@delali/narsil 0.1.14 → 0.2.0

package/dist/languages/finnish.mjs

@@ -1,297 +1,564 @@
-// src/languages/finnish.ts
-var VOWELS = "aeiouy\xE4\xF6";
-var LONG_VOWELS = ["aa", "ee", "ii", "oo", "uu", "\xE4\xE4", "\xF6\xF6"];
-var CONSONANT_PATTERN = /[a-zäö]/;
-var PARTICLES = ["kaan", "k\xE4\xE4n", "han", "h\xE4n", "kin", "ko", "k\xF6", "pa", "p\xE4"];
-var BACK_VOWEL_ENDINGS = ["lla", "na", "ssa", "ta", "lta", "sta"];
-var FRONT_VOWEL_ENDINGS = ["ll\xE4", "n\xE4", "ss\xE4", "t\xE4", "lt\xE4", "st\xE4"];
-var NEUTRAL_ENDINGS = ["lle", "ine"];
-var H_SUFFIXES = [
-  { suffix: "han", requiredPreceding: "a" },
-  { suffix: "hen", requiredPreceding: "e" },
-  { suffix: "hin", requiredPreceding: "i" },
-  { suffix: "hon", requiredPreceding: "o" },
-  { suffix: "hun", requiredPreceding: "u" },
-  { suffix: "hyn", requiredPreceding: "y" },
-  { suffix: "h\xE4n", requiredPreceding: "\xE4" },
-  { suffix: "h\xF6n", requiredPreceding: "\xF6" }
+import { BaseStemmer } from '../chunk-U2BKYEC7.mjs';
+
+// src/languages/snowball/finnish.ts
+var a_0 = [
+  ["pa", 1],
+  ["sti", 2],
+  ["kaan", 1],
+  ["han", 1],
+  ["kin", 1],
+  ["h\xE4n", 1],
+  ["k\xE4\xE4n", 1],
+  ["ko", 1],
+  ["p\xE4", 1],
+  ["k\xF6", 1]
 ];
-var SIMPLE_SUFFIXES = ["ssa", "ss\xE4", "sta", "st\xE4", "lla", "ll\xE4", "lta", "lt\xE4", "lle", "ine", "ksi"];
-var STEP4_SUFFIXES = [
-  { text: "impa", checkPo: false },
-  { text: "imp\xE4", checkPo: false },
-  { text: "impi", checkPo: true },
-  { text: "imma", checkPo: false },
-  { text: "imm\xE4", checkPo: false },
-  { text: "immi", checkPo: true },
-  { text: "eja", checkPo: false },
-  { text: "ej\xE4", checkPo: false },
-  { text: "mpa", checkPo: false },
-  { text: "mp\xE4", checkPo: false },
-  { text: "mpi", checkPo: true },
-  { text: "mma", checkPo: false },
-  { text: "mm\xE4", checkPo: false },
-  { text: "mmi", checkPo: true }
+var a_1 = [
+  ["lla", -1],
+  ["na", -1],
+  ["ssa", -1],
+  ["ta", -1],
+  ["lta", -1, 1],
+  ["sta", -1, 2]
 ];
-function isVowel(ch) {
-  return VOWELS.includes(ch);
-}
-function isConsonant(ch) {
-  return ch.length === 1 && !isVowel(ch) && CONSONANT_PATTERN.test(ch);
-}
-function endsWithLongVowel(word) {
-  if (word.length < 2) return false;
-  const tail = word.slice(-2);
-  return LONG_VOWELS.includes(tail);
-}
-function computeRegions(word) {
-  let r1 = word.length;
-  let r2 = word.length;
-  let foundVowel = false;
-  for (let i = 0; i < word.length; i++) {
-    if (foundVowel && !isVowel(word[i])) {
-      r1 = i + 1;
-      break;
-    }
-    if (isVowel(word[i])) {
-      foundVowel = true;
-    }
-  }
-  foundVowel = false;
-  for (let i = r1; i < word.length; i++) {
-    if (foundVowel && !isVowel(word[i])) {
-      r2 = i + 1;
-      break;
-    }
-    if (isVowel(word[i])) {
-      foundVowel = true;
-    }
-  }
-  return { r1, r2 };
-}
-function suffixInR1(word, suffix, r1) {
-  return word.endsWith(suffix) && word.length - suffix.length >= r1;
-}
-function suffixInR2(word, suffix, r2) {
-  return word.endsWith(suffix) && word.length - suffix.length >= r2;
-}
-function step1(word, r1, r2) {
-  for (const p of PARTICLES) {
-    if (suffixInR1(word, p, r1)) {
-      const charBefore = word[word.length - p.length - 1];
-      if (charBefore && (isVowel(charBefore) || charBefore === "n")) {
-        return word.slice(0, -p.length);
-      }
-    }
-  }
