@delali/narsil 0.1.0

package/dist/languages/spanish.mjs

@@ -0,0 +1,606 @@
+// src/languages/spanish.ts
+var VOWELS = "aeiou\xE1\xE9\xED\xF3\xFA\xFC";
+var ACCENT_A = /á/g;
+var ACCENT_E = /é/g;
+var ACCENT_I = /í/g;
+var ACCENT_O = /ó/g;
+var ACCENT_U = /ú/g;
+var STEP1_GROUP1_SUFFIXES = [
+  "amientos",
+  "imientos",
+  "amiento",
+  "imiento",
+  "aciones",
+  "uciones",
+  "adoras",
+  "adores",
+  "ancias",
+  "encias",
+  "adora",
+  "antes",
+  "anzas",
+  "ismos",
+  "istas",
+  "ables",
+  "ibles",
+  "aci\xF3n",
+  "uci\xF3n",
+  "icas",
+  "ador",
+  "ante",
+  "anza",
+  "icos",
+  "ismo",
+  "ista",
+  "osas",
+  "osos",
+  "iva",
+  "ivo",
+  "ivas",
+  "ivos",
+  "ica",
+  "ico",
+  "osa",
+  "oso",
+  "able",
+  "ible"
+];
+var STEP1_GROUP2_SUFFIXES = ["log\xEDas", "log\xEDa"];
+var STEP1_GROUP3_SUFFIXES = ["uci\xF3n", "uciones"];
+var STEP1_GROUP4_SUFFIXES = ["encia", "encias"];
+var STEP1_GROUP5_SUFFIXES = ["amente"];
+var STEP1_GROUP6_SUFFIXES = ["mente"];
+var STEP1_GROUP7_SUFFIXES = ["idades", "idad"];
+var STEP1_ALL_SUFFIXES = [
+  ...STEP1_GROUP1_SUFFIXES,
+  ...STEP1_GROUP2_SUFFIXES,
+  ...STEP1_GROUP3_SUFFIXES,
+  ...STEP1_GROUP4_SUFFIXES,
+  ...STEP1_GROUP5_SUFFIXES,
+  ...STEP1_GROUP6_SUFFIXES,
+  ...STEP1_GROUP7_SUFFIXES
+];
+var Y_VERB_SUFFIXES = ["yeron", "yendo", "yamos", "yais", "yan", "yen", "yas", "yes", "ya", "ye", "yo", "y\xF3"];
+var STEP2B_VERB_SUFFIXES = [
+  "i\xE9ramos",
+  "i\xE9semos",
+  "er\xEDamos",
+  "ar\xEDamos",
+  "ir\xEDamos",
+  "\xE1ramos",
+  "\xE1bamos",
+  "\xE1semos",
+  "\xEDamos",
+  "ar\xEDais",
+  "er\xEDais",
+  "ir\xEDais",
+  "ieran",
+  "iesen",
+  "ieron",
+  "ir\xEDan",
+  "er\xEDan",
+  "ar\xEDan",
+  "arais",
+  "aseis",
+  "er\xE9is",
+  "ar\xE9is",
+  "ir\xE9is",
+  "ir\xEDas",
+  "er\xEDas",
+  "ar\xEDas",
+  "ieras",
+  "ieses",
+  "abais",
+  "aremos",
+  "eremos",
+  "iremos",
+  "isteis",
+  "asteis",
+  "ierais",
+  "ieseis",
+  "iendo",
+  "ando",
+  "ar\xE1n",
+  "er\xE1n",
+  "ir\xE1n",
+  "aron",
+  "aban",
+  "aran",
+  "adas",
+  "idas",
+  "abas",
+  "aras",
+  "ases",
+  "ir\xEDa",
+  "er\xEDa",
+  "ar\xEDa",
+  "iera",
+  "iese",
+  "aste",
+  "iste",
+  "ados",
+  "idos",
+  "amos",
+  "imos",
+  "\xEDan",
+  "\xE1is",
+  "aba",
+  "ada",
+  "ida",
+  "ara",
+  "ase",
+  "ado",
+  "ido",
+  "\xEDas",
+  "\xE9is",
+  "\xEDa",
+  "ad",
+  "ed",
+  "id",
+  "an",
+  "i\xF3",
+  "ar",
+  "er",
+  "ir",
+  "as",
+  "es",
+  "\xEDs",
+  "en",
+  "ar\xE1",
+  "er\xE1",
+  "ir\xE1",
+  "ar\xE9",
+  "er\xE9",
+  "ir\xE9",
+  "\xE1t"
+];
+var RESIDUAL_SUFFIXES = ["os", "a", "o", "\xE1", "\xED", "\xF3"];
+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) {
+    if (!isVowel(word[1])) {
+      for (let i = 2; i < word.length; i++) {
+        if (isVowel(word[i])) {
+          rv = i + 1;
+          break;
+        }
+      }
+    } else if (isVowel(word[0])) {
+      for (let i = 2; i < word.length; i++) {
+        if (!isVowel(word[i])) {
+          rv = i + 1;
+          break;
+        }
+      }
+    } else {
+      rv = 3;
+    }
