urdu-text-utils 0.1.4 → 0.1.6

package/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## 0.1.6
+
+- Add dedicated minified IIFE browser bundle (`dist/index.iife.js`) exposing `window.UrduTextUtils` for seamless jsDelivr and unpkg CDN usage without a bundler.
+- Add `jsdelivr` and `unpkg` fields and `browser` export condition in `package.json`.
+
+## 0.1.5
+
+- Expand transliteration dictionary to 1,700+ entries across classical/poetic register, commerce & digital terminology, law & governance, geography, and rich verbal inflections.
+- Expand `ROMAN_VARIANTS` with popular Roman Urdu texting and chat conventions (`kidhr`, `thek`, `sahi`, `behtareen`, `mashaallah`, `jazakallah`, etc.).
+- Add automated sitemap generation, OpenGraph metadata, and JSON-LD structured data for docs.
+
 ## 0.1.4
 
 - Add Urdu stop words module (`URDU_STOP_WORDS`, `isStopWord`, `filterStopWords`, `removeStopWords`) with a curated set of 130+ canonical functional words.

package/README.md

@@ -1,4 +1,4 @@
-# urdu-text-utils
+# urdu-text-utils — Urdu Text Processing Toolkit for JavaScript & TypeScript
 
 [![npm version](https://img.shields.io/npm/v/urdu-text-utils?style=flat-square&color=157f52&label=npm)](https://www.npmjs.com/package/urdu-text-utils)
 [![CI](https://img.shields.io/github/actions/workflow/status/Zaid-maker/urdu-text-utils/ci.yml?branch=main&style=flat-square&label=CI)](https://github.com/Zaid-maker/urdu-text-utils/actions/workflows/ci.yml)
@@ -7,9 +7,9 @@
 [![downloads](https://img.shields.io/npm/dm/urdu-text-utils?style=flat-square)](https://www.npmjs.com/package/urdu-text-utils)
 [![license](https://img.shields.io/npm/l/urdu-text-utils?style=flat-square)](./LICENSE)
 
-Urdu text processing toolkit for JavaScript and TypeScript. Normalization, detection, digits, diacritics, collation, search, statistics and transliteration.
+A complete, lightweight **Urdu text processing toolkit for JavaScript and TypeScript** (Node.js, Deno, Bun, and browsers). Zero runtime dependencies. Provides Unicode normalization, Roman Urdu transliteration, Urdu stop words, script detection, Urdu digit conversion, diacritics (aerab / harakat) removal, alphabetical collation / sorting, fuzzy search, and text statistics.
 
-Zero runtime dependencies. ESM + CJS. Ships its own types.
+Zero runtime dependencies. ESM + CJS. Fully typed.
 
 **[Documentation and live playground →](https://zaid-maker.github.io/urdu-text-utils/)**
 
@@ -17,11 +17,41 @@ Zero runtime dependencies. ESM + CJS. Ships its own types.
 npm install urdu-text-utils
 ```
 
+### CDN (Browser / Vanilla JS)
+
+You can use `urdu-text-utils` directly in the browser without any bundler or build step via **jsDelivr** or **unpkg**:
+
+```html
+<!-- jsDelivr (global UrduTextUtils) -->
+<script src="https://cdn.jsdelivr.net/npm/urdu-text-utils/dist/index.iife.js"></script>
+
+<script>
+  const { normalizeUrdu, romanize, isStopWord, searchUrdu } = window.UrduTextUtils;
+  console.log(normalizeUrdu("كيا حال ہے")); // "کیا حال ہے"
+</script>
+```
+
+Or as an ES Module:
+
+```html
+<script type="module">
+  import { normalizeUrdu, romanize } from "https://cdn.jsdelivr.net/npm/urdu-text-utils/+esm";
+  console.log(normalizeUrdu("كيا حال ہے"));
+</script>
+```
+
+
 ```ts
 import {
   normalizeUrdu,
+  romanize,
+  romanToUrdu,
+  urduSlug,
+  isStopWord,
+  removeStopWords,
   isUrdu,
   countWords,
+  splitSentences,
   convertNumbers,
   removeDiacritics,
   sortUrdu,

