Struct deltalake::datafusion::parquet::arrow::async_reader::ParquetObjectReader

pub struct ParquetObjectReader { /* private fields */ }

Reads Parquet files in object storage using ObjectStore.

// Populate configuration from environment
let storage_container = Arc::new(MicrosoftAzureBuilder::from_env().build().unwrap());
let location = Path::from("path/to/blob.parquet");
let meta = storage_container.head(&location).await.unwrap();
println!("Found Blob with {}B at {}", meta.size, meta.location);

// Show Parquet metadata
let reader = ParquetObjectReader::new(storage_container, meta);
let builder = ParquetRecordBatchStreamBuilder::new(reader).await.unwrap();
print_parquet_metadata(&mut stdout(), builder.metadata());

Implementations

impl ParquetObjectReader

pub fn new(store: Arc<dyn ObjectStore>, meta: ObjectMeta) -> ParquetObjectReader

Creates a new ParquetObjectReader for the provided ObjectStore and ObjectMeta

ObjectMeta can be obtained using ObjectStore::list or ObjectStore::head

pub fn with_footer_size_hint(self, hint: usize) -> ParquetObjectReader

Provide a hint as to the size of the parquet file’s footer, see fetch_parquet_metadata

pub fn with_preload_column_index( self, preload_column_index: bool ) -> ParquetObjectReader

Load the Column Index as part of Self::get_metadata

pub fn with_preload_offset_index( self, preload_offset_index: bool ) -> ParquetObjectReader

Load the Offset Index as part of Self::get_metadata

Trait Implementations

impl AsyncFileReader for ParquetObjectReader

fn get_bytes( &mut self, range: Range<usize> ) -> Pin<Box<dyn Future<Output = Result<Bytes, ParquetError>> + Send + '_>>

Retrieve the bytes in range

fn get_byte_ranges( &mut self, ranges: Vec<Range<usize>> ) -> Pin<Box<dyn Future<Output = Result<Vec<Bytes>, ParquetError>> + Send + '_>>

where ParquetObjectReader: Send,

Retrieve multiple byte ranges. The default implementation will call get_bytes sequentially

fn get_metadata( &mut self ) -> Pin<Box<dyn Future<Output = Result<Arc<ParquetMetaData>, ParquetError>> + Send + '_>>

Provides asynchronous access to the ParquetMetaData of a parquet file, allowing fine-grained control over how metadata is sourced, in particular allowing for caching, pre-fetching, catalog metadata, etc…

impl Clone for ParquetObjectReader

fn clone(&self) -> ParquetObjectReader

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for ParquetObjectReader

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

Formats the value using the given formatter.