@delali/narsil 0.1.0

package/dist/languages/portuguese.mjs

@@ -0,0 +1,606 @@
+// src/languages/portuguese.ts
+var VOWELS = "aeiou\xE0\xE1\xE2\xE9\xEA\xED\xF3\xF4\xFA\xFC";
+function isVowel(ch) {
+  return VOWELS.includes(ch);
+}
+function findRegions(word) {
+  const length = word.length;
+  let rv = length;
+  if (length > 3) {
+    if (!isVowel(word[1])) {
+      for (let i = 2; i < length; i++) {
+        if (isVowel(word[i])) {
+          rv = i + 1;
+          break;
+        }
+      }
+    } else if (isVowel(word[0]) && isVowel(word[1])) {
+      for (let i = 2; i < length; i++) {
+        if (!isVowel(word[i])) {
+          rv = i + 1;
+          break;
+        }
+      }
+    } else {
+      rv = 3;
+    }
+  }
+  let r1 = length;
+  for (let i = 1; i < length; i++) {
+    if (!isVowel(word[i]) && isVowel(word[i - 1])) {
+      r1 = i + 1;
+      break;
+    }
+  }
+  let r2 = length;
+  for (let i = r1 + 1; i < length; i++) {
+    if (!isVowel(word[i]) && isVowel(word[i - 1])) {
+      r2 = i + 1;
+      break;
+    }
+  }
+  return { rv, r1, r2 };
+}
+function endsWith(word, suffix) {
+  return word.endsWith(suffix);
+}
+function suffixInRegion(word, suffix, regionStart) {
+  return word.length - suffix.length >= regionStart;
+}
+function removeSuffix(word, suffix) {
+  return word.slice(0, word.length - suffix.length);
+}
+function replaceSuffix(word, suffix, replacement) {
+  return word.slice(0, word.length - suffix.length) + replacement;
+}
+var STANDARD_SUFFIXES = [
+  { suffix: "amentos", group: 1 },
+  { suffix: "imentos", group: 1 },
+  { suffix: "adoras", group: 1 },
+  { suffix: "adores", group: 1 },
+  { suffix: "logias", group: 2 },
+  { suffix: "idades", group: 7 },
+  { suffix: "amento", group: 1 },
+  { suffix: "imento", group: 1 },
+  { suffix: "adora", group: 1 },
+  { suffix: "istas", group: 1 },
+  { suffix: "antes", group: 1 },
+  { suffix: "ismos", group: 1 },
+  { suffix: "\xE2ncia", group: 1 },
+  { suffix: "logia", group: 2 },
+  { suffix: "\xEAncia", group: 4 },
+  { suffix: "\xEAncias", group: 4 },
+  { suffix: "amente", group: 5 },
+  { suffix: "mente", group: 6 },
+  { suffix: "idade", group: 7 },
+  { suffix: "\xE1vel", group: 1 },
+  { suffix: "\xEDvel", group: 1 },
+  { suffix: "ador", group: 1 },
+  { suffix: "ante", group: 1 },
+  { suffix: "ista", group: 1 },
+  { suffix: "ismo", group: 1 },
+  { suffix: "icas", group: 1 },
+  { suffix: "icos", group: 1 },
+  { suffix: "osas", group: 1 },
+  { suffix: "osos", group: 1 },
+  { suffix: "iva", group: 8 },
+  { suffix: "ivo", group: 8 },
+  { suffix: "ivas", group: 8 },
+  { suffix: "ivos", group: 8 },
+  { suffix: "ica", group: 1 },
+  { suffix: "ico", group: 1 },
+  { suffix: "osa", group: 1 },
+  { suffix: "oso", group: 1 },
+  { suffix: "ezas", group: 1 },
+  { suffix: "eza", group: 1 },
+  { suffix: "ira", group: 9 },
+  { suffix: "iras", group: 9 },
+  { suffix: "a\xE7a~o", group: 1 },
+  { suffix: "u\xE7a~o", group: 3 },
+  { suffix: "a\xE7o~es", group: 1 },
+  { suffix: "u\xE7o~es", group: 3 }
+];
+function findLongestMatch(word, suffixes) {
+  let best = null;
+  for (const entry of suffixes) {
+    if (endsWith(word, entry.suffix)) {
+      if (best === null || entry.suffix.length > best.suffix.length) {
+        best = entry;
+      }
+    }
+  }
+  return best;
+}
+function removeStandardSuffix(word, r1, r2, rv) {
