Enum Tokenizer 

pub enum Tokenizer {
    Whitespace,
    Standard,
    Letter,
    NGram {
        min_gram: usize,
        max_gram: usize,
    },
    Pattern {
        pattern: String,
    },
    Keyword,
}

Variants

Whitespace

Standard

Letter

NGram

Fields

min_gram: usize

max_gram: usize

Pattern

Fields

pattern: String

Keyword

Implementations

impl Tokenizer

pub fn validate(&self) -> AnalysisResult<()>

Validate configuration without tokenizing input. This is used when an analyzer is registered, while Self::tokenize repeats the checks so deserialized legacy values can never bypass them.

pub fn tokenize(&self, text: &str) -> AnalysisResult<Vec<String>>

Trait Implementations

impl Clone for Tokenizer

fn clone(&self) -> Tokenizer

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Tokenizer

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Tokenizer

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Tokenizer

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

where __S: Serializer,

Serialize this value into the given Serde serializer.