package/dist/index.cjs

@@ -2885,7 +2885,191 @@ var WORD_DICTIONARY = {
   "\u0641\u0631\u0632\u0627\u0646\u06C1": "farzana",
   "\u0637\u0627\u06C1\u0631\u06C1": "tahira",
   "\u0639\u0635\u0645\u062A": "ismat",
-  "\u0646\u0635\u0631\u062A": "nusrat"
+  "\u0646\u0635\u0631\u062A": "nusrat",
+  // ---- classical, poetic and literary vocabulary ----
+  "\u06AF\u0644\u0633\u062A\u0627\u06BA": "gulistan",
+  "\u06AF\u0644\u0634\u0646": "gulshan",
+  "\u0628\u06C1\u0627\u0631\u0627\u06BA": "baharan",
+  "\u067E\u0631\u0648\u0627\u0646\u06C1": "parwana",
+  "\u0634\u0645\u0639": "shama",
+  "\u0633\u0627\u0642\u06CC": "saqi",
+  "\u0645\u06CC\u062E\u0627\u0646\u06C1": "maikhana",
+  "\u062C\u0627\u0645": "jaam",
+  "\u0635\u0631\u0627\u062D\u06CC": "surahi",
+  "\u0631\u0646\u062F": "rind",
+  "\u0645\u062D\u062A\u0633\u0628": "muhtasib",
+  "\u0642\u0627\u0635\u062F": "qasid",
+  "\u067E\u06CC\u0627\u0645\u0628\u0631": "payambar",
+  "\u0631\u0642\u06CC\u0628": "raqeeb",
+  "\u062D\u0628\u06CC\u0628": "habeeb",
+  "\u0645\u062D\u0628\u0648\u0628": "mahboob",
+  "\u0645\u0639\u0634\u0648\u0642": "mashooq",
+  "\u0635\u0646\u0645": "sanam",
+  "\u0633\u0646\u06AF\u062F\u0644": "sangdil",
+  "\u0628\u06CC\u062F\u0631\u062F": "bedard",
+  "\u063A\u0645\u06AF\u0633\u0627\u0631": "ghamgusar",
+  "\u0645\u0633\u06CC\u062D\u0627": "maseeha",
+  "\u0646\u0627\u0635\u062D": "nasih",
+  "\u0648\u0627\u0639\u0638": "waiz",
+  "\u062A\u0634\u0646\u06C1": "tishna",
+  "\u06AF\u06CC\u0633\u0648": "gesu",
+  "\u0632\u0644\u0641": "zulf",
+  "\u062F\u06CC\u062F\u0627\u0631": "deedar",
+  "\u062C\u0644\u0648\u06C1": "jalwa",
+  "\u062D\u062C\u0627\u0628": "hijab",
+  "\u0646\u0642\u0627\u0628": "niqab",
+  "\u0633\u0648\u0632": "soz",
+  "\u0622\u06C1\u0646\u06AF": "aahang",
+  "\u0646\u063A\u0645\u06C1": "naghma",
+  "\u062A\u0631\u0627\u0646\u06C1": "tarana",
+  "\u062F\u0627\u0633\u062A\u0627\u06BA": "dastan",
+  "\u062D\u0648\u0631": "hoor",
+  "\u067E\u0631\u06CC": "pari",
+  "\u062F\u06CC\u0648": "deo",
+  "\u062C\u0627\u062F\u0648": "jadoo",
+  "\u0637\u0644\u0633\u0645": "tilism",
+  "\u0627\u0641\u0633\u0648\u0646": "afsoon",
+  "\u0633\u062D\u0631\u0627\u0646\u06AF\u06CC\u0632": "sehrangeez",
+  "\u0641\u0633\u0648\u06BA": "fusoon",
+  "\u062C\u0646\u0648\u06BA": "junoon",
+  "\u0633\u0648\u062F\u0627": "sauda",
+  "\u0648\u062D\u0634\u062A": "wahshat",
+  "\u0627\u0631\u0645\u0627\u0646": "arman",
+  "\u0630\u0648\u0642": "zauq",
+  "\u0648\u062C\u062F": "wajd",
+  "\u0645\u0633\u062A\u06CC": "masti",
+  "\u06A9\u06CC\u0641": "kaif",
+  "\u062E\u0645\u0627\u0631": "khumar",
+  "\u0646\u0634\u06C1": "nasha",
+  "\u0628\u06D2\u062E\u0648\u062F\u06CC": "bekhudi",
