@delali/narsil 0.1.14 → 0.2.0

package/dist/languages/swahili.d.ts

@@ -1,4 +1,4 @@
-import { L as LanguageModule } from '../language-ONQ3iVDf.js';
+import { L as LanguageModule } from '../language-CmJBHf1j.js';
 
 declare const swahili: LanguageModule;
 

package/dist/languages/swahili.mjs

@@ -204,9 +204,10 @@ var stopWords = /* @__PURE__ */ new Set([
 ]);
 var swahili = {
   name: "swahili",
+  revision: "1",
   stemmer: stem,
   stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9]+/gi }
+  tokenizer: { splitPattern: /[^a-z0-9']+/gi }
 };
 
 export { swahili };

package/dist/languages/swedish.d.ts

@@ -1,4 +1,4 @@
-import { L as LanguageModule } from '../language-ONQ3iVDf.js';
+import { L as LanguageModule } from '../language-CmJBHf1j.js';
 
 declare const swedish: LanguageModule;
 

package/dist/languages/swedish.mjs

@@ -1,103 +1,244 @@
-// src/languages/swedish.ts
-var VOWELS = "aeiouy\xE4\xE5\xF6";
-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 = "bcdfghjklmnoprtvy";
-var STEP1_SUFFIXES = [
-  "heterna",
-  "hetens",
-  "arnas",
-  "ernas",
-  "ornas",
-  "anden",
-  "heten",
-  "heter",
-  "andes",
-  "arens",
-  "andet",
-  "arna",
-  "erna",
-  "orna",
-  "ande",
-  "arne",
-  "aste",
-  "aren",
-  "ades",
-  "erns",
-  "ade",
-  "are",
-  "ern",
-  "ens",
-  "het",
-  "ast",
-  "ad",
-  "en",
-  "ar",
-  "er",
-  "or",
-  "as",
-  "es",
-  "at",
-  "a",
-  "e",
-  "s"
+import { BaseStemmer } from '../chunk-U2BKYEC7.mjs';
+
+// src/languages/snowball/swedish.ts
+var a_0 = [
+  ["fab", -1],
+  ["h", -1],
+  ["pak", -1],
+  ["rak", -1],
+  ["stak", -1],
+  ["kom", -1],
+  ["iet", -1],
+  ["cit", -1],
+  ["dit", -1],
+  ["alit", -1],
+  ["ilit", -1],
+  ["mit", -1],
+  ["nit", -1],
+  ["pit", -1],
+  ["rit", -1],
+  ["sit", -1],
+  ["tit", -1],
+  ["uit", -1],
+  ["ivit", -1],
+  ["kvit", -1],
+  ["xit", -1]
+];
+var a_1 = [
+  ["a", 1],
+  ["arna", 1, 1],
+  ["erna", 1, 2],
+  ["heterna", 1, 1],
+  ["orna", 1, 4],
+  ["ad", 1],
+  ["e", 1],
+  ["ade", 1, 1],
+  ["ande", 1, 2],
+  ["arne", 1, 3],
+  ["are", 1, 4],
+  ["aste", 1, 5],
+  ["en", 1],
+  ["anden", 1, 1],
+  ["aren", 1, 2],
+  ["heten", 1, 3],
+  ["ern", 1],
+  ["ar", 1],
+  ["er", 1],
+  ["heter", 1, 1],
+  ["or", 1],
+  ["s", 2],
+  ["as", 1, 1],
+  ["arnas", 1, 1],
+  ["ernas", 1, 2],
+  ["ornas", 1, 3],
+  ["es", 1, 5],
+  ["ades", 1, 1],
+  ["andes", 1, 2],
+  ["ens", 1, 8],
+  ["arens", 1, 1],
+  ["hetens", 1, 2],
+  ["erns", 1, 11],
+  ["at", 1],
+  ["et", 3],
+  ["andet", 1, 1],
+  ["het", 1, 2],
+  ["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 === "s") {
-      if (boundary > 0 && S_ENDINGS.includes(word[boundary - 1])) {
-        return word.slice(0, boundary);
+var a_2 = [
+  ["dd", -1],
+  ["gd", -1],
+  ["nn", -1],
+  ["dt", -1],
+  ["gt", -1],
+  ["kt", -1],
+  ["tt", -1]
+];
+var a_3 = [
+  ["ig", 1],
+  ["lig", 1, 1],
+  ["els", 1],
+  ["fullt", 3],
+  ["\xF6st", 2]
+];
+var g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 32];
+var g_s_ending = [119, 127, 149];
+var g_ost_ending = [173, 58];
+var SwedishStemmer = class extends BaseStemmer {
+  #r_et_condition() {
+    const v_1 = this.limit - this.c;
+    if (!this.out_grouping_b(g_v, 97, 246)) return false;
+    if (!this.in_grouping_b(g_v, 97, 246)) return false;
+    if (
+      /**@type {boolean}*/
+      this.c <= this.limit_backward
+    ) return false;
+    this.c = this.limit - v_1;
+    {
+      const v_2 = this.limit - this.c;
+      lab0: {
+        if (this.find_among_b(a_0) === 0) break lab0;
+        return false;
       }
-      continue;
+      this.c = this.limit - v_2;
     }
-    return word.slice(0, boundary);
+    return true;
   }
-  return word;
-}
-var STEP2_ENDINGS = ["dd", "gd", "nn", "dt", "gt", "kt", "tt"];
-function step2(word, r1) {
-  for (const ending of STEP2_ENDINGS) {
-    if (!word.endsWith(ending)) continue;
-    if (word.length - 2 < r1) continue;
-    return word.slice(0, -1);
+  #stem() {
+    let a;
+    let I_x;
+    let I_p1;
+    const v_1 = this.c;
+    lab0: {
+      I_p1 = this.limit;
+      const v_2 = this.c;
+      if (this.c + 3 > this.limit) break lab0;
