marathi-transliterate 1.5.0 → 1.7.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "marathi-transliterate",
-  "version": "1.5.0",
+  "version": "1.7.1",
   "description": "Zero-dependency, offline-first Marathi / Devanagari phonetic transliteration library. Converts English typing to Marathi (e.g. sakhar -> साखर) seamlessly in plain JS, Node.js, and frontend frameworks.",
   "type": "module",
   "main": "src/index.js",

package/src/dictionary.js

@@ -1303,6 +1303,340 @@ export const MARATHI_DICTIONARY = {
   "khanyachadink": "खाण्याचा डिंक",
   "bavchi": "बावची",
   "nagarmotha": "नागरमोथा",
-  "pippali": "पिंपळी"
+  "pippali": "पिंपळी",
 
+  // Kranti (Famous Maharashtrian edible oil brand & name)
+  "kranti": "क्रांती",
+  "cranti": "क्रांती",
+  "kraanti": "क्रांती",
+  "krantee": "क्रांती",
+  "krantioil": "क्रांती तेल",
+  "krantitel": "क्रांती तेल",
+  "krantisunfloweroil": "क्रांती सूर्यफूल तेल",
+  "krantisoyabeanoil": "क्रांती सोयाबीन तेल",
+  "krantigroundnutoil": "क्रांती शेंगदाणा तेल",
+
+  // Electricals, Lighting & General Store terms (Watt, Bulb, LED, etc.)
+  "watt": "वॉट",
+  "watts": "वॉट",
+  "wat": "वाट",
+  "waat": "वाट",
+  "vat": "वात",
+  "bulb": "बल्ब",
+  "bulbs": "बल्ब",
+  "balb": "बल्ब",
+  "led": "एलईडी",
+  "cfl": "सीएफएल",
+  "switch": "स्विच",
+  "switches": "स्विचेस",
+  "socket": "सॉकेट",
+  "wire": "वायर",
+  "wires": "वायर",
+  "plug": "प्लग",
+  "holder": "होल्डर",
+  "tester": "टेस्टर",
+  "tubelight": "ट्युबलाईट",
+  "tube": "ट्यूब",
+  "cell": "सेल",
+  "adaptor": "अ‍ॅडॉप्टर",
+  "adapter": "अ‍ॅडॉप्टर",
+  "cable": "केबल",
+  "fuse": "फ्युज",
+  "mcb": "एमसीबी",
+  "choke": "चोक",
+  "starter": "स्टार्टर",
+  "tape": "टेप",
+  "insulationtape": "इन्स्युलेशन टेप",
+  "regulator": "रेग्युलेटर",
+  "board": "बोर्ड",
+  "extensionboard": "एक्स्टेंशन बोर्ड",
+
+  // Common Marathi vocabulary & items
+  "shanti": "शांती",
+  "shaanti": "शांती",
+  "shantee": "शांती",
+  "kanti": "कांती",
+  "vati": "वाटी",
+  "vatya": "वाट्या",
+  "watti": "वाटी",
+  "wattya": "वाट्या",
+
+  // Anand & names
+  "anand": "आनंद",
+  "aanand": "आनंद",
+
+  // Common customer honorifics, titles, relations and grocery staples
+  "bhaiyya": "भैय्या",
+  "bhaiya": "भैया",
+  "bhayya": "भय्या",
+  "bhaiyys": "भैय्या",
+  "bhaiyas": "भैया",
+  "bhai": "भाई",
+  "bhau": "भाऊ",
+  "mama": "मामा",
+  "kaka": "काका",
+  "nana": "नाना",
+  "bapu": "बापू",
+  "babu": "बाबू",
+  "tai": "ताई",
+  "aai": "आई",
+  "didi": "दीदी",
+  "aaba": "आबा",
+  "aba": "आबा",
+  "saheb": "साहेब",
+  "sahab": "साहेब",
+  "sheth": "शेठ",
+  "seth": "शेठ",
+  "shethji": "शेठजी",
+  "anna": "अण्णा",
+  "appa": "आप्पा",
+  "rao": "राव",
+  "chaha": "चहा",
+  "bhaji": "भाजी",
+  "poha": "पोहे",
