@delali/narsil 0.1.15 → 0.2.1-next.25

package/dist/languages/russian.d.ts

@@ -1,5 +1,14 @@
-import { L as LanguageModule } from '../language-ONQ3iVDf.js';
+import { L as LanguageModule } from '../language-DB8KG1z5.js';
 
+/**
+ * Russian analysis: the Snowball stemmer, the stop word list, and the rules
+ * that split Russian text into tokens.
+ *
+ * Import it and pass it to {@link registerLanguage} before you create an index
+ * whose `language` is `russian`.
+ *
+ * @public
+ */
 declare const russian: LanguageModule;
 
 export { russian };

package/dist/languages/russian.mjs

@@ -1,258 +1,386 @@
-// src/languages/russian.ts
-var VOWELS = "\u0430\u0435\u0438\u043E\u0443\u044B\u044D\u044E\u044F";
-function isVowel(ch) {
-  return VOWELS.includes(ch);
-}
-function findRegions(word) {
-  let rv = word.length;
-  let r1 = word.length;
-  let r2 = word.length;
-  for (let i = 0; i < word.length; i++) {
-    if (isVowel(word[i])) {
-      rv = i + 1;
-      break;
-    }
-  }
-  for (let i = 1; i < word.length; i++) {
-    if (!isVowel(word[i]) && isVowel(word[i - 1])) {
-      r1 = i + 1;
+import { BaseStemmer } from '../chunk-U2BKYEC7.mjs';
+
+// src/languages/snowball/russian.ts
+var a_0 = [
+  ["\u0432", 1],
+  ["\u0438\u0432", 2, 1],
+  ["\u044B\u0432", 2, 2],
+  ["\u0432\u0448\u0438", 1],
+  ["\u0438\u0432\u0448\u0438", 2, 1],
+  ["\u044B\u0432\u0448\u0438", 2, 2],
+  ["\u0432\u0448\u0438\u0441\u044C", 1],
+  ["\u0438\u0432\u0448\u0438\u0441\u044C", 2, 1],
+  ["\u044B\u0432\u0448\u0438\u0441\u044C", 2, 2]
+];
+var a_1 = [
+  ["\u0435\u0435", 1],
+  ["\u0438\u0435", 1],
+  ["\u043E\u0435", 1],
+  ["\u044B\u0435", 1],
+  ["\u0438\u043C\u0438", 1],
+  ["\u044B\u043C\u0438", 1],
+  ["\u0435\u0439", 1],
+  ["\u0438\u0439", 1],
+  ["\u043E\u0439", 1],
+  ["\u044B\u0439", 1],
+  ["\u0435\u043C", 1],
+  ["\u0438\u043C", 1],
+  ["\u043E\u043C", 1],
+  ["\u044B\u043C", 1],
+  ["\u0435\u0433\u043E", 1],
+  ["\u043E\u0433\u043E", 1],
+  ["\u0435\u043C\u0443", 1],
+  ["\u043E\u043C\u0443", 1],
+  ["\u0438\u0445", 1],
+  ["\u044B\u0445", 1],
+  ["\u0435\u044E", 1],
+  ["\u043E\u044E", 1],
+  ["\u0443\u044E", 1],
+  ["\u044E\u044E", 1],
+  ["\u0430\u044F", 1],
+  ["\u044F\u044F", 1]
+];
+var a_2 = [
+  ["\u0435\u043C", 1],
+  ["\u043D\u043D", 1],
+  ["\u0432\u0448", 1],
+  ["\u0438\u0432\u0448", 2, 1],
+  ["\u044B\u0432\u0448", 2, 2],
+  ["\u0449", 1],
+  ["\u044E\u0449", 1, 1],
+  ["\u0443\u044E\u0449", 2, 1]
+];
+var a_3 = [
+  ["\u0441\u044C", 1],
+  ["\u0441\u044F", 1]
+];
+var a_4 = [
+  ["\u043B\u0430", 1],
+  ["\u0438\u043B\u0430", 2, 1],
+  ["\u044B\u043B\u0430", 2, 2],
+  ["\u043D\u0430", 1],
+  ["\u0435\u043D\u0430", 2, 1],
+  ["\u0435\u0442\u0435", 1],
+  ["\u0438\u0442\u0435", 2],
+  ["\u0439\u0442\u0435", 1],
+  ["\u0435\u0439\u0442\u0435", 2, 1],
+  ["\u0443\u0439\u0442\u0435", 2, 2],
+  ["\u043B\u0438", 1],
+  ["\u0438\u043B\u0438", 2, 1],
+  ["\u044B\u043B\u0438", 2, 2],
+  ["\u0439", 1],
+  ["\u0435\u0439", 2, 1],
+  ["\u0443\u0439", 2, 2],
+  ["\u043B", 1],
+  ["\u0438\u043B", 2, 1],
+  ["\u044B\u043B", 2, 2],
+  ["\u0435\u043C", 1],
