@delali/narsil 0.1.15 → 0.2.1-next.25

package/dist/languages/belarusian.d.ts

@@ -0,0 +1,15 @@
+import { L as LanguageModule } from '../language-DB8KG1z5.js';
+
+/**
+ * Belarusian analysis: the stop word list and the rules that split Belarusian
+ * 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 `belarusian`.
+ *
+ * @public
+ */
+declare const belarusian: LanguageModule;
+
+export { belarusian };

package/dist/languages/belarusian.mjs

@@ -0,0 +1,100 @@
+// src/languages/belarusian.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "\u0430",
+  "\u0430\u0431",
+  "\u0430\u0431\u043E",
+  "\u0430\u0434",
+  "\u0430\u0434\u0437\u0456\u043D",
+  "\u0430\u043B\u0435",
+  "\u0431\u0435\u0437",
+  "\u0431\u043E",
+  "\u0431\u044B\u043B\u0430",
+  "\u0431\u044B\u043B\u0456",
+  "\u0431\u044B\u0446\u044C",
+  "\u0431\u044B\u045E",
+  "\u0432\u0430\u0441",
+  "\u0432\u0430\u0448",
+  "\u0432\u0435\u043B\u044C\u043C\u0456",
+  "\u0432\u044B",
+  "\u0433\u044D\u0442\u0430",
+  "\u0433\u044D\u0442\u0430\u044F",
+  "\u0433\u044D\u0442\u044B",
+  "\u0433\u044D\u0442\u044B\u044F",
+  "\u0434\u0430",
+  "\u0434\u0432\u0430",
+  "\u0434\u0437\u0435",
+  "\u0434\u043B\u044F",
+  "\u0434\u044B",
+  "\u0437",
+  "\u0437'\u044F\u045E\u043B\u044F\u0435\u0446\u0446\u0430",
+  "\u0437\u0430",
+  "\u043A\u0430\u0431",
+  "\u043A\u0430\u043B\u044F",
+  "\u043A\u0430\u043B\u0456",
+  "\u043A\u043E\u0436\u043D\u044B",
+  "\u043A\u0443\u0434\u044B",
+  "\u043C\u043E\u0439",
+  "\u043C\u044B",
+  "\u043C\u044F\u043D\u0435",
+  "\u043D\u0430",
+  "\u043D\u0430\u0434",
+  "\u043D\u0430\u0441",
+  "\u043D\u0430\u0448",
+  "\u043D\u0435",
+  "\u043D\u044F",
+  "\u043D\u044F\u043C\u0430",
+  "\u043F\u0430",
+  "\u043F\u0430\u0434",
+  "\u043F\u0430\u043C\u0456\u0436",
+  "\u043F\u0430\u0441\u043B\u044F",
+  "\u043F\u0435\u0440\u0430\u0434",
+  "\u043F\u0440\u0430",
+  "\u043F\u0440\u0430\u0437",
+  "\u043F\u0440\u044B",
+  "\u0441\u0430",
+  "\u0441\u0430\u043C",
+  "\u0441\u0432\u0430\u0435",
+  "\u0441\u0432\u0430\u044E",
+  "\u0441\u0432\u043E\u0439",
+  "\u0441\u044F\u0440\u043E\u0434",
+  "\u0442\u0430\u043A",
+  "\u0442\u0430\u043A\u0441\u0430\u043C\u0430",
+  "\u0442\u0430\u043C\u0443",
+  "\u0442\u0430\u044F",
+  "\u0442\u0432\u043E\u0439",
+  "\u0442\u043E\u0439",
+  "\u0442\u043E\u043B\u044C\u043A\u0456",
+  "\u0442\u044B",
+  "\u0442\u044B\u044F",
+  "\u0443",
+  "\u0443\u0436\u043E",
+  "\u0443\u0441\u0435",
+  "\u0443\u0441\u0451",
+  "\u0446\u044F\u0431\u0435",
+  "\u0446\u0456",
+  "\u0447\u0430\u043C\u0443",
+  "\u0448\u0442\u043E",
+  "\u044F",
+  "\u044F\u0433\u043E",
+  "\u044F\u0435",
+  "\u044F\u043A",
+  "\u044F\u043D\u0430",
+  "\u044F\u043D\u043E",
+  "\u044F\u043D\u044B",
+  "\u044F\u0448\u0447\u044D",
+  "\u0451\u043D",
+  "\u0451\u0441\u0446\u044C",
+  "\u0456",
+  "\u0456\u043D\u0448\u044B",
+  "\u0456\u0445",
+  "\u045E"
+]);
+var belarusian = {
+  name: "belarusian",
+  revision: "0c1d3db2f7d0be62",
+  stemmer: null,
+  stopWords,
+  tokenizer: { splitPattern: /[^\u0400-\u04FF0-9']+/gi }
+};
+
+export { belarusian };