-  if (suffixInR2(word, "sti", r2)) {
-    return word.slice(0, -3);
-  }
-  return word;
-}
-function step2(word, r1) {
-  if (suffixInR1(word, "nsa", r1)) return word.slice(0, -3);
-  if (suffixInR1(word, "ns\xE4", r1)) return word.slice(0, -3);
-  if (suffixInR1(word, "mme", r1)) return word.slice(0, -3);
-  if (suffixInR1(word, "nne", r1)) return word.slice(0, -3);
-  if (suffixInR1(word, "si", r1)) {
-    const base = word.slice(0, -2);
-    if (base.endsWith("k")) return base;
-    if (base.endsWith("kse")) return `${base.slice(0, -3)}ksi`;
-    return base;
-  }
-  if (suffixInR1(word, "ni", r1)) {
-    const base = word.slice(0, -2);
-    if (base.endsWith("kse")) return `${base.slice(0, -3)}ksi`;
-    return base;
-  }
-  if (suffixInR1(word, "an", r1)) {
-    const base = word.slice(0, -2);
-    for (const ending of BACK_VOWEL_ENDINGS) {
-      if (base.endsWith(ending)) return base;
+var a_2 = [
+  ["ll\xE4", -1],
+  ["n\xE4", -1],
+  ["ss\xE4", -1],
+  ["t\xE4", -1],
+  ["lt\xE4", -1, 1],
+  ["st\xE4", -1, 2]
+];
+var a_3 = [
+  ["lle", -1],
+  ["ine", -1]
+];
+var a_4 = [
+  ["nsa", 3],
+  ["mme", 3],
+  ["nne", 3],
+  ["ni", 2],
+  ["si", 1],
+  ["an", 4],
+  ["en", 6],
+  ["\xE4n", 5],
+  ["ns\xE4", 3]
+];
+var a_5 = [
+  ["aa", -1],
+  ["ee", -1],
+  ["ii", -1],
+  ["oo", -1],
+  ["uu", -1],
+  ["\xE4\xE4", -1],
+  ["\xF6\xF6", -1]
+];
+var a_6 = [
+  ["'", -1],
+  ["ai", -1],
+  ["ei", -1],
+  ["ii", -1],
+  ["oi", -1],
+  ["ui", -1],
+  ["\xE4i", -1],
+  ["\xF6i", -1]
+];
+var a_7 = [
+  ["a", 2],
+  ["lla", -1, 1],
+  ["na", -1, 2],
+  ["ssa", -1, 3],
+  ["ta", -1, 4],
+  ["lta", -1, 1],
+  ["sta", -1, 2],
+  ["tta", 3, 3],
+  ["lle", -1],
+  ["ine", -1],
+  ["ksi", -1],
+  ["n", 1],
+  ["han", -1, 1, 3],
+  ["den", -1, 2, 8],
+  ["seen", -1, 3, 9],
+  ["hen", -1, 4, 4],
+  ["tten", -1, 5, 8],
+  ["hin", -1, 6, 5],
+  ["siin", -1, 7, 8],
+  ["hon", -1, 8, 6],
+  ["hun", -1, 9, 7],
+  ["h\xE4n", -1, 10, 1],
+  ["h\xF6n", -1, 11, 2],
+  ["\xE4", 2],
+  ["ll\xE4", -1, 1],
+  ["n\xE4", -1, 2],
+  ["ss\xE4", -1, 3],
+  ["t\xE4", -1, 4],
+  ["lt\xE4", -1, 1],
+  ["st\xE4", -1, 2],
+  ["tt\xE4", 3, 3]
+];
+var a_8 = [
+  ["eja", -1],
+  ["mma", 1],
+  ["imma", -1, 1],
+  ["mpa", 1],
+  ["impa", -1, 1],
+  ["mmi", 1],
+  ["immi", -1, 1],
+  ["mpi", 1],
+  ["impi", -1, 1],
+  ["ej\xE4", -1],
+  ["mm\xE4", 1],
+  ["imm\xE4", -1, 1],
+  ["mp\xE4", 1],
+  ["imp\xE4", -1, 1]
+];
+var a_9 = [
+  ["i", -1],
+  ["j", -1]
+];
+var a_10 = [
+  ["mma", 1],
+  ["imma", -1, 1]
+];
+var g_AEI = [17, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8];
+var g_C = [119, 223, 119, 1];
+var g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 32];
+var g_particle_end = [17, 97, 24, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 32];
+var FinnishStemmer = class extends BaseStemmer {
+  #af_7() {
+    switch (this.af) {
+      case 1:
+        return this.#r_A_();
+      case 2:
+        return this.#r_O_();
+      case 3:
+        return this.#r_A();
+      case 4:
+        return this.#r_E();
+      case 5:
+        return this.#r_I();
+      case 6:
+        return this.#r_O();
+      case 7:
+        return this.#r_U();
+      case 8:
+        return this.#r_VI();
+      case 9:
+        return this.#r_LV();
     }
+    return false;
   }
-  if (suffixInR1(word, "\xE4n", r1)) {
-    const base = word.slice(0, -2);