+  ["\u0438\u043C", 2],
+  ["\u044B\u043C", 2],
+  ["\u043D", 1],
+  ["\u0435\u043D", 2, 1],
+  ["\u043B\u043E", 1],
+  ["\u0438\u043B\u043E", 2, 1],
+  ["\u044B\u043B\u043E", 2, 2],
+  ["\u043D\u043E", 1],
+  ["\u0435\u043D\u043E", 2, 1],
+  ["\u043D\u043D\u043E", 1, 2],
+  ["\u0435\u0442", 1],
+  ["\u0443\u0435\u0442", 2, 1],
+  ["\u0438\u0442", 2],
+  ["\u044B\u0442", 2],
+  ["\u044E\u0442", 1],
+  ["\u0443\u044E\u0442", 2, 1],
+  ["\u044F\u0442", 2],
+  ["\u043D\u044B", 1],
+  ["\u0435\u043D\u044B", 2, 1],
+  ["\u0442\u044C", 1],
+  ["\u0438\u0442\u044C", 2, 1],
+  ["\u044B\u0442\u044C", 2, 2],
+  ["\u0435\u0448\u044C", 1],
+  ["\u0438\u0448\u044C", 2],
+  ["\u044E", 2],
+  ["\u0443\u044E", 2, 1]
+];
+var a_5 = [
+  ["\u0430", 1],
+  ["\u0435\u0432", 1],
+  ["\u043E\u0432", 1],
+  ["\u0435", 1],
+  ["\u0438\u0435", 1, 1],
+  ["\u044C\u0435", 1, 2],
+  ["\u0438", 1],
+  ["\u0435\u0438", 1, 1],
+  ["\u0438\u0438", 1, 2],
+  ["\u0430\u043C\u0438", 1, 3],
+  ["\u044F\u043C\u0438", 1, 4],
+  ["\u0438\u044F\u043C\u0438", 1, 1],
+  ["\u0439", 1],
+  ["\u0435\u0439", 1, 1],
+  ["\u0438\u0435\u0439", 1, 1],
+  ["\u0438\u0439", 1, 3],
+  ["\u043E\u0439", 1, 4],
+  ["\u0430\u043C", 1],
+  ["\u0435\u043C", 1],
+  ["\u0438\u0435\u043C", 1, 1],
+  ["\u043E\u043C", 1],
+  ["\u044F\u043C", 1],
+  ["\u0438\u044F\u043C", 1, 1],
+  ["\u043E", 1],
+  ["\u0443", 1],
+  ["\u0430\u0445", 1],
+  ["\u044F\u0445", 1],
+  ["\u0438\u044F\u0445", 1, 1],
+  ["\u044B", 1],
+  ["\u044C", 1],
+  ["\u044E", 1],
+  ["\u0438\u044E", 1, 1],
+  ["\u044C\u044E", 1, 2],
+  ["\u044F", 1],
+  ["\u0438\u044F", 1, 1],
+  ["\u044C\u044F", 1, 2]
+];
+var a_6 = [
+  ["\u043E\u0441\u0442", 1],
+  ["\u043E\u0441\u0442\u044C", 1]
+];
+var a_7 = [
+  ["\u0435\u0439\u0448\u0435", 1],
+  ["\u043D", 2],
+  ["\u0435\u0439\u0448", 1],
+  ["\u044C", 3]
+];
+var g_v = [33, 65, 8, 232];
+var RussianStemmer = class extends BaseStemmer {
+  #stem() {
+    let a;
+    let I_p2;
+    let I_pV;
+    const v_1 = this.c;
+    while (true) {
+      const v_2 = this.c;
+      lab1: {
+        while (true) {
+          const v_3 = this.c;
+          lab3: {
+            this.bra = this.c;
+            if (!this.eq_s("\u0451")) break lab3;
+            this.ket = this.c;
+            this.c = v_3;
+            break;
+          }
+          this.c = v_3;
+          if (this.c >= this.limit) break lab1;
+          this.c++;
+        }
+        this.slice_from("\u0435");
+        continue;
+      }
+      this.c = v_2;
       break;
     }
-  }
-  for (let i = r1 + 1; i < word.length; i++) {
-    if (!isVowel(word[i]) && isVowel(word[i - 1])) {
-      r2 = i + 1;
-      break;
+    this.c = v_1;
+    {
+      I_pV = this.limit;
+      I_p2 = this.limit;
+      const v_4 = this.c;
+      lab5: {
+        if (!this.go_out_grouping(g_v, 1072, 1103)) break lab5;
+        this.c++;
+        I_pV = this.c;
+        if (!this.go_in_grouping(g_v, 1072, 1103)) break lab5;
+        this.c++;
+        if (!this.go_out_grouping(g_v, 1072, 1103)) break lab5;
+        this.c++;
+        if (!this.go_in_grouping(g_v, 1072, 1103)) break lab5;