+  }
+  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 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 removeAccents(word) {
+  return word.replace(ACCENT_A, "a").replace(ACCENT_E, "e").replace(ACCENT_I, "i").replace(ACCENT_O, "o").replace(ACCENT_U, "u");
+}
+var ATTACHED_PRONOUNS = ["selas", "selos", "sela", "selo", "las", "les", "los", "nos", "la", "le", "lo", "me", "se"];
+var PRONOUN_VERB_SUFFIXES = ["i\xE9ndo", "\xE1ndo", "\xE1r", "\xE9r", "\xEDr", "iendo", "ando", "yendo", "ar", "er", "ir"];
+function step0AttachedPronoun(word, rv) {
+  for (const pronoun of ATTACHED_PRONOUNS) {
+    if (!endsWith(word, pronoun)) continue;
+    if (!suffixInRegion(word, pronoun, rv)) continue;
+    const beforePronoun = removeSuffix(word, pronoun);
+    for (const verbSuffix of PRONOUN_VERB_SUFFIXES) {
+      if (!endsWith(beforePronoun, verbSuffix)) continue;
+      if (verbSuffix === "yendo" && endsWith(removeSuffix(beforePronoun, "yendo"), "u")) {
+        return removeSuffix(word, pronoun);
+      }
+      if (verbSuffix === "i\xE9ndo") {
+        return `${removeSuffix(word, pronoun).slice(0, -5)}iendo`;
+      }
+      if (verbSuffix === "\xE1ndo") {
+        return `${removeSuffix(word, pronoun).slice(0, -4)}ando`;
+      }
+      if (verbSuffix === "\xE1r") {
+        return `${removeSuffix(word, pronoun).slice(0, -2)}ar`;
+      }
+      if (verbSuffix === "\xE9r") {
+        return `${removeSuffix(word, pronoun).slice(0, -2)}er`;
+      }
+      if (verbSuffix === "\xEDr") {
+        return `${removeSuffix(word, pronoun).slice(0, -2)}ir`;
+      }
+      return removeSuffix(word, pronoun);
+    }
+  }
+  return word;
+}
+function step1StandardSuffix(word, r1, r2) {
+  let longestSuffix = null;
+  for (const s of STEP1_ALL_SUFFIXES) {
+    if (endsWith(word, s)) {
+      if (longestSuffix === null || s.length > longestSuffix.length) {
+        longestSuffix = s;
+      }
+    }
+  }
+  if (!longestSuffix) return { word, changed: false };
+  if (STEP1_GROUP1_SUFFIXES.includes(longestSuffix)) {
+    if (longestSuffix === "iva" || longestSuffix === "ivo" || longestSuffix === "ivas" || longestSuffix === "ivos") {
+      if (!suffixInRegion(word, longestSuffix, r2)) return { word, changed: false };
+      word = removeSuffix(word, longestSuffix);
+      if (endsWith(word, "at") && suffixInRegion(word, "at", r2)) {
+        word = removeSuffix(word, "at");
+      }
+      return { word, changed: true };
+    }
+    if (!suffixInRegion(word, longestSuffix, r2)) return { word, changed: false };
+    return { word: removeSuffix(word, longestSuffix), changed: true };
+  }
+  if (STEP1_GROUP2_SUFFIXES.includes(longestSuffix)) {
+    if (!suffixInRegion(word, longestSuffix, r2)) return { word, changed: false };
+    return { word: `${removeSuffix(word, longestSuffix)}log`, changed: true };
+  }
+  if (STEP1_GROUP3_SUFFIXES.includes(longestSuffix)) {
+    if (!suffixInRegion(word, longestSuffix, r2)) return { word, changed: false };
+    return { word: `${removeSuffix(word, longestSuffix)}u`, changed: true };
+  }
