-
-
Save codeguy/6684588 to your computer and use it in GitHub Desktop.
function string_to_slug (str) { | |
str = str.replace(/^\s+|\s+$/g, ''); // trim | |
str = str.toLowerCase(); | |
// remove accents, swap ñ for n, etc | |
var from = "àáäâèéëêìíïîòóöôùúüûñç·/_,:;"; | |
var to = "aaaaeeeeiiiioooouuuunc------"; | |
for (var i=0, l=from.length ; i<l ; i++) { | |
str = str.replace(new RegExp(from.charAt(i), 'g'), to.charAt(i)); | |
} | |
str = str.replace(/[^a-z0-9 -]/g, '') // remove invalid chars | |
.replace(/\s+/g, '-') // collapse whitespace and replace by - | |
.replace(/-+/g, '-'); // collapse dashes | |
return str; | |
} |
something similar to Django's slugify:
export default function (str: string) {
return str
.normalize('NFKD')
.toLowerCase()
.replace(/[^\w\s-]/g, '')
.trim()
.replace(/[-\s]+/g, '-');
};
and tests:
describe('test slugify', () => {
test('test1', () => {
expect(slugify(' Jack & Jill like numbers 1,2,3 and 4 and silly characters ?%.$!/'))
.toEqual('jack-jill-like-numbers-123-and-4-and-silly-characters');
});
test('test2', () => {
expect(slugify("Un \xe9l\xe9phant \xe0 l'or\xe9e du bois"))
.toEqual('un-elephant-a-loree-du-bois');
});
});
@amranwebdeveloper
I'm building a website that sometimes the slug have a chinese character and i want to keep it
1 - Create a file named cleanSlug.js
2 - Inside the file, copy and paste the code below
/**
* * This function create a slug friendily to use in your web application
* * Compatibility with chinese characters
* ! Chinese characters doesn't have any modification
* @param slug
* @returns cleaned slug
*/
export function cleanSlug(slug) {
slug = slug.replace(/^\s+|\s+$/g, '');
slug = slug.toLowerCase();
const from = 'àáäâèéëêìíïîòóöôùúüûñç·/_,:;';
const to = 'aaaaeeeeiiiioooouuuunc------';
for (let i = 0, l = from.length; i < l; i++) {
slug = slug.replace(new RegExp(from.charAt(i), 'g'), to.charAt(i));
}
slug = slug
.normalize('NFD')
.replace(/[^a-z0-9 -]^[\u4e00-\u9fa5]/g, '') // remove all that not are a letter, a number, and are not a chinese word
