@delali/narsil 0.1.14 → 0.2.0

package/dist/languages/icelandic.d.ts

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

package/dist/languages/icelandic.mjs

@@ -0,0 +1,161 @@
+// src/languages/icelandic.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "\xE6tti",
+  "afhverju",
+  "aftan",
+  "aftur",
+  "af\xFEv\xED",
+  "aldrei",
+  "allir",
+  "allt",
+  "alveg",
+  "anna\xF0",
+  "annars",
+  "bara",
+  "dag",
+  "e\xF0a",
+  "eftir",
+  "eiga",
+  "einhver",
+  "einhverjir",
+  "einhvers",
+  "eins",
+  "einu",
+  "eitthva\xF0",
+  "ekkert",
+  "ekki",
+  "enn\xFE\xE1",
+  "eru",
+  "fara",
+  "fer",
+  "finna",
+  "fj\xF6ldi",
+  "f\xF3lk",
+  "fr\xE1",
+  "framan",
+  "frekar",
+  "fyrir",
+  "gegnum",
+  "geta",
+  "getur",
+  "gmg",
+  "gott",
+  "h\xE6gt",
+  "hafa",
+  "hann",
+  "hef",
+  "hefur",
+  "h\xE9r",
+  "h\xE9rna",
+  "heyra",
+  "hj\xE1",
+  "h\xFAn",
+  "hva\xF0",
+  "hvar",
+  "hver",
+  "hverjir",
+  "hverjum",
+  "hvernig",
+  "hvor",
+  "hvort",
+  "img",
+  "inn",
+  "kannski",
+  "koma",
+  "l\xEDka",
+  "lol",
+  "ma\xF0ur",
+  "m\xE1tt",
+  "me\xF0",
+  "mega",
+  "meira",
+  "m\xE9r",
+  "mig",
+  "miki\xF0",
+  "minna",
+  "minni",
+  "missa",
+  "mj\xF6g",
+  "nei",
+  "ni\xF0ur",
+  "n\xFAna",
+  "oft",
+  "okkar",
+  "okkur",
+  "p\xF3st",
+  "p\xF3stur",
+  "rofl",
+  "s\xE6lir",
+  "s\xE6ll",
+  "saman",
+  "sem",
+  "s\xE9r",
+  "s\xED\xF0an",
+  "sig",
+  "sinni",
+  "sj\xE1",
+  "sm\xE1",
+  "sm\xE1tt",
+  "spurja",
+  "spyrja",
+  "sta\xF0ar",
+  "st\xF3rt",
+  "svo",
+  "svona",
+  "taka",
+  "takk",
+  "til",
+  "tilvitnun",
+  "titlar",
+  "upp",
+  "v\xE6ri",
+  "var",
+  "vel",
+  "velkomin",
+  "velkominn",
+  "vera",
+  "ver\xF0ur",
+  "veri\xF0",
+  "vi\xF0",
+  "vil",
+  "vilja",
+  "vill",
+  "vita",
+  "yfir",
+  "ykkar",
+  "\xFEa\xF0",
+  "\xFE\xE6r",
+  "\xFEakka",
+  "\xFEakkir",
+  "\xFEannig",
+  "\xFEar",
+  "\xFEarf",
+  "\xFEau",
+  "\xFEegar",
+  "\xFEeim",
+  "\xFEeir",
+  "\xFEeirra",
+  "\xFE\xE9r",
+  "\xFEess",
+  "\xFEessa",
+  "\xFEessi",
+  "\xFEessu",
+  "\xFEessum",
+  "\xFEetta",
+  "\xFEi\xF0",
+  "\xFE\xEDn",
+  "\xFEinn",
+  "\xFEitt",
+  "\xFEr\xE1\xF0",
+  "\xFEr\xE1\xF0ur",
+  "\xFEv\xED"
+]);
+var icelandic = {
+  name: "icelandic",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9áæéíðóöúþý]+/gi }
+};
+
+export { icelandic };

