@delali/narsil 0.1.15 → 0.2.0

package/dist/languages/norwegian.mjs

@@ -1,95 +1,227 @@
-// src/languages/norwegian.ts
-var VOWELS = "aeiouy\xE5\xE6\xF8";
-function isVowel(ch) {
-  return VOWELS.includes(ch);
-}
-function computeR1(word) {
-  let i = 0;
-  while (i < word.length && !isVowel(word[i])) i++;
-  while (i < word.length && isVowel(word[i])) i++;
-  const r1 = i < word.length ? i + 1 : word.length;
-  return Math.max(r1, 3);
-}
-var S_ENDINGS = "bcdfghjlmnoprtvyz";
-var STEP1_SUFFIXES = [
-  "hetenes",
-  "hetene",
-  "hetens",
-  "endes",
-  "heten",
-  "heter",
-  "ande",
-  "ende",
-  "edes",
-  "enes",
-  "erte",
-  "ane",
-  "ene",
-  "ens",
-  "ers",
-  "ets",
-  "ede",
-  "het",
-  "en",
-  "ar",
-  "er",
-  "et",
-  "as",
-  "es",
-  "ert",
-  "ast",
-  "a",
-  "e",
-  "s"
+import { BaseStemmer } from '../chunk-U2BKYEC7.mjs';
+
+// src/languages/snowball/norwegian.ts
+var a_0 = [
+  ["", 1],
+  ["ind", -1, 1],
+  ["kk", -1, 2],
+  ["nk", -1, 3],
+  ["amm", -1, 4],
+  ["omm", -1, 5],
+  ["kap", -1, 6],
+  ["skap", 1, 1],
+  ["pp", -1, 8],
+  ["lt", -1, 9],
+  ["ast", -1, 10],
+  ["\xF8st", -1, 11],
+  ["v", -1, 12],
+  ["hav", 1, 1],
+  ["giv", 1, 2]
+];
+var a_1 = [
+  ["a", 1],
+  ["e", 1],
+  ["ede", 1, 1],
+  ["ande", 1, 2],
+  ["ende", 1, 3],
+  ["ane", 1, 4],
+  ["ene", 1, 5],
+  ["hetene", 1, 1],
+  ["erte", 4, 7],
+  ["en", 1],
+  ["heten", 1, 1],
+  ["ar", 1],
+  ["er", 1],
+  ["heter", 1, 1],
+  ["s", 3],
+  ["as", 1, 1],
+  ["es", 1, 2],
+  ["edes", 1, 1],
+  ["endes", 1, 2],
+  ["enes", 1, 3],
+  ["hetenes", 1, 1],
+  ["ens", 1, 7],
+  ["hetens", 1, 1],
+  ["ers", 2, 9],
+  ["ets", 1, 10],
+  ["et", 1],
+  ["het", 1, 1],
+  ["ert", 4],
+  ["ast", 1]
 ];
-function step1(word, r1) {
-  for (const suffix of STEP1_SUFFIXES) {
-    if (!word.endsWith(suffix)) continue;
-    const boundary = word.length - suffix.length;
-    if (boundary < r1) continue;
-    if (suffix === "erte" || suffix === "ert") {
-      return `${word.slice(0, boundary)}er`;
+var a_2 = [
+  ["dt", -1],
+  ["vt", -1]
+];
+var a_3 = [
+  ["leg", 1],
+  ["eleg", 1, 1],
+  ["ig", 1],
+  ["eig", 1, 1],
+  ["lig", 1, 2],
+  ["elig", 1, 1],
+  ["els", 1],
+  ["lov", 1],
+  ["elov", 1, 1],
+  ["slov", 1, 2],
+  ["hetslov", 1, 1]
+];
+var g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 48, 2, 142];
+var g_s_ending = [119, 125, 148, 1];
+var NorwegianStemmer = class extends BaseStemmer {
+  #stem() {
+    let a;
+    let I_p1;
+    I_p1 = this.limit;
+    const v_1 = this.c;
+    lab0: {
+      lab1: {
+        const v_2 = this.c;
+        lab2: {
+          while (true) {
+            lab4: {
+              if (!this.eq_s("'")) break lab4;
+              break;
+            }
+            if (this.c >= this.limit) break lab2;
+            this.c++;
+          }
+          break lab1;
+        }
+        this.c = v_2;
+        if (!this.go_out_grouping(g_v, 97, 248)) break lab0;
+        this.c++;
+        if (!this.go_in_grouping(g_v, 97, 248)) break lab0;
+        this.c++;
+      }
+      I_p1 = this.c;
     }
-    if (suffix === "s") {
-      if (boundary > 0) {
-        const preceding = word[boundary - 1];
-        if (S_ENDINGS.includes(preceding)) return word.slice(0, boundary);
-        if (preceding === "k" && boundary > 1 && !isVowel(word[boundary - 2])) {
-          return word.slice(0, boundary);
+    this.c = v_1;
+    const v_3 = this.c;
+    if (this.c + 3 > this.limit) return false;
+    this.c += 3;
+    lab5: {
+      if (
+        /**@type {boolean}*/
+        I_p1 >= this.c
+      ) break lab5;
+      I_p1 = this.c;
+    }
+    this.c = v_3;
+    this.limit_backward = this.c;
+    this.c = this.limit;
+    const v_4 = this.limit - this.c;
+    lab6: {
+      if (this.c < I_p1) break lab6;
+      const v_5 = this.limit_backward;
+      this.limit_backward = I_p1;
+      this.ket = this.c;
+      a = this.find_among_b(a_1);
+      if (a === 0) {