-    for (const ending of FRONT_VOWEL_ENDINGS) {
-      if (base.endsWith(ending)) return base;
-    }
+  #r_LV() {
+    return this.find_among_b(a_5) !== 0;
   }
-  if (suffixInR1(word, "en", r1)) {
-    const base = word.slice(0, -2);
-    for (const ending of NEUTRAL_ENDINGS) {
-      if (base.endsWith(ending)) return base;
-    }
+  #r_VI() {
+    return this.find_among_b(a_6) !== 0;
   }
-  return word;
-}
-function step3(word, r1) {
-  for (const { suffix, requiredPreceding } of H_SUFFIXES) {
-    if (suffixInR1(word, suffix, r1)) {
-      const base = word.slice(0, -suffix.length);
-      if (base.length > 0 && base[base.length - 1] === requiredPreceding) {
-        return { word: base, caseRemoved: true };
+  #r_A() {
+    lab0: {
+      lab1: {
+        if (!this.eq_s_b("a")) break lab1;
+        break lab0;
       }
+      if (!this.eq_s_b("'")) return false;
     }
+    return true;
   }
-  if (suffixInR1(word, "siin", r1)) {
-    const base = word.slice(0, -4);
-    if (base.length >= 2 && isConsonant(base[base.length - 1])) {
-      return { word: base, caseRemoved: true };
-    }
-  }
-  if (suffixInR1(word, "seen", r1)) {
-    const base = word.slice(0, -4);
-    if (endsWithLongVowel(base)) {
-      return { word: base, caseRemoved: true };
-    }
-  }
-  if (suffixInR1(word, "den", r1)) {
-    const base = word.slice(0, -3);
-    if (base.length >= 2 && isConsonant(base[base.length - 1])) {
-      return { word: base, caseRemoved: true };
+  #r_E() {
+    lab0: {
+      lab1: {
+        if (!this.eq_s_b("e")) break lab1;
+        break lab0;
+      }
+      if (!this.eq_s_b("'")) return false;
     }
+    return true;
   }
-  if (suffixInR1(word, "tten", r1)) {
-    const base = word.slice(0, -4);
-    if (base.length >= 2 && isConsonant(base[base.length - 1])) {
-      return { word: base, caseRemoved: true };
+  #r_I() {
+    lab0: {
+      lab1: {
+        if (!this.eq_s_b("i")) break lab1;
+        break lab0;
+      }
+      if (!this.eq_s_b("'")) return false;
     }
+    return true;
   }
-  for (const suffix of SIMPLE_SUFFIXES) {
-    if (suffixInR1(word, suffix, r1)) {
-      return { word: word.slice(0, -suffix.length), caseRemoved: true };
+  #r_O() {
+    lab0: {
+      lab1: {
+        if (!this.eq_s_b("o")) break lab1;
+        break lab0;
+      }
+      if (!this.eq_s_b("'")) return false;
     }
+    return true;
   }
-  if (suffixInR1(word, "na", r1)) return { word: word.slice(0, -2), caseRemoved: true };
-  if (suffixInR1(word, "n\xE4", r1)) return { word: word.slice(0, -2), caseRemoved: true };
-  if (suffixInR1(word, "tta", r1)) {
-    const base = word.slice(0, -3);
-    if (base.length > 0 && isVowel(base[base.length - 1])) {
-      return { word: base, caseRemoved: true };
+  #r_U() {
+    lab0: {
+      lab1: {
+        if (!this.eq_s_b("u")) break lab1;
+        break lab0;
+      }
+      if (!this.eq_s_b("'")) return false;
     }
+    return true;
   }
-  if (suffixInR1(word, "tt\xE4", r1)) {
-    const base = word.slice(0, -3);
-    if (base.length > 0 && isVowel(base[base.length - 1])) {
-      return { word: base, caseRemoved: true };
+  #r_A_() {
+    lab0: {
+      lab1: {
+        if (!this.eq_s_b("\xE4")) break lab1;
+        break lab0;
+      }
+      if (!this.eq_s_b("'")) return false;
     }
+    return true;
   }