+        this.c++;
+        I_p2 = this.c;
+      }
+      this.c = v_4;
     }
-  }
-  return { rv, r1, r2 };
-}
-function removeSuffix(word, suffix, regionStart) {
-  if (!word.endsWith(suffix)) return null;
-  if (word.length - suffix.length < regionStart) return null;
-  return word.slice(0, word.length - suffix.length);
-}
-function findAndRemoveSuffix(word, suffixes, regionStart) {
-  for (const suffix of suffixes) {
-    const result = removeSuffix(word, suffix, regionStart);
-    if (result !== null) return result;
-  }
-  return null;
-}
-var PERFECTIVE_GERUND_GROUP1 = ["\u0432", "\u0432\u0448\u0438", "\u0432\u0448\u0438\u0441\u044C"];
-var PERFECTIVE_GERUND_GROUP2 = ["\u0438\u0432", "\u0438\u0432\u0448\u0438", "\u0438\u0432\u0448\u0438\u0441\u044C", "\u044B\u0432", "\u044B\u0432\u0448\u0438", "\u044B\u0432\u0448\u0438\u0441\u044C"];
-function removePerfectiveGerund(word, rv) {
-  for (const suffix of PERFECTIVE_GERUND_GROUP1) {
-    if (word.endsWith(suffix) && word.length - suffix.length >= rv) {
-      const base = word.slice(0, word.length - suffix.length);
-      if (base.endsWith("\u0430") || base.endsWith("\u044F")) {
-        return base;
+    this.limit_backward = this.c;
+    this.c = this.limit;
+    if (this.c < I_pV) return false;
+    const v_5 = this.limit_backward;
+    this.limit_backward = I_pV;
+    const v_6 = this.limit - this.c;
+    lab6: {
+      lab7: {
+        const v_7 = this.limit - this.c;
+        lab8: {
+          this.ket = this.c;
+          a = this.find_among_b(a_0);
+          if (a === 0) break lab8;
+          this.bra = this.c;
+          switch (a) {
+            case 1: {
+              lab9: {
+                lab10: {
+                  if (!this.eq_s_b("\u0430")) break lab10;
+                  break lab9;
+                }
+                if (!this.eq_s_b("\u044F")) break lab8;
+              }
+              this.slice_del();
+              break;
+            }
+            case 2: {
+              this.slice_del();
+              break;
+            }
+          }
+          break lab7;
+        }
+        this.c = this.limit - v_7;
+        const v_8 = this.limit - this.c;
+        lab11: {
+          this.ket = this.c;
+          if (this.find_among_b(a_3) === 0) {
+            this.c = this.limit - v_8;
+            break lab11;
+          }
+          this.bra = this.c;
+          this.slice_del();
+        }
+        lab12: {
+          const v_9 = this.limit - this.c;
+          lab13: {
+            this.ket = this.c;
+            if (this.find_among_b(a_1) === 0) break lab13;
+            this.bra = this.c;
+            this.slice_del();
+            const v_10 = this.limit - this.c;
+            lab14: {
+              this.ket = this.c;
+              a = this.find_among_b(a_2);
+              if (a === 0) {
+                this.c = this.limit - v_10;
+                break lab14;
+              }
+              this.bra = this.c;
+              switch (a) {
+                case 1: {
+                  lab15: {
+                    lab16: {
+                      if (!this.eq_s_b("\u0430")) break lab16;