+  "pohe": "पोहे",
+  "khari": "खारी",
+  "toast": "टोस्ट",
+
+  // Fast typing & plural slips (ending in s / ys)
+  "bhais": "भाई",
+  "bhaus": "भाऊ",
+  "bhaiyyas": "भैय्या",
+  "bhaiyas": "भैया",
+  "bhayyas": "भय्या",
+  "kakas": "काका",
+  "kakis": "काकी",
+  "mamas": "मामा",
+  "mamis": "मामी",
+  "dadas": "दादा",
+  "nanas": "नाना",
+  "nanis": "नानी",
+  "tais": "ताई",
+  "taais": "ताई",
+  "didis": "दीदी",
+  "sahebs": "साहेब",
+  "sheths": "शेठ",
+  "seths": "शेठ",
+  "annas": "अण्णा",
+  "appas": "आप्पा",
+  "patils": "पाटील",
+  "deshmukhs": "देशमुख",
+  "pawars": "पवार",
+  "shindes": "शिंदे",
+  "jadhavs": "जाधव",
+
+  // Family & Kinship terms
+  "taai": "ताई",
+  "kaki": "काकी",
+  "mami": "मामी",
+  "nani": "नानी",
+  "aaji": "आजी",
+  "aji": "आजी",
+  "aajoba": "आजोबा",
+  "ajoba": "आजोबा",
+  "mavshi": "मावशी",
+  "maushi": "मावशी",
+  "moushi": "मावशी",
+  "vahini": "वहिनी",
+  "wahini": "वहिनी",
+  "bhavji": "भावजी",
+  "bhaoji": "भावजी",
+  "aatya": "आत्या",
+  "atya": "आत्या",
+  "sasre": "सासरे",
+  "sasu": "सासू",
+  "sasubai": "सासूबाई",
+  "javai": "जावई",
+  "dir": "दीर",
+  "tatya": "तात्या",
+  "tatyas": "तात्या",
+  "pant": "पंत",
+  "chota": "छोटा",
+  "chhota": "छोटा",
+  "motha": "मोठा",
+
+  // Titles, prefixes & respectful forms
+  "sau": "सौ.",
+  "smt": "श्रीमती",
+  "shri": "श्री",
+  "shree": "श्री",
+  "chiranjiv": "चिरंजीव",
+  "chi": "चि.",
+  "kumari": "कुमारी",
+  "ku": "कु.",
+  "sir": "सर",
+  "madam": "मॅडम",
+  "sethji": "शेठजी",
+  "bapuji": "बापूजी",
+  "babuji": "बाबूजी",
+
+  // Compound -saheb names
+  "bhausaheb": "भाऊसाहेब",
+  "bhausahebs": "भाऊसाहेब",
+  "dadasaheb": "दादासाहेब",
+  "dadasahebs": "दादासाहेब",
+  "kakasaheb": "काकासाहेब",
+  "kakasahebs": "काकासाहेब",
+  "mamasaheb": "मामासाहेब",
+  "mamasahebs": "मामासाहेब",
+  "nanasaheb": "नानासाहेब",
+  "nanasahebs": "नानासाहेब",
+  "appasaheb": "आप्पासाहेब",
+  "appasahebs": "आप्पासाहेब",
+  "annasaheb": "अण्णासाहेब",
+  "annasahebs": "अण्णासाहेब",
+  "babasaheb": "बाबासाहेब",
+  "babasahebs": "बाबासाहेब",
+  "balasaheb": "बाळासाहेब",
+  "tatyasaheb": "तात्यासाहेब",
+  "patilsaheb": "पाटीलसाहेब",
+  "shethsaheb": "शेठसाहेब",
+  "doctorsaheb": "डॉक्टरसाहेब",
+
+  // Compound -rao names
+  "baburao": "बाबूराव",
+  "anandrao": "आनंदराव",
+  "anandarao": "आनंदराव",
+  "shankarrao": "शंकरराव",
+  "govindrao": "गोविंदराव",
+  "ganpatrao": "गणपतराव",
+  "subhashrao": "सुभाषराव",
+  "madhavrao": "माधवराव",
+  "yashwantrao": "यशवंतराव",
+  "vilasrao": "विलासराव",
+  "chandrakantrao": "चंद्रकांतराव",
+  "ashokrao": "अशोकराव",
+  "rameshrao": "रमेशराव",
+  "sureshrao": "सुरेशराव",
+  "diliprao": "दिलीपराव",
+  "dadarao": "दादाराव",
+  "patilrao": "पाटीलराव",