-  if (suffixInR1(word, "ta", r1)) return { word: word.slice(0, -2), caseRemoved: true };
-  if (suffixInR1(word, "t\xE4", r1)) return { word: word.slice(0, -2), caseRemoved: true };
-  if (suffixInR1(word, "n", r1)) {
-    const base = word.slice(0, -1);
-    if (endsWithLongVowel(base)) {
-      return { word: base.slice(0, -1), caseRemoved: true };
-    }
-    if (base.endsWith("ie")) {
-      return { word: base, caseRemoved: true };
-    }
-    if (base.length > 0 && isVowel(base[base.length - 1]) && isConsonant(base[base.length - 2])) {
-      return { word: base, caseRemoved: true };
+  #r_O_() {
+    lab0: {
+      lab1: {
+        if (!this.eq_s_b("\xF6")) break lab1;
+        break lab0;
+      }
+      lab2: {
+        if (!this.eq_s_b("\xF8")) break lab2;
+        break lab0;
+      }
+      if (!this.eq_s_b("'")) return false;
     }
+    return true;
   }
-  if (suffixInR1(word, "a", r1)) {
-    const base = word.slice(0, -1);
-    if (base.length >= 2 && isVowel(base[base.length - 1]) && isConsonant(base[base.length - 2])) {
-      return { word: base, caseRemoved: true };
+  #stem() {
+    let a;
+    let B_ending_removed;
+    let S_x;
+    let I_p2;
+    let I_p1;
+    const v_1 = this.c;
+    lab0: {
+      I_p1 = this.limit;
+      I_p2 = this.limit;
+      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;
+      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_p2 = this.c;
     }
-  }
-  if (suffixInR1(word, "\xE4", r1)) {
-    const base = word.slice(0, -1);
-    if (base.length >= 2 && isVowel(base[base.length - 1]) && isConsonant(base[base.length - 2])) {
-      return { word: base, caseRemoved: true };
+    this.c = v_1;
+    B_ending_removed = false;
+    this.limit_backward = this.c;
+    this.c = this.limit;
+    const v_2 = this.limit - this.c;
+    lab1: {
+      if (this.c < I_p1) break lab1;
+      const v_3 = this.limit_backward;
+      this.limit_backward = I_p1;
+      this.ket = this.c;
+      a = this.find_among_b(a_0);
+      if (a === 0) {
+        this.limit_backward = v_3;
+        break lab1;
+      }
+      this.bra = this.c;
+      this.limit_backward = v_3;
+      switch (a) {
+        case 1: {
+          if (!this.in_grouping_b(g_particle_end, 97, 246)) break lab1;
+          break;
+        }
+        case 2: {
+          if (
+            /**@type {boolean}*/
+            I_p2 > this.c
+          ) break lab1;
+          break;
+        }
+      }
+      this.slice_del();
     }
-  }
-  return { word, caseRemoved: false };
-}
-function step4(word, r2) {
-  for (const { text, checkPo } of STEP4_SUFFIXES) {
-    if (suffixInR2(word, text, r2)) {
-      if (checkPo) {
-        const base = word.slice(0, -text.length);
-        if (base.endsWith("po")) continue;
+    this.c = this.limit - v_2;
+    const v_4 = this.limit - this.c;
+    lab2: {
+      if (this.c < I_p1) break lab2;
+      const v_5 = this.limit_backward;
+      this.limit_backward = I_p1;
+      this.ket = this.c;
+      a = this.find_among_b(a_4);
+      if (a === 0) {
+        this.limit_backward = v_5;
+        break lab2;
+      }
+      this.bra = this.c;
+      this.limit_backward = v_5;
+      switch (a) {
+        case 1: {
+          lab3: {
+            if (!this.eq_s_b("k")) break lab3;
+            break lab2;
+          }
+          this.slice_del();
+          break;
+        }
+        case 2: {
+          this.slice_del();