.replace(/\s+/g, '-')
.replace(/-+/g, '-')
.replace('-?', '')
.replace('?', '');
return slug;
}
Everybody here is missing the -
in .replace(/[^a-z0-9 ]/g, '')
=> .replace(/[^a-z0-9 -]/g, '')
just a quick edit with some more characters.
export default (str) => { str = String(str).toString(); str = str.replace(/^\s+|\s+$/g, ""); // trim str = str.toLowerCase(); // remove accents, swap ñ for n, etc const swaps = { '0': ['°', '₀', '۰', '0'], '1': ['¹', '₁', '۱', '1'], '2': ['²', '₂', '۲', '2'], '3': ['³', '₃', '۳', '3'], '4': ['⁴', '₄', '۴', '٤', '4'], '5': ['⁵', '₅', '۵', '٥', '5'], '6': ['⁶', '₆', '۶', '٦', '6'], '7': ['⁷', '₇', '۷', '7'], '8': ['⁸', '₈', '۸', '8'], '9': ['⁹', '₉', '۹', '9'], 'a': ['à', 'á', 'ả', 'ã', 'ạ', 'ă', 'ắ', 'ằ', 'ẳ', 'ẵ', 'ặ', 'â', 'ấ', 'ầ', 'ẩ', 'ẫ', 'ậ', 'ā', 'ą', 'å', 'α', 'ά', 'ἀ', 'ἁ', 'ἂ', 'ἃ', 'ἄ', 'ἅ', 'ἆ', 'ἇ', 'ᾀ', 'ᾁ', 'ᾂ', 'ᾃ', 'ᾄ', 'ᾅ', 'ᾆ', 'ᾇ', 'ὰ', 'ά', 'ᾰ', 'ᾱ', 'ᾲ', 'ᾳ', 'ᾴ', 'ᾶ', 'ᾷ', 'а', 'أ', 'အ', 'ာ', 'ါ', 'ǻ', 'ǎ', 'ª', 'ა', 'अ', 'ا', 'a', 'ä'], 'b': ['б', 'β', 'ب', 'ဗ', 'ბ', 'b'], 'c': ['ç', 'ć', 'č', 'ĉ', 'ċ', 'c'], 'd': ['ď', 'ð', 'đ', 'ƌ', 'ȡ', 'ɖ', 'ɗ', 'ᵭ', 'ᶁ', 'ᶑ', 'д', 'δ', 'د', 'ض', 'ဍ', 'ဒ', 'დ', 'd'], 'e': ['é', 'è', 'ẻ', 'ẽ', 'ẹ', 'ê', 'ế', 'ề', 'ể', 'ễ', 'ệ', 'ë', 'ē', 'ę', 'ě', 'ĕ', 'ė', 'ε', 'έ', 'ἐ', 'ἑ', 'ἒ', 'ἓ', 'ἔ', 'ἕ', 'ὲ', 'έ', 'е', 'ё', 'э', 'є', 'ə', 'ဧ', 'ေ', 'ဲ', 'ე', 'ए', 'إ', 'ئ', 'e'], 'f': ['ф', 'φ', 'ف', 'ƒ', 'ფ', 'f'], 'g': ['ĝ', 'ğ', 'ġ', 'ģ', 'г', 'ґ', 'γ', 'ဂ', 'გ', 'گ', 'g'], 'h': ['ĥ', 'ħ', 'η', 'ή', 'ح', 'ه', 'ဟ', 'ှ', 'ჰ', 'h'], 'i': ['í', 'ì', 'ỉ', 'ĩ', 'ị', 'î', 'ï', 'ī', 'ĭ', 'į', 'ı', 'ι', 'ί', 'ϊ', 'ΐ', 'ἰ', 'ἱ', 'ἲ', 'ἳ', 'ἴ', 'ἵ', 'ἶ', 'ἷ', 'ὶ', 'ί', 'ῐ', 'ῑ', 'ῒ', 'ΐ', 'ῖ', 'ῗ', 'і', 'ї', 'и', 'ဣ', 'ိ', 'ီ', 'ည်', 'ǐ', 'ი', 'इ', 'ی', 'i'], 'j': ['ĵ', 'ј', 'Ј', 'ჯ', 'ج', 'j'], 'k': ['ķ', 'ĸ', 'к', 'κ', 'Ķ', 'ق', 'ك', 'က', 'კ', 'ქ', 'ک', 'k'], 'l': ['ł', 'ľ', 'ĺ', 'ļ', 'ŀ', 'л', 'λ', 'ل', 'လ', 'ლ', 'l'], 'm': ['м', 'μ', 'م', 'မ', 'მ', 