@delali/narsil 0.1.14 → 0.2.0

package/dist/languages/hungarian.mjs

@@ -1,348 +1,433 @@
-// src/languages/hungarian.ts
-var VOWELS = "a\xE1e\xE9i\xEDo\xF3\xF6\u0151u\xFA\xFC\u0171";
-function isVowel(ch) {
-  return VOWELS.includes(ch);
-}
-var DOUBLE_CONSONANTS = [
-  ["ccs", "cs"],
-  ["ggy", "gy"],
-  ["lly", "ly"],
-  ["nny", "ny"],
-  ["ssz", "sz"],
-  ["tty", "ty"],
-  ["zzs", "zs"],
-  ["bb", "b"],
-  ["cc", "c"],
-  ["dd", "d"],
-  ["ff", "f"],
-  ["gg", "g"],
-  ["jj", "j"],
-  ["kk", "k"],
-  ["ll", "l"],
-  ["mm", "m"],
-  ["nn", "n"],
-  ["pp", "p"],
-  ["rr", "r"],
-  ["ss", "s"],
-  ["tt", "t"],
-  ["vv", "v"],
-  ["zz", "z"]
+import { BaseStemmer } from '../chunk-U2BKYEC7.mjs';
+
+// src/languages/snowball/hungarian.ts
+var a_0 = [
+  ["\xE1", 1],
+  ["\xE9", 2]
 ];
-var DIGRAPH_STARTS = ["dzs", "cs", "dz", "gy", "ly", "ny", "sz", "ty", "zs"];
-var STEP1_SUFFIXES = ["al", "el"];
-var STEP2_SUFFIXES = [
-  "k\xE9ppen",
-  "onk\xE9nt",
-  "enk\xE9nt",
-  "ank\xE9nt",
-  "k\xE9nt",
-  "k\xE9pp",
-  "ban",
-  "ben",
-  "nak",
-  "nek",
-  "val",
-  "vel",
-  "b\xF3l",
-  "r\xF3l",
-  "t\xF3l",
-  "b\xF6l",
-  "r\u0151l",
-  "t\u0151l",
-  "n\xE1l",
-  "n\xE9l",
-  "hoz",
-  "hez",
-  "h\xF6z",
-  "v\xE1",
-  "v\xE9",
-  "ba",
-  "be",
-  "ra",
-  "re",
-  "an",
-  "en",
-  "on",
-  "\xF6n",
-  "\xE9rt",
-  "kor",
-  "ig",
-  "at",
-  "et",
-  "ot",
-  "\xF6t",
-  "ul",
-  "\xFCl",
-  "n",
-  "t"
+var as_0 = ["a", "e"];
+var a_1 = [
+  ["bb", -1],
+  ["cc", -1],
+  ["dd", -1],
+  ["ff", -1],
+  ["gg", -1],
+  ["jj", -1],
+  ["kk", -1],
+  ["ll", -1],
+  ["mm", -1],
+  ["nn", -1],
+  ["pp", -1],
+  ["rr", -1],
+  ["ccs", -1],
+  ["ss", -1],
+  ["zzs", -1],
+  ["tt", -1],
+  ["vv", -1],
+  ["ggy", -1],
+  ["lly", -1],
+  ["nny", -1],
+  ["tty", -1],
+  ["ssz", -1],
+  ["zz", -1]
 ];
-var STEP3_SUFFIXES = ["\xE1nk\xE9nt", "\xE1n", "\xE9n"];
-var STEP4_SUFFIXES = ["\xE1stul", "\xE9st\xFCl", "astul", "est\xFCl", "stul", "st\xFCl"];
-var STEP5_SUFFIXES = ["\xE1", "\xE9"];
-var STEP6_SUFFIXES = [
-  "\xE9k\xE9i",
-  "\xE1\xE9i",
-  "\xE9\xE9i",
-  "\xE1k\xE9",
-  "\xE9k\xE9",
-  "ok\xE9\xE9",
-  "\xF6k\xE9\xE9",
-  "ak\xE9\xE9",
-  "ek\xE9\xE9",
-  "ok\xE9",
-  "\xF6k\xE9",
-  "ak\xE9",
-  "ek\xE9",
-  "\xE9\xE9",
-  "\xE9i",
-  "k\xE9",
-  "\xE9"
+var a_2 = [
+  ["al", 1],
+  ["el", 1]
 ];
-var STEP7_SUFFIXES = [
-  "\xE1juk",
-  "\xE9j\xFCk",
-  "juk",
-  "j\xFCk",
-  "\xE1nk",
-  "\xE9nk",
-  "\xFCnk",
-  "unk",
-  "\xE1m",
-  "\xE9m",
-  "\xE1d",
-  "\xE9d",
-  "uk",
-  "\xFCk",
-  "ja",
-  "je",
-  "am",
-  "em",
-  "om",
-  "ad",
-  "ed",
-  "od",
-  "\xF6d",
-  "\xE1",
-  "\xE9",
-  "a",
-  "e",
-  "o",
-  "nk",
-  "m",
-  "d"
+var a_3 = [
+  ["ba", -1],
+  ["ra", -1],
+  ["be", -1],
