Struct TokenizerConfig

pub struct TokenizerConfig { /* private fields */ }

Tokenizer configs

Implementations

impl TokenizerConfig

pub fn new(base_tokenizer: String, language: Language) -> Self

pub fn base_tokenizer(self, base_tokenizer: String) -> Self

pub fn language(self, language: &str) -> Result<Self>

pub fn max_token_length(self, max_token_length: Option<usize>) -> Self

pub fn lower_case(self, lower_case: bool) -> Self

pub fn stem(self, stem: bool) -> Self

pub fn remove_stop_words(self, remove_stop_words: bool) -> Self

pub fn ascii_folding(self, ascii_folding: bool) -> Self

pub fn build(&self) -> Result<TextAnalyzer>

Trait Implementations

impl Clone for TokenizerConfig

fn clone(&self) -> TokenizerConfig

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for TokenizerConfig

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

Formats the value using the given formatter.

impl Default for TokenizerConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for TokenizerConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for TokenizerConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.