'm'], 'n': ['ñ', 'ń', 'ň', 'ņ', 'ʼn', 'ŋ', 'ν', 'н', 'ن', 'န', 'ნ', 'n'], 'o': ['ó', 'ò', 'ỏ', 'õ', 'ọ', 'ô', 'ố', 'ồ', 'ổ', 'ỗ', 'ộ', 'ơ', 'ớ', 'ờ', 'ở', 'ỡ', 'ợ', 'ø', 'ō', 'ő', 'ŏ', 'ο', 'ὀ', 'ὁ', 'ὂ', 'ὃ', 'ὄ', 'ὅ', 'ὸ', 'ό', 'о', 'و', 'θ', 'ို', 'ǒ', 'ǿ', 'º', 'ო', 'ओ', 'o', 'ö'], 'p': ['п', 'π', 'ပ', 'პ', 'پ', 'p'], 'q': ['ყ', 'q'], 'r': ['ŕ', 'ř', 'ŗ', 'р', 'ρ', 'ر', 'რ', 'r'], 's': ['ś', 'š', 'ş', 'с', 'σ', 'ș', 'ς', 'س', 'ص', 'စ', 'ſ', 'ს', 's'], 't': ['ť', 'ţ', 'т', 'τ', 'ț', 'ت', 'ط', 'ဋ', 'တ', 'ŧ', 'თ', 'ტ', 't'], 'u': ['ú', 'ù', 'ủ', 'ũ', 'ụ', 'ư', 'ứ', 'ừ', 'ử', 'ữ', 'ự', 'û', 'ū', 'ů', 'ű', 'ŭ', 'ų', 'µ', 'у', 'ဉ', 'ု', 'ူ', 'ǔ', 'ǖ', 'ǘ', 'ǚ', 'ǜ', 'უ', 'उ', 'u', 'ў', 'ü'], 'v': ['в', 'ვ', 'ϐ', 'v'], 'w': ['ŵ', 'ω', 'ώ', 'ဝ', 'ွ', 'w'], 'x': ['χ', 'ξ', 'x'], 'y': ['ý', 'ỳ', 'ỷ', 'ỹ', 'ỵ', 'ÿ', 'ŷ', 'й', 'ы', 'υ', 'ϋ', 'ύ', 'ΰ', 'ي', 'ယ', 'y'], 'z': ['ź', 'ž', 'ż', 'з', 'ζ', 'ز', 'ဇ', 'ზ', 'z'], 'aa': ['ع', 'आ', 'آ'], 'ae': ['æ', 'ǽ'], 'ai': ['ऐ'], 'ch': ['ч', 'ჩ', 'ჭ', 'چ'], 'dj': ['ђ', 'đ'], 'dz': ['џ', 'ძ'], 'ei': ['ऍ'], 'gh': ['غ', 'ღ'], 'ii': ['ई'], 'ij': ['ij'], 'kh': ['х', 'خ', 'ხ'], 'lj': ['љ'], 'nj': ['њ'], 'oe': ['ö', 'œ', 'ؤ'], 'oi': ['ऑ'], 'oii': ['ऒ'], 'ps': ['ψ'], 'sh': ['ш', 'შ', 'ش'], 'shch': ['щ'], 'ss': ['ß'], 'sx': ['ŝ'], 'th': ['þ', 'ϑ', 'ث', 'ذ', 'ظ'], 'ts': ['ц', 'ც', 'წ'], 'ue': ['ü'], 'uu': ['ऊ'], 'ya': ['я'], 'yu': ['ю'], 'zh': ['ж', 'ჟ', 'ژ'], '(c)': ['©'], 'A': ['Á', 'À', 'Ả', 'Ã', 'Ạ', 'Ă', 'Ắ', 'Ằ', 'Ẳ', 'Ẵ', 'Ặ', 'Â', 'Ấ', 'Ầ', 'Ẩ', 'Ẫ', 'Ậ', 'Å', 'Ā', 'Ą', 'Α', 'Ά', 'Ἀ', 'Ἁ', 'Ἂ', 'Ἃ', 'Ἄ', 'Ἅ', 'Ἆ', 'Ἇ', 'ᾈ', 'ᾉ', 'ᾊ', 'ᾋ', 'ᾌ', 'ᾍ', 'ᾎ', 'ᾏ', 'Ᾰ', 'Ᾱ', 'Ὰ', 'Ά', 'ᾼ', 'А', 'Ǻ', 'Ǎ', 'A', 'Ä'], 'B': ['Б', 'Β', 'ब', 'B'], 'C': ['Ç', 'Ć', 'Č', 'Ĉ', 'Ċ', 'C'], 'D': ['Ď', 'Ð', 'Đ', 'Ɖ', 'Ɗ', 'Ƌ', 'ᴅ', 'ᴆ', 'Д', 'Δ', 'D'], 'E': ['É', 'È', 'Ẻ', 'Ẽ', 'Ẹ', 'Ê', 'Ế', 'Ề', 'Ể', 'Ễ', 'Ệ', 'Ë', 'Ē', 'Ę', 'Ě', 'Ĕ', 'Ė', 'Ε', 'Έ', 'Ἐ', 'Ἑ', 'Ἒ', 'Ἓ', 'Ἔ', 'Ἕ', 'Έ', 'Ὲ', 'Е', 'Ё', 'Э', 'Є', 'Ə', 'E'], 'F': ['Ф', 'Φ', 'F'], 'G': ['Ğ', 