Struct DeltaTableState

pub struct DeltaTableState { /* private fields */ }

State snapshot currently held by the Delta Table instance.

Implementations

impl DeltaTableState

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

Create a new DeltaTableState

pub fn version(&self) -> i64

Return table version

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

Get the timestamp when a version commit was created. This is the timestamp of the commit file. If the commit file is not present, None is returned.

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

Returns a semantic accessor to the currently loaded log data.

pub async fn all_tombstones( &self, store: Arc<dyn ObjectStore>, ) -> DeltaResult<impl Iterator<Item = Remove>>

Full list of tombstones (remove actions) representing files removed from table state).

pub async fn unexpired_tombstones( &self, store: Arc<dyn ObjectStore>, ) -> DeltaResult<impl Iterator<Item = Remove>>

List of unexpired tombstones (remove actions) representing files removed from table state. The retention period is set by deletedFileRetentionDuration with default value of 1 week.

pub fn file_actions(&self) -> DeltaResult<Vec<Add>>

Full list of add actions representing all parquet files that are part of the current delta table state.

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

Full list of add actions representing all parquet files that are part of the current delta table state.

pub fn files_count(&self) -> usize

Get the number of files in the current table state

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

Full list of all of the CDC files added as part of the changeDataFeed feature

pub fn file_paths_iter(&self) -> impl Iterator<Item = Path> + '_

Returns an iterator of file names present in the loaded state

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

HashMap containing the last transaction stored for every application.

pub fn protocol(&self) -> &Protocol

The most recent protocol of the table.

pub fn metadata(&self) -> &Metadata

The most recent metadata of the table.

pub fn schema(&self) -> &StructType

The table schema

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 snapshot(&self) -> &EagerSnapshot

Obtain the Eager snapshot of the state

pub async fn update( &mut self, log_store: Arc<dyn LogStore>, version: Option<i64>, ) -> Result<(), DeltaTableError>

Update the state of the table to the given version.

pub fn get_active_add_actions_by_partitions<'a>( &'a self, filters: &'a [PartitionFilter], ) -> Result<impl Iterator<Item = DeltaResult<LogicalFile<'a>>>, DeltaTableError>

Obtain Add actions for files that match the filter

impl DeltaTableState

pub fn add_actions_table( &self, flatten: bool, ) -> Result<RecordBatch, DeltaTableError>

Get an arrow::record_batch::RecordBatch containing add action data.

Arguments

• flatten - whether to flatten the schema. Partition values columns are given the prefix partition., statistics (null_count, min, and max) are given the prefix null_count., min., and max., and tags the prefix tags.. Nested field names are concatenated with ..

Data schema

Each row represents a file that is a part of the selected tables state.

• path (String): relative or absolute to a file.
• size_bytes (Int64): size of file in bytes.
• modification_time (Millisecond Timestamp): time the file was created.
• data_change (Boolean): false if data represents data moved from other files in the same transaction.
• partition.{partition column name} (matches column type): value of partition the file corresponds to.
• null_count.{col_name} (Int64): number of null values for column in this file.
• min.{col_name} (matches column type): minimum value of column in file (if available).
• max.{col_name} (matches column type): maximum value of column in file (if available).
• tag.{tag_key} (String): value of a metadata tag for the file.

impl DeltaTableState

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

Provide table level statistics to Datafusion

Trait Implementations

impl Clone for DeltaTableState

fn clone(&self) -> DeltaTableState

Returns a copy of the value.

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

Performs copy-assignment from source.

impl DataFusionMixins for DeltaTableState

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 DeltaTableState

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DeltaTableState

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PruningStatistics for DeltaTableState

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

Return the minimum values for the named column, if known.

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

Return the maximum values for the named column, if known.

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 UInt64Array

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

Return the number of rows for the named column in each container as an UInt64Array.

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

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

impl Serialize for DeltaTableState

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 DeltaTableState

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

Well known table configuration

fn protocol(&self) -> &Protocol

Get the table protocol of the snapshot

fn metadata(&self) -> &Metadata

Get the table metadata of the snapshot

fn eager_snapshot(&self) -> &EagerSnapshot

Try to cast this table reference to a EagerSnapshot