Created
October 3, 2019 00:36
-
-
Save ijt/f15aaec8dc4f35d84987d3da5e37ee50 to your computer and use it in GitHub Desktop.
Rust program to compute the trigram Jaccard similarity between two strings
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
//! The stringsim program prints out the trigram similarity of two strings | |
//! using what appears to be the same algorithm used by Postgres. | |
//! https://www.postgresql.org/docs/9.1/pgtrgm.html | |
use std::collections::HashSet; | |
use std::hash::Hash; | |
fn main() { | |
let args: Vec<String> = ::std::env::args().collect(); | |
if args.len() != 1+2 { | |
eprintln!("usage: stringsim s1 s2"); | |
::std::process::exit(1); | |
} | |
let s1 = &args[1]; | |
let s2 = &args[2]; | |
let sim = similarity(&s1, &s2); | |
println!("{}", sim); | |
} | |
fn similarity(a: &String, b: &String) -> f32 { | |
let ta = trigrams(a); | |
let tb = trigrams(b); | |
return jaccard(ta, tb); | |
} | |
fn trigrams(s: &String) -> HashSet<String> { | |
let mut ts = HashSet::new(); | |
let s = format!("{} ", s); | |
let mut p1 = ' '; | |
let mut p2 = ' '; | |
for c in s.chars() { | |
let v = vec![p1, p2, c]; | |
let t: String = v.into_iter().collect(); | |
ts.insert(t); | |
p1 = p2; | |
p2 = c; | |
} | |
ts | |
} | |
fn jaccard<T>(s1: HashSet<T>, s2: HashSet<T>) -> f32 where T: Hash+Eq { | |
let i = s1.intersection(&s2).count() as f32; | |
let u = s1.union(&s2).count() as f32; | |
return i / u; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment