@delali/narsil 0.1.0

package/dist/languages/french.mjs

@@ -0,0 +1,635 @@
+// src/languages/french.ts
+var VOWELS = "aeiouy\xE2\xE0\xEB\xE9\xE8\xEF\xEE\xF4\xF9\xFB\xFC";
+function isVowel(ch) {
+  return VOWELS.includes(ch);
+}
+function findRegions(word) {
+  let rv = word.length;
+  let r1 = word.length;
+  let r2 = word.length;
+  if (word.length >= 2 && isVowel(word[0]) && isVowel(word[1])) {
+    rv = 3;
+  } else if (word.startsWith("par") || word.startsWith("col") || word.startsWith("tap")) {
+    rv = 3;
+  } else {
+    for (let i = 1; i < word.length; i++) {
+      if (isVowel(word[i])) {
+        rv = i + 1;
+        break;
+      }
+    }
+  }
+  for (let i = 0; i < word.length - 1; i++) {
+    if (isVowel(word[i]) && !isVowel(word[i + 1])) {
+      r1 = i + 2;
+      break;
+    }
+  }
+  for (let i = r1; i < word.length - 1; i++) {
+    if (isVowel(word[i]) && !isVowel(word[i + 1])) {
+      r2 = i + 2;
+      break;
+    }
+  }
+  return { rv, r1, r2 };
+}
+function markVowelConsonantForms(word) {
+  const chars = word.split("");
+  for (let i = 0; i < chars.length; i++) {
+    if (chars[i] === "u" && i > 0 && i < chars.length - 1 && isVowel(chars[i - 1]) && isVowel(chars[i + 1])) {
+      chars[i] = "U";
+    }
+    if (chars[i] === "i" && i > 0 && i < chars.length - 1 && isVowel(chars[i - 1]) && isVowel(chars[i + 1])) {
+      chars[i] = "I";
+    }
+    if (chars[i] === "y" && i > 0 && isVowel(chars[i - 1])) {
+      chars[i] = "Y";
+    }
+    if (chars[i] === "y" && i < chars.length - 1 && isVowel(chars[i + 1])) {
+      chars[i] = "Y";
+    }
+    if (chars[i] === "u" && i > 0 && chars[i - 1] === "q") {
+      chars[i] = "U";
+    }
+  }
+  return chars.join("");
+}
+function restoreMarkedLetters(word) {
+  return word.replace(/I/g, "i").replace(/U/g, "u").replace(/Y/g, "y");
+}
+function endsWith(word, suffix) {
+  return word.endsWith(suffix);
+}
+function removeSuffix(word, suffix) {
+  return word.slice(0, word.length - suffix.length);
+}
+function suffixInRegion(word, suffix, regionStart) {
+  return word.length - suffix.length >= regionStart;
+}
+function findLongestAmong(word, suffixes, regionStart) {
+  let longestMatch = null;
+  for (const suffix of suffixes) {
+    if (endsWith(word, suffix) && suffixInRegion(word, suffix, regionStart)) {
+      if (longestMatch === null || suffix.length > longestMatch.length) {
+        longestMatch = suffix;
+      }
+    }
+  }
+  return longestMatch;
+}
+function step1StandardSuffix(word, rv, r1, r2) {
+  const standardSuffixes = [
+    "issements",
+    "issement",
+    "atrices",
+    "atrice",
+    "ateurs",
+    "ateur",
+    "ations",
+    "ation",
+    "usions",
+    "ution",
+    "usion",
+    "utions",
+    "logies",
+    "logie",
+    "ements",
+    "ement",
+    "ences",
+    "ence",
+    "ances",
+    "ance",
+    "ables",
+    "able",
+    "ismes",
+    "isme",
+    "istes",
+    "iste",
+    "euses",
+    "euse",
+    "ments",
+    "ment",
+    "iqUes",
+    "iqUe",
+    "it\xE9s",
+    "it\xE9",
+    "ives",
+    "ive",
+    "eaux",
+    "ifs",
+    "if",
+    "aux",
+    "eux"
+  ];
+  const suffix = findLongestAmong(word, standardSuffixes, 0);
+  if (!suffix) return { word, changed: false };
+  if (["ance", "ances", "iqUe", "iqUes", "isme", "ismes", "able", "ables", "iste", "istes"].includes(suffix)) {
+    if (suffixInRegion(word, suffix, r2)) {
+      return { word: removeSuffix(word, suffix), changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (["atrice", "atrices", "ateur", "ateurs", "ation", "ations"].includes(suffix)) {
+    if (suffixInRegion(word, suffix, r2)) {
+      word = removeSuffix(word, suffix);
+      if (endsWith(word, "ic")) {
+        if (suffixInRegion(word, "ic", r2)) {
+          word = removeSuffix(word, "ic");
+        } else {
+          word = `${removeSuffix(word, "ic")}iqU`;
+        }
+      }
+      return { word, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (["logie", "logies"].includes(suffix)) {
+    if (suffixInRegion(word, suffix, r2)) {
+      return { word: `${removeSuffix(word, suffix)}log`, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (["usion", "usions", "ution", "utions"].includes(suffix)) {
+    if (suffixInRegion(word, suffix, r2)) {
+      return { word: `${removeSuffix(word, suffix)}u`, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (["ence", "ences"].includes(suffix)) {
+    if (suffixInRegion(word, suffix, r2)) {
+      return { word: `${removeSuffix(word, suffix)}ent`, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (suffix === "ement" || suffix === "ements") {
+    if (suffixInRegion(word, suffix, rv)) {
+      word = removeSuffix(word, suffix);
+      if (endsWith(word, "iv") && suffixInRegion(word, "iv", r2)) {
+        word = removeSuffix(word, "iv");
+        if (endsWith(word, "at") && suffixInRegion(word, "at", r2)) {
+          word = removeSuffix(word, "at");
+        }
+      } else if (endsWith(word, "eus")) {
+        if (suffixInRegion(word, "eus", r2)) {
+          word = removeSuffix(word, "eus");
+        } else if (suffixInRegion(word, "eus", r1)) {
+          word = `${removeSuffix(word, "eus")}eux`;
+        }
+      } else if (endsWith(word, "abl") && suffixInRegion(word, "abl", r2)) {
+        word = removeSuffix(word, "abl");
+      } else if (endsWith(word, "iqU") && suffixInRegion(word, "iqU", r2)) {
+        word = removeSuffix(word, "iqU");
+      } else if ((endsWith(word, "i\xE8r") || endsWith(word, "I\xE8r")) && suffixInRegion(word, "i\xE8r", rv)) {
+        const sSuffix = endsWith(word, "I\xE8r") ? "I\xE8r" : "i\xE8r";
+        word = `${removeSuffix(word, sSuffix)}i`;
+      }
+      return { word, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (["it\xE9", "it\xE9s"].includes(suffix)) {
+    if (suffixInRegion(word, suffix, r2)) {
+      word = removeSuffix(word, suffix);
+      if (endsWith(word, "abil") && suffixInRegion(word, "abil", r2)) {
+        word = removeSuffix(word, "abil");
+      } else if (endsWith(word, "abil")) {
+        word = `${removeSuffix(word, "abil")}abl`;
+      } else if (endsWith(word, "ic")) {
+        if (suffixInRegion(word, "ic", r2)) {
+          word = removeSuffix(word, "ic");
+        } else {
+          word = `${removeSuffix(word, "ic")}iqU`;
+        }
+      } else if (endsWith(word, "iv") && suffixInRegion(word, "iv", r2)) {
+        word = removeSuffix(word, "iv");
+      }
+      return { word, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (["if", "ifs", "ive", "ives"].includes(suffix)) {
+    if (suffixInRegion(word, suffix, r2)) {
+      word = removeSuffix(word, suffix);
+      if (endsWith(word, "at") && suffixInRegion(word, "at", r2)) {
