@delali/narsil 0.1.14 → 0.2.0

package/dist/languages/italian.mjs

@@ -1,427 +1,723 @@
-// src/languages/italian.ts
-var VOWELS = "aeiou\xE0\xE8\xE9\xEC\xF2\xF3\xF9";
-var RE_QU = /qu/g;
-function isVowel(ch) {
-  return VOWELS.includes(ch);
-}
-function findRegions(word) {
-  const length = word.length;
-  let rv = length;
-  if (length > 3) {
-    if (!isVowel(word[1])) {
-      for (let i = 2; i < length; i++) {
-        if (isVowel(word[i])) {
-          rv = i + 1;
-          break;
+import { BaseStemmer } from '../chunk-U2BKYEC7.mjs';
+
+// src/languages/snowball/italian.ts
+var a_0 = [
+  ["all'", -1],
+  ["d'", -1],
+  ["dall'", -1],
+  ["dell'", -1],
+  ["gl'", -1],
+  ["l'", -1],
+  ["m'", -1],
+  ["nell'", -1],
+  ["quell'", -1],
+  ["quest'", -1],
+  ["s'", -1],
+  ["sull'", -1],
+  ["t'", -1],
+  ["tutt'", -1],
+  ["un'", -1],
+  ["v'", -1]
+];
+var a_1 = [
+  ["", 7],
+  ["qu", 6, 1],
+  ["\xE1", 1, 2],
+  ["\xE9", 2, 3],
+  ["\xED", 3, 4],
+  ["\xF3", 4, 5],
+  ["\xFA", 5, 6]
+];
+var a_2 = [
+  ["", 3],
+  ["I", 1, 1],
+  ["U", 2, 2]
+];
+var a_3 = [
+  ["la", -1],
+  ["cela", -1, 1],
+  ["gliela", -1, 2],
+  ["mela", -1, 3],
+  ["tela", -1, 4],
+  ["vela", -1, 5],
+  ["le", -1],
+  ["cele", -1, 1],
+  ["gliele", -1, 2],
+  ["mele", -1, 3],
+  ["tele", -1, 4],
+  ["vele", -1, 5],
+  ["ne", -1],
+  ["cene", -1, 1],
+  ["gliene", -1, 2],
+  ["mene", -1, 3],
+  ["sene", -1, 4],
+  ["tene", -1, 5],
+  ["vene", -1, 6],
+  ["ci", -1],
+  ["li", -1],
+  ["celi", -1, 1],
+  ["glieli", -1, 2],
+  ["meli", -1, 3],
+  ["teli", -1, 4],
+  ["veli", -1, 5],
+  ["gli", -1, 6],
+  ["mi", -1],
+  ["si", -1],
+  ["ti", -1],
+  ["vi", -1],
+  ["lo", -1],
+  ["celo", -1, 1],
+  ["glielo", -1, 2],
+  ["melo", -1, 3],
+  ["telo", -1, 4],
+  ["velo", -1, 5]
+];
+var a_4 = [
+  ["ando", 1],
+  ["endo", 1],
+  ["ar", 2],
+  ["er", 2],
+  ["ir", 2]
+];
+var as_4 = ["", "e"];
+var a_5 = [
+  ["ic", -1],
+  ["abil", -1],
+  ["os", -1],
+  ["iv", 1]
+];
+var a_6 = [
+  ["ic", 1],
+  ["abil", 1],
+  ["iv", 1]
+];
+var a_7 = [
+  ["ica", 1],
+  ["logia", 3],
+  ["osa", 1],
+  ["ista", 1],
+  ["iva", 9],
+  ["anza", 1],
+  ["enza", 5],
+  ["ice", 1],
+  ["atrice", 1, 1],
+  ["iche", 1],
+  ["logie", 3],
+  ["abile", 1],
+  ["ibile", 1],
+  ["usione", 4],
+  ["azione", 2],
+  ["uzione", 4],
+  ["atore", 2],
+  ["ose", 1],
+  ["ante", 1],
+  ["mente", 1],
+  ["amente", 7, 1],
+  ["iste", 1],
+  ["ive", 9],
+  ["anze", 1],
+  ["enze", 5],
+  ["ici", 1],
+  ["atrici", 1, 1],
+  ["ichi", 1],
+  ["abili", 1],
+  ["ibili", 1],
+  ["ismi", 1],
+  ["usioni", 4],
+  ["azioni", 2],
+  ["uzioni", 4],
+  ["atori", 2],
+  ["osi", 1],
+  ["anti", 1],
+  ["amenti", 6],
+  ["imenti", 6],
+  ["isti", 1],
+  ["ivi", 9],
+  ["ico", 1],
+  ["ismo", 1],
+  ["oso", 1],
+  ["amento", 6],
+  ["imento", 6],
+  ["ivo", 9],
+  ["it\xE0", 8],
+  ["ist\xE0", 1],
+  ["ist\xE8", 1],
+  ["ist\xEC", 1]
+];
+var a_8 = [
+  ["isca", 1],
+  ["enda", 1],
+  ["ata", 1],
+  ["ita", 1],
+  ["uta", 1],
+  ["ava", 1],
+  ["eva", 1],
+  ["iva", 1],
+  ["erebbe", 1],
+  ["irebbe", 1],
+  ["isce", 1],
+  ["ende", 1],
+  ["are", 1],
+  ["ere", 1],
+  ["ire", 1],
+  ["asse", 1],
+  ["ate", 1],
+  ["avate", 1, 1],
+  ["evate", 1, 2],
+  ["ivate", 1, 3],
+  ["ete", 1],
+  ["erete", 1, 1],
+  ["irete", 1, 2],
+  ["ite", 1],
+  ["ereste", 1],
+  ["ireste", 1],
+  ["ute", 1],
+  ["erai", 1],
+  ["irai", 1],
+  ["isci", 1],
+  ["endi", 1],
+  ["erei", 1],
+  ["irei", 1],
+  ["assi", 1],
+  ["ati", 1],
+  ["iti", 1],
+  ["eresti", 1],
+  ["iresti", 1],
+  ["uti", 1],
+  ["avi", 1],
+  ["evi", 1],
+  ["ivi", 1],
+  ["isco", 1],
+  ["ando", 1],
+  ["endo", 1],
+  ["Yamo", 1],