+  ["re", -1],
+  ["ig", -1],
+  ["nak", -1],
+  ["nek", -1],
+  ["val", -1],
+  ["vel", -1],
+  ["ul", -1],
+  ["n\xE1l", -1],
+  ["n\xE9l", -1],
+  ["b\xF3l", -1],
+  ["r\xF3l", -1],
+  ["t\xF3l", -1],
+  ["\xFCl", -1],
+  ["b\u0151l", -1],
+  ["r\u0151l", -1],
+  ["t\u0151l", -1],
+  ["n", -1],
+  ["an", -1, 1],
+  ["ban", -1, 1],
+  ["en", -1, 3],
+  ["ben", -1, 1],
+  ["k\xE9ppen", -1, 2],
+  ["on", -1, 6],
+  ["\xF6n", -1, 7],
+  ["k\xE9pp", -1],
+  ["kor", -1],
+  ["t", -1],
+  ["at", -1, 1],
+  ["et", -1, 2],
+  ["k\xE9nt", -1, 3],
+  ["ank\xE9nt", -1, 1],
+  ["enk\xE9nt", -1, 2],
+  ["onk\xE9nt", -1, 3],
+  ["ot", -1, 7],
+  ["\xE9rt", -1, 8],
+  ["\xF6t", -1, 9],
+  ["hez", -1],
+  ["hoz", -1],
+  ["h\xF6z", -1],
+  ["v\xE1", -1],
+  ["v\xE9", -1]
 ];
-var STEP8_SUFFIXES = [
-  "jaitok",
-  "jeitek",
-  "\xE1itok",
-  "\xE9itek",
-  "jaink",
-  "jeink",
-  "\xE1ink",
-  "\xE9ink",
-  "jaim",
-  "jeim",
-  "jaid",
-  "jeid",
-  "jaik",
-  "jeik",
-  "\xE1im",
-  "\xE9im",
-  "\xE1id",
-  "\xE9id",
-  "\xE1ik",
-  "\xE9ik",
-  "jai",
-  "jei",
-  "\xE1i",
-  "\xE9i",
-  "aink",
-  "eink",
-  "aim",
-  "eim",
-  "aid",
-  "eid",
-  "aik",
-  "eik",
-  "ai",
-  "ei",
-  "itek",
-  "ink",
-  "im",
-  "id",
-  "ik",
-  "i"
+var a_4 = [
+  ["\xE1n", 2],
+  ["\xE9n", 1],
+  ["\xE1nk\xE9nt", 2]
 ];
-var STEP9_SUFFIXES = ["\xE1k", "\xE9k", "\xF6k", "ok", "ek", "ak", "k"];
-function computeR1(word) {
-  if (word.length === 0) return 0;
-  let i = 0;
-  if (isVowel(word[0])) {
-    i = 1;
-    while (i < word.length && isVowel(word[i])) i++;
-    if (i >= word.length) return word.length;
-    let advanced = false;
-    for (const dg of DIGRAPH_STARTS) {
-      if (word.startsWith(dg, i)) {
-        i += dg.length;
-        advanced = true;
-        break;
-      }
-    }
-    if (!advanced) i++;
-  } else {
-    let advanced = false;
-    for (const dg of DIGRAPH_STARTS) {
-      if (word.startsWith(dg, 0)) {
-        i = dg.length;
-        advanced = true;
-        break;
+var as_4 = ["e", "a"];
+var a_5 = [
+  ["stul", 1],
+  ["astul", 1, 1],
+  ["\xE1stul", 2, 2],
+  ["st\xFCl", 1],
+  ["est\xFCl", 1, 1],
+  ["\xE9st\xFCl", 3, 2]
+];
+var as_5 = ["", "a", "e"];
+var a_6 = [
+  ["\xE1", 1],
+  ["\xE9", 1]
+];
+var a_7 = [
+  ["k", 3],
+  ["ak", 3, 1],
+  ["ek", 3, 2],
+  ["ok", 3, 3],
+  ["\xE1k", 1, 4],
+  ["\xE9k", 2, 5],
+  ["\xF6k", 3, 6]
+];
+var as_7 = ["a", "e", ""];
+var a_8 = [
+  ["\xE9i", 1],
+  ["\xE1\xE9i", 3, 1],
+  ["\xE9\xE9i", 2, 2],
+  ["\xE9", 1],
+  ["k\xE9", 1, 1],
+  ["ak\xE9", 1, 1],
+  ["ek\xE9", 1, 2],
+  ["ok\xE9", 1, 3],
+  ["\xE1k\xE9", 3, 4],
+  ["\xE9k\xE9", 2, 5],
+  ["\xF6k\xE9", 1, 6],
+  ["\xE9\xE9", 2, 8]
+];
+var as_8 = ["", "e", "a"];
+var a_9 = [
+  ["a", 1],