'Ġ', 'Ģ', 'Г', 'Ґ', 'Γ', 'G'], 'H': ['Η', 'Ή', 'Ħ', 'H'], 'I': ['Í', 'Ì', 'Ỉ', 'Ĩ', 'Ị', 'Î', 'Ï', 'Ī', 'Ĭ', 'Į', 'İ', 'Ι', 'Ί', 'Ϊ', 'Ἰ', 'Ἱ', 'Ἳ', 'Ἴ', 'Ἵ', 'Ἶ', 'Ἷ', 'Ῐ', 'Ῑ', 'Ὶ', 'Ί', 'И', 'І', 'Ї', 'Ǐ', 'ϒ', 'I'], 'J': ['J'], 'K': ['К', 'Κ', 'K'], 'L': ['Ĺ', 'Ł', 'Л', 'Λ', 'Ļ', 'Ľ', 'Ŀ', 'ल', 'L'], 'M': ['М', 'Μ', 'M'], 'N': ['Ń', 'Ñ', 'Ň', 'Ņ', 'Ŋ', 'Н', 'Ν', 'N'], 'O': ['Ó', 'Ò', 'Ỏ', 'Õ', 'Ọ', 'Ô', 'Ố', 'Ồ', 'Ổ', 'Ỗ', 'Ộ', 'Ơ', 'Ớ', 'Ờ', 'Ở', 'Ỡ', 'Ợ', 'Ø', 'Ō', 'Ő', 'Ŏ', 'Ο', 'Ό', 'Ὀ', 'Ὁ', 'Ὂ', 'Ὃ', 'Ὄ', 'Ὅ', 'Ὸ', 'Ό', 'О', 'Θ', 'Ө', 'Ǒ', 'Ǿ', 'O', 'Ö'], 'P': ['П', 'Π', 'P'], 'Q': ['Q'], 'R': ['Ř', 'Ŕ', 'Р', 'Ρ', 'Ŗ', 'R'], 'S': ['Ş', 'Ŝ', 'Ș', 'Š', 'Ś', 'С', 'Σ', 'S'], 'T': ['Ť', 'Ţ', 'Ŧ', 'Ț', 'Т', 'Τ', 'T'], 'U': ['Ú', 'Ù', 'Ủ', 'Ũ', 'Ụ', 'Ư', 'Ứ', 'Ừ', 'Ử', 'Ữ', 'Ự', 'Û', 'Ū', 'Ů', 'Ű', 'Ŭ', 'Ų', 'У', 'Ǔ', 'Ǖ', 'Ǘ', 'Ǚ', 'Ǜ', 'U', 'Ў', 'Ü'], 'V': ['В', 'V'], 'W': ['Ω', 'Ώ', 'Ŵ', 'W'], 'X': ['Χ', 'Ξ', 'X'], 'Y': ['Ý', 'Ỳ', 'Ỷ', 'Ỹ', 'Ỵ', 'Ÿ', 'Ῠ', 'Ῡ', 'Ὺ', 'Ύ', 'Ы', 'Й', 'Υ', 'Ϋ', 'Ŷ', 'Y'], 'Z': ['Ź', 'Ž', 'Ż', 'З', 'Ζ', 'Z'], 'AE': ['Æ', 'Ǽ'], 'Ch': ['Ч'], 'Dj': ['Ђ'], 'Dz': ['Џ'], 'Gx': ['Ĝ'], 'Hx': ['Ĥ'], 'Ij': ['IJ'], 'Jx': ['Ĵ'], 'Kh': ['Х'], 'Lj': ['Љ'], 'Nj': ['Њ'], 'Oe': ['Œ'], 'Ps': ['Ψ'], 'Sh': ['Ш'], 'Shch': ['Щ'], 'Ss': ['ẞ'], 'Th': ['Þ'], 'Ts': ['Ц'], 'Ya': ['Я'], 'Yu': ['Ю'], 'Zh': ['Ж'], }; Object.keys(swaps).forEach((swap) => { swaps[swap].forEach(s => { str = str.replace(new RegExp(s, "g"), swap); }) }); return str .replace(/[^a-z0-9 -]/g, "") // remove invalid chars .replace(/\s+/g, "-") // collapse whitespace and replace by - .replace(/-+/g, "-") // collapse dashes .replace(/^-+/, "") // trim - from start of text .replace(/-+$/, ""); };
this is too much
@tauseedzaman:
Isn't all the swaps thing achieved with the two lines below?
.normalize( 'NFD' ) // split an accented letter in the base letter and the acent
.replace( /[\u0300-\u036f]/g, '' ) // remove all previously split accents
thanks guys
just a quick edit with some more characters.
