@delali/narsil 0.1.0

package/dist/languages/swahili.mjs

@@ -0,0 +1,212 @@
+// src/languages/swahili.ts
+var SUBJECT_PREFIXES = ["ni", "tu", "wa", "vi", "zi", "li", "ya", "ku"];
+var SHORT_SUBJECT_PREFIXES = ["u", "a", "i", "m"];
+var TENSE_MARKERS = ["na", "li", "ta", "me", "ki"];
+var RELATIVE_MARKERS = ["cho", "vyo", "ye", "zo", "lo", "yo", "ko", "po", "mo"];
+var NEGATIVE_PREFIXES = ["ha", "si"];
+var NOUN_CLASS_PREFIXES = ["wa", "mi", "ki", "vi", "ma"];
+var SHORT_NOUN_PREFIXES = ["m", "u"];
+var LONG_SUFFIXES = ["isha", "ika", "ana", "iwa", "ewa", "aje", "ane", "eni", "ini"];
+var SHORT_SUFFIXES = ["wa", "ia", "ea"];
+var FINAL_VOWELS = ["a", "i", "e", "u"];
+function tryRemovePrefix(word, prefix, minRemaining) {
+  if (word.startsWith(prefix) && word.length - prefix.length >= minRemaining) {
+    return word.slice(prefix.length);
+  }
+  return null;
+}
+function removePrefixes(word) {
+  let current = word;
+  for (const prefix of NEGATIVE_PREFIXES) {
+    const result = tryRemovePrefix(current, prefix, 3);
+    if (result !== null) {
+      current = result;
+      break;
+    }
+  }
+  let subjectRemoved = false;
+  for (const prefix of SUBJECT_PREFIXES) {
+    const result = tryRemovePrefix(current, prefix, 3);
+    if (result !== null) {
+      current = result;
+      subjectRemoved = true;
+      break;
+    }
+  }
+  if (!subjectRemoved) {
+    for (const prefix of SHORT_SUBJECT_PREFIXES) {
+      const result = tryRemovePrefix(current, prefix, 3);
+      if (result !== null) {
+        current = result;
+        subjectRemoved = true;
+        break;
+      }
+    }
+  }
+  if (subjectRemoved) {
+    for (const marker of TENSE_MARKERS) {
+      const result = tryRemovePrefix(current, marker, 3);
+      if (result !== null) {
+        current = result;
+        break;
+      }
+    }
+    for (const marker of RELATIVE_MARKERS) {
+      const result = tryRemovePrefix(current, marker, 3);
+      if (result !== null) {
+        current = result;
+        break;
+      }
+    }
+  }
+  if (!subjectRemoved) {
+    for (const prefix of NOUN_CLASS_PREFIXES) {
+      const result = tryRemovePrefix(current, prefix, 3);
+      if (result !== null) {
+        current = result;
+        break;
+      }
+    }