+  ["ja", 1, 1],
+  ["d", 1],
+  ["ad", 1, 1],
+  ["ed", 1, 2],
+  ["od", 1, 3],
+  ["\xE1d", 2, 4],
+  ["\xE9d", 3, 5],
+  ["\xF6d", 1, 6],
+  ["e", 1],
+  ["je", 1, 1],
+  ["nk", 1],
+  ["unk", 1, 1],
+  ["\xE1nk", 2, 2],
+  ["\xE9nk", 3, 3],
+  ["\xFCnk", 1, 4],
+  ["uk", 1],
+  ["juk", 1, 1],
+  ["\xE1juk", 2, 1],
+  ["\xFCk", 1],
+  ["j\xFCk", 1, 1],
+  ["\xE9j\xFCk", 3, 1],
+  ["m", 1],
+  ["am", 1, 1],
+  ["em", 1, 2],
+  ["om", 1, 3],
+  ["\xE1m", 2, 4],
+  ["\xE9m", 3, 5],
+  ["o", 1],
+  ["\xE1", 2],
+  ["\xE9", 3]
+];
+var as_9 = ["", "a", "e"];
+var a_10 = [
+  ["id", 1],
+  ["aid", 1, 1],
+  ["jaid", 1, 1],
+  ["eid", 1, 3],
+  ["jeid", 1, 1],
+  ["\xE1id", 2, 5],
+  ["\xE9id", 3, 6],
+  ["i", 1],
+  ["ai", 1, 1],
+  ["jai", 1, 1],
+  ["ei", 1, 3],
+  ["jei", 1, 1],
+  ["\xE1i", 2, 5],
+  ["\xE9i", 3, 6],
+  ["itek", 1],
+  ["eitek", 1, 1],
+  ["jeitek", 1, 1],
+  ["\xE9itek", 3, 3],
+  ["ik", 1],
+  ["aik", 1, 1],
+  ["jaik", 1, 1],
+  ["eik", 1, 3],
+  ["jeik", 1, 1],
+  ["\xE1ik", 2, 5],
+  ["\xE9ik", 3, 6],
+  ["ink", 1],
+  ["aink", 1, 1],
+  ["jaink", 1, 1],
+  ["eink", 1, 3],
+  ["jeink", 1, 1],
+  ["\xE1ink", 2, 5],
+  ["\xE9ink", 3, 6],
+  ["aitok", 1],
+  ["jaitok", 1, 1],
+  ["\xE1itok", 2],
+  ["im", 1],
+  ["aim", 1, 1],
+  ["jaim", 1, 1],
+  ["eim", 1, 3],
+  ["jeim", 1, 1],
+  ["\xE1im", 2, 5],
+  ["\xE9im", 3, 6]
+];
+var as_10 = ["", "a", "e"];
+var g_v = [
+  17,
+  65,
+  16,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  1,
+  17,
+  36,
+  10,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  0,
+  1,
+  0,
+  0,
+  0,
+  1
+];
+var HungarianStemmer = class extends BaseStemmer {
+  #r_double() {
+    const v_1 = this.limit - this.c;
+    if (this.find_among_b(a_1) === 0) return false;
+    this.c = this.limit - v_1;
+    return true;
+  }
+  #r_undouble() {
+    if (this.c <= this.limit_backward) return false;
+    this.c--;
+    this.ket = this.c;
+    if (this.c <= this.limit_backward) return false;
+    this.c--;
+    this.bra = this.c;
+    this.slice_del();
+    return true;
+  }
+  #stem() {
+    let a;
+    let I_p1;
+    const v_1 = this.c;
+    lab0: {
+      I_p1 = this.limit;
+      lab1: {
+        const v_2 = this.c;
+        lab2: {
+          if (!this.in_grouping(g_v, 97, 369)) break lab2;
+          const v_3 = this.c;
+          lab3: {
+            if (!this.go_in_grouping(g_v, 97, 369)) break lab3;
+            this.c++;
+            I_p1 = this.c;
+          }
+          this.c = v_3;
+          break lab1;
+        }
+        this.c = v_2;
+        if (!this.go_out_grouping(g_v, 97, 369)) break lab0;
+        this.c++;
+        I_p1 = this.c;
       }
     }
-    if (!advanced) i = 1;
-    while (i < word.length && !isVowel(word[i])) i++;