+                      break lab15;
+                    }
+                    if (!this.eq_s_b("\u044F")) {
+                      this.c = this.limit - v_10;
+                      break lab14;
+                    }
+                  }
+                  this.slice_del();
+                  break;
+                }
+                case 2: {
+                  this.slice_del();
+                  break;
+                }
+              }
+            }
+            break lab12;
+          }
+          this.c = this.limit - v_9;
+          lab17: {
+            this.ket = this.c;
+            a = this.find_among_b(a_4);
+            if (a === 0) break lab17;
+            this.bra = this.c;
+            switch (a) {
+              case 1: {
+                lab18: {
+                  lab19: {
+                    if (!this.eq_s_b("\u0430")) break lab19;
+                    break lab18;
+                  }
+                  if (!this.eq_s_b("\u044F")) break lab17;
+                }
+                this.slice_del();
+                break;
+              }
+              case 2: {
+                this.slice_del();
+                break;
+              }
+            }
+            break lab12;
+          }
+          this.c = this.limit - v_9;
+          this.ket = this.c;
+          if (this.find_among_b(a_5) === 0) break lab6;
+          this.bra = this.c;
+          this.slice_del();
+        }
       }
     }
-  }
-  return findAndRemoveSuffix(word, PERFECTIVE_GERUND_GROUP2, rv);
-}
-var REFLEXIVE_SUFFIXES = ["\u0441\u044F", "\u0441\u044C"];
-function removeReflexive(word, rv) {
-  return findAndRemoveSuffix(word, REFLEXIVE_SUFFIXES, rv);
-}
-var ADJECTIVE_SUFFIXES = [
-  "\u0438\u043C\u0438",
-  "\u044B\u043C\u0438",
-  "\u0435\u0433\u043E",
-  "\u043E\u0433\u043E",
-  "\u0435\u043C\u0443",
-  "\u043E\u043C\u0443",
-  "\u0435\u0435",
-  "\u0438\u0435",
-  "\u043E\u0435",
-  "\u044B\u0435",
-  "\u0435\u0439",
-  "\u0438\u0439",
-  "\u043E\u0439",
-  "\u044B\u0439",
-  "\u0435\u043C",
-  "\u0438\u043C",
-  "\u043E\u043C",
-  "\u044B\u043C",
-  "\u0438\u0445",
-  "\u044B\u0445",
-  "\u0435\u044E",
-  "\u043E\u044E",
-  "\u0443\u044E",
-  "\u044E\u044E",
-  "\u0430\u044F",
-  "\u044F\u044F"
-];
-var PARTICIPLE_GROUP1 = ["\u0435\u043C", "\u043D\u043D", "\u0432\u0448", "\u044E\u0449", "\u0449"];
-var PARTICIPLE_GROUP2 = ["\u0438\u0432\u0448", "\u044B\u0432\u0448", "\u0443\u044E\u0449"];
-function removeAdjectival(word, rv) {
-  const adjResult = findAndRemoveSuffix(word, ADJECTIVE_SUFFIXES, rv);
-  if (adjResult === null) return null;
-  for (const suffix of PARTICIPLE_GROUP1) {
-    if (adjResult.endsWith(suffix) && adjResult.length - suffix.length >= rv) {
-      const base = adjResult.slice(0, adjResult.length - suffix.length);
-      if (base.endsWith("\u0430") || base.endsWith("\u044F")) {
-        return base;
+    this.c = this.limit - v_6;
+    const v_11 = this.limit - this.c;
+    lab20: {
+      this.ket = this.c;
+      if (!this.eq_s_b("\u0438")) {
+        this.c = this.limit - v_11;
