urdu-text-utils 0.1.1 → 0.1.2

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 0.1.2
+
+- Dictionary grows to ~650 entries: news and public-life vocabulary (the densest register in Urdu media), technology, education, health, colours, animals, extended family, food and place names.
+- Rule fallback reads `ی` by position — `e` inside a word (`کھیل` → `khel`), `i` at the end (`پڑھی` → `parhi`) — and recognises the final `یں` plural ending (`سڑکیں` → `sarkein`, previously `sarkin`).
+- `مارنا` transliterates as `maarna` so it no longer collapses into `مرنا` in the reverse direction.
+
 ## 0.1.1
 
 - Expand the transliteration dictionary to ~450 entries: high-frequency vocabulary, oblique infinitives (`کرنے`, `رہنے`), English loanwords (`سکول`, `کمپیوٹر`) and common Roman spelling variants. The dictionary moved to `src/dictionary.ts`.

package/README.md

@@ -155,7 +155,7 @@ Read this before putting it in front of users.
 
 Urdu script omits short vowels, so the mapping is genuinely ambiguous: `کتب` is `kitab` or `kutub` depending on context and no rule table can decide which. The reverse direction is worse, because Roman Urdu has no standard orthography (`hai` / `hay` / `he` all occur).
 
-These functions work in two layers: a dictionary of ~450 high-frequency words, English loanwords and oblique verb forms, then a rule fallback that handles aspirated digraphs, word-initial `و`/`ی` as consonants, word-final `ہ` as `-a`, and a schwa insertion so unseen words stay pronounceable. Dictionary hits are reliable; rule output is an approximation. Do not build anything irreversible on it. A real lexicon plus a statistical model is planned, not faked here.
+These functions work in two layers: a dictionary of ~650 high-frequency words, English loanwords and oblique verb forms, then a rule fallback that handles aspirated digraphs, word-initial `و`/`ی` as consonants, word-final `ہ` as `-a`, `ی` by position (`کھیل` → `khel`, `پڑھی` → `parhi`, `سڑکیں` → `sarkein`), and a schwa insertion so unseen words stay pronounceable. Dictionary hits are reliable; rule output is an approximation. Do not build anything irreversible on it. A real lexicon plus a statistical model is planned, not faked here.
 
 ```ts
 romanize("آپ کیسے ہیں"); // "aap kaisay hain"

package/dist/index.cjs

@@ -1061,6 +1061,201 @@ var WORD_DICTIONARY = {
   "\u0628\u06C1\u062A": "bohat",
   "\u0635\u0631\u0641": "sirf",
   "\u0648\u0627\u0642\u0639\u06CC": "waqai",
+  // ---- more verbs ----
+  "\u06A9\u06BE\u06CC\u0644\u0646\u0627": "khelna",
+  "\u06A9\u06BE\u06CC\u0644\u062A\u0627": "khelta",
+  "\u06C1\u0646\u0633\u0646\u0627": "hansna",
+  "\u0631\u0648\u0646\u0627": "rona",
+  "\u0688\u0631\u0646\u0627": "darna",
+  "\u0628\u06BE\u0648\u0644\u0646\u0627": "bhoolna",
+  "\u06CC\u0627\u062F": "yaad",
+  "\u0633\u06CC\u06A9\u06BE\u0646\u0627": "seekhna",
+  "\u0633\u06A9\u06BE\u0627\u0646\u0627": "sikhana",
+  "\u067E\u06A9\u0627\u0646\u0627": "pakana",
+  "\u062F\u06BE\u0648\u0646\u0627": "dhona",
+  "\u067E\u06C1\u0646\u0646\u0627": "pehanna",
+  "\u0627\u062A\u0627\u0631\u0646\u0627": "utarna",
+  "\u0628\u06CC\u0686\u0646\u0627": "bechna",
+  "\u062E\u0631\u06CC\u062F\u0646\u0627": "khareedna",
+  "\u0628\u06BE\u06CC\u062C\u0646\u0627": "bhejna",
+  "\u067E\u06C1\u0646\u0686\u0646\u0627": "pohanchna",
+  "\u0646\u06A9\u0644\u0646\u0627": "nikalna",
+  "\u06AF\u0631\u0646\u0627": "girna",
+  "\u0627\u0679\u06BE\u0627\u0646\u0627": "uthana",
+  "\u067E\u06A9\u0691\u0646\u0627": "pakarna",
+  "\u0686\u06BE\u0648\u0691\u0646\u0627": "chhorna",
+  "\u062A\u0648\u0691\u0646\u0627": "torna",
+  "\u062C\u0648\u0691\u0646\u0627": "jorna",
+  "\u06A9\u0627\u0679\u0646\u0627": "katna",
+  // مارنا (to hit) and مرنا (to die) differ by one letter; keeping the long vowel
+  // in "maarna" stops them collapsing into one reverse-direction target.
