Struct TextAnalyzer 

pub struct TextAnalyzer {
    pub stem: bool,
    pub stopwords: Stopwords,
    pub ascii_folding: bool,
    pub max_token_length: Option<usize>,
}

Fields

stem: bool

Snowball English stemming.

stopwords: Stopwords

Stop-word removal policy.

ascii_folding: bool

Fold accents via NFKD decomposition before lowercasing.

max_token_length: Option<usize>

Truncate tokens longer than this many characters.

Implementations

impl TextAnalyzer

pub fn plain() -> Self

The historical ANNex policy: lowercase alphanumeric tokens only.

pub fn english() -> Self

Stemming, English stop words, ASCII folding, and a 40-character limit.

pub fn validate(&self) -> Result<(), String>

pub fn description(&self) -> String

Stable identity for provenance records.

Trait Implementations

impl Clone for TextAnalyzer

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TextAnalyzer

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

Formats the value using the given formatter.

impl Default for TextAnalyzer

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for TextAnalyzer

where TextAnalyzer: Default,

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for TextAnalyzer

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl Serialize for TextAnalyzer

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for TextAnalyzer