+      this.c += 3;
+      I_x = this.c;
+      this.c = v_2;
+      if (!this.go_out_grouping(g_v, 97, 246)) break lab0;
+      this.c++;
+      if (!this.go_in_grouping(g_v, 97, 246)) break lab0;
+      this.c++;
+      I_p1 = this.c;
+      lab1: {
+        if (
+          /**@type {boolean}*/
+          I_p1 >= I_x
+        ) break lab1;
+        I_p1 = I_x;
+      }
+    }
+    this.c = v_1;
+    this.limit_backward = this.c;
+    this.c = this.limit;
+    const v_3 = this.limit - this.c;
+    lab2: {
+      if (this.c < I_p1) break lab2;
+      const v_4 = 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_4;
+        break lab2;
+      }
+      this.bra = this.c;
+      this.limit_backward = v_4;
+      switch (a) {
+        case 1: {
+          this.slice_del();
+          break;
+        }
+        case 2: {
+          lab3: {
+            const v_5 = this.limit - this.c;
+            lab4: {
+              if (!this.eq_s_b("et")) break lab4;
+              if (!this.#r_et_condition()) break lab4;
+              this.bra = this.c;
+              break lab3;
+            }
+            this.c = this.limit - v_5;
+            if (!this.in_grouping_b(g_s_ending, 98, 121)) break lab2;
+          }
+          this.slice_del();
+          break;
+        }
+        case 3: {
+          if (!this.#r_et_condition()) break lab2;
+          this.slice_del();
+          break;
+        }
+      }
+    }
+    this.c = this.limit - v_3;
+    const v_6 = this.limit - this.c;
+    lab5: {
+      if (this.c < I_p1) break lab5;
+      const v_7 = this.limit_backward;
+      this.limit_backward = I_p1;
+      const v_8 = this.limit - this.c;
+      if (this.find_among_b(a_2) === 0) {
+        this.limit_backward = v_7;
+        break lab5;
+      }
+      this.c = this.limit - v_8;
+      this.ket = this.c;
+      if (this.c <= this.limit_backward) {
+        this.limit_backward = v_7;
+        break lab5;
+      }
+      this.c--;
+      this.bra = this.c;
+      this.slice_del();
+      this.limit_backward = v_7;
+    }
+    this.c = this.limit - v_6;
+    const v_9 = this.limit - this.c;
+    lab6: {
+      if (this.c < I_p1) break lab6;
+      const v_10 = this.limit_backward;
+      this.limit_backward = I_p1;
+      this.ket = this.c;
+      a = this.find_among_b(a_3);
+      if (a === 0) {
+        this.limit_backward = v_10;
+        break lab6;
+      }
+      this.bra = this.c;
+      this.limit_backward = v_10;
+      switch (a) {
+        case 1: {
+          this.slice_del();
+          break;
+        }
+        case 2: {
+          if (!this.in_grouping_b(g_ost_ending, 105, 118)) break lab6;
+          this.slice_from("\xF6s");
+          break;
+        }
+        case 3: {
+          this.slice_from("full");
+          break;
+        }
+      }
+    }
+    this.c = this.limit - v_9;
+    this.c = this.limit_backward;
+    return true;
   }
-  return word;
-}
-var STEP3_SUFFIXES = [
-  ["fullt", "full"],
-  ["l\xF6st", "l\xF6s"],
-  ["lig", null],
-  ["els", null],
-  ["ig", null]
-];
-function step3(word, r1) {
-  for (const [suffix, replacement] of STEP3_SUFFIXES) {
-    if (!word.endsWith(suffix)) continue;
-    const boundary = word.length - suffix.length;
-    if (boundary < r1) continue;
-    return replacement ? word.slice(0, boundary) + replacement : word.slice(0, boundary);
+  stem(input) {
+    this.setCurrent(input);
+    this.#stem();
+    return this.getCurrent();
   }
-  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;
+};
+var shared = new SwedishStemmer();
+function stem(token) {
+  return shared.stem(token);
 }
+
+// src/languages/swedish.ts
 var stopWords = /* @__PURE__ */ new Set([
   "och",
   "det",
@@ -203,7 +344,7 @@ var stopWords = /* @__PURE__ */ new Set([
   "ditt",
   "vem",
   "vilket",
-  "sitta",
+  "sitt",
   "s\xE5dana",
   "vart",
   "dina",
@@ -216,9 +357,10 @@ var stopWords = /* @__PURE__ */ new Set([
 ]);
 var swedish = {
   name: "swedish",
+  revision: "5ff576fe6e2b2a68",
   stemmer: stem,
   stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9åäöü-]+/gi }
+  tokenizer: { splitPattern: /[^a-z0-9åäöüé-]+/gi }
 };
 
