pub struct AnalyzerConfig {
pub base: BaseTokenizer,
pub language: FtsLanguage,
pub lower_case: bool,
pub stem: bool,
pub remove_stop_words: bool,
pub custom_stop_words: Option<Vec<String>>,
pub ascii_folding: bool,
pub max_token_length: Option<u32>,
}Expand description
Full analyzer pipeline configuration for a full-text index.
This is a backend-agnostic, plainly serializable description of the token
analysis chain. The uni-store Lance backend maps it onto the underlying
InvertedIndexParams; this crate stays free of any Lance dependency.
Every field carries #[serde(default)] so schemas persisted before a field
existed still deserialize.
Fields§
§base: BaseTokenizerBase tokenizer that splits raw text into tokens.
language: FtsLanguageLanguage used for stemming and built-in stop-word lists.
lower_case: boolWhether to lowercase tokens.
stem: boolWhether to apply language-specific stemming.
remove_stop_words: boolWhether to drop stop words (built-in list, or custom_stop_words).
custom_stop_words: Option<Vec<String>>Explicit stop-word list overriding the language’s built-in list.
ascii_folding: boolWhether to fold accented characters to ASCII (é → e).
max_token_length: Option<u32>Drop tokens longer than this many bytes (None keeps the backend default).
Trait Implementations§
Source§impl Clone for AnalyzerConfig
impl Clone for AnalyzerConfig
Source§fn clone(&self) -> AnalyzerConfig
fn clone(&self) -> AnalyzerConfig
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source. Read moreSource§impl Debug for AnalyzerConfig
impl Debug for AnalyzerConfig
Source§impl Default for AnalyzerConfig
impl Default for AnalyzerConfig
Source§impl<'de> Deserialize<'de> for AnalyzerConfig
impl<'de> Deserialize<'de> for AnalyzerConfig
Source§fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
Source§impl PartialEq for AnalyzerConfig
impl PartialEq for AnalyzerConfig
Source§impl Serialize for AnalyzerConfig
impl Serialize for AnalyzerConfig
impl StructuralPartialEq for AnalyzerConfig
Auto Trait Implementations§
impl Freeze for AnalyzerConfig
impl RefUnwindSafe for AnalyzerConfig
impl Send for AnalyzerConfig
impl Sync for AnalyzerConfig
impl Unpin for AnalyzerConfig
impl UnsafeUnpin for AnalyzerConfig
impl UnwindSafe for AnalyzerConfig
Blanket Implementations§
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
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,
impl<T> DeserializeOwned for Twhere
T: for<'de> Deserialize<'de>,
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>
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>
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