export default (str) => { str = String(str).toString(); str = str.replace(/^\s+|\s+$/g, ""); // trim str = str.toLowerCase(); // remove accents, swap ñ for n, etc const swaps = { '0': ['°', '₀', '۰', '0'], '1': ['¹', '₁', '۱', '1'], '2': ['²', '₂', '۲', '2'], '3': ['³', '₃', '۳', '3'], '4': ['⁴', '₄', '۴', '٤', '4'], '5': ['⁵', '₅', '۵', '٥', '5'], '6': ['⁶', '₆', '۶', '٦', '6'], '7': ['⁷', '₇', '۷', '7'], '8': ['⁸', '₈', '۸', '8'], '9': ['⁹', '₉', '۹', '9'], 'a': ['à', 'á', 'ả', 'ã', 'ạ', 'ă', 'ắ', 'ằ', 'ẳ', 'ẵ', 'ặ', 'â', 'ấ', 'ầ', 'ẩ', 'ẫ', 'ậ', 'ā', 'ą', 'å', 'α', 'ά', 'ἀ', 'ἁ', 'ἂ', 'ἃ', 'ἄ', 'ἅ', 'ἆ', 'ἇ', 'ᾀ', 'ᾁ', 'ᾂ', 'ᾃ', 'ᾄ', 'ᾅ', 'ᾆ', 'ᾇ', 'ὰ', 'ά', 'ᾰ', 'ᾱ', 'ᾲ', 'ᾳ', 'ᾴ', 'ᾶ', 'ᾷ', 'а', 'أ', 'အ', 'ာ', 'ါ', 'ǻ', 'ǎ', 'ª', 'ა', 'अ', 'ا', 'a', 'ä'], 'b': ['б', 'β', 'ب', 'ဗ', 'ბ', 'b'], 'c': ['ç', 'ć', 'č', 'ĉ', 'ċ', 'c'], 'd': ['ď', 'ð', 'đ', 'ƌ', 'ȡ', 'ɖ', 'ɗ', 'ᵭ', 'ᶁ', 'ᶑ', 'д', 'δ', 'د', 'ض', 'ဍ', 'ဒ', 'დ', 'd'], 'e': ['é', 'è', 'ẻ', 'ẽ', 'ẹ', 'ê', 'ế', 'ề', 'ể', 'ễ', 'ệ', 'ë', 'ē', 'ę', 'ě', 'ĕ', 'ė', 'ε', 'έ', 'ἐ', 'ἑ', 'ἒ', 'ἓ', 'ἔ', 'ἕ', 'ὲ', 'έ', 'е', 'ё', 'э', 'є', 'ə', 'ဧ', 'ေ', 'ဲ', 'ე', 'ए', 'إ', 'ئ', 'e'], 'f': ['ф', 'φ', 'ف', 'ƒ', 'ფ', 'f'], 'g': ['ĝ', 'ğ', 'ġ', 'ģ', 'г', 'ґ', 'γ', 'ဂ', 'გ', 'گ', 'g'], 'h': ['ĥ', 'ħ', 'η', 'ή', 'ح', 'ه', 'ဟ', 'ှ', 'ჰ', 'h'], 'i': ['í', 'ì', 'ỉ', 'ĩ', 'ị', 'î', 'ï', 'ī', 'ĭ', 'į', 'ı', 'ι', 'ί', 'ϊ', 'ΐ', 'ἰ', 'ἱ', 'ἲ', 'ἳ', 'ἴ', 'ἵ', 'ἶ', 'ἷ', 'ὶ', 'ί', 'ῐ', 'ῑ', 'ῒ', 'ΐ', 'ῖ', 'ῗ', 'і', 'ї', 'и', 'ဣ', 'ိ', 'ီ', 'ည်', 'ǐ', 'ი', 'इ', 'ی', 'i'], 'j': ['ĵ', 'ј', 'Ј', 'ჯ', 'ج', 'j'], 'k': ['ķ', 'ĸ', 'к', 'κ', 'Ķ', 'ق', 'ك', 'က', 'კ', 'ქ', 'ک', 'k'], 'l': ['ł', 'ľ', 'ĺ', 'ļ', 'ŀ', 'л', 'λ', 'ل', 'လ', 'ლ', 'l'], 'm': ['м', 'μ', 'م', 'မ', 'მ', 'm'], 'n': ['ñ', 'ń', 'ň', 'ņ', 'ʼn', 'ŋ', 'ν', 'н', 'ن', 'န', 'ნ', 'n'], 'o': ['ó', 'ò', 'ỏ', 'õ', 'ọ', 'ô', 'ố', 'ồ', 'ổ', 'ỗ', 'ộ', 'ơ', 'ớ', 'ờ', 'ở', 'ỡ', 'ợ', 'ø', 'ō', 'ő', 'ŏ', 'ο', 'ὀ', 'ὁ', 'ὂ', 'ὃ', 'ὄ', 'ὅ', 