+  ["iamo", 1],
+  ["avamo", 1],
+  ["evamo", 1],
+  ["ivamo", 1],
+  ["eremo", 1],
+  ["iremo", 1],
+  ["assimo", 1],
+  ["ammo", 1],
+  ["emmo", 1],
+  ["eremmo", 1, 1],
+  ["iremmo", 1, 2],
+  ["immo", 1],
+  ["ano", 1],
+  ["iscano", 1, 1],
+  ["avano", 1, 2],
+  ["evano", 1, 3],
+  ["ivano", 1, 4],
+  ["eranno", 1],
+  ["iranno", 1],
+  ["ono", 1],
+  ["iscono", 1, 1],
+  ["arono", 1, 2],
+  ["erono", 1, 3],
+  ["irono", 1, 4],
+  ["erebbero", 1],
+  ["irebbero", 1],
+  ["assero", 1],
+  ["essero", 1],
+  ["issero", 1],
+  ["ato", 1],
+  ["ito", 1],
+  ["uto", 1],
+  ["avo", 1],
+  ["evo", 1],
+  ["ivo", 1],
+  ["ar", 1],
+  ["ir", 1],
+  ["er\xE0", 1],
+  ["ir\xE0", 1],
+  ["er\xF2", 1],
+  ["ir\xF2", 1]
+];
+var g_v = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128, 128, 8, 2, 1];
+var g_AEIO = [17, 65, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128, 128, 8, 2];
+var g_CG = [17];
+var ItalianStemmer = class extends BaseStemmer {
+  #stem() {
+    let a;
+    let I_p2;
+    let I_p1;
+    let I_pV;
+    const v_1 = this.c;
+    lab0: {
+      this.bra = this.c;
+      if (this.find_among(a_0) === 0) break lab0;
+      this.ket = this.c;
+      if (
+        /**@type {boolean}*/
+        this.c >= this.limit
+      ) break lab0;
+      this.slice_del();
+    }
+    this.c = v_1;
+    const v_2 = this.c;
+    {
+      const v_3 = this.c;
+      while (true) {
+        const v_4 = this.c;
+        lab2: {
+          this.bra = this.c;
+          a = this.find_among(a_1);
+          this.ket = this.c;
+          switch (a) {
+            case 1: {
+              this.slice_from("\xE0");
+              break;
+            }
+            case 2: {
+              this.slice_from("\xE8");
+              break;
+            }
+            case 3: {
+              this.slice_from("\xEC");
+              break;
+            }
+            case 4: {
+              this.slice_from("\xF2");
+              break;
+            }
+            case 5: {
+              this.slice_from("\xF9");
+              break;
+            }
+            case 6: {
+              this.slice_from("qU");
+              break;
+            }
+            case 7: {
+              if (this.c >= this.limit) break lab2;
+              this.c++;
+              break;
+            }
+          }
+          continue;
         }
+        this.c = v_4;
+        break;
       }
-    } else if (isVowel(word[0]) && isVowel(word[1])) {
-      for (let i = 2; i < length; i++) {
-        if (!isVowel(word[i])) {
-          rv = i + 1;
-          break;
+      this.c = v_3;
+      while (true) {
+        const v_5 = this.c;
+        lab3: {
+          while (true) {
+            const v_6 = this.c;
+            lab5: {
+              if (!this.in_grouping(g_v, 97, 249)) break lab5;
+              this.bra = this.c;
+              lab6: {
+                const v_7 = this.c;
+                lab7: {
+                  if (!this.eq_s("u")) break lab7;
+                  this.ket = this.c;
+                  if (!this.in_grouping(g_v, 97, 249)) break lab7;
+                  this.slice_from("U");
+                  break lab6;
+                }
+                this.c = v_7;
+                if (!this.eq_s("i")) break lab5;
+                this.ket = this.c;
+                if (!this.in_grouping(g_v, 97, 249)) break lab5;
+                this.slice_from("I");
+              }
+              this.c = v_6;
+              break;
+            }
+            this.c = v_6;
+            if (this.c >= this.limit) break lab3;
+            this.c++;
+          }
+          continue;
         }
-      }
-    } else {
-      rv = 3;
