@delali/narsil 0.1.15 → 0.2.1-next.25

package/dist/languages/polish.d.ts

@@ -0,0 +1,14 @@
+import { L as LanguageModule } from '../language-DB8KG1z5.js';
+
+/**
+ * Polish analysis: the Snowball stemmer, the stop word list, and the rules
+ * that split Polish text into tokens.
+ *
+ * Import it and pass it to {@link registerLanguage} before you create an index
+ * whose `language` is `polish`.
+ *
+ * @public
+ */
+declare const polish: LanguageModule;
+
+export { polish };

package/dist/languages/polish.mjs

@@ -0,0 +1,614 @@
+import { BaseStemmer } from '../chunk-U2BKYEC7.mjs';
+
+// src/languages/snowball/polish.ts
+var a_0 = [
+  ["by\u015Bcie", 1],
+  ["bym", 1],
+  ["by", 1],
+  ["by\u015Bmy", 1],
+  ["by\u015B", 1]
+];
+var a_1 = [
+  ["\u0105c", 1],
+  ["aj\u0105c", 1, 1],
+  ["sz\u0105c", 2, 2],
+  ["sz", 1],
+  ["iejsz", 1, 1]
+];
+var as_1 = ["", "s"];
+var a_2 = [
+  ["a", 1, 0, 1],
+  ["\u0105ca", 1, 1],
+  ["aj\u0105ca", 1, 1],
+  ["sz\u0105ca", 2, 2],
+  ["ia", 1, 4, 1],
+  ["sza", 1, 5],
+  ["iejsza", 1, 1],
+  ["a\u0142a", 1, 7],
+  ["ia\u0142a", 1, 1],
+  ["i\u0142a", 1, 9],
+  ["\u0105c", 1],
+  ["aj\u0105c", 1, 1],
+  ["e", 1, 0, 1],
+  ["\u0105ce", 1, 1],
+  ["aj\u0105ce", 1, 1],
+  ["sz\u0105ce", 2, 2],
+  ["ie", 1, 4, 1],
+  ["cie", 1, 1],
+  ["acie", 1, 1],
+  ["ecie", 1, 2],
+  ["icie", 1, 3],
+  ["ajcie", 1, 4],
+  ["li\u015Bcie", 4, 5],
+  ["ali\u015Bcie", 1, 1],
+  ["ieli\u015Bcie", 1, 2],
+  ["ili\u015Bcie", 1, 3],
+  ["\u0142y\u015Bcie", 4, 9],
+  ["a\u0142y\u015Bcie", 1, 1],
+  ["ia\u0142y\u015Bcie", 1, 1],
+  ["i\u0142y\u015Bcie", 1, 3],
+  ["sze", 1, 18],
+  ["iejsze", 1, 1],
+  ["ach", 1, 0, 1],
+  ["iach", 1, 1, 1],
+  ["ich", 5],
+  ["ych", 5],
+  ["i", 1, 0, 1],
+  ["ali", 1, 1],
+  ["ieli", 1, 2],
+  ["ili", 1, 3],
+  ["ami", 1, 4, 1],
+  ["iami", 1, 1, 1],
+  ["imi", 5, 6],
+  ["ymi", 5, 7],
+  ["owi", 1, 8, 1],
+  ["iowi", 1, 1, 1],
+  ["aj", 1],
+  ["ej", 5],
+  ["iej", 5, 1],
+  ["am", 1],
+  ["a\u0142am", 1, 1],
+  ["ia\u0142am", 1, 1],
+  ["i\u0142am", 1, 3],
+  ["em", 1, 0, 1],
+  ["iem", 1, 1, 1],
+  ["a\u0142em", 1, 2],
+  ["ia\u0142em", 1, 1],
+  ["i\u0142em", 1, 4],
+  ["im", 5],
+  ["om", 1, 0, 1],
+  ["iom", 1, 1, 1],
+  ["ym", 5],
+  ["o", 1, 0, 1],
+  ["ego", 5, 1],
+  ["iego", 5, 1],
+  ["a\u0142o", 1, 3],
+  ["ia\u0142o", 1, 1],
+  ["i\u0142o", 1, 5],
+  ["u", 1, 0, 1],
+  ["iu", 1, 1, 1],
+  ["emu", 5, 2],
+  ["iemu", 5, 1],
+  ["\xF3w", 1, 0, 1],
+  ["y", 5],
+  ["amy", 1, 1],
+  ["emy", 1, 2],
+  ["imy", 1, 3],
+  ["li\u015Bmy", 4, 4],
+  ["ali\u015Bmy", 1, 1],
+  ["ieli\u015Bmy", 1, 2],
+  ["ili\u015Bmy", 1, 3],
+  ["\u0142y\u015Bmy", 4, 8],
+  ["a\u0142y\u015Bmy", 1, 1],
+  ["ia\u0142y\u015Bmy", 1, 1],
+  ["i\u0142y\u015Bmy", 1, 3],
+  ["a\u0142y", 1, 12],
+  ["ia\u0142y", 1, 1],
+  ["i\u0142y", 1, 14],
+  ["asz", 1],
+  ["esz", 1],
+  ["isz", 1],
+  ["\u0105", 1, 0, 1],
+  ["\u0105c\u0105", 1, 1],
