@delali/narsil 0.1.0

package/dist/languages/chinese.mjs

@@ -0,0 +1,250 @@
+// src/languages/chinese.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "\u7684",
+  "\u4E86",
+  "\u5728",
+  "\u662F",
+  "\u6211",
+  "\u6709",
+  "\u548C",
+  "\u5C31",
+  "\u4E0D",
+  "\u4EBA",
+  "\u90FD",
+  "\u4E00",
+  "\u4E00\u4E2A",
+  "\u4E0A",
+  "\u4E5F",
+  "\u5F88",
+  "\u5230",
+  "\u8BF4",
+  "\u8981",
+  "\u53BB",
+  "\u4F60",
+  "\u4F1A",
+  "\u7740",
+  "\u6CA1\u6709",
+  "\u770B",
+  "\u597D",
+  "\u81EA\u5DF1",
+  "\u8FD9",
+  "\u4ED6",
+  "\u5979",
+  "\u5B83",
+  "\u4EEC",
+  "\u6211\u4EEC",
+  "\u4F60\u4EEC",
+  "\u4ED6\u4EEC",
+  "\u5979\u4EEC",
+  "\u5B83\u4EEC",
+  "\u90A3",
+  "\u90A3\u4E2A",
+  "\u90A3\u4E9B",
+  "\u90A3\u4E48",
+  "\u90A3\u6837",
+  "\u90A3\u91CC",
+  "\u8FD9\u4E2A",
+  "\u8FD9\u4E9B",
+  "\u8FD9\u4E48",
+  "\u8FD9\u6837",
+  "\u8FD9\u91CC",
+  "\u54EA",
+  "\u54EA\u4E2A",
+  "\u54EA\u4E9B",
+  "\u54EA\u91CC",
+  "\u54EA\u513F",
+  "\u4EC0\u4E48",
+  "\u600E\u4E48",
+  "\u600E\u6837",
+  "\u8C01",
+  "\u591A\u5C11",
+  "\u51E0",
+  "\u4E3A\u4EC0\u4E48",
+  "\u56E0\u4E3A",
+  "\u6240\u4EE5",
+  "\u5982\u679C",
+  "\u867D\u7136",
+  "\u4F46\u662F",
+  "\u53EF\u662F",
+  "\u800C\u4E14",
+  "\u6216\u8005",
+  "\u8FD8\u662F",
+  "\u4E0D\u4F46",
+  "\u4E0D\u4EC5",
+  "\u4E0D\u8FC7",
+  "\u4E0D\u7BA1",
+  "\u4E0D\u8BBA",
+  "\u65E0\u8BBA",
+  "\u4E0E",
+  "\u53CA",
+  "\u4EE5\u53CA",
+  "\u800C",
+  "\u5E76",
+  "\u5E76\u4E14",
+  "\u6216",
+  "\u4F46",
+  "\u5374",
+  "\u7136\u800C",
+  "\u4E8E\u662F",
+  "\u56E0\u6B64",
+  "\u6240",
+  "\u88AB",
+  "\u628A",
+  "\u7ED9",
+  "\u8BA9",
+  "\u5411",
+  "\u5BF9",
+  "\u5BF9\u4E8E",
+  "\u5173\u4E8E",
+  "\u4ECE",
+  "\u7531",
+  "\u7531\u4E8E",
+  "\u4EE5",
+  "\u4EE5\u4E3A",
+  "\u4EE5\u4FBF",
+  "\u4EE5\u514D",
+  "\u4EE5\u6765",
+  "\u4EE5\u4E0A",
+  "\u4EE5\u4E0B",
+  "\u4E4B",
+  "\u4E4B\u4E00",
+  "\u4E4B\u540E",
+  "\u4E4B\u524D",
+  "\u4E4B\u95F4",
+  "\u4E4B\u4E2D",
+  "\u4E4B\u7C7B",
+  "\u4E3A",
+  "\u4E3A\u4E86",
+  "\u4E3A\u4F55",
+  "\u4E3A\u6B62",
+  "\u4E3A\u6B64",
+  "\u4E3A\u7740",
+  "\u5417",
+  "\u5427",
+  "\u5462",
+  "\u554A",
+  "\u5440",
+  "\u54E6",
+  "\u55EF",
+  "\u54C8",
+  "\u5566",
+  "\u561B",
+  "\u5457",
+  "\u7F62\u4E86",
+  "\u800C\u5DF2",
+  "\u8FC7",
+  "\u5730",
+  "\u5F97",
+  "\u4E2A",
+  "\u4E9B",
+  "\u91CC",
+  "\u4E2D",
+  "\u4E0B",
+  "\u524D",
+  "\u540E",
+  "\u5185",
+  "\u5916",
+  "\u95F4",
+  "\u6765",
+  "\u51FA",
+  "\u56DE",
+  "\u8D77",
+  "\u5F53",
+  "\u624D",
+  "\u53C8",
+  "\u8FD8",
+  "\u518D",
+  "\u66F4",
+  "\u6700",
+  "\u5DF2",
+  "\u5DF2\u7ECF",
+  "\u66FE",
+  "\u66FE\u7ECF",
+  "\u6B63\u5728",
+  "\u5C06",
+  "\u5C06\u8981",
+  "\u80FD",
+  "\u80FD\u591F",
+  "\u53EF\u4EE5",
+  "\u53EF\u80FD",
+  "\u5E94\u8BE5",
+  "\u5FC5\u987B",
+  "\u9700\u8981",
+  "\u60F3",
+  "\u613F\u610F",
+  "\u6562",
+  "\u8BE5",
+  "\u6CA1",
+  "\u522B",
+  "\u4E0D\u8981",
+  "\u975E",
+  "\u83AB",
+  "\u592A",
+  "\u6781",
+  "\u771F",
+  "\u633A",
+  "\u591A",
+  "\u5C11",
+  "\u5927",
+  "\u5C0F",
+  "\u574F",
+  "\u505A",
+  "\u7528",
+  "\u7B49",
+  "\u7B49\u7B49",
+  "\u5982",
+  "\u5982\u4F55",
+  "\u5982\u540C",
+  "\u5982\u6B64",
+  "\u82E5",
+  "\u82E5\u662F",
+  "\u53EA",
+  "\u53EA\u662F",
+  "\u53EA\u6709",
+  "\u53EA\u8981",
+  "\u9664",
+  "\u9664\u4E86",
+  "\u9664\u975E",
+  "\u5C3D\u7BA1",
+  "\u5373\u4F7F",
+  "\u5373\u4FBF",
+  "\u5047\u5982",
+  "\u5047\u82E5",
+  "\u5047\u4F7F",
+  "\u65E2\u7136",
+  "\u65E2",
+  "\u6309",
+  "\u6309\u7167",
+  "\u6839\u636E",
+  "\u636E",
+  "\u901A\u8FC7",
+  "\u7ECF\u8FC7",
+  "\u968F",
+  "\u968F\u7740",
+  "\u6CBF",
+  "\u6CBF\u7740",
+  "\u671D",
+  "\u671D\u7740",
+  "\u81F3",
+  "\u81F3\u4E8E",
+  "\u76F4\u5230",
+  "\u8D81",
+  "\u6BD4",
+  "\u540C",
+  "\u8DDF",
+  "\u66FF",
+  "\u8FDE",
+  "\u8FDE\u540C"
+]);
+var chinese = {
+  name: "chinese",
+  stemmer: null,
+  stopWords,
+  tokenizer: {
+    splitPattern: /[^\u4e00-\u9fff\u3400-\u4dbf\uf900-\ufaff0-9a-zA-Z]+/gi,
+    normalizeDiacritics: false,
+    minTokenLength: 1
+  }
+};
+
+export { chinese };