+  // ---- commerce, finance and modern technology ----
+  "\u062E\u0631\u06CC\u062F\u0627\u0631\u06CC": "khareedari",
+  "\u0641\u0631\u0648\u062E\u062A": "farokht",
+  "\u0633\u0631\u0645\u0627\u06CC\u06C1": "sarmaya",
+  "\u0642\u0631\u0636\u06C1": "qarza",
+  "\u0628\u06CC\u0646\u06A9\u0627\u0631\u06CC": "bainkari",
+  "\u0642\u0633\u0637": "qist",
+  "\u0627\u062F\u0627\u0626\u06CC\u06AF\u06CC": "adaigi",
+  "\u0622\u0645\u062F\u0646\u06CC": "aamdani",
+  "\u062E\u0631\u0686\u06C1": "kharcha",
+  "\u0628\u0686\u062A": "bachat",
+  "\u0645\u062D\u0635\u0648\u0644": "mahsool",
+  "\u0645\u0627\u0644\u06CC\u062A": "maliyat",
+  "\u06A9\u062A\u0627\u0628\u062A": "kitabat",
+  "\u0645\u0646\u0688\u06CC": "mandi",
+  "\u0646\u06CC\u0644\u0627\u0645\u06CC": "neelami",
+  "\u0628\u0648\u0644\u06CC": "boli",
+  "\u0634\u0631\u0627\u06A9\u062A": "sharakat",
+  "\u062D\u0635\u0635": "hisas",
+  "\u0627\u0633\u0679\u0627\u06A9": "stock",
+  "\u062F\u0648\u0644\u062A": "daulat",
+  "\u062B\u0631\u0648\u062A": "sarwat",
+  "\u063A\u0631\u0628\u062A": "ghurbat",
+  "\u0627\u0641\u0644\u0627\u0633": "iflas",
+  "\u067E\u0631\u0648\u0641\u0627\u0626\u0644": "profile",
+  "\u0633\u06CC\u0679\u0646\u06AF\u0632": "settings",
+  "\u0646\u0648\u0679\u06CC\u0641\u06A9\u06CC\u0634\u0646": "notification",
+  "\u0633\u0627\u0626\u0679": "site",
+  "\u067E\u0648\u0631\u0679\u0644": "portal",
+  // ---- administration, law, governance and politics ----
+  "\u0639\u062F\u0644\u06CC\u06C1": "adliya",
+  "\u0645\u0642\u0646\u0646\u06C1": "muqannana",
+  "\u0627\u0646\u062A\u0638\u0627\u0645\u06CC\u06C1": "intizamia",
+  "\u062D\u06A9\u0645\u0631\u0627\u0646\u06CC": "hukmrani",
+  "\u062C\u0645\u06C1\u0648\u0631\u06CC\u06C1": "jamhooria",
+  "\u0635\u062F\u0627\u0631\u062A": "sadarat",
+  "\u0648\u0632\u0627\u0631\u062A": "wazarat",
+  "\u0633\u0641\u0627\u0631\u062A": "safarat",
+  "\u0642\u0648\u0646\u0635\u0644": "consul",
+  "\u0633\u0641\u0627\u0631\u062A\u062E\u0627\u0646\u06C1": "safaratkhana",
+  "\u0622\u0626\u06CC\u0646\u06CC": "aaeeni",
+  "\u062F\u0633\u062A\u0648\u0631\u06CC": "dastoori",
+  "\u0641\u0648\u062C\u062F\u0627\u0631\u06CC": "faujdari",
+  "\u062F\u06CC\u0648\u0627\u0646\u06CC": "deewani",
+  "\u0645\u0642\u062F\u0645\u06C1": "muqaddama",
+  "\u0633\u0645\u0627\u0639\u062A": "samaat",
+  "\u062F\u0631\u062E\u0648\u0627\u0633\u062A": "darkhwast",
+  "\u0627\u067E\u06CC\u0644": "appeal",
+  "\u0636\u0645\u0627\u0646\u062A": "zamanat",
+  "\u0628\u0631\u06CC\u062A": "bariyat",
+  "\u0639\u0645\u0631\u0642\u06CC\u062F": "umrqaid",
+  "\u067E\u06BE\u0627\u0646\u0633\u06CC": "phansi",
+  "\u0648\u06A9\u0627\u0644\u062A": "wukalat",