-    if (i >= word.length) return word.length;
-    i++;
-  }
-  if (i <= word.length) return i;
-  return word.length;
-}
-function endsWithDouble(word) {
-  return DOUBLE_CONSONANTS.some(([dbl]) => word.endsWith(dbl));
-}
-function undoubleConsonant(word) {
-  for (const [dbl, single] of DOUBLE_CONSONANTS) {
-    if (word.endsWith(dbl)) {
-      return word.slice(0, word.length - dbl.length) + single;
+    this.c = v_1;
+    this.limit_backward = this.c;
+    this.c = this.limit;
+    const v_4 = this.limit - this.c;
+    lab4: {
+      this.ket = this.c;
+      if (this.find_among_b(a_2) === 0) break lab4;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab4;
+      if (!this.#r_double()) break lab4;
+      this.slice_del();
+      if (!this.#r_undouble()) break lab4;
     }
-  }
-  return word;
-}
-function inR1(word, r1, suffixLen) {
-  return word.length - suffixLen >= r1;
-}
-function trySuffix(word, suffixes) {
-  for (const s of suffixes) {
-    if (word.endsWith(s)) return s;
-  }
-  return null;
-}
-function step1Instrumental(word, r1) {
-  const matched = trySuffix(word, STEP1_SUFFIXES);
-  if (matched && inR1(word, r1, matched.length)) {
-    const stripped = word.slice(0, -matched.length);
-    if (endsWithDouble(stripped)) {
-      return undoubleConsonant(stripped);
+    this.c = this.limit - v_4;
+    const v_5 = this.limit - this.c;
+    lab5: {
+      this.ket = this.c;
+      if (this.find_among_b(a_3) === 0) break lab5;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab5;
+      this.slice_del();
+      this.ket = this.c;
+      a = this.find_among_b(a_0);
+      if (a === 0) break lab5;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab5;
+      this.slice_from(as_0[a - 1]);
     }
-  }
-  return word;
-}
-function step2CaseEndings(word, r1) {
-  const matched = trySuffix(word, STEP2_SUFFIXES);
-  if (matched && inR1(word, r1, matched.length)) {
-    const stripped = word.slice(0, -matched.length);
-    if (stripped.endsWith("\xE1")) {
-      return `${stripped.slice(0, -1)}a`;
+    this.c = this.limit - v_5;
+    const v_6 = this.limit - this.c;
+    lab6: {
+      this.ket = this.c;
+      a = this.find_among_b(a_4);
+      if (a === 0) break lab6;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab6;
+      this.slice_from(as_4[a - 1]);
     }
-    if (stripped.endsWith("\xE9")) {
-      return `${stripped.slice(0, -1)}e`;
+    this.c = this.limit - v_6;
+    const v_7 = this.limit - this.c;
+    lab7: {
+      this.ket = this.c;
+      a = this.find_among_b(a_5);
+      if (a === 0) break lab7;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab7;
+      this.slice_from(as_5[a - 1]);
     }
-    return stripped;
-  }
-  return word;
-}