-    }
-  }
-  let r1 = length;
-  for (let i = 1; i < length; i++) {
-    if (!isVowel(word[i]) && isVowel(word[i - 1])) {
-      r1 = i + 1;
-      break;
-    }
-  }
-  let r2 = length;
-  for (let i = r1 + 1; i < length; i++) {
-    if (!isVowel(word[i]) && isVowel(word[i - 1])) {
-      r2 = i + 1;
-      break;
-    }
-  }
-  return { rv, r1, r2 };
-}
-var RE_ACCENT_A = /á/g;
-var RE_ACCENT_E = /é/g;
-var RE_ACCENT_I = /í/g;
-var RE_ACCENT_O = /ó/g;
-var RE_ACCENT_U = /ú/g;
-function replaceAccentedVowels(word) {
-  return word.replace(RE_ACCENT_A, "\xE0").replace(RE_ACCENT_E, "\xE8").replace(RE_ACCENT_I, "\xEC").replace(RE_ACCENT_O, "\xF2").replace(RE_ACCENT_U, "\xF9");
-}
-function markVowelPairsAsUppercase(word) {
-  let result = "";
-  for (let i = 0; i < word.length; i++) {
-    const ch = word[i];
-    if (i > 0 && i < word.length - 1 && isVowel(word[i - 1]) && isVowel(word[i + 1])) {
-      if (ch === "i") {
-        result += "I";
-        continue;
-      }
-      if (ch === "u") {
-        result += "U";
-        continue;
+        this.c = v_5;
+        break;
       }
     }
-    result += ch;
-  }
-  return result;
-}
-var RE_UPPERCASE_I = /I/g;
-var RE_UPPERCASE_U = /U/g;
-function restoreMarkedVowels(word) {
-  return word.replace(RE_UPPERCASE_I, "i").replace(RE_UPPERCASE_U, "u");
-}
-function endsWith(word, suffix) {
-  return word.endsWith(suffix);
-}
-function suffixInRegion(word, suffix, regionStart) {
-  return word.length - suffix.length >= regionStart;
-}
-function removeSuffix(word, suffix) {
-  return word.slice(0, word.length - suffix.length);
-}
-var STANDARD_SUFFIXES = [
-  { suffix: "atrice", group: "A" },
-  { suffix: "atrici", group: "A" },
-  { suffix: "azione", group: "B" },
-  { suffix: "azioni", group: "B" },
-  { suffix: "uzione", group: "D" },
-  { suffix: "uzioni", group: "D" },
-  { suffix: "usione", group: "D" },
-  { suffix: "usioni", group: "D" },
-  { suffix: "amento", group: "F" },
-  { suffix: "amenti", group: "F" },
-  { suffix: "imento", group: "F" },
-  { suffix: "imenti", group: "F" },
-  { suffix: "amente", group: "G" },
-  { suffix: "atore", group: "B" },
-  { suffix: "atori", group: "B" },
-  { suffix: "mente", group: "A" },
-  { suffix: "logia", group: "C" },
-  { suffix: "logie", group: "C" },
-  { suffix: "abile", group: "A" },
-  { suffix: "abili", group: "A" },
-  { suffix: "ibile", group: "A" },
-  { suffix: "ibili", group: "A" },
-  { suffix: "ista", group: "A" },
-  { suffix: "iste", group: "A" },
-  { suffix: "isti", group: "A" },
-  { suffix: "ist\xE0", group: "A" },
-  { suffix: "ist\xE8", group: "A" },
-  { suffix: "ist\xEC", group: "A" },
-  { suffix: "anza", group: "A" },
-  { suffix: "anze", group: "A" },
-  { suffix: "enza", group: "E" },
-  { suffix: "enze", group: "E" },
-  { suffix: "iche", group: "A" },
-  { suffix: "ichi", group: "A" },
-  { suffix: "ismo", group: "A" },
-  { suffix: "ismi", group: "A" },
-  { suffix: "ante", group: "A" },
-  { suffix: "anti", group: "A" },
-  { suffix: "ica", group: "A" },
-  { suffix: "ice", group: "A" },
-  { suffix: "ico", group: "A" },
-  { suffix: "ici", group: "A" },
-  { suffix: "osa", group: "A" },
-  { suffix: "ose", group: "A" },
-  { suffix: "oso", group: "A" },
-  { suffix: "osi", group: "A" },
-  { suffix: "iva", group: "I" },
-  { suffix: "ive", group: "I" },
-  { suffix: "ivo", group: "I" },
-  { suffix: "ivi", group: "I" },
-  { suffix: "it\xE0", group: "H" }
-];
-function findLongestSuffix(word, suffixes) {
-  let best = null;
-  for (const entry of suffixes) {
-    if (endsWith(word, entry.suffix)) {
-      if (best === null || entry.suffix.length > best.suffix.length) {