 export { swedish };

package/dist/languages/tagalog.d.ts

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

package/dist/languages/tagalog.mjs

@@ -0,0 +1,159 @@
+// src/languages/tagalog.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "akin",
+  "aking",
+  "ako",
+  "alin",
+  "am",
+  "amin",
+  "aming",
+  "ang",
+  "ano",
+  "anumang",
+  "apat",
+  "at",
+  "atin",
+  "ating",
+  "ay",
+  "bababa",
+  "bago",
+  "bakit",
+  "bawat",
+  "bilang",
+  "dahil",
+  "dalawa",
+  "dapat",
+  "din",
+  "dito",
+  "doon",
+  "gagawin",
+  "gayunman",
+  "ginagawa",
+  "ginawa",
+  "ginawang",
+  "gumawa",
+  "gusto",
+  "habang",
+  "hanggang",
+  "hindi",
+  "huwag",
+  "iba",
+  "ibaba",
+  "ibabaw",
+  "ibig",
+  "ikaw",
+  "ilagay",
+  "ilalim",
+  "ilan",
+  "inyong",
+  "isa",
+  "isang",
+  "itaas",
+  "ito",
+  "iyo",
+  "iyon",
+  "iyong",
+  "ka",
+  "kahit",
+  "kailangan",
+  "kailanman",
+  "kami",
+  "kanila",
+  "kanilang",
+  "kanino",
+  "kanya",
+  "kanyang",
+  "kapag",
+  "kapwa",
+  "karamihan",
+  "katiyakan",
+  "katulad",
+  "kaya",
+  "kaysa",
+  "ko",
+  "kong",
+  "kulang",
+  "kumuha",
+  "kung",
+  "laban",
+  "lahat",
+  "lamang",
+  "likod",
+  "lima",
+  "maaari",
+  "maaaring",
+  "maging",
+  "mahusay",
+  "makita",
+  "marami",
+  "marapat",
+  "masyado",
+  "may",
+  "mayroon",
+  "mga",
+  "minsan",
+  "mismo",
+  "mula",
+  "muli",
+  "na",
+  "nabanggit",
+  "naging",
+  "nagkaroon",
+  "nais",
+  "nakita",
+  "namin",
+  "napaka",
+  "narito",
+  "nasaan",
+  "ng",
+  "ngayon",
+  "ni",
+  "nila",
+  "nilang",
+  "nito",
+  "niya",
+  "niyang",
+  "noon",
+  "o",
+  "pa",
+  "paano",
+  "pababa",
+  "paggawa",
+  "pagitan",
+  "pagkakaroon",
+  "pagkatapos",
+  "palabas",
+  "pamamagitan",
+  "panahon",
+  "pangalawa",
+  "para",
+  "paraan",
+  "pareho",
+  "pataas",
+  "pero",
+  "pumunta",
+  "pumupunta",
+  "sa",
+  "saan",
+  "sabi",
+  "sabihin",
+  "sarili",
+  "sila",
+  "sino",
+  "siya",
+  "tatlo",
+  "tayo",
+  "tulad",
+  "tungkol",
+  "una",
+  "walang"
+]);
+var tagalog = {
+  name: "tagalog",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9]+/gi }
+};
+
+export { tagalog };

package/dist/languages/tamil.d.ts

@@ -1,4 +1,4 @@
-import { L as LanguageModule } from '../language-ONQ3iVDf.js';
+import { L as LanguageModule } from '../language-CmJBHf1j.js';
 
 declare const tamil: LanguageModule;