+  const match = findLongestMatch(word, STANDARD_SUFFIXES);
+  if (match === null) return { word, changed: false };
+  const { suffix, group } = match;
+  if (group === 1) {
+    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
+    return { word: removeSuffix(word, suffix), changed: true };
+  }
+  if (group === 2) {
+    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
+    return { word: replaceSuffix(word, suffix, "log"), changed: true };
+  }
+  if (group === 3) {
+    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
+    return { word: replaceSuffix(word, suffix, "u"), changed: true };
+  }
+  if (group === 4) {
+    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
+    return { word: replaceSuffix(word, suffix, "ente"), changed: true };
+  }
+  if (group === 5) {
+    if (!suffixInRegion(word, suffix, r1)) return { word, changed: false };
+    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, "os") && suffixInRegion(word, "os", r2)) {
+      word = removeSuffix(word, "os");
+    } else if (endsWith(word, "ic") && suffixInRegion(word, "ic", r2)) {
+      word = removeSuffix(word, "ic");
+    } else if (endsWith(word, "ad") && suffixInRegion(word, "ad", r2)) {
+      word = removeSuffix(word, "ad");
+    }
+    return { word, changed: true };
+  }
+  if (group === 6) {
+    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
+    word = removeSuffix(word, suffix);
+    if (endsWith(word, "ante") && suffixInRegion(word, "ante", r2)) {
+      word = removeSuffix(word, "ante");
+    } else if (endsWith(word, "avel") && suffixInRegion(word, "avel", r2)) {
+      word = removeSuffix(word, "avel");
+    } else if (endsWith(word, "\xEDvel") && suffixInRegion(word, "\xEDvel", r2)) {
+      word = removeSuffix(word, "\xEDvel");
+    }
+    return { word, changed: true };
+  }
+  if (group === 7) {
+    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
+    word = removeSuffix(word, suffix);
+    if (endsWith(word, "abil") && suffixInRegion(word, "abil", r2)) {
+      word = removeSuffix(word, "abil");
+    } else if (endsWith(word, "ic") && suffixInRegion(word, "ic", r2)) {
+      word = removeSuffix(word, "ic");
+    } else if (endsWith(word, "iv") && suffixInRegion(word, "iv", r2)) {
+      word = removeSuffix(word, "iv");
+    }
+    return { word, changed: true };
+  }
+  if (group === 8) {
+    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
+    word = removeSuffix(word, suffix);
+    if (endsWith(word, "at") && suffixInRegion(word, "at", r2)) {
+      word = removeSuffix(word, "at");
+    }
+    return { word, changed: true };
+  }
+  if (group === 9) {
+    if (!suffixInRegion(word, suffix, rv)) return { word, changed: false };
+    const withoutSuffix = removeSuffix(word, suffix);
+    if (endsWith(withoutSuffix, "e")) {
+      return { word: replaceSuffix(word, suffix, "ir"), changed: true };
+    }
+    return { word, changed: false };
+  }
+  return { word, changed: false };
+}
+var VERB_SUFFIXES = [
+  "ar\xEDamos",
+  "er\xEDamos",
+  "ir\xEDamos",
+  "\xE1ssemos",
+  "\xEAssemos",
+  "\xEDssemos",
+  "\xE1ramos",
+  "\xE9ramos",
+  "\xEDramos",
+  "\xE1vamos",
+  "\xEDamos",
+  "aremos",
+  "eremos",
+  "iremos",
+  "ar\xEDeis",
+  "er\xEDeis",
+  "ir\xEDeis",
+  "\xE1sseis",
+  "\xE9sseis",
+  "\xEDsseis",
+  "\xE1veis",
+  "\xEDeis",
+  "ardes",
+  "erdes",
