用javascript計算兩個字串的「相似度」、或反過來說兩個字串間的「距離」
source: http://andrew.hedges.name/experiments/levenshtein/
經測，該algorithm所謂兩個字串的distance，看來指的是兩個字串間有差異的字元的數量
/*
This script is free to use under the license below.
No obligation, but if you use this it I'd love to know, thanks!
Andrew Hedges, andrew@hedges.name
-----------------------------------------------------------------------------
The MIT License (MIT)
Copyright (c) 2016 Andrew Hedges
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
-----------------------------------------------------------------------------
*/
var levenshteinenator = (function () {
/**
* @param String a
* @param String b
* @return Array
*/
function levenshteinenator(a, b) {
var cost;
var m = a.length;
var n = b.length;
// make sure a.length >= b.length to use O(min(n,m)) space, whatever that is
if (m < n) {
var c = a; a = b; b = c;
var o = m; m = n; n = o;
}
var r = []; r[0] = [];
for (var c = 0; c < n + 1; ++c) {
r[0][c] = c;
}
for (var i = 1; i < m + 1; ++i) {
r[i] = []; r[i][0] = i;
for ( var j = 1; j < n + 1; ++j ) {
cost = a.charAt( i - 1 ) === b.charAt( j - 1 ) ? 0 : 1;
r[i][j] = minimator( r[i-1][j] + 1, r[i][j-1] + 1, r[i-1][j-1] + cost );
}
}
return r;
}
/**
* Return the smallest of the three numbers passed in
* @param Number x
* @param Number y
* @param Number z
* @return Number
*/
function minimator(x, y, z) {
if (x <= y && x <= z) return x;
if (y <= x && y <= z) return y;
return z;
}
return levenshteinenator;
}());
然，
- The Levenshtein distance and Jaro-Winler distance algorithms appear to only work well with short strings. [source]