+    if (current === word) {
+      for (const prefix of SHORT_NOUN_PREFIXES) {
+        const result = tryRemovePrefix(current, prefix, 3);
+        if (result !== null) {
+          current = result;
+          break;
+        }
+      }
+    }
+  }
+  return current;
+}
+function removeSuffixes(word) {
+  for (const suffix of LONG_SUFFIXES) {
+    if (word.endsWith(suffix) && word.length - suffix.length >= 3) {
+      return word.slice(0, -suffix.length);
+    }
+  }
+  for (const suffix of SHORT_SUFFIXES) {
+    if (word.endsWith(suffix) && word.length - suffix.length >= 3) {
+      return word.slice(0, -suffix.length);
+    }
+  }
+  for (const vowel of FINAL_VOWELS) {
+    if (word.endsWith(vowel) && word.length - 1 >= 3) {
+      return word.slice(0, -1);
+    }
+  }
+  return word;
+}
+function stem(word) {
+  if (word.length < 4) return word;
+  let result = removePrefixes(word);
+  result = removeSuffixes(result);
+  return result;
+}
+var stopWords = /* @__PURE__ */ new Set([
+  "wa",
+  "na",
+  "ya",
+  "kwa",
+  "la",
+  "za",
+  "ni",
+  "au",
+  "katika",
+  "kama",
+  "lakini",
+  "pia",
+  "hii",
+  "yake",
+  "wake",
+  "yangu",
+  "yetu",
+  "yao",
+  "ile",
+  "hizo",
+  "hiyo",
+  "hivi",
+  "hivyo",
+  "huku",
+  "kila",
+  "bila",
+  "ama",
+  "bali",
+  "hata",
+  "ingawa",
+  "kwamba",
+  "kuwa",
+  "ili",
+  "mpaka",
+  "tangu",
+  "ndiyo",
+  "hapana",
+  "hapa",
+  "pale",
+  "sana",
+  "tu",
+  "hasa",
+  "kabisa",
+  "ndio",
+  "nini",
+  "gani",
+  "wapi",
+  "lini",
+  "vipi",
+  "nani",
+  "kwani",
+  "basi",
+  "sasa",
+  "tena",
+  "bado",
+  "tayari",
+  "labda",
+  "pengine",
+  "yote",
+  "wote",
+  "zote",
+  "kote",
+  "nyingi",
+  "mengi",
+  "wengi",
+  "chache",
+  "kidogo",
+  "zaidi",
+  "sawa",
+  "kweli",
+  "si",
+  "siyo",
+  "hakuna",
+  "wala",
+  "halafu",
+  "kisha",
+  "baada",
+  "kabla",
+  "wakati",
+  "mara",
+  "daima",
+  "kamwe",
+  "ikiwa",
+  "iwapo",
+  "endapo",
+  "ijapokuwa",
+  "kutoka",
+  "hadi",
+  "kuhusu",
+  "juu",
+  "chini",
+  "ndani",
+  "nje",
+  "mbele",
+  "nyuma",
+  "karibu",
+  "mbali"
+]);
+var swahili = {
+  name: "swahili",
+  stemmer: stem,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9]+/gi }
+};
+
+export { swahili };