-function step3Emotive(word, r1) {
-  const matched = trySuffix(word, STEP3_SUFFIXES);
-  if (matched && inR1(word, r1, matched.length)) {
-    const stripped = word.slice(0, -matched.length);
-    if (matched === "\xE9n") return `${stripped}e`;
-    return `${stripped}a`;
-  }
-  return word;
-}
-function step4Comitative(word, r1) {
-  const matched = trySuffix(word, STEP4_SUFFIXES);
-  if (matched && inR1(word, r1, matched.length)) {
-    const stripped = word.slice(0, -matched.length);
-    if (matched === "\xE1stul") return `${stripped}a`;
-    if (matched === "\xE9st\xFCl") return `${stripped}e`;
-    return stripped;
-  }
-  return word;
-}
-function step5LongVowel(word, r1) {
-  const matched = trySuffix(word, STEP5_SUFFIXES);
-  if (matched && inR1(word, r1, matched.length)) {
-    const stripped = word.slice(0, -matched.length);
-    if (endsWithDouble(stripped)) {
-      return undoubleConsonant(stripped);
+    this.c = this.limit - v_7;
+    const v_8 = this.limit - this.c;
+    lab8: {
+      this.ket = this.c;
+      if (this.find_among_b(a_6) === 0) break lab8;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab8;
+      if (!this.#r_double()) break lab8;
+      this.slice_del();
+      if (!this.#r_undouble()) break lab8;
     }
-  }
-  return word;
-}
-function step6Possessive(word, r1) {
-  const matched = trySuffix(word, STEP6_SUFFIXES);
-  if (matched && inR1(word, r1, matched.length)) {
-    const stripped = word.slice(0, -matched.length);
-    if (matched === "\xE1k\xE9" || matched === "\xE1\xE9i") return `${stripped}a`;
-    if (matched === "\xE9k\xE9" || matched === "\xE9\xE9i" || matched === "\xE9\xE9") return `${stripped}e`;
-    return stripped;
-  }
-  return word;
-}
-function step7SingularPossessive(word, r1) {
-  const matched = trySuffix(word, STEP7_SUFFIXES);
-  if (matched && inR1(word, r1, matched.length)) {
-    const stripped = word.slice(0, -matched.length);
-    if (matched === "\xE1juk" || matched === "\xE1nk" || matched === "\xE1m" || matched === "\xE1d" || matched === "\xE1") {
-      return `${stripped}a`;
+    this.c = this.limit - v_8;
+    const v_9 = this.limit - this.c;
+    lab9: {
+      this.ket = this.c;
+      a = this.find_among_b(a_8);
+      if (a === 0) break lab9;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab9;
+      this.slice_from(as_8[a - 1]);
     }
-    if (matched === "\xE9j\xFCk" || matched === "\xE9nk" || matched === "\xE9m" || matched === "\xE9d" || matched === "\xE9") {
-      return `${stripped}e`;
+    this.c = this.limit - v_9;
+    const v_10 = this.limit - this.c;
+    lab10: {
+      this.ket = this.c;
+      a = this.find_among_b(a_9);
+      if (a === 0) break lab10;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab10;