+          this.ket = this.c;
+          if (!this.eq_s_b("kse")) break lab2;
+          this.bra = this.c;
+          this.slice_from("ksi");
+          break;
+        }
+        case 3: {
+          this.slice_del();
+          break;
+        }
+        case 4: {
+          if (this.find_among_b(a_1) === 0) break lab2;
+          this.slice_del();
+          break;
+        }
+        case 5: {
+          if (this.find_among_b(a_2) === 0) break lab2;
+          this.slice_del();
+          break;
+        }
+        case 6: {
+          if (this.find_among_b(a_3) === 0) break lab2;
+          this.slice_del();
+          break;
+        }
       }
-      return word.slice(0, -text.length);
     }
-  }
-  return word;
-}
-function step5(word, r1, caseRemoved) {
-  if (!caseRemoved) return word;
-  if (suffixInR1(word, "j", r1)) {
-    const base = word.slice(0, -1);
-    if (base.endsWith("o") || base.endsWith("u")) {
-      return base;
+    this.c = this.limit - v_4;
+    const v_6 = this.limit - this.c;
+    lab4: {
+      if (this.c < I_p1) break lab4;
+      const v_7 = this.limit_backward;
+      this.limit_backward = I_p1;
+      this.ket = this.c;
+      a = this.find_among_b(a_7, this.#af_7);
+      if (a === 0) {
+        this.limit_backward = v_7;
+        break lab4;
+      }
+      this.bra = this.c;
+      this.limit_backward = v_7;
+      switch (a) {
+        case 1: {
+          const v_8 = this.limit - this.c;
+          lab5: {
+            const v_9 = this.limit - this.c;
+            lab6: {
+              const v_10 = this.limit - this.c;
+              lab7: {
+                if (!this.#r_LV()) break lab7;
+                break lab6;
+              }
+              this.c = this.limit - v_10;
+              if (!this.eq_s_b("ie")) {
+                this.c = this.limit - v_8;
+                break lab5;
+              }
+            }
+            this.c = this.limit - v_9;
+            if (this.c <= this.limit_backward) {
+              this.c = this.limit - v_8;
+              break lab5;
+            }
+            this.c--;
+            this.bra = this.c;
+          }
+          break;
+        }
+        case 2: {
+          if (!this.in_grouping_b(g_v, 97, 246)) break lab4;
+          if (!this.in_grouping_b(g_C, 98, 122)) break lab4;
+          break;
+        }
+        case 3: {
+          if (!this.eq_s_b("e")) break lab4;
+          break;
+        }
+      }
+      this.slice_del();
+      B_ending_removed = true;
     }
-  }
-  if (suffixInR1(word, "o", r1)) {
-    const base = word.slice(0, -1);
-    if (base.endsWith("j")) {
-      return base;
+    this.c = this.limit - v_6;
+    const v_11 = this.limit - this.c;
+    lab8: {
+      if (this.c < I_p2) break lab8;
+      const v_12 = this.limit_backward;
+      this.limit_backward = I_p2;
+      this.ket = this.c;
+      a = this.find_among_b(a_8);
+      if (a === 0) {
+        this.limit_backward = v_12;
+        break lab8;
+      }
+      this.bra = this.c;
+      this.limit_backward = v_12;
+      switch (a) {
+        case 1: {
+          lab9: {
+            if (!this.eq_s_b("po")) break lab9;
+            break lab8;
+          }
+          break;
+        }
+      }
+      this.slice_del();
     }
-  }
-  if (suffixInR1(word, "i", r1)) {
-    return word.slice(0, -1);
-  }
-  return word;
-}