'ὸ', 'ό', 'о', 'و', 'θ', 'ို', 'ǒ', 'ǿ', 'º', 'ო', 'ओ', 'o', 'ö'], 'p': ['п', 'π', 'ပ', 'პ', 'پ', 'p'], 'q': ['ყ', 'q'], 'r': ['ŕ', 'ř', 'ŗ', 'р', 'ρ', 'ر', 'რ', 'r'], 's': ['ś', 'š', 'ş', 'с', 'σ', 'ș', 'ς', 'س', 'ص', 'စ', 'ſ', 'ს', 's'], 't': ['ť', 'ţ', 'т', 'τ', 'ț', 'ت', 'ط', 'ဋ', 'တ', 'ŧ', 'თ', 'ტ', 't'], 'u': ['ú', 'ù', 'ủ', 'ũ', 'ụ', 'ư', 'ứ', 'ừ', 'ử', 'ữ', 'ự', 'û', 'ū', 'ů', 'ű', 'ŭ', 'ų', 'µ', 'у', 'ဉ', 'ု', 'ူ', 'ǔ', 'ǖ', 'ǘ', 'ǚ', 'ǜ', 'უ', 'उ', 'u', 'ў', 'ü'], 'v': ['в', 'ვ', 'ϐ', 'v'], 'w': ['ŵ', 'ω', 'ώ', 'ဝ', 'ွ', 'w'], 'x': ['χ', 'ξ', 'x'], 'y': ['ý', 'ỳ', 'ỷ', 'ỹ', 'ỵ', 'ÿ', 'ŷ', 'й', 'ы', 'υ', 'ϋ', 'ύ', 'ΰ', 'ي', 'ယ', 'y'], 'z': ['ź', 'ž', 'ż', 'з', 'ζ', 'ز', 'ဇ', 'ზ', 'z'], 'aa': ['ع', 'आ', 'آ'], 'ae': ['æ', 'ǽ'], 'ai': ['ऐ'], 'ch': ['ч', 'ჩ', 'ჭ', 'چ'], 'dj': ['ђ', 'đ'], 'dz': ['џ', 'ძ'], 'ei': ['ऍ'], 'gh': ['غ', 'ღ'], 'ii': ['ई'], 'ij': ['ij'], 'kh': ['х', 'خ', 'ხ'], 'lj': ['љ'], 'nj': ['њ'], 'oe': ['ö', 'œ', 'ؤ'], 'oi': ['ऑ'], 'oii': ['ऒ'], 'ps': ['ψ'], 'sh': ['ш', 'შ', 'ش'], 'shch': ['щ'], 'ss': ['ß'], 'sx': ['ŝ'], 'th': ['þ', 'ϑ', 'ث', 'ذ', 'ظ'], 'ts': ['ц', 'ც', 'წ'], 'ue': ['ü'], 'uu': ['ऊ'], 'ya': ['я'], 'yu': ['ю'], 'zh': ['ж', 'ჟ', 'ژ'], '(c)': ['©'], 'A': ['Á', 'À', 'Ả', 'Ã', 'Ạ', 'Ă', 'Ắ', 'Ằ', 'Ẳ', 'Ẵ', 'Ặ', 'Â', 'Ấ', 'Ầ', 'Ẩ', 'Ẫ', 'Ậ', 'Å', 'Ā', 'Ą', 'Α', 'Ά', 'Ἀ', 'Ἁ', 'Ἂ', 'Ἃ', 'Ἄ', 'Ἅ', 'Ἆ', 'Ἇ', 'ᾈ', 'ᾉ', 'ᾊ', 'ᾋ', 'ᾌ', 'ᾍ', 'ᾎ', 'ᾏ', 'Ᾰ', 'Ᾱ', 'Ὰ', 'Ά', 'ᾼ', 'А', 'Ǻ', 'Ǎ', 'A', 'Ä'], 'B': ['Б', 'Β', 'ब', 'B'], 'C': ['Ç', 'Ć', 'Č', 'Ĉ', 'Ċ', 'C'], 'D': ['Ď', 'Ð', 'Đ', 'Ɖ', 'Ɗ', 'Ƌ', 'ᴅ', 'ᴆ', 'Д', 'Δ', 'D'], 'E': ['É', 'È', 'Ẻ', 'Ẽ', 'Ẹ', 'Ê', 'Ế', 'Ề', 'Ể', 'Ễ', 'Ệ', 'Ë', 'Ē', 'Ę', 'Ě', 'Ĕ', 'Ė', 'Ε', 'Έ', 'Ἐ', 'Ἑ', 'Ἒ', 'Ἓ', 'Ἔ', 'Ἕ', 'Έ', 'Ὲ', 'Е', 'Ё', 'Э', 'Є', 'Ə', 'E'], 'F': ['Ф', 'Φ', 'F'], 'G': ['Ğ', 'Ġ', 'Ģ', 'Г', 'Ґ', 'Γ', 'G'], 'H': ['Η', 'Ή', 'Ħ', 'H'], 'I': ['Í', 'Ì', 'Ỉ', 'Ĩ', 'Ị', 'Î', 'Ï', 'Ī', 'Ĭ', 'Į', 'İ', 'Ι', 'Ί', 'Ϊ', 'Ἰ', 'Ἱ', 'Ἳ', 'Ἴ', 'Ἵ', 'Ἶ', 'Ἷ', 