Struct DeltaTable

pub struct DeltaTable {
    pub state: Option<DeltaTableState>,
    pub config: DeltaTableConfig,
    /* private fields */
}

In memory representation of a Delta Table

Fields

state: Option<DeltaTableState>

The state of the table as of the most recent loaded Delta log entry.

config: DeltaTableConfig

the load options used during load

Implementations

impl DeltaTable

pub fn new(log_store: LogStoreRef, config: DeltaTableConfig) -> Self

Create a new Delta Table struct without loading any data from backing storage.

NOTE: This is for advanced users. If you don’t know why you need to use this method, please call one of the open_table helper methods instead.

pub fn object_store(&self) -> ObjectStoreRef

get a shared reference to the delta object store

pub async fn verify_deltatable_existence(&self) -> DeltaResult<bool>

Check if the DeltaTable exists

pub fn table_uri(&self) -> String

The URI of the underlying data

pub fn log_store(&self) -> LogStoreRef

get a shared reference to the log store

pub async fn get_latest_version(&self) -> Result<i64, DeltaTableError>

returns the latest available version of the table

pub async fn get_earliest_version(&self) -> Result<i64, DeltaTableError>

returns the earliest available version of the table

pub fn version(&self) -> i64

Currently loaded version of the table

pub async fn load(&mut self) -> Result<(), DeltaTableError>

Load DeltaTable with data from latest checkpoint

pub async fn update(&mut self) -> Result<(), DeltaTableError>

Updates the DeltaTable to the most recent state committed to the transaction log by loading the last checkpoint and incrementally applying each version since.

pub async fn peek_next_commit( &self, current_version: i64, ) -> Result<PeekCommit, DeltaTableError>

Get the list of actions for the next commit

pub async fn update_incremental( &mut self, max_version: Option<i64>, ) -> Result<(), DeltaTableError>

Updates the DeltaTable to the latest version by incrementally applying newer versions. It assumes that the table is already updated to the current version self.version.

pub async fn load_version( &mut self, version: i64, ) -> Result<(), DeltaTableError>

Loads the DeltaTable state for the given version.

pub async fn history( &self, limit: Option<usize>, ) -> Result<Vec<CommitInfo>, DeltaTableError>

Returns provenance information, including the operation, user, and so on, for each write to a table. The table history retention is based on the logRetentionDuration property of the Delta Table, 30 days by default. If limit is given, this returns the information of the latest limit commits made to this table. Otherwise, it returns all commits from the earliest commit.

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

pub fn get_files_by_partitions( &self, filters: &[PartitionFilter], ) -> Result<Vec<Path>, DeltaTableError>

Returns the file list tracked in current table state filtered by provided PartitionFilters.

pub fn get_file_uris_by_partitions( &self, filters: &[PartitionFilter], ) -> Result<Vec<String>, DeltaTableError>

Return the file uris as strings for the partition(s)

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

Returns an iterator of file names present in the loaded state

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

Returns a URIs for all active files present in the current table version.

pub fn get_files_count(&self) -> usize

Get the number of files in the table - returns 0 if no metadata is loaded

pub fn snapshot(&self) -> DeltaResult<&DeltaTableState>

Returns the currently loaded state snapshot.

pub fn protocol(&self) -> DeltaResult<&Protocol>

Returns current table protocol

pub fn metadata(&self) -> Result<&Metadata, DeltaTableError>

Returns the metadata associated with the loaded state.

pub fn get_app_transaction_version(&self) -> HashMap<String, Transaction>

Returns the current version of the DeltaTable based on the loaded metadata.

pub fn schema(&self) -> Option<&StructType>

Return table schema parsed from transaction log. Return None if table hasn’t been loaded or no metadata was found in the log.

pub fn get_schema(&self) -> Result<&StructType, DeltaTableError>

Return table schema parsed from transaction log. Return DeltaTableError if table hasn’t been loaded or no metadata was found in the log.

pub async fn load_with_datetime( &mut self, datetime: DateTime<Utc>, ) -> Result<(), DeltaTableError>

Time travel Delta table to the latest version that’s created at or before provided datetime argument.

Internally, this methods performs a binary search on all Delta transaction logs.

Trait Implementations

impl AsRef<DeltaTable> for DeltaOps

fn as_ref(&self) -> &DeltaTable

Converts this type into a shared reference of the (usually inferred) input type.

impl Clone for DeltaTable

fn clone(&self) -> DeltaTable

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for DeltaTable

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DeltaTable

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

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for DeltaTable

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

Formats the value using the given formatter.

impl From<DeltaOps> for DeltaTable

fn from(ops: DeltaOps) -> Self

Converts to this type from the input type.

impl From<DeltaTable> for DeltaOps

fn from(table: DeltaTable) -> Self

Converts to this type from the input type.

impl Serialize for DeltaTable

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

where S: Serializer,

Serialize this value into the given Serde serializer.

impl TableProvider for DeltaTable

fn as_any(&self) -> &dyn Any

Returns the table provider as Any so that it can be downcast to a specific implementation.

fn schema(&self) -> Arc<ArrowSchema>

Get a reference to the schema for this table

fn table_type(&self) -> TableType

Get the type of this table for metadata/catalog purposes.

fn get_table_definition(&self) -> Option<&str>

Get the create statement used to create this table, if available.

fn get_logical_plan(&self) -> Option<Cow<'_, LogicalPlan>>

Get the LogicalPlan of this table, if available.

fn scan<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, session: &'life1 dyn Session, projection: Option<&'life2 Vec<usize>>, filters: &'life3 [Expr], limit: Option<usize>, ) -> Pin<Box<dyn Future<Output = DataFusionResult<Arc<dyn ExecutionPlan>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, 'life3: 'async_trait,

Create an ExecutionPlan for scanning the table with optionally specified projection, filter and limit, described below.

fn supports_filters_pushdown( &self, filter: &[&Expr], ) -> DataFusionResult<Vec<TableProviderFilterPushDown>>

Specify if DataFusion should provide filter expressions to the TableProvider to apply during the scan.

fn statistics(&self) -> Option<Statistics>

Get statistics for this table, if available

fn constraints(&self) -> Option<&Constraints>

Get a reference to the constraints of the table. Returns:

fn get_column_default(&self, _column: &str) -> Option<&Expr>

Get the default value for a column, if available.

fn insert_into<'life0, 'life1, 'async_trait>( &'life0 self, _state: &'life1 dyn Session, _input: Arc<dyn ExecutionPlan>, _insert_op: InsertOp, ) -> Pin<Box<dyn Future<Output = Result<Arc<dyn ExecutionPlan>, DataFusionError>> + Send + 'async_trait>>

where 'life0: 'async_trait, 'life1: 'async_trait, Self: 'async_trait,

Return an ExecutionPlan to insert data into this table, if supported.