+      this.slice_from(as_9[a - 1]);
     }
-    return stripped;
-  }
-  return word;
-}
-function step8PluralPossessive(word, r1) {
-  const matched = trySuffix(word, STEP8_SUFFIXES);
-  if (matched && inR1(word, r1, matched.length)) {
-    const stripped = word.slice(0, -matched.length);
-    if (matched === "\xE1itok" || matched === "\xE1ink" || matched === "\xE1im" || matched === "\xE1id" || matched === "\xE1ik" || matched === "\xE1i") {
-      return `${stripped}a`;
+    this.c = this.limit - v_10;
+    const v_11 = this.limit - this.c;
+    lab11: {
+      this.ket = this.c;
+      a = this.find_among_b(a_10);
+      if (a === 0) break lab11;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab11;
+      this.slice_from(as_10[a - 1]);
     }
-    if (matched === "\xE9itek" || matched === "\xE9ink" || matched === "\xE9im" || matched === "\xE9id" || matched === "\xE9ik" || matched === "\xE9i") {
-      return `${stripped}e`;
+    this.c = this.limit - v_11;
+    const v_12 = this.limit - this.c;
+    lab12: {
+      this.ket = this.c;
+      a = this.find_among_b(a_7);
+      if (a === 0) break lab12;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        I_p1 > this.c
+      ) break lab12;
+      this.slice_from(as_7[a - 1]);
     }
-    return stripped;
+    this.c = this.limit - v_12;
+    this.c = this.limit_backward;
+    return true;
   }
-  return word;
-}
-function step9Plural(word, r1) {
-  const matched = trySuffix(word, STEP9_SUFFIXES);
-  if (matched && inR1(word, r1, matched.length)) {
-    const stripped = word.slice(0, -matched.length);
-    if (matched === "\xE1k") return `${stripped}a`;
-    if (matched === "\xE9k") return `${stripped}e`;
-    return stripped;
+  stem(input) {
+    this.setCurrent(input);
+    this.#stem();
+    return this.getCurrent();
   }
-  return word;
-}
-function stem(word) {
-  if (word.length < 2) return word;
-  word = word.toLowerCase();
-  const r1 = computeR1(word);
-  word = step1Instrumental(word, r1);
-  word = step2CaseEndings(word, r1);
-  word = step3Emotive(word, r1);
-  word = step4Comitative(word, r1);
-  word = step5LongVowel(word, r1);
-  word = step6Possessive(word, r1);
-  word = step7SingularPossessive(word, r1);
-  word = step8PluralPossessive(word, r1);
-  word = step9Plural(word, r1);
-  return word;
+};
+var shared = new HungarianStemmer();
+function stem(token) {
+  return shared.stem(token);
 }
+
+// src/languages/hungarian.ts
 var stopWords = /* @__PURE__ */ new Set([
   "a",
   "abba",
@@ -592,6 +677,7 @@ var stopWords = /* @__PURE__ */ new Set([
 ]);
 var hungarian = {
   name: "hungarian",
+  revision: "7b9c2fc79181fc11",
   stemmer: stem,
   stopWords,
   tokenizer: { splitPattern: /[^a-z0-9áéíóöőúüű]+/gi }