+        word = removeSuffix(word, "at");
+        if (endsWith(word, "ic")) {
+          if (suffixInRegion(word, "ic", r2)) {
+            word = removeSuffix(word, "ic");
+          } else {
+            word = `${removeSuffix(word, "ic")}iqU`;
+          }
+        }
+      }
+      return { word, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (suffix === "eaux") {
+    return { word: `${removeSuffix(word, "eaux")}eau`, changed: true };
+  }
+  if (suffix === "aux") {
+    if (suffixInRegion(word, suffix, r1)) {
+      return { word: `${removeSuffix(word, "aux")}al`, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (["euse", "euses"].includes(suffix)) {
+    if (suffixInRegion(word, suffix, r2)) {
+      return { word: removeSuffix(word, suffix), changed: true };
+    }
+    if (suffixInRegion(word, suffix, r1)) {
+      return { word: `${removeSuffix(word, suffix)}eux`, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (suffix === "issement" || suffix === "issements") {
+    if (suffixInRegion(word, suffix, r1)) {
+      const stemmed = removeSuffix(word, suffix);
+      if (stemmed.length > 0 && !isVowel(stemmed[stemmed.length - 1])) {
+        return { word: stemmed, changed: true };
+      }
+    }
+    return { word, changed: false };
+  }
+  if (suffix === "amment") {
+    if (suffixInRegion(word, suffix, rv)) {
+      return { word: `${removeSuffix(word, "amment")}ant`, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (suffix === "emment") {
+    if (suffixInRegion(word, suffix, rv)) {
+      return { word: `${removeSuffix(word, "emment")}ent`, changed: true };
+    }
+    return { word, changed: false };
+  }
+  if (suffix === "ment" || suffix === "ments") {
+    if (suffixInRegion(word, suffix, rv)) {
+      const stemmed = removeSuffix(word, suffix);
+      if (stemmed.length > 0 && isVowel(stemmed[stemmed.length - 1])) {
+        return { word: stemmed, changed: true };
+      }
+    }
+    return { word, changed: false };
+  }
+  if (suffix === "eux") {
+    if (suffixInRegion(word, suffix, r2)) {
+      return { word: removeSuffix(word, suffix), changed: true };
+    }
+    return { word, changed: false };
+  }
+  return { word, changed: false };
+}
+function step2aIVerbSuffix(word, rv) {
+  const suffixes = [
+    "issantes",
+    "issante",
+    "issants",
+    "issant",
+    "issions",
+    "issons",
+    "issais",
+    "issait",
+    "issiez",
+    "issez",
+    "isses",
+    "isse",
+    "iraIent",
+    "issaIent",
+    "irions",
+    "iront",
+    "irais",
+    "irait",
+    "iriez",
+    "irons",
+    "irent",
+    "irez",
+    "irai",
+    "iras",
+    "\xEEmes",
+    "\xEEtes",
+    "ies",
+    "ira",
+    "ir",
+    "is",
+    "it",
+    "ie",
+    "i",
+    "\xEEt"
+  ];
+  const suffix = findLongestAmong(word, suffixes, rv);
+  if (!suffix) return { word, changed: false };
+  const stemmed = removeSuffix(word, suffix);
+  if (stemmed.length > 0 && !isVowel(stemmed[stemmed.length - 1]) && stemmed[stemmed.length - 1] !== "H") {
+    return { word: stemmed, changed: true };
+  }
+  return { word, changed: false };
+}
+function step2bOtherVerbSuffix(word, rv, r2) {
+  const group1Suffixes = [
+    "eraIent",
+    "erions",
+    "assions",
+    "assent",
+    "assiez",
+    "erais",
+    "erait",
+    "eriez",
+    "erons",
+    "eront",
