You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
136 lines
3.8 KiB
136 lines
3.8 KiB
(function() { |
|
'use strict'; |
|
|
|
var collator; |
|
try { |
|
collator = (typeof Intl !== "undefined" && typeof Intl.Collator !== "undefined") ? Intl.Collator("generic", { sensitivity: "base" }) : null; |
|
} catch (err){ |
|
console.log("Collator could not be initialized and wouldn't be used"); |
|
} |
|
// arrays to re-use |
|
var prevRow = [], |
|
str2Char = []; |
|
|
|
/** |
|
* Based on the algorithm at http://en.wikipedia.org/wiki/Levenshtein_distance. |
|
*/ |
|
var Levenshtein = { |
|
/** |
|
* Calculate levenshtein distance of the two strings. |
|
* |
|
* @param str1 String the first string. |
|
* @param str2 String the second string. |
|
* @param [options] Additional options. |
|
* @param [options.useCollator] Use `Intl.Collator` for locale-sensitive string comparison. |
|
* @return Integer the levenshtein distance (0 and above). |
|
*/ |
|
get: function(str1, str2, options) { |
|
var useCollator = (options && collator && options.useCollator); |
|
|
|
var str1Len = str1.length, |
|
str2Len = str2.length; |
|
|
|
// base cases |
|
if (str1Len === 0) return str2Len; |
|
if (str2Len === 0) return str1Len; |
|
|
|
// two rows |
|
var curCol, nextCol, i, j, tmp; |
|
|
|
// initialise previous row |
|
for (i=0; i<str2Len; ++i) { |
|
prevRow[i] = i; |
|
str2Char[i] = str2.charCodeAt(i); |
|
} |
|
prevRow[str2Len] = str2Len; |
|
|
|
var strCmp; |
|
if (useCollator) { |
|
// calculate current row distance from previous row using collator |
|
for (i = 0; i < str1Len; ++i) { |
|
nextCol = i + 1; |
|
|
|
for (j = 0; j < str2Len; ++j) { |
|
curCol = nextCol; |
|
|
|
// substution |
|
strCmp = 0 === collator.compare(str1.charAt(i), String.fromCharCode(str2Char[j])); |
|
|
|
nextCol = prevRow[j] + (strCmp ? 0 : 1); |
|
|
|
// insertion |
|
tmp = curCol + 1; |
|
if (nextCol > tmp) { |
|
nextCol = tmp; |
|
} |
|
// deletion |
|
tmp = prevRow[j + 1] + 1; |
|
if (nextCol > tmp) { |
|
nextCol = tmp; |
|
} |
|
|
|
// copy current col value into previous (in preparation for next iteration) |
|
prevRow[j] = curCol; |
|
} |
|
|
|
// copy last col value into previous (in preparation for next iteration) |
|
prevRow[j] = nextCol; |
|
} |
|
} |
|
else { |
|
// calculate current row distance from previous row without collator |
|
for (i = 0; i < str1Len; ++i) { |
|
nextCol = i + 1; |
|
|
|
for (j = 0; j < str2Len; ++j) { |
|
curCol = nextCol; |
|
|
|
// substution |
|
strCmp = str1.charCodeAt(i) === str2Char[j]; |
|
|
|
nextCol = prevRow[j] + (strCmp ? 0 : 1); |
|
|
|
// insertion |
|
tmp = curCol + 1; |
|
if (nextCol > tmp) { |
|
nextCol = tmp; |
|
} |
|
// deletion |
|
tmp = prevRow[j + 1] + 1; |
|
if (nextCol > tmp) { |
|
nextCol = tmp; |
|
} |
|
|
|
// copy current col value into previous (in preparation for next iteration) |
|
prevRow[j] = curCol; |
|
} |
|
|
|
// copy last col value into previous (in preparation for next iteration) |
|
prevRow[j] = nextCol; |
|
} |
|
} |
|
return nextCol; |
|
} |
|
|
|
}; |
|
|
|
// amd |
|
if (typeof define !== "undefined" && define !== null && define.amd) { |
|
define(function() { |
|
return Levenshtein; |
|
}); |
|
} |
|
// commonjs |
|
else if (typeof module !== "undefined" && module !== null && typeof exports !== "undefined" && module.exports === exports) { |
|
module.exports = Levenshtein; |
|
} |
|
// web worker |
|
else if (typeof self !== "undefined" && typeof self.postMessage === 'function' && typeof self.importScripts === 'function') { |
|
self.Levenshtein = Levenshtein; |
|
} |
|
// browser main thread |
|
else if (typeof window !== "undefined" && window !== null) { |
|
window.Levenshtein = Levenshtein; |
|
} |
|
}()); |
|
|
|
|