-        best = entry;
+    this.c = v_2;
+    {
+      I_pV = this.limit;
+      I_p1 = this.limit;
+      I_p2 = this.limit;
+      const v_8 = this.c;
+      lab9: {
+        lab10: {
+          const v_9 = this.c;
+          lab11: {
+            if (!this.in_grouping(g_v, 97, 249)) break lab11;
+            lab12: {
+              const v_10 = this.c;
+              lab13: {
+                if (!this.out_grouping(g_v, 97, 249)) break lab13;
+                if (!this.go_out_grouping(g_v, 97, 249)) break lab13;
+                this.c++;
+                break lab12;
+              }
+              this.c = v_10;
+              if (!this.in_grouping(g_v, 97, 249)) break lab11;
+              if (!this.go_in_grouping(g_v, 97, 249)) break lab11;
+              this.c++;
+            }
+            break lab10;
+          }
+          this.c = v_9;
+          lab14: {
+            if (!this.eq_s("divan")) break lab14;
+            break lab10;
+          }
+          this.c = v_9;
+          if (!this.out_grouping(g_v, 97, 249)) break lab9;
+          lab15: {
+            const v_11 = this.c;
+            lab16: {
+              if (!this.out_grouping(g_v, 97, 249)) break lab16;
+              if (!this.go_out_grouping(g_v, 97, 249)) break lab16;
+              this.c++;
+              break lab15;
+            }
+            this.c = v_11;
+            if (!this.in_grouping(g_v, 97, 249)) break lab9;
+            if (this.c >= this.limit) break lab9;
+            this.c++;
+          }
+        }
+        I_pV = this.c;
       }
-    }
-  }
-  return best;
-}
-function removeStandardSuffix(word, r1, r2, rv) {
-  const match = findLongestSuffix(word, STANDARD_SUFFIXES);
-  if (match === null) return { word, changed: false };
-  const { suffix, group } = match;
-  if (group === "A") {
-    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
-    return { word: removeSuffix(word, suffix), changed: true };
-  }
-  if (group === "B") {
-    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
-    word = removeSuffix(word, suffix);
-    if (endsWith(word, "ic") && suffixInRegion(word, "ic", r2)) {
-      word = removeSuffix(word, "ic");
-    }
-    return { word, changed: true };
-  }
-  if (group === "C") {
-    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
-    return { word: `${removeSuffix(word, suffix)}log`, changed: true };
-  }
-  if (group === "D") {
-    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
-    return { word: `${removeSuffix(word, suffix)}u`, changed: true };
-  }
-  if (group === "E") {
-    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
-    return { word: `${removeSuffix(word, suffix)}ente`, changed: true };
-  }
-  if (group === "F") {
-    if (!suffixInRegion(word, suffix, rv)) return { word, changed: false };
-    return { word: removeSuffix(word, suffix), changed: true };
-  }
-  if (group === "G") {
-    if (!suffixInRegion(word, suffix, r1)) return { word, changed: false };
-    word = removeSuffix(word, suffix);
-    if (endsWith(word, "iv") && suffixInRegion(word, "iv", r2)) {
-      word = removeSuffix(word, "iv");
-      if (endsWith(word, "at") && suffixInRegion(word, "at", r2)) {
-        word = removeSuffix(word, "at");
+      this.c = v_8;
+      const v_12 = this.c;
+      lab17: {
+        if (!this.go_out_grouping(g_v, 97, 249)) break lab17;
+        this.c++;
+        if (!this.go_in_grouping(g_v, 97, 249)) break lab17;
+        this.c++;
+        I_p1 = this.c;
+        if (!this.go_out_grouping(g_v, 97, 249)) break lab17;
+        this.c++;
+        if (!this.go_in_grouping(g_v, 97, 249)) break lab17;
+        this.c++;
+        I_p2 = this.c;