+  if (STEP1_GROUP4_SUFFIXES.includes(longestSuffix)) {
+    if (!suffixInRegion(word, longestSuffix, r2)) return { word, changed: false };
+    return { word: `${removeSuffix(word, longestSuffix)}ente`, changed: true };
+  }
+  if (STEP1_GROUP5_SUFFIXES.includes(longestSuffix)) {
+    if (!suffixInRegion(word, longestSuffix, r1)) return { word, changed: false };
+    word = removeSuffix(word, longestSuffix);
+    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 (STEP1_GROUP6_SUFFIXES.includes(longestSuffix)) {
+    if (!suffixInRegion(word, longestSuffix, r2)) return { word, changed: false };
+    word = removeSuffix(word, longestSuffix);
+    if (endsWith(word, "ante") && suffixInRegion(word, "ante", r2)) {
+      word = removeSuffix(word, "ante");
+    } else if (endsWith(word, "able") && suffixInRegion(word, "able", r2)) {
+      word = removeSuffix(word, "able");
+    } else if (endsWith(word, "ible") && suffixInRegion(word, "ible", r2)) {
+      word = removeSuffix(word, "ible");
+    }
+    return { word, changed: true };
+  }
+  if (STEP1_GROUP7_SUFFIXES.includes(longestSuffix)) {
+    if (!suffixInRegion(word, longestSuffix, r2)) return { word, changed: false };
+    word = removeSuffix(word, longestSuffix);
+    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 };
+  }
+  return { word, changed: false };
+}
+function step2aYVerbSuffix(word, rv) {
+  const suffix = findLongestAmong(word, Y_VERB_SUFFIXES, rv);
+  if (suffix) {
+    const stemmed = removeSuffix(word, suffix);
+    if (stemmed.length > 0 && stemmed[stemmed.length - 1] === "u") {
+      return { word: stemmed, changed: true };
+    }
+  }
+  return { word, changed: false };
+}
+function step2bVerbSuffix(word, rv) {
+  const suffix = findLongestAmong(word, STEP2B_VERB_SUFFIXES, rv);
+  if (!suffix) return { word, changed: false };
+  if (suffix === "en" || suffix === "es" || suffix === "\xE9is" || suffix === "emos") {
+    word = removeSuffix(word, suffix);
+    if (endsWith(word, "gu")) {
+      if (suffixInRegion(word, "u", rv)) {
+        word = removeSuffix(word, "u");
+      }
+    }
+    return { word, changed: true };
+  }
+  return { word: removeSuffix(word, suffix), changed: true };
+}
+function step3ResidualSuffix(word, rv) {
+  const suffix = findLongestAmong(word, RESIDUAL_SUFFIXES, rv);
+  if (suffix) {
+    return removeSuffix(word, suffix);
+  }
+  if (endsWith(word, "e") || endsWith(word, "\xE9")) {
+    const eSuffix = endsWith(word, "\xE9") ? "\xE9" : "e";
+    if (suffixInRegion(word, eSuffix, rv)) {
+      word = removeSuffix(word, eSuffix);
+      if (endsWith(word, "gu") && suffixInRegion(word, "u", rv)) {
+        word = removeSuffix(word, "u");
+      }
+      return word;
+    }
+  }
+  return word;
+}
+function stem(word) {
+  if (word.length < 3) return word;
+  const { rv, r1, r2 } = findRegions(word);
+  word = step0AttachedPronoun(word, rv);
+  const step1Result = step1StandardSuffix(word, r1, r2);
+  let stemChanged = step1Result.changed;
+  word = step1Result.word;
+  if (!stemChanged) {
+    const step2aResult = step2aYVerbSuffix(word, rv);