+  ["aj\u0105c\u0105", 1, 1],
+  ["sz\u0105c\u0105", 2, 2],
+  ["i\u0105", 1, 4, 1],
+  ["aj\u0105", 1, 5],
+  ["sz\u0105", 3, 6],
+  ["iejsz\u0105", 1, 1],
+  ["a\u0107", 1],
+  ["ie\u0107", 1],
+  ["i\u0107", 1],
+  ["\u0105\u0107", 1],
+  ["a\u015B\u0107", 1],
+  ["e\u015B\u0107", 1],
+  ["\u0119", 1],
+  ["sz\u0119", 2, 1],
+  ["a\u0142", 1],
+  ["ia\u0142", 1, 1],
+  ["i\u0142", 1],
+  ["\u0142a\u015B", 4],
+  ["a\u0142a\u015B", 1, 1],
+  ["ia\u0142a\u015B", 1, 1],
+  ["i\u0142a\u015B", 1, 3],
+  ["\u0142e\u015B", 4],
+  ["a\u0142e\u015B", 1, 1],
+  ["ia\u0142e\u015B", 1, 1],
+  ["i\u0142e\u015B", 1, 3]
+];
+var a_3 = [
+  ["\u0107", 1],
+  ["\u0144", 2],
+  ["\u015B", 3],
+  ["\u017A", 4]
+];
+var as_3 = ["c", "n", "s", "z"];
+var g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 16, 0, 0, 1];
+var PolishStemmer = class extends BaseStemmer {
+  #I_p1 = 0;
+  #r_R1() {
+    return this.#I_p1 <= this.c;
+  }
+  #stem() {
+    let a;
+    const v_1 = this.c;
+    lab0: {
+      this.#I_p1 = this.limit;
+      if (!this.go_out_grouping(g_v, 97, 281)) break lab0;
+      this.c++;
+      if (!this.go_in_grouping(g_v, 97, 281)) break lab0;
+      this.c++;
+      this.#I_p1 = this.c;
+    }
+    this.c = v_1;
+    lab1: {
+      const v_2 = this.c;
+      lab2: {
+        if (this.c + 2 > this.limit) break lab2;
+        this.c += 2;
+        this.limit_backward = this.c;
+        this.c = this.limit;
+        const v_3 = this.limit - this.c;
+        lab3: {
+          if (this.c < this.#I_p1) break lab3;
+          const v_4 = this.limit_backward;
+          this.limit_backward = this.#I_p1;
+          this.ket = this.c;
+          if (this.find_among_b(a_0) === 0) {
+            this.limit_backward = v_4;
+            break lab3;
+          }
+          this.bra = this.c;
+          this.limit_backward = v_4;
+          this.slice_del();
+        }
+        this.c = this.limit - v_3;
+        this.ket = this.c;
+        a = this.find_among_b(a_2, this.#r_R1);
+        if (a === 0) break lab2;
+        this.bra = this.c;
+        switch (a) {
+          case 1: {
+            this.slice_del();
+            break;
+          }
+          case 2: {
+            this.slice_from("s");
+            break;
+          }
+          case 3: {
+            lab4: {
+              const v_5 = this.limit - this.c;
+              lab5: {
+                if (
+                  /**@type {boolean}*/
+                  this.#I_p1 > this.c
+                ) break lab5;
+                this.slice_del();
+                break lab4;
+              }
+              this.c = this.limit - v_5;
+              this.slice_from("s");
+            }
+            break;
+          }
+          case 4: {
+            this.slice_from("\u0142");
+            break;
+          }
+          case 5: {
+            this.slice_del();
+            const v_6 = this.limit - this.c;