-function step6(word, r1, r2, caseRemoved) {
-  if (caseRemoved) return word;
-  if (suffixInR1(word, "t", r1)) {
-    const base = word.slice(0, -1);
-    if (base.length > 0 && isVowel(base[base.length - 1])) {
-      word = base;
-      if (suffixInR2(word, "imma", r2)) {
-        return word.slice(0, -4);
+    this.c = this.limit - v_11;
+    lab10: {
+      lab11: {
+        if (!B_ending_removed) break lab11;
+        const v_13 = this.limit - this.c;
+        lab12: {
+          if (this.c < I_p1) break lab12;
+          const v_14 = this.limit_backward;
+          this.limit_backward = I_p1;
+          this.ket = this.c;
+          if (this.find_among_b(a_9) === 0) {
+            this.limit_backward = v_14;
+            break lab12;
+          }
+          this.bra = this.c;
+          this.limit_backward = v_14;
+          this.slice_del();
+        }
+        this.c = this.limit - v_13;
+        break lab10;
       }
-      if (suffixInR2(word, "mma", r2)) {
-        const beforeMma = word.slice(0, -3);
-        if (!beforeMma.endsWith("po")) {
-          return beforeMma;
+      const v_15 = this.limit - this.c;
+      lab13: {
+        if (this.c < I_p1) break lab13;
+        const v_16 = this.limit_backward;
+        this.limit_backward = I_p1;
+        this.ket = this.c;
+        if (!this.eq_s_b("t")) {
+          this.limit_backward = v_16;
+          break lab13;
+        }
+        this.bra = this.c;
+        const v_17 = this.limit - this.c;
+        if (!this.in_grouping_b(g_v, 97, 246)) {
+          this.limit_backward = v_16;
+          break lab13;
+        }
+        this.c = this.limit - v_17;
+        this.slice_del();
+        this.limit_backward = v_16;
+        if (this.c < I_p2) break lab13;
+        const v_18 = this.limit_backward;
+        this.limit_backward = I_p2;
+        this.ket = this.c;
+        a = this.find_among_b(a_10);
+        if (a === 0) {
+          this.limit_backward = v_18;
+          break lab13;
+        }
+        this.bra = this.c;
+        this.limit_backward = v_18;
+        switch (a) {
+          case 1: {
+            lab14: {
+              if (!this.eq_s_b("po")) break lab14;
+              break lab13;
+            }
+            break;
+          }
         }
+        this.slice_del();
       }
+      this.c = this.limit - v_15;
     }
-  }
-  return word;
-}
-function step7(word, r1) {
-  if (word.length >= 2 && word.length - 1 >= r1 && endsWithLongVowel(word)) {
-    word = word.slice(0, -1);
-  }
-  let trimmed = word;
-  while (trimmed.length > r1) {
-    const last = trimmed[trimmed.length - 1];
-    if (!isConsonant(last)) break;
-    trimmed = trimmed.slice(0, -1);
-  }
-  if (trimmed.length > 0 && isVowel(trimmed[trimmed.length - 1])) {
-    const afterVowel = word.slice(trimmed.length);
-    if (afterVowel.length >= 2) {
-      const first = afterVowel[0];
-      const second = afterVowel[1];
-      if (isConsonant(first) && first === second) {
-        word = word.slice(0, trimmed.length) + first + afterVowel.slice(2);
+    const v_19 = this.limit - this.c;
+    lab15: {
+      if (this.c < I_p1) break lab15;
+      const v_20 = this.limit_backward;
+      this.limit_backward = I_p1;
+      const v_21 = this.limit - this.c;
+      lab16: {
+        const v_22 = this.limit - this.c;
+        if (!this.#r_LV()) break lab16;
+        this.c = this.limit - v_22;
