🐛 with toSlugCase(), toWords()

Author: wolfram77

README.md

@@ -48,6 +48,8 @@ xstring.tverskyDistance('pikachu', 'raichu', 3, 0.2, 0.4);
 | [toSnakeCase] | Convert a string to snake-case. |
 | [toCamelCase] | Convert a string to camel-case. |
 | [toPascalCase] | Convert a string to pascal-case. |
+| [toSlugCase] | Convert a string to slug-case (URL-friendly kebab-case). |
+| [toWords] | Split a string into words, after de-casing it. |
 |  |  |
 | [toBaseline] | Convert a string to baseline characters (limited support). |
 | [toSuperscript] | Convert a string to superscript characters (limited support). |
@@ -274,6 +276,8 @@ As of 26 June 2025, this project is licensed under AGPL-3.0. Previous versions r
 [toSnakeCase]: https://jsr.io/@nodef/extra-string/doc/~/toSnakeCase
 [toCamelCase]: https://jsr.io/@nodef/extra-string/doc/~/toCamelCase
 [toPascalCase]: https://jsr.io/@nodef/extra-string/doc/~/toPascalCase
+[toSlugCase]: https://jsr.io/@nodef/extra-string/doc/~/toSlugCase
+[toWords]: https://jsr.io/@nodef/extra-string/doc/~/toWords
 [ngrams]: https://jsr.io/@nodef/extra-string/doc/~/ngrams
 [uniqueNgrams]: https://jsr.io/@nodef/extra-string/doc/~/uniqueNgrams
 [countNgrams]: https://jsr.io/@nodef/extra-string/doc/~/countNgrams

deno.json

@@ -1,6 +1,6 @@
 {
   "name": "@nodef/extra-string",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "license": "AGPL-3.0",
   "exports": "./index.ts",
   "exclude": [".github/"]

index.test.ts

@@ -44,7 +44,9 @@ import {
   longestCommonPrefix,
   longestCommonSuffix,
   longestUncommonInfixes,
+  toWords,
   toKebabCase,
+  toSlugCase,
   toSuperscript,
   tverskyDistance,
 } from "./index.ts";
@@ -1225,17 +1227,55 @@ Deno.test("longestUncommonInfixes", () => {
 
 
 
+Deno.test("toWords", () => {
+  const a = toWords("Malwa Plateau");
+  assertEquals(a, ["Malwa", "Plateau"]);
+  const b = toWords("::chota::nagpur::");
+  assertEquals(b, ["chota", "nagpur"]);
+  const c = toWords("deccan___plateau");
+  assertEquals(c, ["deccan", "plateau"]);
+  const d = toWords("westernGhats");
+  assertEquals(d, ["western", "Ghats"]);
+  const e = toWords("parseURLToJSON");
+  assertEquals(e, ["parse", "URL", "To", "JSON"]);
+});
+
+
+
+
 Deno.test("toKebabCase", () => {
   const a = toKebabCase("Malwa Plateau");
   assertEquals(a, "malwa-plateau");
-  const b = toKebabCase("::chota::nagpur::", null, "_");
-  assertEquals(b, "chota_nagpur");
-  const c = toKebabCase("deccan___plateau", /_+/g, ".");
-  assertEquals(c, "deccan.plateau");
-  const d = toKebabCase("Some text_with-mixed CASE");
-  assertEquals(d, "some-text-with-mixed-case");
-  const e = toKebabCase("IAmListeningToFMWhileLoadingDifferentURL");
-  assertEquals(e, "i-am-listening-to-fm-while-loading-different-url");
+  const b = toKebabCase("malwaPlateau");
+  assertEquals(b, "malwa-plateau");
+  const c = toKebabCase("::chota::nagpur::", null, "_");
+  assertEquals(c, "chota_nagpur");
+  const d = toKebabCase("deccan___plateau", /_+/g, ".");
+  assertEquals(d, "deccan.plateau");
+  const e = toKebabCase("Some text_with-mixed CASE");
+  assertEquals(e, "some-text-with-mixed-case");
+  const f = toKebabCase("someTextWithMixedCase");
+  assertEquals(f, "some-text-with-mixed-case");
+  const g = toKebabCase("IAmListeningToFMWhileLoadingDifferentURL");
+  assertEquals(g, "i-am-listening-to-fm-while-loading-different-url");
+  // const h = toKebabCase("I can't believe it's not butter!");
+  // assertEquals(h, "i-cant-believe-its-not-butter");
+});
+
+
+
+
+Deno.test("toSlugCase", () => {
+  const a = toSlugCase("Malwa Plateau");
+  assertEquals(a, "malwa-plateau");
+  const b = toSlugCase("malwaPlateau");
+  assertEquals(b, "malwa-plateau");
+  const c = toSlugCase("Curaçao São Tomé & Príncipe!");
+  assertEquals(c, "curacao-sao-tome-principe");
+  const d = toSlugCase("你好世界 hello world");
+  assertEquals(d, "hello-world");
+  // const e = toSlugCase("Æther & Œuvre — résumé", null, "_");
+  // assertEquals(e, "aether_oeuvre_resume");
 });
 