+  "\u0645\u0627\u0631\u0646\u0627": "maarna",
+  "\u0628\u0686\u0627\u0646\u0627": "bachana",
+  "\u062C\u0644\u0627\u0646\u0627": "jalana",
+  "\u0646\u0627\u0686\u0646\u0627": "nachna",
+  "\u06AF\u0627\u0646\u0627": "gana",
+  "\u0644\u0691\u0646\u0627": "larna",
+  "\u062C\u06CC\u062A\u0646\u0627": "jeetna",
+  "\u06C1\u0627\u0631\u0646\u0627": "haarna",
+  "\u0686\u06BE\u067E\u0627\u0646\u0627": "chhupana",
+  "\u0688\u06BE\u0648\u0646\u0688\u0646\u0627": "dhoondna",
+  "\u0645\u0644\u0627\u0646\u0627": "milana",
+  "\u0628\u062F\u0644\u0646\u0627": "badalna",
+  "\u0631\u06A9\u0646\u0627": "rukna",
+  "\u0627\u0691\u0646\u0627": "urna",
+  "\u062A\u06CC\u0631\u0646\u0627": "tairna",
+  // ---- adverbs and conjunctions ----
+  "\u0641\u0648\u0631\u0627\u064B": "fauran",
+  "\u062F\u0648\u0628\u0627\u0631\u06C1": "dobara",
+  "\u06CC\u0642\u06CC\u0646\u0627\u064B": "yaqeenan",
+  "\u062A\u0642\u0631\u06CC\u0628\u0627\u064B": "taqreeban",
+  "\u0627\u0644\u0628\u062A\u06C1": "albatta",
+  "\u0686\u0648\u0646\u06A9\u06C1": "chunkeh",
+  "\u06A9\u06CC\u0648\u0646\u06A9\u06C1": "kyunkeh",
+  "\u062A\u0627\u06A9\u06C1": "taakeh",
+  "\u0648\u0631\u0646\u06C1": "warna",
+  "\u0628\u0644\u06A9\u06C1": "balkeh",
+  "\u062D\u0627\u0644\u0627\u0646\u06A9\u06C1": "halankeh",
+  "\u0645\u062B\u0644\u0627\u064B": "maslan",
+  "\u0628\u0639\u0636": "baaz",
+  "\u062A\u0645\u0627\u0645": "tamam",
+  "\u067E\u0648\u0631\u0627": "poora",
+  "\u0622\u062F\u06BE\u0627": "aadha",
+  "\u062F\u0648\u0646\u0648\u06BA": "donon",
+  "\u062A\u06CC\u0646\u0648\u06BA": "teenon",
+  "\u0633\u0627\u0631\u0627": "sara",
+  "\u0628\u0627\u0642\u06CC": "baqi",
+  // ---- news and public life, the densest vocabulary in Urdu media ----
+  "\u0633\u06CC\u0627\u0633\u062A": "siyasat",
+  "\u0627\u0644\u06CC\u06A9\u0634\u0646": "election",
+  "\u0648\u0648\u0679": "vote",
+  "\u067E\u0627\u0631\u0679\u06CC": "party",
+  "\u0627\u0633\u0645\u0628\u0644\u06CC": "assembly",
+  "\u0639\u062F\u0627\u0644\u062A": "adalat",
+  "\u0642\u0627\u0646\u0648\u0646": "qanoon",
+  "\u062C\u0631\u0645": "jurm",
+  "\u0641\u0648\u062C\u06CC": "fauji",
+  "\u062C\u0646\u06AF": "jang",
+  "\u0627\u0645\u0646": "aman",
+  "\u0645\u0639\u0627\u06C1\u062F\u06C1": "muahida",
+  "\u0645\u0639\u06CC\u0634\u062A": "maeeshat",
+  "\u062A\u062C\u0627\u0631\u062A": "tijarat",
+  "\u0628\u062C\u0679": "budget",
+  "\u062A\u0631\u0642\u06CC": "taraqqi",
+  "\u0645\u0646\u0635\u0648\u0628\u06C1": "mansooba",
+  "\u0627\u0639\u0644\u0627\u0646": "elaan",
+  "\u0631\u067E\u0648\u0631\u0679": "report",
+  "\u0628\u06CC\u0627\u0646": "bayan",
+  "\u0627\u062C\u0644\u0627\u0633": "ijlas",