+        this.limit_backward = v_5;
+        break lab6;
+      }
+      this.bra = this.c;
+      this.limit_backward = v_5;
+      switch (a) {
+        case 1: {
+          this.slice_del();
+          break;
+        }
+        case 2: {
+          a = this.find_among_b(a_0);
+          switch (a) {
+            case 1: {
+              this.slice_del();
+              break;
+            }
+          }
+          break;
+        }
+        case 3: {
+          lab7: {
+            const v_6 = this.limit - this.c;
+            lab8: {
+              if (!this.in_grouping_b(g_s_ending, 98, 122)) break lab8;
+              break lab7;
+            }
+            this.c = this.limit - v_6;
+            lab9: {
+              if (!this.eq_s_b("r")) break lab9;
+              lab10: {
+                if (!this.eq_s_b("e")) break lab10;
+                break lab9;
+              }
+              break lab7;
+            }
+            this.c = this.limit - v_6;
+            if (!this.eq_s_b("k")) break lab6;
+            if (!this.out_grouping_b(g_v, 97, 248)) break lab6;
+          }
+          this.slice_del();
+          break;
+        }
+        case 4: {
+          this.slice_from("er");
+          break;
         }
       }
-      continue;
     }
-    return word.slice(0, boundary);
-  }
-  return word;
-}
-function step2(word, r1) {
-  if (word.length < 2) return word;
-  const last2 = word.slice(-2);
-  if ((last2 === "dt" || last2 === "vt") && word.length - 2 >= r1) {
-    return word.slice(0, -1);
-  }
-  return word;
-}
-var STEP3_SUFFIXES = ["hetslov", "elov", "slov", "elig", "eleg", "lig", "eig", "leg", "lov", "els", "ig"];
-function step3(word, r1) {
-  for (const suffix of STEP3_SUFFIXES) {
-    if (!word.endsWith(suffix)) continue;
-    if (word.length - suffix.length >= r1) {
-      return word.slice(0, word.length - suffix.length);
+    this.c = this.limit - v_4;
+    const v_7 = this.limit - this.c;
+    lab11: {
+      const v_8 = this.limit - this.c;
+      if (this.c < I_p1) break lab11;
+      const v_9 = this.limit_backward;
+      this.limit_backward = I_p1;
+      this.ket = this.c;
+      if (this.find_among_b(a_2) === 0) {
+        this.limit_backward = v_9;
+        break lab11;
+      }
+      this.bra = this.c;
+      this.limit_backward = v_9;
+      this.c = this.limit - v_8;
+      if (this.c <= this.limit_backward) break lab11;
+      this.c--;
+      this.bra = this.c;
+      this.slice_del();
     }
+    this.c = this.limit - v_7;
+    const v_10 = this.limit - this.c;
+    lab12: {
+      if (this.c < I_p1) break lab12;
+      const v_11 = this.limit_backward;
+      this.limit_backward = I_p1;
+      this.ket = this.c;
+      if (this.find_among_b(a_3) === 0) {
+        this.limit_backward = v_11;
+        break lab12;
+      }
+      this.bra = this.c;
+      this.limit_backward = v_11;
+      this.slice_del();
+    }
+    this.c = this.limit - v_10;
+    this.ket = this.c;
+    if (!this.eq_s_b("'")) return false;
+    this.bra = this.c;
+    this.slice_del();
+    this.c = this.limit_backward;
+    return true;
   }
-  return word;
-}
-function stem(word) {
-  if (word.length < 3) return word;
-  const r1 = computeR1(word);
-  word = step1(word, r1);
-  word = step2(word, r1);
-  word = step3(word, r1);
-  return word;
+  stem(input) {
+    this.setCurrent(input);
+    this.#stem();
+    return this.getCurrent();
+  }
+};
+var shared = new NorwegianStemmer();
+function stem(token) {
+  return shared.stem(token);
 }
+
+// src/languages/norwegian.ts
 var stopWords = /* @__PURE__ */ new Set([
   "og",
   "i",
@@ -266,9 +398,10 @@ var stopWords = /* @__PURE__ */ new Set([
 ]);
 var norwegian = {
   name: "norwegian",
+  revision: "8e862aa3bcec10dd",
   stemmer: stem,
   stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9æøåäöü]+/gi }
+  tokenizer: { splitPattern: /[^a-z0-9æøåäöüéó]+/gi }
 };
 