+  "shinderao": "शिंदेराव",
+  "deshmukhrao": "देशमुखराव",
+
+  // Common Maharashtra Surnames
+  "patil": "पाटील",
+  "deshmukh": "देशमुख",
+  "pawar": "पवार",
+  "shinde": "शिंदे",
+  "jadhav": "जाधव",
+  "jadhao": "जाधव",
+  "more": "मोरे",
+  "kadam": "कदम",
+  "chavan": "चव्हाण",
+  "gaikwad": "गायकवाड",
+  "joshi": "जोशी",
+  "kulkarni": "कुलकर्णी",
+  "ghadge": "घाडगे",
+  "bhosale": "भोसले",
+  "bhosle": "भोसले",
+  "raut": "राऊत",
+  "kale": "काळे",
+  "salunkhe": "साळुंखे",
+  "thakur": "ठाकूर",
+  "sawant": "सावंत",
+  "mane": "माने",
+  "shelke": "शेळके",
+  "jagtap": "जगताप",
+  "wagh": "वाघ",
+  "shete": "शेटे",
+  "khot": "खोत",
+  "nikam": "निकम",
+  "koli": "कोळी",
+  "sonawane": "सोनवणे",
+  "tamboli": "तांबोळी",
+  "magar": "मगर",
+  "ghorpade": "घोरपडे",
+  "darekar": "दरेकर",
+  "gavande": "गवंडे",
+  "gawande": "गवंडे",
+  "katore": "कटोरे",
+  "borade": "बोराडे",
+  "ghule": "घुले",
+  "landge": "लांडगे",
+  "khule": "खुळे",
+  "bidkar": "बीडकर",
+  "sharma": "शर्मा",
+  "verma": "वर्मा",
+  "gupta": "गुप्ता",
+  "shah": "शाह",
+  "jain": "जैन",
+  "agarwal": "अगरवाल",
+  "singh": "सिंग",
+
+  // Common Given Names
+  "sachin": "सचिन",
+  "rahul": "राहुल",
+  "amit": "अमित",
+  "amol": "अमोल",
+  "atul": "अतुल",
+  "ajay": "अजय",
+  "vijay": "विजय",
+  "sanjay": "संजय",
+  "sunil": "सुनील",
+  "anil": "अनिल",
+  "ramesh": "रमेश",
+  "suresh": "सुरेश",
+  "ganesh": "गणेश",
+  "mahesh": "महेश",
+  "dinesh": "दिनेश",
+  "santosh": "संतोष",
+  "vikas": "विकास",
+  "prakash": "प्रकाश",
+  "pradeep": "प्रदीप",
+  "pradip": "प्रदीप",
+  "sandip": "संदीप",
+  "sandeep": "संदीप",
+  "deepak": "दीपक",
+  "dipak": "दीपक",
+  "rohit": "रोहित",
+  "nitin": "नितीन",
+  "kiran": "किरण",
+  "ashok": "अशोक",
+  "swapnil": "स्वप्निल",
+  "mangesh": "मंगेश",
+  "yogesh": "योगेश",
+  "nilesh": "निलेश",
+  "pravin": "प्रवीण",
+  "prashant": "प्रशांत",
+  "sudhir": "सुधीर",
+  "subhash": "सुभाष",
+  "bhagwan": "भगवान",
+  "vishnu": "विष्णू",
+  "pandurang": "पांडुरंग",
+  "tukaram": "तुकाराम",
+  "dnyaneshwar": "ज्ञानेश्वर",
+  "namdev": "नामदेव",
+  "eknath": "एकनाथ",
+  "maruti": "मारुती",
+  "mahadev": "महादेव",
+  "khandu": "खंडू",
+  "chhabu": "छाबू",
+
+  // Dairy & Grocery Staples
+  "doodh": "दूध",
+  "dudh": "दूध",
+  "toop": "तूप",
+  "tup": "तूप",
+  "taak": "ताक",
+  "tak": "ताक",
+  "dahi": "दही",
+  "lonche": "लोणचे",
+  "loncha": "लोणचे",
+  "papad": "पापड",
+  "kurdaya": "कुरडया",
+  "kurdai": "कुरडई",
+  "sandge": "सांडगे",
+  "shev": "शेव",
+  "farsan": "फरसाण",
+  "chivda": "चिवडा",
+  "ladu": "लाडू",
+  "ladoo": "लाडू",
+  "pedha": "पेढा",
+  "peda": "पेढा",
+  "barfi": "बर्फी",
+  "jalebi": "जिलेबी",
+  "gulabjamun": "गुलाबजाम",
+  "biscuit": "बिस्कीट",
 };
+