+            lab6: {
+              this.ket = this.c;
+              a = this.find_among_b(a_1);
+              if (a === 0) {
+                this.c = this.limit - v_6;
+                break lab6;
+              }
+              this.bra = this.c;
+              this.slice_from(as_1[a - 1]);
+            }
+            break;
+          }
+        }
+        const v_7 = this.limit - this.c;
+        lab7: {
+          this.ket = this.c;
+          if (!this.eq_s_b("'")) {
+            this.c = this.limit - v_7;
+            break lab7;
+          }
+          this.bra = this.c;
+          this.slice_del();
+        }
+        this.c = this.limit_backward;
+        break lab1;
+      }
+      this.c = v_2;
+      this.limit_backward = this.c;
+      this.c = this.limit;
+      this.ket = this.c;
+      a = this.find_among_b(a_3);
+      if (a === 0) return false;
+      this.bra = this.c;
+      if (
+        /**@type {boolean}*/
+        this.c <= this.limit_backward
+      ) return false;
+      this.slice_from(as_3[a - 1]);
+      this.c = this.limit_backward;
+    }
+    return true;
+  }
+  stem(input) {
+    this.setCurrent(input);
+    this.#stem();
+    return this.getCurrent();
+  }
+};
+var shared = new PolishStemmer();
+function stem(token) {
+  return shared.stem(token);
+}
+
+// src/languages/polish.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "a",
+  "aby",
+  "ach",
+  "acz",
+  "aczkolwiek",
+  "aj",
+  "albo",
+  "ale",
+  "ale\u017C",
+  "ani",
+  "a\u017C",
+  "bardziej",
+  "bardzo",
+  "b\u0119d\u0105",
+  "b\u0119dzie",
+  "bez",
+  "bo",
+  "bowiem",
+  "by",
+  "by\u0107",
+  "by\u0142",
+  "by\u0142a",
+  "byli",
+  "by\u0142o",
+  "by\u0142y",
+  "bym",
+  "bynajmniej",
+  "ca\u0142a",
+  "cali",
+  "ca\u0142y",
+  "chce",
+  "cho\u0107",
+  "ci",
+  "ci\u0119",
+  "ciebie",
+  "co",
+  "cokolwiek",
+  "coraz",
+  "co\u015B",
+  "czasami",
+  "czasem",
+  "czemu",
+  "cz\u0119sto",
+  "czy",
+  "czyli",
+  "daleko",
+  "dla",
+  "dlaczego",
+  "dlatego",
+  "do",
+  "dobrze",
+  "dok\u0105d",
+  "do\u015B\u0107",
+  "dr",
+  "du\u017Co",
+  "dwa",
+  "dwaj",
+  "dwie",
+  "dwoje",
+  "dzi\u015B",
+  "dzisiaj",
+  "gdy",
+  "gdyby",
+  "gdy\u017C",
+  "gdzie",
+  "gdziekolwiek",
+  "gdzie\u015B",
+  "go",
+  "godz",
+  "hab",
+  "i",
+  "ich",
+  "ii",
+  "iii",
+  "ile",
+  "im",
+  "inna",
+  "inne",
+  "inny",
+  "innych",
+  "in\u017C",
+  "iv",
+  "ix",
+  "i\u017C",
+  "ja",
+  "j\u0105",
+  "jak",
+  "jaka\u015B",
+  "jakby",
+  "jaki",
+  "jakich\u015B",
+  "jakie",
+  "jaki\u015B",
+  "jaki\u017C",
+  "jakkolwiek",
+  "jako",
+  "jako\u015B",
+  "je",
+  "jeden",
+  "jedna",
+  "jednak",
+  "jednak\u017Ce",
+  "jedno",
+  "jednym",
+  "jedynie",
+  "jego",
+  "jej",
+  "jemu",
+  "je\u015Bli",
+  "jest",
+  "jestem",
+  "jeszcze",
+  "je\u017Celi",
+  "ju\u017C",
+  "ka\u017Cdy",
+  "kiedy",
+  "kierunku",