package/dist/languages/igbo.d.ts

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

package/dist/languages/igbo.mjs

@@ -84,10 +84,11 @@ var stopWords = /* @__PURE__ */ new Set([
 ]);
 var igbo = {
   name: "igbo",
+  revision: "1",
   stemmer: null,
   stopWords,
   tokenizer: {
-    splitPattern: /[^a-zA-ZịụọṅĩỊỤỌṄĨ0-9\p{M}]+/giu,
+    splitPattern: /[^a-zA-ZịụọṅĩũỊỤỌṄĨŨàèéòóÀÈÉÒÓȮȯ0-9\p{M}]+/giu,
     normalizeDiacritics: false,
     minTokenLength: 1
   }

package/dist/languages/indonesian.d.ts

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

package/dist/languages/indonesian.mjs

@@ -1,153 +1,344 @@
-// src/languages/indonesian.ts
-var VOWELS = /* @__PURE__ */ new Set(["a", "e", "i", "o", "u"]);
-function countVowels(word) {
-  let count = 0;
-  for (const ch of word) {
-    if (VOWELS.has(ch)) count++;
-  }
-  return count;
-}
-function removeParticle(word) {
-  for (const suffix of ["kah", "lah", "tah", "pun"]) {
-    if (word.endsWith(suffix)) {
-      return { word: word.slice(0, -suffix.length), removed: 1 };
-    }
-  }
-  return { word, removed: 0 };
-}
-function removePossessivePronoun(word) {
-  if (word.endsWith("nya")) return { word: word.slice(0, -3), removed: 1 };
-  if (word.endsWith("ku")) return { word: word.slice(0, -2), removed: 1 };
-  if (word.endsWith("mu")) return { word: word.slice(0, -2), removed: 1 };
-  return { word, removed: 0 };
-}
-function removeFirstPrefix(word) {
-  if (word.startsWith("di") && word.length > 4) {
-    return { word: word.slice(2), prefixType: 1 };
-  }
-  if (word.startsWith("ke") && word.length > 4) {
-    return { word: word.slice(2), prefixType: 1 };
-  }
-  if (word.startsWith("se") && word.length > 4) {
-    return { word: word.slice(2), prefixType: 1 };
-  }
-  if (word.startsWith("me")) {
-    if (word.startsWith("meng") && word.length > 6) {
-      return { word: word.slice(4), prefixType: 1 };
-    }
-    if (word.startsWith("meny") && word.length > 6) {
-      return { word: `s${word.slice(4)}`, prefixType: 3 };
-    }
-    if (word.startsWith("men") && word.length > 5) {
-      return { word: word.slice(3), prefixType: 1 };
-    }
-    if (word.startsWith("mem") && word.length > 5) {
-      const rest = word.slice(3);
-      if (rest.length > 0 && VOWELS.has(rest[0])) {
-        return { word: `p${rest}`, prefixType: 5 };
+import { BaseStemmer } from '../chunk-U2BKYEC7.mjs';
+
+// src/languages/snowball/indonesian.ts
+var a_0 = [
+  ["kah", 1],
+  ["lah", 1],
+  ["pun", 1]
+];
+var a_1 = [
+  ["nya", 1],
+  ["ku", 1],
+  ["mu", 1]
+];
+var a_2 = [
+  ["i", 2],
+  ["an", 1]
+];
+var a_3 = [
+  ["di", 1],
+  ["ke", 3],
+  ["me", 1],
+  ["mem", 5, 1],
+  ["men", 2, 2],
+  ["meng", 1, 1],
+  ["pem", 6],
+  ["pen", 4],
+  ["peng", 3, 1],
+  ["ter", 1]
+];
+var a_4 = [
+  ["be", 2],
+  ["pe", 1]
+];
+var g_vowel = [17, 65, 16];
+var IndonesianStemmer = class extends BaseStemmer {
+  #I_prefix = 0;
+  #I_measure = 0;
+  #r_remove_suffix() {
+    let a;
+    this.ket = this.c;
+    a = this.find_among_b(a_2);
+    if (a === 0) return false;
+    this.bra = this.c;
+    switch (a) {
+      case 1: {
+        lab0: {
+          const v_1 = this.limit - this.c;
+          lab1: {
+            if (
+              /**@type {boolean}*/
+              this.#I_prefix === 3
+            ) break lab1;
+            if (
+              /**@type {boolean}*/
+              this.#I_prefix === 2
+            ) break lab1;
+            if (!this.eq_s_b("k")) break lab1;
+            this.bra = this.c;
+            break lab0;
+          }
+          this.c = this.limit - v_1;
+          if (
+            /**@type {boolean}*/
+            this.#I_prefix === 1