+  "\u062F\u0648\u0631\u06C1": "dora",
+  "\u0645\u0644\u0627\u0642\u0627\u062A": "mulaqat",
+  "\u062A\u0642\u0631\u06CC\u0628": "taqreeb",
+  "\u062A\u0642\u0631\u06CC\u0631": "taqreer",
+  // ---- technology ----
+  "\u0688\u06CC\u0679\u0627": "data",
+  "\u0627\u06CC\u067E": "app",
+  "\u067E\u0631\u0648\u06AF\u0631\u0627\u0645": "program",
+  "\u0633\u0633\u0679\u0645": "system",
+  "\u0635\u0627\u0631\u0641": "sarif",
+  "\u0641\u0627\u0626\u0644": "file",
+  "\u0679\u06CC\u06A9\u0646\u0627\u0644\u0648\u062C\u06CC": "technology",
+  // ---- education ----
+  "\u062C\u0645\u0627\u0639\u062A": "jamaat",
+  "\u06A9\u0644\u0627\u0633": "class",
+  "\u067E\u0631\u0686\u06C1": "parcha",
+  "\u0646\u0645\u0628\u0631": "number",
+  "\u0688\u06AF\u0631\u06CC": "degree",
+  "\u0644\u0627\u0626\u0628\u0631\u06CC\u0631\u06CC": "library",
+  "\u062A\u062D\u0642\u06CC\u0642": "tehqeeq",
+  "\u0645\u0642\u0627\u0644\u06C1": "maqala",
+  // ---- health ----
+  "\u0628\u062E\u0627\u0631": "bukhar",
+  "\u062F\u0631\u062F": "dard",
+  "\u0632\u062E\u0645": "zakhm",
+  "\u0639\u0644\u0627\u062C": "ilaj",
+  "\u062E\u0648\u0646": "khoon",
+  "\u06C1\u0688\u06CC": "haddi",
+  "\u067E\u06CC\u0679": "pet",
+  "\u06AF\u0644\u0627": "gala",
+  // ---- colours ----
+  "\u0633\u0641\u06CC\u062F": "safaid",
+  "\u06A9\u0627\u0644\u0627": "kala",
+  "\u0633\u0631\u062E": "surkh",
+  "\u0646\u06CC\u0644\u0627": "neela",
+  "\u06C1\u0631\u0627": "hara",
+  "\u067E\u06CC\u0644\u0627": "peela",
+  "\u0628\u06BE\u0648\u0631\u0627": "bhura",
+  "\u06AF\u0644\u0627\u0628\u06CC": "gulabi",
+  "\u0633\u0646\u06C1\u0631\u06CC": "sunehri",
+  // ---- animals ----
+  "\u06A9\u062A\u0627": "kutta",
+  "\u0628\u0644\u06CC": "billi",
+  "\u06AF\u06BE\u0648\u0691\u0627": "ghora",
+  "\u06AF\u0627\u0626\u06D2": "gaye",
+  "\u0628\u06A9\u0631\u06CC": "bakri",
+  "\u0628\u06BE\u06CC\u0646\u0633": "bhains",
+  "\u0634\u06CC\u0631": "sheer",
+  "\u06C1\u0627\u062A\u06BE\u06CC": "hathi",
+  "\u0627\u0648\u0646\u0679": "oont",
+  "\u0628\u0646\u062F\u0631": "bandar",
+  "\u0686\u0648\u06C1\u0627": "chooha",
+  "\u067E\u0631\u0646\u062F\u06C1": "parinda",
+  "\u06A9\u0648\u0627": "kawa",
+  "\u0637\u0648\u0637\u0627": "tota",
+  "\u0633\u0627\u0646\u067E": "saanp",
+  // ---- extended family ----
+  "\u0686\u0686\u0627": "chacha",
+  "\u0645\u0627\u0645\u0648\u06BA": "mamoon",
+  "\u062E\u0627\u0644\u06C1": "khala",
+  "\u067E\u06BE\u0648\u067E\u06BE\u06CC": "phupi",
+  "\u062F\u0627\u062F\u0627": "dada",
+  "\u062F\u0627\u062F\u06CC": "dadi",
+  "\u0646\u0627\u0646\u0627": "nana",
+  "\u0646\u0627\u0646\u06CC": "nani",
+  "\u0631\u0634\u062A\u06C1": "rishta",