package/dist/languages/bengali.d.ts

@@ -0,0 +1,15 @@
+import { L as LanguageModule } from '../language-DB8KG1z5.js';
+
+/**
+ * Bengali analysis: the stop word list and the rules that split Bengali
+ * 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 `bengali`.
+ *
+ * @public
+ */
+declare const bengali: LanguageModule;
+
+export { bengali };

package/dist/languages/bengali.mjs

@@ -0,0 +1,128 @@
+// src/languages/bengali.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "\u0985\u09A8\u09C7\u0995",
+  "\u0985\u09A8\u09CD\u09AF",
+  "\u0985\u09AC\u09B6\u09CD\u09AF",
+  "\u0986\u0997\u09C7",
+  "\u0986\u099B\u09C7",
+  "\u0986\u099C",
+  "\u0986\u09AC\u09BE\u09B0",
+  "\u0986\u09AE\u09B0\u09BE",
+  "\u0986\u09AE\u09BE\u09A6\u09C7\u09B0",
+  "\u0986\u09B0",
+  "\u0987",
+  "\u0989\u09A4\u09CD\u09A4\u09B0",
+  "\u0989\u09AA\u09B0",
+  "\u0989\u09AA\u09B0\u09C7",
+  "\u098F",
+  "\u098F\u0987",
+  "\u098F\u0995\u09CD",
+  "\u098F\u0996\u09A8",
+  "\u098F\u09A4",
+  "\u098F\u09AC",
+  "\u098F\u09AE\u09A8",
+  "\u098F\u09AE\u09A8\u09BF",
+  "\u098F\u09B0",
+  "\u098F\u09B8",
+  "\u098F\u09B8\u09C7",
+  "\u0993",
+  "\u0993\u0987",
+  "\u0995\u09AE\u09A8\u09C7",
+  "\u0995\u09AF\u09BC\u09C7\u0995",
+  "\u0995\u09B0\u09BE",
+  "\u0995\u09B0\u09C7",
+  "\u0995\u09BE\u099B\u09C7",
+  "\u0995\u09BE\u099C",
+  "\u0995\u09BE\u099C\u09C7",
+  "\u0995\u09BE\u09B0\u09A3",
+  "\u0995\u09BF",
+  "\u0995\u09BF\u099B\u09C1",
+  "\u0995\u09C7",
+  "\u0995\u09C7\u0989",
+  "\u0995\u09C7\u0996\u09BE",
+  "\u0995\u09C7\u09A8",
+  "\u0995\u09CB\u099F\u09BF",
+  "\u0995\u09CB\u09A8\u09CB",
+  "\u0996\u09C1\u09AC",
+  "\u0997\u09BF\u09AF\u09BC\u09C7",
+  "\u0997\u09C7\u09B2",
+  "\u099A\u09BE\u09B0",
+  "\u099A\u09BE\u09B2\u09C1",
+  "\u099A\u09C7\u09B7\u09CD\u099F\u09BE",
+  "\u099B\u09BF\u09B2",
+  "\u099C\u09BE\u09A8\u09BE",
+  "\u099C\u09CD\u09A8\u099C\u09A8",
+  "\u099F\u09BF",
+  "\u09A4\u0996\u09A8",
+  "\u09A4\u09AC\u09C7",