+  "irdes",
+  "areis",
+  "ereis",
+  "ireis",
+  "\xE1reis",
+  "\xE9reis",
+  "\xEDreis",
+  "asses",
+  "esses",
+  "isses",
+  "astes",
+  "estes",
+  "istes",
+  "ariam",
+  "eriam",
+  "iriam",
+  "arias",
+  "erias",
+  "irias",
+  "assem",
+  "essem",
+  "issem",
+  "armos",
+  "ermos",
+  "irmos",
+  "aram",
+  "eram",
+  "iram",
+  "avam",
+  "arem",
+  "erem",
+  "irem",
+  "ando",
+  "endo",
+  "indo",
+  "ados",
+  "idos",
+  "amos",
+  "emos",
+  "imos",
+  "ar\xE1s",
+  "er\xE1s",
+  "ir\xE1s",
+  "ares",
+  "eres",
+  "ires",
+  "avas",
+  "aria",
+  "eria",
+  "iria",
+  "asse",
+  "esse",
+  "isse",
+  "aste",
+  "este",
+  "iste",
+  "arei",
+  "erei",
+  "irei",
+  "ada",
+  "ida",
+  "ara",
+  "era",
+  "ira",
+  "ava",
+  "ado",
+  "ido",
+  "ais",
+  "eis",
+  "is",
+  "iam",
+  "\xE1mos",
+  "ara~o",
+  "era~o",
+  "ira~o",
+  "am",
+  "em",
+  "ar",
+  "er",
+  "ir",
+  "as",
+  "es",
+  "eu",
+  "iu",
+  "ou",
+  "ia",
+  "ei",
+  "ar\xE1",
+  "er\xE1",
+  "ir\xE1"
+];
+function removeVerbSuffix(word, rv) {
+  let longestSuffix = null;
+  for (const suffix of VERB_SUFFIXES) {
+    if (endsWith(word, suffix) && suffixInRegion(word, suffix, rv)) {
+      if (longestSuffix === null || suffix.length > longestSuffix.length) {
+        longestSuffix = suffix;
+      }
+    }
+  }
+  if (longestSuffix !== null) {
+    return { word: removeSuffix(word, longestSuffix), changed: true };
+  }
+  return { word, changed: false };
+}
+var RESIDUAL_SUFFIXES = ["a", "i", "o", "os", "\xE1", "\xED", "\xF3"];
+function removeResidualSuffix(word, rv) {
+  let longestSuffix = null;
+  for (const suffix of RESIDUAL_SUFFIXES) {
+    if (endsWith(word, suffix) && suffixInRegion(word, suffix, rv)) {
+      if (longestSuffix === null || suffix.length > longestSuffix.length) {
+        longestSuffix = suffix;
+      }
+    }
+  }
+  if (longestSuffix !== null) {
+    return { word: removeSuffix(word, longestSuffix), changed: true };
+  }
+  return { word, changed: false };
+}
+function removeResidualForm(word, rv) {
+  if (endsWith(word, "\xEA") && suffixInRegion(word, "\xEA", rv)) {
+    return removeSuffix(word, "\xEA");
+  }
+  if (endsWith(word, "\xE9") && suffixInRegion(word, "\xE9", rv)) {
+    return removeSuffix(word, "\xE9");
+  }
+  if (endsWith(word, "e") && suffixInRegion(word, "e", rv)) {
+    word = removeSuffix(word, "e");
+    if (endsWith(word, "gu") && suffixInRegion(word, "u", rv)) {
+      word = removeSuffix(word, "u");
+    } else if (endsWith(word, "ci") && suffixInRegion(word, "i", rv)) {
+      word = removeSuffix(word, "i");
+    }
+    return word;
+  }
+  if (endsWith(word, "\xE7")) {
+    return replaceSuffix(word, "\xE7", "c");
+  }
+  return word;
+}
+function normalizeNasals(word) {
+  return word.replace(/\u00e3/g, "a~").replace(/\u00f5/g, "o~");
+}
+function restoreNasals(word) {
+  return word.replace(/a~/g, "\xE3").replace(/o~/g, "\xF5");
+}
+function stem(word) {
+  if (word.length < 3) return word;
+  word = word.toLowerCase();
+  word = normalizeNasals(word);
+  const { rv, r1, r2 } = findRegions(word);
+  const standardResult = removeStandardSuffix(word, r1, r2, rv);
+  let standardOrVerbChanged = standardResult.changed;
+  if (standardResult.changed) {
+    word = standardResult.word;
+  } else {
+    const verbResult = removeVerbSuffix(word, rv);
+    standardOrVerbChanged = verbResult.changed;