'Ῐ', 'Ῑ', 'Ὶ', 'Ί', 'И', 'І', 'Ї', 'Ǐ', 'ϒ', 'I'], 'J': ['J'], 'K': ['К', 'Κ', 'K'], 'L': ['Ĺ', 'Ł', 'Л', 'Λ', 'Ļ', 'Ľ', 'Ŀ', 'ल', 'L'], 'M': ['М', 'Μ', 'M'], 'N': ['Ń', 'Ñ', 'Ň', 'Ņ', 'Ŋ', 'Н', 'Ν', 'N'], 'O': ['Ó', 'Ò', 'Ỏ', 'Õ', 'Ọ', 'Ô', 'Ố', 'Ồ', 'Ổ', 'Ỗ', 'Ộ', 'Ơ', 'Ớ', 'Ờ', 'Ở', 'Ỡ', 'Ợ', 'Ø', 'Ō', 'Ő', 'Ŏ', 'Ο', 'Ό', 'Ὀ', 'Ὁ', 'Ὂ', 'Ὃ', 'Ὄ', 'Ὅ', 'Ὸ', 'Ό', 'О', 'Θ', 'Ө', 'Ǒ', 'Ǿ', 'O', 'Ö'], 'P': ['П', 'Π', 'P'], 'Q': ['Q'], 'R': ['Ř', 'Ŕ', 'Р', 'Ρ', 'Ŗ', 'R'], 'S': ['Ş', 'Ŝ', 'Ș', 'Š', 'Ś', 'С', 'Σ', 'S'], 'T': ['Ť', 'Ţ', 'Ŧ', 'Ț', 'Т', 'Τ', 'T'], 'U': ['Ú', 'Ù', 'Ủ', 'Ũ', 'Ụ', 'Ư', 'Ứ', 'Ừ', 'Ử', 'Ữ', 'Ự', 'Û', 'Ū', 'Ů', 'Ű', 'Ŭ', 'Ų', 'У', 'Ǔ', 'Ǖ', 'Ǘ', 'Ǚ', 'Ǜ', 'U', 'Ў', 'Ü'], 'V': ['В', 'V'], 'W': ['Ω', 'Ώ', 'Ŵ', 'W'], 'X': ['Χ', 'Ξ', 'X'], 'Y': ['Ý', 'Ỳ', 'Ỷ', 'Ỹ', 'Ỵ', 'Ÿ', 'Ῠ', 'Ῡ', 'Ὺ', 'Ύ', 'Ы', 'Й', 'Υ', 'Ϋ', 'Ŷ', 'Y'], 'Z': ['Ź', 'Ž', 'Ż', 'З', 'Ζ', 'Z'], 'AE': ['Æ', 'Ǽ'], 'Ch': ['Ч'], 'Dj': ['Ђ'], 'Dz': ['Џ'], 'Gx': ['Ĝ'], 'Hx': ['Ĥ'], 'Ij': ['IJ'], 'Jx': ['Ĵ'], 'Kh': ['Х'], 'Lj': ['Љ'], 'Nj': ['Њ'], 'Oe': ['Œ'], 'Ps': ['Ψ'], 'Sh': ['Ш'], 'Shch': ['Щ'], 'Ss': ['ẞ'], 'Th': ['Þ'], 'Ts': ['Ц'], 'Ya': ['Я'], 'Yu': ['Ю'], 'Zh': ['Ж'], }; Object.keys(swaps).forEach((swap) => { swaps[swap].forEach(s => { str = str.replace(new RegExp(s, "g"), swap); }) }); return str .replace(/[^a-z0-9 -]/g, "") // remove invalid chars .replace(/\s+/g, "-") // collapse whitespace and replace by - .replace(/-+/g, "-") // collapse dashes .replace(/^-+/, "") // trim - from start of text .replace(/-+$/, ""); };this is too much
My old but still true explain version.
https://gist.github.com/codeguy/6684588?permalink_comment_id=3243980#gistcomment-3243980
More info about normalize()...
https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/normalize
The normalize() method returns the Unicode Normalization Form of a given string.
normalize()
splits an accented character into its base character and the applied accent.