package/src/dom.js

@@ -218,7 +218,7 @@ export function attachDevanagari(target, options = {}) {
         selectCandidate(selectedIndex, e.key === 'Enter' ? '' : ' ');
         return;
       }
-      if (e.key === ' ') {
+      if (e.key === ' ' || e.key === 'Spacebar' || e.code === 'Space') {
         e.preventDefault();
         selectCandidate(selectedIndex, ' ');
         return;

package/src/index.js

@@ -53,6 +53,37 @@ export function transliterateWord(word) {
     return MARATHI_DICTIONARY[clean];
   }
 
+  // 1b. Check trailing "s" fast-typing slip (e.g. bhais -> भाई, bhaus -> भाऊ, kakas -> काका)
+  if (clean.endsWith("s") && clean.length > 2) {
+    const base = clean.replace(/s+$/, "");
+    if (MARATHI_DICTIONARY[base]) {
+      return MARATHI_DICTIONARY[base];
+    }
+  }
+
+  // 1c. Check compound honorific suffixes (-saheb, -sahab, -rao, -sheth, -seth, -ji, -bai)
+  if (clean.endsWith("saheb") && clean.length > 5) {
+    return transliterateWord(clean.slice(0, -5)) + "साहेब";
+  }
+  if (clean.endsWith("sahab") && clean.length > 5) {
+    return transliterateWord(clean.slice(0, -5)) + "साहेब";
+  }
+  if (clean.endsWith("rao") && clean.length > 3) {
+    return transliterateWord(clean.slice(0, -3)) + "राव";
+  }
+  if (clean.endsWith("sheth") && clean.length > 5) {
+    return transliterateWord(clean.slice(0, -5)) + "शेठ";
+  }
+  if (clean.endsWith("seth") && clean.length > 4) {
+    return transliterateWord(clean.slice(0, -4)) + "शेठ";
+  }
+  if (clean.endsWith("ji") && clean.length > 3) {
+    return transliterateWord(clean.slice(0, -2)) + "जी";
+  }
+  if (clean.endsWith("bai") && clean.length > 4) {
+    return transliterateWord(clean.slice(0, -3)) + "बाई";
+  }
+
   // 2. Check local/memory cache
   const cached = getCachedWord(clean);
   if (cached && cached.length > 0) {
@@ -100,6 +131,12 @@ export const toDevanagari = transliterate;
  * @param {boolean} [options.includeOriginal=true]
  * @returns {string[]}
  */
+function transiterateCompound(prefix, suffix) {
+  if (!prefix) return suffix;
+  const p = MARATHI_DICTIONARY[prefix] || phoneticTransliterateWord(prefix);
+  return p + suffix;
+}
+
 export function getSuggestions(word, options = {}) {
   if (!word || !word.trim()) return [];
   const clean = word.toLowerCase().trim();
@@ -223,11 +260,13 @@ export function getSuggestions(word, options = {}) {
 
     // 4l. Chandra "ॉ" (Candra O, \u0949) and "ो" (O, \u094B)
     // Essential for English loanwords in grocery & everyday shop items
-    // e.g. polish -> पॉलिश, coil -> कॉईल, coffee -> कॉफी, doctor -> डॉक्टर, sauce -> सॉस, box -> बॉक्स, ball -> बॉल, stock -> स्टॉक
+    // e.g. watt -> वॉट / वॅट / वाट, polish -> पॉलिश, coil -> कॉईल, coffee -> कॉफी, doctor -> डॉक्टर, sauce -> सॉस, box -> बॉक्स, ball -> बॉल, stock -> स्टॉक
     if (s.includes("ो")) {
       add(s.replace(/ो/g, "ॉ"));
     } else if (s.includes("ॉ")) {
       add(s.replace(/ॉ/g, "ो"));
+      add(s.replace(/ॉ/g, "ॅ"));
+      add(s.replace(/ॉ/g, "ा"));
     }
     if (s.startsWith("ओ")) {
       add("ऑ" + s.slice(1));
@@ -241,6 +280,7 @@ export function getSuggestions(word, options = {}) {
       add(s.replace(/े/g, "ॅ"));
     } else if (s.includes("ॅ")) {
       add(s.replace(/ॅ/g, "े"));
+      add(s.replace(/ॅ/g, "ॉ"));
     }
 
