Struct HashDB

pub struct HashDB<TExtractor>
where
    TExtractor: FeatureExtractor,
{
    pub feature_extractor: TExtractor,
    pub string_collection: Vec<String>,
    pub string_size_map: HashMap<usize, HashSet<String>>,
    pub string_feature_map: HashMap<usize, HashMap<(String, i32), HashSet<String>>>,
    pub lookup_cache: HashMap<(usize, (String, i32)), HashSet<String>>,
}

Fields

feature_extractor: TExtractor

string_collection: Vec<String>

string_size_map: HashMap<usize, HashSet<String>>

string_feature_map: HashMap<usize, HashMap<(String, i32), HashSet<String>>>

lookup_cache: HashMap<(usize, (String, i32)), HashSet<String>>

Implementations

impl<TExtractor> HashDB<TExtractor>

where TExtractor: FeatureExtractor,

pub fn new(feature_extractor: TExtractor) -> Self

Examples found in repository

examples/basic_usage.rs (line 13)

fn main() {
    let _cs = Cosine::new();

    let feature_extractor = CharacterNGrams {
        n: 3,
        padder: " ".to_string(),
    };

    let mut db = HashDB::new(feature_extractor);

    db.insert("hello".to_string());
    db.insert("help".to_string());
    db.insert("halo".to_string());
    db.insert("world".to_string());

    let (total_collection, avg_size_ngrams, total_ngrams) = db.describe_collection();
    println!(
        "Database contains {} strings, average n-gram size {:.2}, total n-grams {}.",
        total_collection, avg_size_ngrams, total_ngrams
    );

    //println!("Complete DB State: {:?}", db); # FIX: db needs a fmt.debug implementation

    let query = "prepress";

    let query_features = db.feature_extractor.extract(query);
    let query_size = query_features.len();

    println!("Query size: {}", query_size);

    println!("Extracted features from query '{}':", query);
    for (feature, count) in &query_features {
        println!(" - Feature: '{}', Count: {}", feature, count);
    }
}

pub fn lookup_feature_set_by_size_feature( &mut self, size: usize, feature: &(String, i32), ) -> &HashSet<String>

Trait Implementations

impl<TExtractor> SimStringDB for HashDB<TExtractor>

where TExtractor: FeatureExtractor,

fn get_max_feature_size(&self) -> usize

fn insert(&mut self, s: String)

fn describe_collection(&self) -> (usize, f64, usize)