Then .replace( /[\u0300-\u036f]/g, '' )
removes all the accents that are aggrupated in that codes range.
I think it works with all current and future accented characters.
edit 01/17/2021
My new version
function slugify(text) { return text .toString() // Cast to string (optional) .normalize('NFKD') // The normalize() using NFKD method returns the Unicode Normalization Form of a given string. .toLowerCase() // Convert the string to lowercase letters .trim() // Remove whitespace from both sides of a string (optional) .replace(/\s+/g, '-') // Replace spaces with - .replace(/[^\w\-]+/g, '') // Remove all non-word chars .replace(/\-\-+/g, '-'); // Replace multiple - with single - }NFKD is probably better than NFD. Any feedback is welcome.
https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/normalize
I broke this:
slugify('Jurassic Park III, 2001 - ★★★')
You get a trailing '-'
jurassic-park-iii-2001-
Maybe add this?
.replace(/\-$/g, ''); // Remove trailing -
hey guys how about converting kanji like japanese words for slug?
hey guys how about converting kanji like japanese words for slug?
You want to keep they or you want to translate to english ?
edit 01/17/2021
My new versionfunction slugify(text) { return text .toString() // Cast to string (optional) .normalize('NFKD') // The normalize() using NFKD method returns the Unicode Normalization Form of a given string. .toLowerCase() // Convert the string to lowercase letters .trim() // Remove whitespace from both sides of a string (optional) .replace(/\s+/g, '-') // Replace spaces with - .replace(/[^\w\-]+/g, '') // Remove all non-word chars .replace(/\-\-+/g, '-'); // Replace multiple - with single - }NFKD is probably better than NFD. Any feedback is welcome.
https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/normalizeI broke this:
slugify('Jurassic Park III, 2001 - ★★★')
You get a trailing '-'
jurassic-park-iii-2001-
Maybe add this?
.replace(/\-$/g, ''); // Remove trailing -
Added that in, and also a line to change underscores to hyphens. May not be perfect but its good for my uses!
const slugify = (text) => {
return text
.toString() // Cast to string (optional)
.normalize('NFKD') // The normalize() using NFKD method returns the Unicode Normalization Form of a given string.
.toLowerCase() // Convert the string to lowercase letters
.trim() // Remove whitespace from both sides of a string (optional)
.replace(/\s+/g, '-') // Replace spaces with -
.replace(/[^\w\-]+/g, '') // Remove all non-word chars
.replace(/\_/g,'-') // Replace _ with -
.replace(/\-\-+/g, '-') // Replace multiple - with single -
.replace(/\-$/g, ''); // Remove trailing -
}
@torma616
AFAIK your version, which looks good, is missing the following line below the normalize one:
replace( /[\u0300-\u036f]/g, '' )
The normalize()
function splits each accented character in two: the base character, and its accent.
The subsequent replace()
line deletes all the accents, which happen to be all in the \u03xx UNICODE block.
Removing the accents requires these two steps.
I got the info for my slugify version from June 6, 2020 from the MDN docs:
https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/normalize
Works! thanks.
@codeguy - Could you please add an open-source license to this gist?
Look seem that does not work for "đ" char
@auvansang
You are right, "đ" can not be normalized, because it's not the combination of a letter with an accent, it's a letter by itself.
Check this:
https://stackoverflow.com/questions/2362810/why-doesnt-%C4%90-get-flattened-to-d-when-removing-accents-diacritics
@auvansang
How should the character "đ" be replaced for you—by "d" or another letter?
@auvansang How should the character "đ" be replaced for you—by "d" or another letter?
Yes d is the correct letter
If "đ" was replaced by "d" it is theoretically possible (albeit not likely) to generate a duplicate slug.
For example if I hat a slug "mad" and generating a new slug the input was "mađ" then I'd have a collision: two "mad" slugs.
For some applications this might be totally irrelevant, because the URLs have a tipically numeric id before the slug, preventing address duplication.
So, the decision on how to replace "đ" depends on the context.
Ewo