+  "\u062D\u0642\u0648\u0642": "huqooq",
+  "\u0641\u0631\u0627\u0626\u0636": "faraiz",
+  "\u0634\u06C1\u0631\u06CC": "shahri",
+  "\u0634\u06C1\u0631\u06CC\u062A": "shahriyat",
+  "\u0634\u0646\u0627\u062E\u062A": "shanakht",
+  "\u0646\u0627\u062F\u0631\u0627": "nadra",
+  "\u0645\u062C\u0644\u0633": "majlis",
+  "\u0634\u0648\u0631\u06CC": "shoora",
+  "\u062D\u0644\u06CC\u0641": "haleef",
+  "\u0645\u062E\u0627\u0644\u0641": "mukhalif",
+  "\u0628\u063A\u0627\u0648\u062A": "baghawat",
+  // ---- geography, nature and terrain ----
+  "\u062E\u0637\u06C1": "khitta",
+  "\u0635\u0648\u0628\u06C1": "sooba",
+  "\u0636\u0644\u0639": "zila",
+  "\u062A\u062D\u0635\u06CC\u0644": "tehsil",
+  "\u06CC\u0648\u0646\u06CC\u0646": "union",
+  "\u06A9\u0648\u0646\u0633\u0644": "council",
+  "\u0642\u0631\u06CC\u06C1": "qarya",
+  "\u0628\u0633\u062A\u06CC": "basti",
+  "\u0634\u06C1\u0631\u0633\u062A\u0627\u0646": "shehristan",
+  "\u0646\u062E\u0644\u0633\u062A\u0627\u0646": "nakhalistan",
+  "\u06A9\u0648\u06C1\u0633\u0627\u0631": "kohsar",
+  "\u06A9\u06C1\u0633\u0627\u0631": "kuhsar",
+  "\u06AF\u06BE\u0627\u0679\u06CC": "ghati",
+  "\u0648\u0627\u062F\u06CC\u0627\u06BA": "wadiyan",
+  "\u06A9\u06BE\u0627\u0626\u06CC": "khaai",
+  "\u062E\u0644\u06CC\u062C": "khaleej",
+  "\u0631\u0627\u0633": "raas",
+  // ---- verbs and verbal inflections ----
+  "\u0645\u0627\u0646\u062A\u06D2": "mante",
+  "\u0645\u0627\u0646\u062A\u06CC": "manti",
+  "\u0645\u0627\u0646\u0648": "mano",
+  "\u0679\u06BE\u06C1\u0631\u0646\u0627": "theharna",
+  "\u0679\u06BE\u06C1\u0631\u0627": "thehra",
+  "\u0679\u06BE\u06C1\u0631\u0648": "thehro",
+  "\u0679\u06BE\u06C1\u0631\u062A\u06D2": "thehrte",
+  "\u0633\u0645\u062C\u06BE\u0627\u0624": "samjhao",
+  "\u067E\u06C1\u0646\u0686\u0627\u0624": "pohonchao",
+  "\u0644\u0679\u0627\u0646\u0627": "lutana",
+  "\u0644\u0679\u0627\u06CC\u0627": "lutaya",
+  "\u0644\u0648\u0679\u0627": "loota",
+  "\u067E\u06A9\u0627\u0631\u0627": "pukara",
+  "\u067E\u06A9\u0627\u0631\u0648": "pukaro",
+  "\u062C\u06BE\u06A9\u0646\u0627": "jhukna",
+  "\u062C\u06BE\u06A9\u0627": "jhuka",
+  "\u062C\u06BE\u06A9\u0627\u0624": "jhukao",
+  "\u062C\u06BE\u06A9\u0627\u0646\u0627": "jhukana",
+  "\u062A\u06BE\u0627\u0645\u0646\u0627": "thamna",
+  "\u062A\u06BE\u0627\u0645\u0627": "thama",
+  "\u062A\u06BE\u0627\u0645\u0648": "thamo",
+  "\u0633\u0646\u0648\u0627\u0631\u0646\u0627": "sanwarna",
+  "\u0633\u0646\u0648\u0627\u0631\u0627": "sanwara",
+  "\u0646\u06A9\u06BE\u0627\u0631\u0646\u0627": "nikharna",
+  "\u0646\u06A9\u06BE\u0627\u0631\u0627": "nikhara",
+  "\u0633\u0646\u0628\u06BE\u0627\u0644\u0646\u0627": "sambhalna",
+  "\u0633\u0646\u0628\u06BE\u0627\u0644\u0627": "sambhala",