       }
-    } else if (endsWith(word, "os") && suffixInRegion(word, "os", r2)) {
-      word = removeSuffix(word, "os");
-    } else if (endsWith(word, "ic") && suffixInRegion(word, "ic", r2)) {
-      word = removeSuffix(word, "ic");
-    } else if (endsWith(word, "abil") && suffixInRegion(word, "abil", r2)) {
-      word = removeSuffix(word, "abil");
-    }
-    return { word, changed: true };
-  }
-  if (group === "H") {
-    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
-    word = removeSuffix(word, suffix);
-    if (endsWith(word, "abil") && suffixInRegion(word, "abil", r2)) {
-      word = removeSuffix(word, "abil");
-    } else if (endsWith(word, "ic") && suffixInRegion(word, "ic", r2)) {
-      word = removeSuffix(word, "ic");
-    } else if (endsWith(word, "iv") && suffixInRegion(word, "iv", r2)) {
-      word = removeSuffix(word, "iv");
+      this.c = v_12;
     }
-    return { word, changed: true };
-  }
-  if (group === "I") {
-    if (!suffixInRegion(word, suffix, r2)) return { word, changed: false };
-    word = removeSuffix(word, suffix);
-    if (endsWith(word, "at") && suffixInRegion(word, "at", r2)) {
-      word = removeSuffix(word, "at");
-      if (endsWith(word, "ic") && suffixInRegion(word, "ic", r2)) {
-        word = removeSuffix(word, "ic");
-      }
+    this.limit_backward = this.c;
+    this.c = this.limit;
+    const v_13 = this.limit - this.c;
+    lab18: {
+      this.ket = this.c;
+      if (this.find_among_b(a_3) === 0) break lab18;
+      this.bra = this.c;
+      a = this.find_among_b(a_4);
+      if (a === 0) break lab18;
+      if (
+        /**@type {boolean}*/
+        I_pV > this.c
+      ) break lab18;
+      this.slice_from(as_4[a - 1]);
     }
-    return { word, changed: true };
-  }
-  return { word, changed: false };
-}
-var VERB_SUFFIXES = [
-  "erebbero",
-  "irebbero",
-  "erebbe",
-  "irebbe",
-  "assero",
-  "essero",
-  "issero",
-  "assimo",
-  "eremmo",
-  "iremmo",
-  "eranno",
-  "iranno",
-  "ereste",
-  "ireste",
-  "iscano",
-  "iscono",
-  "eremo",
-  "iremo",
-  "avamo",
-  "evamo",
-  "ivamo",
-  "avate",
-  "evate",
-  "ivate",
-  "erete",
-  "irete",
-  "arono",
-  "erono",
-  "irono",
-  "avano",
-  "evano",
-  "ivano",
-  "eresti",
-  "iresti",
-  "isco",
-  "isca",
-  "isce",
-  "isci",
-  "ando",
-  "endo",
-  "Yamo",
-  "iamo",
-  "ammo",
-  "emmo",
-  "immo",
-  "asse",
-  "aste",
-  "este",
-  "iste",
-  "erai",
-  "irai",
-  "erei",
-  "irei",
-  "ava",
-  "eva",
-  "iva",
-  "ata",
-  "ita",
-  "uta",
-  "ate",
-  "ete",
-  "ite",
-  "ute",
-  "ati",
-  "iti",
-  "uti",
-  "ato",
-  "ito",
-  "uto",
-  "avo",
-  "evo",
-  "ivo",
-  "ano",
-  "ono",
-  "are",
-  "ere",
-  "ire",
-  "assi",
-  "avi",
-  "evi",
-  "ivi",
-  "endi",
-  "ar",
-  "ir",
-  "er\xE0",
-  "ir\xE0",
-  "er\xF2",
-  "ir\xF2"
-];
-var ATTACHED_PRONOUN_SUFFIXES = [
-  "gliela",
-  "gliele",
-  "glieli",
-  "glielo",
-  "gliene",
-  "cela",
-  "cele",
-  "celi",
-  "celo",
-  "cene",
-  "mela",
-  "mele",
-  "meli",
-  "melo",
-  "mene",
-  "sene",
-  "tela",
-  "tele",
-  "teli",
-  "telo",
-  "tene",
-  "vela",
-  "vele",
-  "veli",
-  "velo",
-  "vene",
-  "gli",
-  "la",
-  "le",
-  "li",
-  "lo",
-  "ci",
-  "mi",
-  "ne",
-  "si",
-  "ti",
-  "vi"
-];
-var ATTACHED_PRONOUN_PRECEDING = ["ando", "endo", "ar", "er", "ir"];
-function removeAttachedPronouns(word, rv) {
-  let longestPronoun = null;
-  for (const pronoun of ATTACHED_PRONOUN_SUFFIXES) {
-    if (endsWith(word, pronoun) && suffixInRegion(word, pronoun, rv)) {
-      if (longestPronoun === null || pronoun.length > longestPronoun.length) {
-        longestPronoun = pronoun;