+    if (step2aResult.changed) {
+      word = step2aResult.word;
+      stemChanged = true;
+    } else {
+      const step2bResult = step2bVerbSuffix(word, rv);
+      word = step2bResult.word;
+      stemChanged = step2bResult.changed;
+    }
+  }
+  word = step3ResidualSuffix(word, rv);
+  word = removeAccents(word);
+  return word;
+}
+var stopWords = /* @__PURE__ */ new Set([
+  "a",
+  "al",
+  "algo",
+  "alguna",
+  "algunas",
+  "alguno",
+  "algunos",
+  "alg\xFAn",
+  "ambos",
+  "ante",
+  "antes",
+  "aquel",
+  "aquella",
+  "aquellas",
+  "aquello",
+  "aquellos",
+  "aqu\xED",
+  "arriba",
+  "as\xED",
+  "aunque",
+  "a\xFAn",
+  "bajo",
+  "bastante",
+  "bien",
+  "cada",
+  "casi",
+  "como",
+  "con",
+  "contra",
+  "cual",
+  "cuales",
+  "cuando",
+  "cu\xE1ndo",
+  "cu\xE1nto",
+  "cu\xE1ntos",
+  "de",
+  "del",
+  "dem\xE1s",
+  "dentro",
+  "desde",
+  "donde",
+  "d\xF3nde",
+  "dos",
+  "durante",
+  "el",
+  "ella",
+  "ellas",
+  "ello",
+  "ellos",
+  "en",
+  "encima",
+  "entonces",
+  "entre",
+  "era",
+  "esa",
+  "esas",
+  "ese",
+  "eso",
+  "esos",
+  "esta",
+  "estaba",
+  "estado",
+  "estas",
+  "este",
+  "esto",
+  "estos",
+  "est\xE1",
+  "est\xE1n",
+  "fue",
+  "fuera",
+  "fueron",
+  "ha",
+  "hace",
+  "hacen",
+  "hacer",
+  "hacia",
+  "han",
+  "hasta",
+  "hay",
+  "la",
+  "las",
+  "le",
+  "les",
+  "lo",
+  "los",
+  "luego",
+  "mas",
+  "m\xE1s",
+  "me",
+  "mejor",
+  "menos",
+  "mi",
+  "mientras",
+  "mis",
+  "misma",
+  "mismo",
+  "mucha",
+  "muchas",
+  "mucho",
+  "muchos",
+  "muy",
+  "m\xED",
+  "m\xEDa",
+  "m\xEDo",
+  "nada",
+  "ni",
+  "ninguna",
+  "ninguno",
+  "ning\xFAn",
+  "no",
+  "nos",
+  "nosotras",
+  "nosotros",
+  "nuestra",
+  "nuestras",
+  "nuestro",
+  "nuestros",
+  "nunca",
+  "o",
+  "os",
+  "otra",
+  "otras",
+  "otro",
+  "otros",
+  "para",
+  "pero",
+  "poca",
+  "pocas",
+  "poco",
+  "pocos",
+  "por",
+  "porque",
+  "que",
+  "qu\xE9",
+  "quien",
+  "qui\xE9n",
+  "se",
+  "sea",
+  "seg\xFAn",
+  "ser",
+  "ser\xE1",
+  "si",
+  "sido",
+  "sin",
+  "sino",
+  "sobre",
+  "somos",
+  "son",
+  "soy",
+  "su",
+  "sus",
+  "suya",
+  "suyas",
+  "suyo",
+  "s\xED",
+  "tambi\xE9n",
+  "tan",
+  "tanto",
+  "te",
+  "tengo",
+  "ti",
+  "tiene",
+  "tienen",
+  "toda",
+  "todas",
+  "todav\xEDa",
+  "todo",
+  "todos",
+  "tu",
+  "tus",
+  "tuya",
+  "tuyo",
+  "t\xFA",
+  "un",
+  "una",
+  "unas",
+  "uno",
+  "unos",
+  "usted",
+  "ustedes",
+  "va",
+  "vamos",
+  "ver",
+  "vez",
+  "vosotras",
+  "vosotros",
+  "vuestra",
+  "vuestras",
+  "vuestro",
+  "vuestros",
+  "y",
+  "ya",
+  "yo",
+  "\xE9l",
+  "\xE9sta",
+  "\xE9stas",
+  "\xE9ste",
+  "\xE9stos",
+  "\xFAltima",
+  "\xFAltimas",
+  "\xFAltimo",
+  "\xFAltimos"
+]);
+var spanish = {
+  name: "spanish",
+  stemmer: stem,
+  stopWords,
+  tokenizer: {
+    splitPattern: /[^a-z0-9á-úñü]+/gi
+  }
+};
+
+export { spanish };

package/dist/languages/swahili.d.ts

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