package/dist/languages/swedish.d.ts

@@ -0,0 +1,5 @@
+import { L as LanguageModule } from '../language-ClUGLuoC.js';
+
+declare const swedish: LanguageModule;
+
+export { swedish };

package/dist/languages/swedish.mjs

@@ -0,0 +1,224 @@
+// src/languages/swedish.ts
+var VOWELS = "aeiouy\xE4\xE5\xF6";
+function isVowel(ch) {
+  return VOWELS.includes(ch);
+}
+function computeR1(word) {
+  let i = 0;
+  while (i < word.length && !isVowel(word[i])) i++;
+  while (i < word.length && isVowel(word[i])) i++;
+  const r1 = i < word.length ? i + 1 : word.length;
+  return Math.max(r1, 3);
+}
+var S_ENDINGS = "bcdfghjklmnoprtvy";
+var STEP1_SUFFIXES = [
+  "heterna",
+  "hetens",
+  "arnas",
+  "ernas",
+  "ornas",
+  "anden",
+  "heten",
+  "heter",
+  "andes",
+  "arens",
+  "andet",
+  "arna",
+  "erna",
+  "orna",
+  "ande",
+  "arne",
+  "aste",
+  "aren",
+  "ades",
+  "erns",
+  "ade",
+  "are",
+  "ern",
+  "ens",
+  "het",
+  "ast",
+  "ad",
+  "en",
+  "ar",
+  "er",
+  "or",
+  "as",
+  "es",
+  "at",
+  "a",
+  "e",
+  "s"
+];
+function step1(word, r1) {
+  for (const suffix of STEP1_SUFFIXES) {
+    if (!word.endsWith(suffix)) continue;
+    const boundary = word.length - suffix.length;
+    if (boundary < r1) continue;
+    if (suffix === "s") {
+      if (boundary > 0 && S_ENDINGS.includes(word[boundary - 1])) {
+        return word.slice(0, boundary);
+      }
+      continue;
+    }
+    return word.slice(0, boundary);
+  }
+  return word;
+}
+var STEP2_ENDINGS = ["dd", "gd", "nn", "dt", "gt", "kt", "tt"];
+function step2(word, r1) {
+  for (const ending of STEP2_ENDINGS) {
+    if (!word.endsWith(ending)) continue;
+    if (word.length - 2 < r1) continue;
+    return word.slice(0, -1);
+  }
+  return word;
+}
+var STEP3_SUFFIXES = [
+  ["fullt", "full"],
+  ["l\xF6st", "l\xF6s"],
+  ["lig", null],
+  ["els", null],
+  ["ig", null]
+];
+function step3(word, r1) {
+  for (const [suffix, replacement] of STEP3_SUFFIXES) {
+    if (!word.endsWith(suffix)) continue;
+    const boundary = word.length - suffix.length;
+    if (boundary < r1) continue;
+    return replacement ? word.slice(0, boundary) + replacement : word.slice(0, boundary);
+  }
+  return word;
+}
+function stem(word) {
+  if (word.length < 3) return word;
+  const r1 = computeR1(word);
+  word = step1(word, r1);
+  word = step2(word, r1);
+  word = step3(word, r1);
+  return word;
+}
+var stopWords = /* @__PURE__ */ new Set([
+  "och",
+  "det",
+  "att",
+  "i",
+  "en",
+  "jag",
+  "hon",
+  "som",
+  "han",
+  "p\xE5",
+  "den",
+  "med",
+  "var",
+  "sig",
+  "f\xF6r",
+  "s\xE5",
+  "till",
+  "\xE4r",
+  "men",
+  "ett",
+  "om",
+  "hade",
+  "de",
+  "av",
+  "icke",
+  "mig",
+  "du",
+  "henne",
+  "d\xE5",
+  "sin",
+  "nu",
+  "har",
+  "inte",
+  "hans",
+  "honom",
+  "skulle",
+  "hennes",
+  "d\xE4r",
+  "min",
+  "man",
+  "ej",
+  "vid",
+  "kunde",
+  "n\xE5got",
+  "fr\xE5n",
+  "ut",
+  "n\xE4r",
+  "efter",
+  "upp",
+  "vi",
+  "dem",
+  "vara",
+  "vad",
+  "\xF6ver",
+  "\xE4n",
+  "dig",
+  "kan",
+  "sina",
+  "h\xE4r",
+  "ha",
+  "mot",
+  "alla",
+  "under",
+  "n\xE5gon",
+  "eller",
+  "allt",
+  "mycket",
+  "sedan",
+  "ju",
+  "denna",
+  "sj\xE4lv",
+  "detta",
+  "\xE5t",
+  "utan",
+  "varit",
+  "hur",
+  "ingen",
+  "mitt",
+  "ni",
+  "bli",
+  "blev",
+  "oss",
+  "din",
+  "dessa",
+  "n\xE5gra",
+  "deras",
+  "blir",
+  "mina",
+  "samma",
+  "vilken",
+  "er",
+  "s\xE5dan",
+  "v\xE5r",
+  "blivit",
+  "dess",
+  "inom",
+  "mellan",
+  "s\xE5dant",
+  "varf\xF6r",
+  "varje",
+  "vilka",
+  "ditt",
+  "vem",
+  "vilket",
+  "sitta",
+  "s\xE5dana",
+  "vart",
+  "dina",
+  "vars",
+  "v\xE5rt",
+  "v\xE5ra",
+  "ert",
+  "era",
+  "vilkas"
+]);
+var swedish = {
+  name: "swedish",
+  stemmer: stem,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9åäöü-]+/gi }
+};
+
+export { swedish };

package/dist/languages/tamil.d.ts

@@ -0,0 +1,5 @@
+import { L as LanguageModule } from '../language-ClUGLuoC.js';
+
+declare const tamil: LanguageModule;
+
+export { tamil };

