Struct SimHash64 

pub struct SimHash64(pub u64);

A 64-bit SimHash fingerprint.

Tuple Fields

0: u64

Implementations

impl SimHash64

pub fn from_features(features: &[WeightedFeature]) -> Self

pub fn from_features_with_options( features: &[WeightedFeature], options: SimHashOptions, ) -> Self

pub fn from_feature_hashes<I>(hashes: I) -> Self

where I: IntoIterator<Item = FeatureHash>,

pub fn from_feature_hashes_with_options<I>( hashes: I, options: SimHashOptions, ) -> Self

where I: IntoIterator<Item = FeatureHash>,

pub fn from_hashes_unweighted_fast(hashes: &[u64]) -> Self

Fast unweighted SimHash over pre-hashed elements.

This uses the byte-lane counter trick described by Otmar Ertl’s FastSimHash article: each byte lane in a u64 counts one bit position, then lanes are flushed before they can overflow. The result is equivalent to the normal unweighted SimHash path.

pub fn from_hashes_unweighted_fast_with_options( hashes: &[u64], options: SimHashOptions, ) -> Self

pub fn from_text(text: &str, extractor: &WebFeatureExtractor) -> Self

pub fn from_html(html: &str, extractor: &WebFeatureExtractor) -> Self

pub fn hamming_distance(self, other: Self) -> u32

pub fn similarity(self, other: Self) -> f64

pub fn is_near_duplicate(self, other: Self, max_distance: u32) -> bool

Trait Implementations

impl Clone for SimHash64

fn clone(&self) -> SimHash64

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for SimHash64

impl Debug for SimHash64

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

Formats the value using the given formatter.

impl Default for SimHash64

fn default() -> SimHash64

Returns the “default value” for a type.

impl Eq for SimHash64

impl Hash for SimHash64

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl Ord for SimHash64

fn cmp(&self, other: &SimHash64) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

where Self: Sized,

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

where Self: Sized,

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

where Self: Sized,

Restrict a value to a certain interval.

impl PartialEq for SimHash64

fn eq(&self, other: &SimHash64) -> bool

Equality operator ==.

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

Inequality operator !=.

impl PartialOrd for SimHash64

fn partial_cmp(&self, other: &SimHash64) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

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

Tests less than (for self and other) and is used by the < operator.

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

Tests less than or equal to (for self and other) and is used by the <= operator.

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

Tests greater than (for self and other) and is used by the > operator.

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

Tests greater than or equal to (for self and other) and is used by the >= operator.

impl StructuralPartialEq for SimHash64