+    "erez",
+    "antes",
+    "asses",
+    "eras",
+    "ante",
+    "asse",
+    "\xE2mes",
+    "\xE2tes",
+    "\xE9es",
+    "era",
+    "erai",
+    "ais",
+    "ait",
+    "ant",
+    "\xE9e",
+    "\xE9s",
+    "er",
+    "ez",
+    "ai",
+    "as",
+    "a",
+    "\xE9",
+    "\xE2t",
+    "\xE8rent"
+  ];
+  const ionsSuffix = "ions";
+  if (endsWith(word, ionsSuffix) && suffixInRegion(word, ionsSuffix, r2)) {
+    return { word: removeSuffix(word, ionsSuffix), changed: true };
+  }
+  const suffix = findLongestAmong(word, group1Suffixes, rv);
+  if (suffix) {
+    return { word: removeSuffix(word, suffix), changed: true };
+  }
+  return { word, changed: false };
+}
+function step3ResidualSuffix(word, rv, r2) {
+  if (endsWith(word, "s")) {
+    const beforeS = word.slice(0, -1);
+    if (beforeS.length > 0) {
+      const lastChar = beforeS[beforeS.length - 1];
+      if (lastChar !== "a" && lastChar !== "i" && lastChar !== "o" && lastChar !== "u" && lastChar !== "\xE8" && lastChar !== "s") {
+        word = beforeS;
+      }
+    }
+  }
+  const ionSuffix = "ion";
+  if (endsWith(word, ionSuffix) && suffixInRegion(word, ionSuffix, r2)) {
+    const stemmed = removeSuffix(word, ionSuffix);
+    if (stemmed.length > 0 && (stemmed[stemmed.length - 1] === "s" || stemmed[stemmed.length - 1] === "t") && suffixInRegion(word, ionSuffix, rv)) {
+      return stemmed;
+    }
+  }
+  const residualSuffixes = ["I\xE8re", "i\xE8re", "Ier", "ier"];
+  for (const suffix of residualSuffixes) {
+    if (endsWith(word, suffix) && suffixInRegion(word, suffix, rv)) {
+      return `${removeSuffix(word, suffix)}i`;
+    }
+  }
+  if (endsWith(word, "e") && suffixInRegion(word, "e", rv)) {
+    return removeSuffix(word, "e");
+  }
+  return word;
+}
+function step4Undouble(word) {
+  const doublePatterns = ["enn", "onn", "ett", "ell", "eill"];
+  for (const pattern of doublePatterns) {
+    if (endsWith(word, pattern)) {
+      return word.slice(0, -1);
+    }
+  }
+  return word;
+}
+function step5UnAccent(word) {
+  if (word.length < 2) return word;
+  const lastChar = word[word.length - 1];
+  const secondLastChar = word[word.length - 2];
+  if ((lastChar === "\xE9" || lastChar === "\xE8") && !isVowel(secondLastChar)) {
+    return `${word.slice(0, -1)}e`;
+  }
+  if (!isVowel(lastChar) && (secondLastChar === "\xE9" || secondLastChar === "\xE8")) {
+    return `${word.slice(0, -2)}e${lastChar}`;
+  }
+  return word;
+}
+function stem(word) {
+  if (word.length < 3) return word;
+  if (word[0] === "y") {
+    word = `Y${word.slice(1)}`;
+  }
+  word = markVowelConsonantForms(word);
+  const { rv, r1, r2 } = findRegions(word);
+  const step1Result = step1StandardSuffix(word, rv, r1, r2);
+  let stemChanged = step1Result.changed;
+  word = step1Result.word;
+  if (!stemChanged) {
+    const step2aResult = step2aIVerbSuffix(word, rv);
+    if (step2aResult.changed) {
+      word = step2aResult.word;
+      stemChanged = true;
+    } else {
+      const step2bResult = step2bOtherVerbSuffix(word, rv, r2);
+      word = step2bResult.word;
+      stemChanged = step2bResult.changed;
+    }
+  }
+  if (stemChanged) {
+    if (endsWith(word, "Y")) {
+      word = `${word.slice(0, -1)}i`;
+    }
+    if (endsWith(word, "\xE7")) {
+      word = `${word.slice(0, -1)}c`;
+    }
+  } else {