+        this.ket = this.c;
+        if (this.c <= this.limit_backward) break lab16;
+        this.c--;
+        this.bra = this.c;
+        this.slice_del();
+      }
+      this.c = this.limit - v_21;
+      const v_23 = this.limit - this.c;
+      lab17: {
+        this.ket = this.c;
+        if (!this.in_grouping_b(g_AEI, 97, 228)) break lab17;
+        this.bra = this.c;
+        if (!this.in_grouping_b(g_C, 98, 122)) break lab17;
+        this.slice_del();
       }
+      this.c = this.limit - v_23;
+      const v_24 = this.limit - this.c;
+      lab18: {
+        this.ket = this.c;
+        if (!this.eq_s_b("j")) break lab18;
+        this.bra = this.c;
+        lab19: {
+          lab20: {
+            if (!this.eq_s_b("o")) break lab20;
+            break lab19;
+          }
+          if (!this.eq_s_b("u")) break lab18;
+        }
+        this.slice_del();
+      }
+      this.c = this.limit - v_24;
+      const v_25 = this.limit - this.c;
+      lab21: {
+        this.ket = this.c;
+        if (!this.eq_s_b("o")) break lab21;
+        this.bra = this.c;
+        if (!this.eq_s_b("j")) break lab21;
+        this.slice_del();
+      }
+      this.c = this.limit - v_25;
+      this.limit_backward = v_20;
+      const v_26 = this.limit - this.c;
+      lab22: {
+        if (!this.go_in_grouping_b(g_v, 97, 246)) break lab22;
+        this.ket = this.c;
+        if (!this.in_grouping_b(g_C, 98, 122)) break lab22;
+        this.bra = this.c;
+        S_x = this.slice_to();
+        if (!this.eq_s_b(S_x)) break lab22;
+        this.slice_del();
+      }
+      this.c = this.limit - v_26;
+      this.ket = this.c;
+      if (!this.eq_s_b("'")) break lab15;
+      this.bra = this.c;
+      this.slice_del();
     }
+    this.c = this.limit - v_19;
+    this.c = this.limit_backward;
+    return true;
   }
-  return word;
-}
-function stem(word) {
-  if (word.length < 3) return word;
-  word = word.toLowerCase();
-  const { r1, r2 } = computeRegions(word);
-  word = step1(word, r1, r2);
-  word = step2(word, r1);
-  const result = step3(word, r1);
-  word = result.word;
-  const caseRemoved = result.caseRemoved;
-  word = step4(word, r2);
-  word = step5(word, r1, caseRemoved);
-  word = step6(word, r1, r2, caseRemoved);
-  word = step7(word, r1);
-  return word;
+  stem(input) {
+    this.setCurrent(input);
+    this.#stem();
+    return this.getCurrent();
+  }
+};
+var shared = new FinnishStemmer();
+function stem(token) {
+  return shared.stem(token);
 }
+
+// src/languages/finnish.ts
 var stopWords = /* @__PURE__ */ new Set([
   "olla",
   "olen",
@@ -412,7 +679,6 @@ var stopWords = /* @__PURE__ */ new Set([
   "sill\xE4",
   "silt\xE4",
   "sille",
-  "sin\xE4",
   "siksi",
   "n\xE4m\xE4",
   "n\xE4iden",
@@ -479,7 +745,6 @@ var stopWords = /* @__PURE__ */ new Set([
   "mill\xE4",
   "milt\xE4",
   "mille",
-  "min\xE4",
   "miksi",
   "mitk\xE4",
   "joka",
@@ -512,7 +777,6 @@ var stopWords = /* @__PURE__ */ new Set([
   "mutta",
   "niin",
   "sek\xE4",
-  "sill\xE4",
   "tai",
   "vaan",
   "vai",
@@ -528,9 +792,10 @@ var stopWords = /* @__PURE__ */ new Set([
 ]);
 var finnish = {
   name: "finnish",
+  revision: "cd95cb543801a620",
   stemmer: stem,
   stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9äö]+/gi }
+  tokenizer: { splitPattern: /[^a-z0-9äöš]+/gi }
 };
 
 export { finnish };