 

index.ts

@@ -1371,6 +1371,45 @@ function _toTitleCase(x: string, re: RegExp | null=null): string {
 }
 
 
+/**
+ * Split a string into words, after de-casing it.
+ * @param x a string
+ * @param re word seperator pattern [/[^0-9A-Za-z]+/g]
+ * @returns words in the string
+ * @example
+ * ```javascript
+ * xstring.toWords('Malwa Plateau');
+ * // → ['Malwa', 'Plateau']
+ *
+ * xstring.toWords('::chota::nagpur::');
+ * // → ['chota', 'nagpur']
+ *
+ * xstring.toWords('deccan___plateau');
+ * // → ['deccan', 'plateau']
+ *
+ * xstring.toWords('westernGhats');
+ * // → ['western', 'Ghats']
+ *
+ * xstring.toWords('parseURLToJSON');
+ * // → ['parse', 'URL', 'To', 'JSON']
+ */
+export function toWords(x: string, re: RegExp | null=null): string[] {
+  const words  = [];
+  const tokens = x.split(re || /[^0-9A-Za-z]+/g).filter(IDENTITY);
+  for (const token of tokens) {
+    const re = /[A-Z]+/g;
+    let m = null, i = 0;
+    while ((m = re.exec(token)) != null) {
+      if (i!==m.index) words.push(token.slice(i, m.index));
+      if (m[0].length===1 || m.index + m[0].length === token.length) i = m.index;
+      else { words.push(token.slice(m.index, m.index + m[0].length - 1)); i = m.index + m[0].length - 1; }
+    }
+    if (i!==token.length) words.push(token.slice(i));
+  }
+  return words;
+}
+
+
 /**
  * Convert a string to kebab-case.
  * @param x a string
@@ -1445,6 +1484,21 @@ export function toCamelCase(x: string, re: RegExp | null=null, upper: boolean=fa
 export function toPascalCase(x: string, re: RegExp | null=null): string {
   return toCamelCase(x, re, true);
 }
+
+
+/**
+ * Convert a string to slug-case (URL-friendly kebab-case).
+ * @param x a string
+ * @param re word separator pattern [/[^0-9A-Za-z]+/g]
+ * @param sep separator to join with [-]
+ * @returns slug-case | slug<join>case
+ */
+export function toSlugCase(x: string, re: RegExp | null = null, sep: string = "-"): string {
+  x = x.normalize("NFKD").replace(/[\u0300-\u036f]/g, ""); // Remove accents
+  // deno-lint-ignore no-control-regex
+  return toKebabCase(x.replace(/[^\x00-\x7F]/g, ""), re, sep); // Remove non-ASCII chars
+}
+export {toSlugCase as slugify};
 //#endregion