+  "\u09A4\u09BE",
+  "\u09A4\u09BE\u0987",
+  "\u09A4\u09CB",
+  "\u09A5\u09BE\u0995\u09BE",
+  "\u09A5\u09C7\u0995\u09C7",
+  "\u09A6\u09BF\u09A8",
+  "\u09A6\u09C1",
+  "\u09A6\u09C1\u0987",
+  "\u09A6\u09C7\u0993\u09AF\u09BC\u09BE",
+  "\u09A7\u09BE\u09AE\u09BE\u09B0",
+  "\u09A8\u09A4\u09C1\u09A8",
+  "\u09A8\u09AF\u09BC",
+  "\u09A8\u09BE",
+  "\u09A8\u09BE\u0997\u09BE\u09A6",
+  "\u09A8\u09BF\u09AF\u09BC\u09C7",
+  "\u09A8\u09C7\u0993\u09AF\u09BC\u09BE",
+  "\u09AA\u09B0",
+  "\u09AA\u09B0\u09C7",
+  "\u09AA\u09BE\u099A",
+  "\u09AA\u09BF",
+  "\u09AA\u09C7\u09AF\u09BC\u09CD\u09B0\u09CD",
+  "\u09AA\u09CD\u09B0\u09A4\u09BF",
+  "\u09AA\u09CD\u09B0\u09A5\u09AE",
+  "\u09AA\u09CD\u09B0\u09AF\u09A8\u09CD\u09A4",
+  "\u09AA\u09CD\u09B0\u09BE\u09A5\u09AE\u09BF\u0995",
+  "\u09AA\u09CD\u09B0\u09BE\u09AF\u09BC",
+  "\u09AC\u0995\u09CD\u09A4\u09AC\u09CD\u09AF",
+  "\u09AC\u09A8",
+  "\u09AC\u09B2\u09BE",
+  "\u09AC\u09B2\u09C7",
+  "\u09AC\u09B2\u09C7\u09A8",
+  "\u09AC\u09B9\u09C1",
+  "\u09AC\u09BE",
+  "\u09AC\u09BF",
+  "\u09AC\u09BF\u09AD\u09BF\u09A8\u09CD\u09A8",
+  "\u09AC\u09C7\u09B6",
+  "\u09AC\u09C7\u09B6\u09BF",
+  "\u09AE\u09A4\u09CB",
+  "\u09AE\u09A7\u09CD\u09AF\u09C7",
+  "\u09AE\u09A8\u09C7",
+  "\u09AF\u0996\u09A8",
+  "\u09AF\u09A6\u09BF",
+  "\u09AF\u09BE",
+  "\u09AF\u09BE\u0993\u09AF\u09BC\u09BE",
+  "\u09AF\u09C7",
+  "\u09B0",
+  "\u09B0\u0995\u09AE",
+  "\u09B2\u0995\u09CD\u09B7",
+  "\u09B6\u09C1\u09A7\u09C1",
+  "\u09B6\u09C1\u09B0\u09C1",
+  "\u09B8\u0999\u09CD\u0997\u09C7",
+  "\u09B8\u09AC",
+  "\u09B8\u09B9",
+  "\u09B8\u09BE\u09A7\u09BE\u09B0\u09A3",
+  "\u09B8\u09BE\u09AE\u09A8\u09C7",
+  "\u09B8\u09BF",
+  "\u09B8\u09C7",
+  "\u09B8\u09C7\u0987",
+  "\u09B9\u09A4\u09C7",
+  "\u09B9\u09AF\u09BC",
+  "\u09B9\u09BE\u099C\u09BE\u09B0"
+]);
+var bengali = {
+  name: "bengali",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: { splitPattern: /[^\u0980-\u09ffa-z0-9]+/gi }
+};
+
+export { bengali };