+    word = verbResult.word;
+  }
+  if (standardOrVerbChanged) {
+    if (endsWith(word, "i") && suffixInRegion(word, "i", rv)) {
+      const preceding = word.length >= 2 ? word[word.length - 2] : "";
+      if (preceding === "c") {
+        word = removeSuffix(word, "i");
+      }
+    }
+  } else {
+    const residualResult = removeResidualSuffix(word, rv);
+    word = residualResult.word;
+  }
+  word = removeResidualForm(word, rv);
+  word = restoreNasals(word);
+  return word;
+}
+var stopWords = /* @__PURE__ */ new Set([
+  "de",
+  "a",
+  "o",
+  "que",
+  "e",
+  "do",
+  "da",
+  "em",
+  "um",
+  "para",
+  "com",
+  "n\xE3o",
+  "uma",
+  "os",
+  "no",
+  "se",
+  "na",
+  "por",
+  "mais",
+  "as",
+  "dos",
+  "como",
+  "mas",
+  "ao",
+  "ele",
+  "das",
+  "\xE0",
+  "seu",
+  "sua",
+  "ou",
+  "quando",
+  "muito",
+  "nos",
+  "j\xE1",
+  "eu",
+  "tamb\xE9m",
+  "s\xF3",
+  "pelo",
+  "pela",
+  "at\xE9",
+  "isso",
+  "ela",
+  "entre",
+  "depois",
+  "sem",
+  "mesmo",
+  "aos",
+  "seus",
+  "quem",
+  "nas",
+  "me",
+  "esse",
+  "eles",
+  "voc\xEA",
+  "essa",
+  "num",
+  "nem",
+  "suas",
+  "meu",
+  "\xE0s",
+  "minha",
+  "numa",
+  "pelos",
+  "elas",
+  "qual",
+  "n\xF3s",
+  "lhe",
+  "deles",
+  "essas",
+  "esses",
+  "pelas",
+  "este",
+  "dele",
+  "tu",
+  "te",
+  "voc\xEAs",
+  "vos",
+  "lhes",
+  "meus",
+  "minhas",
+  "teu",
+  "tua",
+  "teus",
+  "tuas",
+  "nosso",
+  "nossa",
+  "nossos",
+  "nossas",
+  "dela",
+  "delas",
+  "esta",
+  "estes",
+  "estas",
+  "aquele",
+  "aquela",
+  "aqueles",
+  "aquelas",
+  "isto",
+  "aquilo",
+  "estou",
+  "est\xE1",
+  "estamos",
+  "est\xE3o",
+  "estive",
+  "esteve",
+  "estivemos",
+  "estiveram",
+  "estava",
+  "est\xE1vamos",
+  "estavam",
+  "estivera",
+  "estiv\xE9ramos",
+  "esteja",
+  "estejamos",
+  "estejam",
+  "estivesse",
+  "estiv\xE9ssemos",
+  "estivessem",
+  "estiver",
+  "estivermos",
+  "estiverem",
+  "hei",
+  "h\xE1",
+  "havemos",
+  "h\xE3o",
+  "houve",
+  "houvemos",
+  "houveram",
+  "houvera",
+  "houv\xE9ramos",
+  "haja",
+  "hajamos",
+  "hajam",
+  "houvesse",
+  "houv\xE9ssemos",
+  "houvessem",
+  "houver",
+  "houvermos",
+  "houverem",
+  "houverei",
+  "houver\xE1",
+  "houveremos",
+  "houver\xE3o",
+  "houveria",
+  "houver\xEDamos",
+  "houveriam",
+  "sou",
+  "somos",
+  "s\xE3o",
+  "era",
+  "\xE9ramos",
+  "eram",
+  "fui",
+  "foi",
+  "fomos",
+  "foram",
+  "fora",
+  "f\xF4ramos",
+  "seja",
+  "sejamos",
+  "sejam",
+  "fosse",
+  "f\xF4ssemos",
+  "fossem",
+  "for",
+  "formos",
+  "forem",
+  "serei",
+  "ser\xE1",
+  "seremos",
+  "ser\xE3o",
+  "seria",
+  "ser\xEDamos",
+  "seriam",
+  "tenho",
+  "tem",
+  "temos",
+  "t\xE9m",
+  "tinha",
+  "t\xEDnhamos",
+  "tinham",
+  "tive",
+  "teve",
+  "tivemos",
+  "tiveram",
+  "tivera",
+  "tiv\xE9ramos",
+  "tenha",
+  "tenhamos",
+  "tenham",
+  "tivesse",
+  "tiv\xE9ssemos",
+  "tivessem",
+  "tiver",
+  "tivermos",
+  "tiverem",
+  "terei",
+  "ter\xE1",
+  "teremos",
+  "ter\xE3o",
+  "teria",
+  "ter\xEDamos",
+  "teriam"
+]);
+var portuguese = {
+  name: "portuguese",
+  stemmer: stem,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9\u00e0-\u00fa]+/gi }
+};
+
+export { portuguese };

package/dist/languages/romanian.d.ts

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