Struct DatasetRecord 

pub struct DatasetRecord { /* private fields */ }

Format-agnostic structured dataset row.

Implementations

impl DatasetRecord

pub fn new(fields: BTreeMap<String, Value>) -> Self

Create a record from named fields.

pub fn from_fields<I, K>(fields: I) -> Self

where I: IntoIterator<Item = (K, Value)>, K: Into<String>,

Create a record from any iterator of named fields.

pub fn get(&self, name: &str) -> Option<&Value>

Borrow a field by name.

pub fn fields(&self) -> &BTreeMap<String, Value>

Borrow all record fields in deterministic key order.

pub fn into_fields(self) -> BTreeMap<String, Value>

Consume this record into its fields.

pub fn select(&self, columns: &[String]) -> Self

Return a projected record with only the requested columns.

pub fn into_json(self) -> Value

Convert this record to a JSON object.

pub fn to_json(&self) -> Value

Borrow this record as a JSON object without consuming it.

Trait Implementations

impl Clone for DatasetRecord

fn clone(&self) -> DatasetRecord

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl DatasetItem for DatasetRecord

fn label(&self) -> Label

Classification label used to route and count the item. Defaults to Label::Real.

fn source_offset(&self) -> Option<usize>

Source-provided resume cursor observed after this item, if any.

impl Debug for DatasetRecord

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

Formats the value using the given formatter.

impl ItemSink<DatasetRecord> for RecordSink

fn name(&self) -> &str

Stable sink name.

fn prepare<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = AppResult<()>> + Send + 'async_trait>>

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

Prepare the destination before any item is written (create directories, seed counters).

fn write<'life0, 'async_trait>( &'life0 self, item: DatasetRecord, ) -> Pin<Box<dyn Future<Output = AppResult<()>> + Send + 'async_trait>>

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

Materialize a single collected item.

fn finish<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = AppResult<()>> + Send + 'async_trait>>

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

Flush and finalize the destination after the last item is written.

impl PartialEq for DatasetRecord

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

Equality operator ==.

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

Inequality operator !=.

impl Source<DatasetRecord> for RecordSource

fn name(&self) -> &str

Stable source identifier used in manifests.

fn stream( self: Box<Self>, _cancel: CancellationToken, ) -> BoxItemStream<DatasetRecord>

Stream items from this source.

fn cache_key(&self) -> Value

Stable cache key describing this source’s configured inputs.

fn max_items(&self) -> Option<usize>

Optional maximum number of items this source will emit.

fn display_name(&self) -> &str

Human-readable source label.

fn set_resume_state(&mut self, _offset: usize, _already_fetched: usize)

Configure resume state before streaming.

impl StructuralPartialEq for DatasetRecord

impl Validator<DatasetRecord> for SchemaValidator

fn validate(&self, item: &DatasetRecord) -> AppResult<()>

Return an error when item fails validation; Ok(()) accepts it.