package/dist/languages/bosnian.d.ts

@@ -0,0 +1,15 @@
+import { L as LanguageModule } from '../language-DB8KG1z5.js';
+
+/**
+ * Bosnian analysis: the stop word list and the rules that split Bosnian
+ * 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 `bosnian`.
+ *
+ * @public
+ */
+declare const bosnian: LanguageModule;
+
+export { bosnian };

package/dist/languages/bosnian.mjs

@@ -0,0 +1,197 @@
+// src/languages/bosnian.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "a",
+  "ako",
+  "ali",
+  "bi",
+  "bih",
+  "bila",
+  "bili",
+  "bilo",
+  "bio",
+  "bismo",
+  "biste",
+  "biti",
+  "bumo",
+  "\u0107e",
+  "\u0107emo",
+  "\u0107e\u0161",
+  "\u0107ete",
+  "\u0107u",
+  "da",
+  "do",
+  "du\u017E",
+  "ga",
+  "ho\u0107e",
+  "ho\u0107emo",
+  "ho\u0107e\u0161",
+  "ho\u0107ete",
+  "ho\u0107u",
+  "i",
+  "iako",
+  "ih",
+  "ili",
+  "iz",
+  "ja",
+  "je",
+  "jedna",
+  "jedne",
+  "jedno",
+  "jer",
+  "jesam",
+  "jesi",
+  "jesmo",
+  "jest",
+  "jeste",
+  "jesu",
+  "jim",
+  "joj",
+  "jo\u0161",
+  "ju",
+  "kada",
+  "kako",
+  "kao",
+  "ko",
+  "koja",
+  "koje",
+  "koji",
+  "kojima",
+  "koju",
+  "kroz",
+  "li",
+  "me",
+  "mene",
+  "meni",
+  "mi",
+  "mimo",
+  "moj",
+  "moja",
+  "moje",
+  "mu",
+  "na",
+  "nad",
+  "nakon",
+  "nam",
+  "nama",
+  "nas",
+  "na\u0161",
+  "na\u0161a",
+  "na\u0161e",
+  "na\u0161eg",
+  "ne",
+  "ne\u0107e",
+  "ne\u0107emo",
+  "ne\u0107e\u0161",
+  "ne\u0107ete",
+  "ne\u0107u",
+  "nego",
+  "neka",
+  "neki",
+  "neko",
+  "nekog",
+  "neku",
+  "nema",
+  "ne\u0161to",
+  "netko",
+  "ni",
+  "nije",
+  "niko",
+  "nikoga",
+  "nikoje",
+  "nikoju",
+  "nisam",
+  "nisi",
+  "nismo",
+  "niste",
+  "nisu",
+  "njega",
+  "njegov",
+  "njegova",
+  "njegovo",
+  "njemu",
+  "njezin",
+  "njezina",
+  "njezino",
+  "njih",
+  "njihov",
+  "njihova",
+  "njihovo",
+  "njim",
+  "njima",
+  "njoj",
+  "nju",
+  "no",
+  "o",
+  "od",
+  "odmah",
+  "on",
+  "ona",
+  "oni",
+  "ono",
+  "ova",
+  "pa",
+  "pak",
+  "po",
+  "pod",
+  "pored",
+  "prije",
+  "s",
+  "sa",
+  "sam",
+  "samo",
+  "se",
+  "sebe",
+  "sebi",
+  "si",
+  "smo",
+  "\u0161ta",
+  "ste",
+  "\u0161to",
+  "su",
+  "sve",
+  "svi",
+  "svog",
+  "svoj",
+  "svoja",
+  "svoje",
+  "svom",
+  "ta",
+  "tada",
+  "taj",
+  "tako",
+  "tako\u0111e",
+  "tako\u0111er",
+  "te",
+  "tebe",
+  "tebi",
+  "ti",
+  "to",
+  "toj",
+  "tome",
+  "tu",
+  "tvoj",
+  "tvoja",
+  "tvoje",
+  "u",
+  "uz",
+  "vam",
+  "vama",
+  "vas",
+  "va\u0161",
+  "va\u0161a",
+  "va\u0161e",
+  "ve\u0107",
+  "vi",
+  "vrlo",
+  "za",
+  "zar"
+]);
+var bosnian = {
+  name: "bosnian",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9čćđšž]+/gi }
+};
+
+export { bosnian };

package/dist/languages/breton.d.ts

@@ -0,0 +1,15 @@
+import { L as LanguageModule } from '../language-DB8KG1z5.js';
+
+/**
+ * Breton analysis: the stop word list and the rules that split Breton
+ * 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 `breton`.
+ *
+ * @public
+ */
+declare const breton: LanguageModule;
+
+export { breton };

package/dist/languages/breton.mjs

@@ -0,0 +1,96 @@
+// src/languages/breton.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "a",
+  "al",
+  "all",
+  "ama\xF1",
+  "an",
+  "ar",
+  "arall",
+  "atav",
+  "avat",
+  "aze",
+  "bet",
+  "betek",
+  "brema\xF1",
+  "c'hoazh",
+  "da",
+  "dindan",
+  "diouzh",
+  "diwar",
+  "dre",
+  "e",
+  "egile",
+  "en",
+  "e\xF1",
+  "eno",
+  "eo",
+  "er",
+  "etre",
+  "eus",
+  "evel",
+  "evit",
+  "ez",
+  "gant",
+  "goude",
+  "gwall",
+  "ha",
+  "hag",
+  "he",
+  "hep",
+  "hi",
+  "ho",
+  "hogen",
+  "holl",
+  "hon",
+  "hor",
+  "int",
+  "ivez",
+  "kaer",
+  "kel",
+  "kement",
+  "ken",
+  "kentre",
+  "ket",
+  "ma",
+  "mar",
+  "me",
+  "met",
+  "nag",
+  "ne",
+  "nemet",
+  "neuze",
+  "ni",
+  "o",
+  "oa",
+  "ouzh",
+  "pa",
+  "pe",
+  "pegoulz",
+  "penaos",
+  "pep",
+  "perak",
+  "petra",
+  "piv",
+  "rak",
+  "re",
+  "se",
+  "seul",
+  "te",
+  "tra",
+  "ul",
+  "un",
+  "ur",
+  "va",
+  "war",
+  "zo"
+]);
+var breton = {
+  name: "breton",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9êñù']+/gi }
+};
+
+export { breton };