+    this.c = this.limit - v_13;
+    const v_14 = this.limit - this.c;
+    lab19: {
+      lab20: {
+        const v_15 = this.limit - this.c;
+        lab21: {
+          this.ket = this.c;
+          a = this.find_among_b(a_7);
+          if (a === 0) break lab21;
+          this.bra = this.c;
+          switch (a) {
+            case 1: {
+              if (
+                /**@type {boolean}*/
+                I_p2 > this.c
+              ) break lab21;
+              this.slice_del();
+              break;
+            }
+            case 2: {
+              if (
+                /**@type {boolean}*/
+                I_p2 > this.c
+              ) break lab21;
+              this.slice_del();
+              const v_16 = this.limit - this.c;
+              lab22: {
+                this.ket = this.c;
+                if (!this.eq_s_b("ic")) {
+                  this.c = this.limit - v_16;
+                  break lab22;
+                }
+                this.bra = this.c;
+                if (
+                  /**@type {boolean}*/
+                  I_p2 > this.c
+                ) {
+                  this.c = this.limit - v_16;
+                  break lab22;
+                }
+                this.slice_del();
+              }
+              break;
+            }
+            case 3: {
+              if (
+                /**@type {boolean}*/
+                I_p2 > this.c
+              ) break lab21;
+              this.slice_from("log");
+              break;
+            }
+            case 4: {
+              if (
+                /**@type {boolean}*/
+                I_p2 > this.c
+              ) break lab21;
+              this.slice_from("u");
+              break;
+            }
+            case 5: {
+              if (
+                /**@type {boolean}*/
+                I_p2 > this.c
+              ) break lab21;
+              this.slice_from("ente");
+              break;
+            }
+            case 6: {
+              if (
+                /**@type {boolean}*/
+                I_pV > this.c
+              ) break lab21;
+              this.slice_del();
+              break;
+            }
+            case 7: {
+              if (
+                /**@type {boolean}*/
+                I_p1 > this.c
+              ) break lab21;
+              this.slice_del();
+              const v_17 = this.limit - this.c;
+              lab23: {
+                this.ket = this.c;
+                a = this.find_among_b(a_5);
+                if (a === 0) {
+                  this.c = this.limit - v_17;
+                  break lab23;
+                }
+                this.bra = this.c;
+                if (
+                  /**@type {boolean}*/
+                  I_p2 > this.c
+                ) {
+                  this.c = this.limit - v_17;
+                  break lab23;
+                }
+                this.slice_del();
+                switch (a) {
+                  case 1: {
+                    this.ket = this.c;
+                    if (!this.eq_s_b("at")) {
+                      this.c = this.limit - v_17;
+                      break lab23;
+                    }
+                    this.bra = this.c;
+                    if (
+                      /**@type {boolean}*/
+                      I_p2 > this.c
+                    ) {
+                      this.c = this.limit - v_17;
+                      break lab23;
+                    }
+                    this.slice_del();
+                    break;
+                  }
+                }
+              }
+              break;
+            }
+            case 8: {
+              if (
+                /**@type {boolean}*/
