Created
July 1, 2016 09:37
-
-
Save rapee/ab633dc45beda305b8042f06d7c8b75a to your computer and use it in GitHub Desktop.
Regex for multiple languages (en/th/jp)
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
/** | |
* Make slug from string. | |
* Support: en, th, ja | |
* @see https://gist.github.com/mathewbyrne/1280286 | |
* @see http://so-zou.jp/software/tech/programming/tech/regular-expression/meta-character/variable-width-encoding.htm | |
* @see https://python3.wannaphong.com/2015/12/regular-expression-ภาษาไทย-และภาษาอื่น-python.html | |
* @return {String} Slug | |
*/ | |
const whitespace_like_regex = /[\s_]+/g; | |
// en: a-z, A-Z, 0-9, - | |
// th: Ko Kai - Sara Uu, Sara Ee - Thanthakhat, Thai Zero - Thai Nine | |
// (Excludes Phintu, Thai Baht, Nikhahit, Yamakkan, Fongman, Angkhankhu, Khomut) | |
// ja: Kanji, Hiragana, Katakana | |
const nonword_regex = /[^a-z0-9\-ก-\u0E39เ-\u0E4C๐-๙亜-熙ぁ-んァ-ヶ]+/g; | |
module.export = function slugify(str) { | |
return str.toString().toLowerCase() | |
.replace(whitespace_like_regex, '-') // Replace spaces with - | |
.replace(nonword_regex, '') // Remove all non-word chars | |
.replace(/\-\-+/g, '-') // Replace multiple - with single - | |
.replace(/^-+/, '') // Trim - from start of text | |
.replace(/-+$/, ''); | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment