Struct DuplicateCluster 

pub struct DuplicateCluster {
    pub id: usize,
    pub indices: Vec<usize>,
    pub representative: usize,
}

A cluster of duplicate documents.

Fields

id: usize

Cluster ID (sequential from 0).

indices: Vec<usize>

Document indices in this cluster.

representative: usize

Representative index (first in cluster).

Implementations

impl DuplicateCluster

pub fn new(id: usize, representative: usize) -> Self

Create a new duplicate cluster.

pub fn add(&mut self, index: usize)

Add an index to the cluster.

pub fn len(&self) -> usize

Get the number of documents.

pub fn is_empty(&self) -> bool

Check if cluster has no documents.

pub fn is_duplicate(&self) -> bool

Check if cluster has duplicates.

pub fn contains(&self, index: usize) -> bool

Check if this cluster contains a document.

Trait Implementations

impl Clone for DuplicateCluster

fn clone(&self) -> DuplicateCluster

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DuplicateCluster

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

Formats the value using the given formatter.

impl PartialEq for DuplicateCluster

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for DuplicateCluster