+                I_p2 > this.c
+              ) break lab21;
+              this.slice_del();
+              const v_18 = this.limit - this.c;
+              lab24: {
+                this.ket = this.c;
+                if (this.find_among_b(a_6) === 0) {
+                  this.c = this.limit - v_18;
+                  break lab24;
+                }
+                this.bra = this.c;
+                if (
+                  /**@type {boolean}*/
+                  I_p2 > this.c
+                ) {
+                  this.c = this.limit - v_18;
+                  break lab24;
+                }
+                this.slice_del();
+              }
+              break;
+            }
+            case 9: {
+              if (
+                /**@type {boolean}*/
+                I_p2 > this.c
+              ) break lab21;
+              this.slice_del();
+              const v_19 = this.limit - this.c;
+              lab25: {
+                this.ket = this.c;
+                if (!this.eq_s_b("at")) {
+                  this.c = this.limit - v_19;
+                  break lab25;
+                }
+                this.bra = this.c;
+                if (
+                  /**@type {boolean}*/
+                  I_p2 > this.c
+                ) {
+                  this.c = this.limit - v_19;
+                  break lab25;
+                }
+                this.slice_del();
+                this.ket = this.c;
+                if (!this.eq_s_b("ic")) {
+                  this.c = this.limit - v_19;
+                  break lab25;
+                }
+                this.bra = this.c;
+                if (
+                  /**@type {boolean}*/
+                  I_p2 > this.c
+                ) {
+                  this.c = this.limit - v_19;
+                  break lab25;
+                }
+                this.slice_del();
+              }
+              break;
+            }
+          }
+          break lab20;
+        }
+        this.c = this.limit - v_15;
+        if (this.c < I_pV) break lab19;
+        const v_20 = this.limit_backward;
+        this.limit_backward = I_pV;
+        this.ket = this.c;
+        if (this.find_among_b(a_8) === 0) {
+          this.limit_backward = v_20;
+          break lab19;
+        }
+        this.bra = this.c;
+        this.slice_del();
+        this.limit_backward = v_20;
       }
     }
-  }
-  if (longestPronoun === null) return word;
-  const stemmed = removeSuffix(word, longestPronoun);
-  for (const preceding of ATTACHED_PRONOUN_PRECEDING) {
-    if (endsWith(stemmed, preceding)) {
-      if (preceding === "ar" || preceding === "er" || preceding === "ir") {
-        return `${removeSuffix(stemmed, preceding) + preceding}e`;
+    this.c = this.limit - v_14;
+    const v_21 = this.limit - this.c;
+    {
+      const v_22 = this.limit - this.c;
+      lab27: {
+        this.ket = this.c;
+        if (!this.in_grouping_b(g_AEIO, 97, 242)) {
+          this.c = this.limit - v_22;
+          break lab27;
+        }
+        this.bra = this.c;
+        if (
+          /**@type {boolean}*/
+          I_pV > this.c
+        ) {
+          this.c = this.limit - v_22;
+          break lab27;
+        }
+        this.slice_del();
+        this.ket = this.c;
+        if (!this.eq_s_b("i")) {
+          this.c = this.limit - v_22;
+          break lab27;
+        }
+        this.bra = this.c;
+        if (
+          /**@type {boolean}*/
+          I_pV > this.c
+        ) {
+          this.c = this.limit - v_22;
+          break lab27;
+        }
+        this.slice_del();
       }
-      return stemmed;
-    }
-  }
-  return word;
-}
-function removeVerbSuffix(word, rv) {
-  let longestSuffix = null;
-  for (const suffix of VERB_SUFFIXES) {
-    if (endsWith(word, suffix)) {
-      if (longestSuffix === null || suffix.length > longestSuffix.length) {
-        longestSuffix = suffix;
+      const v_23 = this.limit - this.c;
+      lab28: {
+        this.ket = this.c;
+        if (!this.eq_s_b("h")) {
+          this.c = this.limit - v_23;
+          break lab28;
+        }
+        this.bra = this.c;
+        if (!this.in_grouping_b(g_CG, 99, 103)) {
+          this.c = this.limit - v_23;
+          break lab28;
+        }
+        if (
+          /**@type {boolean}*/
+          I_pV > this.c
+        ) {
+          this.c = this.limit - v_23;
+          break lab28;
+        }
+        this.slice_del();
       }
     }
-  }
-  if (longestSuffix !== null && suffixInRegion(word, longestSuffix, rv)) {
-    return { word: removeSuffix(word, longestSuffix), changed: true };
-  }
-  return { word, changed: false };
-}
-function removeResidualSuffix(word, rv) {
-  const lastChar = word[word.length - 1];
-  if (lastChar === "a" || lastChar === "e" || lastChar === "i" || lastChar === "o" || lastChar === "\xE0" || lastChar === "\xE8" || lastChar === "\xEC" || lastChar === "\xF2") {
-    if (suffixInRegion(word, lastChar, rv)) {
-      word = word.slice(0, -1);
-      if (word.length > 0 && word[word.length - 1] === "i" && suffixInRegion(word, "i", rv)) {
-        word = word.slice(0, -1);
+    this.c = this.limit - v_21;
+    this.c = this.limit_backward;
+    const v_24 = this.c;
+    while (true) {
+      const v_25 = this.c;
+      lab30: {
+        this.bra = this.c;
+        a = this.find_among(a_2);
+        this.ket = this.c;
+        switch (a) {
+          case 1: {
+            this.slice_from("i");
+            break;
+          }
+          case 2: {
+            this.slice_from("u");
+            break;
+          }
+          case 3: {
+            if (this.c >= this.limit) break lab30;
+            this.c++;
+            break;
+          }
+        }
+        continue;
       }
+      this.c = v_25;
+      break;
     }
+    this.c = v_24;
+    return true;
   }
-  if (endsWith(word, "h") && suffixInRegion(word, "h", rv)) {
-    const twoBack = word.length >= 2 ? word[word.length - 2] : "";
-    if (twoBack === "c" || twoBack === "g") {
-      word = word.slice(0, -1);
-    }
-  }
-  return word;
-}
-function stem(word) {
-  if (word.length < 3) return word;
-  word = word.toLowerCase();
-  word = replaceAccentedVowels(word);
-  word = word.replace(RE_QU, "qU");
-  word = markVowelPairsAsUppercase(word);
-  const { rv, r1, r2 } = findRegions(word);
-  word = removeAttachedPronouns(word, rv);
-  const standardResult = removeStandardSuffix(word, r1, r2, rv);
-  if (standardResult.changed) {
-    word = standardResult.word;
-  } else {
-    const verbResult = removeVerbSuffix(word, rv);
-    word = verbResult.word;
+  stem(input) {
+    this.setCurrent(input);
+    this.#stem();
+    return this.getCurrent();
   }
-  word = removeResidualSuffix(word, rv);
-  word = restoreMarkedVowels(word);
-  return word;
+};
+var shared = new ItalianStemmer();
+function stem(token) {
+  return shared.stem(token);
 }
+
+// src/languages/italian.ts
 var stopWords = /* @__PURE__ */ new Set([
   "ad",
   "al",
@@ -705,9 +1001,10 @@ var stopWords = /* @__PURE__ */ new Set([
 ]);
 var italian = {
   name: "italian",
+  revision: "c4d2339182390e18",
   stemmer: stem,
   stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9\u00e0\u00e8\u00e9\u00ec\u00f2\u00f3\u00f9'-]+/gi }
+  tokenizer: { splitPattern: /[^a-z0-9àèéìîòóù-]+/gi }
 };
 
 export { italian };