Open the file at the given path using the provided object store.

The passed fragment ID determines the first 32-bits of the row IDs.

If a manifest is passed in, it will be used to load the schema and dictionary. This is typically done if the file is part of a dataset fragment. If no manifest is passed in, then it is read from the file itself.

The session passed in is used to cache metadata about the file. If no session is passed in, there will be no caching.

pub async fn try_new_from_reader( path: &Path, object_reader: Arc<dyn Reader>, metadata: Option<Arc<Metadata>>, schema: Schema, fragment_id: u32, field_id_offset: i32, max_field_id: i32, session: Option<&FileMetadataCache>, ) -> Result<Self>

pub async fn read_metadata( object_reader: &dyn Reader, cache: Option<&FileMetadataCache>, ) -> Result<Arc<Metadata>>

pub async fn try_new( object_store: &ObjectStore, path: &Path, schema: Schema, ) -> Result<Self>

Open one Lance data file for read.

pub fn schema(&self) -> &Schema

Requested projection of the data in this file, excluding the row id column.

pub fn num_batches(&self) -> usize

pub fn num_rows_in_batch(&self, batch_id: i32) -> usize

Get the number of rows in this batch

pub fn len(&self) -> usize

Count the number of rows in this file.

pub fn is_empty(&self) -> bool

pub async fn read_batch( &self, batch_id: i32, params: impl Into<ReadBatchParams>, projection: &Schema, ) -> Result<RecordBatch>

Read a batch of data from the file.

The schema of the returned RecordBatch is set by FileReader::schema().

pub async fn read_range( &self, range: Range<usize>, projection: &Schema, ) -> Result<RecordBatch>

Read a range of records into one batch.

Note that it might call concat if the range is crossing multiple batches, which makes it less efficient than FileReader::read_batch().

pub async fn take( &self, indices: &[u32], projection: &Schema, ) -> Result<RecordBatch>

Take by records by indices within the file.

The indices must be sorted.

pub fn page_stats_schema(&self, field_ids: &[i32]) -> Option<Schema>

Get the schema of the statistics page table, for the given data field ids.

pub async fn read_page_stats( &self, field_ids: &[i32], ) -> Result<Option<RecordBatch>>

Get the page statistics for the given data field ids.

Trait Implementations

impl Clone for FileReader

fn clone(&self) -> FileReader

Returns a copy 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.

impl DeepSizeOf for FileReader

fn deep_size_of_children(&self, context: &mut Context) -> usize

Returns an estimation of the heap-managed storage of this object. This does not include the size of the object itself.

fn deep_size_of(&self) -> usize

Returns an estimation of a total size of memory owned by the object, including heap-managed storage.