@delali/narsil 0.1.0

package/dist/languages/irish.d.ts

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

package/dist/languages/irish.mjs

@@ -0,0 +1,268 @@
+// src/languages/irish.ts
+var VOWELS = "aeiou\xE1\xE9\xED\xF3\xFA";
+function isVowel(ch) {
+  return VOWELS.includes(ch);
+}
+function findRegions(word) {
+  let r1 = word.length;
+  let r2 = word.length;
+  let rv = word.length;
+  for (let i = 1; i < word.length; i++) {
+    if (!isVowel(word[i]) && isVowel(word[i - 1])) {
+      r1 = i + 1;
+      break;
+    }
+  }
+  for (let i = r1 + 1; i < word.length; i++) {
+    if (!isVowel(word[i]) && isVowel(word[i - 1])) {
+      r2 = i + 1;
+      break;
+    }
+  }
+  let foundConsonantCluster = false;
+  for (let i = 0; i < word.length; i++) {
+    if (!foundConsonantCluster) {
+      if (!isVowel(word[i])) continue;
+      foundConsonantCluster = false;
+      for (let j = i + 1; j < word.length; j++) {
+        if (!isVowel(word[j])) {
+          rv = j + 1;
+          foundConsonantCluster = true;
+          break;
+        }
+      }
+      if (foundConsonantCluster) break;
+    }
+  }
+  return { r1, r2, rv };
+}
+var ECLIPSIS = [
+  ["bhf", "f"],
+  ["mb", "b"],
+  ["gc", "c"],
+  ["nd", "d"],
+  ["ng", "g"],
+  ["bp", "p"],
+  ["ts", "s"],
+  ["dt", "t"]
+];
+var LENITION = [
+  ["bh", "b"],
+  ["ch", "c"],
+  ["dh", "d"],
+  ["fh", "f"],
+  ["gh", "g"],
+  ["mh", "m"],
+  ["ph", "p"],
+  ["sh", "s"],
+  ["th", "t"]
+];
+function removeInitialMutations(word) {
+  if (word.startsWith("d'") || word.startsWith("b'")) {
+    const rest = word.slice(2);
+    if (rest.length > 0 && isVowel(rest[0])) {
+      return rest;
+    }
+  }
+  if (word.startsWith("h-") || word.startsWith("n-") || word.startsWith("t-")) {
+    const rest = word.slice(2);
+    if (rest.length > 0 && isVowel(rest[0])) {
+      return rest;
+    }
+  }
+  for (const [mutation, replacement] of ECLIPSIS) {
+    if (word.startsWith(mutation)) {
+      return `${replacement}${word.slice(mutation.length)}`;
+    }
+  }
+  for (const [mutation, replacement] of LENITION) {
+    if (word.startsWith(mutation)) {
+      return `${replacement}${word.slice(mutation.length)}`;
+    }
+  }
+  return word;
+}
+var NOUN_SUFFIXES = [
+  "arcachta\xED",
+  "gineadach",
+  "a\xEDochta\xED",
+  "eachta\xED",
+  "\xEDochta\xED",
+  "a\xEDochta",
+  "achta\xED",
+  "eachta",
+  "gineas",
+  "\xE9altas",
+  "\xEDochta",
+  "a\xEDocht",
+  "eanna",
+  "achta",
+  "eacht",
+  "anna",
+  "acht",
+  "aire",
+  "ire"
+];
+var VERB_SUFFIXES = [
+  "a\xEDomar",
+  "a\xEDtear",
+  "aimid",
+  "aim\xEDs",
+  "aimis",
+  "a\xEDodh",
+  "a\xEDonn",
+  "eamar",
+  "imid",
+  "\xEDmid",
+  "\xEDm\xEDs",
+  "imis",
+  "tear",
+  "eadh",
+  "aidh",
+  "igh",
+  "ann",
+  "adh"
+];
+function removeSuffixInRegion(word, suffixes, regionStart) {
+  for (const suffix of suffixes) {
+    if (word.endsWith(suffix) && word.length - suffix.length >= regionStart) {
+      return word.slice(0, word.length - suffix.length);
+    }
+  }
+  return null;
+}
+function stem(word) {
+  if (word.length < 3) return word;
+  word = removeInitialMutations(word);
+  if (word.length < 3) return word;
+  const { r2, rv } = findRegions(word);
+  const nounResult = removeSuffixInRegion(word, NOUN_SUFFIXES, r2);
+  if (nounResult !== null) {
+    word = nounResult;
+  } else {
+    const verbResult = removeSuffixInRegion(word, VERB_SUFFIXES, rv);
+    if (verbResult !== null) {
+      word = verbResult;
+    }
+  }
+  return word;
+}
+var stopWords = /* @__PURE__ */ new Set([
+  "a",
+  "ach",
+  "ag",
+  "agus",
+  "an",
+  "aon",
+  "ar",
+  "arna",
+  "as",
+  "b",
+  "ba",
+  "beirt",
+  "bh\xFAr",
+  "caoga",
+  "ceathair",
+  "ceathrar",
+  "chomh",
+  "cht\xF3",
+  "chuig",
+  "chun",
+  "cois",
+  "c\xE9ad",
+  "c\xFAig",
+  "c\xFAigear",
+  "d",
+  "daichead",
+  "dar",
+  "de",
+  "deich",
+  "deichni\xFAr",
+  "den",
+  "dh\xE1",
+  "do",
+  "don",
+  "dt\xED",
+  "d\xE1",
+  "d\xE1r",
+  "d\xF3",
+  "faoi",
+  "faoin",
+  "faoina",
+  "faoin\xE1r",
+  "fara",
+  "fiche",
+  "gach",
+  "gan",
+  "go",
+  "gur",
+  "haon",
+  "hocht",
+  "i",
+  "iad",
+  "idir",
+  "in",
+  "ina",
+  "ins",
+  "in\xE1r",
+  "is",
+  "le",
+  "leis",
+  "lena",
+  "len\xE1r",
+  "m",
+  "mar",
+  "mo",
+  "m\xE9",
+  "na",
+  "nach",
+  "naoi",
+  "naon\xFAr",
+  "n\xE1",
+  "n\xED",
+  "n\xEDor",
+  "n\xF3",
+  "n\xF3cha",
+  "ocht",
+  "ochtar",
+  "os",
+  "roimh",
+  "sa",
+  "seacht",
+  "seachtar",
+  "seacht\xF3",
+  "seasca",
+  "seisear",
+  "siad",
+  "sibh",
+  "sinn",
+  "sna",
+  "s\xE9",
+  "s\xED",
+  "tar",
+  "thar",
+  "th\xFA",
+  "tri\xFAr",
+  "tr\xED",
+  "tr\xEDna",
+  "tr\xEDn\xE1r",
+  "tr\xEDocha",
+  "t\xFA",
+  "um",
+  "\xE1r",
+  "\xE9",
+  "\xE9is",
+  "\xED",
+  "\xF3",
+  "\xF3n",
+  "\xF3na",
+  "\xF3n\xE1r"
+]);
+var irish = {
+  name: "irish",
+  stemmer: stem,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9áéíóú]+/gi }
+};
+
+export { irish };

package/dist/languages/italian.d.ts

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