+          ) return false;
+        }
+        break;
       }
-      return { word: rest, prefixType: 1 };
-    }
-    if (word.startsWith("me") && word.length > 4) {
-      return { word: word.slice(2), prefixType: 1 };
-    }
-  }
-  if (word.startsWith("pe")) {
-    if (word.startsWith("peng") && word.length > 6) {
-      return { word: word.slice(4), prefixType: 2 };
-    }
-    if (word.startsWith("peny") && word.length > 6) {
-      return { word: `s${word.slice(4)}`, prefixType: 4 };
-    }
-    if (word.startsWith("pen") && word.length > 5) {
-      return { word: word.slice(3), prefixType: 2 };
-    }
-    if (word.startsWith("pem") && word.length > 5) {
-      const rest = word.slice(3);
-      if (rest.length > 0 && VOWELS.has(rest[0])) {
-        return { word: `p${rest}`, prefixType: 6 };
+      case 2: {
+        if (
+          /**@type {boolean}*/
+          this.#I_prefix > 2
+        ) return false;
+        lab2: {
+          if (!this.eq_s_b("s")) break lab2;
+          return false;
+        }
+        break;
       }
-      return { word: rest, prefixType: 2 };
-    }
-    if (word === "pelajar" || word.startsWith("pelajar")) {
-      return { word: word.slice(3), prefixType: 1 };
-    }
-    if (word.startsWith("pe") && word.length > 4) {
-      return { word: word.slice(2), prefixType: 2 };
     }
+    this.slice_del();
+    --this.#I_measure;
+    return true;
   }
-  if (word.startsWith("ter") && word.length > 5) {
-    return { word: word.slice(3), prefixType: 1 };
-  }
-  if (word.startsWith("belajar")) {
-    return { word: word.slice(3), prefixType: 3 };
-  }
-  if (word.startsWith("ber") && word.length > 5) {
-    return { word: word.slice(3), prefixType: 3 };
-  }
-  if (word.startsWith("per") && word.length > 5) {
-    return { word: word.slice(3), prefixType: 1 };
-  }
-  return { word, prefixType: 0 };
-}
-function removeDerivationalSuffix(word, prefixType) {
-  if (word.endsWith("kan") && word.length > 5) {
-    if (prefixType !== 3 && prefixType !== 2) {
-      return word.slice(0, -3);
+  #r_remove_second_order_prefix() {
+    let a;
+    this.bra = this.c;
+    a = this.find_among(a_4);
+    if (a === 0) return false;
+    switch (a) {
+      case 1: {
+        lab0: {
+          const v_1 = this.c;
+          lab1: {
+            if (!this.eq_s("r")) break lab1;
+            this.ket = this.c;
+            this.#I_prefix = 2;
+            break lab0;
+          }
+          this.c = v_1;
+          lab2: {
+            if (!this.eq_s("l")) break lab2;
+            this.ket = this.c;
+            if (!this.eq_s("ajar")) break lab2;
+            break lab0;
+          }
+          this.c = v_1;
+          this.ket = this.c;
+          this.#I_prefix = 2;
+        }
+        break;
+      }
+      case 2: {
+        lab3: {
+          const v_2 = this.c;
+          lab4: {
+            if (!this.eq_s("r")) break lab4;
+            this.ket = this.c;
+            break lab3;
+          }
+          this.c = v_2;
+          lab5: {
+            if (!this.eq_s("l")) break lab5;
+            this.ket = this.c;
+            if (!this.eq_s("ajar")) break lab5;
+            break lab3;
+          }
+          this.c = v_2;
+          this.ket = this.c;
+          if (!this.out_grouping(g_vowel, 97, 117)) return false;
+          if (!this.eq_s("er")) return false;
+        }
+        this.#I_prefix = 4;
+        break;
+      }
     }
+    --this.#I_measure;
+    this.slice_del();
+    return true;
   }
-  if (word.endsWith("an") && word.length > 4) {
-    if (prefixType !== 1) {
-      return word.slice(0, -2);
+  #stem() {
+    let a;
+    this.#I_measure = 0;