+  "\u062E\u0627\u0646\u062F\u0627\u0646": "khandan",
+  "\u0645\u06C1\u0645\u0627\u0646": "mehman",
+  // ---- food ----
+  "\u06A9\u06BE\u06CC\u0631": "kheer",
+  "\u062D\u0644\u0648\u06C1": "halwa",
+  "\u0628\u0631\u06CC\u0627\u0646\u06CC": "biryani",
+  "\u06A9\u0628\u0627\u0628": "kabab",
+  "\u0633\u0627\u0644\u0646": "salan",
+  "\u062F\u0627\u0644": "daal",
+  "\u0622\u0679\u0627": "aata",
+  "\u0645\u06A9\u06BE\u0646": "makhan",
+  "\u062F\u06C1\u06CC": "dahi",
+  "\u0634\u06C1\u062F": "shehad",
+  "\u0645\u0631\u0686": "mirch",
+  "\u06C1\u0644\u062F\u06CC": "haldi",
+  "\u0644\u06C1\u0633\u0646": "lehsun",
+  "\u067E\u06CC\u0627\u0632": "pyaz",
+  "\u0679\u0645\u0627\u0679\u0631": "tamatar",
+  "\u0622\u0644\u0648": "aloo",
+  "\u06AF\u0627\u062C\u0631": "gajar",
+  "\u062A\u0631\u0628\u0648\u0632": "tarbooz",
+  "\u0627\u0646\u0627\u0631": "anar",
+  "\u06A9\u06BE\u062C\u0648\u0631": "khajoor",
+  "\u0628\u0627\u062F\u0627\u0645": "badam",
+  // ---- places on the map ----
+  "\u06A9\u0631\u0627\u0686\u06CC": "karachi",
+  "\u0644\u0627\u06C1\u0648\u0631": "lahore",
+  "\u067E\u0634\u0627\u0648\u0631": "peshawar",
+  "\u06A9\u0648\u0626\u0679\u06C1": "quetta",
+  "\u0645\u0644\u062A\u0627\u0646": "multan",
+  "\u0631\u0627\u0648\u0644\u067E\u0646\u0688\u06CC": "rawalpindi",
+  "\u0633\u06CC\u0627\u0644\u06A9\u0648\u0679": "sialkot",
+  "\u0628\u06BE\u0627\u0631\u062A": "bharat",
+  "\u06C1\u0646\u062F\u0648\u0633\u062A\u0627\u0646": "hindustan",
+  "\u0686\u06CC\u0646": "cheen",
+  "\u0627\u0645\u0631\u06CC\u06A9\u06C1": "amreeka",
+  "\u0628\u0631\u0637\u0627\u0646\u06CC\u06C1": "bartania",
+  "\u0627\u06CC\u0631\u0627\u0646": "iran",
+  "\u0627\u0641\u063A\u0627\u0646\u0633\u062A\u0627\u0646": "afghanistan",
+  "\u06A9\u0634\u0645\u06CC\u0631": "kashmir",
+  "\u067E\u0646\u062C\u0627\u0628": "punjab",
+  "\u0633\u0646\u062F\u06BE": "sindh",
+  "\u0628\u0644\u0648\u0686\u0633\u062A\u0627\u0646": "balochistan",
   // ---- names that appear constantly in Urdu content ----
   "\u0645\u062D\u0645\u062F": "muhammad",
   "\u0627\u062D\u0645\u062F": "ahmed",
@@ -1231,6 +1426,15 @@ function romanizeWord(word) {
       pieces.push({ text: "a", vowel: true });
       continue;
     }
+    if (ch === "\u06CC" && chars[i + 1] === "\u06BA" && i + 1 === chars.length - 1) {
+      pieces.push({ text: "ein", vowel: true });
+      i++;
+      continue;
+    }
+    if (ch === "\u06CC" && !last) {
+      pieces.push({ text: "e", vowel: true });
+      continue;
+    }
     pieces.push({ text: LETTERS[ch] ?? ch, vowel: VOWEL_LETTERS.has(ch) });
   }
   if (pieces.length > 2 && !pieces[0].vowel && !pieces[1].vowel) {