+    word = step3ResidualSuffix(word, rv, r2);
+  }
+  word = step4Undouble(word);
+  word = step5UnAccent(word);
+  word = restoreMarkedLetters(word);
+  return word.toLowerCase();
+}
+var stopWords = /* @__PURE__ */ new Set([
+  "au",
+  "aux",
+  "avec",
+  "ce",
+  "ces",
+  "dans",
+  "de",
+  "des",
+  "du",
+  "elle",
+  "en",
+  "et",
+  "eux",
+  "il",
+  "je",
+  "la",
+  "le",
+  "leur",
+  "lui",
+  "ma",
+  "mais",
+  "me",
+  "m\xEAme",
+  "mes",
+  "moi",
+  "mon",
+  "ne",
+  "nos",
+  "notre",
+  "nous",
+  "on",
+  "ou",
+  "par",
+  "pas",
+  "pour",
+  "qu",
+  "que",
+  "qui",
+  "sa",
+  "se",
+  "ses",
+  "son",
+  "sur",
+  "ta",
+  "te",
+  "tes",
+  "toi",
+  "ton",
+  "tu",
+  "un",
+  "une",
+  "vos",
+  "votre",
+  "vous",
+  "c",
+  "d",
+  "j",
+  "l",
+  "\xE0",
+  "m",
+  "n",
+  "s",
+  "t",
+  "y",
+  "\xE9t\xE9",
+  "\xE9t\xE9e",
+  "\xE9t\xE9es",
+  "\xE9t\xE9s",
+  "\xE9tant",
+  "suis",
+  "es",
+  "est",
+  "sommes",
+  "\xEAtes",
+  "sont",
+  "serai",
+  "seras",
+  "sera",
+  "serons",
+  "serez",
+  "seront",
+  "serais",
+  "serait",
+  "serions",
+  "seriez",
+  "seraient",
+  "\xE9tais",
+  "\xE9tait",
+  "\xE9tions",
+  "\xE9tiez",
+  "\xE9taient",
+  "fus",
+  "fut",
+  "f\xFBmes",
+  "f\xFBtes",
+  "furent",
+  "sois",
+  "soit",
+  "soyons",
+  "soyez",
+  "soient",
+  "fusse",
+  "fusses",
+  "f\xFBt",
+  "fussions",
+  "fussiez",
+  "fussent",
+  "ayant",
+  "eu",
+  "eue",
+  "eues",
+  "eus",
+  "ai",
+  "as",
+  "avons",
+  "avez",
+  "ont",
+  "aurai",
+  "auras",
+  "aura",
+  "aurons",
+  "aurez",
+  "auront",
+  "aurais",
+  "aurait",
+  "aurions",
+  "auriez",
+  "auraient",
+  "avais",
+  "avait",
+  "avions",
+  "aviez",
+  "avaient",
+  "eut",
+  "e\xFBmes",
+  "e\xFBtes",
+  "eurent",
+  "aie",
+  "aies",
+  "ait",
+  "ayons",
+  "ayez",
+  "aient",
+  "eusse",
+  "eusses",
+  "e\xFBt",
+  "eussions",
+  "eussiez",
+  "eussent",
+  "ceci",
+  "cela",
+  "cel\xE0",
+  "cet",
+  "cette",
+  "ici",
+  "ils",
+  "les",
+  "leurs",
+  "quel",
+  "quels",
+  "quelle",
+  "quelles",
+  "sans",
+  "soi"
+]);
+var french = {
+  name: "french",
+  stemmer: stem,
+  stopWords,
+  tokenizer: {
+    splitPattern: /[^a-z0-9äâàéèëêïîöôùüûœç-]+/gi
+  }
+};
+
+export { french };

package/dist/languages/ga.d.ts

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

package/dist/languages/ga.mjs

@@ -0,0 +1,69 @@
+// src/languages/ga.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "mi",
+  "bo",
+  "e",
+  "w\u0254",
+  "ni",
+  "am\u025B",
+  "l\u025B",
+  "m\u0254",
+  "n\u0254",
+  "he",
+  "le",
+  "k\u025B",
+  "shi",
+  "ba",
+  "y\u025B",
+  "ko",
+  "tso",
+  "ts\u0254",
+  "naa",
+  "n\u025B\u025B",
+  "fee",
+  "kane",
+  "shishi",
+  "moko",
+  "lo",
+  "la",
+  "mo",
+  "ji",
+  "ana",
+  "mli",
+  "nii",
+  "noko",
+  "ahi",
+  "kome",
+  "eno",
+  "eni",
+  "bee",
+  "tee",
+  "laa",
+  "nee",
+  "no",
+  "nu",
+  "ne",
+  "na",
+  "ta",
+  "fo",
+  "esa",
+  "bii",
+  "saa",
+  "f\u025B\u025B",
+  "ak\u025B",
+  "yaan\u0254",
+  "eee",
+  "ekome"
+]);
+var ga = {
+  name: "ga",
+  stemmer: null,
+  stopWords,
+  tokenizer: {
+    splitPattern: /[^a-zA-ZɛɔƐƆŋŊ0-9\p{M}]+/giu,
+    normalizeDiacritics: false,
+    minTokenLength: 1
+  }
+};
+
+export { ga };

package/dist/languages/german.d.ts

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