package/dist/languages/bulgarian.d.ts

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

package/dist/languages/bulgarian.mjs

@@ -1,3 +1,6 @@
+import { removeMarks } from '../chunk-KH3YGMVT.mjs';
+import { withNormalisedSpellings } from '../chunk-GHJWC2E5.mjs';
+
 // src/languages/bulgarian.ts
 function stem(word) {
   let len = word.length;
@@ -320,11 +323,17 @@ var stopWords = /* @__PURE__ */ new Set([
   "\u044F",
   "\u044F\u043A"
 ]);
+var STRESS_MARK = /\u0300/g;
+function normalize(token) {
+  return removeMarks(token, STRESS_MARK);
+}
 var bulgarian = {
   name: "bulgarian",
+  revision: "1",
   stemmer: stem,
-  stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9а-яъ]+/gi }
+  stopWords: withNormalisedSpellings(stopWords, normalize),
+  normalizer: normalize,
+  tokenizer: { splitPattern: /[^a-z0-9а-яъѝЍ\p{M}]+/giu }
 };
 
 export { bulgarian };

package/dist/languages/burmese.d.ts

@@ -0,0 +1,15 @@
+import { L as LanguageModule } from '../language-DB8KG1z5.js';
+
+/**
+ * Burmese analysis: the stop word list and the rules that split Burmese
+ * 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 `burmese`.
+ *
+ * @public
+ */
+declare const burmese: LanguageModule;
+
+export { burmese };

package/dist/languages/burmese.mjs

@@ -0,0 +1,57 @@
+// src/languages/burmese.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "\u104D",
+  "\u104E\u1004\u103A\u1038",
+  "\u1044\u1004\u103A\u1038",
+  "\u1000\u103B\u1014\u1031\u102C\u103A",
+  "\u1000\u103B\u1019",
+  "\u1000\u103B\u102F\u1015\u103A",
+  "\u1000\u1032\u1037\u101E\u102D\u102F\u1037",
+  "\u1004\u102B",
+  "\u1004\u102B\u1000\u102D\u102F",
+  "\u1004\u102B\u1010\u102D\u102F\u1037",
+  "\u1010\u1032\u1037",
+  "\u1011\u102D\u102F",
+  "\u1011\u102D\u102F\u101F\u102C",
+  "\u1012\u102B",
+  "\u1012\u102E\u101F\u102C",
+  "\u1014\u103E\u1004\u1037\u103A",
+  "\u1015\u102B\u1000",
+  "\u1015\u1031\u1019\u1032\u1037",
+  "\u1018\u102C\u101C\u1032",
+  "\u1019\u1004\u103A\u1038",
+  "\u1019\u100A\u1037\u103A",
+  "\u101C\u103B\u103E\u1004\u103A",
+  "\u101C\u102F\u1036\u1038\u101C\u102F\u1036\u1038",
+  "\u101E\u1004\u103A",
+  "\u101E\u100A\u1037\u103A",
+  "\u101E\u1030",
+  "\u101E\u1030\u104F",
+  "\u101E\u1030\u1037\u1000\u102D\u102F",
+  "\u101E\u1030\u1010\u102D\u102F\u1037",
+  "\u101E\u1030\u1019",
+  "\u101E\u1030\u101F\u102C",
+  "\u101E\u1030\u1037\u101F\u102C",
+  "\u101F\u102D\u102F\u101F\u102C",
+  "\u101F\u1031\u102C\u1012\u102B",
+  "\u101F\u1031\u102C\u1012\u102E",
+  "\u1021\u1001\u103B\u102D\u102F\u1037",
+  "\u1021\u1015\u1031\u102B\u103A",
+  "\u1021\u102C\u1038\u101C\u102F\u1036\u1038",
+  "\u1021\u1032\u1012\u102B",
+  "\u1024\u1019\u103B\u103E"
+]);
+var burmese = {
+  name: "burmese",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: {
+    splitPattern: /[^က-၉၌-႟a-z0-9]+/giu,
+    normalizeDiacritics: false,
+    minTokenLength: 1,
+    ngramSize: 2
+  }
+};
+
+export { burmese };