+  "kilka",
+  "kilku",
+  "kim\u015B",
+  "kto",
+  "ktokolwiek",
+  "kt\xF3ra",
+  "kt\xF3re",
+  "kt\xF3rego",
+  "kt\xF3rej",
+  "kt\xF3ry",
+  "kt\xF3rych",
+  "kt\xF3rym",
+  "kt\xF3rzy",
+  "kto\u015B",
+  "ku",
+  "lat",
+  "lecz",
+  "lub",
+  "ma",
+  "maj\u0105",
+  "ma\u0142o",
+  "mam",
+  "mamy",
+  "mgr",
+  "mi",
+  "mia\u0142",
+  "mi\u0119dzy",
+  "mimo",
+  "mn\u0105",
+  "mnie",
+  "mog\u0105",
+  "moi",
+  "moim",
+  "m\xF3j",
+  "moja",
+  "moje",
+  "mo\u017Ce",
+  "mo\u017Cliwe",
+  "mo\u017Cna",
+  "mu",
+  "musi",
+  "my",
+  "na",
+  "nad",
+  "nam",
+  "nami",
+  "nas",
+  "nasi",
+  "nasz",
+  "nasza",
+  "nasze",
+  "naszego",
+  "naszych",
+  "natomiast",
+  "natychmiast",
+  "nawet",
+  "ni\u0105",
+  "nic",
+  "nich",
+  "nie",
+  "niech",
+  "niego",
+  "niej",
+  "niemu",
+  "nigdy",
+  "nim",
+  "nimi",
+  "ni\u017C",
+  "no",
+  "nowe",
+  "np",
+  "nr",
+  "o",
+  "obok",
+  "od",
+  "ok",
+  "oko\u0142o",
+  "on",
+  "ona",
+  "one",
+  "oni",
+  "ono",
+  "oraz",
+  "oto",
+  "owszem",
+  "pan",
+  "pana",
+  "pani",
+  "pl",
+  "po",
+  "pod",
+  "podczas",
+  "pomimo",
+  "ponad",
+  "poniewa\u017C",
+  "powinien",
+  "powinna",
+  "powinni",
+  "powinno",
+  "poza",
+  "prawie",
+  "prof",
+  "przecie\u017C",
+  "przed",
+  "przede",
+  "przedtem",
+  "przez",
+  "przy",
+  "raz",
+  "razie",
+  "roku",
+  "r\xF3wnie\u017C",
+  "s\u0105",
+  "sam",
+  "sama",
+  "si\u0119",
+  "sk\u0105d",
+  "sob\u0105",
+  "sobie",
+  "spos\xF3b",
+  "swoje",
+  "ta",
+  "tak",
+  "taka",
+  "taki",
+  "takich",
+  "takie",
+  "tak\u017Ce",
+  "tam",
+  "te",
+  "t\u0119",
+  "tego",
+  "tej",
+  "tel",
+  "temu",
+  "ten",
+  "teraz",
+  "te\u017C",
+  "to",
+  "tob\u0105",
+  "tobie",
+  "tote\u017C",
+  "totob\u0105",
+  "trzeba",
+  "tu",
+  "tutaj",
+  "twoi",
+  "twoim",
+  "tw\xF3j",
+  "twoja",
+  "twoje",
+  "twym",
+  "ty",
+  "tych",
+  "tylko",
+  "tym",
+  "tys",
+  "tzw",
+  "u",
+  "ul",
+  "vi",
+  "vii",
+  "viii",
+  "vol",
+  "w",
+  "wam",
+  "wami",
+  "was",
+  "wasi",
+  "wasz",
+  "wasza",
+  "wasze",
+  "we",
+  "wed\u0142ug",
+  "wie",
+  "wi\u0119c",
+  "wi\u0119cej",
+  "wiele",
+  "wielu",
+  "w\u0142a\u015Bnie",
+  "w\u015Br\xF3d",
+  "wszyscy",
+  "wszystkich",
+  "wszystkie",
+  "wszystkim",
+  "wszystko",
+  "wtedy",
+  "www",
+  "wy",
+  "xi",
+  "xii",
+  "xiii",
+  "xiv",
+  "xv",
+  "z",
+  "za",
+  "\u017Caden",
+  "\u017Cadna",
+  "\u017Cadne",
+  "\u017Cadnych",
+  "zapewne",
+  "za\u015B",
+  "zawsze",
+  "ze",
+  "\u017Ce",
+  "\u017Ceby",
+  "zeznowu",
+  "z\u0142",
+  "zn\xF3w",
+  "znowu",
+  "zosta\u0142"
+]);
+var polish = {
+  name: "polish",
+  revision: "373ece41a2c5684b",
+  stemmer: stem,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9ąćęłńóśźż]+/gi }
+};
+
+export { polish };

package/dist/languages/portuguese.d.ts

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