package/dist/languages/dagbani.d.ts

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

package/dist/languages/dagbani.mjs

@@ -0,0 +1,85 @@
+// src/languages/dagbani.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "n",
+  "a",
+  "o",
+  "di",
+  "ti",
+  "yi",
+  "b\u025B",
+  "\u014Ba",
+  "ma",
+  "li",
+  "ba",
+  "ya",
+  "mani",
+  "nyini",
+  "\u014Buni",
+  "\u014Buna",
+  "dini",
+  "dina",
+  "tinima",
+  "yinima",
+  "b\u025Bna",
+  "bana",
+  "\u014Bana",
+  "\u014B\u028An",
+  "ni",
+  "la",
+  "ka",
+  "d\u0259",
+  "sa",
+  "daa",
+  "na",
+  "siri",
+  "yaa",
+  "dii",
+  "b\u0259",
+  "n\u0259",
+  "ku",
+  "de",
+  "lah",
+  "bi",
+  "pa",
+  "bee",
+  "amaa",
+  "taba",
+  "ma\u014Ba",
+  "bo",
+  "maa",
+  "din",
+  "sheli",
+  "pam",
+  "nye",
+  "nyela",
+  "nima",
+  "bahi",
+  "yeli",
+  "sani",
+  "nyin",
+  "so",
+  "shin",
+  "gba",
+  "nti",
+  "\u014Bun",
+  "tooi",
+  "pahi",
+  "lana",
+  "mini",
+  "puni",
+  "zaa",
+  "kam",
+  "ban"
+]);
+var dagbani = {
+  name: "dagbani",
+  stemmer: null,
+  stopWords,
+  tokenizer: {
+    splitPattern: /[^a-zA-ZɛɔƐƆŋŊɣƔʒƷʊƱəƏ0-9]+/gi,
+    normalizeDiacritics: false,
+    minTokenLength: 1
+  }
+};
+
+export { dagbani };