package/dist/languages/tamil.mjs

@@ -0,0 +1,186 @@
+// src/languages/tamil.ts
+var VERB_SUFFIXES = [
+  "\u0B95\u0BBF\u0BB1\u0BC0\u0BB0\u0BCD\u0B95\u0BB3\u0BCD",
+  "\u0B95\u0BBF\u0BB1\u0BBE\u0BB0\u0BCD\u0B95\u0BB3\u0BCD",
+  "\u0BA8\u0BCD\u0BA4\u0BC0\u0BB0\u0BCD\u0B95\u0BB3\u0BCD",
+  "\u0BA8\u0BCD\u0BA4\u0BBE\u0BB0\u0BCD\u0B95\u0BB3\u0BCD",
+  "\u0BB5\u0BC0\u0BB0\u0BCD\u0B95\u0BB3\u0BCD",
+  "\u0BB5\u0BBE\u0BB0\u0BCD\u0B95\u0BB3\u0BCD",
+  "\u0B95\u0BBF\u0BB1\u0BC7\u0BA9\u0BCD",
+  "\u0B95\u0BBF\u0BB1\u0BBE\u0BAF\u0BCD",
+  "\u0B95\u0BBF\u0BB1\u0BBE\u0BA9\u0BCD",
+  "\u0B95\u0BBF\u0BB1\u0BBE\u0BB3\u0BCD",
+  "\u0B95\u0BBF\u0BB1\u0BCB\u0BAE\u0BCD",
+  "\u0B95\u0BBF\u0BA9\u0BCD\u0BB1\u0BA9",
+  "\u0BA8\u0BCD\u0BA4\u0BC7\u0BA9\u0BCD",
+  "\u0BA8\u0BCD\u0BA4\u0BBE\u0BAF\u0BCD",
+  "\u0BA8\u0BCD\u0BA4\u0BBE\u0BA9\u0BCD",
+  "\u0BA8\u0BCD\u0BA4\u0BBE\u0BB3\u0BCD",
+  "\u0BA8\u0BCD\u0BA4\u0BCB\u0BAE\u0BCD",
+  "\u0B95\u0BBF\u0BB1\u0BA4\u0BC1",
+  "\u0BA8\u0BCD\u0BA4\u0BA4\u0BC1",
+  "\u0BB5\u0BC7\u0BA9\u0BCD",
+  "\u0BB5\u0BBE\u0BAF\u0BCD",
+  "\u0BB5\u0BBE\u0BA9\u0BCD",
+  "\u0BB5\u0BBE\u0BB3\u0BCD",
+  "\u0BB5\u0BCB\u0BAE\u0BCD",
+  "\u0BA8\u0BCD\u0BA4\u0BC1",
+  "\u0BA4\u0BCD\u0BA4\u0BC1",
+  "\u0BB5\u0BA4\u0BC1",
+  "\u0B95\u0BCD\u0B95",
+  "\u0BAF"
+];
+var CASE_SUFFIXES = [
+  "\u0B87\u0B9F\u0BAE\u0BBF\u0BB0\u0BC1\u0BA8\u0BCD\u0BA4\u0BC1",
+  "\u0B87\u0BB0\u0BC1\u0BA8\u0BCD\u0BA4\u0BC1",
+  "\u0B89\u0B95\u0BCD\u0B95\u0BC1",
+  "\u0B89\u0B9F\u0BC8\u0BAF",
+  "\u0B95\u0BCD\u0B95\u0BC1",
+  "\u0B87\u0B9F\u0BAE\u0BCD",
+  "\u0B89\u0B9F\u0BA9\u0BCD",
+  "\u0B86\u0BB2\u0BCD",
+  "\u0B92\u0B9F\u0BC1",
+  "\u0B87\u0BA9\u0BCD",
+  "\u0B85\u0BA4\u0BC1",
+  "\u0B87\u0BB2\u0BCD",
+  "\u0B95\u0BA3\u0BCD",
+  "\u0B93\u0B9F\u0BC1",
+  "\u0B90"
+];
+var POST_POSITIONS = ["\u0BAA\u0BB1\u0BCD\u0BB1\u0BBF", "\u0BAE\u0BC7\u0BB2\u0BCD", "\u0B95\u0BC0\u0BB4\u0BCD", "\u0BAE\u0BC0\u0BA4\u0BC1", "\u0BB5\u0BB0\u0BC8"];
+function removeLongestSuffix(word, suffixes, minLength) {
+  for (const suffix of suffixes) {
+    if (word.endsWith(suffix) && word.length - suffix.length >= minLength) {
+      return word.slice(0, word.length - suffix.length);
+    }
+  }
+  return word;
+}
+function stem(word) {
+  if (word.length < 4) return word;