+    const v_1 = this.c;
+    while (true) {
+      const v_2 = this.c;
+      lab1: {
+        if (!this.go_out_grouping(g_vowel, 97, 117)) break lab1;
+        this.c++;
+        ++this.#I_measure;
+        continue;
+      }
+      this.c = v_2;
+      break;
     }
-  }
-  if (word.endsWith("i") && word.length > 3) {
-    const beforeI = word[word.length - 2];
-    if (beforeI !== "s" && prefixType <= 2) {
-      return word.slice(0, -1);
+    this.c = v_1;
+    if (
+      /**@type {boolean}*/
+      this.#I_measure < 3
+    ) return false;
+    this.#I_prefix = 0;
+    this.limit_backward = this.c;
+    this.c = this.limit;
+    const v_3 = this.limit - this.c;
+    lab2: {
+      this.ket = this.c;
+      if (this.find_among_b(a_0) === 0) break lab2;
+      this.bra = this.c;
+      this.slice_del();
+      --this.#I_measure;
     }
-  }
-  return word;
-}
-function stem(input) {
-  let word = input.toLowerCase();
-  if (countVowels(word) < 3) return word;
-  const original = word;
-  const particle = removeParticle(word);
-  word = particle.word;
-  const possessive = removePossessivePronoun(word);
-  word = possessive.word;
-  if (countVowels(word) < 2) return original;
-  const withPrefix = removeFirstPrefix(word);
-  let prefixType = withPrefix.prefixType;
-  const afterPrefix = withPrefix.word;
-  if (prefixType > 0 && countVowels(afterPrefix) >= 2) {
-    word = afterPrefix;
-    const withSuffix = removeDerivationalSuffix(word, prefixType);
-    if (withSuffix !== word && countVowels(withSuffix) >= 2) {
-      word = withSuffix;
+    this.c = this.limit - v_3;
+    if (
+      /**@type {boolean}*/
+      this.#I_measure < 3
+    ) return false;
+    const v_4 = this.limit - this.c;
+    lab3: {
+      this.ket = this.c;
+      if (this.find_among_b(a_1) === 0) break lab3;
+      this.bra = this.c;
+      this.slice_del();
+      --this.#I_measure;
     }
-  } else {
-    word = possessive.word;
-    const withSuffix = removeDerivationalSuffix(word, 0);
-    if (withSuffix !== word && countVowels(withSuffix) >= 2) {
-      word = withSuffix;
-      const secondPrefix = removeFirstPrefix(word);
-      if (secondPrefix.prefixType > 0 && countVowels(secondPrefix.word) >= 2) {
-        word = secondPrefix.word;
-        prefixType = secondPrefix.prefixType;
+    this.c = this.limit - v_4;
+    this.c = this.limit_backward;
+    if (
+      /**@type {boolean}*/
+      this.#I_measure < 3
+    ) return false;
+    lab4: {
+      const v_5 = this.c;
+      lab5: {
+        const v_6 = this.c;
+        this.bra = this.c;
+        a = this.find_among(a_3);
+        if (a === 0) break lab5;
+        this.ket = this.c;
+        switch (a) {
+          case 1: {
+            this.slice_del();
+            this.#I_prefix = 1;
+            --this.#I_measure;
+            break;
+          }
+          case 2: {
+            lab6: {
+              const v_7 = this.c;
+              lab7: {
+                if (!this.eq_s("y")) break lab7;
+                const v_8 = this.c;
+                if (!this.in_grouping(g_vowel, 97, 117)) break lab7;
+                this.c = v_8;
+                this.ket = this.c;
+                this.slice_from("s");
+                this.#I_prefix = 1;
+                --this.#I_measure;
+                break lab6;
+              }
+              this.c = v_7;
+              this.slice_del();
+              this.#I_prefix = 1;
+              --this.#I_measure;
+            }
+            break;
+          }
+          case 3: {
+            this.slice_del();
+            this.#I_prefix = 3;
+            --this.#I_measure;
+            break;
+          }
+          case 4: {
