pub struct TokenizerConfig {
pub mode: TokenizerMode,
pub lowercase: bool,
pub min_token_length: usize,
pub max_token_length: usize,
pub ngram_size: usize,
pub stop_words: Vec<String>,
}Expand description
Configuration for SemanticTokenizer.
Fields§
§mode: TokenizerModeTokenization mode.
lowercase: boolWhether to lowercase all tokens (default true).
min_token_length: usizeMinimum token length to keep (default 1).
max_token_length: usizeMaximum token length to keep (default 100).
ngram_size: usizeCharacter n-gram size (only used with TokenizerMode::NGram, default 3).
stop_words: Vec<String>Words to exclude from output.
Trait Implementations§
Source§impl Clone for TokenizerConfig
impl Clone for TokenizerConfig
Source§fn clone(&self) -> TokenizerConfig
fn clone(&self) -> TokenizerConfig
Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreSource§impl Debug for TokenizerConfig
impl Debug for TokenizerConfig
Auto Trait Implementations§
impl Freeze for TokenizerConfig
impl RefUnwindSafe for TokenizerConfig
impl Send for TokenizerConfig
impl Sync for TokenizerConfig
impl Unpin for TokenizerConfig
impl UnsafeUnpin for TokenizerConfig
impl UnwindSafe for TokenizerConfig
Blanket Implementations§
impl<T> Allocation for T
Source§impl<'a, T, E> AsTaggedExplicit<'a, E> for Twhere
T: 'a,
impl<'a, T, E> AsTaggedExplicit<'a, E> for Twhere
T: 'a,
Source§impl<'a, T, E> AsTaggedImplicit<'a, E> for Twhere
T: 'a,
impl<'a, T, E> AsTaggedImplicit<'a, E> for Twhere
T: 'a,
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
Source§impl<T> Instrument for T
impl<T> Instrument for T
Source§fn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
Source§fn in_current_span(self) -> Instrumented<Self>
fn in_current_span(self) -> Instrumented<Self>
Source§impl<T> IntoEither for T
impl<T> IntoEither for T
Source§fn into_either(self, into_left: bool) -> Either<Self, Self>
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 moreSource§fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
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 moreSource§impl<T> Pointable for T
impl<T> Pointable for T
impl<T> Read<Exclusive, BecauseExclusive> for Twhere
T: ?Sized,
Source§impl<SS, SP> SupersetOf<SS> for SPwhere
SS: SubsetOf<SP>,
impl<SS, SP> SupersetOf<SS> for SPwhere
SS: SubsetOf<SP>,
Source§fn to_subset(&self) -> Option<SS>
fn to_subset(&self) -> Option<SS>
The inverse inclusion map: attempts to construct
self from the equivalent element of its
superset. Read moreSource§fn is_in_subset(&self) -> bool
fn is_in_subset(&self) -> bool
Checks if
self is actually part of its subset T (and can be converted to it).Source§fn to_subset_unchecked(&self) -> SS
fn to_subset_unchecked(&self) -> SS
Use with care! Same as
self.to_subset but without any property checks. Always succeeds.Source§fn from_subset(element: &SS) -> SP
fn from_subset(element: &SS) -> SP
The inclusion map: converts
self to the equivalent element of its superset.