+  if (word.endsWith("\u0B95\u0BB3\u0BCD") && word.length - 3 >= 2) {
+    word = word.slice(0, word.length - 3);
+  }
+  word = removeLongestSuffix(word, CASE_SUFFIXES, 2);
+  word = removeLongestSuffix(word, VERB_SUFFIXES, 2);
+  word = removeLongestSuffix(word, POST_POSITIONS, 2);
+  return word;
+}
+var stopWords = /* @__PURE__ */ new Set([
+  "\u0B92\u0BB0\u0BC1",
+  "\u0B8E\u0BA9\u0BCD\u0BB1\u0BC1",
+  "\u0BAE\u0BB1\u0BCD\u0BB1\u0BC1\u0BAE\u0BCD",
+  "\u0B87\u0BA8\u0BCD\u0BA4",
+  "\u0B87\u0BA4\u0BC1",
+  "\u0B8E\u0BA9\u0BCD\u0BB1",
+  "\u0B95\u0BCA\u0BA3\u0BCD\u0B9F\u0BC1",
+  "\u0B8E\u0BA9\u0BCD\u0BAA\u0BA4\u0BC1",
+  "\u0BAA\u0BB2",
+  "\u0B86\u0B95\u0BC1\u0BAE\u0BCD",
+  "\u0B85\u0BB2\u0BCD\u0BB2\u0BA4\u0BC1",
+  "\u0B85\u0BB5\u0BB0\u0BCD",
+  "\u0BA8\u0BBE\u0BA9\u0BCD",
+  "\u0B89\u0BB3\u0BCD\u0BB3",
+  "\u0B85\u0BA8\u0BCD\u0BA4",
+  "\u0B87\u0BB5\u0BB0\u0BCD",
+  "\u0B8E\u0BA9",
+  "\u0BAE\u0BC1\u0BA4\u0BB2\u0BCD",
+  "\u0B8E\u0BA9\u0BCD\u0BA9",
+  "\u0B87\u0BB0\u0BC1\u0BA8\u0BCD\u0BA4\u0BC1",
+  "\u0B9A\u0BBF\u0BB2",
+  "\u0B8E\u0BA9\u0BCD",
+  "\u0BAA\u0BCB\u0BA9\u0BCD\u0BB1",
+  "\u0BB5\u0BC7\u0BA3\u0BCD\u0B9F\u0BC1\u0BAE\u0BCD",
+  "\u0BB5\u0BA8\u0BCD\u0BA4\u0BC1",
+  "\u0B87\u0BA4\u0BA9\u0BCD",
+  "\u0B85\u0BA4\u0BC1",
+  "\u0B85\u0BB5\u0BA9\u0BCD",
+  "\u0BA4\u0BBE\u0BA9\u0BCD",
+  "\u0B8E\u0BA9\u0BCD\u0BA9\u0BC1\u0BAE\u0BCD",
+  "\u0BAE\u0BC7\u0BB2\u0BC1\u0BAE\u0BCD",
+  "\u0BAA\u0BBF\u0BA9\u0BCD\u0BA9\u0BB0\u0BCD",
+  "\u0B95\u0BCA\u0BA3\u0BCD\u0B9F",
+  "\u0B87\u0BB0\u0BC1\u0B95\u0BCD\u0B95\u0BC1\u0BAE\u0BCD",
+  "\u0BA4\u0BA9\u0BA4\u0BC1",
+  "\u0B89\u0BB3\u0BCD\u0BB3\u0BA4\u0BC1",
+  "\u0BAA\u0BCB\u0BA4\u0BC1",
+  "\u0B8E\u0BA9\u0BCD\u0BB1\u0BC1\u0BAE\u0BCD",
+  "\u0B85\u0BA4\u0BA9\u0BCD",
+  "\u0BA4\u0BA9\u0BCD",
+  "\u0BAA\u0BBF\u0BB1\u0B95\u0BC1",
+  "\u0B85\u0BB5\u0BB0\u0BCD\u0B95\u0BB3\u0BCD",
+  "\u0BB5\u0BB0\u0BC8",
+  "\u0B85\u0BB5\u0BB3\u0BCD",
+  "\u0BA8\u0BC0",
+  "\u0B86\u0B95\u0BBF\u0BAF",
+  "\u0B89\u0BB3\u0BCD\u0BB3\u0BA9",
+  "\u0BB5\u0BA8\u0BCD\u0BA4",
+  "\u0B87\u0BB0\u0BC1\u0BA8\u0BCD\u0BA4",
+  "\u0BAE\u0BBF\u0B95\u0BB5\u0BC1\u0BAE\u0BCD",
+  "\u0B87\u0B99\u0BCD\u0B95\u0BC1",
+  "\u0BAE\u0BC0\u0BA4\u0BC1",
+  "\u0B93\u0BB0\u0BCD",