+  "\u0633\u0646\u0628\u06BE\u0627\u0644\u0648": "sambhalo",
+  "\u067E\u0686\u06BE\u062A\u0627\u0646\u0627": "pachtana",
+  "\u067E\u0686\u06BE\u062A\u0627\u06CC\u0627": "pachtaya",
+  "\u06AF\u06BE\u0628\u0631\u0627\u0646\u0627": "ghabrana",
+  "\u06AF\u06BE\u0628\u0631\u0627\u06CC\u0627": "ghabraya",
+  "\u0645\u0633\u06A9\u0631\u0627\u0646\u0627": "muskurana",
+  "\u0645\u0633\u06A9\u0631\u0627\u06CC\u0627": "muskuraya",
+  "\u0645\u0633\u06A9\u0631\u0627\u06C1\u0679": "muskurahat",
+  "\u062C\u06BE\u0646\u062C\u06BE\u0644\u0627\u0646\u0627": "jhanjhlana",
+  "\u062A\u0644\u0645\u0644\u0627\u0646\u0627": "tilmilana",
+  "\u0628\u0644\u0628\u0644\u0627\u0646\u0627": "bilbilana",
+  "\u06A9\u06BE\u0644\u06A9\u06BE\u0644\u0627\u0646\u0627": "khilkhilana",
+  "\u06A9\u06BE\u0679\u06A9\u06BE\u0679\u0627\u0646\u0627": "khatkhatana",
+  "\u062C\u06BE\u0644\u0645\u0644\u0627\u0646\u0627": "jhilmilana",
+  "\u0686\u0645\u0686\u0645\u0627\u062A\u0627": "chamchamata",
+  "\u0644\u06C1\u0631\u0627\u0646\u0627": "lehrana",
+  "\u0644\u06C1\u0631\u0627\u06CC\u0627": "lehraya",
+  "\u0644\u06C1\u0631": "lehar"
 };
 var ROMAN_VARIANTS = {
   hay: "\u06C1\u06D2",
@@ -3073,7 +3257,35 @@ var ROMAN_VARIANTS = {
   daur: "\u062F\u0648\u0631",
   kurta: "\u06A9\u0631\u062A\u0627",
   haseen: "\u062D\u0633\u06CC\u0646",
-  malik: "\u0645\u0644\u06A9"
+  malik: "\u0645\u0644\u06A9",
+  kidhr: "\u06A9\u062F\u06BE\u0631",
+  idhr: "\u0627\u062F\u06BE\u0631",
+  jdhr: "\u062C\u062F\u06BE\u0631",
+  thek: "\u0679\u06BE\u06CC\u06A9",
+  thk: "\u0679\u06BE\u06CC\u06A9",
+  sahi: "\u0635\u062D\u06CC\u062D",
+  galat: "\u063A\u0644\u0637",
+  ghalat: "\u063A\u0644\u0637",
+  sb: "\u0633\u0628",
+  hmsha: "\u06C1\u0645\u06CC\u0634\u06C1",
+  kbhi: "\u06A9\u0628\u06BE\u06CC",
+  aksar: "\u0627\u06A9\u062B\u0631",
+  behtareen: "\u0628\u06C1\u062A\u0631\u06CC\u0646",
+  zabardast: "\u0632\u0628\u0631\u062F\u0633\u062A",
+  shandar: "\u0634\u0627\u0646\u062F\u0627\u0631",
+  khoob: "\u062E\u0648\u0628",
+  khub: "\u062E\u0648\u0628",
+  sharam: "\u0634\u0631\u0645",
+  haya: "\u062D\u06CC\u0627",
+  ghairat: "\u063A\u06CC\u0631\u062A",
+  himmat: "\u06C1\u0645\u062A",
+  hosla: "\u062D\u0648\u0635\u0644\u06C1",
+  mashaallah: "\u0645\u0627\u0634\u0627\u0621\u0627\u0644\u0644\u06C1",
+  inshaallah: "\u0627\u0646\u0634\u0627\u0621\u0627\u0644\u0644\u06C1",
+  mashallah: "\u0645\u0627\u0634\u0627\u0621\u0627\u0644\u0644\u06C1",
+  inshallah: "\u0627\u0646\u0634\u0627\u0621\u0627\u0644\u0644\u06C1",
+  alhamdulillah: "\u0627\u0644\u062D\u0645\u062F\u0644\u0644\u06C1",
+  jazakallah: "\u062C\u0632\u0627\u06A9\u200C\u0627\u0644\u0644\u06C1"
 };
 
 // src/transliterate.ts