+            lab8: {
+              const v_9 = this.c;
+              lab9: {
+                if (!this.eq_s("y")) break lab9;
+                const v_10 = this.c;
+                if (!this.in_grouping(g_vowel, 97, 117)) break lab9;
+                this.c = v_10;
+                this.ket = this.c;
+                this.slice_from("s");
+                this.#I_prefix = 3;
+                --this.#I_measure;
+                break lab8;
+              }
+              this.c = v_9;
+              this.slice_del();
+              this.#I_prefix = 3;
+              --this.#I_measure;
+            }
+            break;
+          }
+          case 5: {
+            this.#I_prefix = 1;
+            --this.#I_measure;
+            lab10: {
+              const v_11 = this.c;
+              lab11: {
+                const v_12 = this.c;
+                if (!this.in_grouping(g_vowel, 97, 117)) break lab11;
+                this.c = v_12;
+                this.slice_from("p");
+                break lab10;
+              }
+              this.c = v_11;
+              this.slice_del();
+            }
+            break;
+          }
+          case 6: {
+            this.#I_prefix = 3;
+            --this.#I_measure;
+            lab12: {
+              const v_13 = this.c;
+              lab13: {
+                const v_14 = this.c;
+                if (!this.in_grouping(g_vowel, 97, 117)) break lab13;
+                this.c = v_14;
+                this.slice_from("p");
+                break lab12;
+              }
+              this.c = v_13;
+              this.slice_del();
+            }
+            break;
+          }
+        }
+        const v_15 = this.c;
+        lab14: {
+          const v_16 = this.c;
+          if (
+            /**@type {boolean}*/
+            this.#I_measure < 3
+          ) break lab14;
+          this.limit_backward = this.c;
+          this.c = this.limit;
+          if (!this.#r_remove_suffix()) break lab14;
+          this.c = this.limit_backward;
+          this.c = v_16;
+          if (
+            /**@type {boolean}*/
+            this.#I_measure < 3
+          ) break lab14;
+          if (!this.#r_remove_second_order_prefix()) break lab14;
+        }
+        this.c = v_15;
+        this.c = v_6;
+        break lab4;
       }
-    } else {
-      word = afterPrefix;
-      prefixType = withPrefix.prefixType;
-      const suffixResult = removeDerivationalSuffix(word, prefixType);
-      if (suffixResult !== word && countVowels(suffixResult) >= 2) {
-        word = suffixResult;
+      this.c = v_5;
+      const v_17 = this.c;
+      this.#r_remove_second_order_prefix();
+      this.c = v_17;
+      const v_18 = this.c;
+      lab15: {
+        if (
+          /**@type {boolean}*/
+          this.#I_measure < 3
+        ) break lab15;
+        this.limit_backward = this.c;
+        this.c = this.limit;
+        if (!this.#r_remove_suffix()) break lab15;
+        this.c = this.limit_backward;
       }
+      this.c = v_18;
     }
+    return true;
   }
-  return word;
+  stem(input) {
+    this.setCurrent(input);
+    this.#stem();
+    return this.getCurrent();
+  }
+};
+var shared = new IndonesianStemmer();
+function stem(token) {
+  return shared.stem(token);
 }
+
+// src/languages/indonesian.ts
 var stopWords = /* @__PURE__ */ new Set([
   "ada",
   "adalah",
@@ -888,9 +1079,10 @@ var stopWords = /* @__PURE__ */ new Set([
 ]);
 var indonesian = {
   name: "indonesian",
+  revision: "c0b2b853663a1396",
   stemmer: stem,
   stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9]+/gi }
+  tokenizer: { splitPattern: /[^a-z0-9-]+/gi }
 };
 
 export { indonesian };