+  "\u0B87\u0BB5\u0BC8",
+  "\u0BAA\u0BB1\u0BCD\u0BB1\u0BBF",
+  "\u0BB5\u0BB0\u0BC1\u0BAE\u0BCD",
+  "\u0BB5\u0BC7\u0BB1\u0BC1",
+  "\u0B87\u0BB0\u0BC1",
+  "\u0B87\u0BA4\u0BBF\u0BB2\u0BCD",
+  "\u0BAA\u0BCB\u0BB2\u0BCD",
+  "\u0B87\u0BAA\u0BCD\u0BAA\u0BCB\u0BA4\u0BC1",
+  "\u0B85\u0BB5\u0BB0\u0BA4\u0BC1",
+  "\u0BAE\u0B9F\u0BCD\u0B9F\u0BC1\u0BAE\u0BCD",
+  "\u0B8E\u0BA9\u0BC1\u0BAE\u0BCD",
+  "\u0BAE\u0BC7\u0BB2\u0BCD",
+  "\u0BAA\u0BBF\u0BA9\u0BCD",
+  "\u0B86\u0B95\u0BBF\u0BAF\u0BCB\u0BB0\u0BCD",
+  "\u0B87\u0BA9\u0BCD\u0BA9\u0BC1\u0BAE\u0BCD",
+  "\u0B85\u0BA9\u0BCD\u0BB1\u0BC1",
+  "\u0B92\u0BB0\u0BC7",
+  "\u0BAE\u0BBF\u0B95",
+  "\u0B85\u0B99\u0BCD\u0B95\u0BC1",
+  "\u0BAA\u0BB2\u0BCD\u0BB5\u0BC7\u0BB1\u0BC1",
+  "\u0B85\u0BA4\u0BC8",
+  "\u0BAA\u0BB1\u0BCD\u0BB1\u0BBF\u0BAF",
+  "\u0B89\u0BA9\u0BCD",
+  "\u0B85\u0BA4\u0BBF\u0B95",
+  "\u0BAA\u0BC7\u0BB0\u0BCD",
+  "\u0B87\u0BA4\u0BA9\u0BBE\u0BB2\u0BCD",
+  "\u0B85\u0BB5\u0BC8",
+  "\u0B85\u0BA4\u0BC7",
+  "\u0B8F\u0BA9\u0BCD",
+  "\u0BAE\u0BC1\u0BB1\u0BC8",
+  "\u0BAF\u0BBE\u0BB0\u0BCD",
+  "\u0B8E\u0BA9\u0BCD\u0BAA\u0BA4\u0BC8",
+  "\u0B8E\u0BB2\u0BCD\u0BB2\u0BBE\u0BAE\u0BCD",
+  "\u0BAE\u0B9F\u0BCD\u0B9F\u0BC1\u0BAE\u0BC7",
+  "\u0B87\u0B99\u0BCD\u0B95\u0BC7",
+  "\u0B85\u0B99\u0BCD\u0B95\u0BC7",
+  "\u0B87\u0B9F\u0BAE\u0BCD",
+  "\u0B85\u0BA4\u0BBF\u0BB2\u0BCD",
+  "\u0BA8\u0BBE\u0BAE\u0BCD",
+  "\u0B85\u0BA4\u0BB1\u0BCD\u0B95\u0BC1",
+  "\u0B8E\u0BA9\u0BB5\u0BC7",
+  "\u0BAA\u0BBF\u0BB1",
+  "\u0B9A\u0BBF\u0BB1\u0BC1",
+  "\u0BAE\u0BB1\u0BCD\u0BB1",
+  "\u0BB5\u0BBF\u0B9F",
+  "\u0B8E\u0BA8\u0BCD\u0BA4",
+  "\u0B85\u0B9F\u0BC1\u0BA4\u0BCD\u0BA4",
+  "\u0B87\u0BA4\u0BA9\u0BC8",
+  "\u0B87\u0BA4\u0BC8",
+  "\u0B95\u0BCA\u0BB3\u0BCD\u0BB3",
+  "\u0B87\u0BA4\u0BB1\u0BCD\u0B95\u0BC1",
+  "\u0B85\u0BA4\u0BA9\u0BBE\u0BB2\u0BCD",
+  "\u0BA4\u0BB5\u0BBF\u0BB0",
+  "\u0BAA\u0BCB\u0BB2",
+  "\u0B9A\u0BB1\u0BCD\u0BB1\u0BC1"
+]);
+var tamil = {
+  name: "tamil",
+  stemmer: stem,
+  stopWords,
+  tokenizer: { splitPattern: /[^\u0B80-\u0BFFa-z0-9]+/gi }
+};
+
+export { tamil };

package/dist/languages/turkish.d.ts

@@ -0,0 +1,5 @@
+import { L as LanguageModule } from '../language-ClUGLuoC.js';
+
+declare const turkish: LanguageModule;
+
+export { turkish };