 export { norwegian };

package/dist/languages/oromo.d.ts

@@ -0,0 +1,5 @@
+import { L as LanguageModule } from '../language-CmJBHf1j.js';
+
+declare const oromo: LanguageModule;
+
+export { oromo };

package/dist/languages/oromo.mjs

@@ -0,0 +1,78 @@
+// src/languages/oromo.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "achi",
+  "akka",
+  "akkam",
+  "akkasumas",
+  "amma",
+  "ammas",
+  "ammo",
+  "ani",
+  "as",
+  "ati",
+  "booda",
+  "dha",
+  "dura",
+  "eenyu",
+  "eessa",
+  "erga",
+  "fi",
+  "garuu",
+  "gidduu",
+  "hin",
+  "illee",
+  "immoo",
+  "inni",
+  "irra",
+  "irratti",
+  "isa",
+  "isaa",
+  "isaan",
+  "isaanii",
+  "ishee",
+  "isheen",
+  "isin",
+  "jala",
+  "jira",
+  "jiran",
+  "jirti",
+  "jiru",
+  "kan",
+  "kana",
+  "kanaaf",
+  "kee",
+  "keenya",
+  "keessa",
+  "keessan",
+  "keessatti",
+  "koo",
+  "kun",
+  "maal",
+  "malee",
+  "miti",
+  "ni",
+  "nu",
+  "nuti",
+  "osoo",
+  "qofa",
+  "sana",
+  "sun",
+  "ta'an",
+  "ta'e",
+  "ture",
+  "waan",
+  "waliin",
+  "ykn",
+  "yoo",
+  "yookiin",
+  "yoom"
+]);
+var oromo = {
+  name: "oromo",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9']+/gi }
+};
+
+export { oromo };

package/dist/languages/persian.d.ts

@@ -0,0 +1,5 @@
+import { L as LanguageModule } from '../language-CmJBHf1j.js';
+
+declare const persian: LanguageModule;
+
+export { persian };