Struct DatasetRegistry 

pub struct DatasetRegistry { /* private fields */ }

Registry for dynamically registered custom datasets.

This allows users to register their own datasets at runtime without modifying the built-in enum.

Implementations

impl DatasetRegistry

pub fn new() -> DatasetRegistry

Create a new empty registry.

pub fn register( &mut self, dataset: impl DatasetSpec + 'static, ) -> Option<Box<dyn DatasetSpec>>

Register a custom dataset.

Returns the previous dataset with this ID if one existed.

pub fn get(&self, id: &str) -> Option<&dyn DatasetSpec>

Get a dataset by ID.

pub fn unregister(&mut self, id: &str) -> Option<Box<dyn DatasetSpec>>

Remove a dataset by ID.

pub fn list_ids(&self) -> Vec<&str>

List all registered dataset IDs.

pub fn len(&self) -> usize

Number of registered datasets.

pub fn is_empty(&self) -> bool

Check if registry is empty.

pub fn iter(&self) -> impl Iterator<Item = (&str, &dyn DatasetSpec)>

Iterate over all registered datasets.

pub fn by_task(&self, task: Task) -> impl Iterator<Item = &dyn DatasetSpec>

Filter datasets by task.

pub fn by_language<'a>( &'a self, lang: &'a str, ) -> impl Iterator<Item = &'a dyn DatasetSpec>

Filter datasets by language.

pub fn by_domain( &self, domain: Domain, ) -> impl Iterator<Item = &dyn DatasetSpec>

Filter datasets by domain.

pub fn public_only(&self) -> impl Iterator<Item = &dyn DatasetSpec>

Filter datasets that are publicly available (no auth, redistributable license).

pub fn historical(&self) -> impl Iterator<Item = &dyn DatasetSpec>

Filter historical/ancient language datasets.

pub fn with_entity_type<'a>( &'a self, entity_type: &'a str, ) -> impl Iterator<Item = &'a dyn DatasetSpec>

Find datasets supporting a specific entity type.

pub fn summary(&self) -> RegistrySummary

Get summary statistics about registered datasets.

Trait Implementations

impl Debug for DatasetRegistry

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

Formats the value using the given formatter.

impl Default for DatasetRegistry

fn default() -> DatasetRegistry

Returns the “default value” for a type.