package/dist/languages/danish.d.ts

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

package/dist/languages/danish.mjs

@@ -0,0 +1,224 @@
+// src/languages/danish.ts
+var VOWELS = "aeiouy\xE5\xE6\xF8";
+var S_ENDINGS = "abcdfghjklmnoprtvyz\xE5";
+var STEP1_SUFFIXES = [
+  "erendes",
+  "hedens",
+  "erende",
+  "erens",
+  "endes",
+  "ernes",
+  "enes",
+  "eres",
+  "erets",
+  "heder",
+  "ethed",
+  "erede",
+  "heden",
+  "ered",
+  "erer",
+  "ende",
+  "erne",
+  "ene",
+  "ere",
+  "eren",
+  "heds",
+  "eret",
+  "ens",
+  "ers",
+  "ets",
+  "hed",
+  "en",
+  "er",
+  "es",
+  "et",
+  "e"
+];
+var UNDOUBLE_PAIRS = ["gd", "dt", "gt", "kt"];
+var STEP3_SUFFIXES = [
+  { text: "elig", replacement: null },
+  { text: "l\xF8st", replacement: "l\xF8s" },
+  { text: "lig", replacement: null },
+  { text: "els", replacement: null },
+  { text: "ig", replacement: null }
+];
+function isVowel(ch) {
+  return VOWELS.includes(ch);
+}
+function isConsonant(ch) {
+  return ch.length === 1 && !isVowel(ch);
+}
+function computeR1(word) {
+  let foundVowel = false;
+  for (let i = 0; i < word.length; i++) {
+    if (foundVowel && !isVowel(word[i])) {
+      return Math.max(i + 1, 3);
+    }
+    if (isVowel(word[i])) {
+      foundVowel = true;
+    }
+  }
+  return word.length;
+}
+function step1(word, r1) {
+  for (const suffix of STEP1_SUFFIXES) {
+    if (word.endsWith(suffix) && word.length - suffix.length >= r1) {
+      return word.slice(0, -suffix.length);
+    }
+  }
+  if (word.endsWith("s") && word.length - 1 >= r1) {
+    const preceding = word[word.length - 2];
+    if (preceding && S_ENDINGS.includes(preceding)) {
+      return word.slice(0, -1);
+    }
+  }
+  return word;
+}
+function undouble(word, r1) {
+  if (word.length < r1) return word;
+  for (const pair of UNDOUBLE_PAIRS) {
+    if (word.endsWith(pair)) {
+      return word.slice(0, -1);
+    }
+  }
+  return word;
+}
+function step3(word, r1) {
+  if (word.endsWith("igst")) {
+    word = word.slice(0, -2);
+  }
+  for (const { text, replacement } of STEP3_SUFFIXES) {
+    if (word.endsWith(text) && word.length - text.length >= r1) {
+      if (replacement !== null) {
+        return word.slice(0, -text.length) + replacement;
+      }
+      word = word.slice(0, -text.length);
+      word = undouble(word, r1);
+      return word;
+    }
+  }
+  return word;
+}
+function step4(word, r1) {
+  if (word.length < 2 || word.length <= r1) return word;
+  const last = word[word.length - 1];
+  const secondLast = word[word.length - 2];
+  if (isConsonant(last) && last === secondLast) {
+    return word.slice(0, -1);
+  }
+  return word;
+}
+function stem(word) {
+  if (word.length < 3) return word;
+  word = word.toLowerCase();
+  const r1 = computeR1(word);
+  word = step1(word, r1);
+  word = undouble(word, r1);
+  word = step3(word, r1);
+  word = step4(word, r1);
+  return word;
+}
+var stopWords = /* @__PURE__ */ new Set([
+  "og",
+  "i",
+  "jeg",
+  "det",
+  "at",
+  "en",
+  "den",
+  "til",
+  "er",
+  "som",
+  "p\xE5",
+  "de",
+  "med",
+  "han",
+  "af",
+  "for",
+  "ikke",
+  "der",
+  "var",
+  "mig",
+  "sig",
+  "men",
+  "et",
+  "har",
+  "om",
+  "vi",
+  "min",
+  "havde",
+  "ham",
+  "hun",
+  "nu",
+  "over",
+  "da",
+  "fra",
+  "du",
+  "ud",
+  "sin",
+  "dem",
+  "os",
+  "op",
+  "man",
+  "hans",
+  "hvor",
+  "eller",
+  "hvad",
+  "skal",
+  "selv",
+  "her",
+  "alle",
+  "vil",
+  "blev",
+  "kunne",
+  "ind",
+  "n\xE5r",
+  "v\xE6re",
+  "dog",
+  "noget",
+  "ville",
+  "jo",
+  "deres",
+  "efter",
+  "ned",
+  "skulle",
+  "denne",
+  "end",
+  "dette",
+  "mit",
+  "ogs\xE5",
+  "under",
+  "have",
+  "dig",
+  "anden",
+  "hende",
+  "mine",
+  "alt",
+  "meget",
+  "sit",
+  "sine",
+  "vor",
+  "mod",
+  "disse",
+  "hvis",
+  "din",
+  "nogle",
+  "hos",
+  "blive",
+  "mange",
+  "ad",
+  "bliver",
+  "hendes",
+  "v\xE6ret",
+  "thi",
+  "jer",
+  "s\xE5dan"
+]);
+var danish = {
+  name: "danish",
+  stemmer: stem,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9æøå]+/gi }
+};
+
+export { danish };

package/dist/languages/dutch.d.ts

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