Struct EagerSnapshot

pub struct EagerSnapshot { /* private fields */ }

A snapshot of a Delta table that has been eagerly loaded into memory.

Implementations

impl EagerSnapshot

pub fn datafusion_table_statistics(&self) -> Option<Statistics>

Provide table level statistics to Datafusion

impl EagerSnapshot

pub async fn try_new( table_root: &Path, store: Arc<dyn ObjectStore>, config: DeltaTableConfig, version: Option<i64>, ) -> DeltaResult<Self>

Create a new EagerSnapshot instance

pub async fn try_new_with_visitor( table_root: &Path, store: Arc<dyn ObjectStore>, config: DeltaTableConfig, version: Option<i64>, tracked_actions: HashSet<ActionType>, ) -> DeltaResult<Self>

Create a new EagerSnapshot instance

pub async fn update<'a>( &mut self, log_store: Arc<dyn LogStore>, target_version: Option<i64>, ) -> DeltaResult<()>

Update the snapshot to the given version

pub fn version(&self) -> i64

Get the table version of the snapshot

pub fn version_timestamp(&self, version: i64) -> Option<i64>

Get the timestamp of the given version

pub fn schema(&self) -> &StructType

Get the table schema of the snapshot

pub fn metadata(&self) -> &Metadata

Get the table metadata of the snapshot

pub fn protocol(&self) -> &Protocol

Get the table protocol of the snapshot

pub fn table_root(&self) -> Path

Get the table root of the snapshot

pub fn load_config(&self) -> &DeltaTableConfig

Get the table config which is loaded with of the snapshot

pub fn table_config(&self) -> TableConfig<'_>

Well known table configuration

pub fn log_data(&self) -> LogDataHandler<'_>

Get a LogDataHandler for the snapshot to inspect the currently loaded state of the log.

pub fn files_count(&self) -> usize

Get the number of files in the snapshot

pub fn file_actions(&self) -> DeltaResult<impl Iterator<Item = Add> + '_>

Get the files in the snapshot

pub fn files(&self) -> impl Iterator<Item = LogicalFile<'_>>

Get a file action iterator for the given version

pub fn cdc_files(&self) -> DeltaResult<impl Iterator<Item = AddCDCFile> + '_>

Get an iterator for the CDC files added in this version

pub fn transactions( &self, ) -> DeltaResult<impl Iterator<Item = Transaction> + '_>

Iterate over all latest app transactions

pub fn advance<'a>( &mut self, commits: impl IntoIterator<Item = &'a CommitData>, ) -> DeltaResult<i64>

Advance the snapshot based on the given commit actions

Trait Implementations

impl Clone for EagerSnapshot

fn clone(&self) -> EagerSnapshot

Returns a copy of the value.

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

Performs copy-assignment from source.

impl DataFusionMixins for EagerSnapshot

fn arrow_schema(&self) -> DeltaResult<ArrowSchemaRef>

The physical datafusion schema of a table

fn input_schema(&self) -> DeltaResult<ArrowSchemaRef>

Get the table schema as an ArrowSchemaRef

fn parse_predicate_expression( &self, expr: impl AsRef<str>, df_state: &SessionState, ) -> DeltaResult<Expr>

Parse an expression string into a datafusion Expr

impl Debug for EagerSnapshot

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EagerSnapshot

fn deserialize<D>(deserializer: D) -> Result<EagerSnapshot, D::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for EagerSnapshot

fn eq(&self, other: &EagerSnapshot) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl PruningStatistics for EagerSnapshot

fn min_values(&self, column: &Column) -> Option<ArrayRef>

return the minimum values for the named column, if known. Note: the returned array must contain num_containers() rows

fn max_values(&self, column: &Column) -> Option<ArrayRef>

return the maximum values for the named column, if known. Note: the returned array must contain num_containers() rows.

fn num_containers(&self) -> usize

return the number of containers (e.g. row groups) being pruned with these statistics

fn null_counts(&self, column: &Column) -> Option<ArrayRef>

return the number of null values for the named column as an Option<UInt64Array>.

Note: the returned array must contain num_containers() rows.

fn row_counts(&self, column: &Column) -> Option<ArrayRef>

return the number of rows for the named column in each container as an Option<UInt64Array>.

Note: the returned array must contain num_containers() rows

fn contained( &self, column: &Column, value: &HashSet<ScalarValue>, ) -> Option<BooleanArray>

Returns BooleanArray where each row represents information known about specific literal values in a column.

impl Serialize for EagerSnapshot

fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>

where S: Serializer,

Serialize this value into the given Serde serializer.

impl TableReference for EagerSnapshot

fn protocol(&self) -> &Protocol

Get the table protocol of the snapshot

fn metadata(&self) -> &Metadata

Get the table metadata of the snapshot

fn config(&self) -> TableConfig<'_>

Well known table configuration

fn eager_snapshot(&self) -> &EagerSnapshot

Try to cast this table reference to a EagerSnapshot

impl StructuralPartialEq for EagerSnapshot