     // 4n. Smart Anusvara on "su" prefixes and "sunth"
@@ -254,6 +294,49 @@ export function getSuggestions(word, options = {}) {
     if (clean.startsWith("rajh")) {
       add("राजहंस");
     }
+
+    // 4p. Smart Kana + Anusvara (ां) expansion (मराठी शुद्धलेखन)
+    // e.g. "kranti" -> "क्रांती" / "क्रांति", "shanti" -> "शांती", "kanti" -> "कांती", "kanda" -> "कांदा", "gandhi" -> "गांधी"
+    if (s.includes("ं")) {
+      const withKanaAnusvar = s.replace(/([^ािीुूेैोौॉॅ्\s])ं/g, "$1ां");
+      if (withKanaAnusvar !== s) {
+        add(withKanaAnusvar);
+        if (withKanaAnusvar.endsWith("ि")) add(withKanaAnusvar.slice(0, -1) + "ी");
+        if (withKanaAnusvar.endsWith("ी")) add(withKanaAnusvar.slice(0, -1) + "ि");
+      }
+    }
+
+    // 4q. Customer honorifics & bhai/bhau expansions
+    if (clean.startsWith("bhai") || clean.startsWith("bhay")) {
+      add("भैय्या");
+      add("भैया");
+      add("भय्या");
+      add("भाई");
+    }
+    if (clean.startsWith("bhau")) {
+      add("भाऊ");
+    }
+    if (clean.endsWith("s") && clean.length > 2) {
+      const base = clean.replace(/s+$/, "");
+      if (MARATHI_DICTIONARY[base]) {
+        add(MARATHI_DICTIONARY[base]);
+      }
+    }
+    if (clean.endsWith("saheb") && clean.length > 5) {
+      add(transiterateCompound(clean.slice(0, -5), "साहेब"));
+    }
+    if (clean.endsWith("rao") && clean.length > 3) {
+      add(transiterateCompound(clean.slice(0, -3), "राव"));
+    }
+    if (clean.endsWith("sheth") && clean.length > 5) {
+      add(transiterateCompound(clean.slice(0, -5), "शेठ"));
+    }
+
+  }
+
+  // Background fetch to enrich cache if online (non-blocking)
+  if (typeof fetch !== "undefined" && !getCachedWord(clean)) {
+    fetchOnlineMarathi(clean).catch(() => {});
   }
 
   // 5. Prefix matches from dictionary (if clean.length >= 2)

package/src/phonetics.js

@@ -63,7 +63,12 @@ const CONSONANTS = [
 
 const INDEPENDENT_VOWELS = [
   { en: "aa", mr: "आ" },
-  { en: "A", mr: "आ" },
+  { en: "A", mr: "आ", caseSensitive: true },
+  { en: "ai", mr: "ऐ" },
+  { en: "ay", mr: "ऐ" },
+  { en: "au", mr: "औ" },
+  { en: "ou", mr: "औ" },
+  { en: "ow", mr: "औ" },
   { en: "a", mr: "अ" },
   { en: "ee", mr: "ई" },
   { en: "ii", mr: "ई" },
@@ -71,11 +76,6 @@ const INDEPENDENT_VOWELS = [
   { en: "oo", mr: "ऊ" },
   { en: "uu", mr: "ऊ" },
   { en: "u", mr: "उ" },
-  { en: "ai", mr: "ऐ" },
-  { en: "ay", mr: "ऐ" },
-  { en: "au", mr: "औ" },
-  { en: "ou", mr: "औ" },
-  { en: "ow", mr: "औ" },
   { en: "e", mr: "ए" },
   { en: "o", mr: "ओ" },
   { en: "am", mr: "अं" },
@@ -86,8 +86,14 @@ const INDEPENDENT_VOWELS = [
 ];
 
 const MATRAS = [
+  { en: "ao", mr: "ाव" },
   { en: "aa", mr: "ा" },
-  { en: "A", mr: "ा" },
+  { en: "A", mr: "ा", caseSensitive: true },
+  { en: "ai", mr: "ै" },
+  { en: "ay", mr: "ै" },
+  { en: "au", mr: "ौ" },
+  { en: "ou", mr: "ौ" },
+  { en: "ow", mr: "ौ" },
   { en: "a", mr: "" }, // Inherent vowel: cancels halant; at word end becomes kana
   { en: "ee", mr: "ी" },
   { en: "ii", mr: "ी" },
@@ -95,11 +101,6 @@ const MATRAS = [
   { en: "oo", mr: "ू" },
   { en: "uu", mr: "ू" },
   { en: "u", mr: "ु" },
-  { en: "ai", mr: "ै" },
-  { en: "ay", mr: "ै" },
-  { en: "au", mr: "ौ" },
-  { en: "ou", mr: "ौ" },
-  { en: "ow", mr: "ौ" },
   { en: "e", mr: "े" },
   { en: "o", mr: "ो" },
   { en: "am", mr: "ं" },
@@ -153,6 +154,10 @@ export function phoneticTransliterateWord(text) {
           res += "ऊ";
           i += 1;
           matchedVowel = true;
+        } else if (clean[i].toLowerCase() === "o" && prevChar.toLowerCase() === "a") {
+          res += "व";
+          i += 1;
+          matchedVowel = true;
         } else if (clean[i].toLowerCase() === "a") {
           i += 1;
           matchedVowel = true;