Skip to main content

CharTokenizer

torsh_data::text::transforms

Struct CharTokenizer

pub struct CharTokenizer;

Expand description

Character-level tokenization

Trait Implementations§

impl Transform<TextSequence> for CharTokenizer

type Output = TextSequence

fn transform(&self, input: TextSequence) -> Result<Self::Output>

Apply the transformation to the input

fn is_deterministic(&self) -> bool

Check if the transform is deterministic Read more

Auto Trait Implementations§

impl Freeze for CharTokenizer

impl RefUnwindSafe for CharTokenizer

impl Send for CharTokenizer

impl Sync for CharTokenizer

impl Unpin for CharTokenizer

impl UnsafeUnpin for CharTokenizer

impl UnwindSafe for CharTokenizer

Blanket Implementations§

impl<T> Any for T
where T: 'static + ?Sized,

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

impl<T> Borrow<T> for T
where T: ?Sized,

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

impl<T> BorrowMut<T> for T
where T: ?Sized,

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more

impl<T> From<T> for T

fn from(t: T) -> T

Returns the argument unchanged.

impl<T, U> Into<U> for T
where U: From<T>,

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

impl<T> IntoEither for T

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

impl<T> Pointable for T

const ALIGN: usize

The alignment of pointer.

type Init = T

The type for initializers.

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more

impl<T> Same for T

type Output = T

Should always be Self

impl<SS, SP> SupersetOf<SS> for SP
where SS: SubsetOf<SP>,

fn to_subset(&self) -> Option<SS>

The inverse inclusion map: attempts to construct self from the equivalent element of its superset. Read more

fn is_in_subset(&self) -> bool

Checks if self is actually part of its subset T (and can be converted to it).

fn to_subset_unchecked(&self) -> SS

Use with care! Same as self.to_subset but without any property checks. Always succeeds.

fn from_subset(element: &SS) -> SP

The inclusion map: converts self to the equivalent element of its superset.

impl<T, U> TransformExt<T> for U
where U: Transform<T>,

fn then<U: Transform<Self::Output>>(self, other: U) -> Chain<Self, U>
where Self: Sized,

Chain this transform with another

impl<T, U> TryFrom<U> for T
where U: Into<T>,

type Error = Infallible

The type returned in the event of a conversion error.

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

fn vzip(self) -> V