+        break lab20;
       }
+      this.bra = this.c;
+      this.slice_del();
     }
-  }
-  const partResult = findAndRemoveSuffix(adjResult, PARTICIPLE_GROUP2, rv);
-  if (partResult !== null) return partResult;
-  return adjResult;
-}
-var VERB_GROUP1 = [
-  "\u043B\u0430",
-  "\u043D\u0430",
-  "\u0435\u0442\u0435",
-  "\u0439\u0442\u0435",
-  "\u043B\u0438",
-  "\u0439",
-  "\u043B",
-  "\u0435\u043C",
-  "\u043D",
-  "\u043B\u043E",
-  "\u043D\u043E",
-  "\u0435\u0442",
-  "\u044E\u0442",
-  "\u043D\u044B",
-  "\u0442\u044C",
-  "\u0435\u0448\u044C",
-  "\u043D\u043D\u043E"
-];
-var VERB_GROUP2 = [
-  "\u0438\u043B\u0430",
-  "\u044B\u043B\u0430",
-  "\u0435\u043D\u0430",
-  "\u0435\u0439\u0442\u0435",
-  "\u0443\u0439\u0442\u0435",
-  "\u0438\u0442\u0435",
-  "\u0438\u043B\u0438",
-  "\u044B\u043B\u0438",
-  "\u0435\u0439",
-  "\u0443\u0439",
-  "\u0438\u043B",
-  "\u044B\u043B",
-  "\u0438\u043C",
-  "\u044B\u043C",
-  "\u0435\u043D",
-  "\u0438\u043B\u043E",
-  "\u044B\u043B\u043E",
-  "\u0435\u043D\u043E",
-  "\u044F\u0442",
-  "\u0443\u0435\u0442",
-  "\u0443\u044E\u0442",
-  "\u0438\u0442",
-  "\u044B\u0442",
-  "\u0435\u043D\u044B",
-  "\u0438\u0442\u044C",
-  "\u044B\u0442\u044C",
-  "\u0438\u0448\u044C",
-  "\u0443\u044E",
-  "\u044E"
-];
-function removeVerb(word, rv) {
-  for (const suffix of VERB_GROUP1) {
-    if (word.endsWith(suffix) && word.length - suffix.length >= rv) {
-      const base = word.slice(0, word.length - suffix.length);
-      if (base.endsWith("\u0430") || base.endsWith("\u044F")) {
-        return base;
+    const v_12 = this.limit - this.c;
+    lab21: {
+      this.ket = this.c;
+      if (this.find_among_b(a_6) === 0) break lab21;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p2 > this.c
+      ) break lab21;
+      this.slice_del();
+    }
+    this.c = this.limit - v_12;
+    const v_13 = this.limit - this.c;
+    lab22: {
+      this.ket = this.c;
+      a = this.find_among_b(a_7);
+      if (a === 0) break lab22;
+      this.bra = this.c;
+      switch (a) {
+        case 1: {
+          this.slice_del();
+          this.ket = this.c;
+          if (!this.eq_s_b("\u043D")) break lab22;
+          this.bra = this.c;
+          if (!this.eq_s_b("\u043D")) break lab22;
+          this.slice_del();
+          break;
+        }
+        case 2: {
+          if (!this.eq_s_b("\u043D")) break lab22;
+          this.slice_del();
+          break;
+        }
+        case 3: {
+          this.slice_del();
+          break;
+        }
       }
     }
+    this.c = this.limit - v_13;
+    this.limit_backward = v_5;
+    this.c = this.limit_backward;
+    return true;
   }
-  return findAndRemoveSuffix(word, VERB_GROUP2, rv);
-}
-var NOUN_SUFFIXES = [
-  "\u0438\u044F\u043C\u0438",
-  "\u044F\u043C\u0438",
-  "\u0438\u044F\u043C",
-  "\u0438\u0435\u0439",
-  "\u0438\u0435\u043C",
-  "\u0430\u043C\u0438",
-  "\u0438\u0438",
-  "\u0435\u0432",
-  "\u043E\u0432",
-  "\u0438\u0435",
-  "\u044C\u0435",
-  "\u0435\u0438",
-  "\u0435\u0439",
-  "\u0438\u0439",
-  "\u043E\u0439",
-  "\u0430\u043C",
-  "\u044F\u043C",
