15 lines
1.4 KiB
JavaScript
15 lines
1.4 KiB
JavaScript
import diacritics from 'diacritics';
|
||
|
||
// remove spaces, punctuation, diacritics
|
||
// for punction see https://stackoverflow.com/a/21224179
|
||
export function simplify(str) {
|
||
if (typeof str !== 'string') return '';
|
||
|
||
return diacritics.remove(
|
||
str
|
||
.replace(/&/g, 'and')
|
||
.replace(/İ/ig, 'i') // for BİM, İşbank - #5017
|
||
.replace(/[\s\-=_!"#%'*{},.\/:;?\(\)\[\]@\\$\^*+<>«»~`’\u00a1\u00a7\u00b6\u00b7\u00bf\u037e\u0387\u055a-\u055f\u0589\u05c0\u05c3\u05c6\u05f3\u05f4\u0609\u060a\u060c\u060d\u061b\u061e\u061f\u066a-\u066d\u06d4\u0700-\u070d\u07f7-\u07f9\u0830-\u083e\u085e\u0964\u0965\u0970\u0af0\u0df4\u0e4f\u0e5a\u0e5b\u0f04-\u0f12\u0f14\u0f85\u0fd0-\u0fd4\u0fd9\u0fda\u104a-\u104f\u10fb\u1360-\u1368\u166d\u166e\u16eb-\u16ed\u1735\u1736\u17d4-\u17d6\u17d8-\u17da\u1800-\u1805\u1807-\u180a\u1944\u1945\u1a1e\u1a1f\u1aa0-\u1aa6\u1aa8-\u1aad\u1b5a-\u1b60\u1bfc-\u1bff\u1c3b-\u1c3f\u1c7e\u1c7f\u1cc0-\u1cc7\u1cd3\u2000-\u206f\u2cf9-\u2cfc\u2cfe\u2cff\u2d70\u2e00-\u2e7f\u3001-\u3003\u303d\u30fb\ua4fe\ua4ff\ua60d-\ua60f\ua673\ua67e\ua6f2-\ua6f7\ua874-\ua877\ua8ce\ua8cf\ua8f8-\ua8fa\ua92e\ua92f\ua95f\ua9c1-\ua9cd\ua9de\ua9df\uaa5c-\uaa5f\uaade\uaadf\uaaf0\uaaf1\uabeb\ufe10-\ufe16\ufe19\ufe30\ufe45\ufe46\ufe49-\ufe4c\ufe50-\ufe52\ufe54-\ufe57\ufe5f-\ufe61\ufe68\ufe6a\ufe6b\ufeff\uff01-\uff03\uff05-\uff07\uff0a\uff0c\uff0e\uff0f\uff1a\uff1b\uff1f\uff20\uff3c\uff61\uff64\uff65]+/g,'')
|
||
.toLowerCase()
|
||
);
|
||
}
|