-  "\u0435\u043C",
-  "\u043E\u043C",
-  "\u044F\u0445",
-  "\u0430\u0445",
-  "\u0438\u044E",
-  "\u044C\u044E",
-  "\u0438\u044F",
-  "\u044C\u044F",
-  "\u0430",
-  "\u0435",
-  "\u0438",
-  "\u043E",
-  "\u0443",
-  "\u044B",
-  "\u044C",
-  "\u044E",
-  "\u044F"
-];
-function removeNoun(word, rv) {
-  return findAndRemoveSuffix(word, NOUN_SUFFIXES, rv);
-}
-var DERIVATIONAL_SUFFIXES = ["\u043E\u0441\u0442\u044C", "\u043E\u0441\u0442"];
-function removeDerivational(word, r2) {
-  const result = findAndRemoveSuffix(word, DERIVATIONAL_SUFFIXES, r2);
-  return result ?? word;
-}
-function step1(word, rv) {
-  const pgResult = removePerfectiveGerund(word, rv);
-  if (pgResult !== null) return pgResult;
-  const reflexResult = removeReflexive(word, rv);
-  const base = reflexResult ?? word;
-  const adjResult = removeAdjectival(base, rv);
-  if (adjResult !== null) return adjResult;
-  const verbResult = removeVerb(base, rv);
-  if (verbResult !== null) return verbResult;
-  const nounResult = removeNoun(base, rv);
-  if (nounResult !== null) return nounResult;
-  return base;
-}
-function step2(word, rv) {
-  if (word.endsWith("\u0438") && word.length - 1 >= rv) {
-    return word.slice(0, -1);
-  }
-  return word;
-}
-function step3(word, r2) {
-  return removeDerivational(word, r2);
-}
-function step4(word, rv) {
-  if (word.endsWith("\u0435\u0439\u0448\u0435") && word.length - 4 >= rv) {
-    return word.slice(0, -4);
-  }
-  if (word.endsWith("\u0435\u0439\u0448") && word.length - 3 >= rv) {
-    return word.slice(0, -3);
-  }
-  if (word.endsWith("\u043D\u043D") && word.length - 2 >= rv) {
-    return word.slice(0, -1);
-  }
-  if (word.endsWith("\u044C") && word.length - 1 >= rv) {
-    return word.slice(0, -1);
+  stem(input) {
+    this.setCurrent(input);
+    this.#stem();
+    return this.getCurrent();
   }
-  return word;
-}
-var RE_YO = /ё/g;
-function stem(word) {
-  word = word.replace(RE_YO, "\u0435");
-  const { rv, r2 } = findRegions(word);
-  word = step1(word, rv);
-  word = step2(word, rv);
-  word = step3(word, r2);
-  word = step4(word, rv);
-  return word;
+};
+var shared = new RussianStemmer();
+function stem(token) {
+  return shared.stem(token);
 }
+
+// src/languages/russian.ts
 var stopWords = /* @__PURE__ */ new Set([
   "\u0438",
   "\u0432",
@@ -416,9 +544,10 @@ var stopWords = /* @__PURE__ */ new Set([
 ]);
 var russian = {
   name: "russian",
+  revision: "87767119dd36215c",
   stemmer: stem,
   stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9а-яё]+/gi }
+  tokenizer: { splitPattern: /[^a-z0-9а-яёѣі-]+/gi }
 };
 
 export { russian };

package/dist/languages/samoan.d.ts

@@ -0,0 +1,15 @@
+import { L as LanguageModule } from '../language-DB8KG1z5.js';
+
+/**
+ * Samoan analysis: the stop word list and the rules that split Samoan
+ * text into tokens. Tokens are indexed as the normaliser leaves them,
+ * without stemming.
+ *
+ * Import it and pass it to {@link registerLanguage} before you create an index
+ * whose `language` is `samoan`.
+ *
+ * @public
+ */
+declare const samoan: LanguageModule;
+
+export { samoan };